for sizeopt in whole trunc ; do
echo "### creating {raw,gud,bad}.tlw files from ${sizeopt}.tlw ###"
for smp in ${smps[@]} ; do
echo " "
get-sample-raw-gud-bad-files.sh ${smp} ${sizeopt}
done
summarize-counts.sh ${sizeopt} ${smps[@]}
done
*** output flushed ***
for sizeopt in whole trunc ; do
echo "### creating {raw,gud,bad}.tlw files from ${sizeopt}.tlw ###"
for smp in ${smps[@]} ; do
echo " "
get-sample-raw-gud-bad-files.sh ${smp} ${sizeopt}
done
summarize-counts.sh ${sizeopt} ${smps[@]}
done
*** output flushed ***
for sizeopt in whole trunc ; do
echo "### creating {raw,gud,bad}.tlw files from ${sizeopt}.tlw ###"
for smp in ${smps[@]} ; do
echo " "
get-sample-raw-gud-bad-files.sh ${smp} ${sizeopt}
echo " "
done
summarize-counts.sh ${sizeopt} ${smps[@]}
done
### creating {raw,gud,bad}.tlw files from whole.tlw ###
=== creating the derived word files dat/hebr/tav/*/{raw,gud,bad}.{tlw,wdf,wfr} (whole) ===
... creating word files dat/hebr/tav/gen.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
18744 dat/hebr/tav/gen.1/whole.tlw
removed 'dat/hebr/tav/gen.1/raw.tlw'
removed 'dat/hebr/tav/gen.1/gud.tlw'
removed 'dat/hebr/tav/gen.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/hebr/tav/gen.1/raw.wdf
sample:
bĪ°rëĄsđïyą bĪâr⥠Ą°ęlöhïym Ąëą häsĪđâmäyïm w°Ąëą hâĄâręþ =
w°hâĄâręþ hây°ąâh ąöhwĪ wâböhwĪ w°įösđęk° ŋälpĪ°nëy ą°hwöm w°rwĪįä
Ą°ęlöhïym m°räįępęą ŋälpĪ°nëy hämĪâyïm =
wäyĪöĄmęr Ą°ęlöhïym y°hïy Ąwör wäy°hïyĄwör =
wäyĪär°Ą Ą°ęlöhïym ĄęąhâĄwör kĪïytwöb wäyĪäb°dĪël Ą°ęlöhïym bĪëyn hâĄwör
wĪbëyn häįösđęk° =
wäyĪïq°r⥠Ą°ęlöhïym lâĄwör ywöm w°läįösđęk° qâr⥠lây°lâh wäy°hïyŋęręb
wäy°hïyböqęr ywöm Ąęįâd =
wäyĪöĄmęr Ą°ęlöhïym y°hïy râqïyŋä bĪ°ąwök° hämĪâyïm wïyhïy mäb°dĪïyl
bĪëyn mäyïm lâmâyïm =
wäyĪäŋäsē Ą°ęlöhïym Ąęąhârâqïyŋä wäyĪäb°dĪël bĪëyn hämĪäyïm Ą°äsđęr
mïąĪäįäą lârâqïyŋä wĪbëyn hämĪäyïm Ą°äsđęr mëŋäl lârâqïyŋä wäy°hïykën =
wäyĪïq°r⥠Ą°ęlöhïym lârâqïyŋä sđâmâyïm wäy°hïyŋęręb wäy°hïyböqęr ywöm
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
wäyĪâmâą ywösëp bĪęnmëĄâh wâŋęsēęr sđânïym wäyĪäįän°twĪ Ąöąwö wäyĪïysēęm
bĪâĄârwön bĪ°mïþ°râyïm =
removed 'dat/hebr/tav/gen.1/raw.wfr'
creating the word frequency file dat/hebr/tav/gen.1/raw.wfr
the 10 most common words in dat/hebr/tav/gen.1/raw.tlw:
1533 0.08179 =
318 0.01697 wäyĪöĄmęr
226 0.01206 Ą°äsđęr
149 0.00795 Ą°ęlöhïym
145 0.00774 kĪïy
129 0.00688 y°hwâh
109 0.00582 yäŋ°äqöb
103 0.00550 ywösëp
101 0.00539 sđânâh
93 0.00496 wäy°hïy
removed 'dat/hebr/tav/gen.1/raw-whole-wds-summary.tex'
removed 'exp/hebr/tav/gen.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/hebr/tav/gen.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:30:41 by tex-make-sample-summary.sh
% Token and word counts for hebr/tav/gen.1/raw.wfr
%
\def\hebrtavwholegenPBrawTks{18744}
\def\hebrtavwholegenPBrawTksPct{100.0}
\def\hebrtavwholegenPBrawWds{7213}
\def\hebrtavwholegenPBrawWdsPct{38.5}
copied '/tmp/559967.file' -> 'exp/hebr/tav/gen.1/raw-whole-wds-summary.tex'
removed '/tmp/559967.file'
creating running text file dat/hebr/tav/gen.1/gud.wdf
sample:
bĪ°rëĄsđïyą bĪâr⥠Ą°ęlöhïym Ąëą häsĪđâmäyïm w°Ąëą hâĄâręþ w°hâĄâręþ
hây°ąâh ąöhwĪ wâböhwĪ w°įösđęk° ŋälpĪ°nëy ą°hwöm w°rwĪįä Ą°ęlöhïym
m°räįępęą ŋälpĪ°nëy hämĪâyïm wäyĪöĄmęr Ą°ęlöhïym y°hïy Ąwör wäy°hïyĄwör
wäyĪär°Ą Ą°ęlöhïym ĄęąhâĄwör kĪïytwöb wäyĪäb°dĪël Ą°ęlöhïym bĪëyn hâĄwör
wĪbëyn häįösđęk° wäyĪïq°r⥠Ą°ęlöhïym lâĄwör ywöm w°läįösđęk° qârâĄ
lây°lâh wäy°hïyŋęręb wäy°hïyböqęr ywöm Ąęįâd wäyĪöĄmęr Ą°ęlöhïym y°hïy
râqïyŋä bĪ°ąwök° hämĪâyïm wïyhïy mäb°dĪïyl bĪëyn mäyïm lâmâyïm wäyĪäŋäsē
Ą°ęlöhïym Ąęąhârâqïyŋä wäyĪäb°dĪël bĪëyn hämĪäyïm Ą°äsđęr mïąĪäįäą
lârâqïyŋä wĪbëyn hämĪäyïm Ą°äsđęr mëŋäl lârâqïyŋä wäy°hïykën wäyĪïq°râĄ
Ą°ęlöhïym lârâqïyŋä sđâmâyïm wäy°hïyŋęręb wäy°hïyböqęr ywöm sđënïy
wäyĪöĄmęr Ą°ęlöhïym yïqĪâwwĪ hämĪäyïm mïąĪäįäą häsĪđâmäyïm Ąęlmâqwöm
Ąęįâd w°ąërâĄęh häyĪäbĪâsđâh wäy°hïykën wäyĪïq°r⥠Ą°ęlöhïym
läyĪäbĪâsđâh Ąęręþ wĪl°mïq°wëh hämĪäyïm qâr⥠yämĪïym wäyĪär°Ą Ą°ęlöhïym
kĪïytwöb wäyĪöĄmęr Ą°ęlöhïym ąĪäd°sđëĄ hâĄâręþ dĪęsđęĄ ŋësēęb mäz°rïyŋä
zęräŋ ŋëþ pĪ°rïy ŋösēęh pĪ°rïy l°mïynwö Ą°äsđęr zär°ŋwöbwö ŋälhâĄâręþ
wäy°hïykën wäąĪwöþëĄ hâĄâręþ dĪęsđęĄ ŋësēęb mäz°rïyŋä zęräŋ l°mïynëhwĪ
w°ŋëþ ŋösēęhpĪ°rïy Ą°äsđęr zär°ŋwöbwö l°mïynëhwĪ wäyĪär°Ą Ą°ęlöhïym
kĪïytwöb wäy°hïyŋęręb wäy°hïyböqęr ywöm sđ°lïysđïy wäyĪöĄmęr Ą°ęlöhïym
y°hïy m°Ąöröą bĪïr°qïyŋä häsĪđâmäyïm l°häb°dĪïyl bĪëyn häyĪwöm wĪbëyn
hälĪây°lâh w°hâywĪ l°Ąöąöą wĪl°mwöŋ°ädïym wĪl°yâmïym w°sđânïym w°hâywĪ
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
yïsē°râĄël lëĄmör pĪâqöd yïp°qöd Ą°ęlöhïym Ąęą°kęm w°häŋ°älïąęm
Ąęąŋäþ°möąäy mïzĪęh wäyĪâmâą ywösëp bĪęnmëĄâh wâŋęsēęr sđânïym
wäyĪäįän°twĪ Ąöąwö wäyĪïysēęm bĪâĄârwön bĪ°mïþ°râyïm
removed 'dat/hebr/tav/gen.1/gud.wfr'
creating the word frequency file dat/hebr/tav/gen.1/gud.wfr
the 10 most common words in dat/hebr/tav/gen.1/gud.tlw:
318 0.01848 wäyĪöĄmęr
226 0.01313 Ą°äsđęr
149 0.00866 Ą°ęlöhïym
145 0.00842 kĪïy
129 0.00750 y°hwâh
109 0.00633 yäŋ°äqöb
103 0.00598 ywösëp
101 0.00587 sđânâh
93 0.00540 wäy°hïy
87 0.00505 Ąäb°râhâm
removed 'dat/hebr/tav/gen.1/gud-whole-wds-summary.tex'
removed 'exp/hebr/tav/gen.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/hebr/tav/gen.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:30:41 by tex-make-sample-summary.sh
% Token and word counts for hebr/tav/gen.1/gud.wfr
%
\def\hebrtavwholegenPBgudTks{17211}
\def\hebrtavwholegenPBgudTksPct{91.8}
\def\hebrtavwholegenPBgudWds{7212}
\def\hebrtavwholegenPBgudWdsPct{38.5}
copied '/tmp/560014.file' -> 'exp/hebr/tav/gen.1/gud-whole-wds-summary.tex'
removed '/tmp/560014.file'
creating running text file dat/hebr/tav/gen.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/hebr/tav/gen.1/bad.wfr'
creating the word frequency file dat/hebr/tav/gen.1/bad.wfr
the 10 most common words in dat/hebr/tav/gen.1/bad.tlw:
1533 1.00000 =
removed 'dat/hebr/tav/gen.1/bad-whole-wds-summary.tex'
removed 'exp/hebr/tav/gen.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/hebr/tav/gen.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:30:41 by tex-make-sample-summary.sh
% Token and word counts for hebr/tav/gen.1/bad.wfr
%
\def\hebrtavwholegenPBbadTks{1533}
\def\hebrtavwholegenPBbadTksPct{8.2}
\def\hebrtavwholegenPBbadWds{1}
\def\hebrtavwholegenPBbadWdsPct{0.0}
copied '/tmp/560058.file' -> 'exp/hebr/tav/gen.1/bad-whole-wds-summary.tex'
removed '/tmp/560058.file'
... creating word files dat/hebr/tav/exo.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
15079 dat/hebr/tav/exo.1/whole.tlw
removed 'dat/hebr/tav/exo.1/raw.tlw'
removed 'dat/hebr/tav/exo.1/gud.tlw'
removed 'dat/hebr/tav/exo.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/hebr/tav/exo.1/raw.wdf
sample:
w°ĄëlĪęh sđ°mwöą bĪ°nëy yïsē°râĄël häbĪâĄïym mïþ°rây°mâh Ąëą yäŋ°äqöb
Ąïysđ wĪbëyąwö bĪâĄwĪ =
r°ĄwĪbën sđïm°ŋwön lëwïy wïyhwĪdâh =
yïsĪēâskâr z°bwĪlün wĪbïn°yâmïn =
dĪân w°näp°ąĪâlïy gĪâd w°Ąâsđër =
wäy°hïy kĪâlnępęsđ yöþ°Ąëy yęręk°yäŋ°äqöbsđïb°ŋïym nâpęsđ w°ywösëp hâyâh
b°mïþ°râyïm =
wäyĪâmâą ywösëp w°kâlĄęįâyw w°köl hädĪwör hähwĪĄ =
wĪb°nëy yïsē°râĄël pĪârwĪ wäyĪïsđ°r°þwĪ wäyĪïr°bĪwĪ wäyĪäŋäþ°mwĪbĪïm°Ąöd
m°Ąöd wäąĪïmĪâlëĄ hâĄâręþ Ąöąâm =
wäyĪâqâm męlęk°įâdâsđ ŋälmïþ°râyïm Ą°äsđęr löĄyâdäŋ Ąęąywösëp =
wäyĪöĄmęr ĄęlŋämĪwö hïnĪëh ŋäm bĪ°nëy yïsē°râĄëlräb w°ŋâþwĪm mïmĪęnĪwĪ =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
kĪïy ŋ°änän y°hwâh ŋälhämĪïsđ°kĪân ywömâm w°Ąësđ ąĪïh°yęh läy°lâh
bĪwöl°ŋëynëy kâlbĪëyąyïsē°râĄël bĪ°kâlmäs°ŋëyhęm =
removed 'dat/hebr/tav/exo.1/raw.wfr'
creating the word frequency file dat/hebr/tav/exo.1/raw.wfr
the 10 most common words in dat/hebr/tav/exo.1/raw.tlw:
1209 0.08018 =
286 0.01897 y°hwâh
172 0.01141 Ą°äsđęr
151 0.01001 mösđęh
147 0.00975 wäyĪöĄmęr
102 0.00676 yïsē°râĄël
100 0.00663 kĪïy
86 0.00570 zâhâb
82 0.00544 löĄ
76 0.00504 Ąęlmösđęh
removed 'dat/hebr/tav/exo.1/raw-whole-wds-summary.tex'
removed 'exp/hebr/tav/exo.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/hebr/tav/exo.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:30:41 by tex-make-sample-summary.sh
% Token and word counts for hebr/tav/exo.1/raw.wfr
%
\def\hebrtavwholeexoPBrawTks{15079}
\def\hebrtavwholeexoPBrawTksPct{100.0}
\def\hebrtavwholeexoPBrawWds{5712}
\def\hebrtavwholeexoPBrawWdsPct{37.9}
copied '/tmp/560112.file' -> 'exp/hebr/tav/exo.1/raw-whole-wds-summary.tex'
removed '/tmp/560112.file'
creating running text file dat/hebr/tav/exo.1/gud.wdf
sample:
w°ĄëlĪęh sđ°mwöą bĪ°nëy yïsē°râĄël häbĪâĄïym mïþ°rây°mâh Ąëą yäŋ°äqöb
Ąïysđ wĪbëyąwö bĪâĄwĪ r°ĄwĪbën sđïm°ŋwön lëwïy wïyhwĪdâh yïsĪēâskâr
z°bwĪlün wĪbïn°yâmïn dĪân w°näp°ąĪâlïy gĪâd w°Ąâsđër wäy°hïy kĪâlnępęsđ
yöþ°Ąëy yęręk°yäŋ°äqöbsđïb°ŋïym nâpęsđ w°ywösëp hâyâh b°mïþ°râyïm
wäyĪâmâą ywösëp w°kâlĄęįâyw w°köl hädĪwör hähwĪĄ wĪb°nëy yïsē°râĄël
pĪârwĪ wäyĪïsđ°r°þwĪ wäyĪïr°bĪwĪ wäyĪäŋäþ°mwĪbĪïm°Ąöd m°Ąöd wäąĪïmĪâlëĄ
hâĄâręþ Ąöąâm wäyĪâqâm męlęk°įâdâsđ ŋälmïþ°râyïm Ą°äsđęr löĄyâdäŋ
Ąęąywösëp wäyĪöĄmęr ĄęlŋämĪwö hïnĪëh ŋäm bĪ°nëy yïsē°râĄëlräb w°ŋâþwĪm
mïmĪęnĪwĪ hâbâh nïą°įäkĪ°mâh lwö pĪęnyïr°bĪęh w°hâyâh kĪïyąïq°ręĄnâh
mïl°įâmâh w°nwösäp gĪämhwĪĄ ŋälsēön°ĄëynwĪ w°nïl°įämbĪânwĪ w°ŋâlâh
mïnhâĄâręþ wäyĪâsēïymwĪ ŋâlâyw sēârëy mïsĪïym l°mäŋän ŋänĪöąwö
bĪ°sïb°löąâm wäyĪïbęn ŋârëy mïs°kĪ°nwöą l°pär°ŋöhĄęąpĪïąöm
w°Ąęąräŋäm°sës w°k䥰äsđęr y°ŋänĪwĪ Ąöąwö kĪën yïr°bĪęh w°kën yïp°röþ
wäyĪâqüþwĪ mïpĪ°nëy bĪ°nëy yïsē°râĄël wäyĪäŋ°äbïdwĪ mïþ°räyïm ĄęąbĪ°nëy
yïsē°râĄël bĪ°pâręk° wäy°mâr°rwĪ ĄęąįäyĪëyhęm bĪäŋ°äbödâh qâsđâh
bĪ°įömęr wĪbïl°bënïym wĪb°kâlŋ°äbödâh bĪäsĪēâdęhĄëą kĪâlŋ°äbödâąâm
Ą°äsđęrŋâb°dwĪ bâhęm bĪ°pâręk° wäyĪöĄmęr męlęk° mïþ°räyïm läm°yälĪ°döą
hâŋïb°rïyĪöą Ą°äsđęr sđëm hâĄäįäą sđïp°râh w°sđëm häsĪđënïyą pĪwĪŋâh
wäyĪöĄmęr bĪ°yälĪęd°kęn Ąęąhâŋïb°rïyĪwöą wĪr°Ąïyąęn ŋälhâĄâb°nâyïm
ĄïmbĪën hwĪĄ wäh°ämïąĪęn Ąöąwö w°ĄïmbĪäą hïwĄ wâįâyâh wäąĪïyręĄnâ
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
mäs°ŋëyhęm w°ĄïmlöĄ yëŋâlęh hęŋânânw°löĄ yïs°ŋwĪ ŋädywöm hëŋâlöąwö kĪïy
ŋ°änän y°hwâh ŋälhämĪïsđ°kĪân ywömâm w°Ąësđ ąĪïh°yęh läy°lâh
bĪwöl°ŋëynëy kâlbĪëyąyïsē°râĄël bĪ°kâlmäs°ŋëyhęm
removed 'dat/hebr/tav/exo.1/gud.wfr'
creating the word frequency file dat/hebr/tav/exo.1/gud.wfr
the 10 most common words in dat/hebr/tav/exo.1/gud.tlw:
286 0.02062 y°hwâh
172 0.01240 Ą°äsđęr
151 0.01089 mösđęh
147 0.01060 wäyĪöĄmęr
102 0.00735 yïsē°râĄël
100 0.00721 kĪïy
86 0.00620 zâhâb
82 0.00591 löĄ
76 0.00548 Ąęlmösđęh
57 0.00411 mïþ°räyïm
removed 'dat/hebr/tav/exo.1/gud-whole-wds-summary.tex'
removed 'exp/hebr/tav/exo.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/hebr/tav/exo.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:30:41 by tex-make-sample-summary.sh
% Token and word counts for hebr/tav/exo.1/gud.wfr
%
\def\hebrtavwholeexoPBgudTks{13870}
\def\hebrtavwholeexoPBgudTksPct{92.0}
\def\hebrtavwholeexoPBgudWds{5711}
\def\hebrtavwholeexoPBgudWdsPct{37.9}
copied '/tmp/560156.file' -> 'exp/hebr/tav/exo.1/gud-whole-wds-summary.tex'
removed '/tmp/560156.file'
creating running text file dat/hebr/tav/exo.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/hebr/tav/exo.1/bad.wfr'
creating the word frequency file dat/hebr/tav/exo.1/bad.wfr
the 10 most common words in dat/hebr/tav/exo.1/bad.tlw:
1209 1.00000 =
removed 'dat/hebr/tav/exo.1/bad-whole-wds-summary.tex'
removed 'exp/hebr/tav/exo.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/hebr/tav/exo.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:30:41 by tex-make-sample-summary.sh
% Token and word counts for hebr/tav/exo.1/bad.wfr
%
\def\hebrtavwholeexoPBbadTks{1209}
\def\hebrtavwholeexoPBbadTksPct{8.0}
\def\hebrtavwholeexoPBbadWds{1}
\def\hebrtavwholeexoPBbadWdsPct{0.0}
copied '/tmp/560200.file' -> 'exp/hebr/tav/exo.1/bad-whole-wds-summary.tex'
removed '/tmp/560200.file'
... creating word files dat/hebr/tav/num.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
14862 dat/hebr/tav/num.1/whole.tlw
removed 'dat/hebr/tav/num.1/raw.tlw'
removed 'dat/hebr/tav/num.1/gud.tlw'
removed 'dat/hebr/tav/num.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/hebr/tav/num.1/raw.wdf
sample:
wäy°däbĪër y°hwâh Ąęlmösđęh bĪ°mïd°bĪär sïynäy bĪ°Ąöhęl mwöŋëd bĪ°Ąęįâd
läįödęsđ häsĪđënïy bĪäsĪđânâh häsĪđënïyą l°þ륹âm mëĄęręþ
mïþ°räyïmlëĄmör =
sē°ĄwĪ ĄęąröĄsđ kĪâlŋ°ädäą bĪ°nëyyïsē°râĄël l°mïsđ°pĪ°įöąâm l°bëyą
Ą°äböąâmbĪ°mïs°pĪär sđëmwöą kĪâlzâkâr l°gül°gĪ°löąâm =
mïbĪęn ŋęsē°rïym sđânâh wâmäŋ°lâh kĪâlyöþëĄ þâbâĄ
bĪ°yïsē°râĄëląĪïp°q°dwĪ Ąöąâm l°þïb°Ąöąâm ĄäąĪâh w°Ąäh°ärön =
w°ĄïąĪ°kęm yïh°ywĪ Ąïysđ Ąïysđ lämĪätĪęhĄïysđ röĄsđ l°bëyąĄ°äböąâyw hwĪĄ
=
w°ĄëlĪęh sđ°mwöą h⥰änâsđïym Ą°äsđęr yäŋäm°dwĪ ĄïąĪ°kęm lïr°ĄwĪbën
Ą°ęlïyþwĪr bĪęnsđ°dëyĄwĪr =
l°sđïm°ŋwön sđ°lümïyĄël bĪęnþwĪrïysđädĪây =
lïyhwĪdâh näį°sđwön bĪęnŋämĪïynâdâb =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
bĪ°yädmösđęhĄęlbĪ°nëy yïsē°râĄël bĪ°ŋär°böą mwöĄâb ŋäl yär°dĪën y°rëįwö
=
removed 'dat/hebr/tav/num.1/raw.wfr'
creating the word frequency file dat/hebr/tav/num.1/raw.wfr
the 10 most common words in dat/hebr/tav/num.1/raw.tlw:
1289 0.08673 =
286 0.01924 y°hwâh
153 0.01029 Ą°äsđęr
149 0.01003 yïsē°râĄël
111 0.00747 bĪ°nëy
102 0.00686 mösđęh
97 0.00653 Ąęįâd
84 0.00565 wäyĪöĄmęr
78 0.00525 Ąęlmösđęh
65 0.00437 löĄ
removed 'dat/hebr/tav/num.1/raw-whole-wds-summary.tex'
removed 'exp/hebr/tav/num.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/hebr/tav/num.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:30:41 by tex-make-sample-summary.sh
% Token and word counts for hebr/tav/num.1/raw.wfr
%
\def\hebrtavwholenumPBrawTks{14862}
\def\hebrtavwholenumPBrawTksPct{100.0}
\def\hebrtavwholenumPBrawWds{5307}
\def\hebrtavwholenumPBrawWdsPct{35.7}
copied '/tmp/560254.file' -> 'exp/hebr/tav/num.1/raw-whole-wds-summary.tex'
removed '/tmp/560254.file'
creating running text file dat/hebr/tav/num.1/gud.wdf
sample:
wäy°däbĪër y°hwâh Ąęlmösđęh bĪ°mïd°bĪär sïynäy bĪ°Ąöhęl mwöŋëd bĪ°Ąęįâd
läįödęsđ häsĪđënïy bĪäsĪđânâh häsĪđënïyą l°þ륹âm mëĄęręþ
mïþ°räyïmlëĄmör sē°ĄwĪ ĄęąröĄsđ kĪâlŋ°ädäą bĪ°nëyyïsē°râĄël
l°mïsđ°pĪ°įöąâm l°bëyą Ą°äböąâmbĪ°mïs°pĪär sđëmwöą kĪâlzâkâr
l°gül°gĪ°löąâm mïbĪęn ŋęsē°rïym sđânâh wâmäŋ°lâh kĪâlyöþëĄ þâbâĄ
bĪ°yïsē°râĄëląĪïp°q°dwĪ Ąöąâm l°þïb°Ąöąâm ĄäąĪâh w°Ąäh°ärön w°ĄïąĪ°kęm
yïh°ywĪ Ąïysđ Ąïysđ lämĪätĪęhĄïysđ röĄsđ l°bëyąĄ°äböąâyw hwĪĄ w°ĄëlĪęh
sđ°mwöą h⥰änâsđïym Ą°äsđęr yäŋäm°dwĪ ĄïąĪ°kęm lïr°ĄwĪbën Ą°ęlïyþwĪr
bĪęnsđ°dëyĄwĪr l°sđïm°ŋwön sđ°lümïyĄël bĪęnþwĪrïysđädĪây lïyhwĪdâh
näį°sđwön bĪęnŋämĪïynâdâb l°yïsĪēâskâr n°ąän°Ąël bĪęnþwĪŋâr lïz°bwĪlün
Ą°ęlïyĄâb bĪęnįëlön lïb°nëy ywösëpl°Ąęp°räyïm Ą°ęlïysđâmâŋ
bĪęnŋämĪïyhwĪd lïm°näsĪđęh gĪäm°lïyĄël bĪęnpĪ°dâhþwĪr l°bïn°yâmïn
Ą°äbïydân bĪęngĪïd°ŋönïy l°dân Ą°äįïyŋęzęr bĪęnŋämĪïysđädĪây l°Ąâsđër
pĪäg°ŋïyĄël bĪęnŋâk°rân l°gâd Ąęl°yâsâp bĪęndĪ°ŋwĪĄël l°näp°ąĪâlïy
Ą°äįïyräŋ bĪęnŋëynân ĄëlĪęh qryĄy q°rwĪĄëy hâŋëdâh n°sēïyĄëy mätĪwöą
Ą°äbwöąâm râĄsđëy Ąäl°pëy yïsē°râĄël hëm wäyĪïqĪäį mösđęh w°Ąäh°ärön Ąëą
h⥰änâsđïym hâĄëlĪęh Ą°äsđęr nïqĪ°bwĪ bĪ°sđëmöą w°Ąëą kĪâlhâŋëdâh
hïq°hïylwĪ bĪ°Ąęįâd läįödęsđ häsĪđënïy wäyĪïą°yäl°dwĪ ŋälmïsđ°pĪ°įöąâm
l°bëyą Ą°äböąâm bĪ°mïs°pĪär sđëmwöą mïbĪęn ŋęsē°rïym sđânâh
wâmäŋ°lâhl°gül°gĪ°löąâm kĪ䥰äsđęr þïwĪâh y°hwâh Ąęąmösđęh wäyĪïp°q°dëm
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
wäąĪ°hïy näį°älâąân ŋälmätĪëh mïsđ°pĪäįäą Ą°äbïyhęn ĄëlĪęh hämĪïþ°wöą
w°hämĪïsđ°pĪâtïym Ą°äsđęr þïwĪâh y°hwâh bĪ°yädmösđęhĄęlbĪ°nëy yïsē°râĄël
bĪ°ŋär°böą mwöĄâb ŋäl yär°dĪën y°rëįwö
removed 'dat/hebr/tav/num.1/gud.wfr'
creating the word frequency file dat/hebr/tav/num.1/gud.wfr
the 10 most common words in dat/hebr/tav/num.1/gud.tlw:
286 0.02107 y°hwâh
153 0.01127 Ą°äsđęr
149 0.01098 yïsē°râĄël
111 0.00818 bĪ°nëy
102 0.00751 mösđęh
97 0.00715 Ąęįâd
84 0.00619 wäyĪöĄmęr
78 0.00575 Ąęlmösđęh
65 0.00479 löĄ
64 0.00472 kĪïy
removed 'dat/hebr/tav/num.1/gud-whole-wds-summary.tex'
removed 'exp/hebr/tav/num.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/hebr/tav/num.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:30:42 by tex-make-sample-summary.sh
% Token and word counts for hebr/tav/num.1/gud.wfr
%
\def\hebrtavwholenumPBgudTks{13573}
\def\hebrtavwholenumPBgudTksPct{91.3}
\def\hebrtavwholenumPBgudWds{5306}
\def\hebrtavwholenumPBgudWdsPct{35.7}
copied '/tmp/560298.file' -> 'exp/hebr/tav/num.1/gud-whole-wds-summary.tex'
removed '/tmp/560298.file'
creating running text file dat/hebr/tav/num.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/hebr/tav/num.1/bad.wfr'
creating the word frequency file dat/hebr/tav/num.1/bad.wfr
the 10 most common words in dat/hebr/tav/num.1/bad.tlw:
1289 1.00000 =
removed 'dat/hebr/tav/num.1/bad-whole-wds-summary.tex'
removed 'exp/hebr/tav/num.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/hebr/tav/num.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:30:42 by tex-make-sample-summary.sh
% Token and word counts for hebr/tav/num.1/bad.wfr
%
\def\hebrtavwholenumPBbadTks{1289}
\def\hebrtavwholenumPBbadTksPct{8.7}
\def\hebrtavwholenumPBbadWds{1}
\def\hebrtavwholenumPBbadWdsPct{0.0}
copied '/tmp/560342.file' -> 'exp/hebr/tav/num.1/bad-whole-wds-summary.tex'
removed '/tmp/560342.file'
... creating word files dat/hebr/tav/lev.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
10509 dat/hebr/tav/lev.1/whole.tlw
removed 'dat/hebr/tav/lev.1/raw.tlw'
removed 'dat/hebr/tav/lev.1/gud.tlw'
removed 'dat/hebr/tav/lev.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/hebr/tav/lev.1/raw.wdf
sample:
wäyĪïq°râ Ąęlmösđęh wäy°däbĪër y°hwâh Ąëlâyw mëĄöhęl mwöŋëd lëĄmör =
dĪäbĪër ĄęlbĪ°nëy yïsē°râĄël w°Ąâmär°ąĪâ Ą°älëhęm Ąâdâm kĪïyyäq°rïyb
mïkĪęm qâr°bĪân läyhwâhmïnhäbĪ°hëmâh mïnhäbĪâqâr wĪmïnhäþĪöĄn
ąĪäq°rïybwĪ Ąęąqâr°bĪän°kęm =
Ąïmŋölâh qâr°bĪânwö mïnhäbĪâqâr zâkâr ąĪâmïym yäq°rïybęnĪwĪ ĄęlpĪęąäį
Ąöhęl mwöŋëd yäq°rïyb Ąöąwö lïr°þönwö lïp°nëy y°hwâh =
w°sâmäk° yâdwö ŋäl röĄsđ hâŋölâh w°nïr°þâh lwö l°käpĪër ŋâlâyw =
w°sđâįät ĄęąbĪęn häbĪâqâr lïp°nëy y°hwâh w°hïq°rïybwĪ bĪ°nëy Ąäh°ärön
häkĪöh°änïym ĄęąhädĪâm w°zâr°qwĪ ĄęąhädĪâm ŋälhämĪïz°bĪëįä sâbïyb
Ą°äsđęrpĪęąäį Ąöhęl mwöŋëd =
w°hïp°sđïyt Ąęąhâŋölâh w°nïąĪäį ĄöąâhĪ lïn°ąâįęyhâ =
w°nâą°nwĪ bĪ°nëy Ąäh°ärön häkĪöhën ĄësđŋälhämĪïz°bĪëįä w°ŋâr°kwĪ ŋëþïym
ŋälhâĄësđ =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
ĄëlĪęh hämĪïþ°wöą Ą°äsđęr þïwĪâh y°hwâh ĄęąmösđęhĄęlbĪ°nëy yïsē°râĄël
bĪ°här sïynây =
removed 'dat/hebr/tav/lev.1/raw.wfr'
creating the word frequency file dat/hebr/tav/lev.1/raw.wfr
the 10 most common words in dat/hebr/tav/lev.1/raw.tlw:
859 0.08174 =
198 0.01884 y°hwâh
184 0.01751 Ą°äsđęr
142 0.01351 häkĪöhën
124 0.01180 löĄ
99 0.00942 Ąwö
74 0.00704 läyhwâh
73 0.00695 hwĪĄ
65 0.00619 kĪïy
63 0.00599 lïp°nëy
removed 'dat/hebr/tav/lev.1/raw-whole-wds-summary.tex'
removed 'exp/hebr/tav/lev.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/hebr/tav/lev.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:30:42 by tex-make-sample-summary.sh
% Token and word counts for hebr/tav/lev.1/raw.wfr
%
\def\hebrtavwholelevPBrawTks{10509}
\def\hebrtavwholelevPBrawTksPct{100.0}
\def\hebrtavwholelevPBrawWds{3861}
\def\hebrtavwholelevPBrawWdsPct{36.7}
copied '/tmp/560396.file' -> 'exp/hebr/tav/lev.1/raw-whole-wds-summary.tex'
removed '/tmp/560396.file'
creating running text file dat/hebr/tav/lev.1/gud.wdf
sample:
wäyĪïq°râ Ąęlmösđęh wäy°däbĪër y°hwâh Ąëlâyw mëĄöhęl mwöŋëd lëĄmör
dĪäbĪër ĄęlbĪ°nëy yïsē°râĄël w°Ąâmär°ąĪâ Ą°älëhęm Ąâdâm kĪïyyäq°rïyb
mïkĪęm qâr°bĪân läyhwâhmïnhäbĪ°hëmâh mïnhäbĪâqâr wĪmïnhäþĪöĄn
ąĪäq°rïybwĪ Ąęąqâr°bĪän°kęm Ąïmŋölâh qâr°bĪânwö mïnhäbĪâqâr zâkâr
ąĪâmïym yäq°rïybęnĪwĪ ĄęlpĪęąäį Ąöhęl mwöŋëd yäq°rïyb Ąöąwö lïr°þönwö
lïp°nëy y°hwâh w°sâmäk° yâdwö ŋäl röĄsđ hâŋölâh w°nïr°þâh lwö l°käpĪër
ŋâlâyw w°sđâįät ĄęąbĪęn häbĪâqâr lïp°nëy y°hwâh w°hïq°rïybwĪ bĪ°nëy
Ąäh°ärön häkĪöh°änïym ĄęąhädĪâm w°zâr°qwĪ ĄęąhädĪâm ŋälhämĪïz°bĪëįä
sâbïyb Ą°äsđęrpĪęąäį Ąöhęl mwöŋëd w°hïp°sđïyt Ąęąhâŋölâh w°nïąĪäį ĄöąâhĪ
lïn°ąâįęyhâ w°nâą°nwĪ bĪ°nëy Ąäh°ärön häkĪöhën ĄësđŋälhämĪïz°bĪëįä
w°ŋâr°kwĪ ŋëþïym ŋälhâĄësđ w°ŋâr°kwĪ bĪ°nëy Ąäh°ärön häkĪöh°änïym Ąëą
hänĪ°ąâįïym ĄęąhâröĄsđ w°ĄęąhäpĪâdęrŋälhâŋëþïym Ą°äsđęr ŋälhâĄësđ
Ą°äsđęr ŋälhämĪïz°bĪëįä w°qïr°bĪwö wĪk°râŋâyw yïr°įäþ bĪämĪâyïm
w°hïq°tïyr häkĪöhën ĄęąhäkĪöl hämĪïz°bĪëįâh ŋölâh ĄïsĪđëh rëyįänïyįwöįä
läyhwâh w°ĄïmmïnhäþĪöĄn qâr°bĪânwö mïnhäkĪ°sēâbïym Ąwö mïnhâŋïzĪïym
l°ŋölâhzâkâr ąĪâmïym yäq°rïybęnĪwĪ w°sđâįät Ąöąwö ŋäl yęręk°
hämĪïz°bĪëįä þâpönâhlïp°nëy y°hwâh w°zâr°qwĪ bĪ°nëy Ąäh°ärön
häkĪöh°änïym ĄęądĪâmwö ŋälhämĪïz°bĪëįäsâbïyb w°nïąĪäį Ąöąwö lïn°ąâįâyw
w°ĄęąröĄsđwö w°ĄęąpĪïd°rwö w°ŋâräk° häkĪöhën Ąöąâm ŋälhâŋëþïym Ą°äsđęr
ŋälhâĄësđ Ą°äsđęr ŋälhämĪïz°bĪëįä w°häqĪęręb w°häkĪ°râŋäyïm yïr°įäþ
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
lâräŋ w°löĄ y°mïyręnĪwĪ w°Ąïmhâmër y°mïyręnĪwĪ w°hâyâhhwĪĄ wĪą°mwĪrâąwö
yïh°yęhqĪödęsđ löĄ yïgĪâĄël ĄëlĪęh hämĪïþ°wöą Ą°äsđęr þïwĪâh y°hwâh
ĄęąmösđęhĄęlbĪ°nëy yïsē°râĄël bĪ°här sïynây
removed 'dat/hebr/tav/lev.1/gud.wfr'
creating the word frequency file dat/hebr/tav/lev.1/gud.wfr
the 10 most common words in dat/hebr/tav/lev.1/gud.tlw:
198 0.02052 y°hwâh
184 0.01907 Ą°äsđęr
142 0.01472 häkĪöhën
124 0.01285 löĄ
99 0.01026 Ąwö
74 0.00767 läyhwâh
73 0.00756 hwĪĄ
65 0.00674 kĪïy
63 0.00653 lïp°nëy
60 0.00622 lâkęm
removed 'dat/hebr/tav/lev.1/gud-whole-wds-summary.tex'
removed 'exp/hebr/tav/lev.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/hebr/tav/lev.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:30:42 by tex-make-sample-summary.sh
% Token and word counts for hebr/tav/lev.1/gud.wfr
%
\def\hebrtavwholelevPBgudTks{9650}
\def\hebrtavwholelevPBgudTksPct{91.8}
\def\hebrtavwholelevPBgudWds{3860}
\def\hebrtavwholelevPBgudWdsPct{36.7}
copied '/tmp/560440.file' -> 'exp/hebr/tav/lev.1/gud-whole-wds-summary.tex'
removed '/tmp/560440.file'
creating running text file dat/hebr/tav/lev.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/hebr/tav/lev.1/bad.wfr'
creating the word frequency file dat/hebr/tav/lev.1/bad.wfr
the 10 most common words in dat/hebr/tav/lev.1/bad.tlw:
859 1.00000 =
removed 'dat/hebr/tav/lev.1/bad-whole-wds-summary.tex'
removed 'exp/hebr/tav/lev.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/hebr/tav/lev.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:30:42 by tex-make-sample-summary.sh
% Token and word counts for hebr/tav/lev.1/bad.wfr
%
\def\hebrtavwholelevPBbadTks{859}
\def\hebrtavwholelevPBbadTksPct{8.2}
\def\hebrtavwholelevPBbadWds{1}
\def\hebrtavwholelevPBbadWdsPct{0.0}
copied '/tmp/560484.file' -> 'exp/hebr/tav/lev.1/bad-whole-wds-summary.tex'
removed '/tmp/560484.file'
... creating word files dat/hebr/tav/deu.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
12962 dat/hebr/tav/deu.1/whole.tlw
removed 'dat/hebr/tav/deu.1/raw.tlw'
removed 'dat/hebr/tav/deu.1/gud.tlw'
removed 'dat/hebr/tav/deu.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/hebr/tav/deu.1/raw.wdf
sample:
ĄëlĪęh hädĪ°bârïym Ą°äsđęr dĪïbĪęr mösđęh ĄęlkĪâlyïsē°râĄël bĪ°ŋëbęr
häyĪär°dĪën bĪämĪïd°bĪâr bĪâŋ°ärâbâh mwöl swĪp bĪëynpĪâĄrân wĪbëynąĪöpęl
w°lâbân wäį°äþëröąw°dïy zâhâb =
Ąäįäd ŋâsēâr ywöm mëįörëb dĪęręk° härsēëŋïyr ŋäd qâdësđ bĪär°nëŋä =
wäy°hïy bĪ°Ąär°bĪâŋïym sđânâh bĪ°ŋäsđ°ąĪëyŋâsēâr įödęsđ bĪ°Ąęįâd
läįödęsđ dĪïbĪęr mösđęh ĄęlbĪ°nëy yïsē°râĄël kĪ°köl Ą°äsđęr þïwĪâh
y°hwâh Ąöąwö Ą°älëhęm =
Ąäį°ärëy häkĪöąwö Ąëą sïyįön męlęk° h⥰ęmörïy Ą°äsđęr ywösđëb
bĪ°įęsđ°bĪwönw°Ąëą ŋwög męlęk° häbĪâsđân Ą°äsđęrywösđëb bĪ°ŋäsđ°ąĪâröą
bĪ°Ąęd°ręŋïy =
bĪ°ŋëbęr häyĪär°dĪën bĪ°Ąęręþ mwöĄâb hwöĄïyl mösđęh bĪëĄër ĄęąhäąĪwörâh
häzĪöĄą lëĄmör =
y°hwâh Ą°ęlöhëynwĪ dĪïbĪęr ĄëlëynwĪ bĪ°įörëb lëĄmör räblâkęm sđębęą
bĪâhâr häzĪęh =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
wĪl°köl häyĪâd häį°äzâqâh wĪl°köl hämĪwör⥠hägĪâdwöl Ą°äsđęr ŋâsēâh
mösđęh l°ŋëynëy kĪâlyïsē°râĄël =
removed 'dat/hebr/tav/deu.1/raw.wfr'
creating the word frequency file dat/hebr/tav/deu.1/raw.wfr
the 10 most common words in dat/hebr/tav/deu.1/raw.tlw:
955 0.07368 =
425 0.03279 y°hwâh
370 0.02854 Ą°äsđęr
219 0.01690 Ą°ęlöhęykâ
138 0.01065 kĪïy
112 0.00864 löĄ
74 0.00571 l°kâ
71 0.00548 w°löĄ
67 0.00517 r
57 0.00440 häzĪęh
removed 'dat/hebr/tav/deu.1/raw-whole-wds-summary.tex'
removed 'exp/hebr/tav/deu.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/hebr/tav/deu.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:30:42 by tex-make-sample-summary.sh
% Token and word counts for hebr/tav/deu.1/raw.wfr
%
\def\hebrtavwholedeuPBrawTks{12962}
\def\hebrtavwholedeuPBrawTksPct{100.0}
\def\hebrtavwholedeuPBrawWds{5456}
\def\hebrtavwholedeuPBrawWdsPct{42.1}
copied '/tmp/560538.file' -> 'exp/hebr/tav/deu.1/raw-whole-wds-summary.tex'
removed '/tmp/560538.file'
creating running text file dat/hebr/tav/deu.1/gud.wdf
sample:
ĄëlĪęh hädĪ°bârïym Ą°äsđęr dĪïbĪęr mösđęh ĄęlkĪâlyïsē°râĄël bĪ°ŋëbęr
häyĪär°dĪën bĪämĪïd°bĪâr bĪâŋ°ärâbâh mwöl swĪp bĪëynpĪâĄrân wĪbëynąĪöpęl
w°lâbân wäį°äþëröąw°dïy zâhâb Ąäįäd ŋâsēâr ywöm mëįörëb dĪęręk°
härsēëŋïyr ŋäd qâdësđ bĪär°nëŋä wäy°hïy bĪ°Ąär°bĪâŋïym sđânâh
bĪ°ŋäsđ°ąĪëyŋâsēâr įödęsđ bĪ°Ąęįâd läįödęsđ dĪïbĪęr mösđęh ĄęlbĪ°nëy
yïsē°râĄël kĪ°köl Ą°äsđęr þïwĪâh y°hwâh Ąöąwö Ą°älëhęm Ąäį°ärëy häkĪöąwö
Ąëą sïyįön męlęk° h⥰ęmörïy Ą°äsđęr ywösđëb bĪ°įęsđ°bĪwönw°Ąëą ŋwög
męlęk° häbĪâsđân Ą°äsđęrywösđëb bĪ°ŋäsđ°ąĪâröą bĪ°Ąęd°ręŋïy bĪ°ŋëbęr
häyĪär°dĪën bĪ°Ąęręþ mwöĄâb hwöĄïyl mösđęh bĪëĄër ĄęąhäąĪwörâh häzĪöĄą
lëĄmör y°hwâh Ą°ęlöhëynwĪ dĪïbĪęr ĄëlëynwĪ bĪ°įörëb lëĄmör räblâkęm
sđębęą bĪâhâr häzĪęh pĪ°nwĪ wĪs°ŋwĪ lâkęm wĪböĄwĪ här h⥰ęmörïy
w°ĄęlkĪâlsđ°kënâyw bĪâŋ°ärâbâh bâhâr wĪbäsĪđ°pëlâh wĪbänĪęgęb wĪb°įwöp
häyĪâmĄęręþ häkĪ°näŋ°änïy w°hälĪ°bânwön ŋädhänĪâhâr hägĪâdöl n°härpĪ°râą
r°Ąëh nâąäąĪïy lïp°nëykęm ĄęąhâĄâręþ bĪöĄwĪ wĪr°sđwĪ ĄęąhâĄâręþ Ą°äsđęr
nïsđ°bĪäŋ y°hwâh l䥰äböąëykęm l°Ąäb°râhâm l°yïþ°įâq wĪl°yäŋ°äqöb lâąëą
lâhęm wĪl°zär°ŋâm Ąäį°ärëyhęm wâĄömär Ą°älëkęm bĪâŋëą hähïwĄ lëĄmör
löĄĄwĪkäl l°bädĪïy sē°Ąëą Ąęą°kęm y°hwâh Ą°ęlöhëykęm hïr°bĪâh Ąęą°kęm
w°hïnĪ°kęm häyĪwöm kĪ°kwök°bëy häsĪđâmäyïm lâröb y°hwâh Ą°ęlöhëy
Ą°äbwöąëkęm yösëp ŋ°älëykęm kĪâkęmĄęlęp pĪ°ŋâmïym wïybârëk° Ąęą°kęm
kĪ䥰äsđęr dĪïbĪęr lâkęm Ąëykâh ĄęsĪē⥠l°bädĪïy târ°į°äkęm
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
Ą°äsđęr sđ°lâįwö y°hwâh läŋ°äsēwöą bĪ°Ąęręþ mïþ°râyïml°pär°ŋöh
wĪl°kâlŋ°äbâdâyw wĪl°kâlĄär°þwö wĪl°köl häyĪâd häį°äzâqâh wĪl°köl
hämĪwör⥠hägĪâdwöl Ą°äsđęr ŋâsēâh mösđęh l°ŋëynëy kĪâlyïsē°râĄël
removed 'dat/hebr/tav/deu.1/gud.wfr'
creating the word frequency file dat/hebr/tav/deu.1/gud.wfr
the 10 most common words in dat/hebr/tav/deu.1/gud.tlw:
425 0.03540 y°hwâh
370 0.03082 Ą°äsđęr
219 0.01824 Ą°ęlöhęykâ
138 0.01149 kĪïy
112 0.00933 löĄ
74 0.00616 l°kâ
71 0.00591 w°löĄ
67 0.00558 r
57 0.00475 häzĪęh
55 0.00458 häyĪwöm
removed 'dat/hebr/tav/deu.1/gud-whole-wds-summary.tex'
removed 'exp/hebr/tav/deu.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/hebr/tav/deu.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:30:42 by tex-make-sample-summary.sh
% Token and word counts for hebr/tav/deu.1/gud.wfr
%
\def\hebrtavwholedeuPBgudTks{12007}
\def\hebrtavwholedeuPBgudTksPct{92.6}
\def\hebrtavwholedeuPBgudWds{5455}
\def\hebrtavwholedeuPBgudWdsPct{42.1}
copied '/tmp/560582.file' -> 'exp/hebr/tav/deu.1/gud-whole-wds-summary.tex'
removed '/tmp/560582.file'
creating running text file dat/hebr/tav/deu.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/hebr/tav/deu.1/bad.wfr'
creating the word frequency file dat/hebr/tav/deu.1/bad.wfr
the 10 most common words in dat/hebr/tav/deu.1/bad.tlw:
955 1.00000 =
removed 'dat/hebr/tav/deu.1/bad-whole-wds-summary.tex'
removed 'exp/hebr/tav/deu.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/hebr/tav/deu.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:30:42 by tex-make-sample-summary.sh
% Token and word counts for hebr/tav/deu.1/bad.wfr
%
\def\hebrtavwholedeuPBbadTks{955}
\def\hebrtavwholedeuPBbadTksPct{7.4}
\def\hebrtavwholedeuPBbadWds{1}
\def\hebrtavwholedeuPBbadWdsPct{0.0}
copied '/tmp/560626.file' -> 'exp/hebr/tav/deu.1/bad-whole-wds-summary.tex'
removed '/tmp/560626.file'
... creating word files dat/hebr/tav/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
72156 dat/hebr/tav/tot.1/whole.tlw
removed 'dat/hebr/tav/tot.1/raw.tlw'
removed 'dat/hebr/tav/tot.1/gud.tlw'
removed 'dat/hebr/tav/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/hebr/tav/tot.1/raw.wdf
sample:
bĪ°rëĄsđïyą bĪâr⥠Ą°ęlöhïym Ąëą häsĪđâmäyïm w°Ąëą hâĄâręþ =
w°hâĄâręþ hây°ąâh ąöhwĪ wâböhwĪ w°įösđęk° ŋälpĪ°nëy ą°hwöm w°rwĪįä
Ą°ęlöhïym m°räįępęą ŋälpĪ°nëy hämĪâyïm =
wäyĪöĄmęr Ą°ęlöhïym y°hïy Ąwör wäy°hïyĄwör =
wäyĪär°Ą Ą°ęlöhïym ĄęąhâĄwör kĪïytwöb wäyĪäb°dĪël Ą°ęlöhïym bĪëyn hâĄwör
wĪbëyn häįösđęk° =
wäyĪïq°r⥠Ą°ęlöhïym lâĄwör ywöm w°läįösđęk° qâr⥠lây°lâh wäy°hïyŋęręb
wäy°hïyböqęr ywöm Ąęįâd =
wäyĪöĄmęr Ą°ęlöhïym y°hïy râqïyŋä bĪ°ąwök° hämĪâyïm wïyhïy mäb°dĪïyl
bĪëyn mäyïm lâmâyïm =
wäyĪäŋäsē Ą°ęlöhïym Ąęąhârâqïyŋä wäyĪäb°dĪël bĪëyn hämĪäyïm Ą°äsđęr
mïąĪäįäą lârâqïyŋä wĪbëyn hämĪäyïm Ą°äsđęr mëŋäl lârâqïyŋä wäy°hïykën =
wäyĪïq°r⥠Ą°ęlöhïym lârâqïyŋä sđâmâyïm wäy°hïyŋęręb wäy°hïyböqęr ywöm
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
wĪl°köl häyĪâd häį°äzâqâh wĪl°köl hämĪwör⥠hägĪâdwöl Ą°äsđęr ŋâsēâh
mösđęh l°ŋëynëy kĪâlyïsē°râĄël =
removed 'dat/hebr/tav/tot.1/raw.wfr'
creating the word frequency file dat/hebr/tav/tot.1/raw.wfr
the 10 most common words in dat/hebr/tav/tot.1/raw.tlw:
5845 0.08101 =
1324 0.01835 y°hwâh
1105 0.01531 Ą°äsđęr
581 0.00805 wäyĪöĄmęr
512 0.00710 kĪïy
454 0.00629 löĄ
365 0.00506 yïsē°râĄël
316 0.00438 mösđęh
254 0.00352 hwĪĄ
239 0.00331 bĪ°nëy
removed 'dat/hebr/tav/tot.1/raw-whole-wds-summary.tex'
removed 'exp/hebr/tav/tot.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/hebr/tav/tot.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:30:42 by tex-make-sample-summary.sh
% Token and word counts for hebr/tav/tot.1/raw.wfr
%
\def\hebrtavwholetotPBrawTks{72156}
\def\hebrtavwholetotPBrawTksPct{100.0}
\def\hebrtavwholetotPBrawWds{20977}
\def\hebrtavwholetotPBrawWdsPct{29.1}
copied '/tmp/560680.file' -> 'exp/hebr/tav/tot.1/raw-whole-wds-summary.tex'
removed '/tmp/560680.file'
creating running text file dat/hebr/tav/tot.1/gud.wdf
sample:
bĪ°rëĄsđïyą bĪâr⥠Ą°ęlöhïym Ąëą häsĪđâmäyïm w°Ąëą hâĄâręþ w°hâĄâręþ
hây°ąâh ąöhwĪ wâböhwĪ w°įösđęk° ŋälpĪ°nëy ą°hwöm w°rwĪįä Ą°ęlöhïym
m°räįępęą ŋälpĪ°nëy hämĪâyïm wäyĪöĄmęr Ą°ęlöhïym y°hïy Ąwör wäy°hïyĄwör
wäyĪär°Ą Ą°ęlöhïym ĄęąhâĄwör kĪïytwöb wäyĪäb°dĪël Ą°ęlöhïym bĪëyn hâĄwör
wĪbëyn häįösđęk° wäyĪïq°r⥠Ą°ęlöhïym lâĄwör ywöm w°läįösđęk° qârâĄ
lây°lâh wäy°hïyŋęręb wäy°hïyböqęr ywöm Ąęįâd wäyĪöĄmęr Ą°ęlöhïym y°hïy
râqïyŋä bĪ°ąwök° hämĪâyïm wïyhïy mäb°dĪïyl bĪëyn mäyïm lâmâyïm wäyĪäŋäsē
Ą°ęlöhïym Ąęąhârâqïyŋä wäyĪäb°dĪël bĪëyn hämĪäyïm Ą°äsđęr mïąĪäįäą
lârâqïyŋä wĪbëyn hämĪäyïm Ą°äsđęr mëŋäl lârâqïyŋä wäy°hïykën wäyĪïq°râĄ
Ą°ęlöhïym lârâqïyŋä sđâmâyïm wäy°hïyŋęręb wäy°hïyböqęr ywöm sđënïy
wäyĪöĄmęr Ą°ęlöhïym yïqĪâwwĪ hämĪäyïm mïąĪäįäą häsĪđâmäyïm Ąęlmâqwöm
Ąęįâd w°ąërâĄęh häyĪäbĪâsđâh wäy°hïykën wäyĪïq°r⥠Ą°ęlöhïym
läyĪäbĪâsđâh Ąęręþ wĪl°mïq°wëh hämĪäyïm qâr⥠yämĪïym wäyĪär°Ą Ą°ęlöhïym
kĪïytwöb wäyĪöĄmęr Ą°ęlöhïym ąĪäd°sđëĄ hâĄâręþ dĪęsđęĄ ŋësēęb mäz°rïyŋä
zęräŋ ŋëþ pĪ°rïy ŋösēęh pĪ°rïy l°mïynwö Ą°äsđęr zär°ŋwöbwö ŋälhâĄâręþ
wäy°hïykën wäąĪwöþëĄ hâĄâręþ dĪęsđęĄ ŋësēęb mäz°rïyŋä zęräŋ l°mïynëhwĪ
w°ŋëþ ŋösēęhpĪ°rïy Ą°äsđęr zär°ŋwöbwö l°mïynëhwĪ wäyĪär°Ą Ą°ęlöhïym
kĪïytwöb wäy°hïyŋęręb wäy°hïyböqęr ywöm sđ°lïysđïy wäyĪöĄmęr Ą°ęlöhïym
y°hïy m°Ąöröą bĪïr°qïyŋä häsĪđâmäyïm l°häb°dĪïyl bĪëyn häyĪwöm wĪbëyn
hälĪây°lâh w°hâywĪ l°Ąöąöą wĪl°mwöŋ°ädïym wĪl°yâmïym w°sđânïym w°hâywĪ
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
Ą°äsđęr sđ°lâįwö y°hwâh läŋ°äsēwöą bĪ°Ąęręþ mïþ°râyïml°pär°ŋöh
wĪl°kâlŋ°äbâdâyw wĪl°kâlĄär°þwö wĪl°köl häyĪâd häį°äzâqâh wĪl°köl
hämĪwör⥠hägĪâdwöl Ą°äsđęr ŋâsēâh mösđęh l°ŋëynëy kĪâlyïsē°râĄël
removed 'dat/hebr/tav/tot.1/gud.wfr'
creating the word frequency file dat/hebr/tav/tot.1/gud.wfr
the 10 most common words in dat/hebr/tav/tot.1/gud.tlw:
1324 0.01997 y°hwâh
1105 0.01666 Ą°äsđęr
581 0.00876 wäyĪöĄmęr
512 0.00772 kĪïy
454 0.00685 löĄ
365 0.00550 yïsē°râĄël
316 0.00477 mösđęh
254 0.00383 hwĪĄ
239 0.00360 bĪ°nëy
235 0.00354 Ą°ęlöhęykâ
removed 'dat/hebr/tav/tot.1/gud-whole-wds-summary.tex'
removed 'exp/hebr/tav/tot.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/hebr/tav/tot.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:30:42 by tex-make-sample-summary.sh
% Token and word counts for hebr/tav/tot.1/gud.wfr
%
\def\hebrtavwholetotPBgudTks{66311}
\def\hebrtavwholetotPBgudTksPct{91.9}
\def\hebrtavwholetotPBgudWds{20976}
\def\hebrtavwholetotPBgudWdsPct{29.1}
copied '/tmp/560725.file' -> 'exp/hebr/tav/tot.1/gud-whole-wds-summary.tex'
removed '/tmp/560725.file'
creating running text file dat/hebr/tav/tot.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/hebr/tav/tot.1/bad.wfr'
creating the word frequency file dat/hebr/tav/tot.1/bad.wfr
the 10 most common words in dat/hebr/tav/tot.1/bad.tlw:
5845 1.00000 =
removed 'dat/hebr/tav/tot.1/bad-whole-wds-summary.tex'
removed 'exp/hebr/tav/tot.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/hebr/tav/tot.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:30:42 by tex-make-sample-summary.sh
% Token and word counts for hebr/tav/tot.1/bad.wfr
%
\def\hebrtavwholetotPBbadTks{5845}
\def\hebrtavwholetotPBbadTksPct{8.1}
\def\hebrtavwholetotPBbadWds{1}
\def\hebrtavwholetotPBbadWdsPct{0.0}
copied '/tmp/560769.file' -> 'exp/hebr/tav/tot.1/bad-whole-wds-summary.tex'
removed '/tmp/560769.file'
lines words bytes file
------- ------- --------- ------------
7213 21626 193208 dat/hebr/tav/gen.1/raw.wfr
5712 17127 153676 dat/hebr/tav/exo.1/raw.wfr
5307 15916 143970 dat/hebr/tav/num.1/raw.wfr
3861 11578 105365 dat/hebr/tav/lev.1/raw.wfr
5456 16359 147102 dat/hebr/tav/deu.1/raw.wfr
20977 62912 577020 dat/hebr/tav/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
7212 21623 193190 dat/hebr/tav/gen.1/gud.wfr
5711 17124 153658 dat/hebr/tav/exo.1/gud.wfr
5306 15913 143952 dat/hebr/tav/num.1/gud.wfr
3860 11575 105347 dat/hebr/tav/lev.1/gud.wfr
5455 16356 147084 dat/hebr/tav/deu.1/gud.wfr
20976 62909 577002 dat/hebr/tav/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
1 3 18 dat/hebr/tav/gen.1/bad.wfr
1 3 18 dat/hebr/tav/exo.1/bad.wfr
1 3 18 dat/hebr/tav/num.1/bad.wfr
1 3 18 dat/hebr/tav/lev.1/bad.wfr
1 3 18 dat/hebr/tav/deu.1/bad.wfr
1 3 18 dat/hebr/tav/tot.1/bad.wfr
gen.1 raw = 18744 gud = 17211 bad = 1533
exo.1 raw = 15079 gud = 13870 bad = 1209
num.1 raw = 14862 gud = 13573 bad = 1289
lev.1 raw = 10509 gud = 9650 bad = 859
deu.1 raw = 12962 gud = 12007 bad = 955
tot.1 raw = 72156 gud = 66311 bad = 5845
=== creating the derived word files dat/hebr/tad/*/{raw,gud,bad}.{tlw,wdf,wfr} (whole) ===
... creating word files dat/hebr/tad/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
72156 dat/hebr/tad/tot.1/whole.tlw
removed 'dat/hebr/tad/tot.1/raw.tlw'
removed 'dat/hebr/tad/tot.1/gud.tlw'
removed 'dat/hebr/tad/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/hebr/tad/tot.1/raw.wdf
sample:
bĪrĄsđyą bĪrĄ Ąlhym Ąą hsĪđmym wĄą hĄrþ =
whĄrþ hyąh ąhwĪ wbhwĪ wįsđk ŋlpĪny ąhwm wrwĪį Ąlhym mrįpą ŋlpĪny hmĪym =
wyĪĄmr Ąlhym yhy Ąwr wyhyĄwr =
wyĪrĄ Ąlhym ĄąhĄwr kĪytwb wyĪbdĪl Ąlhym bĪyn hĄwr wĪbyn hįsđk =
wyĪqrĄ Ąlhym lĄwr ywm wlįsđk qrĄ lylh wyhyŋrb wyhybqr ywm Ąįd =
wyĪĄmr Ąlhym yhy rqyŋ bĪąwk hmĪym wyhy mbdĪyl bĪyn mym lmym =
wyĪŋsē Ąlhym Ąąhrqyŋ wyĪbdĪl bĪyn hmĪym Ąsđr mąĪįą lrqyŋ wĪbyn hmĪym
Ąsđr mŋl lrqyŋ wyhykn =
wyĪqrĄ Ąlhym lrqyŋ sđmym wyhyŋrb wyhybqr ywm sđny =
wyĪĄmr Ąlhym yqĪwwĪ hmĪym mąĪįą hsĪđmym Ąlmqwm Ąįd wąrĄh hyĪbĪsđh wyhykn
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
wĪlkl hyĪd hįzqh wĪlkl hmĪwrĄ hgĪdwl Ąsđr ŋsēh msđh lŋyny kĪlysērĄl =
removed 'dat/hebr/tad/tot.1/raw.wfr'
creating the word frequency file dat/hebr/tad/tot.1/raw.wfr
the 10 most common words in dat/hebr/tad/tot.1/raw.tlw:
5845 0.08101 =
1328 0.01840 yhwh
1114 0.01544 Ąsđr
617 0.00855 wyĪĄmr
512 0.00710 kĪy
454 0.00629 lĄ
365 0.00506 ysērĄl
316 0.00438 msđh
263 0.00364 bĪny
254 0.00352 hwĪĄ
removed 'dat/hebr/tad/tot.1/raw-whole-wds-summary.tex'
removed 'exp/hebr/tad/tot.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/hebr/tad/tot.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:30:42 by tex-make-sample-summary.sh
% Token and word counts for hebr/tad/tot.1/raw.wfr
%
\def\hebrtadwholetotPBrawTks{72156}
\def\hebrtadwholetotPBrawTksPct{100.0}
\def\hebrtadwholetotPBrawWds{19557}
\def\hebrtadwholetotPBrawWdsPct{27.1}
copied '/tmp/560939.file' -> 'exp/hebr/tad/tot.1/raw-whole-wds-summary.tex'
removed '/tmp/560939.file'
creating running text file dat/hebr/tad/tot.1/gud.wdf
sample:
bĪrĄsđyą bĪrĄ Ąlhym Ąą hsĪđmym wĄą hĄrþ whĄrþ hyąh ąhwĪ wbhwĪ wįsđk
ŋlpĪny ąhwm wrwĪį Ąlhym mrįpą ŋlpĪny hmĪym wyĪĄmr Ąlhym yhy Ąwr wyhyĄwr
wyĪrĄ Ąlhym ĄąhĄwr kĪytwb wyĪbdĪl Ąlhym bĪyn hĄwr wĪbyn hįsđk wyĪqrĄ
Ąlhym lĄwr ywm wlįsđk qrĄ lylh wyhyŋrb wyhybqr ywm Ąįd wyĪĄmr Ąlhym yhy
rqyŋ bĪąwk hmĪym wyhy mbdĪyl bĪyn mym lmym wyĪŋsē Ąlhym Ąąhrqyŋ wyĪbdĪl
bĪyn hmĪym Ąsđr mąĪįą lrqyŋ wĪbyn hmĪym Ąsđr mŋl lrqyŋ wyhykn wyĪqrĄ
Ąlhym lrqyŋ sđmym wyhyŋrb wyhybqr ywm sđny wyĪĄmr Ąlhym yqĪwwĪ hmĪym
mąĪįą hsĪđmym Ąlmqwm Ąįd wąrĄh hyĪbĪsđh wyhykn wyĪqrĄ Ąlhym lyĪbĪsđh Ąrþ
wĪlmqwh hmĪym qrĄ ymĪym wyĪrĄ Ąlhym kĪytwb wyĪĄmr Ąlhym ąĪdsđĄ hĄrþ
dĪsđĄ ŋsēb mzryŋ zrŋ ŋþ pĪry ŋsēh pĪry lmynw Ąsđr zrŋwbw ŋlhĄrþ wyhykn
wąĪwþĄ hĄrþ dĪsđĄ ŋsēb mzryŋ zrŋ lmynhwĪ wŋþ ŋsēhpĪry Ąsđr zrŋwbw
lmynhwĪ wyĪrĄ Ąlhym kĪytwb wyhyŋrb wyhybqr ywm sđlysđy wyĪĄmr Ąlhym yhy
mĄrą bĪrqyŋ hsĪđmym lhbdĪyl bĪyn hyĪwm wĪbyn hlĪylh whywĪ lĄąą wĪlmwŋdym
wĪlymym wsđnym whywĪ lmĄwrą bĪrqyŋ hsĪđmym lhĄyr ŋlhĄrþ wyhykn wyĪŋsē
Ąlhym Ąąsđny hmĪĄrą hgĪdlym ĄąhmĪĄwr hgĪdl lmmsđlą hyĪwm wĄąhmĪĄwr hqĪtn
lmmsđlą hlĪylh wĄą hkĪwkbym wyĪąĪn Ąąm Ąlhym bĪrqyŋ hsĪđmym lhĄyr ŋlhĄrþ
wlmsđl bĪyĪwm wĪblĪylh wĪlhbdĪyl bĪyn hĄwr wĪbyn hįsđk wyĪrĄ Ąlhym
kĪytwb wyhyŋrb wyhybqr ywm rbyŋy wyĪĄmr ĄlhymysđrþwĪ hmĪym sđrþ npsđ
įyĪh wŋwp yŋwpp ŋlhĄrþ ŋlpĪny rqyŋ hsĪđmym wyĪbrĄ Ąlhym ĄąhąĪnĪynm
hgĪdlym wĄą kĪlnpsđ hįyĪh hrmsēą Ąsđr sđrþwĪ hmĪym lmynhm wĄą kĪlŋwp
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
pĪnym ĄlpĪnym lklhĄąą whmĪwpąym Ąsđr sđlįw yhwh lŋsēwą bĪĄrþ mþrymlprŋh
wĪlklŋbdyw wĪlklĄrþw wĪlkl hyĪd hįzqh wĪlkl hmĪwrĄ hgĪdwl Ąsđr ŋsēh msđh
lŋyny kĪlysērĄl
removed 'dat/hebr/tad/tot.1/gud.wfr'
creating the word frequency file dat/hebr/tad/tot.1/gud.wfr
the 10 most common words in dat/hebr/tad/tot.1/gud.tlw:
1328 0.02003 yhwh
1114 0.01680 Ąsđr
617 0.00930 wyĪĄmr
512 0.00772 kĪy
454 0.00685 lĄ
365 0.00550 ysērĄl
316 0.00477 msđh
263 0.00397 bĪny
254 0.00383 hwĪĄ
235 0.00354 Ąlhyk
removed 'dat/hebr/tad/tot.1/gud-whole-wds-summary.tex'
removed 'exp/hebr/tad/tot.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/hebr/tad/tot.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:30:43 by tex-make-sample-summary.sh
% Token and word counts for hebr/tad/tot.1/gud.wfr
%
\def\hebrtadwholetotPBgudTks{66311}
\def\hebrtadwholetotPBgudTksPct{91.9}
\def\hebrtadwholetotPBgudWds{19556}
\def\hebrtadwholetotPBgudWdsPct{27.1}
copied '/tmp/560983.file' -> 'exp/hebr/tad/tot.1/gud-whole-wds-summary.tex'
removed '/tmp/560983.file'
creating running text file dat/hebr/tad/tot.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/hebr/tad/tot.1/bad.wfr'
creating the word frequency file dat/hebr/tad/tot.1/bad.wfr
the 10 most common words in dat/hebr/tad/tot.1/bad.tlw:
5845 1.00000 =
removed 'dat/hebr/tad/tot.1/bad-whole-wds-summary.tex'
removed 'exp/hebr/tad/tot.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/hebr/tad/tot.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:30:43 by tex-make-sample-summary.sh
% Token and word counts for hebr/tad/tot.1/bad.wfr
%
\def\hebrtadwholetotPBbadTks{5845}
\def\hebrtadwholetotPBbadTksPct{8.1}
\def\hebrtadwholetotPBbadWds{1}
\def\hebrtadwholetotPBbadWdsPct{0.0}
copied '/tmp/561027.file' -> 'exp/hebr/tad/tot.1/bad-whole-wds-summary.tex'
removed '/tmp/561027.file'
lines words bytes file
------- ------- --------- ------------
19557 58655 465897 dat/hebr/tad/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
19556 58652 465879 dat/hebr/tad/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
1 3 18 dat/hebr/tad/tot.1/bad.wfr
tot.1 raw = 72156 gud = 66311 bad = 5845
=== creating the derived word files dat/geez/gok/*/{raw,gud,bad}.{tlw,wdf,wfr} (whole) ===
... creating word files dat/geez/gok/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
34788 dat/geez/gok/tot.1/whole.tlw
removed 'dat/geez/gok/tot.1/raw.tlw'
removed 'dat/geez/gok/tot.1/gud.tlw'
removed 'dat/geez/gok/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/geez/gok/tot.1/raw.wdf
sample:
be'akWetEtu le'Igzi'AbHEr 'ab 'a`hazE kWulu webeweldu 'iyesus krstos
zebotu kWulu kone weze'InbelEhuse 'albo zekone webemenfes qdus
PeraqliTos zeywe`S'I 'Im'ab weyne`s'I 'Imweld `1 'amlak 'ab weweld
wemenfes qdus ne'amn wengeni le`slus =
fkarE wezEna ze`3`100`10 we`8 rtu`ane haymanot be'Inte kbr we`Ibey
wetedla zekeme wehebe 'Igzi'AbHEr ledeqiqa 'adam wefedfadese zebe'Inte
`Ibeya wekbra leSyon tabote Hgu le'Igzi'AbHEr 'Inte gebariha wekEnyaha
lelihu bewste SrHe meqdesu 'Imqdme kWulu fTret mela'Ikt weseb'I 'Isme
be`hbret webe`smret webe`Irina gebrwa 'ab weweld wemenfes qdus leSyon
semayawit lema`hdare sbHetihomu we'Imz ybE 'ab leweld welemenfes qdus
ngber seb'a be'ar'ayane webe'amsaline we`hebru we`semru bez mkr weybE
weld 'ane 'Ilebs `sgahu le'adam weybE menfes qdus 'ane 'a`hedr wste lbe
nebiyat weSadqan wezati `hbret wekidan tegebret bewste Syon ma`hdere
sbHetihomu wedawitni ybE tezeker ma`hbereke ze'aqdemke feTire
lemed`henite betre rstke bedebre Syon ze`hederke wstEta =
wegebro le'adam bezezi'ahu 'ar'aya we'amsal keme yn`sto lesayTan be'Inte
t`Ibitu msle serawitu weyaqmo le'adam tekle zi'ahu msle `heran deqiqu
lesbHetihu 'Isme `hluq wemtur mkre 'Igzi'AbHEr 'Inte ybE 'Ikewn seb'a
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
we'Imd`hrEhu 'agb'a lomu ykWuno 'amlak yagba Syon baHr seged Hzbe 'ar`ad
qdme seged Zan seged wdm 'ar`ad `amde Syon =
removed 'dat/geez/gok/tot.1/raw.wfr'
creating the word frequency file dat/geez/gok/tot.1/raw.wfr
the 10 most common words in dat/geez/gok/tot.1/raw.tlw:
571 0.01641 keme
481 0.01383 'Igzi'AbHEr
426 0.01225 'Isme
357 0.01026 wste
226 0.00650 =
187 0.00538 'Inze
179 0.00515 `hebe
174 0.00500 be'Inte
172 0.00494 msle
166 0.00477 ngu`s
removed 'dat/geez/gok/tot.1/raw-whole-wds-summary.tex'
removed 'exp/geez/gok/tot.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/geez/gok/tot.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:30:43 by tex-make-sample-summary.sh
% Token and word counts for geez/gok/tot.1/raw.wfr
%
\def\geezgokwholetotPBrawTks{34788}
\def\geezgokwholetotPBrawTksPct{100.0}
\def\geezgokwholetotPBrawWds{12356}
\def\geezgokwholetotPBrawWdsPct{35.5}
copied '/tmp/561122.file' -> 'exp/geez/gok/tot.1/raw-whole-wds-summary.tex'
removed '/tmp/561122.file'
creating running text file dat/geez/gok/tot.1/gud.wdf
sample:
be'akWetEtu le'Igzi'AbHEr 'ab 'a`hazE kWulu webeweldu 'iyesus krstos
zebotu kWulu kone weze'InbelEhuse 'albo zekone webemenfes qdus
PeraqliTos zeywe`S'I 'Im'ab weyne`s'I 'Imweld 'amlak 'ab weweld wemenfes
qdus ne'amn wengeni le`slus fkarE wezEna rtu`ane haymanot be'Inte kbr
we`Ibey wetedla zekeme wehebe 'Igzi'AbHEr ledeqiqa 'adam wefedfadese
zebe'Inte `Ibeya wekbra leSyon tabote Hgu le'Igzi'AbHEr 'Inte gebariha
wekEnyaha lelihu bewste SrHe meqdesu 'Imqdme kWulu fTret mela'Ikt
weseb'I 'Isme be`hbret webe`smret webe`Irina gebrwa 'ab weweld wemenfes
qdus leSyon semayawit lema`hdare sbHetihomu we'Imz ybE 'ab leweld
welemenfes qdus ngber seb'a be'ar'ayane webe'amsaline we`hebru we`semru
bez mkr weybE weld 'ane 'Ilebs `sgahu le'adam weybE menfes qdus 'ane
'a`hedr wste lbe nebiyat weSadqan wezati `hbret wekidan tegebret bewste
Syon ma`hdere sbHetihomu wedawitni ybE tezeker ma`hbereke ze'aqdemke
feTire lemed`henite betre rstke bedebre Syon ze`hederke wstEta wegebro
le'adam bezezi'ahu 'ar'aya we'amsal keme yn`sto lesayTan be'Inte t`Ibitu
msle serawitu weyaqmo le'adam tekle zi'ahu msle `heran deqiqu lesbHetihu
'Isme `hluq wemtur mkre 'Igzi'AbHEr 'Inte ybE 'Ikewn seb'a we'Aster'i
lekWulu zefeTerku be`sga 'Itgeses webede`hari mewa`Il be`smretu tewelde
be`sga 'Imdagmawit Syon dagmawi 'adam zw'Itu med`henine krstos zati
y'Iti mkHne wehaymanotne tesfane weHywetne Syon samayawit hebukE ngba'I
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
'ikonu 'Imnegede dawit weHzbe 'Isra'El bekeme ybE 'Igzi'abHEr 'ane
'aqen'omu beze'ikone Hzb we'Imd`hrEhu 'agb'a lomu ykWuno 'amlak yagba
Syon baHr seged Hzbe 'ar`ad qdme seged Zan seged wdm 'ar`ad `amde Syon
removed 'dat/geez/gok/tot.1/gud.wfr'
creating the word frequency file dat/geez/gok/tot.1/gud.wfr
the 10 most common words in dat/geez/gok/tot.1/gud.tlw:
571 0.01665 keme
481 0.01403 'Igzi'AbHEr
426 0.01242 'Isme
357 0.01041 wste
187 0.00545 'Inze
179 0.00522 `hebe
174 0.00507 be'Inte
172 0.00502 msle
166 0.00484 ngu`s
163 0.00475 'Iske
removed 'dat/geez/gok/tot.1/gud-whole-wds-summary.tex'
removed 'exp/geez/gok/tot.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/geez/gok/tot.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:30:43 by tex-make-sample-summary.sh
% Token and word counts for geez/gok/tot.1/gud.wfr
%
\def\geezgokwholetotPBgudTks{34291}
\def\geezgokwholetotPBgudTksPct{98.6}
\def\geezgokwholetotPBgudWds{12272}
\def\geezgokwholetotPBgudWdsPct{35.3}
copied '/tmp/561166.file' -> 'exp/geez/gok/tot.1/gud-whole-wds-summary.tex'
removed '/tmp/561166.file'
creating running text file dat/geez/gok/tot.1/bad.wdf
sample:
`1 =
ze`3`100`10 we`8 =
=
=
`10 we`5 =
=
be`9 =
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/geez/gok/tot.1/bad.wfr'
creating the word frequency file dat/geez/gok/tot.1/bad.wfr
the 10 most common words in dat/geez/gok/tot.1/bad.tlw:
226 0.45473 =
26 0.05231 `1
22 0.04427 `10
21 0.04225 `3
16 0.03219 we`2
9 0.01811 `2
8 0.01610 `4
7 0.01408 `7
7 0.01408 `70
6 0.01207 `6
removed 'dat/geez/gok/tot.1/bad-whole-wds-summary.tex'
removed 'exp/geez/gok/tot.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/geez/gok/tot.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:30:43 by tex-make-sample-summary.sh
% Token and word counts for geez/gok/tot.1/bad.wfr
%
\def\geezgokwholetotPBbadTks{497}
\def\geezgokwholetotPBbadTksPct{1.4}
\def\geezgokwholetotPBbadWds{84}
\def\geezgokwholetotPBbadWdsPct{0.2}
copied '/tmp/561210.file' -> 'exp/geez/gok/tot.1/bad-whole-wds-summary.tex'
removed '/tmp/561210.file'
lines words bytes file
------- ------- --------- ------------
12356 37068 306126 dat/geez/gok/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
12272 36816 304244 dat/geez/gok/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
84 252 1882 dat/geez/gok/tot.1/bad.wfr
tot.1 raw = 34788 gud = 34291 bad = 497
=== creating the derived word files dat/geez/eno/*/{raw,gud,bad}.{tlw,wdf,wfr} (whole) ===
... creating word files dat/geez/eno/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
18215 dat/geez/eno/tot.1/whole.tlw
removed 'dat/geez/eno/tot.1/raw.tlw'
removed 'dat/geez/eno/tot.1/gud.tlw'
removed 'dat/geez/eno/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/geez/eno/tot.1/raw.wdf
sample:
qale bereket zehEnok zekeme bareke `hruyane weSadqane 'Ile helewu ykunu
be`Ilete mndabE le'aseslo kWulu 'Ikuyan weresi`an we'aw`s'a weybE hEnok
b'Isi Sadq ze'Im`hebe Igzi'abHEr 'Inze 'a`Iyntihu k`sutat weyrE'i ra'Iye
qduse zebesemayat ze'ar'ayuni mela'Ikt wesema`Iku 'Im`hebEhomu kWulo
we'a'Imerku 'ane ze'IrE'i we'ako lez twld 'ala lezeymeS'I twld r`huqan
be'Inte `hruyan 'IbE we'aw`sa'Iku be'Inti'ahomu msle zeywe`S'I qdus
we`ebiy 'Ima`hderu we'amlake `alem we'Imhye ykeyd dibe sina debr
weyaster'i bet`Iyntu weyaster'i beSn`e `heylu 'Imsemay weyferh kWulu
weyadleqelqu tguhan weyne`s'omu frhet were`ad `ebiy 'Iske 'aSnafe mdr
weydeneg`Su 'adbar newa`han weytEHetu 'awgr newa`hat weytmesewu keme
me`are gra 'Imlahb wet`seTem mdr wekWulu zewste mdr ytHegWel weykewn ftH
la`Ile kWulu wela`Ile Sadqan kWulomu leSadqanse selame ygebr lomu
weye`eqbomu le`hruyan weykewn `sahl la`IlEhomu weykewnu kWulomu ze'amlak
wey`sErHu weytbareku weyherh lomu brhane 'amlak wenahu meS'a bet'Ilfet
qdusan keme ygber ftHe la`IlEhomu weyaHegWulomu leresi`an weytwaqes
kWulo ze`sga be'Inte kWulu zegebru wereseyu la`IlEhu `haT'an weresi`an
Teyequ kWulo zewste semay gbre 'Ifo 'iymeyTu fnawihomu brhanat zewste
semay keme kWulu y`serq weye`erb `sru`I kWulu bebezemenu we'iyt`edewu
'Imt'Izazomu r'Iywa lemdr welebwu be'Inte mgbar zeytgeber la`IlEha
'Imqedami 'Iske tefSamEtu keme iytmeyeT kWulu gbru le'amlak 'Inze
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
le'Ile teweldu beSlmet ytwedeyu beSlmet Inze ytwe`hew`hu Sadqan weySerHu
weyrE'Iywomu `haT'An 'Inze yberhu weyeHewru Imuntuhi be`hebe teSHfe lomu
mewa`Il we'azman
removed 'dat/geez/eno/tot.1/raw.wfr'
creating the word frequency file dat/geez/eno/tot.1/raw.wfr
the 10 most common words in dat/geez/eno/tot.1/raw.tlw:
273 0.01499 keme
176 0.00966 mdr
170 0.00933 'Ile
147 0.00807 'Isme
139 0.00763 dibe
114 0.00626 w'Itu
113 0.00620 semay
113 0.00620 wste
107 0.00587 menafst
106 0.00582 'Iske
removed 'dat/geez/eno/tot.1/raw-whole-wds-summary.tex'
removed 'exp/geez/eno/tot.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/geez/eno/tot.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:30:43 by tex-make-sample-summary.sh
% Token and word counts for geez/eno/tot.1/raw.wfr
%
\def\geezenowholetotPBrawTks{18215}
\def\geezenowholetotPBrawTksPct{100.0}
\def\geezenowholetotPBrawWds{6356}
\def\geezenowholetotPBrawWdsPct{34.9}
copied '/tmp/561305.file' -> 'exp/geez/eno/tot.1/raw-whole-wds-summary.tex'
removed '/tmp/561305.file'
creating running text file dat/geez/eno/tot.1/gud.wdf
sample:
qale bereket zehEnok zekeme bareke `hruyane weSadqane 'Ile helewu ykunu
be`Ilete mndabE le'aseslo kWulu 'Ikuyan weresi`an we'aw`s'a weybE hEnok
b'Isi Sadq ze'Im`hebe Igzi'abHEr 'Inze 'a`Iyntihu k`sutat weyrE'i ra'Iye
qduse zebesemayat ze'ar'ayuni mela'Ikt wesema`Iku 'Im`hebEhomu kWulo
we'a'Imerku 'ane ze'IrE'i we'ako lez twld 'ala lezeymeS'I twld r`huqan
be'Inte `hruyan 'IbE we'aw`sa'Iku be'Inti'ahomu msle zeywe`S'I qdus
we`ebiy 'Ima`hderu we'amlake `alem we'Imhye ykeyd dibe sina debr
weyaster'i bet`Iyntu weyaster'i beSn`e `heylu 'Imsemay weyferh kWulu
weyadleqelqu tguhan weyne`s'omu frhet were`ad `ebiy 'Iske 'aSnafe mdr
weydeneg`Su 'adbar newa`han weytEHetu 'awgr newa`hat weytmesewu keme
me`are gra 'Imlahb wet`seTem mdr wekWulu zewste mdr ytHegWel weykewn ftH
la`Ile kWulu wela`Ile Sadqan kWulomu leSadqanse selame ygebr lomu
weye`eqbomu le`hruyan weykewn `sahl la`IlEhomu weykewnu kWulomu ze'amlak
wey`sErHu weytbareku weyherh lomu brhane 'amlak wenahu meS'a bet'Ilfet
qdusan keme ygber ftHe la`IlEhomu weyaHegWulomu leresi`an weytwaqes
kWulo ze`sga be'Inte kWulu zegebru wereseyu la`IlEhu `haT'an weresi`an
Teyequ kWulo zewste semay gbre 'Ifo 'iymeyTu fnawihomu brhanat zewste
semay keme kWulu y`serq weye`erb `sru`I kWulu bebezemenu we'iyt`edewu
'Imt'Izazomu r'Iywa lemdr welebwu be'Inte mgbar zeytgeber la`IlEha
'Imqedami 'Iske tefSamEtu keme iytmeyeT kWulu gbru le'amlak 'Inze
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
beSlmet ytwedeyu beSlmet Inze ytwe`hew`hu Sadqan weySerHu weyrE'Iywomu
`haT'An 'Inze yberhu weyeHewru Imuntuhi be`hebe teSHfe lomu mewa`Il
we'azman
removed 'dat/geez/eno/tot.1/gud.wfr'
creating the word frequency file dat/geez/eno/tot.1/gud.wfr
the 10 most common words in dat/geez/eno/tot.1/gud.tlw:
273 0.01539 keme
176 0.00992 mdr
170 0.00959 'Ile
147 0.00829 'Isme
139 0.00784 dibe
114 0.00643 w'Itu
113 0.00637 semay
113 0.00637 wste
107 0.00603 menafst
106 0.00598 'Iske
removed 'dat/geez/eno/tot.1/gud-whole-wds-summary.tex'
removed 'exp/geez/eno/tot.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/geez/eno/tot.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:30:43 by tex-make-sample-summary.sh
% Token and word counts for geez/eno/tot.1/gud.wfr
%
\def\geezenowholetotPBgudTks{17736}
\def\geezenowholetotPBgudTksPct{97.4}
\def\geezenowholetotPBgudWds{6274}
\def\geezenowholetotPBgudWdsPct{34.4}
copied '/tmp/561349.file' -> 'exp/geez/eno/tot.1/gud-whole-wds-summary.tex'
removed '/tmp/561349.file'
creating running text file dat/geez/eno/tot.1/bad.wdf
sample:
`10 we`4 `2 `3 `2`100 'urakibe*ramE'El le`2`100 bebe`30`100 `5`100 le`70
`10`100 `10 welele`1 `1 `4 `7 `3 we`3 we`1 we`1 `7 `1 `1 `1 `1 `1 `1 `7
`1 `1 we`4 `1 `1 `1 `3 `1 `7 `1 `1 `3 `1 dibe`1 we`3 `1 dibe`1 `1 `1 `1
`1 `7 `1 `1 lele`1 `3 bebe`1 be`2 `3 `3 `3 bebe`1 `3 we`1 webe`4 `4 `4
`4 `4 we`4 `1 `1 `1 `1 le`1 be`1 `1`1 `5`100 `1 `2 `1 we`1 `1 we`1`1
we`1 `2 `1 `1 `1 be`1 `1 be`1 `10 we`1 `10 we`2 `10 we`3 `10 we`4 `10
we`5 `10 we`6 `10 we`7 `10 we`8 `10 we`9 `20 `20 we`1 `100 `50 `10 `2 `2
`1 'Im`4 `1`1 `1`1 `1`1 `6 we`7 `1`1 `60 `30 `30 `10 `8 `30 `20 `10 we`1
`7 `30 we`1 `10 we`2 `60 `30 `30 `1 `10 we`1 `7 `30 `2 `10 `8 `30 we`1
`9 `9 `30 `30 `30 `10 `8 `30 `10 we`1 `7 `30 we`1 `10 we`2 `7 `30 `1 `1
`10 we`1 `7 `30 `10 `8 `30 we`1 `9 `9 `3`100 we`60 `60 `7 le`2 be`30 `30
`7 `1 'Im`10 we`4 `7 we`7 `7 we`7 `7 we`7 `10 we`5 be`1 `7`7 webebe`7`7
`1`1 webe`2 `2 `7 `5 `30 le`1 `5 `3`100 we`60 we`4 'Im`5 `30 `30
bebe`3`100 we`6 we`4 le`3 `10`100 we`90 we`2 wele`5 `10 we`8`100 we`20
le`8 `20 we`9`100 we`10 we`2 le`3 `10`100 we`8 we`2 wele`5 `50 dibe`8
we`2 le`5 `10 we`7`100 we`70 le`8 `20`100 we`8`100 we`30 we`2 le`8 `80
'Im`8 `80 `30 `4 `4 `1 we`1 we`1 we`1 bebe`3`100 we`8 we`4 `10 we`2 `10
we`2 we`1 `10 we`2 `3 we`3 we`3 we`3 we`3 we`3 we`3 we`3 be`4 `8 be`3
'Im`3 `4 `10 we`2 ze`4 `3 `1 `7 `7 `1 `2 `4 we`2 `2 we`5 `1 `4 `1 `2 `7
we`3 `3 `10 we`4 `10 we`3 `10 we`2 `10 we`1 `10 `9 `8 `7 `6 `5 webe`10
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
lele`1`1 lele`1`1 `1`1 `1`1 `1`1 `1 `1`1 `10 we`2 `3 `30 we`7 `20 we`3
`50 we`8 le`1 `1 `1 `10 we`2 `7 `1 `7 `70 `70 `1 be`1 `3 we`1 `1 be`2
be`2 `7 `7 `7 be`1 be`1 be`1 we`3 le`1 `10`1
removed 'dat/geez/eno/tot.1/bad.wfr'
creating the word frequency file dat/geez/eno/tot.1/bad.wfr
the 10 most common words in dat/geez/eno/tot.1/bad.tlw:
66 0.13779 `1
40 0.08351 `10
38 0.07933 we`1
26 0.05428 `7
24 0.05010 `30
22 0.04593 `4
21 0.04384 we`2
21 0.04384 we`3
20 0.04175 `3
13 0.02714 we`4
removed 'dat/geez/eno/tot.1/bad-whole-wds-summary.tex'
removed 'exp/geez/eno/tot.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/geez/eno/tot.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:30:43 by tex-make-sample-summary.sh
% Token and word counts for geez/eno/tot.1/bad.wfr
%
\def\geezenowholetotPBbadTks{479}
\def\geezenowholetotPBbadTksPct{2.6}
\def\geezenowholetotPBbadWds{82}
\def\geezenowholetotPBbadWdsPct{0.5}
copied '/tmp/561393.file' -> 'exp/geez/eno/tot.1/bad-whole-wds-summary.tex'
removed '/tmp/561393.file'
lines words bytes file
------- ------- --------- ------------
6356 19068 157086 dat/geez/eno/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
6274 18822 155279 dat/geez/eno/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
82 246 1807 dat/geez/eno/tot.1/bad.wfr
tot.1 raw = 18215 gud = 17736 bad = 479
=== creating the derived word files dat/engl/wow/*/{raw,gud,bad}.{tlw,wdf,wfr} (whole) ===
... creating word files dat/engl/wow/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
61191 dat/engl/wow/tot.1/whole.tlw
removed 'dat/engl/wow/tot.1/raw.tlw'
removed 'dat/engl/wow/tot.1/gud.tlw'
removed 'dat/engl/wow/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/engl/wow/tot.1/raw.wdf
sample:
no one would have believed in the last years of the nineteenth century
that this world was being watched keenly and closely by intelligences
greater than man's and yet as mortal as his own that as men busied
themselves about their various concerns they were scrutinised and
studied perhaps almost as narrowly as a man with a microscope might
scrutinise the transient creatures that swarm and multiply in a drop of
water with infinite complacency men went to and fro over this globe
about their little affairs serene in their assurance of their empire
over matter it is possible that the infusoria under the microscope do
the same no one gave a thought to the older worlds of space as sources
of human danger or thought of them only to dismiss the idea of life upon
them as impossible or improbable it is curious to recall some of the
mental habits of those departed days at most terrestrial men fancied
there might be other men upon mars perhaps inferior to themselves and
ready to welcome a missionary enterprise yet across the gulf of space
minds that are to our minds as ours are to those of the beasts that
perish intellects vast and cool and unsympathetic regarded this earth
with envious eyes and slowly and surely drew their plans against us and
early in the twentieth century came the great disillusionment =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
and strangest of all is it to hold my wife's hand again and to think
that i have counted her and that she has counted me among the dead =
removed 'dat/engl/wow/tot.1/raw.wfr'
creating the word frequency file dat/engl/wow/tot.1/raw.wfr
the 10 most common words in dat/engl/wow/tot.1/raw.tlw:
4764 0.07785 the
2502 0.04089 and
2292 0.03746 of
1635 0.02672 a
1268 0.02072 i
1175 0.01920 to
994 0.01624 in
884 0.01445 =
853 0.01394 was
772 0.01262 that
removed 'dat/engl/wow/tot.1/raw-whole-wds-summary.tex'
removed 'exp/engl/wow/tot.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/engl/wow/tot.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:30:43 by tex-make-sample-summary.sh
% Token and word counts for engl/wow/tot.1/raw.wfr
%
\def\englwowwholetotPBrawTks{61191}
\def\englwowwholetotPBrawTksPct{100.0}
\def\englwowwholetotPBrawWds{6799}
\def\englwowwholetotPBrawWdsPct{11.1}
copied '/tmp/561488.file' -> 'exp/engl/wow/tot.1/raw-whole-wds-summary.tex'
removed '/tmp/561488.file'
creating running text file dat/engl/wow/tot.1/gud.wdf
sample:
no one would have believed in the last years of the nineteenth century
that this world was being watched keenly and closely by intelligences
greater than man's and yet as mortal as his own that as men busied
themselves about their various concerns they were scrutinised and
studied perhaps almost as narrowly as a man with a microscope might
scrutinise the transient creatures that swarm and multiply in a drop of
water with infinite complacency men went to and fro over this globe
about their little affairs serene in their assurance of their empire
over matter it is possible that the infusoria under the microscope do
the same no one gave a thought to the older worlds of space as sources
of human danger or thought of them only to dismiss the idea of life upon
them as impossible or improbable it is curious to recall some of the
mental habits of those departed days at most terrestrial men fancied
there might be other men upon mars perhaps inferior to themselves and
ready to welcome a missionary enterprise yet across the gulf of space
minds that are to our minds as ours are to those of the beasts that
perish intellects vast and cool and unsympathetic regarded this earth
with envious eyes and slowly and surely drew their plans against us and
early in the twentieth century came the great disillusionment the planet
mars i scarcely need remind the reader revolves about the sun at a mean
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
bright and clear cut hard and silent under the dawn of that last great
day and strangest of all is it to hold my wife's hand again and to think
that i have counted her and that she has counted me among the dead
removed 'dat/engl/wow/tot.1/gud.wfr'
creating the word frequency file dat/engl/wow/tot.1/gud.wfr
the 10 most common words in dat/engl/wow/tot.1/gud.tlw:
4764 0.07901 the
2502 0.04150 and
2292 0.03801 of
1635 0.02712 a
1268 0.02103 i
1175 0.01949 to
994 0.01649 in
853 0.01415 was
772 0.01280 that
659 0.01093 it
removed 'dat/engl/wow/tot.1/gud-whole-wds-summary.tex'
removed 'exp/engl/wow/tot.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/engl/wow/tot.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:30:43 by tex-make-sample-summary.sh
% Token and word counts for engl/wow/tot.1/gud.wfr
%
\def\englwowwholetotPBgudTks{60293}
\def\englwowwholetotPBgudTksPct{98.5}
\def\englwowwholetotPBgudWds{6789}
\def\englwowwholetotPBgudWdsPct{11.1}
copied '/tmp/561532.file' -> 'exp/engl/wow/tot.1/gud-whole-wds-summary.tex'
removed '/tmp/561532.file'
creating running text file dat/engl/wow/tot.1/bad.wdf
sample:
=
140 000 000 =
=
35 000 000 =
=
=
=
1894 2 =
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/engl/wow/tot.1/bad.wfr'
creating the word frequency file dat/engl/wow/tot.1/bad.wfr
the 10 most common words in dat/engl/wow/tot.1/bad.tlw:
884 0.98441 =
6 0.00668 000
1 0.00111 10
1 0.00111 12
1 0.00111 140
1 0.00111 1893
1 0.00111 1894
1 0.00111 2
1 0.00111 35
1 0.00111 8th
removed 'dat/engl/wow/tot.1/bad-whole-wds-summary.tex'
removed 'exp/engl/wow/tot.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/engl/wow/tot.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:30:43 by tex-make-sample-summary.sh
% Token and word counts for engl/wow/tot.1/bad.wfr
%
\def\englwowwholetotPBbadTks{898}
\def\englwowwholetotPBbadTksPct{1.5}
\def\englwowwholetotPBbadWds{10}
\def\englwowwholetotPBbadWdsPct{0.0}
copied '/tmp/561576.file' -> 'exp/engl/wow/tot.1/bad-whole-wds-summary.tex'
removed '/tmp/561576.file'
lines words bytes file
------- ------- --------- ------------
6799 20397 163696 dat/engl/wow/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
6789 20367 163501 dat/engl/wow/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
10 30 195 dat/engl/wow/tot.1/bad.wfr
tot.1 raw = 61191 gud = 60293 bad = 898
=== creating the derived word files dat/engl/wnm/*/{raw,gud,bad}.{tlw,wdf,wfr} (whole) ===
... creating word files dat/engl/wnm/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
831 dat/engl/wnm/tot.1/whole.tlw
removed 'dat/engl/wnm/tot.1/raw.tlw'
removed 'dat/engl/wnm/tot.1/gud.tlw'
removed 'dat/engl/wnm/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
!! empty raw.tlw file '='
creating running text file dat/engl/wnm/tot.1/raw.wdf
sample:
mars mars mars mars mars tasmanians european martians martians
schiaparelli mars martians lick perrotin english august mars lavelle
java ogilvy ottershaw ogilvy ogilvy ogilvy mars ogilvy ottershaw
chertsey mars mars martians mars martians markham zodiac mars chertsey
isleworth winchester albin denning french ottershaw berkshire surrey
middlesex ogilvy horsell ottershaw woking weybridge ogilvy mars woking
horsell henderson london henderson henderson horsell henderson henderson
ogilvy henderson henderson london mars ottershaw henderson ogilvy
henderson's gregg england ogilvy henderson mars ogilvy mars maybury
london ogilvy's woking chobham woking chertsey ottershaw chobham
henderson ogilvy stent stent ogilvy hilton hilton london waterloo woking
stent's ogilvy woking stent martian gorgon chobham woking martians
woking chobham god woking woking chobham woking horsell martians ogilvy
stent henderson chertsey knaphill martians woking horsell martians
woking martians martians horsell maybury chobham woking ottershaw woking
horsell woking henderson martians stent stent ogilvy horsell martians
woking martians horsell maybury oriental mars mars ogilvy ogilvy
martians mars martian mars mars martians martian ogilvy's martians
mauritius friday friday woking stent london germany london henderson's
mars woking horsell chobham woking smith's mars londonwards horsell
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
stanmore stanmore george stanmore thames ostend blackwater shoeburyness
essex martian martian titan naze martians martians essex martian
martians martian martian's martian martian martian martian
removed 'dat/engl/wnm/tot.1/raw.wfr'
creating the word frequency file dat/engl/wnm/tot.1/raw.wfr
the 10 most common words in dat/engl/wnm/tot.1/raw.tlw:
89 0.10710 martians
48 0.05776 woking
37 0.04452 martian
36 0.04332 london
28 0.03369 mars
23 0.02768 horsell
22 0.02647 weybridge
20 0.02407 ogilvy
18 0.02166 chertsey
17 0.02046 maybury
removed 'dat/engl/wnm/tot.1/raw-whole-wds-summary.tex'
removed 'exp/engl/wnm/tot.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/engl/wnm/tot.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:30:43 by tex-make-sample-summary.sh
% Token and word counts for engl/wnm/tot.1/raw.wfr
%
\def\englwnmwholetotPBrawTks{831}
\def\englwnmwholetotPBrawTksPct{100.0}
\def\englwnmwholetotPBrawWds{194}
\def\englwnmwholetotPBrawWdsPct{23.3}
copied '/tmp/561673.file' -> 'exp/engl/wnm/tot.1/raw-whole-wds-summary.tex'
removed '/tmp/561673.file'
creating running text file dat/engl/wnm/tot.1/gud.wdf
sample:
mars mars mars mars mars tasmanians european martians martians
schiaparelli mars martians lick perrotin english august mars lavelle
java ogilvy ottershaw ogilvy ogilvy ogilvy mars ogilvy ottershaw
chertsey mars mars martians mars martians markham zodiac mars chertsey
isleworth winchester albin denning french ottershaw berkshire surrey
middlesex ogilvy horsell ottershaw woking weybridge ogilvy mars woking
horsell henderson london henderson henderson horsell henderson henderson
ogilvy henderson henderson london mars ottershaw henderson ogilvy
henderson's gregg england ogilvy henderson mars ogilvy mars maybury
london ogilvy's woking chobham woking chertsey ottershaw chobham
henderson ogilvy stent stent ogilvy hilton hilton london waterloo woking
stent's ogilvy woking stent martian gorgon chobham woking martians
woking chobham god woking woking chobham woking horsell martians ogilvy
stent henderson chertsey knaphill martians woking horsell martians
woking martians martians horsell maybury chobham woking ottershaw woking
horsell woking henderson martians stent stent ogilvy horsell martians
woking martians horsell maybury oriental mars mars ogilvy ogilvy
martians mars martian mars mars martians martian ogilvy's martians
mauritius friday friday woking stent london germany london henderson's
mars woking horsell chobham woking smith's mars londonwards horsell
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
stanmore stanmore george stanmore thames ostend blackwater shoeburyness
essex martian martian titan naze martians martians essex martian
martians martian martian's martian martian martian martian
removed 'dat/engl/wnm/tot.1/gud.wfr'
creating the word frequency file dat/engl/wnm/tot.1/gud.wfr
the 10 most common words in dat/engl/wnm/tot.1/gud.tlw:
89 0.10710 martians
48 0.05776 woking
37 0.04452 martian
36 0.04332 london
28 0.03369 mars
23 0.02768 horsell
22 0.02647 weybridge
20 0.02407 ogilvy
18 0.02166 chertsey
17 0.02046 maybury
removed 'dat/engl/wnm/tot.1/gud-whole-wds-summary.tex'
removed 'exp/engl/wnm/tot.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/engl/wnm/tot.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:30:43 by tex-make-sample-summary.sh
% Token and word counts for engl/wnm/tot.1/gud.wfr
%
\def\englwnmwholetotPBgudTks{831}
\def\englwnmwholetotPBgudTksPct{100.0}
\def\englwnmwholetotPBgudWds{194}
\def\englwnmwholetotPBgudWdsPct{23.3}
copied '/tmp/561717.file' -> 'exp/engl/wnm/tot.1/gud-whole-wds-summary.tex'
removed '/tmp/561717.file'
creating running text file dat/engl/wnm/tot.1/bad.wdf
sample:
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
removed 'dat/engl/wnm/tot.1/bad.wfr'
creating the word frequency file dat/engl/wnm/tot.1/bad.wfr
the 10 most common words in dat/engl/wnm/tot.1/bad.tlw:
removed 'dat/engl/wnm/tot.1/bad-whole-wds-summary.tex'
removed 'exp/engl/wnm/tot.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/engl/wnm/tot.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:30:43 by tex-make-sample-summary.sh
% Token and word counts for engl/wnm/tot.1/bad.wfr
%
\def\englwnmwholetotPBbadTks{0}
\def\englwnmwholetotPBbadTksPct{0.0}
\def\englwnmwholetotPBbadWds{0}
\def\englwnmwholetotPBbadWdsPct{0.0}
copied '/tmp/561761.file' -> 'exp/engl/wnm/tot.1/bad-whole-wds-summary.tex'
removed '/tmp/561761.file'
lines words bytes file
------- ------- --------- ------------
194 582 4698 dat/engl/wnm/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
194 582 4698 dat/engl/wnm/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
0 0 0 dat/engl/wnm/tot.1/bad.wfr
tot.1 raw = 831 gud = 831 bad = 0
=== creating the derived word files dat/engl/cul/*/{raw,gud,bad}.{tlw,wdf,wfr} (whole) ===
... creating word files dat/engl/cul/pre.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
2824 dat/engl/cul/pre.1/whole.tlw
removed 'dat/engl/cul/pre.1/raw.tlw'
removed 'dat/engl/cul/pre.1/gud.tlw'
removed 'dat/engl/cul/pre.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/engl/cul/pre.1/raw.wdf
sample:
courteous reader =
aristotle in his metaphysicks writing of the nature of man hit the nail
on the head when he said that man is naturally enclined to and desirous
of knowledg and indeed it is palpable and apparent that as pride is the
first visible sin in a child whereby we may gather that it was the first
sin of adam so knowledg being the first vertue a child minds as is
apparent to them that do but with the eye of reason heed their actions
even whilst they are very yong even before they are a yeer old even by
natural instinct whereby a man may more than guess that knowledg was the
greatest loss or at least one of the greatest we lost by the fall of
adam knowledg saith aristotle is in prosperity an ornament in adversity
a refuge and truly there is almost no greater enemy to knowledg in the
world that pride and covetousness excellently said juvenal sat° 7 =
*{scire} ..*{=} and again some men are so damnable proud and envious
withal that they would have no body know any thing but themselves the
one i hope will shortly learn better manners and the other be a burden
too heavy for the earth long to bear =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
the book either through my own forgetfulness or my amanuensis was
omitted and here i shal give it you plainly without any circumstances =
removed 'dat/engl/cul/pre.1/raw.wfr'
creating the word frequency file dat/engl/cul/pre.1/raw.wfr
the 10 most common words in dat/engl/cul/pre.1/raw.tlw:
180 0.06374 the
133 0.04710 of
103 0.03647 and
79 0.02797 in
73 0.02585 to
50 0.01771 that
49 0.01735 a
45 0.01593 i
38 0.01346 it
32 0.01133 by
removed 'dat/engl/cul/pre.1/raw-whole-wds-summary.tex'
removed 'exp/engl/cul/pre.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/engl/cul/pre.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:30:44 by tex-make-sample-summary.sh
% Token and word counts for engl/cul/pre.1/raw.wfr
%
\def\englculwholeprePBrawTks{2824}
\def\englculwholeprePBrawTksPct{100.0}
\def\englculwholeprePBrawWds{799}
\def\englculwholeprePBrawWdsPct{28.3}
copied '/tmp/561856.file' -> 'exp/engl/cul/pre.1/raw-whole-wds-summary.tex'
removed '/tmp/561856.file'
creating running text file dat/engl/cul/pre.1/gud.wdf
sample:
courteous reader aristotle in his metaphysicks writing of the nature of
man hit the nail on the head when he said that man is naturally enclined
to and desirous of knowledg and indeed it is palpable and apparent that
as pride is the first visible sin in a child whereby we may gather that
it was the first sin of adam so knowledg being the first vertue a child
minds as is apparent to them that do but with the eye of reason heed
their actions even whilst they are very yong even before they are a yeer
old even by natural instinct whereby a man may more than guess that
knowledg was the greatest loss or at least one of the greatest we lost
by the fall of adam knowledg saith aristotle is in prosperity an
ornament in adversity a refuge and truly there is almost no greater
enemy to knowledg in the world that pride and covetousness excellently
said juvenal and again some men are so damnable proud and envious withal
that they would have no body know any thing but themselves the one i
hope will shortly learn better manners and the other be a burden too
heavy for the earth long to bear the subject which i here fixed my
thoughts upon is not only the description and nature of herbs which had
it been all i had authority sufficient to bear me out in it for solomon
employed part of that wisdom he asked and received of god in searching
after them which he wrote in books even of all herbs plants and trees
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
another herb of the same planet which in the book either through my own
forgetfulness or my amanuensis was omitted and here i shal give it you
plainly without any circumstances
removed 'dat/engl/cul/pre.1/gud.wfr'
creating the word frequency file dat/engl/cul/pre.1/gud.wfr
the 10 most common words in dat/engl/cul/pre.1/gud.tlw:
180 0.06515 the
133 0.04814 of
103 0.03728 and
79 0.02859 in
73 0.02642 to
50 0.01810 that
49 0.01773 a
45 0.01629 i
38 0.01375 it
32 0.01158 by
removed 'dat/engl/cul/pre.1/gud-whole-wds-summary.tex'
removed 'exp/engl/cul/pre.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/engl/cul/pre.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:30:44 by tex-make-sample-summary.sh
% Token and word counts for engl/cul/pre.1/gud.wfr
%
\def\englculwholeprePBgudTks{2763}
\def\englculwholeprePBgudTksPct{97.8}
\def\englculwholeprePBgudWds{778}
\def\englculwholeprePBgudWdsPct{27.5}
copied '/tmp/561900.file' -> 'exp/engl/cul/pre.1/gud-whole-wds-summary.tex'
removed '/tmp/561900.file'
creating running text file dat/engl/cul/pre.1/bad.wdf
sample:
=
sat° 7 =
*{scire} ..*{=} =
=
=
*{ad} ..*{=} viz° =
*{ipse} ..*{=} =
&c° &c° &c° dr° dr° dr° mr° =
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/engl/cul/pre.1/bad.wfr'
creating the word frequency file dat/engl/cul/pre.1/bad.wfr
the 10 most common words in dat/engl/cul/pre.1/bad.tlw:
28 0.45902 =
6 0.09836 ..*{=}
5 0.08197 &c°
3 0.04918 dr°
2 0.03279 1
2 0.03279 viz°
1 0.01639 &c
1 0.01639 *{1}
1 0.01639 *{ad}
1 0.01639 *{excideret}
removed 'dat/engl/cul/pre.1/bad-whole-wds-summary.tex'
removed 'exp/engl/cul/pre.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/engl/cul/pre.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:30:44 by tex-make-sample-summary.sh
% Token and word counts for engl/cul/pre.1/bad.wfr
%
\def\englculwholeprePBbadTks{61}
\def\englculwholeprePBbadTksPct{2.2}
\def\englculwholeprePBbadWds{21}
\def\englculwholeprePBbadWdsPct{0.7}
copied '/tmp/561944.file' -> 'exp/engl/cul/pre.1/bad-whole-wds-summary.tex'
removed '/tmp/561944.file'
... creating word files dat/engl/cul/her.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
116329 dat/engl/cul/her.1/whole.tlw
removed 'dat/engl/cul/her.1/raw.tlw'
removed 'dat/engl/cul/her.1/gud.tlw'
removed 'dat/engl/cul/her.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/engl/cul/her.1/raw.wdf
sample:
*{description} ..*{=} this small herb hath but one leaf which grows with
the stalk a fingers length above the ground being fat and of a fresh
green colour broad like the water plantane but less without any middle
rib in it from the bottom of which leaf on the inside riseth up
ordinarily one somtimes two or three small slender stalks the upper half
wherof is somwhat bigger and dented with smal round dents of a yellowish
green colour like the tongue of an adder or serpent only this is as
useful as they are formidable the root continues all the year =
*{place} ..*{=} it groweth in moist meadows and such like places =
*{time} ..*{=} and is to be found in april and may for it quickly
perisheth with a little heat =
*{vertues} ..*{=} it is temperate in respect of heat but dry in the
second degree the juyce of the leaves drunk with the distilled water of
horstail is a singular remedy for all manner of wounds in the breast
bowels or other parts of the body and is given with good success unto
those who are troubled with casting vomiting or bleeding at the mouth or
nose or otherwise downwards the said juyce given in the distilled water
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
master chyron the centaure and certainly a very profitable herb it is in
the camp and perhaps therfore called militaris =
removed 'dat/engl/cul/her.1/raw.wfr'
creating the word frequency file dat/engl/cul/her.1/raw.wfr
the 10 most common words in dat/engl/cul/her.1/raw.tlw:
9672 0.08314 the
6303 0.05418 and
4089 0.03515 of
2868 0.02465 in
2178 0.01872 to
2165 0.01861 it
2135 0.01835 or
1942 0.01669 is
1821 0.01565 a
1298 0.01116 =
removed 'dat/engl/cul/her.1/raw-whole-wds-summary.tex'
removed 'exp/engl/cul/her.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/engl/cul/her.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:30:44 by tex-make-sample-summary.sh
% Token and word counts for engl/cul/her.1/raw.wfr
%
\def\englculwholeherPBrawTks{116329}
\def\englculwholeherPBrawTksPct{100.0}
\def\englculwholeherPBrawWds{5855}
\def\englculwholeherPBrawWdsPct{5.0}
copied '/tmp/561998.file' -> 'exp/engl/cul/her.1/raw-whole-wds-summary.tex'
removed '/tmp/561998.file'
creating running text file dat/engl/cul/her.1/gud.wdf
sample:
this small herb hath but one leaf which grows with the stalk a fingers
length above the ground being fat and of a fresh green colour broad like
the water plantane but less without any middle rib in it from the bottom
of which leaf on the inside riseth up ordinarily one somtimes two or
three small slender stalks the upper half wherof is somwhat bigger and
dented with smal round dents of a yellowish green colour like the tongue
of an adder or serpent only this is as useful as they are formidable the
root continues all the year it groweth in moist meadows and such like
places and is to be found in april and may for it quickly perisheth with
a little heat it is temperate in respect of heat but dry in the second
degree the juyce of the leaves drunk with the distilled water of
horstail is a singular remedy for all manner of wounds in the breast
bowels or other parts of the body and is given with good success unto
those who are troubled with casting vomiting or bleeding at the mouth or
nose or otherwise downwards the said juyce given in the distilled water
of oaken buds is very good for women who have their usual courses or the
whites flowing down too abundantly it helps sore eyes the leaves infused
or boyled in oyl omphacine or unripe olives set in the sun for certain
daies or the green leaves sufficiently boyled in the said oyl is made an
excellent green balsom not only for green and fresh wounds but also for
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
to posterity having learned them of his master chyron the centaure and
certainly a very profitable herb it is in the camp and perhaps therfore
called militaris
removed 'dat/engl/cul/her.1/gud.wfr'
creating the word frequency file dat/engl/cul/her.1/gud.wfr
the 10 most common words in dat/engl/cul/her.1/gud.tlw:
9672 0.08582 the
6303 0.05593 and
4089 0.03628 of
2868 0.02545 in
2178 0.01933 to
2165 0.01921 it
2135 0.01894 or
1942 0.01723 is
1821 0.01616 a
1232 0.01093 with
removed 'dat/engl/cul/her.1/gud-whole-wds-summary.tex'
removed 'exp/engl/cul/her.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/engl/cul/her.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:30:44 by tex-make-sample-summary.sh
% Token and word counts for engl/cul/her.1/gud.wfr
%
\def\englculwholeherPBgudTks{112695}
\def\englculwholeherPBgudTksPct{96.9}
\def\englculwholeherPBgudWds{5685}
\def\englculwholeherPBgudWdsPct{4.9}
copied '/tmp/562042.file' -> 'exp/engl/cul/her.1/gud-whole-wds-summary.tex'
removed '/tmp/562042.file'
creating running text file dat/engl/cul/her.1/bad.wdf
sample:
*{description} ..*{=} =
*{place} ..*{=} =
*{time} ..*{=} =
*{vertues} ..*{=} =
*{wounds} ..*{.} =
viz° &c° 1651 =
=
*{description} ..*{=} =
*{place} ..*{=} =
*{time} ..*{=} =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
*{vertues} ..*{=} =
removed 'dat/engl/cul/her.1/bad.wfr'
creating the word frequency file dat/engl/cul/her.1/bad.wfr
the 10 most common words in dat/engl/cul/her.1/bad.tlw:
1298 0.35718 =
867 0.23858 ..*{=}
262 0.07210 *{vertues}
228 0.06274 ..*{.}
203 0.05586 *{place}
199 0.05476 *{time}
139 0.03825 *{description}
35 0.00963 st°
28 0.00771 &c°
27 0.00743 viz°
removed 'dat/engl/cul/her.1/bad-whole-wds-summary.tex'
removed 'exp/engl/cul/her.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/engl/cul/her.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:30:44 by tex-make-sample-summary.sh
% Token and word counts for engl/cul/her.1/bad.wfr
%
\def\englculwholeherPBbadTks{3634}
\def\englculwholeherPBbadTksPct{3.1}
\def\englculwholeherPBbadWds{170}
\def\englculwholeherPBbadWdsPct{0.1}
copied '/tmp/562086.file' -> 'exp/engl/cul/her.1/bad-whole-wds-summary.tex'
removed '/tmp/562086.file'
... creating word files dat/engl/cul/rec.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
7084 dat/engl/cul/rec.1/whole.tlw
removed 'dat/engl/cul/rec.1/raw.tlw'
removed 'dat/engl/cul/rec.1/gud.tlw'
removed 'dat/engl/cul/rec.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/engl/cul/rec.1/raw.wdf
sample:
1 of leaves chuse only such as are green and full of juyce pick them
carefully and cast away such as are any way declining for they will
putrifie the rest so shall one handful be worth ten of those you buy in
cheap side =
2 note in what place they most delight to grow in and gather them there
for bettony that grows in the shadow is far better than that which grows
in the sun because it delights in the shadow so also such herbs as
delight to grow neer the water though happily you may find some of them
upon dry ground the treatise will inform you where every herb delights
to grow =
3 the leaves of such herbs as run up to seed are not so good when they
are in flower as before some few excepted the leaves of which are seldom
or never used in such cases if through ignorance they were not known or
through negligence forgotten you had better take the top and the flower
than the leaf =
4 dry them well in the sun and not in the shadow as the swinge of
physitians is for if the sun draw away the vertues of herbs it must
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
*{mr°} ..*{=} my answer to the letter was to this effect =
*{sir} ..*{=}
removed 'dat/engl/cul/rec.1/raw.wfr'
creating the word frequency file dat/engl/cul/rec.1/raw.wfr
the 10 most common words in dat/engl/cul/rec.1/raw.tlw:
377 0.05322 the
244 0.03444 of
214 0.03021 and
175 0.02470 a
171 0.02414 in
166 0.02343 to
150 0.02117 =
149 0.02103 it
141 0.01990 you
124 0.01750 as
removed 'dat/engl/cul/rec.1/raw-whole-wds-summary.tex'
removed 'exp/engl/cul/rec.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/engl/cul/rec.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:30:44 by tex-make-sample-summary.sh
% Token and word counts for engl/cul/rec.1/raw.wfr
%
\def\englculwholerecPBrawTks{7084}
\def\englculwholerecPBrawTksPct{100.0}
\def\englculwholerecPBrawWds{1260}
\def\englculwholerecPBrawWdsPct{17.8}
copied '/tmp/562140.file' -> 'exp/engl/cul/rec.1/raw-whole-wds-summary.tex'
removed '/tmp/562140.file'
creating running text file dat/engl/cul/rec.1/gud.wdf
sample:
of leaves chuse only such as are green and full of juyce pick them
carefully and cast away such as are any way declining for they will
putrifie the rest so shall one handful be worth ten of those you buy in
cheap side note in what place they most delight to grow in and gather
them there for bettony that grows in the shadow is far better than that
which grows in the sun because it delights in the shadow so also such
herbs as delight to grow neer the water though happily you may find some
of them upon dry ground the treatise will inform you where every herb
delights to grow the leaves of such herbs as run up to seed are not so
good when they are in flower as before some few excepted the leaves of
which are seldom or never used in such cases if through ignorance they
were not known or through negligence forgotten you had better take the
top and the flower than the leaf dry them well in the sun and not in the
shadow as the swinge of physitians is for if the sun draw away the
vertues of herbs it must needs do the like by hay by the same rule which
the experience of every country farmer will explode for a notable piece
of non sense such as are artists in astrology and indeed none else are
fit to make physitians such i advise let the planet that governs the
herb be angular and the stronger the better if they can in herbs of
saturn let saturn be in the ascendent in the herbs of mars let mars be
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
of bedfordhsire from a gentleman at that time altogether to me unknown
though since well known who was a student both in astrologie and physick
the words which are these my answer to the letter was to this effect
removed 'dat/engl/cul/rec.1/gud.wfr'
creating the word frequency file dat/engl/cul/rec.1/gud.wfr
the 10 most common words in dat/engl/cul/rec.1/gud.tlw:
377 0.05568 the
244 0.03604 of
214 0.03161 and
175 0.02585 a
171 0.02525 in
166 0.02452 to
149 0.02201 it
141 0.02082 you
124 0.01831 as
113 0.01669 them
removed 'dat/engl/cul/rec.1/gud-whole-wds-summary.tex'
removed 'exp/engl/cul/rec.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/engl/cul/rec.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:30:44 by tex-make-sample-summary.sh
% Token and word counts for engl/cul/rec.1/gud.wfr
%
\def\englculwholerecPBgudTks{6771}
\def\englculwholerecPBgudTksPct{95.6}
\def\englculwholerecPBgudWds{1240}
\def\englculwholerecPBgudWdsPct{17.5}
copied '/tmp/562184.file' -> 'exp/engl/cul/rec.1/gud-whole-wds-summary.tex'
removed '/tmp/562184.file'
creating running text file dat/engl/cul/rec.1/bad.wdf
sample:
1 =
2 =
3 =
4 =
5 =
6 =
7 =
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
*{mr°} ..*{=} =
*{sir} ..*{=}
removed 'dat/engl/cul/rec.1/bad.wfr'
creating the word frequency file dat/engl/cul/rec.1/bad.wfr
the 10 most common words in dat/engl/cul/rec.1/bad.tlw:
150 0.47923 =
22 0.07029 1
22 0.07029 2
20 0.06390 3
17 0.05431 4
14 0.04473 5
13 0.04153 &c°
10 0.03195 ..*{=}
10 0.03195 6
8 0.02556 *{1}
removed 'dat/engl/cul/rec.1/bad-whole-wds-summary.tex'
removed 'exp/engl/cul/rec.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/engl/cul/rec.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:30:44 by tex-make-sample-summary.sh
% Token and word counts for engl/cul/rec.1/bad.wfr
%
\def\englculwholerecPBbadTks{313}
\def\englculwholerecPBbadTksPct{4.4}
\def\englculwholerecPBbadWds{20}
\def\englculwholerecPBbadWdsPct{0.3}
copied '/tmp/562228.file' -> 'exp/engl/cul/rec.1/bad-whole-wds-summary.tex'
removed '/tmp/562228.file'
... creating word files dat/engl/cul/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
126237 dat/engl/cul/tot.1/whole.tlw
removed 'dat/engl/cul/tot.1/raw.tlw'
removed 'dat/engl/cul/tot.1/gud.tlw'
removed 'dat/engl/cul/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/engl/cul/tot.1/raw.wdf
sample:
courteous reader =
aristotle in his metaphysicks writing of the nature of man hit the nail
on the head when he said that man is naturally enclined to and desirous
of knowledg and indeed it is palpable and apparent that as pride is the
first visible sin in a child whereby we may gather that it was the first
sin of adam so knowledg being the first vertue a child minds as is
apparent to them that do but with the eye of reason heed their actions
even whilst they are very yong even before they are a yeer old even by
natural instinct whereby a man may more than guess that knowledg was the
greatest loss or at least one of the greatest we lost by the fall of
adam knowledg saith aristotle is in prosperity an ornament in adversity
a refuge and truly there is almost no greater enemy to knowledg in the
world that pride and covetousness excellently said juvenal sat° 7 =
*{scire} ..*{=} and again some men are so damnable proud and envious
withal that they would have no body know any thing but themselves the
one i hope will shortly learn better manners and the other be a burden
too heavy for the earth long to bear =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
*{mr°} ..*{=} my answer to the letter was to this effect =
*{sir} ..*{=}
removed 'dat/engl/cul/tot.1/raw.wfr'
creating the word frequency file dat/engl/cul/tot.1/raw.wfr
the 10 most common words in dat/engl/cul/tot.1/raw.tlw:
10229 0.08103 the
6620 0.05244 and
4466 0.03538 of
3118 0.02470 in
2417 0.01915 to
2352 0.01863 it
2203 0.01745 or
2071 0.01641 is
2045 0.01620 a
1476 0.01169 =
removed 'dat/engl/cul/tot.1/raw-whole-wds-summary.tex'
removed 'exp/engl/cul/tot.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/engl/cul/tot.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:30:44 by tex-make-sample-summary.sh
% Token and word counts for engl/cul/tot.1/raw.wfr
%
\def\englculwholetotPBrawTks{126237}
\def\englculwholetotPBrawTksPct{100.0}
\def\englculwholetotPBrawWds{6379}
\def\englculwholetotPBrawWdsPct{5.1}
copied '/tmp/562282.file' -> 'exp/engl/cul/tot.1/raw-whole-wds-summary.tex'
removed '/tmp/562282.file'
creating running text file dat/engl/cul/tot.1/gud.wdf
sample:
courteous reader aristotle in his metaphysicks writing of the nature of
man hit the nail on the head when he said that man is naturally enclined
to and desirous of knowledg and indeed it is palpable and apparent that
as pride is the first visible sin in a child whereby we may gather that
it was the first sin of adam so knowledg being the first vertue a child
minds as is apparent to them that do but with the eye of reason heed
their actions even whilst they are very yong even before they are a yeer
old even by natural instinct whereby a man may more than guess that
knowledg was the greatest loss or at least one of the greatest we lost
by the fall of adam knowledg saith aristotle is in prosperity an
ornament in adversity a refuge and truly there is almost no greater
enemy to knowledg in the world that pride and covetousness excellently
said juvenal and again some men are so damnable proud and envious withal
that they would have no body know any thing but themselves the one i
hope will shortly learn better manners and the other be a burden too
heavy for the earth long to bear the subject which i here fixed my
thoughts upon is not only the description and nature of herbs which had
it been all i had authority sufficient to bear me out in it for solomon
employed part of that wisdom he asked and received of god in searching
after them which he wrote in books even of all herbs plants and trees
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
of bedfordhsire from a gentleman at that time altogether to me unknown
though since well known who was a student both in astrologie and physick
the words which are these my answer to the letter was to this effect
removed 'dat/engl/cul/tot.1/gud.wfr'
creating the word frequency file dat/engl/cul/tot.1/gud.wfr
the 10 most common words in dat/engl/cul/tot.1/gud.tlw:
10229 0.08369 the
6620 0.05416 and
4466 0.03654 of
3118 0.02551 in
2417 0.01977 to
2352 0.01924 it
2203 0.01802 or
2071 0.01694 is
2045 0.01673 a
1290 0.01055 with
removed 'dat/engl/cul/tot.1/gud-whole-wds-summary.tex'
removed 'exp/engl/cul/tot.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/engl/cul/tot.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:30:44 by tex-make-sample-summary.sh
% Token and word counts for engl/cul/tot.1/gud.wfr
%
\def\englculwholetotPBgudTks{122229}
\def\englculwholetotPBgudTksPct{96.8}
\def\englculwholetotPBgudWds{6193}
\def\englculwholetotPBgudWdsPct{4.9}
copied '/tmp/562326.file' -> 'exp/engl/cul/tot.1/gud-whole-wds-summary.tex'
removed '/tmp/562326.file'
creating running text file dat/engl/cul/tot.1/bad.wdf
sample:
=
sat° 7 =
*{scire} ..*{=} =
=
=
*{ad} ..*{=} viz° =
*{ipse} ..*{=} =
&c° &c° &c° dr° dr° dr° mr° =
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
*{mr°} ..*{=} =
*{sir} ..*{=}
removed 'dat/engl/cul/tot.1/bad.wfr'
creating the word frequency file dat/engl/cul/tot.1/bad.wfr
the 10 most common words in dat/engl/cul/tot.1/bad.tlw:
1476 0.36826 =
883 0.22031 ..*{=}
262 0.06537 *{vertues}
228 0.05689 ..*{.}
203 0.05065 *{place}
199 0.04965 *{time}
139 0.03468 *{description}
46 0.01148 &c°
35 0.00873 st°
35 0.00873 viz°
removed 'dat/engl/cul/tot.1/bad-whole-wds-summary.tex'
removed 'exp/engl/cul/tot.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/engl/cul/tot.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:30:44 by tex-make-sample-summary.sh
% Token and word counts for engl/cul/tot.1/bad.wfr
%
\def\englculwholetotPBbadTks{4008}
\def\englculwholetotPBbadTksPct{3.2}
\def\englculwholetotPBbadWds{186}
\def\englculwholetotPBbadWdsPct{0.1}
copied '/tmp/562370.file' -> 'exp/engl/cul/tot.1/bad-whole-wds-summary.tex'
removed '/tmp/562370.file'
lines words bytes file
------- ------- --------- ------------
799 2397 18379 dat/engl/cul/pre.1/raw.wfr
5855 17565 139485 dat/engl/cul/her.1/raw.wfr
1260 3780 28823 dat/engl/cul/rec.1/raw.wfr
6379 19137 152117 dat/engl/cul/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
778 2334 17930 dat/engl/cul/pre.1/gud.wfr
5685 17055 135139 dat/engl/cul/her.1/gud.wfr
1240 3720 28433 dat/engl/cul/rec.1/gud.wfr
6193 18579 147418 dat/engl/cul/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
21 63 449 dat/engl/cul/pre.1/bad.wfr
170 510 4346 dat/engl/cul/her.1/bad.wfr
20 60 390 dat/engl/cul/rec.1/bad.wfr
186 558 4699 dat/engl/cul/tot.1/bad.wfr
pre.1 raw = 2824 gud = 2763 bad = 61
her.1 raw = 116329 gud = 112695 bad = 3634
rec.1 raw = 7084 gud = 6771 bad = 313
tot.1 raw = 126237 gud = 122229 bad = 4008
=== creating the derived word files dat/engl/cpn/*/{raw,gud,bad}.{tlw,wdf,wfr} (whole) ===
... creating word files dat/engl/cpn/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
544 dat/engl/cpn/tot.1/whole.tlw
removed 'dat/engl/cpn/tot.1/raw.tlw'
removed 'dat/engl/cpn/tot.1/gud.tlw'
removed 'dat/engl/cpn/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/engl/cpn/tot.1/raw.wdf
sample:
adders tongue agrimony alehoof ground ivy alexander black alder tree
common alder tree angelica apples arrach wild stinking archangel arsmart
asarabacca asparagus sparagus sperage prickly asparagus sparagus sperage
ash tree avens balm barberry barly garden bazil sweet bazil bay tree
beans french beans ladies bedstraw beets water betony wood betony beech
tree bilberries som whorts whortleberries bifoyl twayblade birch tree
birds foot bishops weed bistort snakeweed one blade bramble black berry
bush blites borrage bugloss bluebottles briony wild vine brooklime
butchers broom broom broomrape buck horn plantane bugle burnet butter
bur bur dock cabbages coleworts sea colewort calamint mountain mint
chamomel campions wild carrots caraway celandine lesser celondine of
pilewort ordinary small centaury cherry tree winter cherries chervil
sweet chervil sweet cicely chickweed cich peas cicers cinkfoyl five
leaved grass in five finger'd grass clary cleavers goosgrass clowns
woundwort cocks head columbines coltsfoot foalsfoot comfry costmary
alecost cudweed cottonweed cowslips sciatica cresses water cresses
crosswort crowfoot cuckowpint wake robin daisies dandelyon vulgarly piss
a beds darnel dill devils bit dock dodder of time epithimum other
dodders dogs grass quich grass dovesfoot cranes bill ducksmeat down
cotton thistle elder tree dwarf elder elm tree endive elecampane eringo
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
valerian vervain vine violets vipers bugloss wall flowers winter gilly
flowers walnut tree wold weld dyers weed wheat willow tree woad woodbine
honey suckles wormwood yarrow
removed 'dat/engl/cpn/tot.1/raw.wfr'
creating the word frequency file dat/engl/cpn/tot.1/raw.wfr
the 10 most common words in dat/engl/cpn/tot.1/raw.tlw:
18 0.03309 tree
7 0.01287 grass
6 0.01103 thistle
5 0.00919 garden
5 0.00919 of
5 0.00919 sweet
5 0.00919 water
5 0.00919 winter
4 0.00735 herb
4 0.00735 mustard
removed 'dat/engl/cpn/tot.1/raw-whole-wds-summary.tex'
removed 'exp/engl/cpn/tot.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/engl/cpn/tot.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:30:45 by tex-make-sample-summary.sh
% Token and word counts for engl/cpn/tot.1/raw.wfr
%
\def\englcpnwholetotPBrawTks{544}
\def\englcpnwholetotPBrawTksPct{100.0}
\def\englcpnwholetotPBrawWds{402}
\def\englcpnwholetotPBrawWdsPct{73.9}
copied '/tmp/562510.file' -> 'exp/engl/cpn/tot.1/raw-whole-wds-summary.tex'
removed '/tmp/562510.file'
creating running text file dat/engl/cpn/tot.1/gud.wdf
sample:
adders tongue agrimony alehoof ground ivy alexander black alder tree
common alder tree angelica apples arrach wild stinking archangel arsmart
asarabacca asparagus sparagus sperage prickly asparagus sparagus sperage
ash tree avens balm barberry barly garden bazil sweet bazil bay tree
beans french beans ladies bedstraw beets water betony wood betony beech
tree bilberries som whorts whortleberries bifoyl twayblade birch tree
birds foot bishops weed bistort snakeweed one blade bramble black berry
bush blites borrage bugloss bluebottles briony wild vine brooklime
butchers broom broom broomrape buck horn plantane bugle burnet butter
bur bur dock cabbages coleworts sea colewort calamint mountain mint
chamomel campions wild carrots caraway celandine lesser celondine of
pilewort ordinary small centaury cherry tree winter cherries chervil
sweet chervil sweet cicely chickweed cich peas cicers cinkfoyl five
leaved grass in five finger'd grass clary cleavers goosgrass clowns
woundwort cocks head columbines coltsfoot foalsfoot comfry costmary
alecost cudweed cottonweed cowslips sciatica cresses water cresses
crosswort crowfoot cuckowpint wake robin daisies dandelyon vulgarly piss
a beds darnel dill devils bit dock dodder of time epithimum other
dodders dogs grass quich grass dovesfoot cranes bill ducksmeat down
cotton thistle elder tree dwarf elder elm tree endive elecampane eringo
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
valerian vervain vine violets vipers bugloss wall flowers winter gilly
flowers walnut tree wold weld dyers weed wheat willow tree woad woodbine
honey suckles wormwood yarrow
removed 'dat/engl/cpn/tot.1/gud.wfr'
creating the word frequency file dat/engl/cpn/tot.1/gud.wfr
the 10 most common words in dat/engl/cpn/tot.1/gud.tlw:
18 0.03327 tree
7 0.01294 grass
6 0.01109 thistle
5 0.00924 garden
5 0.00924 of
5 0.00924 sweet
5 0.00924 water
5 0.00924 winter
4 0.00739 herb
4 0.00739 mustard
removed 'dat/engl/cpn/tot.1/gud-whole-wds-summary.tex'
removed 'exp/engl/cpn/tot.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/engl/cpn/tot.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:30:45 by tex-make-sample-summary.sh
% Token and word counts for engl/cpn/tot.1/gud.wfr
%
\def\englcpnwholetotPBgudTks{541}
\def\englcpnwholetotPBgudTksPct{99.4}
\def\englcpnwholetotPBgudWds{400}
\def\englcpnwholetotPBgudWdsPct{73.5}
copied '/tmp/562554.file' -> 'exp/engl/cpn/tot.1/gud-whole-wds-summary.tex'
removed '/tmp/562554.file'
creating running text file dat/engl/cpn/tot.1/bad.wdf
sample:
st° mas° st°
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
st° mas° st°
removed 'dat/engl/cpn/tot.1/bad.wfr'
creating the word frequency file dat/engl/cpn/tot.1/bad.wfr
the 10 most common words in dat/engl/cpn/tot.1/bad.tlw:
2 0.66667 st°
1 0.33333 mas°
removed 'dat/engl/cpn/tot.1/bad-whole-wds-summary.tex'
removed 'exp/engl/cpn/tot.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/engl/cpn/tot.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:30:45 by tex-make-sample-summary.sh
% Token and word counts for engl/cpn/tot.1/bad.wfr
%
\def\englcpnwholetotPBbadTks{3}
\def\englcpnwholetotPBbadTksPct{0.6}
\def\englcpnwholetotPBbadWds{2}
\def\englcpnwholetotPBbadWdsPct{0.4}
copied '/tmp/562598.file' -> 'exp/engl/cpn/tot.1/bad-whole-wds-summary.tex'
removed '/tmp/562598.file'
lines words bytes file
------- ------- --------- ------------
402 1206 9426 dat/engl/cpn/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
400 1200 9385 dat/engl/cpn/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
2 6 41 dat/engl/cpn/tot.1/bad.wfr
tot.1 raw = 544 gud = 541 bad = 3
=== creating the derived word files dat/engl/twp/*/{raw,gud,bad}.{tlw,wdf,wfr} (whole) ===
... creating word files dat/engl/twp/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
95816 dat/engl/twp/tot.1/whole.tlw
removed 'dat/engl/twp/tot.1/raw.tlw'
removed 'dat/engl/twp/tot.1/gud.tlw'
removed 'dat/engl/twp/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/engl/twp/tot.1/raw.wdf
sample:
=
*{ego} ..*{=} i am the first the last also =
oone god in mageste =
meruelus of myght most =
ffader & son & holy goost =
on god in trinyte =
i am without begynnyng =
my godhede hath none endyng =
i am god in trone =
oone god in persons thre =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
man neuer se ayre =
removed 'dat/engl/twp/tot.1/raw.wfr'
creating the word frequency file dat/engl/twp/tot.1/raw.wfr
the 10 most common words in dat/engl/twp/tot.1/raw.tlw:
14198 0.14818 =
2900 0.03027 i
2461 0.02568 and
2066 0.02156 that
1795 0.01873 to
1733 0.01809 the
1230 0.01284 in
1106 0.01154 of
1087 0.01134 he
1024 0.01069 thou
removed 'dat/engl/twp/tot.1/raw-whole-wds-summary.tex'
removed 'exp/engl/twp/tot.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/engl/twp/tot.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:30:45 by tex-make-sample-summary.sh
% Token and word counts for engl/twp/tot.1/raw.wfr
%
\def\engltwpwholetotPBrawTks{95816}
\def\engltwpwholetotPBrawTksPct{100.0}
\def\engltwpwholetotPBrawWds{6848}
\def\engltwpwholetotPBrawWdsPct{7.1}
copied '/tmp/562693.file' -> 'exp/engl/twp/tot.1/raw-whole-wds-summary.tex'
removed '/tmp/562693.file'
creating running text file dat/engl/twp/tot.1/gud.wdf
sample:
i am the first the last also oone god in mageste meruelus of myght most
ffader & son & holy goost on god in trinyte i am without begynnyng my
godhede hath none endyng i am god in trone oone god in persons thre
which may neuer twynnyd be ffor i am god alone all maner thyng is in my
thoght withoutten me ther may be noght ffor all is in my sight hit shall
be done after my will that i haue thoght i shall fulfill and manteyn
with my myght at the begynnyng of oure dede make we heuen & erth on
brede and lyghtys fayre to se ffor it is good to be so darknes from
light we parte on two in tyme to serue and be darknes we call the nyght
and lith also the bright it shall be as i say after my will this is
furth broght euen and morne both ar thay wroght and thus is maid a day
in medys the water bi oure assent be now maide the firmament and parte
ather from othere water aboue i wis euen and morne maide is this a day
so was the tothere waters that so wyde ben spred be gedered to geder in
to one stede that dry the erth may seym that at is dry the erth shall be
the waters also i call the see this warke to me is queme out of the erth
herbys shal spryng trees to florish and frute furth bryng thare kynde
that it be kyd this is done after my will even & morn maide is ther till
a day this is the thryd son & moyne set in the heuen with starnes & the
planettys seuen to stand in thare degre the son to serue the day lyght
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
be kyng sone aftur with in yeres too in the land hit befell soo the
qweyn hir selff with child can goo a son sche bayr a fayrer child from
tope to too man neuer se ayre
removed 'dat/engl/twp/tot.1/gud.wfr'
creating the word frequency file dat/engl/twp/tot.1/gud.wfr
the 10 most common words in dat/engl/twp/tot.1/gud.tlw:
2900 0.03558 i
2461 0.03020 and
2066 0.02535 that
1795 0.02203 to
1733 0.02126 the
1230 0.01509 in
1106 0.01357 of
1087 0.01334 he
1024 0.01256 thou
942 0.01156 my
removed 'dat/engl/twp/tot.1/gud-whole-wds-summary.tex'
removed 'exp/engl/twp/tot.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/engl/twp/tot.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:30:45 by tex-make-sample-summary.sh
% Token and word counts for engl/twp/tot.1/gud.wfr
%
\def\engltwpwholetotPBgudTks{81498}
\def\engltwpwholetotPBgudTksPct{85.1}
\def\engltwpwholetotPBgudWds{6799}
\def\engltwpwholetotPBgudWdsPct{7.1}
copied '/tmp/562737.file' -> 'exp/engl/twp/tot.1/gud-whole-wds-summary.tex'
removed '/tmp/562737.file'
creating running text file dat/engl/twp/tot.1/bad.wdf
sample:
=
*{ego} ..*{=} =
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/engl/twp/tot.1/bad.wfr'
creating the word frequency file dat/engl/twp/tot.1/bad.wfr
the 10 most common words in dat/engl/twp/tot.1/bad.tlw:
14198 0.99162 =
53 0.00370 ..*{=}
6 0.00042 *{Ŧ}
4 0.00028 *{et}
3 0.00021 *{in}
3 0.00021 ..*{ŧ}
2 0.00014 *{atrox}
2 0.00014 *{attollite}
2 0.00014 *{a}
2 0.00014 *{cum}
removed 'dat/engl/twp/tot.1/bad-whole-wds-summary.tex'
removed 'exp/engl/twp/tot.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/engl/twp/tot.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:30:45 by tex-make-sample-summary.sh
% Token and word counts for engl/twp/tot.1/bad.wfr
%
\def\engltwpwholetotPBbadTks{14318}
\def\engltwpwholetotPBbadTksPct{14.9}
\def\engltwpwholetotPBbadWds{49}
\def\engltwpwholetotPBbadWdsPct{0.1}
copied '/tmp/562781.file' -> 'exp/engl/twp/tot.1/bad-whole-wds-summary.tex'
removed '/tmp/562781.file'
lines words bytes file
------- ------- --------- ------------
6848 20544 155398 dat/engl/twp/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
6799 20397 154175 dat/engl/twp/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
49 147 1223 dat/engl/twp/tot.1/bad.wfr
tot.1 raw = 95816 gud = 81498 bad = 14318
=== creating the derived word files dat/latn/ptt/*/{raw,gud,bad}.{tlw,wdf,wfr} (whole) ===
... creating word files dat/latn/ptt/gen.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
26748 dat/latn/ptt/gen.1/whole.tlw
removed 'dat/latn/ptt/gen.1/raw.tlw'
removed 'dat/latn/ptt/gen.1/gud.tlw'
removed 'dat/latn/ptt/gen.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/latn/ptt/gen.1/raw.wdf
sample:
in principio creavit deus caelum et terram =
terra autem erat inanis et vacua et tenebrae super faciem abyssi et
spiritus dei ferebatur super aquas =
dixitque deus fiat lux et facta est lux =
et vidit deus lucem quod esset bona et divisit lucem ac tenebras =
appellavitque lucem diem et tenebras noctem factumque est vespere et
mane dies unus =
dixit quoque deus fiat firmamentum in medio aquarum et dividat aquas ab
aquis =
et fecit deus firmamentum divisitque aquas quae erant sub firmamento ab
his quae erant super firmamentum et factum est ita =
vocavitque deus firmamentum caelum et factum est vespere et mane dies
secundus =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
mortuus est expletis centum decem vitae suae annis et conditus
aromatibus repositus est in loculo in aegypto =
removed 'dat/latn/ptt/gen.1/raw.wfr'
creating the word frequency file dat/latn/ptt/gen.1/raw.wfr
the 10 most common words in dat/latn/ptt/gen.1/raw.tlw:
1878 0.07021 et
1531 0.05724 =
692 0.02587 in
391 0.01462 est
372 0.01391 ad
182 0.00680 ut
180 0.00673 de
173 0.00647 autem
169 0.00632 qui
169 0.00632 quod
removed 'dat/latn/ptt/gen.1/raw-whole-wds-summary.tex'
removed 'exp/latn/ptt/gen.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/latn/ptt/gen.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:30:45 by tex-make-sample-summary.sh
% Token and word counts for latn/ptt/gen.1/raw.wfr
%
\def\latnpttwholegenPBrawTks{26748}
\def\latnpttwholegenPBrawTksPct{100.0}
\def\latnpttwholegenPBrawWds{5714}
\def\latnpttwholegenPBrawWdsPct{21.4}
copied '/tmp/562876.file' -> 'exp/latn/ptt/gen.1/raw-whole-wds-summary.tex'
removed '/tmp/562876.file'
creating running text file dat/latn/ptt/gen.1/gud.wdf
sample:
in principio creavit deus caelum et terram terra autem erat inanis et
vacua et tenebrae super faciem abyssi et spiritus dei ferebatur super
aquas dixitque deus fiat lux et facta est lux et vidit deus lucem quod
esset bona et divisit lucem ac tenebras appellavitque lucem diem et
tenebras noctem factumque est vespere et mane dies unus dixit quoque
deus fiat firmamentum in medio aquarum et dividat aquas ab aquis et
fecit deus firmamentum divisitque aquas quae erant sub firmamento ab his
quae erant super firmamentum et factum est ita vocavitque deus
firmamentum caelum et factum est vespere et mane dies secundus dixit
vero deus congregentur aquae quae sub caelo sunt in locum unum et
appareat arida factumque est ita et vocavit deus aridam terram
congregationesque aquarum appellavit maria et vidit deus quod esset
bonum et ait germinet terra herbam virentem et facientem semen et lignum
pomiferum faciens fructum iuxta genus suum cuius semen in semet ipso sit
super terram et factum est ita et protulit terra herbam virentem et
adferentem semen iuxta genus suum lignumque faciens fructum et habens
unumquodque sementem secundum speciem suam et vidit deus quod esset
bonum factumque est vespere et mane dies tertius dixit autem deus fiant
luminaria in firmamento caeli ut dividant diem ac noctem et sint in
signa et tempora et dies et annos ut luceant in firmamento caeli et
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
adiurasset eos atque dixisset deus visitabit vos asportate vobiscum ossa
mea de loco isto mortuus est expletis centum decem vitae suae annis et
conditus aromatibus repositus est in loculo in aegypto
removed 'dat/latn/ptt/gen.1/gud.wfr'
creating the word frequency file dat/latn/ptt/gen.1/gud.wfr
the 10 most common words in dat/latn/ptt/gen.1/gud.tlw:
1878 0.07447 et
692 0.02744 in
391 0.01551 est
372 0.01475 ad
182 0.00722 ut
180 0.00714 de
173 0.00686 autem
169 0.00670 qui
169 0.00670 quod
166 0.00658 cum
removed 'dat/latn/ptt/gen.1/gud-whole-wds-summary.tex'
removed 'exp/latn/ptt/gen.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/latn/ptt/gen.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:30:45 by tex-make-sample-summary.sh
% Token and word counts for latn/ptt/gen.1/gud.wfr
%
\def\latnpttwholegenPBgudTks{25217}
\def\latnpttwholegenPBgudTksPct{94.3}
\def\latnpttwholegenPBgudWds{5713}
\def\latnpttwholegenPBgudWdsPct{21.4}
copied '/tmp/562920.file' -> 'exp/latn/ptt/gen.1/gud-whole-wds-summary.tex'
removed '/tmp/562920.file'
creating running text file dat/latn/ptt/gen.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/latn/ptt/gen.1/bad.wfr'
creating the word frequency file dat/latn/ptt/gen.1/bad.wfr
the 10 most common words in dat/latn/ptt/gen.1/bad.tlw:
1531 1.00000 =
removed 'dat/latn/ptt/gen.1/bad-whole-wds-summary.tex'
removed 'exp/latn/ptt/gen.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/latn/ptt/gen.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:30:45 by tex-make-sample-summary.sh
% Token and word counts for latn/ptt/gen.1/bad.wfr
%
\def\latnpttwholegenPBbadTks{1531}
\def\latnpttwholegenPBbadTksPct{5.7}
\def\latnpttwholegenPBbadWds{1}
\def\latnpttwholegenPBbadWdsPct{0.0}
copied '/tmp/562964.file' -> 'exp/latn/ptt/gen.1/bad-whole-wds-summary.tex'
removed '/tmp/562964.file'
... creating word files dat/latn/ptt/exo.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
21271 dat/latn/ptt/exo.1/whole.tlw
removed 'dat/latn/ptt/exo.1/raw.tlw'
removed 'dat/latn/ptt/exo.1/gud.tlw'
removed 'dat/latn/ptt/exo.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/latn/ptt/exo.1/raw.wdf
sample:
haec sunt nomina filiorum israhel qui ingressi sunt aegyptum cum iacob
singuli cum domibus suis introierunt =
ruben symeon levi iuda =
isachar zabulon et beniamin =
dan et nepthalim gad et aser =
erant igitur omnes animae eorum qui egressi sunt de femore iacob
septuaginta ioseph autem in aegypto erat =
quo mortuo et universis fratribus eius omnique cognatione illa =
filii israhel creverunt et quasi germinantes multiplicati sunt ac
roborati nimis impleverunt terram =
surrexit interea rex novus super aegyptum qui ignorabat ioseph =
et ait ad populum suum ecce populus filiorum israhel multus et fortior
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
nubes quippe domini incubabat per diem tabernaculo et ignis in nocte
videntibus populis israhel per cunctas mansiones suas =
removed 'dat/latn/ptt/exo.1/raw.wfr'
creating the word frequency file dat/latn/ptt/exo.1/raw.wfr
the 10 most common words in dat/latn/ptt/exo.1/raw.tlw:
1462 0.06873 et
1211 0.05693 =
693 0.03258 in
345 0.01622 ad
244 0.01147 de
230 0.01081 dominus
203 0.00954 est
181 0.00851 non
181 0.00851 ut
159 0.00747 israhel
removed 'dat/latn/ptt/exo.1/raw-whole-wds-summary.tex'
removed 'exp/latn/ptt/exo.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/latn/ptt/exo.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:30:45 by tex-make-sample-summary.sh
% Token and word counts for latn/ptt/exo.1/raw.wfr
%
\def\latnpttwholeexoPBrawTks{21271}
\def\latnpttwholeexoPBrawTksPct{100.0}
\def\latnpttwholeexoPBrawWds{4702}
\def\latnpttwholeexoPBrawWdsPct{22.1}
copied '/tmp/563018.file' -> 'exp/latn/ptt/exo.1/raw-whole-wds-summary.tex'
removed '/tmp/563018.file'
creating running text file dat/latn/ptt/exo.1/gud.wdf
sample:
haec sunt nomina filiorum israhel qui ingressi sunt aegyptum cum iacob
singuli cum domibus suis introierunt ruben symeon levi iuda isachar
zabulon et beniamin dan et nepthalim gad et aser erant igitur omnes
animae eorum qui egressi sunt de femore iacob septuaginta ioseph autem
in aegypto erat quo mortuo et universis fratribus eius omnique
cognatione illa filii israhel creverunt et quasi germinantes
multiplicati sunt ac roborati nimis impleverunt terram surrexit interea
rex novus super aegyptum qui ignorabat ioseph et ait ad populum suum
ecce populus filiorum israhel multus et fortior nobis venite sapienter
opprimamus eum ne forte multiplicetur et si ingruerit contra nos bellum
addatur inimicis nostris expugnatisque nobis egrediatur e terra
praeposuit itaque eis magistros operum ut adfligerent eos oneribus
aedificaveruntque urbes tabernaculorum pharaoni phiton et ramesses
quantoque opprimebant eos tanto magis multiplicabantur et crescebant
oderantque filios israhel aegyptii et adfligebant inludentes eis atque
ad amaritudinem perducebant vitam eorum operibus duris luti et lateris
omnique famulatu quo in terrae operibus premebantur dixit autem rex
aegypti obsetricibus hebraeorum quarum una vocabatur sephra altera phua
praecipiens eis quando obsetricabitis hebraeas et partus tempus
advenerit si masculus fuerit interficite illum si femina reservate
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
israhel per turmas suas si pendebat desuper manebant in eodem loco nubes
quippe domini incubabat per diem tabernaculo et ignis in nocte
videntibus populis israhel per cunctas mansiones suas
removed 'dat/latn/ptt/exo.1/gud.wfr'
creating the word frequency file dat/latn/ptt/exo.1/gud.wfr
the 10 most common words in dat/latn/ptt/exo.1/gud.tlw:
1462 0.07288 et
693 0.03455 in
345 0.01720 ad
244 0.01216 de
230 0.01147 dominus
203 0.01012 est
181 0.00902 non
181 0.00902 ut
159 0.00793 israhel
144 0.00718 eius
removed 'dat/latn/ptt/exo.1/gud-whole-wds-summary.tex'
removed 'exp/latn/ptt/exo.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/latn/ptt/exo.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:30:45 by tex-make-sample-summary.sh
% Token and word counts for latn/ptt/exo.1/gud.wfr
%
\def\latnpttwholeexoPBgudTks{20060}
\def\latnpttwholeexoPBgudTksPct{94.3}
\def\latnpttwholeexoPBgudWds{4701}
\def\latnpttwholeexoPBgudWdsPct{22.1}
copied '/tmp/563062.file' -> 'exp/latn/ptt/exo.1/gud-whole-wds-summary.tex'
removed '/tmp/563062.file'
creating running text file dat/latn/ptt/exo.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/latn/ptt/exo.1/bad.wfr'
creating the word frequency file dat/latn/ptt/exo.1/bad.wfr
the 10 most common words in dat/latn/ptt/exo.1/bad.tlw:
1211 1.00000 =
removed 'dat/latn/ptt/exo.1/bad-whole-wds-summary.tex'
removed 'exp/latn/ptt/exo.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/latn/ptt/exo.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:30:45 by tex-make-sample-summary.sh
% Token and word counts for latn/ptt/exo.1/bad.wfr
%
\def\latnpttwholeexoPBbadTks{1211}
\def\latnpttwholeexoPBbadTksPct{5.7}
\def\latnpttwholeexoPBbadWds{1}
\def\latnpttwholeexoPBbadWdsPct{0.0}
copied '/tmp/563106.file' -> 'exp/latn/ptt/exo.1/bad-whole-wds-summary.tex'
removed '/tmp/563106.file'
... creating word files dat/latn/ptt/num.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
20604 dat/latn/ptt/num.1/whole.tlw
removed 'dat/latn/ptt/num.1/raw.tlw'
removed 'dat/latn/ptt/num.1/gud.tlw'
removed 'dat/latn/ptt/num.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/latn/ptt/num.1/raw.wdf
sample:
locutusque est dominus ad mosen in deserto sinai in tabernaculo foederis
prima die mensis secundi anno altero egressionis eorum ex aegypto dicens
=
tollite summam universae congregationis filiorum israhel per cognationes
et domos suas et nomina singulorum quicquid sexus est masculini =
a vicesimo anno et supra omnium virorum fortium ex israhel et
numerabitis eos per turmas suas tu et aaron =
eruntque vobiscum principes tribuum ac domorum in cognationibus suis =
quorum ista sunt nomina de ruben elisur filius sedeur =
de symeon salamihel filius surisaddai =
de iuda naasson filius aminadab =
de isachar nathanahel filius suar =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
haec sunt mandata atque iudicia quae praecepit dominus per manum mosi ad
filios israhel in campestribus moab super iordanem contra hiericho =
removed 'dat/latn/ptt/num.1/raw.wfr'
creating the word frequency file dat/latn/ptt/num.1/raw.wfr
the 10 most common words in dat/latn/ptt/num.1/raw.tlw:
1288 0.06251 =
1221 0.05926 et
569 0.02762 in
364 0.01767 ad
254 0.01233 est
253 0.01228 de
190 0.00922 per
188 0.00912 qui
187 0.00908 israhel
168 0.00815 sunt
removed 'dat/latn/ptt/num.1/raw-whole-wds-summary.tex'
removed 'exp/latn/ptt/num.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/latn/ptt/num.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:30:45 by tex-make-sample-summary.sh
% Token and word counts for latn/ptt/num.1/raw.wfr
%
\def\latnpttwholenumPBrawTks{20604}
\def\latnpttwholenumPBrawTksPct{100.0}
\def\latnpttwholenumPBrawWds{4341}
\def\latnpttwholenumPBrawWdsPct{21.1}
copied '/tmp/563160.file' -> 'exp/latn/ptt/num.1/raw-whole-wds-summary.tex'
removed '/tmp/563160.file'
creating running text file dat/latn/ptt/num.1/gud.wdf
sample:
locutusque est dominus ad mosen in deserto sinai in tabernaculo foederis
prima die mensis secundi anno altero egressionis eorum ex aegypto dicens
tollite summam universae congregationis filiorum israhel per cognationes
et domos suas et nomina singulorum quicquid sexus est masculini a
vicesimo anno et supra omnium virorum fortium ex israhel et numerabitis
eos per turmas suas tu et aaron eruntque vobiscum principes tribuum ac
domorum in cognationibus suis quorum ista sunt nomina de ruben elisur
filius sedeur de symeon salamihel filius surisaddai de iuda naasson
filius aminadab de isachar nathanahel filius suar de zabulon heliab
filius helon filiorum autem ioseph de ephraim helisama filius ammiud de
manasse gamalihel filius phadassur de beniamin abidan filius gedeonis de
dan ahiezer filius amisaddai de aser phegihel filius ochran de gad
heliasaph filius duhel de nepthali ahira filius henan hii nobilissimi
principes multitudinis per tribus et cognationes suas et capita
exercitus israhel quos tulerunt moses et aaron cum omni vulgi
multitudine et congregaverunt primo die mensis secundi recensentes eos
per cognationes et domos ac familias et capita et nomina singulorum a
vicesimo anno et supra sicut praeceperat dominus mosi numeratique sunt
in deserto sinai de ruben primogenito israhelis per generationes et
familias ac domos suas et nomina capitum singulorum omne quod sexus est
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
familia patris earum haec sunt mandata atque iudicia quae praecepit
dominus per manum mosi ad filios israhel in campestribus moab super
iordanem contra hiericho
removed 'dat/latn/ptt/num.1/gud.wfr'
creating the word frequency file dat/latn/ptt/num.1/gud.wfr
the 10 most common words in dat/latn/ptt/num.1/gud.tlw:
1221 0.06321 et
569 0.02946 in
364 0.01884 ad
254 0.01315 est
253 0.01310 de
190 0.00984 per
188 0.00973 qui
187 0.00968 israhel
168 0.00870 sunt
163 0.00844 dominus
removed 'dat/latn/ptt/num.1/gud-whole-wds-summary.tex'
removed 'exp/latn/ptt/num.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/latn/ptt/num.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:30:45 by tex-make-sample-summary.sh
% Token and word counts for latn/ptt/num.1/gud.wfr
%
\def\latnpttwholenumPBgudTks{19316}
\def\latnpttwholenumPBgudTksPct{93.7}
\def\latnpttwholenumPBgudWds{4340}
\def\latnpttwholenumPBgudWdsPct{21.1}
copied '/tmp/563204.file' -> 'exp/latn/ptt/num.1/gud-whole-wds-summary.tex'
removed '/tmp/563204.file'
creating running text file dat/latn/ptt/num.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/latn/ptt/num.1/bad.wfr'
creating the word frequency file dat/latn/ptt/num.1/bad.wfr
the 10 most common words in dat/latn/ptt/num.1/bad.tlw:
1288 1.00000 =
removed 'dat/latn/ptt/num.1/bad-whole-wds-summary.tex'
removed 'exp/latn/ptt/num.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/latn/ptt/num.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:30:45 by tex-make-sample-summary.sh
% Token and word counts for latn/ptt/num.1/bad.wfr
%
\def\latnpttwholenumPBbadTks{1288}
\def\latnpttwholenumPBbadTksPct{6.3}
\def\latnpttwholenumPBbadWds{1}
\def\latnpttwholenumPBbadWdsPct{0.0}
copied '/tmp/563248.file' -> 'exp/latn/ptt/num.1/bad-whole-wds-summary.tex'
removed '/tmp/563248.file'
... creating word files dat/latn/ptt/lev.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
14633 dat/latn/ptt/lev.1/whole.tlw
removed 'dat/latn/ptt/lev.1/raw.tlw'
removed 'dat/latn/ptt/lev.1/gud.tlw'
removed 'dat/latn/ptt/lev.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/latn/ptt/lev.1/raw.wdf
sample:
vocavit autem mosen et locutus est ei dominus de tabernaculo testimonii
dicens =
loquere filiis israhel et dices ad eos homo qui obtulerit ex vobis
hostiam domino de pecoribus id est de bubus et ovibus offerens victimas
=
si holocaustum fuerit eius oblatio ac de armento masculum inmaculatum
offeret ad ostium tabernaculi testimonii ad placandum sibi dominum =
ponetque manus super caput hostiae et acceptabilis erit atque in
expiationem eius proficiens =
immolabitque vitulum coram domino et offerent filii aaron sacerdotes
sanguinem eius fundentes super altaris circuitum quod est ante ostium
tabernaculi =
detractaque pelle hostiae artus in frusta concident =
et subicient in altari ignem strue lignorum ante conposita =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
haec sunt praecepta quae mandavit dominus mosi ad filios israhel in
monte sinai =
removed 'dat/latn/ptt/lev.1/raw.wfr'
creating the word frequency file dat/latn/ptt/lev.1/raw.wfr
the 10 most common words in dat/latn/ptt/lev.1/raw.tlw:
882 0.06027 et
858 0.05863 =
385 0.02631 in
231 0.01579 est
197 0.01346 ad
185 0.01264 non
168 0.01148 qui
156 0.01066 de
130 0.00888 pro
127 0.00868 eius
removed 'dat/latn/ptt/lev.1/raw-whole-wds-summary.tex'
removed 'exp/latn/ptt/lev.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/latn/ptt/lev.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:30:45 by tex-make-sample-summary.sh
% Token and word counts for latn/ptt/lev.1/raw.wfr
%
\def\latnpttwholelevPBrawTks{14633}
\def\latnpttwholelevPBrawTksPct{100.0}
\def\latnpttwholelevPBrawWds{3234}
\def\latnpttwholelevPBrawWdsPct{22.1}
copied '/tmp/563302.file' -> 'exp/latn/ptt/lev.1/raw-whole-wds-summary.tex'
removed '/tmp/563302.file'
creating running text file dat/latn/ptt/lev.1/gud.wdf
sample:
vocavit autem mosen et locutus est ei dominus de tabernaculo testimonii
dicens loquere filiis israhel et dices ad eos homo qui obtulerit ex
vobis hostiam domino de pecoribus id est de bubus et ovibus offerens
victimas si holocaustum fuerit eius oblatio ac de armento masculum
inmaculatum offeret ad ostium tabernaculi testimonii ad placandum sibi
dominum ponetque manus super caput hostiae et acceptabilis erit atque in
expiationem eius proficiens immolabitque vitulum coram domino et
offerent filii aaron sacerdotes sanguinem eius fundentes super altaris
circuitum quod est ante ostium tabernaculi detractaque pelle hostiae
artus in frusta concident et subicient in altari ignem strue lignorum
ante conposita et membra quae caesa sunt desuper ordinantes caput
videlicet et cuncta quae adherent iecori intestinis et pedibus lotis
aqua adolebitque ea sacerdos super altare in holocaustum et suavem
odorem domino quod si de pecoribus oblatio est de ovibus sive de capris
holocaustum anniculum et absque macula offeret immolabitque ad latus
altaris quod respicit ad aquilonem coram domino sanguinem vero illius
fundent super altare filii aaron per circuitum dividentque membra caput
et omnia quae adherent iecori et inponent super ligna quibus subiciendus
est ignis intestina vero et pedes lavabunt aqua et oblata omnia adolebit
sacerdos super altare in holocaustum et odorem suavissimum domino sin
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
commutabitur si quis mutaverit et quod mutatum est et pro quo mutatum
est sanctificabitur domino et non redimetur haec sunt praecepta quae
mandavit dominus mosi ad filios israhel in monte sinai
removed 'dat/latn/ptt/lev.1/gud.wfr'
creating the word frequency file dat/latn/ptt/lev.1/gud.wfr
the 10 most common words in dat/latn/ptt/lev.1/gud.tlw:
882 0.06403 et
385 0.02795 in
231 0.01677 est
197 0.01430 ad
185 0.01343 non
168 0.01220 qui
156 0.01132 de
130 0.00944 pro
127 0.00922 eius
123 0.00893 si
removed 'dat/latn/ptt/lev.1/gud-whole-wds-summary.tex'
removed 'exp/latn/ptt/lev.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/latn/ptt/lev.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:30:46 by tex-make-sample-summary.sh
% Token and word counts for latn/ptt/lev.1/gud.wfr
%
\def\latnpttwholelevPBgudTks{13775}
\def\latnpttwholelevPBgudTksPct{94.1}
\def\latnpttwholelevPBgudWds{3233}
\def\latnpttwholelevPBgudWdsPct{22.1}
copied '/tmp/563346.file' -> 'exp/latn/ptt/lev.1/gud-whole-wds-summary.tex'
removed '/tmp/563346.file'
creating running text file dat/latn/ptt/lev.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/latn/ptt/lev.1/bad.wfr'
creating the word frequency file dat/latn/ptt/lev.1/bad.wfr
the 10 most common words in dat/latn/ptt/lev.1/bad.tlw:
858 1.00000 =
removed 'dat/latn/ptt/lev.1/bad-whole-wds-summary.tex'
removed 'exp/latn/ptt/lev.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/latn/ptt/lev.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:30:46 by tex-make-sample-summary.sh
% Token and word counts for latn/ptt/lev.1/bad.wfr
%
\def\latnpttwholelevPBbadTks{858}
\def\latnpttwholelevPBbadTksPct{5.9}
\def\latnpttwholelevPBbadWds{1}
\def\latnpttwholelevPBbadWdsPct{0.0}
copied '/tmp/563390.file' -> 'exp/latn/ptt/lev.1/bad-whole-wds-summary.tex'
removed '/tmp/563390.file'
... creating word files dat/latn/ptt/deu.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
19461 dat/latn/ptt/deu.1/whole.tlw
removed 'dat/latn/ptt/deu.1/raw.tlw'
removed 'dat/latn/ptt/deu.1/gud.tlw'
removed 'dat/latn/ptt/deu.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/latn/ptt/deu.1/raw.wdf
sample:
haec sunt verba quae locutus est moses ad omnem israhel trans iordanem
in solitudine campestri contra mare rubrum inter pharan et thophel et
laban et aseroth ubi auri est plurimum =
undecim diebus de horeb per viam montis seir usque cadesbarne =
quadragesimo anno undecimo mense prima die mensis locutus est moses ad
filios israhel omnia quae praeceperat illi dominus ut diceret eis =
postquam percussit seon regem amorreorum qui habitavit in esebon et og
regem basan qui mansit in aseroth et in edrai =
trans iordanem in terra moab coepitque moses explanare legem et dicere =
dominus deus noster locutus est ad nos in horeb dicens sufficit vobis
quod in hoc monte mansistis =
revertimini et venite ad montem amorreorum et ad cetera quae ei proxima
sunt campestria atque montana et humiliora loca contra meridiem et iuxta
litus maris terram chananeorum et libani usque ad flumen magnum eufraten
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
et cunctam manum robustam magnaque mirabilia quae fecit moses coram
universo israhel =
removed 'dat/latn/ptt/deu.1/raw.wfr'
creating the word frequency file dat/latn/ptt/deu.1/raw.wfr
the 10 most common words in dat/latn/ptt/deu.1/raw.tlw:
1375 0.07065 et
959 0.04928 =
679 0.03489 in
285 0.01464 dominus
268 0.01377 non
240 0.01233 est
212 0.01089 ut
201 0.01033 ad
187 0.00961 de
179 0.00920 deus
removed 'dat/latn/ptt/deu.1/raw-whole-wds-summary.tex'
removed 'exp/latn/ptt/deu.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/latn/ptt/deu.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:30:46 by tex-make-sample-summary.sh
% Token and word counts for latn/ptt/deu.1/raw.wfr
%
\def\latnpttwholedeuPBrawTks{19461}
\def\latnpttwholedeuPBrawTksPct{100.0}
\def\latnpttwholedeuPBrawWds{4467}
\def\latnpttwholedeuPBrawWdsPct{23.0}
copied '/tmp/563444.file' -> 'exp/latn/ptt/deu.1/raw-whole-wds-summary.tex'
removed '/tmp/563444.file'
creating running text file dat/latn/ptt/deu.1/gud.wdf
sample:
haec sunt verba quae locutus est moses ad omnem israhel trans iordanem
in solitudine campestri contra mare rubrum inter pharan et thophel et
laban et aseroth ubi auri est plurimum undecim diebus de horeb per viam
montis seir usque cadesbarne quadragesimo anno undecimo mense prima die
mensis locutus est moses ad filios israhel omnia quae praeceperat illi
dominus ut diceret eis postquam percussit seon regem amorreorum qui
habitavit in esebon et og regem basan qui mansit in aseroth et in edrai
trans iordanem in terra moab coepitque moses explanare legem et dicere
dominus deus noster locutus est ad nos in horeb dicens sufficit vobis
quod in hoc monte mansistis revertimini et venite ad montem amorreorum
et ad cetera quae ei proxima sunt campestria atque montana et humiliora
loca contra meridiem et iuxta litus maris terram chananeorum et libani
usque ad flumen magnum eufraten en inquit tradidi vobis ingredimini et
possidete eam super qua iuravit dominus patribus vestris abraham et
isaac et iacob ut daret illam eis et semini eorum post eos dixique vobis
illo in tempore non possum solus sustinere vos quia dominus deus vester
multiplicavit vos et estis hodie sicut stellae caeli plurimae dominus
deus patrum vestrorum addat ad hunc numerum multa milia et benedicat
vobis sicut locutus est non valeo solus vestra negotia sustinere et
pondus ac iurgia date e vobis viros sapientes et gnaros et quorum
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
in terra aegypti pharaoni et omnibus servis eius universaeque terrae
illius et cunctam manum robustam magnaque mirabilia quae fecit moses
coram universo israhel
removed 'dat/latn/ptt/deu.1/gud.wfr'
creating the word frequency file dat/latn/ptt/deu.1/gud.wfr
the 10 most common words in dat/latn/ptt/deu.1/gud.tlw:
1375 0.07432 et
679 0.03670 in
285 0.01540 dominus
268 0.01448 non
240 0.01297 est
212 0.01146 ut
201 0.01086 ad
187 0.01011 de
179 0.00967 deus
167 0.00903 tibi
removed 'dat/latn/ptt/deu.1/gud-whole-wds-summary.tex'
removed 'exp/latn/ptt/deu.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/latn/ptt/deu.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:30:46 by tex-make-sample-summary.sh
% Token and word counts for latn/ptt/deu.1/gud.wfr
%
\def\latnpttwholedeuPBgudTks{18502}
\def\latnpttwholedeuPBgudTksPct{95.1}
\def\latnpttwholedeuPBgudWds{4466}
\def\latnpttwholedeuPBgudWdsPct{22.9}
copied '/tmp/563488.file' -> 'exp/latn/ptt/deu.1/gud-whole-wds-summary.tex'
removed '/tmp/563488.file'
creating running text file dat/latn/ptt/deu.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/latn/ptt/deu.1/bad.wfr'
creating the word frequency file dat/latn/ptt/deu.1/bad.wfr
the 10 most common words in dat/latn/ptt/deu.1/bad.tlw:
959 1.00000 =
removed 'dat/latn/ptt/deu.1/bad-whole-wds-summary.tex'
removed 'exp/latn/ptt/deu.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/latn/ptt/deu.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:30:46 by tex-make-sample-summary.sh
% Token and word counts for latn/ptt/deu.1/bad.wfr
%
\def\latnpttwholedeuPBbadTks{959}
\def\latnpttwholedeuPBbadTksPct{4.9}
\def\latnpttwholedeuPBbadWds{1}
\def\latnpttwholedeuPBbadWdsPct{0.0}
copied '/tmp/563532.file' -> 'exp/latn/ptt/deu.1/bad-whole-wds-summary.tex'
removed '/tmp/563532.file'
... creating word files dat/latn/ptt/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
102717 dat/latn/ptt/tot.1/whole.tlw
removed 'dat/latn/ptt/tot.1/raw.tlw'
removed 'dat/latn/ptt/tot.1/gud.tlw'
removed 'dat/latn/ptt/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/latn/ptt/tot.1/raw.wdf
sample:
in principio creavit deus caelum et terram =
terra autem erat inanis et vacua et tenebrae super faciem abyssi et
spiritus dei ferebatur super aquas =
dixitque deus fiat lux et facta est lux =
et vidit deus lucem quod esset bona et divisit lucem ac tenebras =
appellavitque lucem diem et tenebras noctem factumque est vespere et
mane dies unus =
dixit quoque deus fiat firmamentum in medio aquarum et dividat aquas ab
aquis =
et fecit deus firmamentum divisitque aquas quae erant sub firmamento ab
his quae erant super firmamentum et factum est ita =
vocavitque deus firmamentum caelum et factum est vespere et mane dies
secundus =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
et cunctam manum robustam magnaque mirabilia quae fecit moses coram
universo israhel =
removed 'dat/latn/ptt/tot.1/raw.wfr'
creating the word frequency file dat/latn/ptt/tot.1/raw.wfr
the 10 most common words in dat/latn/ptt/tot.1/raw.tlw:
6818 0.06638 et
5847 0.05692 =
3018 0.02938 in
1479 0.01440 ad
1319 0.01284 est
1020 0.00993 de
919 0.00895 non
892 0.00868 dominus
819 0.00797 qui
788 0.00767 ut
removed 'dat/latn/ptt/tot.1/raw-whole-wds-summary.tex'
removed 'exp/latn/ptt/tot.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/latn/ptt/tot.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:30:46 by tex-make-sample-summary.sh
% Token and word counts for latn/ptt/tot.1/raw.wfr
%
\def\latnpttwholetotPBrawTks{102717}
\def\latnpttwholetotPBrawTksPct{100.0}
\def\latnpttwholetotPBrawWds{13947}
\def\latnpttwholetotPBrawWdsPct{13.6}
copied '/tmp/563586.file' -> 'exp/latn/ptt/tot.1/raw-whole-wds-summary.tex'
removed '/tmp/563586.file'
creating running text file dat/latn/ptt/tot.1/gud.wdf
sample:
in principio creavit deus caelum et terram terra autem erat inanis et
vacua et tenebrae super faciem abyssi et spiritus dei ferebatur super
aquas dixitque deus fiat lux et facta est lux et vidit deus lucem quod
esset bona et divisit lucem ac tenebras appellavitque lucem diem et
tenebras noctem factumque est vespere et mane dies unus dixit quoque
deus fiat firmamentum in medio aquarum et dividat aquas ab aquis et
fecit deus firmamentum divisitque aquas quae erant sub firmamento ab his
quae erant super firmamentum et factum est ita vocavitque deus
firmamentum caelum et factum est vespere et mane dies secundus dixit
vero deus congregentur aquae quae sub caelo sunt in locum unum et
appareat arida factumque est ita et vocavit deus aridam terram
congregationesque aquarum appellavit maria et vidit deus quod esset
bonum et ait germinet terra herbam virentem et facientem semen et lignum
pomiferum faciens fructum iuxta genus suum cuius semen in semet ipso sit
super terram et factum est ita et protulit terra herbam virentem et
adferentem semen iuxta genus suum lignumque faciens fructum et habens
unumquodque sementem secundum speciem suam et vidit deus quod esset
bonum factumque est vespere et mane dies tertius dixit autem deus fiant
luminaria in firmamento caeli ut dividant diem ac noctem et sint in
signa et tempora et dies et annos ut luceant in firmamento caeli et
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
in terra aegypti pharaoni et omnibus servis eius universaeque terrae
illius et cunctam manum robustam magnaque mirabilia quae fecit moses
coram universo israhel
removed 'dat/latn/ptt/tot.1/gud.wfr'
creating the word frequency file dat/latn/ptt/tot.1/gud.wfr
the 10 most common words in dat/latn/ptt/tot.1/gud.tlw:
6818 0.07038 et
3018 0.03116 in
1479 0.01527 ad
1319 0.01362 est
1020 0.01053 de
919 0.00949 non
892 0.00921 dominus
819 0.00845 qui
788 0.00813 ut
671 0.00693 eius
removed 'dat/latn/ptt/tot.1/gud-whole-wds-summary.tex'
removed 'exp/latn/ptt/tot.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/latn/ptt/tot.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:30:46 by tex-make-sample-summary.sh
% Token and word counts for latn/ptt/tot.1/gud.wfr
%
\def\latnpttwholetotPBgudTks{96870}
\def\latnpttwholetotPBgudTksPct{94.3}
\def\latnpttwholetotPBgudWds{13946}
\def\latnpttwholetotPBgudWdsPct{13.6}
copied '/tmp/563630.file' -> 'exp/latn/ptt/tot.1/gud-whole-wds-summary.tex'
removed '/tmp/563630.file'
creating running text file dat/latn/ptt/tot.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/latn/ptt/tot.1/bad.wfr'
creating the word frequency file dat/latn/ptt/tot.1/bad.wfr
the 10 most common words in dat/latn/ptt/tot.1/bad.tlw:
5847 1.00000 =
removed 'dat/latn/ptt/tot.1/bad-whole-wds-summary.tex'
removed 'exp/latn/ptt/tot.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/latn/ptt/tot.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:30:46 by tex-make-sample-summary.sh
% Token and word counts for latn/ptt/tot.1/bad.wfr
%
\def\latnpttwholetotPBbadTks{5847}
\def\latnpttwholetotPBbadTksPct{5.7}
\def\latnpttwholetotPBbadWds{1}
\def\latnpttwholetotPBbadWdsPct{0.0}
copied '/tmp/563674.file' -> 'exp/latn/ptt/tot.1/bad-whole-wds-summary.tex'
removed '/tmp/563674.file'
lines words bytes file
------- ------- --------- ------------
5714 17142 140329 dat/latn/ptt/gen.1/raw.wfr
4702 14106 115841 dat/latn/ptt/exo.1/raw.wfr
4341 13023 107004 dat/latn/ptt/num.1/raw.wfr
3234 9702 79498 dat/latn/ptt/lev.1/raw.wfr
4467 13401 109883 dat/latn/ptt/deu.1/raw.wfr
13947 41841 349288 dat/latn/ptt/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
5713 17139 140311 dat/latn/ptt/gen.1/gud.wfr
4701 14103 115823 dat/latn/ptt/exo.1/gud.wfr
4340 13020 106986 dat/latn/ptt/num.1/gud.wfr
3233 9699 79480 dat/latn/ptt/lev.1/gud.wfr
4466 13398 109865 dat/latn/ptt/deu.1/gud.wfr
13946 41838 349270 dat/latn/ptt/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
1 3 18 dat/latn/ptt/gen.1/bad.wfr
1 3 18 dat/latn/ptt/exo.1/bad.wfr
1 3 18 dat/latn/ptt/num.1/bad.wfr
1 3 18 dat/latn/ptt/lev.1/bad.wfr
1 3 18 dat/latn/ptt/deu.1/bad.wfr
1 3 18 dat/latn/ptt/tot.1/bad.wfr
gen.1 raw = 26748 gud = 25217 bad = 1531
exo.1 raw = 21271 gud = 20060 bad = 1211
num.1 raw = 20604 gud = 19316 bad = 1288
lev.1 raw = 14633 gud = 13775 bad = 858
deu.1 raw = 19461 gud = 18502 bad = 959
tot.1 raw = 102717 gud = 96870 bad = 5847
=== creating the derived word files dat/latn/nwt/*/{raw,gud,bad}.{tlw,wdf,wfr} (whole) ===
... creating word files dat/latn/nwt/mat.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
17502 dat/latn/nwt/mat.1/whole.tlw
removed 'dat/latn/nwt/mat.1/raw.tlw'
removed 'dat/latn/nwt/mat.1/gud.tlw'
removed 'dat/latn/nwt/mat.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/latn/nwt/mat.1/raw.wdf
sample:
liber generationis iesu christi filii david filii abraham =
abraham genuit isaac isaac autem genuit iacob iacob autem genuit iudam
et fratres eius =
iudas autem genuit phares et zara de thamar phares autem genuit esrom
esrom autem genuit aram =
aram autem genuit aminadab aminadab autem genuit naasson naasson autem
genuit salmon =
salmon autem genuit booz de rachab booz autem genuit obed ex ruth obed
autem genuit iesse iesse autem genuit david regem =
david autem rex genuit salomonem ex ea quae fuit uriae =
salomon autem genuit roboam roboam autem genuit abiam abia autem genuit
asa =
asa autem genuit iosaphat iosaphat autem genuit ioram ioram autem genuit
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
docentes eos servare omnia quaecumque mandavi vobis et ecce ego vobiscum
sum omnibus diebus usque ad consummationem saeculi =
removed 'dat/latn/nwt/mat.1/raw.wfr'
creating the word frequency file dat/latn/nwt/mat.1/raw.wfr
the 10 most common words in dat/latn/nwt/mat.1/raw.tlw:
1267 0.07239 et
1069 0.06108 =
509 0.02908 in
370 0.02114 autem
293 0.01674 est
222 0.01268 non
222 0.01268 qui
157 0.00897 eum
133 0.00760 cum
121 0.00691 eius
removed 'dat/latn/nwt/mat.1/raw-whole-wds-summary.tex'
removed 'exp/latn/nwt/mat.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/latn/nwt/mat.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:30:46 by tex-make-sample-summary.sh
% Token and word counts for latn/nwt/mat.1/raw.wfr
%
\def\latnnwtwholematPBrawTks{17502}
\def\latnnwtwholematPBrawTksPct{100.0}
\def\latnnwtwholematPBrawWds{3914}
\def\latnnwtwholematPBrawWdsPct{22.4}
copied '/tmp/563844.file' -> 'exp/latn/nwt/mat.1/raw-whole-wds-summary.tex'
removed '/tmp/563844.file'
creating running text file dat/latn/nwt/mat.1/gud.wdf
sample:
liber generationis iesu christi filii david filii abraham abraham genuit
isaac isaac autem genuit iacob iacob autem genuit iudam et fratres eius
iudas autem genuit phares et zara de thamar phares autem genuit esrom
esrom autem genuit aram aram autem genuit aminadab aminadab autem genuit
naasson naasson autem genuit salmon salmon autem genuit booz de rachab
booz autem genuit obed ex ruth obed autem genuit iesse iesse autem
genuit david regem david autem rex genuit salomonem ex ea quae fuit
uriae salomon autem genuit roboam roboam autem genuit abiam abia autem
genuit asa asa autem genuit iosaphat iosaphat autem genuit ioram ioram
autem genuit oziam ozias autem genuit ioatham ioatham autem genuit achaz
achaz autem genuit ezechiam ezechias autem genuit manassen manasses
autem genuit amon amon autem genuit iosiam iosias autem genuit iechoniam
et fratres eius in transmigratione babylonis et post transmigrationem
babylonis iechonias genuit salathihel salathihel autem genuit zorobabel
zorobabel autem genuit abiud abiud autem genuit eliachim eliachim autem
genuit azor azor autem genuit saddoc saddoc autem genuit achim achim
autem genuit eliud eliud autem genuit eleazar eleazar autem genuit
matthan matthan autem genuit iacob iacob autem genuit ioseph virum
mariae de qua natus est iesus qui vocatur christus omnes ergo
generationes ab abraham usque ad david generationes quattuordecim et a
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
docete omnes gentes baptizantes eos in nomine patris et filii et
spiritus sancti docentes eos servare omnia quaecumque mandavi vobis et
ecce ego vobiscum sum omnibus diebus usque ad consummationem saeculi
removed 'dat/latn/nwt/mat.1/gud.wfr'
creating the word frequency file dat/latn/nwt/mat.1/gud.wfr
the 10 most common words in dat/latn/nwt/mat.1/gud.tlw:
1267 0.07711 et
509 0.03098 in
370 0.02252 autem
293 0.01783 est
222 0.01351 non
222 0.01351 qui
157 0.00956 eum
133 0.00809 cum
121 0.00736 eius
121 0.00736 iesus
removed 'dat/latn/nwt/mat.1/gud-whole-wds-summary.tex'
removed 'exp/latn/nwt/mat.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/latn/nwt/mat.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:30:46 by tex-make-sample-summary.sh
% Token and word counts for latn/nwt/mat.1/gud.wfr
%
\def\latnnwtwholematPBgudTks{16431}
\def\latnnwtwholematPBgudTksPct{93.9}
\def\latnnwtwholematPBgudWds{3911}
\def\latnnwtwholematPBgudWdsPct{22.3}
copied '/tmp/563888.file' -> 'exp/latn/nwt/mat.1/gud-whole-wds-summary.tex'
removed '/tmp/563888.file'
creating running text file dat/latn/nwt/mat.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/latn/nwt/mat.1/bad.wfr'
creating the word frequency file dat/latn/nwt/mat.1/bad.wfr
the 10 most common words in dat/latn/nwt/mat.1/bad.tlw:
1069 0.99813 =
1 0.00093 *{heli}
1 0.00093 ..*{sabacthani}
removed 'dat/latn/nwt/mat.1/bad-whole-wds-summary.tex'
removed 'exp/latn/nwt/mat.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/latn/nwt/mat.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:30:46 by tex-make-sample-summary.sh
% Token and word counts for latn/nwt/mat.1/bad.wfr
%
\def\latnnwtwholematPBbadTks{1071}
\def\latnnwtwholematPBbadTksPct{6.1}
\def\latnnwtwholematPBbadWds{3}
\def\latnnwtwholematPBbadWdsPct{0.0}
copied '/tmp/563932.file' -> 'exp/latn/nwt/mat.1/bad-whole-wds-summary.tex'
removed '/tmp/563932.file'
... creating word files dat/latn/nwt/mrk.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
10959 dat/latn/nwt/mrk.1/whole.tlw
removed 'dat/latn/nwt/mrk.1/raw.tlw'
removed 'dat/latn/nwt/mrk.1/gud.tlw'
removed 'dat/latn/nwt/mrk.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/latn/nwt/mrk.1/raw.wdf
sample:
initium evangelii iesu christi filii dei =
sicut scriptum est in esaia propheta ecce mitto angelum meum ante faciem
tuam qui praeparabit viam tuam =
vox clamantis in deserto parate viam domini rectas facite semitas eius =
fuit iohannes in deserto baptizans et praedicans baptismum paenitentiae
in remissionem peccatorum =
et egrediebatur ad illum omnis iudaeae regio et hierosolymitae universi
et baptizabantur ab illo in iordane flumine confitentes peccata sua =
et erat iohannes vestitus pilis cameli et zona pellicia circa lumbos
eius et lucustas et mel silvestre edebat =
et praedicabat dicens venit fortior me post me cuius non sum dignus
procumbens solvere corrigiam calciamentorum eius =
ego baptizavi vos aqua ille vero baptizabit vos spiritu sancto =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
illi autem profecti praedicaverunt ubique domino cooperante et sermonem
confirmante sequentibus signis =
removed 'dat/latn/nwt/mrk.1/raw.wfr'
creating the word frequency file dat/latn/nwt/mrk.1/raw.wfr
the 10 most common words in dat/latn/nwt/mrk.1/raw.tlw:
1084 0.09891 et
677 0.06178 =
303 0.02765 in
174 0.01588 eum
146 0.01332 est
134 0.01223 non
125 0.01141 cum
112 0.01022 autem
107 0.00976 qui
87 0.00794 illis
removed 'dat/latn/nwt/mrk.1/raw-whole-wds-summary.tex'
removed 'exp/latn/nwt/mrk.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/latn/nwt/mrk.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:30:46 by tex-make-sample-summary.sh
% Token and word counts for latn/nwt/mrk.1/raw.wfr
%
\def\latnnwtwholemrkPBrawTks{10959}
\def\latnnwtwholemrkPBrawTksPct{100.0}
\def\latnnwtwholemrkPBrawWds{2916}
\def\latnnwtwholemrkPBrawWdsPct{26.6}
copied '/tmp/563986.file' -> 'exp/latn/nwt/mrk.1/raw-whole-wds-summary.tex'
removed '/tmp/563986.file'
creating running text file dat/latn/nwt/mrk.1/gud.wdf
sample:
initium evangelii iesu christi filii dei sicut scriptum est in esaia
propheta ecce mitto angelum meum ante faciem tuam qui praeparabit viam
tuam vox clamantis in deserto parate viam domini rectas facite semitas
eius fuit iohannes in deserto baptizans et praedicans baptismum
paenitentiae in remissionem peccatorum et egrediebatur ad illum omnis
iudaeae regio et hierosolymitae universi et baptizabantur ab illo in
iordane flumine confitentes peccata sua et erat iohannes vestitus pilis
cameli et zona pellicia circa lumbos eius et lucustas et mel silvestre
edebat et praedicabat dicens venit fortior me post me cuius non sum
dignus procumbens solvere corrigiam calciamentorum eius ego baptizavi
vos aqua ille vero baptizabit vos spiritu sancto et factum est in diebus
illis venit iesus a nazareth galilaeae et baptizatus est in iordane ab
iohanne et statim ascendens de aqua vidit apertos caelos et spiritum
tamquam columbam descendentem et manentem in ipso et vox facta est de
caelis tu es filius meus dilectus in te conplacui et statim spiritus
expellit eum in desertum et erat in deserto quadraginta diebus et
quadraginta noctibus et temptabatur a satana eratque cum bestiis et
angeli ministrabant illi postquam autem traditus est iohannes venit
iesus in galilaeam praedicans evangelium regni dei et dicens quoniam
impletum est tempus et adpropinquavit regnum dei paenitemini et credite
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
postquam locutus est eis adsumptus est in caelum et sedit a dextris dei
illi autem profecti praedicaverunt ubique domino cooperante et sermonem
confirmante sequentibus signis
removed 'dat/latn/nwt/mrk.1/gud.wfr'
creating the word frequency file dat/latn/nwt/mrk.1/gud.wfr
the 10 most common words in dat/latn/nwt/mrk.1/gud.tlw:
1084 0.10545 et
303 0.02947 in
174 0.01693 eum
146 0.01420 est
134 0.01304 non
125 0.01216 cum
112 0.01089 autem
107 0.01041 qui
87 0.00846 illis
80 0.00778 ut
removed 'dat/latn/nwt/mrk.1/gud-whole-wds-summary.tex'
removed 'exp/latn/nwt/mrk.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/latn/nwt/mrk.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:30:46 by tex-make-sample-summary.sh
% Token and word counts for latn/nwt/mrk.1/gud.wfr
%
\def\latnnwtwholemrkPBgudTks{10280}
\def\latnnwtwholemrkPBgudTksPct{93.8}
\def\latnnwtwholemrkPBgudWds{2913}
\def\latnnwtwholemrkPBgudWdsPct{26.6}
copied '/tmp/564030.file' -> 'exp/latn/nwt/mrk.1/gud-whole-wds-summary.tex'
removed '/tmp/564030.file'
creating running text file dat/latn/nwt/mrk.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/latn/nwt/mrk.1/bad.wfr'
creating the word frequency file dat/latn/nwt/mrk.1/bad.wfr
the 10 most common words in dat/latn/nwt/mrk.1/bad.tlw:
677 0.99705 =
1 0.00147 *{heloi}
1 0.00147 ..*{sabacthani}
removed 'dat/latn/nwt/mrk.1/bad-whole-wds-summary.tex'
removed 'exp/latn/nwt/mrk.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/latn/nwt/mrk.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:30:46 by tex-make-sample-summary.sh
% Token and word counts for latn/nwt/mrk.1/bad.wfr
%
\def\latnnwtwholemrkPBbadTks{679}
\def\latnnwtwholemrkPBbadTksPct{6.2}
\def\latnnwtwholemrkPBbadWds{3}
\def\latnnwtwholemrkPBbadWdsPct{0.0}
copied '/tmp/564074.file' -> 'exp/latn/nwt/mrk.1/bad-whole-wds-summary.tex'
removed '/tmp/564074.file'
... creating word files dat/latn/nwt/luk.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
19155 dat/latn/nwt/luk.1/whole.tlw
removed 'dat/latn/nwt/luk.1/raw.tlw'
removed 'dat/latn/nwt/luk.1/gud.tlw'
removed 'dat/latn/nwt/luk.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/latn/nwt/luk.1/raw.wdf
sample:
quoniam quidem multi conati sunt ordinare narrationem quae in nobis
conpletae sunt rerum =
sicut tradiderunt nobis qui ab initio ipsi viderunt et ministri fuerunt
sermonis =
visum est et mihi adsecuto a principio omnibus diligenter ex ordine tibi
scribere optime theophile =
ut cognoscas eorum verborum de quibus eruditus es veritatem =
fuit in diebus herodis regis iudaeae sacerdos quidam nomine zaccharias
de vice abia et uxor illi de filiabus aaron et nomen eius elisabeth =
erant autem iusti ambo ante deum incedentes in omnibus mandatis et
iustificationibus domini sine querella =
et non erat illis filius eo quod esset elisabeth sterilis et ambo
processissent in diebus suis =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
et erant semper in templo laudantes et benedicentes deum amen =
removed 'dat/latn/nwt/luk.1/raw.wfr'
creating the word frequency file dat/latn/nwt/luk.1/raw.wfr
the 10 most common words in dat/latn/nwt/luk.1/raw.tlw:
1593 0.08316 et
1151 0.06009 =
589 0.03075 in
360 0.01879 autem
302 0.01577 qui
287 0.01498 est
223 0.01164 non
211 0.01102 ad
177 0.00924 cum
148 0.00773 dixit
removed 'dat/latn/nwt/luk.1/raw-whole-wds-summary.tex'
removed 'exp/latn/nwt/luk.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/latn/nwt/luk.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:30:46 by tex-make-sample-summary.sh
% Token and word counts for latn/nwt/luk.1/raw.wfr
%
\def\latnnwtwholelukPBrawTks{19155}
\def\latnnwtwholelukPBrawTksPct{100.0}
\def\latnnwtwholelukPBrawWds{4407}
\def\latnnwtwholelukPBrawWdsPct{23.0}
copied '/tmp/564128.file' -> 'exp/latn/nwt/luk.1/raw-whole-wds-summary.tex'
removed '/tmp/564128.file'
creating running text file dat/latn/nwt/luk.1/gud.wdf
sample:
quoniam quidem multi conati sunt ordinare narrationem quae in nobis
conpletae sunt rerum sicut tradiderunt nobis qui ab initio ipsi viderunt
et ministri fuerunt sermonis visum est et mihi adsecuto a principio
omnibus diligenter ex ordine tibi scribere optime theophile ut cognoscas
eorum verborum de quibus eruditus es veritatem fuit in diebus herodis
regis iudaeae sacerdos quidam nomine zaccharias de vice abia et uxor
illi de filiabus aaron et nomen eius elisabeth erant autem iusti ambo
ante deum incedentes in omnibus mandatis et iustificationibus domini
sine querella et non erat illis filius eo quod esset elisabeth sterilis
et ambo processissent in diebus suis factum est autem cum sacerdotio
fungeretur in ordine vicis suae ante deum secundum consuetudinem
sacerdotii sorte exiit ut incensum poneret ingressus in templum domini
et omnis multitudo erat populi orans foris hora incensi apparuit autem
illi angelus domini stans a dextris altaris incensi et zaccharias
turbatus est videns et timor inruit super eum ait autem ad illum angelus
ne timeas zaccharia quoniam exaudita est deprecatio tua et uxor tua
elisabeth pariet tibi filium et vocabis nomen eius iohannem et erit
gaudium tibi et exultatio et multi in nativitate eius gaudebunt erit
enim magnus coram domino et vinum et sicera non bibet et spiritu sancto
replebitur adhuc ex utero matris suae et multos filiorum israhel
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
eis et factum est dum benediceret illis recessit ab eis et ferebatur in
caelum et ipsi adorantes regressi sunt in hierusalem cum gaudio magno et
erant semper in templo laudantes et benedicentes deum amen
removed 'dat/latn/nwt/luk.1/gud.wfr'
creating the word frequency file dat/latn/nwt/luk.1/gud.wfr
the 10 most common words in dat/latn/nwt/luk.1/gud.tlw:
1593 0.08848 et
589 0.03271 in
360 0.02000 autem
302 0.01677 qui
287 0.01594 est
223 0.01239 non
211 0.01172 ad
177 0.00983 cum
148 0.00822 dixit
143 0.00794 quia
removed 'dat/latn/nwt/luk.1/gud-whole-wds-summary.tex'
removed 'exp/latn/nwt/luk.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/latn/nwt/luk.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:30:47 by tex-make-sample-summary.sh
% Token and word counts for latn/nwt/luk.1/gud.wfr
%
\def\latnnwtwholelukPBgudTks{18004}
\def\latnnwtwholelukPBgudTksPct{94.0}
\def\latnnwtwholelukPBgudWds{4406}
\def\latnnwtwholelukPBgudWdsPct{23.0}
copied '/tmp/564172.file' -> 'exp/latn/nwt/luk.1/gud-whole-wds-summary.tex'
removed '/tmp/564172.file'
creating running text file dat/latn/nwt/luk.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/latn/nwt/luk.1/bad.wfr'
creating the word frequency file dat/latn/nwt/luk.1/bad.wfr
the 10 most common words in dat/latn/nwt/luk.1/bad.tlw:
1151 1.00000 =
removed 'dat/latn/nwt/luk.1/bad-whole-wds-summary.tex'
removed 'exp/latn/nwt/luk.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/latn/nwt/luk.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:30:47 by tex-make-sample-summary.sh
% Token and word counts for latn/nwt/luk.1/bad.wfr
%
\def\latnnwtwholelukPBbadTks{1151}
\def\latnnwtwholelukPBbadTksPct{6.0}
\def\latnnwtwholelukPBbadWds{1}
\def\latnnwtwholelukPBbadWdsPct{0.0}
copied '/tmp/564216.file' -> 'exp/latn/nwt/luk.1/bad-whole-wds-summary.tex'
removed '/tmp/564216.file'
... creating word files dat/latn/nwt/joh.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
14905 dat/latn/nwt/joh.1/whole.tlw
removed 'dat/latn/nwt/joh.1/raw.tlw'
removed 'dat/latn/nwt/joh.1/gud.tlw'
removed 'dat/latn/nwt/joh.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/latn/nwt/joh.1/raw.wdf
sample:
in principio erat verbum et verbum erat apud deum et deus erat verbum =
hoc erat in principio apud deum =
omnia per ipsum facta sunt et sine ipso factum est nihil quod factum est
=
in ipso vita erat et vita erat lux hominum =
et lux in tenebris lucet et tenebrae eam non conprehenderunt =
fuit homo missus a deo cui nomen erat iohannes =
hic venit in testimonium ut testimonium perhiberet de lumine ut omnes
crederent per illum =
non erat ille lux sed ut testimonium perhiberet de lumine =
erat lux vera quae inluminat omnem hominem venientem in mundum =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
sunt autem et alia multa quae fecit iesus quae si scribantur per singula
nec ipsum arbitror mundum capere eos qui scribendi sunt libros amen =
removed 'dat/latn/nwt/joh.1/raw.wfr'
creating the word frequency file dat/latn/nwt/joh.1/raw.wfr
the 10 most common words in dat/latn/nwt/joh.1/raw.tlw:
898 0.06025 et
879 0.05897 =
377 0.02529 in
307 0.02060 non
258 0.01731 quia
235 0.01577 est
213 0.01429 me
207 0.01389 qui
201 0.01349 autem
199 0.01335 iesus
removed 'dat/latn/nwt/joh.1/raw-whole-wds-summary.tex'
removed 'exp/latn/nwt/joh.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/latn/nwt/joh.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:30:47 by tex-make-sample-summary.sh
% Token and word counts for latn/nwt/joh.1/raw.wfr
%
\def\latnnwtwholejohPBrawTks{14905}
\def\latnnwtwholejohPBrawTksPct{100.0}
\def\latnnwtwholejohPBrawWds{2524}
\def\latnnwtwholejohPBrawWdsPct{16.9}
copied '/tmp/564270.file' -> 'exp/latn/nwt/joh.1/raw-whole-wds-summary.tex'
removed '/tmp/564270.file'
creating running text file dat/latn/nwt/joh.1/gud.wdf
sample:
in principio erat verbum et verbum erat apud deum et deus erat verbum
hoc erat in principio apud deum omnia per ipsum facta sunt et sine ipso
factum est nihil quod factum est in ipso vita erat et vita erat lux
hominum et lux in tenebris lucet et tenebrae eam non conprehenderunt
fuit homo missus a deo cui nomen erat iohannes hic venit in testimonium
ut testimonium perhiberet de lumine ut omnes crederent per illum non
erat ille lux sed ut testimonium perhiberet de lumine erat lux vera quae
inluminat omnem hominem venientem in mundum in mundo erat et mundus per
ipsum factus est et mundus eum non cognovit in propria venit et sui eum
non receperunt quotquot autem receperunt eum dedit eis potestatem filios
dei fieri his qui credunt in nomine eius qui non ex sanguinibus neque ex
voluntate carnis neque ex voluntate viri sed ex deo nati sunt et verbum
caro factum est et habitavit in nobis et vidimus gloriam eius gloriam
quasi unigeniti a patre plenum gratiae et veritatis iohannes testimonium
perhibet de ipso et clamat dicens hic erat quem dixi vobis qui post me
venturus est ante me factus est quia prior me erat et de plenitudine
eius nos omnes accepimus et gratiam pro gratia quia lex per mosen data
est gratia et veritas per iesum christum facta est deum nemo vidit
umquam unigenitus filius qui est in sinu patris ipse enarravit et hoc
est testimonium iohannis quando miserunt iudaei ab hierosolymis
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
quia verum est testimonium eius sunt autem et alia multa quae fecit
iesus quae si scribantur per singula nec ipsum arbitror mundum capere
eos qui scribendi sunt libros amen
removed 'dat/latn/nwt/joh.1/gud.wfr'
creating the word frequency file dat/latn/nwt/joh.1/gud.wfr
the 10 most common words in dat/latn/nwt/joh.1/gud.tlw:
898 0.06402 et
377 0.02688 in
307 0.02189 non
258 0.01839 quia
235 0.01675 est
213 0.01519 me
207 0.01476 qui
201 0.01433 autem
199 0.01419 iesus
190 0.01355 eum
removed 'dat/latn/nwt/joh.1/gud-whole-wds-summary.tex'
removed 'exp/latn/nwt/joh.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/latn/nwt/joh.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:30:47 by tex-make-sample-summary.sh
% Token and word counts for latn/nwt/joh.1/gud.wfr
%
\def\latnnwtwholejohPBgudTks{14026}
\def\latnnwtwholejohPBgudTksPct{94.1}
\def\latnnwtwholejohPBgudWds{2523}
\def\latnnwtwholejohPBgudWdsPct{16.9}
copied '/tmp/564314.file' -> 'exp/latn/nwt/joh.1/gud-whole-wds-summary.tex'
removed '/tmp/564314.file'
creating running text file dat/latn/nwt/joh.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/latn/nwt/joh.1/bad.wfr'
creating the word frequency file dat/latn/nwt/joh.1/bad.wfr
the 10 most common words in dat/latn/nwt/joh.1/bad.tlw:
879 1.00000 =
removed 'dat/latn/nwt/joh.1/bad-whole-wds-summary.tex'
removed 'exp/latn/nwt/joh.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/latn/nwt/joh.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:30:47 by tex-make-sample-summary.sh
% Token and word counts for latn/nwt/joh.1/bad.wfr
%
\def\latnnwtwholejohPBbadTks{879}
\def\latnnwtwholejohPBbadTksPct{5.9}
\def\latnnwtwholejohPBbadWds{1}
\def\latnnwtwholejohPBbadWdsPct{0.0}
copied '/tmp/564358.file' -> 'exp/latn/nwt/joh.1/bad-whole-wds-summary.tex'
removed '/tmp/564358.file'
... creating word files dat/latn/nwt/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
62521 dat/latn/nwt/tot.1/whole.tlw
removed 'dat/latn/nwt/tot.1/raw.tlw'
removed 'dat/latn/nwt/tot.1/gud.tlw'
removed 'dat/latn/nwt/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/latn/nwt/tot.1/raw.wdf
sample:
liber generationis iesu christi filii david filii abraham =
abraham genuit isaac isaac autem genuit iacob iacob autem genuit iudam
et fratres eius =
iudas autem genuit phares et zara de thamar phares autem genuit esrom
esrom autem genuit aram =
aram autem genuit aminadab aminadab autem genuit naasson naasson autem
genuit salmon =
salmon autem genuit booz de rachab booz autem genuit obed ex ruth obed
autem genuit iesse iesse autem genuit david regem =
david autem rex genuit salomonem ex ea quae fuit uriae =
salomon autem genuit roboam roboam autem genuit abiam abia autem genuit
asa =
asa autem genuit iosaphat iosaphat autem genuit ioram ioram autem genuit
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
sunt autem et alia multa quae fecit iesus quae si scribantur per singula
nec ipsum arbitror mundum capere eos qui scribendi sunt libros amen =
removed 'dat/latn/nwt/tot.1/raw.wfr'
creating the word frequency file dat/latn/nwt/tot.1/raw.wfr
the 10 most common words in dat/latn/nwt/tot.1/raw.tlw:
4842 0.07745 et
3776 0.06040 =
1778 0.02844 in
1043 0.01668 autem
961 0.01537 est
886 0.01417 non
838 0.01340 qui
633 0.01012 eum
561 0.00897 quia
553 0.00885 cum
removed 'dat/latn/nwt/tot.1/raw-whole-wds-summary.tex'
removed 'exp/latn/nwt/tot.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/latn/nwt/tot.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:30:47 by tex-make-sample-summary.sh
% Token and word counts for latn/nwt/tot.1/raw.wfr
%
\def\latnnwtwholetotPBrawTks{62521}
\def\latnnwtwholetotPBrawTksPct{100.0}
\def\latnnwtwholetotPBrawWds{7994}
\def\latnnwtwholetotPBrawWdsPct{12.8}
copied '/tmp/564412.file' -> 'exp/latn/nwt/tot.1/raw-whole-wds-summary.tex'
removed '/tmp/564412.file'
creating running text file dat/latn/nwt/tot.1/gud.wdf
sample:
liber generationis iesu christi filii david filii abraham abraham genuit
isaac isaac autem genuit iacob iacob autem genuit iudam et fratres eius
iudas autem genuit phares et zara de thamar phares autem genuit esrom
esrom autem genuit aram aram autem genuit aminadab aminadab autem genuit
naasson naasson autem genuit salmon salmon autem genuit booz de rachab
booz autem genuit obed ex ruth obed autem genuit iesse iesse autem
genuit david regem david autem rex genuit salomonem ex ea quae fuit
uriae salomon autem genuit roboam roboam autem genuit abiam abia autem
genuit asa asa autem genuit iosaphat iosaphat autem genuit ioram ioram
autem genuit oziam ozias autem genuit ioatham ioatham autem genuit achaz
achaz autem genuit ezechiam ezechias autem genuit manassen manasses
autem genuit amon amon autem genuit iosiam iosias autem genuit iechoniam
et fratres eius in transmigratione babylonis et post transmigrationem
babylonis iechonias genuit salathihel salathihel autem genuit zorobabel
zorobabel autem genuit abiud abiud autem genuit eliachim eliachim autem
genuit azor azor autem genuit saddoc saddoc autem genuit achim achim
autem genuit eliud eliud autem genuit eleazar eleazar autem genuit
matthan matthan autem genuit iacob iacob autem genuit ioseph virum
mariae de qua natus est iesus qui vocatur christus omnes ergo
generationes ab abraham usque ad david generationes quattuordecim et a
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
quia verum est testimonium eius sunt autem et alia multa quae fecit
iesus quae si scribantur per singula nec ipsum arbitror mundum capere
eos qui scribendi sunt libros amen
removed 'dat/latn/nwt/tot.1/gud.wfr'
creating the word frequency file dat/latn/nwt/tot.1/gud.wfr
the 10 most common words in dat/latn/nwt/tot.1/gud.tlw:
4842 0.08243 et
1778 0.03027 in
1043 0.01776 autem
961 0.01636 est
886 0.01508 non
838 0.01427 qui
633 0.01078 eum
561 0.00955 quia
553 0.00941 cum
540 0.00919 ad
removed 'dat/latn/nwt/tot.1/gud-whole-wds-summary.tex'
removed 'exp/latn/nwt/tot.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/latn/nwt/tot.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:30:47 by tex-make-sample-summary.sh
% Token and word counts for latn/nwt/tot.1/gud.wfr
%
\def\latnnwtwholetotPBgudTks{58741}
\def\latnnwtwholetotPBgudTksPct{94.0}
\def\latnnwtwholetotPBgudWds{7990}
\def\latnnwtwholetotPBgudWdsPct{12.8}
copied '/tmp/564456.file' -> 'exp/latn/nwt/tot.1/gud-whole-wds-summary.tex'
removed '/tmp/564456.file'
creating running text file dat/latn/nwt/tot.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/latn/nwt/tot.1/bad.wfr'
creating the word frequency file dat/latn/nwt/tot.1/bad.wfr
the 10 most common words in dat/latn/nwt/tot.1/bad.tlw:
3776 0.99894 =
2 0.00053 ..*{sabacthani}
1 0.00026 *{heli}
1 0.00026 *{heloi}
removed 'dat/latn/nwt/tot.1/bad-whole-wds-summary.tex'
removed 'exp/latn/nwt/tot.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/latn/nwt/tot.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:30:47 by tex-make-sample-summary.sh
% Token and word counts for latn/nwt/tot.1/bad.wfr
%
\def\latnnwtwholetotPBbadTks{3780}
\def\latnnwtwholetotPBbadTksPct{6.0}
\def\latnnwtwholetotPBbadWds{4}
\def\latnnwtwholetotPBbadWdsPct{0.0}
copied '/tmp/564500.file' -> 'exp/latn/nwt/tot.1/bad-whole-wds-summary.tex'
removed '/tmp/564500.file'
lines words bytes file
------- ------- --------- ------------
3914 11742 95586 dat/latn/nwt/mat.1/raw.wfr
2916 8748 71527 dat/latn/nwt/mrk.1/raw.wfr
4407 13221 108191 dat/latn/nwt/luk.1/raw.wfr
2524 7572 61121 dat/latn/nwt/joh.1/raw.wfr
7994 23982 198821 dat/latn/nwt/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
3911 11733 95512 dat/latn/nwt/mat.1/gud.wfr
2913 8739 71452 dat/latn/nwt/mrk.1/gud.wfr
4406 13218 108173 dat/latn/nwt/luk.1/gud.wfr
2523 7569 61103 dat/latn/nwt/joh.1/gud.wfr
7990 23970 198722 dat/latn/nwt/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
3 9 74 dat/latn/nwt/mat.1/bad.wfr
3 9 75 dat/latn/nwt/mrk.1/bad.wfr
1 3 18 dat/latn/nwt/luk.1/bad.wfr
1 3 18 dat/latn/nwt/joh.1/bad.wfr
4 12 99 dat/latn/nwt/tot.1/bad.wfr
mat.1 raw = 17502 gud = 16431 bad = 1071
mrk.1 raw = 10959 gud = 10280 bad = 679
luk.1 raw = 19155 gud = 18004 bad = 1151
joh.1 raw = 14905 gud = 14026 bad = 879
tot.1 raw = 62521 gud = 58741 bad = 3780
=== creating the derived word files dat/latn/ock/*/{raw,gud,bad}.{tlw,wdf,wfr} (whole) ===
... creating word files dat/latn/ock/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
37637 dat/latn/ock/tot.1/whole.tlw
removed 'dat/latn/ock/tot.1/raw.tlw'
removed 'dat/latn/ock/tot.1/gud.tlw'
removed 'dat/latn/ock/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/latn/ock/tot.1/raw.wdf
sample:
claves regni celorum esse datas a christo romano pontifici id est beato
petro christianorum non ambigit ut estimo multitudo quare non dubitat
quin sit a christo aliqua concessa potestas plures eciam auctoritates
sanctorum patrum videntur asserere quod aliquam ex humana ordinacione
acceperit potestatem de quarum utraque si utramque habeat interrogabo
quamplura quam videlicet et quo iure divino scilicet an humano habeat
potestatem super spiritualia et ecclesiasticas personas quam et quo iure
super laicos in spiritualibus quam et quo iure super res et iura
temporalia que ad solam romanam spectant ecclesiam quam et quo iure
super res et temporalia iura que ad alios clericos pertinere noscuntur
quam et quo iure super personas res et iura temporalia fidelium laicorum
quam et quo iure super res infidelium et eciam personas ipsorum postea
autem nonnulla similia de potestate cleri perscrutare propono ante omnia
autem interrogare decrevi an potestas pape ad omnia que non sunt contra
legem divinam neque contra ius nature se extendat hec enim interrogacio
videtur comprehendere omnia predicta de potestate pape et forte ex
sentenciis et opinionibus circa ipsam quas recitare studebis dabitur
michi occasio de singulis in speciali querendi circa hanc
interrogacionem diverse et adverse inveniuntur sentencie una est quod
papa tam in temporalibus quam in spiritualibus talem ex ordinacione
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
regulariter expedit ut regatur a pluribus quorum nullus sit superior
alio quamvis in aliquo casu qui possit accidere magis expediret quod
totus orbis regeretur ab uno quam a pluribus
removed 'dat/latn/ock/tot.1/raw.wfr'
creating the word frequency file dat/latn/ock/tot.1/raw.wfr
the 10 most common words in dat/latn/ock/tot.1/raw.tlw:
1584 0.04209 et
795 0.02112 in
747 0.01985 non
722 0.01918 quod
622 0.01653 est
468 0.01243 ad
329 0.00874 ut
301 0.00800 de
300 0.00797 vel
283 0.00752 qui
removed 'dat/latn/ock/tot.1/raw-whole-wds-summary.tex'
removed 'exp/latn/ock/tot.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/latn/ock/tot.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:30:48 by tex-make-sample-summary.sh
% Token and word counts for latn/ock/tot.1/raw.wfr
%
\def\latnockwholetotPBrawTks{37637}
\def\latnockwholetotPBrawTksPct{100.0}
\def\latnockwholetotPBrawWds{5828}
\def\latnockwholetotPBrawWdsPct{15.5}
copied '/tmp/564655.file' -> 'exp/latn/ock/tot.1/raw-whole-wds-summary.tex'
removed '/tmp/564655.file'
creating running text file dat/latn/ock/tot.1/gud.wdf
sample:
claves regni celorum esse datas a christo romano pontifici id est beato
petro christianorum non ambigit ut estimo multitudo quare non dubitat
quin sit a christo aliqua concessa potestas plures eciam auctoritates
sanctorum patrum videntur asserere quod aliquam ex humana ordinacione
acceperit potestatem de quarum utraque si utramque habeat interrogabo
quamplura quam videlicet et quo iure divino scilicet an humano habeat
potestatem super spiritualia et ecclesiasticas personas quam et quo iure
super laicos in spiritualibus quam et quo iure super res et iura
temporalia que ad solam romanam spectant ecclesiam quam et quo iure
super res et temporalia iura que ad alios clericos pertinere noscuntur
quam et quo iure super personas res et iura temporalia fidelium laicorum
quam et quo iure super res infidelium et eciam personas ipsorum postea
autem nonnulla similia de potestate cleri perscrutare propono ante omnia
autem interrogare decrevi an potestas pape ad omnia que non sunt contra
legem divinam neque contra ius nature se extendat hec enim interrogacio
videtur comprehendere omnia predicta de potestate pape et forte ex
sentenciis et opinionibus circa ipsam quas recitare studebis dabitur
michi occasio de singulis in speciali querendi circa hanc
interrogacionem diverse et adverse inveniuntur sentencie una est quod
papa tam in temporalibus quam in spiritualibus talem ex ordinacione
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
regulariter expedit ut regatur a pluribus quorum nullus sit superior
alio quamvis in aliquo casu qui possit accidere magis expediret quod
totus orbis regeretur ab uno quam a pluribus
removed 'dat/latn/ock/tot.1/gud.wfr'
creating the word frequency file dat/latn/ock/tot.1/gud.wfr
the 10 most common words in dat/latn/ock/tot.1/gud.tlw:
1584 0.04251 et
795 0.02133 in
747 0.02005 non
722 0.01938 quod
622 0.01669 est
468 0.01256 ad
329 0.00883 ut
301 0.00808 de
300 0.00805 vel
283 0.00759 qui
removed 'dat/latn/ock/tot.1/gud-whole-wds-summary.tex'
removed 'exp/latn/ock/tot.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/latn/ock/tot.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:30:48 by tex-make-sample-summary.sh
% Token and word counts for latn/ock/tot.1/gud.wfr
%
\def\latnockwholetotPBgudTks{37263}
\def\latnockwholetotPBgudTksPct{99.0}
\def\latnockwholetotPBgudWds{5774}
\def\latnockwholetotPBgudWdsPct{15.3}
copied '/tmp/564699.file' -> 'exp/latn/ock/tot.1/gud-whole-wds-summary.tex'
removed '/tmp/564699.file'
creating running text file dat/latn/ock/tot.1/bad.wdf
sample:
16 19 1 1 14 3 1 1 3 3 5 3 6 1 6 2 1 2 1 2 31 1 2 5 55 12 19 19 24 1 24
1 24 1 19 2 6 3us 22 22 1 9 3 17 4 16 50 27 2 25 1 5 15 6 11 3 40 5 4 25
1 15 3us 9us 17 4 2 3us 1 5 15 12 4 2 3 2 5 15 4 15 16 12 1 15 15 3 19 2
3us 6 5 2 8 10 96 12 1 54 1 2 12 2 17 4 15 6 2 2 88 21 5 1 16 1 88 21 3~
6 20 23 9 10 22 3 11 1 5 3us 1 96 11 16 1 17 9 3 2 6 17 2 6 21 17 3 6 2
6 3us 19 25 2 1 93 95 5 18~ 21 24 1 2 7 21 9 3 24 1 5 10 3 11 24 1 3us 1
9 1 12 1 10 11 21 17 4~ 18 1 6 1 12 1 1 14 7 1 15 7 23 5 8~ 6 13 15 13
14 15 20 28 29 2 8 14~ 15 16 8 3 5 3 10 2~ 10 3 3 3 1 12 63 8 1 11 3 1 1
63 13 10 2 8 c~5 10 2 11 2 7 1 3 12 13 12 12 1 1 13~ 16 13 13 2 24 1 8 9
2 15 15 8 5 18 81 45 1 65 1 2 3 31 9 40 4 3 40 23 4 16 1 31 19 4 3 2 61
23 12 6 2 29 21 1 1 24 2 10 21 24 1 24 1 25 1 22 1 7 1 1 10 20 5 23 1 5
5 22 1 10 22 5 19 10 25 1 23 1 20 1 25 1 25 15 3 45 1 1 7 1 7 1 24 1 25
1 26 6 35 4 4 21 1 2 7 1 7 1 3 20 15 20 1 11 3 11 22 1 2 2 10 6 1
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
23 12 6 2 29 21 1 1 24 2 10 21 24 1 24 1 25 1 22 1 7 1 1 10 20 5 23 1 5
5 22 1 10 22 5 19 10 25 1 23 1 20 1 25 1 25 15 3 45 1 1 7 1 7 1 24 1 25
1 26 6 35 4 4 21 1 2 7 1 7 1 3 20 15 20 1 11 3 11 22 1 2 2 10 6 1
removed 'dat/latn/ock/tot.1/bad.wfr'
creating the word frequency file dat/latn/ock/tot.1/bad.wfr
the 10 most common words in dat/latn/ock/tot.1/bad.tlw:
72 0.19251 1
33 0.08824 2
26 0.06952 3
18 0.04813 5
16 0.04278 15
16 0.04278 6
13 0.03476 10
12 0.03209 12
11 0.02941 24
11 0.02941 4
removed 'dat/latn/ock/tot.1/bad-whole-wds-summary.tex'
removed 'exp/latn/ock/tot.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/latn/ock/tot.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:30:48 by tex-make-sample-summary.sh
% Token and word counts for latn/ock/tot.1/bad.wfr
%
\def\latnockwholetotPBbadTks{374}
\def\latnockwholetotPBbadTksPct{1.0}
\def\latnockwholetotPBbadWds{54}
\def\latnockwholetotPBbadWdsPct{0.1}
copied '/tmp/564743.file' -> 'exp/latn/ock/tot.1/bad-whole-wds-summary.tex'
removed '/tmp/564743.file'
lines words bytes file
------- ------- --------- ------------
5828 17484 146927 dat/latn/ock/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
5774 17322 145904 dat/latn/ock/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
54 162 1023 dat/latn/ock/tot.1/bad.wfr
tot.1 raw = 37637 gud = 37263 bad = 374
=== creating the derived word files dat/grek/nwt/*/{raw,gud,bad}.{tlw,wdf,wfr} (whole) ===
... creating word files dat/grek/nwt/mat.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
19816 dat/grek/nwt/mat.1/whole.tlw
removed 'dat/grek/nwt/mat.1/raw.tlw'
removed 'dat/grek/nwt/mat.1/gud.tlw'
removed 'dat/grek/nwt/mat.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/grek/nwt/mat.1/raw.wdf
sample:
biblos geneseôs iësou qristou uiou dauid uiou abraam =
abraam egennësen ton isaak isaak de egennësen ton iakôb iakôb de
egennësen ton ioudan kai tous adelfous autou =
ioudas de egennësen ton fares kai ton zara ek tës ðamar fares de
egennësen ton esrôm esrôm de egennësen ton aram =
aram de egennësen ton aminadab aminadab de egennësen ton naassôn naassôn
de egennësen ton salmôn =
salmôn de egennësen ton booz ek tës raqab booz de egennësen ton ôbëd ek
tës rouð ôbëd de egennësen ton iessai =
iessai de egennësen ton dauid ton basilea dauid de o basileus egennësen
ton solomôna ek tës tou ouriou =
solomôn de egennësen ton roboam roboam de egennësen ton abia abia de
egennësen ton asa =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
didaskontes autous tërein panta osa eneteilamën umin kai idou egô með
umôn eimi pasas tas ëmeras eôs tës sunteleias tou aiônos amën =
removed 'dat/grek/nwt/mat.1/raw.wfr'
creating the word frequency file dat/grek/nwt/mat.1/raw.wfr
the 10 most common words in dat/grek/nwt/mat.1/raw.tlw:
1220 0.06157 kai
1071 0.05405 =
549 0.02770 o
485 0.02448 de
311 0.01569 en
305 0.01539 tou
278 0.01403 autou
240 0.01211 eis
235 0.01186 to
231 0.01166 oi
removed 'dat/grek/nwt/mat.1/raw-whole-wds-summary.tex'
removed 'exp/grek/nwt/mat.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/grek/nwt/mat.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:30:48 by tex-make-sample-summary.sh
% Token and word counts for grek/nwt/mat.1/raw.wfr
%
\def\greknwtwholematPBrawTks{19816}
\def\greknwtwholematPBrawTksPct{100.0}
\def\greknwtwholematPBrawWds{3959}
\def\greknwtwholematPBrawWdsPct{20.0}
copied '/tmp/564838.file' -> 'exp/grek/nwt/mat.1/raw-whole-wds-summary.tex'
removed '/tmp/564838.file'
creating running text file dat/grek/nwt/mat.1/gud.wdf
sample:
biblos geneseôs iësou qristou uiou dauid uiou abraam abraam egennësen
ton isaak isaak de egennësen ton iakôb iakôb de egennësen ton ioudan kai
tous adelfous autou ioudas de egennësen ton fares kai ton zara ek tës
ðamar fares de egennësen ton esrôm esrôm de egennësen ton aram aram de
egennësen ton aminadab aminadab de egennësen ton naassôn naassôn de
egennësen ton salmôn salmôn de egennësen ton booz ek tës raqab booz de
egennësen ton ôbëd ek tës rouð ôbëd de egennësen ton iessai iessai de
egennësen ton dauid ton basilea dauid de o basileus egennësen ton
solomôna ek tës tou ouriou solomôn de egennësen ton roboam roboam de
egennësen ton abia abia de egennësen ton asa asa de egennësen ton
iôsafat iôsafat de egennësen ton iôram iôram de egennësen ton ozian
ozias de egennësen ton iôaðam iôaðam de egennësen ton aqaz aqaz de
egennësen ton ezekian ezekias de egennësen ton manassë manassës de
egennësen ton amôn amôn de egennësen ton iôsian iôsias de egennësen ton
ieqonian kai tous adelfous autou epi tës metoikesias babulônos meta de
tën metoikesian babulônos ieqonias egennësen ton salaðiël salaðiël de
egennësen ton zorobabel zorobabel de egennësen ton abioud abioud de
egennësen ton eliakeim eliakeim de egennësen ton azôr azôr de egennësen
ton sadôk sadôk de egennësen ton aqeim aqeim de egennësen ton elioud
elioud de egennësen ton eleazar eleazar de egennësen ton matðan matðan
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
baptizontes autous eis to onoma tou patros kai tou uiou kai tou agiou
pneumatos didaskontes autous tërein panta osa eneteilamën umin kai idou
egô með umôn eimi pasas tas ëmeras eôs tës sunteleias tou aiônos amën
removed 'dat/grek/nwt/mat.1/gud.wfr'
creating the word frequency file dat/grek/nwt/mat.1/gud.wfr
the 10 most common words in dat/grek/nwt/mat.1/gud.tlw:
1220 0.06508 kai
549 0.02929 o
485 0.02587 de
311 0.01659 en
305 0.01627 tou
278 0.01483 autou
240 0.01280 eis
235 0.01254 to
231 0.01232 oi
221 0.01179 ton
removed 'dat/grek/nwt/mat.1/gud-whole-wds-summary.tex'
removed 'exp/grek/nwt/mat.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/grek/nwt/mat.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:30:48 by tex-make-sample-summary.sh
% Token and word counts for grek/nwt/mat.1/gud.wfr
%
\def\greknwtwholematPBgudTks{18745}
\def\greknwtwholematPBgudTksPct{94.6}
\def\greknwtwholematPBgudWds{3958}
\def\greknwtwholematPBgudWdsPct{20.0}
copied '/tmp/564882.file' -> 'exp/grek/nwt/mat.1/gud-whole-wds-summary.tex'
removed '/tmp/564882.file'
creating running text file dat/grek/nwt/mat.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/grek/nwt/mat.1/bad.wfr'
creating the word frequency file dat/grek/nwt/mat.1/bad.wfr
the 10 most common words in dat/grek/nwt/mat.1/bad.tlw:
1071 1.00000 =
removed 'dat/grek/nwt/mat.1/bad-whole-wds-summary.tex'
removed 'exp/grek/nwt/mat.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/grek/nwt/mat.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:30:48 by tex-make-sample-summary.sh
% Token and word counts for grek/nwt/mat.1/bad.wfr
%
\def\greknwtwholematPBbadTks{1071}
\def\greknwtwholematPBbadTksPct{5.4}
\def\greknwtwholematPBbadWds{1}
\def\greknwtwholematPBbadWdsPct{0.0}
copied '/tmp/564926.file' -> 'exp/grek/nwt/mat.1/bad-whole-wds-summary.tex'
removed '/tmp/564926.file'
... creating word files dat/grek/nwt/mrk.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
12310 dat/grek/nwt/mrk.1/whole.tlw
removed 'dat/grek/nwt/mrk.1/raw.tlw'
removed 'dat/grek/nwt/mrk.1/gud.tlw'
removed 'dat/grek/nwt/mrk.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/grek/nwt/mrk.1/raw.wdf
sample:
arqë tou euaggeliou iësou qristou uiou tou ðeou =
ôs gegraptai en tois profëtais idou egô apostellô ton aggelon mou pro
prosôpou sou os kataskeuasei tën odon sou emprosðen sou =
fônë boôntos en të erëmô etoimasate tën odon kuriou euðeias poieite tas
tribous autou =
egeneto iôannës baptizôn en të erëmô kai kërussôn baptisma metanoias eis
afesin amartiôn =
kai exeporeueto pros auton pasa ë ioudaia qôra kai oi ierosolumitai kai
ebaptizonto pantes en tô iordanë potamô up autou exomologoumenoi tas
amartias autôn =
ën de o iôannës endedumenos triqas kamëlou kai zônën dermatinën peri tën
osfun autou kai esðiôn akridas kai meli agrion =
kai ekërussen legôn erqetai o isquroteros mou opisô mou ou ouk eimi
ikanos kuįas lusai ton imanta tôn upodëmatôn autou =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
ekeinoi de exelðontes ekëruxan pantaqou tou kuriou sunergountos kai ton
logon bebaiountos dia tôn epakolouðountôn sëmeiôn amën =
removed 'dat/grek/nwt/mrk.1/raw.wfr'
creating the word frequency file dat/grek/nwt/mrk.1/raw.wfr
the 10 most common words in dat/grek/nwt/mrk.1/raw.tlw:
1094 0.08887 kai
678 0.05508 =
289 0.02348 o
195 0.01584 de
187 0.01519 eis
186 0.01511 auton
177 0.01438 autou
151 0.01227 en
146 0.01186 ton
140 0.01137 tou
removed 'dat/grek/nwt/mrk.1/raw-whole-wds-summary.tex'
removed 'exp/grek/nwt/mrk.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/grek/nwt/mrk.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:30:48 by tex-make-sample-summary.sh
% Token and word counts for grek/nwt/mrk.1/raw.wfr
%
\def\greknwtwholemrkPBrawTks{12310}
\def\greknwtwholemrkPBrawTksPct{100.0}
\def\greknwtwholemrkPBrawWds{2899}
\def\greknwtwholemrkPBrawWdsPct{23.5}
copied '/tmp/564980.file' -> 'exp/grek/nwt/mrk.1/raw-whole-wds-summary.tex'
removed '/tmp/564980.file'
creating running text file dat/grek/nwt/mrk.1/gud.wdf
sample:
arqë tou euaggeliou iësou qristou uiou tou ðeou ôs gegraptai en tois
profëtais idou egô apostellô ton aggelon mou pro prosôpou sou os
kataskeuasei tën odon sou emprosðen sou fônë boôntos en të erëmô
etoimasate tën odon kuriou euðeias poieite tas tribous autou egeneto
iôannës baptizôn en të erëmô kai kërussôn baptisma metanoias eis afesin
amartiôn kai exeporeueto pros auton pasa ë ioudaia qôra kai oi
ierosolumitai kai ebaptizonto pantes en tô iordanë potamô up autou
exomologoumenoi tas amartias autôn ën de o iôannës endedumenos triqas
kamëlou kai zônën dermatinën peri tën osfun autou kai esðiôn akridas kai
meli agrion kai ekërussen legôn erqetai o isquroteros mou opisô mou ou
ouk eimi ikanos kuįas lusai ton imanta tôn upodëmatôn autou egô men
ebaptisa umas en udati autos de baptisei umas en pneumati agiô kai
egeneto en ekeinais tais ëmerais ëlðen iësous apo nazaret tës galilaias
kai ebaptisðë upo iôannou eis ton iordanën kai euðeôs anabainôn apo tou
udatos eiden sqizomenous tous ouranous kai to pneuma ôsei peristeran
katabainon ep auton kai fônë egeneto ek tôn ouranôn su ei o uios mou o
agapëtos en ô eudokësa kai euðus to pneuma auton ekballei eis tën erëmon
kai ën ekei en të erëmô ëmeras tessarakonta peirazomenos upo tou satana
kai ën meta tôn ðëriôn kai oi aggeloi diëkonoun autô meta de to
paradoðënai ton iôannën ëlðen o iësous eis tën galilaian kërussôn to
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
ek dexiôn tou ðeou ekeinoi de exelðontes ekëruxan pantaqou tou kuriou
sunergountos kai ton logon bebaiountos dia tôn epakolouðountôn sëmeiôn
amën
removed 'dat/grek/nwt/mrk.1/gud.wfr'
creating the word frequency file dat/grek/nwt/mrk.1/gud.wfr
the 10 most common words in dat/grek/nwt/mrk.1/gud.tlw:
1094 0.09405 kai
289 0.02485 o
195 0.01676 de
187 0.01608 eis
186 0.01599 auton
177 0.01522 autou
151 0.01298 en
146 0.01255 ton
140 0.01204 tou
137 0.01178 to
removed 'dat/grek/nwt/mrk.1/gud-whole-wds-summary.tex'
removed 'exp/grek/nwt/mrk.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/grek/nwt/mrk.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:30:48 by tex-make-sample-summary.sh
% Token and word counts for grek/nwt/mrk.1/gud.wfr
%
\def\greknwtwholemrkPBgudTks{11632}
\def\greknwtwholemrkPBgudTksPct{94.5}
\def\greknwtwholemrkPBgudWds{2898}
\def\greknwtwholemrkPBgudWdsPct{23.5}
copied '/tmp/565024.file' -> 'exp/grek/nwt/mrk.1/gud-whole-wds-summary.tex'
removed '/tmp/565024.file'
creating running text file dat/grek/nwt/mrk.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/grek/nwt/mrk.1/bad.wfr'
creating the word frequency file dat/grek/nwt/mrk.1/bad.wfr
the 10 most common words in dat/grek/nwt/mrk.1/bad.tlw:
678 1.00000 =
removed 'dat/grek/nwt/mrk.1/bad-whole-wds-summary.tex'
removed 'exp/grek/nwt/mrk.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/grek/nwt/mrk.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:30:48 by tex-make-sample-summary.sh
% Token and word counts for grek/nwt/mrk.1/bad.wfr
%
\def\greknwtwholemrkPBbadTks{678}
\def\greknwtwholemrkPBbadTksPct{5.5}
\def\greknwtwholemrkPBbadWds{1}
\def\greknwtwholemrkPBbadWdsPct{0.0}
copied '/tmp/565068.file' -> 'exp/grek/nwt/mrk.1/bad-whole-wds-summary.tex'
removed '/tmp/565068.file'
... creating word files dat/grek/nwt/luk.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
21037 dat/grek/nwt/luk.1/whole.tlw
removed 'dat/grek/nwt/luk.1/raw.tlw'
removed 'dat/grek/nwt/luk.1/gud.tlw'
removed 'dat/grek/nwt/luk.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/grek/nwt/luk.1/raw.wdf
sample:
epeidëper polloi epeqeirësan anataxasðai diëgësin peri tôn
peplëroforëmenôn en ëmin pragmatôn =
kaðôs paredosan ëmin oi ap arqës autoptai kai upëretai genomenoi tou
logou =
edoxen kamoi parëkolouðëkoti anôðen pasin akribôs kaðexës soi graįai
kratiste ðeofile =
ina epignôs peri ôn katëqëðës logôn tën asfaleian =
egeneto en tais ëmerais ërôdou tou basileôs tës ioudaias iereus tis
onomati zaqarias ex efëmerias abia kai ë gunë autou ek tôn ðugaterôn
aarôn kai to onoma autës elisabet =
ësan de dikaioi amfoteroi enôpion tou ðeou poreuomenoi en pasais tais
entolais kai dikaiômasin tou kuriou amemptoi =
kai ouk ën autois teknon kaðoti ë elisabet ën steira kai amfoteroi
probebëkotes en tais ëmerais autôn ësan =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
kai ësan dia pantos en tô ierô ainountes kai eulogountes ton ðeon amën =
removed 'dat/grek/nwt/luk.1/raw.wfr'
creating the word frequency file dat/grek/nwt/luk.1/raw.wfr
the 10 most common words in dat/grek/nwt/luk.1/raw.tlw:
1524 0.07244 kai
1150 0.05467 =
538 0.02557 de
447 0.02125 o
391 0.01859 tou
372 0.01768 en
274 0.01302 autou
242 0.01150 eis
237 0.01127 eipen
229 0.01089 to
removed 'dat/grek/nwt/luk.1/raw-whole-wds-summary.tex'
removed 'exp/grek/nwt/luk.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/grek/nwt/luk.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:30:48 by tex-make-sample-summary.sh
% Token and word counts for grek/nwt/luk.1/raw.wfr
%
\def\greknwtwholelukPBrawTks{21037}
\def\greknwtwholelukPBrawTksPct{100.0}
\def\greknwtwholelukPBrawWds{4610}
\def\greknwtwholelukPBrawWdsPct{21.9}
copied '/tmp/565122.file' -> 'exp/grek/nwt/luk.1/raw-whole-wds-summary.tex'
removed '/tmp/565122.file'
creating running text file dat/grek/nwt/luk.1/gud.wdf
sample:
epeidëper polloi epeqeirësan anataxasðai diëgësin peri tôn
peplëroforëmenôn en ëmin pragmatôn kaðôs paredosan ëmin oi ap arqës
autoptai kai upëretai genomenoi tou logou edoxen kamoi parëkolouðëkoti
anôðen pasin akribôs kaðexës soi graįai kratiste ðeofile ina epignôs
peri ôn katëqëðës logôn tën asfaleian egeneto en tais ëmerais ërôdou tou
basileôs tës ioudaias iereus tis onomati zaqarias ex efëmerias abia kai
ë gunë autou ek tôn ðugaterôn aarôn kai to onoma autës elisabet ësan de
dikaioi amfoteroi enôpion tou ðeou poreuomenoi en pasais tais entolais
kai dikaiômasin tou kuriou amemptoi kai ouk ën autois teknon kaðoti ë
elisabet ën steira kai amfoteroi probebëkotes en tais ëmerais autôn ësan
egeneto de en tô ierateuein auton en të taxei tës efëmerias autou enanti
tou ðeou kata to eðos tës ierateias elaqen tou ðumiasai eiselðôn eis ton
naon tou kuriou kai pan to plëðos ën tou laou proseuqomenon exô të ôra
tou ðumiamatos ôfðë de autô aggelos kuriou estôs ek dexiôn tou
ðusiastëriou tou ðumiamatos kai etaraqðë zaqarias idôn kai fobos
epepesen ep auton eipen de pros auton o aggelos më fobou zaqaria dioti
eisëkousðë ë deësis sou kai ë gunë sou elisabet gennësei uion soi kai
kaleseis to onoma autou iôannën kai estai qara soi kai agalliasis kai
polloi epi të gennësei autou qarësontai estai gar megas enôpion tou
kuriou kai oinon kai sikera ou më pië kai pneumatos agiou plësðësetai
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
auton autous diestë ap autôn kai anefereto eis ton ouranon kai autoi
proskunësantes auton upestreįan eis ierousalëm meta qaras megalës kai
ësan dia pantos en tô ierô ainountes kai eulogountes ton ðeon amën
removed 'dat/grek/nwt/luk.1/gud.wfr'
creating the word frequency file dat/grek/nwt/luk.1/gud.wfr
the 10 most common words in dat/grek/nwt/luk.1/gud.tlw:
1524 0.07663 kai
538 0.02705 de
447 0.02248 o
391 0.01966 tou
372 0.01871 en
274 0.01378 autou
242 0.01217 eis
237 0.01192 eipen
229 0.01152 to
220 0.01106 ton
removed 'dat/grek/nwt/luk.1/gud-whole-wds-summary.tex'
removed 'exp/grek/nwt/luk.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/grek/nwt/luk.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:30:48 by tex-make-sample-summary.sh
% Token and word counts for grek/nwt/luk.1/gud.wfr
%
\def\greknwtwholelukPBgudTks{19887}
\def\greknwtwholelukPBgudTksPct{94.5}
\def\greknwtwholelukPBgudWds{4609}
\def\greknwtwholelukPBgudWdsPct{21.9}
copied '/tmp/565166.file' -> 'exp/grek/nwt/luk.1/gud-whole-wds-summary.tex'
removed '/tmp/565166.file'
creating running text file dat/grek/nwt/luk.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/grek/nwt/luk.1/bad.wfr'
creating the word frequency file dat/grek/nwt/luk.1/bad.wfr
the 10 most common words in dat/grek/nwt/luk.1/bad.tlw:
1150 1.00000 =
removed 'dat/grek/nwt/luk.1/bad-whole-wds-summary.tex'
removed 'exp/grek/nwt/luk.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/grek/nwt/luk.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:30:48 by tex-make-sample-summary.sh
% Token and word counts for grek/nwt/luk.1/bad.wfr
%
\def\greknwtwholelukPBbadTks{1150}
\def\greknwtwholelukPBbadTksPct{5.5}
\def\greknwtwholelukPBbadWds{1}
\def\greknwtwholelukPBbadWdsPct{0.0}
copied '/tmp/565210.file' -> 'exp/grek/nwt/luk.1/bad-whole-wds-summary.tex'
removed '/tmp/565210.file'
... creating word files dat/grek/nwt/joh.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
16798 dat/grek/nwt/joh.1/whole.tlw
removed 'dat/grek/nwt/joh.1/raw.tlw'
removed 'dat/grek/nwt/joh.1/gud.tlw'
removed 'dat/grek/nwt/joh.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/grek/nwt/joh.1/raw.wdf
sample:
en arqë ën o logos kai o logos ën pros ton ðeon kai ðeos ën o logos =
outos ën en arqë pros ton ðeon =
panta di autou egeneto kai qôris autou egeneto oude en o gegonen =
en autô zôë ën kai ë zôë ën to fôs tôn anðrôpôn =
kai to fôs en të skotia fainei kai ë skotia auto ou katelaben =
egeneto anðrôpos apestalmenos para ðeou onoma autô iôannës =
outos ëlðen eis marturian ina marturësë peri tou fôtos ina pantes
pisteusôsin di autou =
ouk ën ekeinos to fôs all ina marturësë peri tou fôtos =
ën to fôs to alëðinon o fôtizei panta anðrôpon erqomenon eis ton kosmon
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
estin de kai alla polla osa epoiësen o iësous atina ean grafëtai kað en
oude auton oimai ton kosmon qôrësai ta grafomena biblia amën =
removed 'dat/grek/nwt/joh.1/raw.wfr'
creating the word frequency file dat/grek/nwt/joh.1/raw.wfr
the 10 most common words in dat/grek/nwt/joh.1/raw.tlw:
879 0.05233 =
867 0.05161 kai
647 0.03852 o
267 0.01589 oti
248 0.01476 ton
247 0.01470 tou
239 0.01423 en
231 0.01375 de
208 0.01238 eis
205 0.01220 iësous
removed 'dat/grek/nwt/joh.1/raw-whole-wds-summary.tex'
removed 'exp/grek/nwt/joh.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/grek/nwt/joh.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:30:48 by tex-make-sample-summary.sh
% Token and word counts for grek/nwt/joh.1/raw.wfr
%
\def\greknwtwholejohPBrawTks{16798}
\def\greknwtwholejohPBrawTksPct{100.0}
\def\greknwtwholejohPBrawWds{2587}
\def\greknwtwholejohPBrawWdsPct{15.4}
copied '/tmp/565264.file' -> 'exp/grek/nwt/joh.1/raw-whole-wds-summary.tex'
removed '/tmp/565264.file'
creating running text file dat/grek/nwt/joh.1/gud.wdf
sample:
en arqë ën o logos kai o logos ën pros ton ðeon kai ðeos ën o logos
outos ën en arqë pros ton ðeon panta di autou egeneto kai qôris autou
egeneto oude en o gegonen en autô zôë ën kai ë zôë ën to fôs tôn
anðrôpôn kai to fôs en të skotia fainei kai ë skotia auto ou katelaben
egeneto anðrôpos apestalmenos para ðeou onoma autô iôannës outos ëlðen
eis marturian ina marturësë peri tou fôtos ina pantes pisteusôsin di
autou ouk ën ekeinos to fôs all ina marturësë peri tou fôtos ën to fôs
to alëðinon o fôtizei panta anðrôpon erqomenon eis ton kosmon en tô
kosmô ën kai o kosmos di autou egeneto kai o kosmos auton ouk egnô eis
ta idia ëlðen kai oi idioi auton ou parelabon osoi de elabon auton
edôken autois exousian tekna ðeou genesðai tois pisteuousin eis to onoma
autou oi ouk ex aimatôn oude ek ðelëmatos sarkos oude ek ðelëmatos
andros all ek ðeou egennëðësan kai o logos sarx egeneto kai eskënôsen en
ëmin kai eðeasameða tën doxan autou doxan ôs monogenous para patros
plërës qaritos kai alëðeias iôannës marturei peri autou kai kekragen
legôn outos ën on eipon o opisô mou erqomenos emprosðen mou gegonen oti
prôtos mou ën kai ek tou plërômatos autou ëmeis pantes elabomen kai
qarin anti qaritos oti o nomos dia môseôs edoðë ë qaris kai ë alëðeia
dia iësou qristou egeneto ðeon oudeis eôraken pôpote o monogenës uios o
ôn eis ton kolpon tou patros ekeinos exëgësato kai autë estin ë marturia
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
estin ë marturia autou estin de kai alla polla osa epoiësen o iësous
atina ean grafëtai kað en oude auton oimai ton kosmon qôrësai ta
grafomena biblia amën
removed 'dat/grek/nwt/joh.1/gud.wfr'
creating the word frequency file dat/grek/nwt/joh.1/gud.wfr
the 10 most common words in dat/grek/nwt/joh.1/gud.tlw:
867 0.05446 kai
647 0.04064 o
267 0.01677 oti
248 0.01558 ton
247 0.01552 tou
239 0.01501 en
231 0.01451 de
208 0.01307 eis
205 0.01288 iësous
201 0.01263 oun
removed 'dat/grek/nwt/joh.1/gud-whole-wds-summary.tex'
removed 'exp/grek/nwt/joh.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/grek/nwt/joh.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:30:48 by tex-make-sample-summary.sh
% Token and word counts for grek/nwt/joh.1/gud.wfr
%
\def\greknwtwholejohPBgudTks{15919}
\def\greknwtwholejohPBgudTksPct{94.8}
\def\greknwtwholejohPBgudWds{2586}
\def\greknwtwholejohPBgudWdsPct{15.4}
copied '/tmp/565308.file' -> 'exp/grek/nwt/joh.1/gud-whole-wds-summary.tex'
removed '/tmp/565308.file'
creating running text file dat/grek/nwt/joh.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/grek/nwt/joh.1/bad.wfr'
creating the word frequency file dat/grek/nwt/joh.1/bad.wfr
the 10 most common words in dat/grek/nwt/joh.1/bad.tlw:
879 1.00000 =
removed 'dat/grek/nwt/joh.1/bad-whole-wds-summary.tex'
removed 'exp/grek/nwt/joh.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/grek/nwt/joh.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:30:48 by tex-make-sample-summary.sh
% Token and word counts for grek/nwt/joh.1/bad.wfr
%
\def\greknwtwholejohPBbadTks{879}
\def\greknwtwholejohPBbadTksPct{5.2}
\def\greknwtwholejohPBbadWds{1}
\def\greknwtwholejohPBbadWdsPct{0.0}
copied '/tmp/565352.file' -> 'exp/grek/nwt/joh.1/bad-whole-wds-summary.tex'
removed '/tmp/565352.file'
... creating word files dat/grek/nwt/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
69961 dat/grek/nwt/tot.1/whole.tlw
removed 'dat/grek/nwt/tot.1/raw.tlw'
removed 'dat/grek/nwt/tot.1/gud.tlw'
removed 'dat/grek/nwt/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/grek/nwt/tot.1/raw.wdf
sample:
biblos geneseôs iësou qristou uiou dauid uiou abraam =
abraam egennësen ton isaak isaak de egennësen ton iakôb iakôb de
egennësen ton ioudan kai tous adelfous autou =
ioudas de egennësen ton fares kai ton zara ek tës ðamar fares de
egennësen ton esrôm esrôm de egennësen ton aram =
aram de egennësen ton aminadab aminadab de egennësen ton naassôn naassôn
de egennësen ton salmôn =
salmôn de egennësen ton booz ek tës raqab booz de egennësen ton ôbëd ek
tës rouð ôbëd de egennësen ton iessai =
iessai de egennësen ton dauid ton basilea dauid de o basileus egennësen
ton solomôna ek tës tou ouriou =
solomôn de egennësen ton roboam roboam de egennësen ton abia abia de
egennësen ton asa =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
estin de kai alla polla osa epoiësen o iësous atina ean grafëtai kað en
oude auton oimai ton kosmon qôrësai ta grafomena biblia amën =
removed 'dat/grek/nwt/tot.1/raw.wfr'
creating the word frequency file dat/grek/nwt/tot.1/raw.wfr
the 10 most common words in dat/grek/nwt/tot.1/raw.tlw:
4705 0.06725 kai
3778 0.05400 =
1932 0.02762 o
1449 0.02071 de
1083 0.01548 tou
1073 0.01534 en
907 0.01296 autou
877 0.01254 eis
835 0.01194 ton
753 0.01076 to
removed 'dat/grek/nwt/tot.1/raw-whole-wds-summary.tex'
removed 'exp/grek/nwt/tot.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/grek/nwt/tot.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:30:48 by tex-make-sample-summary.sh
% Token and word counts for grek/nwt/tot.1/raw.wfr
%
\def\greknwtwholetotPBrawTks{69961}
\def\greknwtwholetotPBrawTksPct{100.0}
\def\greknwtwholetotPBrawWds{8302}
\def\greknwtwholetotPBrawWdsPct{11.9}
copied '/tmp/565406.file' -> 'exp/grek/nwt/tot.1/raw-whole-wds-summary.tex'
removed '/tmp/565406.file'
creating running text file dat/grek/nwt/tot.1/gud.wdf
sample:
biblos geneseôs iësou qristou uiou dauid uiou abraam abraam egennësen
ton isaak isaak de egennësen ton iakôb iakôb de egennësen ton ioudan kai
tous adelfous autou ioudas de egennësen ton fares kai ton zara ek tës
ðamar fares de egennësen ton esrôm esrôm de egennësen ton aram aram de
egennësen ton aminadab aminadab de egennësen ton naassôn naassôn de
egennësen ton salmôn salmôn de egennësen ton booz ek tës raqab booz de
egennësen ton ôbëd ek tës rouð ôbëd de egennësen ton iessai iessai de
egennësen ton dauid ton basilea dauid de o basileus egennësen ton
solomôna ek tës tou ouriou solomôn de egennësen ton roboam roboam de
egennësen ton abia abia de egennësen ton asa asa de egennësen ton
iôsafat iôsafat de egennësen ton iôram iôram de egennësen ton ozian
ozias de egennësen ton iôaðam iôaðam de egennësen ton aqaz aqaz de
egennësen ton ezekian ezekias de egennësen ton manassë manassës de
egennësen ton amôn amôn de egennësen ton iôsian iôsias de egennësen ton
ieqonian kai tous adelfous autou epi tës metoikesias babulônos meta de
tën metoikesian babulônos ieqonias egennësen ton salaðiël salaðiël de
egennësen ton zorobabel zorobabel de egennësen ton abioud abioud de
egennësen ton eliakeim eliakeim de egennësen ton azôr azôr de egennësen
ton sadôk sadôk de egennësen ton aqeim aqeim de egennësen ton elioud
elioud de egennësen ton eleazar eleazar de egennësen ton matðan matðan
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
estin ë marturia autou estin de kai alla polla osa epoiësen o iësous
atina ean grafëtai kað en oude auton oimai ton kosmon qôrësai ta
grafomena biblia amën
removed 'dat/grek/nwt/tot.1/gud.wfr'
creating the word frequency file dat/grek/nwt/tot.1/gud.wfr
the 10 most common words in dat/grek/nwt/tot.1/gud.tlw:
4705 0.07109 kai
1932 0.02919 o
1449 0.02189 de
1083 0.01636 tou
1073 0.01621 en
907 0.01370 autou
877 0.01325 eis
835 0.01262 ton
753 0.01138 to
719 0.01086 oi
removed 'dat/grek/nwt/tot.1/gud-whole-wds-summary.tex'
removed 'exp/grek/nwt/tot.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/grek/nwt/tot.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:30:48 by tex-make-sample-summary.sh
% Token and word counts for grek/nwt/tot.1/gud.wfr
%
\def\greknwtwholetotPBgudTks{66183}
\def\greknwtwholetotPBgudTksPct{94.6}
\def\greknwtwholetotPBgudWds{8301}
\def\greknwtwholetotPBgudWdsPct{11.9}
copied '/tmp/565450.file' -> 'exp/grek/nwt/tot.1/gud-whole-wds-summary.tex'
removed '/tmp/565450.file'
creating running text file dat/grek/nwt/tot.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/grek/nwt/tot.1/bad.wfr'
creating the word frequency file dat/grek/nwt/tot.1/bad.wfr
the 10 most common words in dat/grek/nwt/tot.1/bad.tlw:
3778 1.00000 =
removed 'dat/grek/nwt/tot.1/bad-whole-wds-summary.tex'
removed 'exp/grek/nwt/tot.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/grek/nwt/tot.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:30:48 by tex-make-sample-summary.sh
% Token and word counts for grek/nwt/tot.1/bad.wfr
%
\def\greknwtwholetotPBbadTks{3778}
\def\greknwtwholetotPBbadTksPct{5.4}
\def\greknwtwholetotPBbadWds{1}
\def\greknwtwholetotPBbadWdsPct{0.0}
copied '/tmp/565494.file' -> 'exp/grek/nwt/tot.1/bad-whole-wds-summary.tex'
removed '/tmp/565494.file'
lines words bytes file
------- ------- --------- ------------
3959 11874 96879 dat/grek/nwt/mat.1/raw.wfr
2899 8694 70995 dat/grek/nwt/mrk.1/raw.wfr
4610 13827 113419 dat/grek/nwt/luk.1/raw.wfr
2587 7758 62078 dat/grek/nwt/joh.1/raw.wfr
8302 24902 206528 dat/grek/nwt/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
3958 11871 96861 dat/grek/nwt/mat.1/gud.wfr
2898 8691 70977 dat/grek/nwt/mrk.1/gud.wfr
4609 13824 113401 dat/grek/nwt/luk.1/gud.wfr
2586 7755 62060 dat/grek/nwt/joh.1/gud.wfr
8301 24899 206510 dat/grek/nwt/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
1 3 18 dat/grek/nwt/mat.1/bad.wfr
1 3 18 dat/grek/nwt/mrk.1/bad.wfr
1 3 18 dat/grek/nwt/luk.1/bad.wfr
1 3 18 dat/grek/nwt/joh.1/bad.wfr
1 3 18 dat/grek/nwt/tot.1/bad.wfr
mat.1 raw = 19816 gud = 18745 bad = 1071
mrk.1 raw = 12310 gud = 11632 bad = 678
luk.1 raw = 21037 gud = 19887 bad = 1150
joh.1 raw = 16798 gud = 15919 bad = 879
tot.1 raw = 69961 gud = 66183 bad = 3778
=== creating the derived word files dat/span/qvi/*/{raw,gud,bad}.{tlw,wdf,wfr} (whole) ===
... creating word files dat/span/qvi/one.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
179274 dat/span/qvi/one.1/whole.tlw
removed 'dat/span/qvi/one.1/raw.tlw'
removed 'dat/span/qvi/one.1/gud.tlw'
removed 'dat/span/qvi/one.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/span/qvi/one.1/raw.wdf
sample:
en vn lugar de la mancha de cuyo nombre no quiero acordarme no ha mucho
tiempo que viuia vn hidalgo de los de lanįa en astillero adarga antigua
rozin flaco y galgo corredor vna olla de algo mas vaca que carnero
salpicon las mas noches duelos y quebrantos los sabados lantejas los
viernes algun palomino de aņadidura los domingos consumian las tres
partes de su hazienda el resto della concluian sayo de velarte calįas de
velludo para las fiestas con sus pantuflos de lo mesmo y los dias de
entre semana se honraua con su vellori de lo mas fino =
tenia en su casa vna ama que passaua de los quarenta y vna sobrina que
no llegaua a los veynte y vn moįo de campo y plaįa que assi ensillaua el
rozin como tomaua la podadera frisaua la edad de nuestro hidalgo con los
cinquenta aņos era de complexion rezia seco de carnes enjuto de rostro
gran madrugador y amigo de la caįa quieren dezir que tenia el
sobrenombre de quixada o quesada que en esto ay alguna diferencia en los
autores que deste caso escriuen aunque por conjeturas verosimiles se
dexa entender que se llamaua quexana pero esto importa poco a nuestro
cuento basta que en la narracion del no se salga vn punto de la verdad =
es pues de saber que este sobredicho hidalgo los ratos que estaua ocioso
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
con esperanįa de la tercera salida de don quixote =
*{/} ..*{=}
removed 'dat/span/qvi/one.1/raw.wfr'
creating the word frequency file dat/span/qvi/one.1/raw.wfr
the 10 most common words in dat/span/qvi/one.1/raw.tlw:
10276 0.05732 que
8505 0.04744 de
8260 0.04607 y
4725 0.02636 la
4648 0.02593 a
4322 0.02411 el
3804 0.02122 en
2970 0.01657 no
2460 0.01372 se
2114 0.01179 =
removed 'dat/span/qvi/one.1/raw-whole-wds-summary.tex'
removed 'exp/span/qvi/one.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/span/qvi/one.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:30:49 by tex-make-sample-summary.sh
% Token and word counts for span/qvi/one.1/raw.wfr
%
\def\spanqviwholeonePBrawTks{179274}
\def\spanqviwholeonePBrawTksPct{100.0}
\def\spanqviwholeonePBrawWds{14289}
\def\spanqviwholeonePBrawWdsPct{8.0}
copied '/tmp/565649.file' -> 'exp/span/qvi/one.1/raw-whole-wds-summary.tex'
removed '/tmp/565649.file'
creating running text file dat/span/qvi/one.1/gud.wdf
sample:
en vn lugar de la mancha de cuyo nombre no quiero acordarme no ha mucho
tiempo que viuia vn hidalgo de los de lanįa en astillero adarga antigua
rozin flaco y galgo corredor vna olla de algo mas vaca que carnero
salpicon las mas noches duelos y quebrantos los sabados lantejas los
viernes algun palomino de aņadidura los domingos consumian las tres
partes de su hazienda el resto della concluian sayo de velarte calįas de
velludo para las fiestas con sus pantuflos de lo mesmo y los dias de
entre semana se honraua con su vellori de lo mas fino tenia en su casa
vna ama que passaua de los quarenta y vna sobrina que no llegaua a los
veynte y vn moįo de campo y plaįa que assi ensillaua el rozin como
tomaua la podadera frisaua la edad de nuestro hidalgo con los cinquenta
aņos era de complexion rezia seco de carnes enjuto de rostro gran
madrugador y amigo de la caįa quieren dezir que tenia el sobrenombre de
quixada o quesada que en esto ay alguna diferencia en los autores que
deste caso escriuen aunque por conjeturas verosimiles se dexa entender
que se llamaua quexana pero esto importa poco a nuestro cuento basta que
en la narracion del no se salga vn punto de la verdad es pues de saber
que este sobredicho hidalgo los ratos que estaua ocioso que eran los mas
del aņo se daua a leer libros de cauallerias con tanta aficion y gusto
que oluidó casi de todo punto el exercicio de la caįa y aun la
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
por congeturas los declarasse tienese noticia que lo ha hecho a costa de
muchas vigilias y mucho trabajo y que tiene intencion de sacallos a luz
con esperanįa de la tercera salida de don quixote
removed 'dat/span/qvi/one.1/gud.wfr'
creating the word frequency file dat/span/qvi/one.1/gud.wfr
the 10 most common words in dat/span/qvi/one.1/gud.tlw:
10276 0.05804 que
8505 0.04803 de
8260 0.04665 y
4725 0.02669 la
4648 0.02625 a
4322 0.02441 el
3804 0.02148 en
2970 0.01677 no
2460 0.01389 se
2059 0.01163 los
removed 'dat/span/qvi/one.1/gud-whole-wds-summary.tex'
removed 'exp/span/qvi/one.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/span/qvi/one.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:30:49 by tex-make-sample-summary.sh
% Token and word counts for span/qvi/one.1/gud.wfr
%
\def\spanqviwholeonePBgudTks{177061}
\def\spanqviwholeonePBgudTksPct{98.8}
\def\spanqviwholeonePBgudWds{14247}
\def\spanqviwholeonePBgudWdsPct{7.9}
copied '/tmp/565693.file' -> 'exp/span/qvi/one.1/gud-whole-wds-summary.tex'
removed '/tmp/565693.file'
creating running text file dat/span/qvi/one.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
*{tantum} ..*{,} =
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
*{epitafio} ..*{=} =
*{/} ..*{=}
removed 'dat/span/qvi/one.1/bad.wfr'
creating the word frequency file dat/span/qvi/one.1/bad.wfr
the 10 most common words in dat/span/qvi/one.1/bad.tlw:
2114 0.95526 =
27 0.01220 ..*{=}
8 0.00362 *{soneto}
6 0.00271 ..*{,}
4 0.00181 ..*{.}
4 0.00181 ..*{ũ}
3 0.00136 *{,}
3 0.00136 *{/}
3 0.00136 *{`}
3 0.00136 *{epitafio}
removed 'dat/span/qvi/one.1/bad-whole-wds-summary.tex'
removed 'exp/span/qvi/one.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/span/qvi/one.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:30:49 by tex-make-sample-summary.sh
% Token and word counts for span/qvi/one.1/bad.wfr
%
\def\spanqviwholeonePBbadTks{2213}
\def\spanqviwholeonePBbadTksPct{1.2}
\def\spanqviwholeonePBbadWds{42}
\def\spanqviwholeonePBbadWdsPct{0.0}
copied '/tmp/565737.file' -> 'exp/span/qvi/one.1/bad-whole-wds-summary.tex'
removed '/tmp/565737.file'
... creating word files dat/span/qvi/two.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
190831 dat/span/qvi/two.1/whole.tlw
removed 'dat/span/qvi/two.1/raw.tlw'
removed 'dat/span/qvi/two.1/gud.tlw'
removed 'dat/span/qvi/two.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/span/qvi/two.1/raw.wdf
sample:
cuenta zide hamete benengeli en la segunda parte desta historia y
tercera salida de don quixote que el cura y el barbero se estuuieron
casi vn mes sin verle por no renouarle y traerle a la memoria las cosas
passadas pero no por esto dexaron de visitar a su sobrina y a su ama
encargandolas tuuiessen cuenta con regalarle dandole a comer cosas
confortatiuas y apropiadas para el coraįon y el celebro de donde
procedia segun buen discurso toda su mala ventura las quales dixeron que
assi lo hazian y lo harian con la voluntad y cuydado possible porque
echauan de ver que su seņor por momentos yua dando muestras de estar en
su entero juyzio de lo qual recibieron los dos gran contento por
parecerles que auian acertado en auerle traydo encantado en el carro de
los bueyes como se conto en la primera parte desta tan grande como
puntual historia en su vltimo capitulo y assi determinaron de visitarle
y hazer esperiencia de su mejoria aunque tenian casi por impossible que
la tuuiesse y acordaron de no tocarle en ningun punto de la andante
caualleria por no ponerse a peligro de descosser los de la herida que
tan tiernos estauan =
visitaronle en fin y hallaronle sentado en la cama vestida vna almilla
de vayeta verde con vn bonete colorado toledano y estaua tan seco y
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
las de mi verdadero don quixote van ya tropeįando y han de caer del todo
sin duda alguna *{/} ..*{.} =
removed 'dat/span/qvi/two.1/raw.wfr'
creating the word frequency file dat/span/qvi/two.1/raw.wfr
the 10 most common words in dat/span/qvi/two.1/raw.tlw:
9634 0.05048 que
9219 0.04831 y
8887 0.04657 de
5132 0.02689 la
4884 0.02559 a
4693 0.02459 el
4031 0.02112 en
3163 0.01657 no
2894 0.01517 =
2529 0.01325 los
removed 'dat/span/qvi/two.1/raw-whole-wds-summary.tex'
removed 'exp/span/qvi/two.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/span/qvi/two.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:30:49 by tex-make-sample-summary.sh
% Token and word counts for span/qvi/two.1/raw.wfr
%
\def\spanqviwholetwoPBrawTks{190831}
\def\spanqviwholetwoPBrawTksPct{100.0}
\def\spanqviwholetwoPBrawWds{16084}
\def\spanqviwholetwoPBrawWdsPct{8.4}
copied '/tmp/565792.file' -> 'exp/span/qvi/two.1/raw-whole-wds-summary.tex'
removed '/tmp/565792.file'
creating running text file dat/span/qvi/two.1/gud.wdf
sample:
cuenta zide hamete benengeli en la segunda parte desta historia y
tercera salida de don quixote que el cura y el barbero se estuuieron
casi vn mes sin verle por no renouarle y traerle a la memoria las cosas
passadas pero no por esto dexaron de visitar a su sobrina y a su ama
encargandolas tuuiessen cuenta con regalarle dandole a comer cosas
confortatiuas y apropiadas para el coraįon y el celebro de donde
procedia segun buen discurso toda su mala ventura las quales dixeron que
assi lo hazian y lo harian con la voluntad y cuydado possible porque
echauan de ver que su seņor por momentos yua dando muestras de estar en
su entero juyzio de lo qual recibieron los dos gran contento por
parecerles que auian acertado en auerle traydo encantado en el carro de
los bueyes como se conto en la primera parte desta tan grande como
puntual historia en su vltimo capitulo y assi determinaron de visitarle
y hazer esperiencia de su mejoria aunque tenian casi por impossible que
la tuuiesse y acordaron de no tocarle en ningun punto de la andante
caualleria por no ponerse a peligro de descosser los de la herida que
tan tiernos estauan visitaronle en fin y hallaronle sentado en la cama
vestida vna almilla de vayeta verde con vn bonete colorado toledano y
estaua tan seco y amoxamado que no parecia sino hecho de carne momia
fueron del muy bien recebidos preguntaronle por su salud y el dio cuenta
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
poner en aborrecimiento de los hombres las fingidas y disparatadas
historias de los libros de cauallerias que por las de mi verdadero don
quixote van ya tropeįando y han de caer del todo sin duda alguna
removed 'dat/span/qvi/two.1/gud.wfr'
creating the word frequency file dat/span/qvi/two.1/gud.wfr
the 10 most common words in dat/span/qvi/two.1/gud.tlw:
9634 0.05131 que
9219 0.04910 y
8887 0.04733 de
5132 0.02733 la
4884 0.02601 a
4693 0.02499 el
4031 0.02147 en
3163 0.01684 no
2529 0.01347 los
2419 0.01288 se
removed 'dat/span/qvi/two.1/gud-whole-wds-summary.tex'
removed 'exp/span/qvi/two.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/span/qvi/two.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:30:50 by tex-make-sample-summary.sh
% Token and word counts for span/qvi/two.1/gud.wfr
%
\def\spanqviwholetwoPBgudTks{187776}
\def\spanqviwholetwoPBgudTksPct{98.4}
\def\spanqviwholetwoPBgudWds{16023}
\def\spanqviwholetwoPBgudWdsPct{8.4}
copied '/tmp/565836.file' -> 'exp/span/qvi/two.1/gud-whole-wds-summary.tex'
removed '/tmp/565836.file'
creating running text file dat/span/qvi/two.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
*{/} ..*{.} =
removed 'dat/span/qvi/two.1/bad.wfr'
creating the word frequency file dat/span/qvi/two.1/bad.wfr
the 10 most common words in dat/span/qvi/two.1/bad.tlw:
2894 0.94730 =
33 0.01080 ..*{=}
16 0.00524 ..*{ũ}
15 0.00491 *{`}
9 0.00295 *{Ŧ}
9 0.00295 ..*{,}
5 0.00164 ..*{.}
5 0.00164 10
4 0.00131 *{/}
3 0.00098 *{Ą}
removed 'dat/span/qvi/two.1/bad-whole-wds-summary.tex'
removed 'exp/span/qvi/two.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/span/qvi/two.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:30:50 by tex-make-sample-summary.sh
% Token and word counts for span/qvi/two.1/bad.wfr
%
\def\spanqviwholetwoPBbadTks{3055}
\def\spanqviwholetwoPBbadTksPct{1.6}
\def\spanqviwholetwoPBbadWds{61}
\def\spanqviwholetwoPBbadWdsPct{0.0}
copied '/tmp/565880.file' -> 'exp/span/qvi/two.1/bad-whole-wds-summary.tex'
removed '/tmp/565880.file'
... creating word files dat/span/qvi/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
370105 dat/span/qvi/tot.1/whole.tlw
removed 'dat/span/qvi/tot.1/raw.tlw'
removed 'dat/span/qvi/tot.1/gud.tlw'
removed 'dat/span/qvi/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/span/qvi/tot.1/raw.wdf
sample:
en vn lugar de la mancha de cuyo nombre no quiero acordarme no ha mucho
tiempo que viuia vn hidalgo de los de lanįa en astillero adarga antigua
rozin flaco y galgo corredor vna olla de algo mas vaca que carnero
salpicon las mas noches duelos y quebrantos los sabados lantejas los
viernes algun palomino de aņadidura los domingos consumian las tres
partes de su hazienda el resto della concluian sayo de velarte calįas de
velludo para las fiestas con sus pantuflos de lo mesmo y los dias de
entre semana se honraua con su vellori de lo mas fino =
tenia en su casa vna ama que passaua de los quarenta y vna sobrina que
no llegaua a los veynte y vn moįo de campo y plaįa que assi ensillaua el
rozin como tomaua la podadera frisaua la edad de nuestro hidalgo con los
cinquenta aņos era de complexion rezia seco de carnes enjuto de rostro
gran madrugador y amigo de la caįa quieren dezir que tenia el
sobrenombre de quixada o quesada que en esto ay alguna diferencia en los
autores que deste caso escriuen aunque por conjeturas verosimiles se
dexa entender que se llamaua quexana pero esto importa poco a nuestro
cuento basta que en la narracion del no se salga vn punto de la verdad =
es pues de saber que este sobredicho hidalgo los ratos que estaua ocioso
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
las de mi verdadero don quixote van ya tropeįando y han de caer del todo
sin duda alguna *{/} ..*{.} =
removed 'dat/span/qvi/tot.1/raw.wfr'
creating the word frequency file dat/span/qvi/tot.1/raw.wfr
the 10 most common words in dat/span/qvi/tot.1/raw.tlw:
19910 0.05380 que
17479 0.04723 y
17392 0.04699 de
9857 0.02663 la
9532 0.02575 a
9015 0.02436 el
7835 0.02117 en
6133 0.01657 no
5008 0.01353 =
4879 0.01318 se
removed 'dat/span/qvi/tot.1/raw-whole-wds-summary.tex'
removed 'exp/span/qvi/tot.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/span/qvi/tot.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:30:50 by tex-make-sample-summary.sh
% Token and word counts for span/qvi/tot.1/raw.wfr
%
\def\spanqviwholetotPBrawTks{370105}
\def\spanqviwholetotPBrawTksPct{100.0}
\def\spanqviwholetotPBrawWds{22563}
\def\spanqviwholetotPBrawWdsPct{6.1}
copied '/tmp/565934.file' -> 'exp/span/qvi/tot.1/raw-whole-wds-summary.tex'
removed '/tmp/565934.file'
creating running text file dat/span/qvi/tot.1/gud.wdf
sample:
en vn lugar de la mancha de cuyo nombre no quiero acordarme no ha mucho
tiempo que viuia vn hidalgo de los de lanįa en astillero adarga antigua
rozin flaco y galgo corredor vna olla de algo mas vaca que carnero
salpicon las mas noches duelos y quebrantos los sabados lantejas los
viernes algun palomino de aņadidura los domingos consumian las tres
partes de su hazienda el resto della concluian sayo de velarte calįas de
velludo para las fiestas con sus pantuflos de lo mesmo y los dias de
entre semana se honraua con su vellori de lo mas fino tenia en su casa
vna ama que passaua de los quarenta y vna sobrina que no llegaua a los
veynte y vn moįo de campo y plaįa que assi ensillaua el rozin como
tomaua la podadera frisaua la edad de nuestro hidalgo con los cinquenta
aņos era de complexion rezia seco de carnes enjuto de rostro gran
madrugador y amigo de la caįa quieren dezir que tenia el sobrenombre de
quixada o quesada que en esto ay alguna diferencia en los autores que
deste caso escriuen aunque por conjeturas verosimiles se dexa entender
que se llamaua quexana pero esto importa poco a nuestro cuento basta que
en la narracion del no se salga vn punto de la verdad es pues de saber
que este sobredicho hidalgo los ratos que estaua ocioso que eran los mas
del aņo se daua a leer libros de cauallerias con tanta aficion y gusto
que oluidó casi de todo punto el exercicio de la caįa y aun la
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
poner en aborrecimiento de los hombres las fingidas y disparatadas
historias de los libros de cauallerias que por las de mi verdadero don
quixote van ya tropeįando y han de caer del todo sin duda alguna
removed 'dat/span/qvi/tot.1/gud.wfr'
creating the word frequency file dat/span/qvi/tot.1/gud.wfr
the 10 most common words in dat/span/qvi/tot.1/gud.tlw:
19910 0.05457 que
17479 0.04791 y
17392 0.04767 de
9857 0.02702 la
9532 0.02613 a
9015 0.02471 el
7835 0.02148 en
6133 0.01681 no
4879 0.01337 se
4588 0.01258 los
removed 'dat/span/qvi/tot.1/gud-whole-wds-summary.tex'
removed 'exp/span/qvi/tot.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/span/qvi/tot.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:30:51 by tex-make-sample-summary.sh
% Token and word counts for span/qvi/tot.1/gud.wfr
%
\def\spanqviwholetotPBgudTks{364837}
\def\spanqviwholetotPBgudTksPct{98.6}
\def\spanqviwholetotPBgudWds{22475}
\def\spanqviwholetotPBgudWdsPct{6.1}
copied '/tmp/565978.file' -> 'exp/span/qvi/tot.1/gud-whole-wds-summary.tex'
removed '/tmp/565978.file'
creating running text file dat/span/qvi/tot.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
*{tantum} ..*{,} =
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
*{/} ..*{.} =
removed 'dat/span/qvi/tot.1/bad.wfr'
creating the word frequency file dat/span/qvi/tot.1/bad.wfr
the 10 most common words in dat/span/qvi/tot.1/bad.tlw:
5008 0.95065 =
60 0.01139 ..*{=}
20 0.00380 ..*{ũ}
18 0.00342 *{`}
15 0.00285 ..*{,}
12 0.00228 *{Ŧ}
9 0.00171 ..*{.}
8 0.00152 *{soneto}
7 0.00133 *{/}
5 0.00095 10
removed 'dat/span/qvi/tot.1/bad-whole-wds-summary.tex'
removed 'exp/span/qvi/tot.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/span/qvi/tot.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:30:51 by tex-make-sample-summary.sh
% Token and word counts for span/qvi/tot.1/bad.wfr
%
\def\spanqviwholetotPBbadTks{5268}
\def\spanqviwholetotPBbadTksPct{1.4}
\def\spanqviwholetotPBbadWds{88}
\def\spanqviwholetotPBbadWdsPct{0.0}
copied '/tmp/566022.file' -> 'exp/span/qvi/tot.1/bad-whole-wds-summary.tex'
removed '/tmp/566022.file'
lines words bytes file
------- ------- --------- ------------
14289 42867 352961 dat/span/qvi/one.1/raw.wfr
16084 48252 397611 dat/span/qvi/two.1/raw.wfr
22563 67689 561682 dat/span/qvi/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
14247 42741 351950 dat/span/qvi/one.1/gud.wfr
16023 48069 396163 dat/span/qvi/two.1/gud.wfr
22475 67425 559560 dat/span/qvi/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
42 126 1011 dat/span/qvi/one.1/bad.wfr
61 183 1448 dat/span/qvi/two.1/bad.wfr
88 264 2122 dat/span/qvi/tot.1/bad.wfr
one.1 raw = 179274 gud = 177061 bad = 2213
two.1 raw = 190831 gud = 187776 bad = 3055
tot.1 raw = 370105 gud = 364837 bad = 5268
=== creating the derived word files dat/ital/psp/*/{raw,gud,bad}.{tlw,wdf,wfr} (whole) ===
... creating word files dat/ital/psp/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
219894 dat/ital/psp/tot.1/whole.tlw
removed 'dat/ital/psp/tot.1/raw.tlw'
removed 'dat/ital/psp/tot.1/gud.tlw'
removed 'dat/ital/psp/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/ital/psp/tot.1/raw.wdf
sample:
quel ramo del lago di como che volge a mezzogiorno tra due catene non
interrotte di monti tutto a seni e a golfi a seconda dello sporgere e
del rientrare di quelli vien quasi a un tratto a ristringersi e a
prender corso e figura di fiume tra un promontorio a destra e un' ampia
costiera dall' altra parte e il ponte che ivi congiunge le due rive par
che renda ancor pių sensibile all' occhio questa trasformazione e segni
il punto in cui il lago cessa e l' adda rincomincia per ripigliar poi
nome di lago dove le rive allontanandosi di nuovo lascian l' acqua
distendersi e rallentarsi in nuovi golfi e in nuovi seni la costiera
formata dal deposito di tre grossi torrenti scende appoggiata a due
monti contigui l' uno detto di san martino l' altro con voce lombarda il
resegone dai molti suoi cocuzzoli in fila che in vero lo fanno
somigliare a una sega talché non č chi al primo vederlo purché sia di
fronte come per esempio di su le mura di milano che guardano a
settentrione non lo discerna tosto a un tal contrassegno in quella lunga
e vasta giogaia dagli altri monti di nome pių oscuro e di forma pių
comune per un buon pezzo la costa sale con un pendėo lento e continuo
poi si rompe in poggi e in valloncelli in erte e in ispianate secondo l'
ossatura de' due monti e il lavoro dell' acque il lembo estremo tagliato
dalle foci de' torrenti č quasi tutto ghiaia e ciottoloni il resto campi
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
scritta e anche un pochino a chi l' ha raccomodata ma se in vece fossimo
riusciti ad annoiarvi credete che non s' č fatto apposta =
removed 'dat/ital/psp/tot.1/raw.wfr'
creating the word frequency file dat/ital/psp/tot.1/raw.wfr
the 10 most common words in dat/ital/psp/tot.1/raw.tlw:
7926 0.03604 e
6459 0.02937 che
6120 0.02783 di
4496 0.02045 a
3829 0.01741 il
3551 0.01615 la
3395 0.01544 un
3353 0.01525 in
3284 0.01493 non
2740 0.01246 per
removed 'dat/ital/psp/tot.1/raw-whole-wds-summary.tex'
removed 'exp/ital/psp/tot.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/ital/psp/tot.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:30:51 by tex-make-sample-summary.sh
% Token and word counts for ital/psp/tot.1/raw.wfr
%
\def\italpspwholetotPBrawTks{219894}
\def\italpspwholetotPBrawTksPct{100.0}
\def\italpspwholetotPBrawWds{19053}
\def\italpspwholetotPBrawWdsPct{8.7}
copied '/tmp/566147.file' -> 'exp/ital/psp/tot.1/raw-whole-wds-summary.tex'
removed '/tmp/566147.file'
creating running text file dat/ital/psp/tot.1/gud.wdf
sample:
quel ramo del lago di como che volge a mezzogiorno tra due catene non
interrotte di monti tutto a seni e a golfi a seconda dello sporgere e
del rientrare di quelli vien quasi a un tratto a ristringersi e a
prender corso e figura di fiume tra un promontorio a destra e un' ampia
costiera dall' altra parte e il ponte che ivi congiunge le due rive par
che renda ancor pių sensibile all' occhio questa trasformazione e segni
il punto in cui il lago cessa e l' adda rincomincia per ripigliar poi
nome di lago dove le rive allontanandosi di nuovo lascian l' acqua
distendersi e rallentarsi in nuovi golfi e in nuovi seni la costiera
formata dal deposito di tre grossi torrenti scende appoggiata a due
monti contigui l' uno detto di san martino l' altro con voce lombarda il
resegone dai molti suoi cocuzzoli in fila che in vero lo fanno
somigliare a una sega talché non č chi al primo vederlo purché sia di
fronte come per esempio di su le mura di milano che guardano a
settentrione non lo discerna tosto a un tal contrassegno in quella lunga
e vasta giogaia dagli altri monti di nome pių oscuro e di forma pių
comune per un buon pezzo la costa sale con un pendėo lento e continuo
poi si rompe in poggi e in valloncelli in erte e in ispianate secondo l'
ossatura de' due monti e il lavoro dell' acque il lembo estremo tagliato
dalle foci de' torrenti č quasi tutto ghiaia e ciottoloni il resto campi
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
storia la quale se non v' č dispiaciuta affatto vogliatene bene a chi l'
ha scritta e anche un pochino a chi l' ha raccomodata ma se in vece
fossimo riusciti ad annoiarvi credete che non s' č fatto apposta
removed 'dat/ital/psp/tot.1/gud.wfr'
creating the word frequency file dat/ital/psp/tot.1/gud.wfr
the 10 most common words in dat/ital/psp/tot.1/gud.tlw:
7926 0.03653 e
6459 0.02977 che
6120 0.02821 di
4496 0.02072 a
3829 0.01765 il
3551 0.01637 la
3395 0.01565 un
3353 0.01545 in
3284 0.01514 non
2740 0.01263 per
removed 'dat/ital/psp/tot.1/gud-whole-wds-summary.tex'
removed 'exp/ital/psp/tot.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/ital/psp/tot.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:30:51 by tex-make-sample-summary.sh
% Token and word counts for ital/psp/tot.1/gud.wfr
%
\def\italpspwholetotPBgudTks{216969}
\def\italpspwholetotPBgudTksPct{98.7}
\def\italpspwholetotPBgudWds{18965}
\def\italpspwholetotPBgudWdsPct{8.6}
copied '/tmp/566191.file' -> 'exp/ital/psp/tot.1/gud-whole-wds-summary.tex'
removed '/tmp/566191.file'
creating running text file dat/ital/psp/tot.1/bad.wdf
sample:
=
7 1628 =
=
1583 12 =
*{/} ..*{/} =
*{juan} ..*{,} 5 1593 23 1598 =
5 1600 =
22 1612 *{de} ..*{,} 24 1618 5 1627 =
13 1632 *{/} ..*{,} =
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/ital/psp/tot.1/bad.wfr'
creating the word frequency file dat/ital/psp/tot.1/bad.wfr
the 10 most common words in dat/ital/psp/tot.1/bad.tlw:
2610 0.89231 =
79 0.02701 *{/}
33 0.01128 ..*{,}
29 0.00991 ..*{.}
19 0.00650 ***
17 0.00581 ..*{/}
8 0.00274 ..*{;}
5 0.00171 *{(}
5 0.00171 *{-}
5 0.00171 1630
removed 'dat/ital/psp/tot.1/bad-whole-wds-summary.tex'
removed 'exp/ital/psp/tot.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/ital/psp/tot.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:30:52 by tex-make-sample-summary.sh
% Token and word counts for ital/psp/tot.1/bad.wfr
%
\def\italpspwholetotPBbadTks{2925}
\def\italpspwholetotPBbadTksPct{1.3}
\def\italpspwholetotPBbadWds{88}
\def\italpspwholetotPBbadWdsPct{0.0}
copied '/tmp/566235.file' -> 'exp/ital/psp/tot.1/bad-whole-wds-summary.tex'
removed '/tmp/566235.file'
lines words bytes file
------- ------- --------- ------------
19053 57157 479573 dat/ital/psp/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
18965 56894 477738 dat/ital/psp/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
88 263 1835 dat/ital/psp/tot.1/bad.wfr
tot.1 raw = 219894 gud = 216969 bad = 2925
=== creating the derived word files dat/fran/tal/*/{raw,gud,bad}.{tlw,wdf,wfr} (whole) ===
... creating word files dat/fran/tal/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
55551 dat/fran/tal/tot.1/whole.tlw
removed 'dat/fran/tal/tot.1/raw.tlw'
removed 'dat/fran/tal/tot.1/gud.tlw'
removed 'dat/fran/tal/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/fran/tal/tot.1/raw.wdf
sample:
pendant la guerre fédérale des états unis un nouveau club trčs influent
s' établit dans la ville de baltimore en plein maryland on sait avec
quelle énergie l' instinct militaire se développa chez ce peuple d'
armateurs de marchands et de mécaniciens de simples négociants
enjambčrent leur comptoir pour s' improviser capitaines colonels
généraux sans avoir passé par les écoles d' application de west point
ils égalčrent bientôt dans l' art de la guerre leurs collčgues du vieux
continent et comme eux ils remportčrent des victoires ā force de
prodiguer les boulets les millions et les hommes =
*{école} ..*{.} mais en quoi les américains surpassčrent singuličrement
les européens ce fut dans la science de la balistique non que leurs
armes atteignissent un plus haut degré de perfection mais elles
offrirent des dimensions inusitées et eurent par conséquent des portées
inconnues jusqu' alors en fait de tirs rasants plongeants ou de plein
fouet de feux d' écharpe d' enfilade ou de revers les anglais les
franįais les prussiens n' ont plus rien ā apprendre mais leurs canons
leurs obusiers leurs mortiers ne sont que des pistolets de poche auprčs
des formidables engins de l' artillerie américaine =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
de l' art de la science et de l' industrie avec cela on fait ce qu' on
veut et vous verrez qu' ils se tireront d' affaire =
removed 'dat/fran/tal/tot.1/raw.wfr'
creating the word frequency file dat/fran/tal/tot.1/raw.wfr
the 10 most common words in dat/fran/tal/tot.1/raw.tlw:
2446 0.04403 de
1406 0.02531 la
1166 0.02099 =
1166 0.02099 et
1151 0.02072 le
1149 0.02068 ā
1067 0.01921 les
1060 0.01908 l'
826 0.01487 un
759 0.01366 il
removed 'dat/fran/tal/tot.1/raw-whole-wds-summary.tex'
removed 'exp/fran/tal/tot.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/fran/tal/tot.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:30:52 by tex-make-sample-summary.sh
% Token and word counts for fran/tal/tot.1/raw.wfr
%
\def\frantalwholetotPBrawTks{55551}
\def\frantalwholetotPBrawTksPct{100.0}
\def\frantalwholetotPBrawWds{8242}
\def\frantalwholetotPBrawWdsPct{14.8}
copied '/tmp/566330.file' -> 'exp/fran/tal/tot.1/raw-whole-wds-summary.tex'
removed '/tmp/566330.file'
creating running text file dat/fran/tal/tot.1/gud.wdf
sample:
pendant la guerre fédérale des états unis un nouveau club trčs influent
s' établit dans la ville de baltimore en plein maryland on sait avec
quelle énergie l' instinct militaire se développa chez ce peuple d'
armateurs de marchands et de mécaniciens de simples négociants
enjambčrent leur comptoir pour s' improviser capitaines colonels
généraux sans avoir passé par les écoles d' application de west point
ils égalčrent bientôt dans l' art de la guerre leurs collčgues du vieux
continent et comme eux ils remportčrent des victoires ā force de
prodiguer les boulets les millions et les hommes mais en quoi les
américains surpassčrent singuličrement les européens ce fut dans la
science de la balistique non que leurs armes atteignissent un plus haut
degré de perfection mais elles offrirent des dimensions inusitées et
eurent par conséquent des portées inconnues jusqu' alors en fait de tirs
rasants plongeants ou de plein fouet de feux d' écharpe d' enfilade ou
de revers les anglais les franįais les prussiens n' ont plus rien ā
apprendre mais leurs canons leurs obusiers leurs mortiers ne sont que
des pistolets de poche auprčs des formidables engins de l' artillerie
américaine ceci ne doit étonner personne les yankees ces premiers
mécaniciens du monde sont ingénieurs comme les italiens sont musiciens
et les allemands métaphysiciens de naissance rien de plus naturel dčs
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
ingénieux a eux trois ils emportent dans l' espace toutes les ressources
de l' art de la science et de l' industrie avec cela on fait ce qu' on
veut et vous verrez qu' ils se tireront d' affaire
removed 'dat/fran/tal/tot.1/gud.wfr'
creating the word frequency file dat/fran/tal/tot.1/gud.wfr
the 10 most common words in dat/fran/tal/tot.1/gud.tlw:
2446 0.04525 de
1406 0.02601 la
1166 0.02157 et
1151 0.02129 le
1149 0.02125 ā
1067 0.01974 les
1060 0.01961 l'
826 0.01528 un
759 0.01404 il
748 0.01384 d'
removed 'dat/fran/tal/tot.1/gud-whole-wds-summary.tex'
removed 'exp/fran/tal/tot.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/fran/tal/tot.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:30:52 by tex-make-sample-summary.sh
% Token and word counts for fran/tal/tot.1/gud.wfr
%
\def\frantalwholetotPBgudTks{54061}
\def\frantalwholetotPBgudTksPct{97.3}
\def\frantalwholetotPBgudWds{8102}
\def\frantalwholetotPBgudWdsPct{14.6}
copied '/tmp/566374.file' -> 'exp/fran/tal/tot.1/gud-whole-wds-summary.tex'
removed '/tmp/566374.file'
creating running text file dat/fran/tal/tot.1/bad.wdf
sample:
=
*{école} ..*{.} =
=
=
*{badaud} *{.} =
*{littéralement} ..*{.} =
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/fran/tal/tot.1/bad.wfr'
creating the word frequency file dat/fran/tal/tot.1/bad.wfr
the 10 most common words in dat/fran/tal/tot.1/bad.tlw:
1166 0.78255 =
79 0.05302 ..*{.}
10 0.00671 *{_}
8 0.00537 ..*{_}
8 0.00537 3
6 0.00403 10
6 0.00403 20
6 0.00403 4
5 0.00336 *{c'}
5 0.00336 *{le}
removed 'dat/fran/tal/tot.1/bad-whole-wds-summary.tex'
removed 'exp/fran/tal/tot.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/fran/tal/tot.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:30:52 by tex-make-sample-summary.sh
% Token and word counts for fran/tal/tot.1/bad.wfr
%
\def\frantalwholetotPBbadTks{1490}
\def\frantalwholetotPBbadTksPct{2.7}
\def\frantalwholetotPBbadWds{140}
\def\frantalwholetotPBbadWdsPct{0.3}
copied '/tmp/566418.file' -> 'exp/fran/tal/tot.1/bad-whole-wds-summary.tex'
removed '/tmp/566418.file'
lines words bytes file
------- ------- --------- ------------
8242 24723 203708 dat/fran/tal/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
8102 24303 200608 dat/fran/tal/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
140 420 3100 dat/fran/tal/tot.1/bad.wfr
tot.1 raw = 55551 gud = 54061 bad = 1490
=== creating the derived word files dat/port/csm/*/{raw,gud,bad}.{tlw,wdf,wfr} (whole) ===
... creating word files dat/port/csm/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
64691 dat/port/csm/tot.1/whole.tlw
removed 'dat/port/csm/tot.1/raw.tlw'
removed 'dat/port/csm/tot.1/gud.tlw'
removed 'dat/port/csm/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/port/csm/tot.1/raw.wdf
sample:
uma noite destas vindo da cidade para o engenho novo encontrei no trem
da central um rapaz aqui do bairro que eu conheįo de vista e de chapéu
cumprimentou~me sentou~se ao pé de mim falou da lua e dos ministros e
acabou recitando~me versos a viagem era curta e os versos pode ser que
não fossem inteiramente maus sucedeu porém que como eu estava cansado
fechei os olhos tręs ou quatro vezes tanto bastou para que ele
interrompesse a leitura e metesse os versos no bolso continue disse eu
acordando já acabei murmurou ele são muito bonitos vi~lhe fazer um gesto
para tirá~los outra vez do bolso mas não passou do gesto estava amuado
no dia seguinte entrou a dizer de mim nomes feios e acabou alcunhando~me
dom casmurro os vizinhos que não gostam dos meus hábitos reclusos e
calados deram curso ā alcunha que afinal pegou nem por isso me zanguei
contei a anedota aos amigos da cidade e eles por graįa chamam~me assim
alguns em bilhetes dom casmurro domingo vou jantar com vocę vou para
petrópolis dom casmurro a casa é a mesma da renânia vę se deixas essa
caverna do engenho novo e vai lá passar uns quinze dias comigo meu caro
dom casmurro não cuide que o dispenso do teatro amanhã venha e dormirá
aqui na cidade dou~lhe camarote dou~lhe chá dou~lhe cama só não lhe dou
moįa não consultes dicionários casmurro não está aqui no sentido que
eles lhe dão mas no que lhe pôs o vulgo de homem calado e metido consigo
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
minha primeira amiga e o meu maior amigo tão extremosos ambos e tão
queridos também quis o destino que acabassem juntando~se e enganando~me
a terra lhes seja leve vamos ā história dos subúrbios
removed 'dat/port/csm/tot.1/raw.wfr'
creating the word frequency file dat/port/csm/tot.1/raw.wfr
the 10 most common words in dat/port/csm/tot.1/raw.tlw:
2677 0.04138 que
2461 0.03804 a
2179 0.03368 e
1950 0.03014 de
1646 0.02544 o
1527 0.02360 não
760 0.01175 um
714 0.01104 é
661 0.01022 os
625 0.00966 da
removed 'dat/port/csm/tot.1/raw-whole-wds-summary.tex'
removed 'exp/port/csm/tot.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/port/csm/tot.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:30:52 by tex-make-sample-summary.sh
% Token and word counts for port/csm/tot.1/raw.wfr
%
\def\portcsmwholetotPBrawTks{64691}
\def\portcsmwholetotPBrawTksPct{100.0}
\def\portcsmwholetotPBrawWds{9079}
\def\portcsmwholetotPBrawWdsPct{14.0}
copied '/tmp/566513.file' -> 'exp/port/csm/tot.1/raw-whole-wds-summary.tex'
removed '/tmp/566513.file'
creating running text file dat/port/csm/tot.1/gud.wdf
sample:
uma noite destas vindo da cidade para o engenho novo encontrei no trem
da central um rapaz aqui do bairro que eu conheįo de vista e de chapéu
cumprimentou~me sentou~se ao pé de mim falou da lua e dos ministros e
acabou recitando~me versos a viagem era curta e os versos pode ser que
não fossem inteiramente maus sucedeu porém que como eu estava cansado
fechei os olhos tręs ou quatro vezes tanto bastou para que ele
interrompesse a leitura e metesse os versos no bolso continue disse eu
acordando já acabei murmurou ele são muito bonitos vi~lhe fazer um gesto
para tirá~los outra vez do bolso mas não passou do gesto estava amuado
no dia seguinte entrou a dizer de mim nomes feios e acabou alcunhando~me
dom casmurro os vizinhos que não gostam dos meus hábitos reclusos e
calados deram curso ā alcunha que afinal pegou nem por isso me zanguei
contei a anedota aos amigos da cidade e eles por graįa chamam~me assim
alguns em bilhetes dom casmurro domingo vou jantar com vocę vou para
petrópolis dom casmurro a casa é a mesma da renânia vę se deixas essa
caverna do engenho novo e vai lá passar uns quinze dias comigo meu caro
dom casmurro não cuide que o dispenso do teatro amanhã venha e dormirá
aqui na cidade dou~lhe camarote dou~lhe chá dou~lhe cama só não lhe dou
moįa não consultes dicionários casmurro não está aqui no sentido que
eles lhe dão mas no que lhe pôs o vulgo de homem calado e metido consigo
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
tão extremosos ambos e tão queridos também quis o destino que acabassem
juntando~se e enganando~me a terra lhes seja leve vamos ā história dos
subúrbios
removed 'dat/port/csm/tot.1/gud.wfr'
creating the word frequency file dat/port/csm/tot.1/gud.wfr
the 10 most common words in dat/port/csm/tot.1/gud.tlw:
2677 0.04144 que
2461 0.03809 a
2179 0.03373 e
1950 0.03018 de
1646 0.02548 o
1527 0.02364 não
760 0.01176 um
714 0.01105 é
661 0.01023 os
625 0.00967 da
removed 'dat/port/csm/tot.1/gud-whole-wds-summary.tex'
removed 'exp/port/csm/tot.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/port/csm/tot.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:30:52 by tex-make-sample-summary.sh
% Token and word counts for port/csm/tot.1/gud.wfr
%
\def\portcsmwholetotPBgudTks{64602}
\def\portcsmwholetotPBgudTksPct{99.9}
\def\portcsmwholetotPBgudWds{9032}
\def\portcsmwholetotPBgudWdsPct{14.0}
copied '/tmp/566557.file' -> 'exp/port/csm/tot.1/gud-whole-wds-summary.tex'
removed '/tmp/566557.file'
creating running text file dat/port/csm/tot.1/bad.wdf
sample:
1857 1857 *{_} ..*{_} *{_} ..*{_} *{_} ..*{_} *{_} ..*{_} *{_} ..*{_}
*{_} ..*{?} 6š *{_} ..*{_} x 1882 1859 1860 58 1859 1860 4004 *{_}
..*{_} *{_} ..*{_} *{_} ..*{_} 1858 1851 *{_} ..*{_} *{_} ..*{_} 1824
1825 *{2+2} ..*{4} d t b p s c z k g 4 4 7 7 4 7 11 11 22 484 5 5 00 500
p pp 1Ķ070$000 70$000 180$000 1Ķ070$000 1Ķ070$000 *{_} ..*{_} 1865 1858
cx rãs 20 4 70 1871 *{_} ..*{fronde} 1872 *{_} ..*{_} *{_} ..*{_} 1
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
1825 *{2+2} ..*{4} d t b p s c z k g 4 4 7 7 4 7 11 11 22 484 5 5 00 500
p pp 1Ķ070$000 70$000 180$000 1Ķ070$000 1Ķ070$000 *{_} ..*{_} 1865 1858
cx rãs 20 4 70 1871 *{_} ..*{fronde} 1872 *{_} ..*{_} *{_} ..*{_} 1
removed 'dat/port/csm/tot.1/bad.wfr'
creating the word frequency file dat/port/csm/tot.1/bad.wfr
the 10 most common words in dat/port/csm/tot.1/bad.tlw:
16 0.17978 *{_}
14 0.15730 ..*{_}
4 0.04494 4
3 0.03371 1Ķ070$000
3 0.03371 7
2 0.02247 11
2 0.02247 1857
2 0.02247 1858
2 0.02247 1859
2 0.02247 1860
removed 'dat/port/csm/tot.1/bad-whole-wds-summary.tex'
removed 'exp/port/csm/tot.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/port/csm/tot.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:30:52 by tex-make-sample-summary.sh
% Token and word counts for port/csm/tot.1/bad.wfr
%
\def\portcsmwholetotPBbadTks{89}
\def\portcsmwholetotPBbadTksPct{0.1}
\def\portcsmwholetotPBbadWds{47}
\def\portcsmwholetotPBbadWdsPct{0.1}
copied '/tmp/566601.file' -> 'exp/port/csm/tot.1/bad-whole-wds-summary.tex'
removed '/tmp/566601.file'
lines words bytes file
------- ------- --------- ------------
9079 27234 223126 dat/port/csm/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
9032 27093 222177 dat/port/csm/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
47 141 949 dat/port/csm/tot.1/bad.wfr
tot.1 raw = 64691 gud = 64602 bad = 89
=== creating the derived word files dat/germ/sim/*/{raw,gud,bad}.{tlw,wdf,wfr} (whole) ===
... creating word files dat/germ/sim/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
185396 dat/germ/sim/tot.1/whole.tlw
removed 'dat/germ/sim/tot.1/raw.tlw'
removed 'dat/germ/sim/tot.1/gud.tlw'
removed 'dat/germ/sim/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/germ/sim/tot.1/raw.wdf
sample:
es eröffnet sich zu dieser unserer zeit von welcher man glaubt daß es
die letzte sei unter geringen leuten eine sucht in der die patienten
wenn sie daran krank liegen und so viel zusammen geraspelt und
erschachert haben daß sie neben ein paar hellern im beutel ein
närrisches kleid auf die neue mode mit tausenderlei seidenen bändern
antragen können oder sonst etwa durch glücksfall mannhaft und bekannt
worden gleich rittermäßige herren und adelige personen von uraltem
geschlecht sein wollen da sich doch oft befindet daß ihre voreltern
taglöhner karchelzieher und lastträger ihre vettern eseltreiber ihre
brüder büttel und schergen ihre schwestern huren ihre mütter
kupplerinnen oder gar hexen und in summa ihr ganzes geschlecht von allen
32 anichen her also besudelt und befleckt gewesen als des zuckerbastels
zunft zu prag immer sein mögen ja sie diese neuen nobilisten sind oft
selbst so schwarz als wenn sie in guinea geboren und erzogen wären
worden =
solchen närrischen leuten nun mag ich mich nicht gleich stellen obzwar
die wahrheit zu bekennen nicht ohn ist daß ich mir oft eingebildet ich
müsse ohnfehlbar auch von einem großen herrn oder wenigst einem gemeinen
edelmann meinen ursprung haben weil ich von natur geneigt das
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
wiederum zu kräften kamen und der teutsche selbst die ganze zeit so er
daselbst gewesen von krankheit nichts gewahr worden =
removed 'dat/germ/sim/tot.1/raw.wfr'
creating the word frequency file dat/germ/sim/tot.1/raw.wfr
the 10 most common words in dat/germ/sim/tot.1/raw.tlw:
6991 0.03771 und
5588 0.03014 ich
3211 0.01732 zu
3158 0.01703 die
2800 0.01510 der
2564 0.01383 er
2182 0.01177 daß
2170 0.01170 so
2128 0.01148 in
1939 0.01046 ein
removed 'dat/germ/sim/tot.1/raw-whole-wds-summary.tex'
removed 'exp/germ/sim/tot.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/germ/sim/tot.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:30:52 by tex-make-sample-summary.sh
% Token and word counts for germ/sim/tot.1/raw.wfr
%
\def\germsimwholetotPBrawTks{185396}
\def\germsimwholetotPBrawTksPct{100.0}
\def\germsimwholetotPBrawWds{18657}
\def\germsimwholetotPBrawWdsPct{10.1}
copied '/tmp/566696.file' -> 'exp/germ/sim/tot.1/raw-whole-wds-summary.tex'
removed '/tmp/566696.file'
creating running text file dat/germ/sim/tot.1/gud.wdf
sample:
es eröffnet sich zu dieser unserer zeit von welcher man glaubt daß es
die letzte sei unter geringen leuten eine sucht in der die patienten
wenn sie daran krank liegen und so viel zusammen geraspelt und
erschachert haben daß sie neben ein paar hellern im beutel ein
närrisches kleid auf die neue mode mit tausenderlei seidenen bändern
antragen können oder sonst etwa durch glücksfall mannhaft und bekannt
worden gleich rittermäßige herren und adelige personen von uraltem
geschlecht sein wollen da sich doch oft befindet daß ihre voreltern
taglöhner karchelzieher und lastträger ihre vettern eseltreiber ihre
brüder büttel und schergen ihre schwestern huren ihre mütter
kupplerinnen oder gar hexen und in summa ihr ganzes geschlecht von allen
anichen her also besudelt und befleckt gewesen als des zuckerbastels
zunft zu prag immer sein mögen ja sie diese neuen nobilisten sind oft
selbst so schwarz als wenn sie in guinea geboren und erzogen wären
worden solchen närrischen leuten nun mag ich mich nicht gleich stellen
obzwar die wahrheit zu bekennen nicht ohn ist daß ich mir oft
eingebildet ich müsse ohnfehlbar auch von einem großen herrn oder
wenigst einem gemeinen edelmann meinen ursprung haben weil ich von natur
geneigt das junkernhandwerk zu treiben wenn ich nur den verlag und das
werkzeug dazu hätte zwar ohngescherzt mein herkommen und auferziehung
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
ort in der welt weil unser kranken innerhalb fünf tagen alle miteinander
wiederum zu kräften kamen und der teutsche selbst die ganze zeit so er
daselbst gewesen von krankheit nichts gewahr worden
removed 'dat/germ/sim/tot.1/gud.wfr'
creating the word frequency file dat/germ/sim/tot.1/gud.wfr
the 10 most common words in dat/germ/sim/tot.1/gud.tlw:
6991 0.03789 und
5588 0.03029 ich
3211 0.01740 zu
3158 0.01712 die
2800 0.01518 der
2564 0.01390 er
2182 0.01183 daß
2170 0.01176 so
2128 0.01153 in
1939 0.01051 ein
removed 'dat/germ/sim/tot.1/gud-whole-wds-summary.tex'
removed 'exp/germ/sim/tot.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/germ/sim/tot.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:30:53 by tex-make-sample-summary.sh
% Token and word counts for germ/sim/tot.1/gud.wfr
%
\def\germsimwholetotPBgudTks{184498}
\def\germsimwholetotPBgudTksPct{99.5}
\def\germsimwholetotPBgudWds{18556}
\def\germsimwholetotPBgudWdsPct{10.0}
copied '/tmp/566740.file' -> 'exp/germ/sim/tot.1/gud-whole-wds-summary.tex'
removed '/tmp/566740.file'
creating running text file dat/germ/sim/tot.1/bad.wdf
sample:
32 =
=
=
600 000 =
=
=
*{du} ..*{=} =
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
100 000 =
removed 'dat/germ/sim/tot.1/bad.wfr'
creating the word frequency file dat/germ/sim/tot.1/bad.wfr
the 10 most common words in dat/germ/sim/tot.1/bad.tlw:
730 0.81292 =
16 0.01782 ..*{=}
9 0.01002 *{>}
8 0.00891 ..*{,}
8 0.00891 ..*{<}
7 0.00780 *{ŧ}
7 0.00780 000
4 0.00445 ..*{Ŧ}
3 0.00334 ..*{.}
3 0.00334 26š
removed 'dat/germ/sim/tot.1/bad-whole-wds-summary.tex'
removed 'exp/germ/sim/tot.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/germ/sim/tot.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:30:53 by tex-make-sample-summary.sh
% Token and word counts for germ/sim/tot.1/bad.wfr
%
\def\germsimwholetotPBbadTks{898}
\def\germsimwholetotPBbadTksPct{0.5}
\def\germsimwholetotPBbadWds{101}
\def\germsimwholetotPBbadWdsPct{0.1}
copied '/tmp/566784.file' -> 'exp/germ/sim/tot.1/bad-whole-wds-summary.tex'
removed '/tmp/566784.file'
lines words bytes file
------- ------- --------- ------------
18657 55971 475558 dat/germ/sim/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
18556 55668 473282 dat/germ/sim/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
101 303 2276 dat/germ/sim/tot.1/bad.wfr
tot.1 raw = 185396 gud = 184498 bad = 898
=== creating the derived word files dat/russ/pic/*/{raw,gud,bad}.{tlw,wdf,wfr} (whole) ===
... creating word files dat/russ/pic/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
47369 dat/russ/pic/tot.1/whole.tlw
removed 'dat/russ/pic/tot.1/raw.tlw'
removed 'dat/russ/pic/tot.1/gud.tlw'
removed 'dat/russ/pic/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/russ/pic/tot.1/raw.wdf
sample:
nakanune stoim eto my s nim v hranilishche uzhe vecherom ostaetsya
tol'ko specovki sbrosit' i mozhno zakatit'sya v borzhch prinyat' v
organizm kapel'ku druguyu krepkogo ya stoyu prosto tak stenu podpirayu
svoe otrabotal i uzhe derzhu nagotove sigaretku kurit' hochetsya diko
dva chasa ne kuril a on vse vozitsya so svoim dobrom odin sejf zagruzil
zaper i opechatal teper' drugoj zagruzhaet beret s transportera
pustyshki kazhduyu so vseh storon osmatrivaet a ona tyazhelaya svoloch'
shest' s polovinoj kilo mezhdu prochim i s kryahten'em akkuratnen'ko
vodvoryaet na polku =
skol'ko uzhe vremeni on s etimi pustyshkami b'etsya i po moemu bez
vsyakoj pol'zy dlya chelovechestva na ego meste ya davnym davno by uzhe
plyunul i chem nibud' drugim zanyalsya za te zhe den'gi hotya s drugoj
storony esli podumat' pustyshka dejstvitel'no shtuka zagadochnaya i
kakaya to nevrazumitel'naya chto li skol'ko ya ih na sebe peretaskal a
vse ravno kazhdyj raz kak uvizhu ne mogu porazhayus' vsego to v nej dva
mednyh diska s chajnoe blyudce millimetrov pyat' tolshchinoj i
rasstoyanie mezhdu diskami millimetrov chetyresta i krome etogo
rasstoyaniya nichego mezhdu nimi net to est' sovsem nichego pusto mozhno
tuda prosunut' ruku mozhno i golovu esli ty sovsem obaldel ot izumleniya
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
hochu ved' ne mozhet zhe byt' chtoby ya hotel plohogo bud' ono vse
proklyato ved' ya nichego ne mogu pridumat' krome etih ego slov schastxe
dlya vseh darom i pustx nikto ne ujdet obizhennyj
removed 'dat/russ/pic/tot.1/raw.wfr'
creating the word frequency file dat/russ/pic/tot.1/raw.wfr
the 10 most common words in dat/russ/pic/tot.1/raw.tlw:
1881 0.03971 i
1445 0.03051 =
1027 0.02168 ne
1005 0.02122 v
833 0.01759 on
778 0.01642 na
592 0.01250 ya
577 0.01218 chto
568 0.01199 a
484 0.01022 s
removed 'dat/russ/pic/tot.1/raw-whole-wds-summary.tex'
removed 'exp/russ/pic/tot.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/russ/pic/tot.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:30:53 by tex-make-sample-summary.sh
% Token and word counts for russ/pic/tot.1/raw.wfr
%
\def\russpicwholetotPBrawTks{47369}
\def\russpicwholetotPBrawTksPct{100.0}
\def\russpicwholetotPBrawWds{11837}
\def\russpicwholetotPBrawWdsPct{25.0}
copied '/tmp/566879.file' -> 'exp/russ/pic/tot.1/raw-whole-wds-summary.tex'
removed '/tmp/566879.file'
creating running text file dat/russ/pic/tot.1/gud.wdf
sample:
nakanune stoim eto my s nim v hranilishche uzhe vecherom ostaetsya
tol'ko specovki sbrosit' i mozhno zakatit'sya v borzhch prinyat' v
organizm kapel'ku druguyu krepkogo ya stoyu prosto tak stenu podpirayu
svoe otrabotal i uzhe derzhu nagotove sigaretku kurit' hochetsya diko
dva chasa ne kuril a on vse vozitsya so svoim dobrom odin sejf zagruzil
zaper i opechatal teper' drugoj zagruzhaet beret s transportera
pustyshki kazhduyu so vseh storon osmatrivaet a ona tyazhelaya svoloch'
shest' s polovinoj kilo mezhdu prochim i s kryahten'em akkuratnen'ko
vodvoryaet na polku skol'ko uzhe vremeni on s etimi pustyshkami b'etsya
i po moemu bez vsyakoj pol'zy dlya chelovechestva na ego meste ya davnym
davno by uzhe plyunul i chem nibud' drugim zanyalsya za te zhe den'gi
hotya s drugoj storony esli podumat' pustyshka dejstvitel'no shtuka
zagadochnaya i kakaya to nevrazumitel'naya chto li skol'ko ya ih na sebe
peretaskal a vse ravno kazhdyj raz kak uvizhu ne mogu porazhayus' vsego
to v nej dva mednyh diska s chajnoe blyudce millimetrov pyat'
tolshchinoj i rasstoyanie mezhdu diskami millimetrov chetyresta i krome
etogo rasstoyaniya nichego mezhdu nimi net to est' sovsem nichego pusto
mozhno tuda prosunut' ruku mozhno i golovu esli ty sovsem obaldel ot
izumleniya pustota i pustota odin vozduh i pri vsem pri tom chto to
mezhdu nimi konechno est' sila kakaya to kak ya eto ponimayu potomu chto
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
hochu ved' ne mozhet zhe byt' chtoby ya hotel plohogo bud' ono vse
proklyato ved' ya nichego ne mogu pridumat' krome etih ego slov schastxe
dlya vseh darom i pustx nikto ne ujdet obizhennyj
removed 'dat/russ/pic/tot.1/gud.wfr'
creating the word frequency file dat/russ/pic/tot.1/gud.wfr
the 10 most common words in dat/russ/pic/tot.1/gud.tlw:
1881 0.04097 i
1027 0.02237 ne
1005 0.02189 v
833 0.01814 on
778 0.01694 na
592 0.01289 ya
577 0.01257 chto
568 0.01237 a
484 0.01054 s
406 0.00884 kak
removed 'dat/russ/pic/tot.1/gud-whole-wds-summary.tex'
removed 'exp/russ/pic/tot.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/russ/pic/tot.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:30:53 by tex-make-sample-summary.sh
% Token and word counts for russ/pic/tot.1/gud.wfr
%
\def\russpicwholetotPBgudTks{45915}
\def\russpicwholetotPBgudTksPct{96.9}
\def\russpicwholetotPBgudWds{11831}
\def\russpicwholetotPBgudWdsPct{25.0}
copied '/tmp/566923.file' -> 'exp/russ/pic/tot.1/gud-whole-wds-summary.tex'
removed '/tmp/566923.file'
creating running text file dat/russ/pic/tot.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/russ/pic/tot.1/bad.wfr'
creating the word frequency file dat/russ/pic/tot.1/bad.wfr
the 10 most common words in dat/russ/pic/tot.1/bad.tlw:
1445 0.99381 =
2 0.00138 23
2 0.00138 k
1 0.00069 19
1 0.00069 27
1 0.00069 56
1 0.00069 77
1 0.00069 b
removed 'dat/russ/pic/tot.1/bad-whole-wds-summary.tex'
removed 'exp/russ/pic/tot.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/russ/pic/tot.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:30:53 by tex-make-sample-summary.sh
% Token and word counts for russ/pic/tot.1/bad.wfr
%
\def\russpicwholetotPBbadTks{1454}
\def\russpicwholetotPBbadTksPct{3.1}
\def\russpicwholetotPBbadWds{8}
\def\russpicwholetotPBbadWdsPct{0.0}
copied '/tmp/566967.file' -> 'exp/russ/pic/tot.1/bad-whole-wds-summary.tex'
removed '/tmp/566967.file'
lines words bytes file
------- ------- --------- ------------
11837 35510 297337 dat/russ/pic/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
11831 35492 297224 dat/russ/pic/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
8 24 149 dat/russ/pic/tot.1/bad.wfr
tot.1 raw = 47369 gud = 45915 bad = 1454
=== creating the derived word files dat/russ/ptt/*/{raw,gud,bad}.{tlw,wdf,wfr} (whole) ===
... creating word files dat/russ/ptt/gen.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
28445 dat/russ/ptt/gen.1/whole.tlw
removed 'dat/russ/ptt/gen.1/raw.tlw'
removed 'dat/russ/ptt/gen.1/gud.tlw'
removed 'dat/russ/ptt/gen.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
!! empty raw.tlw file '='
creating running text file dat/russ/ptt/gen.1/raw.wdf
sample:
ũ
îáþáėå óïôũïōéė âïį îåâï é úåíėā úåíėņ öå âųėá âåúũéäîá é ðõóôá é ôøíá
îáä âåúäîïā é äõč âïöéę îïóéėóņ îáä ũïäïā é óëáúáė âïį äá âõäåô óũåô é
óôáė óũåô é õũéäåė âïį óũåô þôï ïî čïōïû é ïôäåėéė âïį óũåô ïô ôøíų é
îáúũáė âïį óũåô äîåí á ôøíõ îïþøā é âųė ũåþåō é âųėï õôōï äåîø ïäéî é
óëáúáė âïį äá âõäåô ôũåōäø ðïóōåäé ũïäų é äá ïôäåėņåô ïîá ũïäõ ïô ũïäų é
óïúäáė âïį ôũåōäø é ïôäåėéė ũïäõ ëïôïōáņ ðïä ôũåōäøā ïô ũïäų ëïôïōáņ îáä
ôũåōäøā é óôáėï ôáë é îáúũáė âïį ôũåōäø îåâïí é âųė ũåþåō é âųėï õôōï
äåîø ũôïōïę é óëáúáė âïį äá óïâåōåôóņ ũïäá ëïôïōáņ ðïä îåâïí ũ
ïäîï íåóôï é äá ņũéôóņ óõûá é óôáėï ôáë é îáúũáė âïį óõûõ úåíėåā á
óïâōáîéå ũïä îáúũáė íïōņíé é õũéäåė âïį þôï üôï čïōïûï é óëáúáė âïį äá
ðōïéúōáóôéô úåíėņ úåėåîø ôōáũõ óåāýõā óåíņ äåōåũï ðėïäïũéôïå ðōéîïóņýåå
ðï ōïäõ óũïåíõ ðėïä ũ
ëïôïōïí óåíņ åįï îá úåíėå é óôáėï ôáë é ðōïéúũåėá úåíėņ úåėåîø ôōáũõ
óåāýõā óåíņ ðï ōïäõ åå é äåōåũï ðōéîïóņýåå ðėïä ũ
ëïôïōïí óåíņ åįï ðï ōïäõ åįï é õũéäåė âïį þôï üôï čïōïûï é âųė ũåþåō é
âųėï õôōï äåîø ôōåôéę é óëáúáė âïį äá âõäõô óũåôéėá îá ôũåōäé îåâåóîïę
äėņ ïôäåėåîéņ äîņ ïô îïþé é äėņ úîáíåîéę é ũōåíåî é äîåę é įïäïũ é äá
âõäõô ïîé óũåôéėøîéëáíé îá ôũåōäé îåâåóîïę þôïâų óũåôéôø îá úåíėā é
óôáėï ôáë é óïúäáė âïį äũá óũåôéėá ũåėéëéå óũåôéėï âïėøûåå äėņ
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
éïóéæ óôá äåóņôé ėåô é îáâáėøúáíéōïũáėé åįï é ðïėïöéėé ũ
ëïũþåį ũ
åįéðôå
removed 'dat/russ/ptt/gen.1/raw.wfr'
creating the word frequency file dat/russ/ptt/gen.1/raw.wfr
the 10 most common words in dat/russ/ptt/gen.1/raw.tlw:
2885 0.10142 é
624 0.02194 ũ
397 0.01396 óëáúáė
386 0.01357 åįï
328 0.01153 ņ
323 0.01136 îå
300 0.01055 ïî
299 0.01051 þôï
281 0.00988 îá
268 0.00942 ó
removed 'dat/russ/ptt/gen.1/raw-whole-wds-summary.tex'
removed 'exp/russ/ptt/gen.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/russ/ptt/gen.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:30:53 by tex-make-sample-summary.sh
% Token and word counts for russ/ptt/gen.1/raw.wfr
%
\def\russpttwholegenPBrawTks{28445}
\def\russpttwholegenPBrawTksPct{100.0}
\def\russpttwholegenPBrawWds{4899}
\def\russpttwholegenPBrawWdsPct{17.2}
copied '/tmp/567064.file' -> 'exp/russ/ptt/gen.1/raw-whole-wds-summary.tex'
removed '/tmp/567064.file'
creating running text file dat/russ/ptt/gen.1/gud.wdf
sample:
ũ
îáþáėå óïôũïōéė âïį îåâï é úåíėā úåíėņ öå âųėá âåúũéäîá é ðõóôá é ôøíá
îáä âåúäîïā é äõč âïöéę îïóéėóņ îáä ũïäïā é óëáúáė âïį äá âõäåô óũåô é
óôáė óũåô é õũéäåė âïį óũåô þôï ïî čïōïû é ïôäåėéė âïį óũåô ïô ôøíų é
îáúũáė âïį óũåô äîåí á ôøíõ îïþøā é âųė ũåþåō é âųėï õôōï äåîø ïäéî é
óëáúáė âïį äá âõäåô ôũåōäø ðïóōåäé ũïäų é äá ïôäåėņåô ïîá ũïäõ ïô ũïäų é
óïúäáė âïį ôũåōäø é ïôäåėéė ũïäõ ëïôïōáņ ðïä ôũåōäøā ïô ũïäų ëïôïōáņ îáä
ôũåōäøā é óôáėï ôáë é îáúũáė âïį ôũåōäø îåâïí é âųė ũåþåō é âųėï õôōï
äåîø ũôïōïę é óëáúáė âïį äá óïâåōåôóņ ũïäá ëïôïōáņ ðïä îåâïí ũ
ïäîï íåóôï é äá ņũéôóņ óõûá é óôáėï ôáë é îáúũáė âïį óõûõ úåíėåā á
óïâōáîéå ũïä îáúũáė íïōņíé é õũéäåė âïį þôï üôï čïōïûï é óëáúáė âïį äá
ðōïéúōáóôéô úåíėņ úåėåîø ôōáũõ óåāýõā óåíņ äåōåũï ðėïäïũéôïå ðōéîïóņýåå
ðï ōïäõ óũïåíõ ðėïä ũ
ëïôïōïí óåíņ åįï îá úåíėå é óôáėï ôáë é ðōïéúũåėá úåíėņ úåėåîø ôōáũõ
óåāýõā óåíņ ðï ōïäõ åå é äåōåũï ðōéîïóņýåå ðėïä ũ
ëïôïōïí óåíņ åįï ðï ōïäõ åįï é õũéäåė âïį þôï üôï čïōïûï é âųė ũåþåō é
âųėï õôōï äåîø ôōåôéę é óëáúáė âïį äá âõäõô óũåôéėá îá ôũåōäé îåâåóîïę
äėņ ïôäåėåîéņ äîņ ïô îïþé é äėņ úîáíåîéę é ũōåíåî é äîåę é įïäïũ é äá
âõäõô ïîé óũåôéėøîéëáíé îá ôũåōäé îåâåóîïę þôïâų óũåôéôø îá úåíėā é
óôáėï ôáë é óïúäáė âïį äũá óũåôéėá ũåėéëéå óũåôéėï âïėøûåå äėņ
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
éïóéæ óôá äåóņôé ėåô é îáâáėøúáíéōïũáėé åįï é ðïėïöéėé ũ
ëïũþåį ũ
åįéðôå
removed 'dat/russ/ptt/gen.1/gud.wfr'
creating the word frequency file dat/russ/ptt/gen.1/gud.wfr
the 10 most common words in dat/russ/ptt/gen.1/gud.tlw:
2885 0.10142 é
624 0.02194 ũ
397 0.01396 óëáúáė
386 0.01357 åįï
328 0.01153 ņ
323 0.01136 îå
300 0.01055 ïî
299 0.01051 þôï
281 0.00988 îá
268 0.00942 ó
removed 'dat/russ/ptt/gen.1/gud-whole-wds-summary.tex'
removed 'exp/russ/ptt/gen.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/russ/ptt/gen.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:30:53 by tex-make-sample-summary.sh
% Token and word counts for russ/ptt/gen.1/gud.wfr
%
\def\russpttwholegenPBgudTks{28445}
\def\russpttwholegenPBgudTksPct{100.0}
\def\russpttwholegenPBgudWds{4899}
\def\russpttwholegenPBgudWdsPct{17.2}
copied '/tmp/567108.file' -> 'exp/russ/ptt/gen.1/gud-whole-wds-summary.tex'
removed '/tmp/567108.file'
creating running text file dat/russ/ptt/gen.1/bad.wdf
sample:
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
removed 'dat/russ/ptt/gen.1/bad.wfr'
creating the word frequency file dat/russ/ptt/gen.1/bad.wfr
the 10 most common words in dat/russ/ptt/gen.1/bad.tlw:
removed 'dat/russ/ptt/gen.1/bad-whole-wds-summary.tex'
removed 'exp/russ/ptt/gen.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/russ/ptt/gen.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:30:53 by tex-make-sample-summary.sh
% Token and word counts for russ/ptt/gen.1/bad.wfr
%
\def\russpttwholegenPBbadTks{0}
\def\russpttwholegenPBbadTksPct{0.0}
\def\russpttwholegenPBbadWds{0}
\def\russpttwholegenPBbadWdsPct{0.0}
copied '/tmp/567152.file' -> 'exp/russ/ptt/gen.1/bad-whole-wds-summary.tex'
removed '/tmp/567152.file'
... creating word files dat/russ/ptt/exo.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
22960 dat/russ/ptt/exo.1/whole.tlw
removed 'dat/russ/ptt/exo.1/raw.tlw'
removed 'dat/russ/ptt/exo.1/gud.tlw'
removed 'dat/russ/ptt/exo.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
!! empty raw.tlw file '='
creating running text file dat/russ/ptt/exo.1/raw.wdf
sample:
ũïô éíåîá óųîïũ éúōáéėåũųč ëïôïōųå ũïûėé ũ
åįéðåô ó éáëïũïí ũïûėé ëáöäųę ó äïíïí óũïéí ōõũéí óéíåïî ėåũéę é éõäá
éóóáčáō úáũõėïî é ũåîéáíéî äáî é îåææáėéí įáä é áóéō ũóåč öå äõû
ðōïéóûåäûéč ïô þōåóė éáëïũá âųėï óåíøäåóņô á éïóéæ âųė õöå ũ
åįéðôå é õíåō éïóéæ é ũóå âōáôøņ åįï é ũåóø ōïä éč á óųîų éúōáéėåũų
ōáóðėïäéėéóø é ōáúíîïöéėéóø é ũïúōïóėé é õóéėéėéóø þōåúũųþáęîï é
îáðïėîéėáóø éíé úåíėņ ôá é ũïóóôáė ũ
åįéðôå îïũųę ãáōø ëïôïōųę îå úîáė éïóéæá é óëáúáė îáōïäõ óũïåíõ ũïô
îáōïä óųîïũ éúōáéėåũųč íîïįïþéóėåî é óéėøîåå îáó ðåōåčéôōéí öå åįï þôïâų
ïî îå ōáúíîïöáėóņ éîáþå ëïįäá óėõþéôóņ ũïęîá óïåäéîéôóņ é ïî ó îáûéíé
îåðōéņôåėņíé é ũïïōõöéôóņ ðōïôéũ îáó é ũųęäåô éú úåíėé îáûåę é ðïóôáũéėé
îáä îéí îáþáėøîéëïũ ōáâïô þôïâų éúîõōņėé åįï ôņöëéíé ōáâïôáíé é ïî
ðïóôōïéė æáōáïîõ ðéæïí é ōááíóåó įïōïäá äėņ úáðáóïũ îï þåí âïėåå
éúîõōņėé åįï ôåí âïėåå ïî õíîïöáėóņ é ôåí âïėåå ũïúōáóôáė ôáë þôï
ïðáóáėéóø óųîïũ éúōáéėåũųč é ðïôïíõ åįéðôņîå ó öåóôïëïóôøā ðōéîõöäáėé
óųîïũ éúōáéėåũųč ë ōáâïôáí é äåėáėé öéúîø éč įïōøëïā ïô ôņöëïę ōáâïôų
îáä įėéîïā é ëéōðéþáíé é ïô ũóņëïę ōáâïôų ðïėåũïę ïô ũóņëïę ōáâïôų ë
ëïôïōïę ðōéîõöäáėé éč ó öåóôïëïóôøā ãáōø åįéðåôóëéę ðïũåėåė ðïũéũáėøîųí
âáâëáí åũōåņîïë éú ëïéč ïäîïę éíņ ûéæōá á äōõįïę æõá é óëáúáė ëïįäá ũų
âõäåôå ðïũéũáôø õ åũōåņîïë ôï îáâėāäáęôå ðōé ōïäáč åóėé âõäåô óųî ôï
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
ðõôø äïëïėå ïîï îå ðïäîéíáėïóø éâï ïâėáëï įïóðïäîå óôïņėï îáä óëéîéåā
äîåí é ïįïîø âųė îïþøā ũ
îåę ðōåä įėáúáíé ũóåįï äïíá éúōáéėåũá ũï ũóå ðõôåûåóôũéå éč
removed 'dat/russ/ptt/exo.1/raw.wfr'
creating the word frequency file dat/russ/ptt/exo.1/raw.wfr
the 10 most common words in dat/russ/ptt/exo.1/raw.tlw:
2196 0.09564 é
503 0.02191 ũ
400 0.01742 åįï
388 0.01690 îá
331 0.01442 îå
323 0.01407 éú
244 0.01063 įïóðïäø
218 0.00949 ó
198 0.00862 äėņ
194 0.00845 éč
removed 'dat/russ/ptt/exo.1/raw-whole-wds-summary.tex'
removed 'exp/russ/ptt/exo.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/russ/ptt/exo.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:30:53 by tex-make-sample-summary.sh
% Token and word counts for russ/ptt/exo.1/raw.wfr
%
\def\russpttwholeexoPBrawTks{22960}
\def\russpttwholeexoPBrawTksPct{100.0}
\def\russpttwholeexoPBrawWds{4084}
\def\russpttwholeexoPBrawWdsPct{17.8}
copied '/tmp/567208.file' -> 'exp/russ/ptt/exo.1/raw-whole-wds-summary.tex'
removed '/tmp/567208.file'
creating running text file dat/russ/ptt/exo.1/gud.wdf
sample:
ũïô éíåîá óųîïũ éúōáéėåũųč ëïôïōųå ũïûėé ũ
åįéðåô ó éáëïũïí ũïûėé ëáöäųę ó äïíïí óũïéí ōõũéí óéíåïî ėåũéę é éõäá
éóóáčáō úáũõėïî é ũåîéáíéî äáî é îåææáėéí įáä é áóéō ũóåč öå äõû
ðōïéóûåäûéč ïô þōåóė éáëïũá âųėï óåíøäåóņô á éïóéæ âųė õöå ũ
åįéðôå é õíåō éïóéæ é ũóå âōáôøņ åįï é ũåóø ōïä éč á óųîų éúōáéėåũų
ōáóðėïäéėéóø é ōáúíîïöéėéóø é ũïúōïóėé é õóéėéėéóø þōåúũųþáęîï é
îáðïėîéėáóø éíé úåíėņ ôá é ũïóóôáė ũ
åįéðôå îïũųę ãáōø ëïôïōųę îå úîáė éïóéæá é óëáúáė îáōïäõ óũïåíõ ũïô
îáōïä óųîïũ éúōáéėåũųč íîïįïþéóėåî é óéėøîåå îáó ðåōåčéôōéí öå åįï þôïâų
ïî îå ōáúíîïöáėóņ éîáþå ëïįäá óėõþéôóņ ũïęîá óïåäéîéôóņ é ïî ó îáûéíé
îåðōéņôåėņíé é ũïïōõöéôóņ ðōïôéũ îáó é ũųęäåô éú úåíėé îáûåę é ðïóôáũéėé
îáä îéí îáþáėøîéëïũ ōáâïô þôïâų éúîõōņėé åįï ôņöëéíé ōáâïôáíé é ïî
ðïóôōïéė æáōáïîõ ðéæïí é ōááíóåó įïōïäá äėņ úáðáóïũ îï þåí âïėåå
éúîõōņėé åįï ôåí âïėåå ïî õíîïöáėóņ é ôåí âïėåå ũïúōáóôáė ôáë þôï
ïðáóáėéóø óųîïũ éúōáéėåũųč é ðïôïíõ åįéðôņîå ó öåóôïëïóôøā ðōéîõöäáėé
óųîïũ éúōáéėåũųč ë ōáâïôáí é äåėáėé öéúîø éč įïōøëïā ïô ôņöëïę ōáâïôų
îáä įėéîïā é ëéōðéþáíé é ïô ũóņëïę ōáâïôų ðïėåũïę ïô ũóņëïę ōáâïôų ë
ëïôïōïę ðōéîõöäáėé éč ó öåóôïëïóôøā ãáōø åįéðåôóëéę ðïũåėåė ðïũéũáėøîųí
âáâëáí åũōåņîïë éú ëïéč ïäîïę éíņ ûéæōá á äōõįïę æõá é óëáúáė ëïįäá ũų
âõäåôå ðïũéũáôø õ åũōåņîïë ôï îáâėāäáęôå ðōé ōïäáč åóėé âõäåô óųî ôï
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
ðõôø äïëïėå ïîï îå ðïäîéíáėïóø éâï ïâėáëï įïóðïäîå óôïņėï îáä óëéîéåā
äîåí é ïįïîø âųė îïþøā ũ
îåę ðōåä įėáúáíé ũóåįï äïíá éúōáéėåũá ũï ũóå ðõôåûåóôũéå éč
removed 'dat/russ/ptt/exo.1/gud.wfr'
creating the word frequency file dat/russ/ptt/exo.1/gud.wfr
the 10 most common words in dat/russ/ptt/exo.1/gud.tlw:
2196 0.09564 é
503 0.02191 ũ
400 0.01742 åįï
388 0.01690 îá
331 0.01442 îå
323 0.01407 éú
244 0.01063 įïóðïäø
218 0.00949 ó
198 0.00862 äėņ
194 0.00845 éč
removed 'dat/russ/ptt/exo.1/gud-whole-wds-summary.tex'
removed 'exp/russ/ptt/exo.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/russ/ptt/exo.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:30:53 by tex-make-sample-summary.sh
% Token and word counts for russ/ptt/exo.1/gud.wfr
%
\def\russpttwholeexoPBgudTks{22960}
\def\russpttwholeexoPBgudTksPct{100.0}
\def\russpttwholeexoPBgudWds{4084}
\def\russpttwholeexoPBgudWdsPct{17.8}
copied '/tmp/567252.file' -> 'exp/russ/ptt/exo.1/gud-whole-wds-summary.tex'
removed '/tmp/567252.file'
creating running text file dat/russ/ptt/exo.1/bad.wdf
sample:
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
removed 'dat/russ/ptt/exo.1/bad.wfr'
creating the word frequency file dat/russ/ptt/exo.1/bad.wfr
the 10 most common words in dat/russ/ptt/exo.1/bad.tlw:
removed 'dat/russ/ptt/exo.1/bad-whole-wds-summary.tex'
removed 'exp/russ/ptt/exo.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/russ/ptt/exo.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:30:53 by tex-make-sample-summary.sh
% Token and word counts for russ/ptt/exo.1/bad.wfr
%
\def\russpttwholeexoPBbadTks{0}
\def\russpttwholeexoPBbadTksPct{0.0}
\def\russpttwholeexoPBbadWds{0}
\def\russpttwholeexoPBbadWdsPct{0.0}
copied '/tmp/567296.file' -> 'exp/russ/ptt/exo.1/bad-whole-wds-summary.tex'
removed '/tmp/567296.file'
... creating word files dat/russ/ptt/num.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
22530 dat/russ/ptt/num.1/whole.tlw
removed 'dat/russ/ptt/num.1/raw.tlw'
removed 'dat/russ/ptt/num.1/gud.tlw'
removed 'dat/russ/ptt/num.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
!! empty raw.tlw file '='
creating running text file dat/russ/ptt/num.1/raw.wdf
sample:
é óëáúáė įïóðïäø íïéóåā ũ
ðõóôųîå óéîáęóëïę ũ
óëéîéé óïâōáîéņ ũ
ðåōũųę äåîø ũôïōïįï íåóņãá ũï ũôïōïę įïä ðï ũųčïäå éč éú úåíėé
åįéðåôóëïę įïũïōņ éóþéóėéôå ũóå ïâýåóôũï óųîïũ éúōáéėåũųč ðï ōïäáí éč ðï
óåíåęóôũáí éč ðï þéóėõ éíåî ũóåč íõöåóëïįï ðïėá ðïįïėïũîï ïô äũáäãáôé
ėåô é ũųûå ũóåč įïäîųč äėņ ũïęîų õ éúōáéėņ ðï ïðïėþåîéņí éč éóþéóėéôå éč
ôų é ááōïî ó ũáíé äïėöîų âųôø éú ëáöäïįï ëïėåîá ðï ïäîïíõ þåėïũåëõ
ëïôïōųę ũ
ōïäå óũïåí åóôø įėáũîųę é ũïô éíåîá íõöåę ëïôïōųå âõäõô ó ũáíé ïô ōõũéíá
åėéãõō óųî ûåäåõōá ïô óéíåïîá ûåėõíééė óųî ãõōéûáääáņ ïô éõäų îááóóïî
óųî áíéîáäáũá ïô éóóáčáōá îáæáîáéė óųî ãõáōá ïô úáũõėïîá åėéáũ óųî
čåėïîá ïô óųîïũ éïóéæá ïô åæōåíá åėéûáíá óųî áííéõäá ïô íáîáóóéé
įáíáėééė óųî ðåäáãõōá ïô ũåîéáíéîá áũéäáî óųî įéäåïîéņ ïô äáîá áčéåúåō
óųî áííéûáääáņ ïô áóéōá ðáįééė óųî ïčōáîá ïô įáäá åėéáóáæ óųî ōåįõéėá ïô
îåææáėéíá áčéōá óųî åîáîá üôï éúâōáîîųå íõöé ïâýåóôũá îáþáėøîéëé ëïėåî
ïôãïũ óũïéč įėáũų ôųóņþ éúōáéėåũųč é ũúņė íïéóåę é ááōïî íõöåę óéč
ëïôïōųå îáúũáîų ðïéíåîîï é óïâōáėé ïîé ũóå ïâýåóôũï ũ
ðåōũųę äåîø ũôïōïįï íåóņãá é ïâĸņũéėé ïîé ōïäïóėïũéņ óũïé ðï ōïäáí éč ðï
óåíåęóôũáí éč ðï þéóėõ éíåî ïô äũáäãáôé ėåô é ũųûå ðïįïėïũîï ëáë ðïũåėåė
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
ëïėåîå ðėåíåîé ïôãá éč óéé óõôø úáðïũåäé é ðïóôáîïũėåîéņ ëïôïōųå äáė
įïóðïäø óųîáí éúōáéėåũųí þōåú íïéóåņ îá ōáũîéîáč íïáũéôóëéč õ éïōäáîá
ðōïôéũ éåōéčïîá
removed 'dat/russ/ptt/num.1/raw.wfr'
creating the word frequency file dat/russ/ptt/num.1/raw.wfr
the 10 most common words in dat/russ/ptt/num.1/raw.tlw:
1944 0.08628 é
632 0.02805 ũ
307 0.01363 éč
286 0.01269 ðï
266 0.01181 îá
256 0.01136 ïô
252 0.01119 éú
237 0.01052 åįï
233 0.01034 îå
189 0.00839 óųîïũ
removed 'dat/russ/ptt/num.1/raw-whole-wds-summary.tex'
removed 'exp/russ/ptt/num.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/russ/ptt/num.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:30:53 by tex-make-sample-summary.sh
% Token and word counts for russ/ptt/num.1/raw.wfr
%
\def\russpttwholenumPBrawTks{22530}
\def\russpttwholenumPBrawTksPct{100.0}
\def\russpttwholenumPBrawWds{3952}
\def\russpttwholenumPBrawWdsPct{17.5}
copied '/tmp/567352.file' -> 'exp/russ/ptt/num.1/raw-whole-wds-summary.tex'
removed '/tmp/567352.file'
creating running text file dat/russ/ptt/num.1/gud.wdf
sample:
é óëáúáė įïóðïäø íïéóåā ũ
ðõóôųîå óéîáęóëïę ũ
óëéîéé óïâōáîéņ ũ
ðåōũųę äåîø ũôïōïįï íåóņãá ũï ũôïōïę įïä ðï ũųčïäå éč éú úåíėé
åįéðåôóëïę įïũïōņ éóþéóėéôå ũóå ïâýåóôũï óųîïũ éúōáéėåũųč ðï ōïäáí éč ðï
óåíåęóôũáí éč ðï þéóėõ éíåî ũóåč íõöåóëïįï ðïėá ðïįïėïũîï ïô äũáäãáôé
ėåô é ũųûå ũóåč įïäîųč äėņ ũïęîų õ éúōáéėņ ðï ïðïėþåîéņí éč éóþéóėéôå éč
ôų é ááōïî ó ũáíé äïėöîų âųôø éú ëáöäïįï ëïėåîá ðï ïäîïíõ þåėïũåëõ
ëïôïōųę ũ
ōïäå óũïåí åóôø įėáũîųę é ũïô éíåîá íõöåę ëïôïōųå âõäõô ó ũáíé ïô ōõũéíá
åėéãõō óųî ûåäåõōá ïô óéíåïîá ûåėõíééė óųî ãõōéûáääáņ ïô éõäų îááóóïî
óųî áíéîáäáũá ïô éóóáčáōá îáæáîáéė óųî ãõáōá ïô úáũõėïîá åėéáũ óųî
čåėïîá ïô óųîïũ éïóéæá ïô åæōåíá åėéûáíá óųî áííéõäá ïô íáîáóóéé
įáíáėééė óųî ðåäáãõōá ïô ũåîéáíéîá áũéäáî óųî įéäåïîéņ ïô äáîá áčéåúåō
óųî áííéûáääáņ ïô áóéōá ðáįééė óųî ïčōáîá ïô įáäá åėéáóáæ óųî ōåįõéėá ïô
îåææáėéíá áčéōá óųî åîáîá üôï éúâōáîîųå íõöé ïâýåóôũá îáþáėøîéëé ëïėåî
ïôãïũ óũïéč įėáũų ôųóņþ éúōáéėåũųč é ũúņė íïéóåę é ááōïî íõöåę óéč
ëïôïōųå îáúũáîų ðïéíåîîï é óïâōáėé ïîé ũóå ïâýåóôũï ũ
ðåōũųę äåîø ũôïōïįï íåóņãá é ïâĸņũéėé ïîé ōïäïóėïũéņ óũïé ðï ōïäáí éč ðï
óåíåęóôũáí éč ðï þéóėõ éíåî ïô äũáäãáôé ėåô é ũųûå ðïįïėïũîï ëáë ðïũåėåė
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
ëïėåîå ðėåíåîé ïôãá éč óéé óõôø úáðïũåäé é ðïóôáîïũėåîéņ ëïôïōųå äáė
įïóðïäø óųîáí éúōáéėåũųí þōåú íïéóåņ îá ōáũîéîáč íïáũéôóëéč õ éïōäáîá
ðōïôéũ éåōéčïîá
removed 'dat/russ/ptt/num.1/gud.wfr'
creating the word frequency file dat/russ/ptt/num.1/gud.wfr
the 10 most common words in dat/russ/ptt/num.1/gud.tlw:
1944 0.08628 é
632 0.02805 ũ
307 0.01363 éč
286 0.01269 ðï
266 0.01181 îá
256 0.01136 ïô
252 0.01119 éú
237 0.01052 åįï
233 0.01034 îå
189 0.00839 óųîïũ
removed 'dat/russ/ptt/num.1/gud-whole-wds-summary.tex'
removed 'exp/russ/ptt/num.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/russ/ptt/num.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:30:53 by tex-make-sample-summary.sh
% Token and word counts for russ/ptt/num.1/gud.wfr
%
\def\russpttwholenumPBgudTks{22530}
\def\russpttwholenumPBgudTksPct{100.0}
\def\russpttwholenumPBgudWds{3952}
\def\russpttwholenumPBgudWdsPct{17.5}
copied '/tmp/567396.file' -> 'exp/russ/ptt/num.1/gud-whole-wds-summary.tex'
removed '/tmp/567396.file'
creating running text file dat/russ/ptt/num.1/bad.wdf
sample:
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
removed 'dat/russ/ptt/num.1/bad.wfr'
creating the word frequency file dat/russ/ptt/num.1/bad.wfr
the 10 most common words in dat/russ/ptt/num.1/bad.tlw:
removed 'dat/russ/ptt/num.1/bad-whole-wds-summary.tex'
removed 'exp/russ/ptt/num.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/russ/ptt/num.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:30:53 by tex-make-sample-summary.sh
% Token and word counts for russ/ptt/num.1/bad.wfr
%
\def\russpttwholenumPBbadTks{0}
\def\russpttwholenumPBbadTksPct{0.0}
\def\russpttwholenumPBbadWds{0}
\def\russpttwholenumPBbadWdsPct{0.0}
copied '/tmp/567440.file' -> 'exp/russ/ptt/num.1/bad-whole-wds-summary.tex'
removed '/tmp/567440.file'
... creating word files dat/russ/ptt/lev.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
16901 dat/russ/ptt/lev.1/whole.tlw
removed 'dat/russ/ptt/lev.1/raw.tlw'
removed 'dat/russ/ptt/lev.1/gud.tlw'
removed 'dat/russ/ptt/lev.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
!! empty raw.tlw file '='
creating running text file dat/russ/ptt/lev.1/raw.wdf
sample:
é ũïúúũáė įïóðïäø ë íïéóåā é óëáúáė åíõ éú óëéîéé óïâōáîéņ įïũïōņ ïâĸņũé
óųîáí éúōáéėåũųí é óëáöé éí ëïįäá ëôï éú ũáó čïþåô ðōéîåóôé öåōôũõ
įïóðïäõ ôï åóėé éú óëïôá ðōéîïóéôå öåōôũõ ũáûõ éú óëïôá ëōõðîïįï é
íåėëïįï åóėé öåōôũá åįï åóôø ũóåóïööåîéå éú ëōõðîïįï óëïôá ðõóôø
ðōéîåóåô åå íõöåóëïįï ðïėá âåú ðïōïëá ðõóôø ðōéũåäåô åå ë äũåōņí óëéîéé
óïâōáîéņ þôïâų ðōéïâōåóôé åíõ âėáįïũïėåîéå ðōåä įïóðïäïí é ũïúėïöéô ōõëõ
óũïā îá įïėïũõ öåōôũų ũóåóïööåîéņ é ðōéïâōåôåô ïî âėáįïũïėåîéå ũï
ïþéýåîéå įōåčïũ åįï é úáëïėåô ôåėøãá ðōåä įïóðïäïí óųîų öå ááōïîïũų
óũņýåîîéëé ðōéîåóõô ëōïũø é ðïëōïðņô ëōïũøā óï ũóåč óôïōïî îá öåōôũåîîéë
ëïôïōųę õ ũčïäá óëéîéé óïâōáîéņ é óîéíåô ëïöõ ó öåōôũų ũóåóïööåîéņ é
ōáóóåþåô åå îá þáóôé óųîų öå ááōïîïũų óũņýåîîéëé ðïėïöáô îá öåōôũåîîéë
ïįïîø é îá ïįîå ōáúėïöáô äōïũá é ōáúėïöáô óųîų ááōïîïũų óũņýåîîéëé þáóôé
įïėïũõ é ôõë îá äōïũáč ëïôïōųå îá ïįîå îá öåōôũåîîéëå á ũîõôōåîîïóôé
öåōôũų é îïįé åå ũųíïåô ïî ũïäïā é óïööåô óũņýåîîéë ũóå îá öåōôũåîîéëå
üôï ũóåóïööåîéå öåōôũá âėáįïõčáîéå ðōéņôîïå įïóðïäõ åóėé öåōôũá
ũóåóïööåîéņ åįï éú íåėëïįï óëïôá éú ïũåã éėé éú ëïú ðõóôø ðōéîåóåô åå
íõöåóëïįï ðïėá âåú ðïōïëá é úáëïėåô åå ðōåä įïóðïäïí îá óåũåōîïę óôïōïîå
öåōôũåîîéëá é óųîų ááōïîïũų óũņýåîîéëé ðïëōïðņô ëōïũøā åå îá öåōôũåîîéë
óï ũóåč óôïōïî é ōáóóåëõô åå îá þáóôé ïôäåėéũ įïėïũõ åå é ôõë åå é
ōáúėïöéô éč óũņýåîîéë îá äōïũáč ëïôïōųå îá ïįîå îá öåōôũåîîéëå á
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
îå äïėöîï úáíåîņôø åįï åóėé öå ëôï úáíåîéô åįï ôï é óáíï ïîï é úáíåî åįï
âõäåô óũņôųîåā é îå íïöåô âųôø ũųëõðėåîï ũïô úáðïũåäé ëïôïōųå úáðïũåäáė
įïóðïäø íïéóåā äėņ óųîïũ éúōáéėåũųč îá įïōå óéîáå
removed 'dat/russ/ptt/lev.1/raw.wfr'
creating the word frequency file dat/russ/ptt/lev.1/raw.wfr
the 10 most common words in dat/russ/ptt/lev.1/raw.tlw:
1285 0.07603 é
439 0.02597 îá
355 0.02100 ũ
321 0.01899 îå
273 0.01615 åįï
190 0.01124 éú
176 0.01041 ïî
172 0.01018 åóėé
165 0.00976 ôï
154 0.00911 âõäåô
removed 'dat/russ/ptt/lev.1/raw-whole-wds-summary.tex'
removed 'exp/russ/ptt/lev.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/russ/ptt/lev.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:30:54 by tex-make-sample-summary.sh
% Token and word counts for russ/ptt/lev.1/raw.wfr
%
\def\russpttwholelevPBrawTks{16901}
\def\russpttwholelevPBrawTksPct{100.0}
\def\russpttwholelevPBrawWds{2659}
\def\russpttwholelevPBrawWdsPct{15.7}
copied '/tmp/567496.file' -> 'exp/russ/ptt/lev.1/raw-whole-wds-summary.tex'
removed '/tmp/567496.file'
creating running text file dat/russ/ptt/lev.1/gud.wdf
sample:
é ũïúúũáė įïóðïäø ë íïéóåā é óëáúáė åíõ éú óëéîéé óïâōáîéņ įïũïōņ ïâĸņũé
óųîáí éúōáéėåũųí é óëáöé éí ëïįäá ëôï éú ũáó čïþåô ðōéîåóôé öåōôũõ
įïóðïäõ ôï åóėé éú óëïôá ðōéîïóéôå öåōôũõ ũáûõ éú óëïôá ëōõðîïįï é
íåėëïįï åóėé öåōôũá åįï åóôø ũóåóïööåîéå éú ëōõðîïįï óëïôá ðõóôø
ðōéîåóåô åå íõöåóëïįï ðïėá âåú ðïōïëá ðõóôø ðōéũåäåô åå ë äũåōņí óëéîéé
óïâōáîéņ þôïâų ðōéïâōåóôé åíõ âėáįïũïėåîéå ðōåä įïóðïäïí é ũïúėïöéô ōõëõ
óũïā îá įïėïũõ öåōôũų ũóåóïööåîéņ é ðōéïâōåôåô ïî âėáįïũïėåîéå ũï
ïþéýåîéå įōåčïũ åįï é úáëïėåô ôåėøãá ðōåä įïóðïäïí óųîų öå ááōïîïũų
óũņýåîîéëé ðōéîåóõô ëōïũø é ðïëōïðņô ëōïũøā óï ũóåč óôïōïî îá öåōôũåîîéë
ëïôïōųę õ ũčïäá óëéîéé óïâōáîéņ é óîéíåô ëïöõ ó öåōôũų ũóåóïööåîéņ é
ōáóóåþåô åå îá þáóôé óųîų öå ááōïîïũų óũņýåîîéëé ðïėïöáô îá öåōôũåîîéë
ïįïîø é îá ïįîå ōáúėïöáô äōïũá é ōáúėïöáô óųîų ááōïîïũų óũņýåîîéëé þáóôé
įïėïũõ é ôõë îá äōïũáč ëïôïōųå îá ïįîå îá öåōôũåîîéëå á ũîõôōåîîïóôé
öåōôũų é îïįé åå ũųíïåô ïî ũïäïā é óïööåô óũņýåîîéë ũóå îá öåōôũåîîéëå
üôï ũóåóïööåîéå öåōôũá âėáįïõčáîéå ðōéņôîïå įïóðïäõ åóėé öåōôũá
ũóåóïööåîéņ åįï éú íåėëïįï óëïôá éú ïũåã éėé éú ëïú ðõóôø ðōéîåóåô åå
íõöåóëïįï ðïėá âåú ðïōïëá é úáëïėåô åå ðōåä įïóðïäïí îá óåũåōîïę óôïōïîå
öåōôũåîîéëá é óųîų ááōïîïũų óũņýåîîéëé ðïëōïðņô ëōïũøā åå îá öåōôũåîîéë
óï ũóåč óôïōïî é ōáóóåëõô åå îá þáóôé ïôäåėéũ įïėïũõ åå é ôõë åå é
ōáúėïöéô éč óũņýåîîéë îá äōïũáč ëïôïōųå îá ïįîå îá öåōôũåîîéëå á
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
îå äïėöîï úáíåîņôø åįï åóėé öå ëôï úáíåîéô åįï ôï é óáíï ïîï é úáíåî åįï
âõäåô óũņôųîåā é îå íïöåô âųôø ũųëõðėåîï ũïô úáðïũåäé ëïôïōųå úáðïũåäáė
įïóðïäø íïéóåā äėņ óųîïũ éúōáéėåũųč îá įïōå óéîáå
removed 'dat/russ/ptt/lev.1/gud.wfr'
creating the word frequency file dat/russ/ptt/lev.1/gud.wfr
the 10 most common words in dat/russ/ptt/lev.1/gud.tlw:
1285 0.07603 é
439 0.02597 îá
355 0.02100 ũ
321 0.01899 îå
273 0.01615 åįï
190 0.01124 éú
176 0.01041 ïî
172 0.01018 åóėé
165 0.00976 ôï
154 0.00911 âõäåô
removed 'dat/russ/ptt/lev.1/gud-whole-wds-summary.tex'
removed 'exp/russ/ptt/lev.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/russ/ptt/lev.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:30:54 by tex-make-sample-summary.sh
% Token and word counts for russ/ptt/lev.1/gud.wfr
%
\def\russpttwholelevPBgudTks{16901}
\def\russpttwholelevPBgudTksPct{100.0}
\def\russpttwholelevPBgudWds{2659}
\def\russpttwholelevPBgudWdsPct{15.7}
copied '/tmp/567540.file' -> 'exp/russ/ptt/lev.1/gud-whole-wds-summary.tex'
removed '/tmp/567540.file'
creating running text file dat/russ/ptt/lev.1/bad.wdf
sample:
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
removed 'dat/russ/ptt/lev.1/bad.wfr'
creating the word frequency file dat/russ/ptt/lev.1/bad.wfr
the 10 most common words in dat/russ/ptt/lev.1/bad.tlw:
removed 'dat/russ/ptt/lev.1/bad-whole-wds-summary.tex'
removed 'exp/russ/ptt/lev.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/russ/ptt/lev.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:30:54 by tex-make-sample-summary.sh
% Token and word counts for russ/ptt/lev.1/bad.wfr
%
\def\russpttwholelevPBbadTks{0}
\def\russpttwholelevPBbadTksPct{0.0}
\def\russpttwholelevPBbadWds{0}
\def\russpttwholelevPBbadWdsPct{0.0}
copied '/tmp/567584.file' -> 'exp/russ/ptt/lev.1/bad-whole-wds-summary.tex'
removed '/tmp/567584.file'
... creating word files dat/russ/ptt/deu.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
20988 dat/russ/ptt/deu.1/whole.tlw
removed 'dat/russ/ptt/deu.1/raw.tlw'
removed 'dat/russ/ptt/deu.1/gud.tlw'
removed 'dat/russ/ptt/deu.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
!! empty raw.tlw file '='
creating running text file dat/russ/ptt/deu.1/raw.wdf
sample:
óéé óõôø óėïũá ëïôïōųå įïũïōéė íïéóåę ũóåí éúōáéėøôņîáí úá éïōäáîïí ũ
ðõóôųîå îá ōáũîéîå ðōïôéũ óõæá íåöäõ æáōáîïí é ôïæåėïí é ėáũáîïí é
áóéōïæïí é äéúáįáũïí ũ
ōáóóôïņîéé ïäéîîáäãáôé äîåę ðõôé ïô čïōéũá ðï äïōïįå ïô įïōų óåéō ë
ëáäåó ũáōîé óïōïëïũïįï įïäá ïäéîîáäãáôïįï íåóņãá ũ
ðåōũųę äåîø íåóņãá įïũïōéė íïéóåę óųîáí éúōáéėåũųí ũóå þôï úáðïũåäáė åíõ
įïóðïäø ï îéč ðï õâéåîéé éí óéįïîá ãáōņ áíïōōåęóëïįï ëïôïōųę öéė ũ
åóåũïîå é ïįá ãáōņ ũáóáîóëïįï ëïôïōųę öéė ũ
áûôåōïæå ũ
åäōåé úá éïōäáîïí ũ
úåíėå íïáũéôóëïę îáþáė íïéóåę éúĸņóîņôø úáëïî óåę é óëáúáė įïóðïäø âïį
îáû įïũïōéė îáí ũ
čïōéũå é óëáúáė ðïėîï ũáí öéôø îá įïōå óåę ïâōáôéôåóø ïôðōáũøôåóø ũ
ðõôø é ðïęäéôå îá įïōõ áíïōōååũ é ëï ũóåí óïóåäņí éč îá ōáũîéîõ îá įïōõ
îá îéúëéå íåóôá é îá āöîųę ëōáę é ë âåōåįáí íïōņ ũ
úåíėā čáîááîóëõā é ë ėéũáîõ äáöå äï ōåëé ũåėéëïę ōåëé åũæōáôá ũïô ņ äáā
ũáí úåíėā óéā ðïęäéôå ũïúøíéôå ũ
îáóėåäéå úåíėā ëïôïōõā įïóðïäø ó ëėņôũïā ïâåýáė äáôø ïôãáí ũáûéí áũōááíõ
éóááëõ é éáëïũõ éí é ðïôïíóôũõ éč é ņ óëáúáė ũáí ũ
ôï ũōåíņ îå íïįõ ïäéî ũïäéôø ũáó įïóðïäø âïį ũáû ōáúíîïöéė ũáó é ũïô ũų
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
úåíėå åįéðåôóëïę îáä æáōáïîïí é îáä ũóåíé ōáâáíé åįï é îáä ũóåā úåíėåā
åįï é ðï ōõëå óéėøîïę é ðï ũåėéëéí þõäåóáí ëïôïōųå íïéóåę óïũåōûéė ðōåä
įėáúáíé ũóåįï éúōáéėņ
removed 'dat/russ/ptt/deu.1/raw.wfr'
creating the word frequency file dat/russ/ptt/deu.1/raw.wfr
the 10 most common words in dat/russ/ptt/deu.1/raw.tlw:
1726 0.08224 é
524 0.02497 îå
459 0.02187 ũ
345 0.01644 įïóðïäø
330 0.01572 îá
306 0.01458 åįï
215 0.01024 ôåâņ
207 0.00986 ôų
197 0.00939 âïį
190 0.00905 éč
removed 'dat/russ/ptt/deu.1/raw-whole-wds-summary.tex'
removed 'exp/russ/ptt/deu.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/russ/ptt/deu.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:30:54 by tex-make-sample-summary.sh
% Token and word counts for russ/ptt/deu.1/raw.wfr
%
\def\russpttwholedeuPBrawTks{20988}
\def\russpttwholedeuPBrawTksPct{100.0}
\def\russpttwholedeuPBrawWds{3913}
\def\russpttwholedeuPBrawWdsPct{18.6}
copied '/tmp/567640.file' -> 'exp/russ/ptt/deu.1/raw-whole-wds-summary.tex'
removed '/tmp/567640.file'
creating running text file dat/russ/ptt/deu.1/gud.wdf
sample:
óéé óõôø óėïũá ëïôïōųå įïũïōéė íïéóåę ũóåí éúōáéėøôņîáí úá éïōäáîïí ũ
ðõóôųîå îá ōáũîéîå ðōïôéũ óõæá íåöäõ æáōáîïí é ôïæåėïí é ėáũáîïí é
áóéōïæïí é äéúáįáũïí ũ
ōáóóôïņîéé ïäéîîáäãáôé äîåę ðõôé ïô čïōéũá ðï äïōïįå ïô įïōų óåéō ë
ëáäåó ũáōîé óïōïëïũïįï įïäá ïäéîîáäãáôïįï íåóņãá ũ
ðåōũųę äåîø íåóņãá įïũïōéė íïéóåę óųîáí éúōáéėåũųí ũóå þôï úáðïũåäáė åíõ
įïóðïäø ï îéč ðï õâéåîéé éí óéįïîá ãáōņ áíïōōåęóëïįï ëïôïōųę öéė ũ
åóåũïîå é ïįá ãáōņ ũáóáîóëïįï ëïôïōųę öéė ũ
áûôåōïæå ũ
åäōåé úá éïōäáîïí ũ
úåíėå íïáũéôóëïę îáþáė íïéóåę éúĸņóîņôø úáëïî óåę é óëáúáė įïóðïäø âïį
îáû įïũïōéė îáí ũ
čïōéũå é óëáúáė ðïėîï ũáí öéôø îá įïōå óåę ïâōáôéôåóø ïôðōáũøôåóø ũ
ðõôø é ðïęäéôå îá įïōõ áíïōōååũ é ëï ũóåí óïóåäņí éč îá ōáũîéîõ îá įïōõ
îá îéúëéå íåóôá é îá āöîųę ëōáę é ë âåōåįáí íïōņ ũ
úåíėā čáîááîóëõā é ë ėéũáîõ äáöå äï ōåëé ũåėéëïę ōåëé åũæōáôá ũïô ņ äáā
ũáí úåíėā óéā ðïęäéôå ũïúøíéôå ũ
îáóėåäéå úåíėā ëïôïōõā įïóðïäø ó ëėņôũïā ïâåýáė äáôø ïôãáí ũáûéí áũōááíõ
éóááëõ é éáëïũõ éí é ðïôïíóôũõ éč é ņ óëáúáė ũáí ũ
ôï ũōåíņ îå íïįõ ïäéî ũïäéôø ũáó įïóðïäø âïį ũáû ōáúíîïöéė ũáó é ũïô ũų
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
úåíėå åįéðåôóëïę îáä æáōáïîïí é îáä ũóåíé ōáâáíé åįï é îáä ũóåā úåíėåā
åįï é ðï ōõëå óéėøîïę é ðï ũåėéëéí þõäåóáí ëïôïōųå íïéóåę óïũåōûéė ðōåä
įėáúáíé ũóåįï éúōáéėņ
removed 'dat/russ/ptt/deu.1/gud.wfr'
creating the word frequency file dat/russ/ptt/deu.1/gud.wfr
the 10 most common words in dat/russ/ptt/deu.1/gud.tlw:
1726 0.08224 é
524 0.02497 îå
459 0.02187 ũ
345 0.01644 įïóðïäø
330 0.01572 îá
306 0.01458 åįï
215 0.01024 ôåâņ
207 0.00986 ôų
197 0.00939 âïį
190 0.00905 éč
removed 'dat/russ/ptt/deu.1/gud-whole-wds-summary.tex'
removed 'exp/russ/ptt/deu.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/russ/ptt/deu.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:30:54 by tex-make-sample-summary.sh
% Token and word counts for russ/ptt/deu.1/gud.wfr
%
\def\russpttwholedeuPBgudTks{20988}
\def\russpttwholedeuPBgudTksPct{100.0}
\def\russpttwholedeuPBgudWds{3913}
\def\russpttwholedeuPBgudWdsPct{18.6}
copied '/tmp/567684.file' -> 'exp/russ/ptt/deu.1/gud-whole-wds-summary.tex'
removed '/tmp/567684.file'
creating running text file dat/russ/ptt/deu.1/bad.wdf
sample:
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
removed 'dat/russ/ptt/deu.1/bad.wfr'
creating the word frequency file dat/russ/ptt/deu.1/bad.wfr
the 10 most common words in dat/russ/ptt/deu.1/bad.tlw:
removed 'dat/russ/ptt/deu.1/bad-whole-wds-summary.tex'
removed 'exp/russ/ptt/deu.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/russ/ptt/deu.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:30:54 by tex-make-sample-summary.sh
% Token and word counts for russ/ptt/deu.1/bad.wfr
%
\def\russpttwholedeuPBbadTks{0}
\def\russpttwholedeuPBbadTksPct{0.0}
\def\russpttwholedeuPBbadWds{0}
\def\russpttwholedeuPBbadWdsPct{0.0}
copied '/tmp/567728.file' -> 'exp/russ/ptt/deu.1/bad-whole-wds-summary.tex'
removed '/tmp/567728.file'
... creating word files dat/russ/ptt/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
111824 dat/russ/ptt/tot.1/whole.tlw
removed 'dat/russ/ptt/tot.1/raw.tlw'
removed 'dat/russ/ptt/tot.1/gud.tlw'
removed 'dat/russ/ptt/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
!! empty raw.tlw file '='
creating running text file dat/russ/ptt/tot.1/raw.wdf
sample:
ũ
îáþáėå óïôũïōéė âïį îåâï é úåíėā úåíėņ öå âųėá âåúũéäîá é ðõóôá é ôøíá
îáä âåúäîïā é äõč âïöéę îïóéėóņ îáä ũïäïā é óëáúáė âïį äá âõäåô óũåô é
óôáė óũåô é õũéäåė âïį óũåô þôï ïî čïōïû é ïôäåėéė âïį óũåô ïô ôøíų é
îáúũáė âïį óũåô äîåí á ôøíõ îïþøā é âųė ũåþåō é âųėï õôōï äåîø ïäéî é
óëáúáė âïį äá âõäåô ôũåōäø ðïóōåäé ũïäų é äá ïôäåėņåô ïîá ũïäõ ïô ũïäų é
óïúäáė âïį ôũåōäø é ïôäåėéė ũïäõ ëïôïōáņ ðïä ôũåōäøā ïô ũïäų ëïôïōáņ îáä
ôũåōäøā é óôáėï ôáë é îáúũáė âïį ôũåōäø îåâïí é âųė ũåþåō é âųėï õôōï
äåîø ũôïōïę é óëáúáė âïį äá óïâåōåôóņ ũïäá ëïôïōáņ ðïä îåâïí ũ
ïäîï íåóôï é äá ņũéôóņ óõûá é óôáėï ôáë é îáúũáė âïį óõûõ úåíėåā á
óïâōáîéå ũïä îáúũáė íïōņíé é õũéäåė âïį þôï üôï čïōïûï é óëáúáė âïį äá
ðōïéúōáóôéô úåíėņ úåėåîø ôōáũõ óåāýõā óåíņ äåōåũï ðėïäïũéôïå ðōéîïóņýåå
ðï ōïäõ óũïåíõ ðėïä ũ
ëïôïōïí óåíņ åįï îá úåíėå é óôáėï ôáë é ðōïéúũåėá úåíėņ úåėåîø ôōáũõ
óåāýõā óåíņ ðï ōïäõ åå é äåōåũï ðōéîïóņýåå ðėïä ũ
ëïôïōïí óåíņ åįï ðï ōïäõ åįï é õũéäåė âïį þôï üôï čïōïûï é âųė ũåþåō é
âųėï õôōï äåîø ôōåôéę é óëáúáė âïį äá âõäõô óũåôéėá îá ôũåōäé îåâåóîïę
äėņ ïôäåėåîéņ äîņ ïô îïþé é äėņ úîáíåîéę é ũōåíåî é äîåę é įïäïũ é äá
âõäõô ïîé óũåôéėøîéëáíé îá ôũåōäé îåâåóîïę þôïâų óũåôéôø îá úåíėā é
óôáėï ôáë é óïúäáė âïį äũá óũåôéėá ũåėéëéå óũåôéėï âïėøûåå äėņ
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
úåíėå åįéðåôóëïę îáä æáōáïîïí é îáä ũóåíé ōáâáíé åįï é îáä ũóåā úåíėåā
åįï é ðï ōõëå óéėøîïę é ðï ũåėéëéí þõäåóáí ëïôïōųå íïéóåę óïũåōûéė ðōåä
įėáúáíé ũóåįï éúōáéėņ
removed 'dat/russ/ptt/tot.1/raw.wfr'
creating the word frequency file dat/russ/ptt/tot.1/raw.wfr
the 10 most common words in dat/russ/ptt/tot.1/raw.tlw:
10036 0.08975 é
2573 0.02301 ũ
1732 0.01549 îå
1704 0.01524 îá
1602 0.01433 åįï
1070 0.00957 éú
992 0.00887 éč
986 0.00882 įïóðïäø
945 0.00845 ïî
945 0.00845 ó
removed 'dat/russ/ptt/tot.1/raw-whole-wds-summary.tex'
removed 'exp/russ/ptt/tot.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/russ/ptt/tot.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:30:54 by tex-make-sample-summary.sh
% Token and word counts for russ/ptt/tot.1/raw.wfr
%
\def\russpttwholetotPBrawTks{111824}
\def\russpttwholetotPBrawTksPct{100.0}
\def\russpttwholetotPBrawWds{12034}
\def\russpttwholetotPBrawWdsPct{10.8}
copied '/tmp/567784.file' -> 'exp/russ/ptt/tot.1/raw-whole-wds-summary.tex'
removed '/tmp/567784.file'
creating running text file dat/russ/ptt/tot.1/gud.wdf
sample:
ũ
îáþáėå óïôũïōéė âïį îåâï é úåíėā úåíėņ öå âųėá âåúũéäîá é ðõóôá é ôøíá
îáä âåúäîïā é äõč âïöéę îïóéėóņ îáä ũïäïā é óëáúáė âïį äá âõäåô óũåô é
óôáė óũåô é õũéäåė âïį óũåô þôï ïî čïōïû é ïôäåėéė âïį óũåô ïô ôøíų é
îáúũáė âïį óũåô äîåí á ôøíõ îïþøā é âųė ũåþåō é âųėï õôōï äåîø ïäéî é
óëáúáė âïį äá âõäåô ôũåōäø ðïóōåäé ũïäų é äá ïôäåėņåô ïîá ũïäõ ïô ũïäų é
óïúäáė âïį ôũåōäø é ïôäåėéė ũïäõ ëïôïōáņ ðïä ôũåōäøā ïô ũïäų ëïôïōáņ îáä
ôũåōäøā é óôáėï ôáë é îáúũáė âïį ôũåōäø îåâïí é âųė ũåþåō é âųėï õôōï
äåîø ũôïōïę é óëáúáė âïį äá óïâåōåôóņ ũïäá ëïôïōáņ ðïä îåâïí ũ
ïäîï íåóôï é äá ņũéôóņ óõûá é óôáėï ôáë é îáúũáė âïį óõûõ úåíėåā á
óïâōáîéå ũïä îáúũáė íïōņíé é õũéäåė âïį þôï üôï čïōïûï é óëáúáė âïį äá
ðōïéúōáóôéô úåíėņ úåėåîø ôōáũõ óåāýõā óåíņ äåōåũï ðėïäïũéôïå ðōéîïóņýåå
ðï ōïäõ óũïåíõ ðėïä ũ
ëïôïōïí óåíņ åįï îá úåíėå é óôáėï ôáë é ðōïéúũåėá úåíėņ úåėåîø ôōáũõ
óåāýõā óåíņ ðï ōïäõ åå é äåōåũï ðōéîïóņýåå ðėïä ũ
ëïôïōïí óåíņ åįï ðï ōïäõ åįï é õũéäåė âïį þôï üôï čïōïûï é âųė ũåþåō é
âųėï õôōï äåîø ôōåôéę é óëáúáė âïį äá âõäõô óũåôéėá îá ôũåōäé îåâåóîïę
äėņ ïôäåėåîéņ äîņ ïô îïþé é äėņ úîáíåîéę é ũōåíåî é äîåę é įïäïũ é äá
âõäõô ïîé óũåôéėøîéëáíé îá ôũåōäé îåâåóîïę þôïâų óũåôéôø îá úåíėā é
óôáėï ôáë é óïúäáė âïį äũá óũåôéėá ũåėéëéå óũåôéėï âïėøûåå äėņ
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
úåíėå åįéðåôóëïę îáä æáōáïîïí é îáä ũóåíé ōáâáíé åįï é îáä ũóåā úåíėåā
åįï é ðï ōõëå óéėøîïę é ðï ũåėéëéí þõäåóáí ëïôïōųå íïéóåę óïũåōûéė ðōåä
įėáúáíé ũóåįï éúōáéėņ
removed 'dat/russ/ptt/tot.1/gud.wfr'
creating the word frequency file dat/russ/ptt/tot.1/gud.wfr
the 10 most common words in dat/russ/ptt/tot.1/gud.tlw:
10036 0.08975 é
2573 0.02301 ũ
1732 0.01549 îå
1704 0.01524 îá
1602 0.01433 åįï
1070 0.00957 éú
992 0.00887 éč
986 0.00882 įïóðïäø
945 0.00845 ïî
945 0.00845 ó
removed 'dat/russ/ptt/tot.1/gud-whole-wds-summary.tex'
removed 'exp/russ/ptt/tot.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/russ/ptt/tot.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:30:54 by tex-make-sample-summary.sh
% Token and word counts for russ/ptt/tot.1/gud.wfr
%
\def\russpttwholetotPBgudTks{111824}
\def\russpttwholetotPBgudTksPct{100.0}
\def\russpttwholetotPBgudWds{12034}
\def\russpttwholetotPBgudWdsPct{10.8}
copied '/tmp/567828.file' -> 'exp/russ/ptt/tot.1/gud-whole-wds-summary.tex'
removed '/tmp/567828.file'
creating running text file dat/russ/ptt/tot.1/bad.wdf
sample:
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
removed 'dat/russ/ptt/tot.1/bad.wfr'
creating the word frequency file dat/russ/ptt/tot.1/bad.wfr
the 10 most common words in dat/russ/ptt/tot.1/bad.tlw:
removed 'dat/russ/ptt/tot.1/bad-whole-wds-summary.tex'
removed 'exp/russ/ptt/tot.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/russ/ptt/tot.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:30:54 by tex-make-sample-summary.sh
% Token and word counts for russ/ptt/tot.1/bad.wfr
%
\def\russpttwholetotPBbadTks{0}
\def\russpttwholetotPBbadTksPct{0.0}
\def\russpttwholetotPBbadWds{0}
\def\russpttwholetotPBbadWdsPct{0.0}
copied '/tmp/567872.file' -> 'exp/russ/ptt/tot.1/bad-whole-wds-summary.tex'
removed '/tmp/567872.file'
lines words bytes file
------- ------- --------- ------------
4899 9798 116560 dat/russ/ptt/gen.1/raw.wfr
4084 8168 97660 dat/russ/ptt/exo.1/raw.wfr
3952 7904 94780 dat/russ/ptt/num.1/raw.wfr
2659 5318 63570 dat/russ/ptt/lev.1/raw.wfr
3913 7826 93645 dat/russ/ptt/deu.1/raw.wfr
12034 24068 292848 dat/russ/ptt/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
4899 9798 116560 dat/russ/ptt/gen.1/gud.wfr
4084 8168 97660 dat/russ/ptt/exo.1/gud.wfr
3952 7904 94780 dat/russ/ptt/num.1/gud.wfr
2659 5318 63570 dat/russ/ptt/lev.1/gud.wfr
3913 7826 93645 dat/russ/ptt/deu.1/gud.wfr
12034 24068 292848 dat/russ/ptt/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
0 0 0 dat/russ/ptt/gen.1/bad.wfr
0 0 0 dat/russ/ptt/exo.1/bad.wfr
0 0 0 dat/russ/ptt/num.1/bad.wfr
0 0 0 dat/russ/ptt/lev.1/bad.wfr
0 0 0 dat/russ/ptt/deu.1/bad.wfr
0 0 0 dat/russ/ptt/tot.1/bad.wfr
gen.1 raw = 28445 gud = 28445 bad = 0
exo.1 raw = 22960 gud = 22960 bad = 0
num.1 raw = 22530 gud = 22530 bad = 0
lev.1 raw = 16901 gud = 16901 bad = 0
deu.1 raw = 20988 gud = 20988 bad = 0
tot.1 raw = 111824 gud = 111824 bad = 0
=== creating the derived word files dat/arab/quf/*/{raw,gud,bad}.{tlw,wdf,wfr} (whole) ===
... creating word files dat/arab/quf/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
83724 dat/arab/quf/tot.1/whole.tlw
removed 'dat/arab/quf/tot.1/raw.tlw'
removed 'dat/arab/quf/tot.1/gud.tlw'
removed 'dat/arab/quf/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/arab/quf/tot.1/raw.wdf
sample:
bîs°mî alllâhî alrrâĩ°mânî alrrâĩîymî =
al°ĩâm°dû lîllâhî râbbî al°ŋâlâmîynâ =
alrrâĩ°mânî alrrâĩîymî =
mâlîkî yâw°mî alddîynî =
aĄîyyâakâ nâŋ°bûdû wâaĄîyyâakâ nâs°tâŋîynû =
ah°dînâa alßßîrâąâ al°mûs°tâqîymâ =
ßîrâąâ allâĢîynâ a!ân°ŋâm°tâ ŋâlây°hîm° Īây°rî al°mâĪ°ðûwbî ŋâlây°hîm°
wâlâa alððâallîynâ =
a/l/m =
Ģâlîkâ al°kîtâbû lâa rây°bâ fîyhî hûdäå lîl°mûttâqîynâ =
allâĢîynâ yûw!°mînûwnâ bîal°Īây°bî wâyûqîymûwnâ alßßâlâwĻâ wâmîmmâa
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
mîn° al°jînnâĻî wâalnnâasî =
removed 'dat/arab/quf/tot.1/raw.wfr'
creating the word frequency file dat/arab/quf/tot.1/raw.wfr
the 10 most common words in dat/arab/quf/tot.1/raw.tlw:
6236 0.07448 =
2316 0.02766 mîn°
1184 0.01414 fîy
989 0.01181 mâa
791 0.00945 alllâhî
781 0.00933 lâa
778 0.00929 allâĢîynâ
714 0.00853 alllâhû
641 0.00766 ŋâlâå
632 0.00755 wâmâa
removed 'dat/arab/quf/tot.1/raw-whole-wds-summary.tex'
removed 'exp/arab/quf/tot.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/arab/quf/tot.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:30:54 by tex-make-sample-summary.sh
% Token and word counts for arab/quf/tot.1/raw.wfr
%
\def\arabqufwholetotPBrawTks{83724}
\def\arabqufwholetotPBrawTksPct{100.0}
\def\arabqufwholetotPBrawWds{19921}
\def\arabqufwholetotPBrawWdsPct{23.8}
copied '/tmp/568043.file' -> 'exp/arab/quf/tot.1/raw-whole-wds-summary.tex'
removed '/tmp/568043.file'
creating running text file dat/arab/quf/tot.1/gud.wdf
sample:
bîs°mî alllâhî alrrâĩ°mânî alrrâĩîymî al°ĩâm°dû lîllâhî râbbî
al°ŋâlâmîynâ alrrâĩ°mânî alrrâĩîymî mâlîkî yâw°mî alddîynî aĄîyyâakâ
nâŋ°bûdû wâaĄîyyâakâ nâs°tâŋîynû ah°dînâa alßßîrâąâ al°mûs°tâqîymâ
ßîrâąâ allâĢîynâ a!ân°ŋâm°tâ ŋâlây°hîm° Īây°rî al°mâĪ°ðûwbî ŋâlây°hîm°
wâlâa alððâallîynâ Ģâlîkâ al°kîtâbû lâa rây°bâ fîyhî hûdäå
lîl°mûttâqîynâ allâĢîynâ yûw!°mînûwnâ bîal°Īây°bî wâyûqîymûwnâ
alßßâlâwĻâ wâmîmmâa râzâq°nâhûm° yûnfîqûwnâ wâallâĢîynâ yûw!°mînûwnâ
bîmâa aûn°zîlâ aîlây°kâ wâmâa aûn°zîlâ mîn° qâb°lîkâ wâbîal°a'ĐîrâĻî
hûm° yûwqînûwnâ aûw°ly!îkâ ŋâlâå hûdäå mîn° râbbîhîm° waûw°ly!îkâ hûm°
al°mûf°lîĩûwnâ aînnâ allâĢîynâ kâfârûwa sâwâa'ü ŋâlây°hîm°
'âanĢâr°tâhûm° am° lâm° tûnĢîr°hûm° lâa yûw!°mînûwnâ Đâtâmâ alllâhû
ŋâlâå qûlûwbîhîm° wâŋâlâå sâm°ŋîhîm° wâŋâlâå ab°ßârîhîm° ĪîxâwâĻü
wâlâhûm° ŋâĢâabü ŋâįîymü wâmîn° alnnâasî mân° yâqûwlû 'amânnâa bîalllâhî
wâbîal°yâw°mî al°a'Đîrî wâmâa hûm° bîmûw!°mînîynâ yûĐâdîŋûwnâ alllâhâ
wâallâĢîynâ 'amânûwa wâmâa yâĐ°dâŋûwnâ aîllâa anfûsâhûm° wâmâa
yâx°ŋûrûwnâ fîy qûlûwbîhîm° mârâðü fâzâadâhûm° alllâhû mârâðäa wâlâhûm°
ŋâĢâabü alîymü bîmâa kâanûwa yâk°Ģîbûwnâ wâaîĢâa qîylâ lâhûm° lâa
tûf°sîdûwa fîy al°ar°ðî qâalûwa aînnâmâa nâĩ°nû mûß°lîĩûwnâ alâa
aînnâhûm° hûm° al°mûf°sîdûwnâ wâlâkîn° lâa yâx°ŋûrûwnâ wâaîĢâa qîylâ
lâhûm° 'amînûwa kâmâa 'amânâ alnnâasû qâalûwa anûw!°mînû kâmâa 'amânâ
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
ĩâsâdâ qûl° a!âŋûwĢû bîrâbbî alnnâasî mâlîkî alnnâasî aĄîlâhî alnnâasî
mîn° xârrî al°wâs°wâasî al°Đânnâasî allâĢîy yûwâs°wîsû fîy ßûdûwrî
alnnâasî mîn° al°jînnâĻî wâalnnâasî
removed 'dat/arab/quf/tot.1/gud.wfr'
creating the word frequency file dat/arab/quf/tot.1/gud.wfr
the 10 most common words in dat/arab/quf/tot.1/gud.tlw:
2316 0.02992 mîn°
1184 0.01530 fîy
989 0.01278 mâa
791 0.01022 alllâhî
781 0.01009 lâa
778 0.01005 allâĢîynâ
714 0.00923 alllâhû
641 0.00828 ŋâlâå
632 0.00817 wâmâa
630 0.00814 wâlâa
removed 'dat/arab/quf/tot.1/gud-whole-wds-summary.tex'
removed 'exp/arab/quf/tot.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/arab/quf/tot.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:30:55 by tex-make-sample-summary.sh
% Token and word counts for arab/quf/tot.1/gud.wfr
%
\def\arabqufwholetotPBgudTks{77394}
\def\arabqufwholetotPBgudTksPct{92.4}
\def\arabqufwholetotPBgudWds{19852}
\def\arabqufwholetotPBgudWdsPct{23.7}
copied '/tmp/568087.file' -> 'exp/arab/quf/tot.1/gud-whole-wds-summary.tex'
removed '/tmp/568087.file'
creating running text file dat/arab/quf/tot.1/bad.wdf
sample:
=
=
=
=
=
=
=
a/l/m =
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/arab/quf/tot.1/bad.wfr'
creating the word frequency file dat/arab/quf/tot.1/bad.wfr
the 10 most common words in dat/arab/quf/tot.1/bad.tlw:
6236 0.98515 =
7 0.00111 ĩ/m
6 0.00095 a/l/m
5 0.00079 a/l/r
4 0.00063 û
3 0.00047 tâkû°
2 0.00032 lîl°âmâlây!îkâĻî
2 0.00032 nîŋ°mâtââ
2 0.00032 wâal°âmâlây!îkâĻî
2 0.00032 ą/s/m
removed 'dat/arab/quf/tot.1/bad-whole-wds-summary.tex'
removed 'exp/arab/quf/tot.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/arab/quf/tot.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:30:55 by tex-make-sample-summary.sh
% Token and word counts for arab/quf/tot.1/bad.wfr
%
\def\arabqufwholetotPBbadTks{6330}
\def\arabqufwholetotPBbadTksPct{7.6}
\def\arabqufwholetotPBbadWds{69}
\def\arabqufwholetotPBbadWdsPct{0.1}
copied '/tmp/568131.file' -> 'exp/arab/quf/tot.1/bad-whole-wds-summary.tex'
removed '/tmp/568131.file'
lines words bytes file
------- ------- --------- ------------
19921 59749 529880 dat/arab/quf/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
19852 59545 528082 dat/arab/quf/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
69 204 1798 dat/arab/quf/tot.1/bad.wfr
tot.1 raw = 83724 gud = 77394 bad = 6330
=== creating the derived word files dat/arab/quv/*/{raw,gud,bad}.{tlw,wdf,wfr} (whole) ===
... creating word files dat/arab/quv/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
83724 dat/arab/quv/tot.1/whole.tlw
removed 'dat/arab/quv/tot.1/raw.tlw'
removed 'dat/arab/quv/tot.1/gud.tlw'
removed 'dat/arab/quv/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/arab/quv/tot.1/raw.wdf
sample:
bîsmî alllâhî alrrâĩmânî alrrâĩîymî =
alĩâmdû lîllâhî râbbî alŋâlâmîynâ =
alrrâĩmânî alrrâĩîymî =
mâlîkî yâwmî alddîynî =
aĄîyyâakâ nâŋbûdû wâaĄîyyâakâ nâstâŋîynû =
ahdînâa alßßîrâąâ almûstâqîymâ =
ßîrâąâ allâĢîynâ a!ânŋâmtâ ŋâlâyhîm Īâyrî almâĪðûwbî ŋâlâyhîm wâlâa
alððâallîynâ =
a/l/m =
Ģâlîkâ alkîtâbû lâa râybâ fîyhî hûdäå lîlmûttâqîynâ =
allâĢîynâ yûw!mînûwnâ bîalĪâybî wâyûqîymûwnâ alßßâlâwĻâ wâmîmmâa
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
mîn aljînnâĻî wâalnnâasî =
removed 'dat/arab/quv/tot.1/raw.wfr'
creating the word frequency file dat/arab/quv/tot.1/raw.wfr
the 10 most common words in dat/arab/quv/tot.1/raw.tlw:
6236 0.07448 =
2317 0.02767 mîn
1184 0.01414 fîy
989 0.01181 mâa
791 0.00945 alllâhî
781 0.00933 lâa
778 0.00929 allâĢîynâ
714 0.00853 alllâhû
641 0.00766 ŋâlâå
632 0.00755 wâmâa
removed 'dat/arab/quv/tot.1/raw-whole-wds-summary.tex'
removed 'exp/arab/quv/tot.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/arab/quv/tot.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:30:55 by tex-make-sample-summary.sh
% Token and word counts for arab/quv/tot.1/raw.wfr
%
\def\arabquvwholetotPBrawTks{83724}
\def\arabquvwholetotPBrawTksPct{100.0}
\def\arabquvwholetotPBrawWds{19586}
\def\arabquvwholetotPBrawWdsPct{23.4}
copied '/tmp/568226.file' -> 'exp/arab/quv/tot.1/raw-whole-wds-summary.tex'
removed '/tmp/568226.file'
creating running text file dat/arab/quv/tot.1/gud.wdf
sample:
bîsmî alllâhî alrrâĩmânî alrrâĩîymî alĩâmdû lîllâhî râbbî alŋâlâmîynâ
alrrâĩmânî alrrâĩîymî mâlîkî yâwmî alddîynî aĄîyyâakâ nâŋbûdû
wâaĄîyyâakâ nâstâŋîynû ahdînâa alßßîrâąâ almûstâqîymâ ßîrâąâ allâĢîynâ
a!ânŋâmtâ ŋâlâyhîm Īâyrî almâĪðûwbî ŋâlâyhîm wâlâa alððâallîynâ Ģâlîkâ
alkîtâbû lâa râybâ fîyhî hûdäå lîlmûttâqîynâ allâĢîynâ yûw!mînûwnâ
bîalĪâybî wâyûqîymûwnâ alßßâlâwĻâ wâmîmmâa râzâqnâhûm yûnfîqûwnâ
wâallâĢîynâ yûw!mînûwnâ bîmâa aûnzîlâ aîlâykâ wâmâa aûnzîlâ mîn qâblîkâ
wâbîala'ĐîrâĻî hûm yûwqînûwnâ aûwly!îkâ ŋâlâå hûdäå mîn râbbîhîm
waûwly!îkâ hûm almûflîĩûwnâ aînnâ allâĢîynâ kâfârûwa sâwâa'ü ŋâlâyhîm
'âanĢârtâhûm am lâm tûnĢîrhûm lâa yûw!mînûwnâ Đâtâmâ alllâhû ŋâlâå
qûlûwbîhîm wâŋâlâå sâmŋîhîm wâŋâlâå abßârîhîm ĪîxâwâĻü wâlâhûm ŋâĢâabü
ŋâįîymü wâmîn alnnâasî mân yâqûwlû 'amânnâa bîalllâhî wâbîalyâwmî
ala'Đîrî wâmâa hûm bîmûw!mînîynâ yûĐâdîŋûwnâ alllâhâ wâallâĢîynâ
'amânûwa wâmâa yâĐdâŋûwnâ aîllâa anfûsâhûm wâmâa yâxŋûrûwnâ fîy
qûlûwbîhîm mârâðü fâzâadâhûm alllâhû mârâðäa wâlâhûm ŋâĢâabü alîymü
bîmâa kâanûwa yâkĢîbûwnâ wâaîĢâa qîylâ lâhûm lâa tûfsîdûwa fîy alarðî
qâalûwa aînnâmâa nâĩnû mûßlîĩûwnâ alâa aînnâhûm hûm almûfsîdûwnâ wâlâkîn
lâa yâxŋûrûwnâ wâaîĢâa qîylâ lâhûm 'amînûwa kâmâa 'amânâ alnnâasû
qâalûwa anûw!mînû kâmâa 'amânâ alssûfâhâa'û alâa aînnâhûm hûm
alssûfâhâa'û wâlâkîn lâa yâŋlâmûwnâ wâaîĢâa lâqûwa allâĢîynâ 'amânûwa
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
aĄîĢâa ĩâsâdâ qûl a!âŋûwĢû bîrâbbî alnnâasî mâlîkî alnnâasî aĄîlâhî
alnnâasî mîn xârrî alwâswâasî alĐânnâasî allâĢîy yûwâswîsû fîy ßûdûwrî
alnnâasî mîn aljînnâĻî wâalnnâasî
removed 'dat/arab/quv/tot.1/gud.wfr'
creating the word frequency file dat/arab/quv/tot.1/gud.wfr
the 10 most common words in dat/arab/quv/tot.1/gud.tlw:
2317 0.02993 mîn
1184 0.01529 fîy
989 0.01278 mâa
791 0.01022 alllâhî
781 0.01009 lâa
778 0.01005 allâĢîynâ
714 0.00922 alllâhû
641 0.00828 ŋâlâå
632 0.00816 wâmâa
630 0.00814 wâlâa
removed 'dat/arab/quv/tot.1/gud-whole-wds-summary.tex'
removed 'exp/arab/quv/tot.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/arab/quv/tot.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:30:55 by tex-make-sample-summary.sh
% Token and word counts for arab/quv/tot.1/gud.wfr
%
\def\arabquvwholetotPBgudTks{77411}
\def\arabquvwholetotPBgudTksPct{92.5}
\def\arabquvwholetotPBgudWds{19530}
\def\arabquvwholetotPBgudWdsPct{23.3}
copied '/tmp/568270.file' -> 'exp/arab/quv/tot.1/gud-whole-wds-summary.tex'
removed '/tmp/568270.file'
creating running text file dat/arab/quv/tot.1/bad.wdf
sample:
=
=
=
=
=
=
=
a/l/m =
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/arab/quv/tot.1/bad.wfr'
creating the word frequency file dat/arab/quv/tot.1/bad.wfr
the 10 most common words in dat/arab/quv/tot.1/bad.tlw:
6236 0.98780 =
7 0.00111 ĩ/m
6 0.00095 a/l/m
5 0.00079 a/l/r
4 0.00063 û
2 0.00032 nîŋmâtââ
2 0.00032 ą/s/m
2 0.00032 âawâlâm
2 0.00032 ü
1 0.00016 a/l/m/r
removed 'dat/arab/quv/tot.1/bad-whole-wds-summary.tex'
removed 'exp/arab/quv/tot.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/arab/quv/tot.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:30:55 by tex-make-sample-summary.sh
% Token and word counts for arab/quv/tot.1/bad.wfr
%
\def\arabquvwholetotPBbadTks{6313}
\def\arabquvwholetotPBbadTksPct{7.5}
\def\arabquvwholetotPBbadWds{56}
\def\arabquvwholetotPBbadWdsPct{0.1}
copied '/tmp/568314.file' -> 'exp/arab/quv/tot.1/bad-whole-wds-summary.tex'
removed '/tmp/568314.file'
lines words bytes file
------- ------- --------- ------------
19586 58744 506867 dat/arab/quv/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
19530 58579 505470 dat/arab/quv/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
56 165 1397 dat/arab/quv/tot.1/bad.wfr
tot.1 raw = 83724 gud = 77411 bad = 6313
=== creating the derived word files dat/arab/qud/*/{raw,gud,bad}.{tlw,wdf,wfr} (whole) ===
... creating word files dat/arab/qud/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
83717 dat/arab/qud/tot.1/whole.tlw
removed 'dat/arab/qud/tot.1/raw.tlw'
removed 'dat/arab/qud/tot.1/gud.tlw'
removed 'dat/arab/qud/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/arab/qud/tot.1/raw.wdf
sample:
bsm alllh alrrĩmn alrrĩym =
alĩmd lllh rbb alŋlmyn =
alrrĩmn alrrĩym =
mlk ywm alddyn =
ayyak nŋbd wayyak nstŋyn =
ahdna alßßrą almstqym =
ßrą allĢyn anŋmt ŋlyhm Īyr almĪðwb ŋlyhm wla alððallyn =
a/l/m =
Ģlk alktb la ryb fyh hdå llmttqyn =
allĢyn ywmnwn balĪyb wyqymwn alßßlwĻ wmmma rzqnhm ynfqwn =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
mn aljnnĻ walnnas =
removed 'dat/arab/qud/tot.1/raw.wfr'
creating the word frequency file dat/arab/qud/tot.1/raw.wfr
the 10 most common words in dat/arab/qud/tot.1/raw.tlw:
6236 0.07449 =
2755 0.03291 mn
2089 0.02495 alllh
1184 0.01414 fy
1004 0.01199 ma
897 0.01071 an
810 0.00968 la
780 0.00932 allĢyn
707 0.00845 ann
670 0.00800 ŋlå
removed 'dat/arab/qud/tot.1/raw-whole-wds-summary.tex'
removed 'exp/arab/qud/tot.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/arab/qud/tot.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:30:56 by tex-make-sample-summary.sh
% Token and word counts for arab/qud/tot.1/raw.wfr
%
\def\arabqudwholetotPBrawTks{83717}
\def\arabqudwholetotPBrawTksPct{100.0}
\def\arabqudwholetotPBrawWds{15325}
\def\arabqudwholetotPBrawWdsPct{18.3}
copied '/tmp/568409.file' -> 'exp/arab/qud/tot.1/raw-whole-wds-summary.tex'
removed '/tmp/568409.file'
creating running text file dat/arab/qud/tot.1/gud.wdf
sample:
bsm alllh alrrĩmn alrrĩym alĩmd lllh rbb alŋlmyn alrrĩmn alrrĩym mlk ywm
alddyn ayyak nŋbd wayyak nstŋyn ahdna alßßrą almstqym ßrą allĢyn anŋmt
ŋlyhm Īyr almĪðwb ŋlyhm wla alððallyn Ģlk alktb la ryb fyh hdå llmttqyn
allĢyn ywmnwn balĪyb wyqymwn alßßlwĻ wmmma rzqnhm ynfqwn wallĢyn ywmnwn
bma anzl alyk wma anzl mn qblk wbala'ĐrĻ hm ywqnwn awlyk ŋlå hdå mn
rbbhm wawlyk hm almflĩwn ann allĢyn kfrwa swa' ŋlyhm 'anĢrthm am lm
tnĢrhm la ywmnwn Đtm alllh ŋlå qlwbhm wŋlå smŋhm wŋlå abßrhm ĪxwĻ wlhm
ŋĢab ŋįym wmn alnnas mn yqwl 'amnna balllh wbalywm ala'Đr wma hm bmwmnyn
yĐdŋwn alllh wallĢyn 'amnwa wma yĐdŋwn alla anfshm wma yxŋrwn fy qlwbhm
mrð fzadhm alllh mrða wlhm ŋĢab alym bma kanwa ykĢbwn waĢa qyl lhm la
tfsdwa fy alarð qalwa annma nĩn mßlĩwn ala annhm hm almfsdwn wlkn la
yxŋrwn waĢa qyl lhm 'amnwa kma 'amn alnnas qalwa anwmn kma 'amn alssfha'
ala annhm hm alssfha' wlkn la yŋlmwn waĢa lqwa allĢyn 'amnwa qalwa
'amnna waĢa Đlwa alå xyąynhm qalwa anna mŋkm annma nĩn msthz'wn alllh
ysthzy bhm wymddhm fy ąĪynhm yŋmhwn awlyk allĢyn axtrwa alððllĻ balhdå
fma rbĩt tjrthm wma kanwa mhtdyn mþlhm kmþl allĢy astwqd nara flmma
aða't ma ĩwlh Ģhb alllh bnwrhm wtrkhm fy įlmt la ybßrwn ßmm bkm ŋmy fhm
la yrjŋwn aw kßyyb mn alssma' fyh įlmt wrŋd wbrq yjŋlwn aßbŋhm fy
'aĢanhm mn alßßwŋq ĩĢr almwt walllh mĩyą balkfryn ykad albrq yĐąf abßrhm
kllma aða' lhm mxwa fyh waĢa aįlm ŋlyhm qamwa wlw xa' alllh lĢhb bsmŋhm
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
aĢa wqb wmn xrr alnnffþt fy alŋqd wmn xrr ĩasd aĢa ĩsd ql aŋwĢ brbb
alnnas mlk alnnas alh alnnas mn xrr alwswas alĐnnas allĢy ywsws fy ßdwr
alnnas mn aljnnĻ walnnas
removed 'dat/arab/qud/tot.1/gud.wfr'
creating the word frequency file dat/arab/qud/tot.1/gud.wfr
the 10 most common words in dat/arab/qud/tot.1/gud.tlw:
2755 0.03557 mn
2089 0.02697 alllh
1184 0.01529 fy
1004 0.01296 ma
897 0.01158 an
810 0.01046 la
780 0.01007 allĢyn
707 0.00913 ann
670 0.00865 ŋlå
661 0.00853 alla
removed 'dat/arab/qud/tot.1/gud-whole-wds-summary.tex'
removed 'exp/arab/qud/tot.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/arab/qud/tot.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:30:56 by tex-make-sample-summary.sh
% Token and word counts for arab/qud/tot.1/gud.wfr
%
\def\arabqudwholetotPBgudTks{77455}
\def\arabqudwholetotPBgudTksPct{92.5}
\def\arabqudwholetotPBgudWds{15314}
\def\arabqudwholetotPBgudWdsPct{18.3}
copied '/tmp/568453.file' -> 'exp/arab/qud/tot.1/gud-whole-wds-summary.tex'
removed '/tmp/568453.file'
creating running text file dat/arab/qud/tot.1/bad.wdf
sample:
=
=
=
=
=
=
=
a/l/m =
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/arab/qud/tot.1/bad.wfr'
creating the word frequency file dat/arab/qud/tot.1/bad.wfr
the 10 most common words in dat/arab/qud/tot.1/bad.tlw:
6236 0.99585 =
7 0.00112 ĩ/m
6 0.00096 a/l/m
5 0.00080 a/l/r
2 0.00032 ą/s/m
1 0.00016 a/l/m/r
1 0.00016 a/l/m/ß
1 0.00016 k/h/y/ŋ/ß
1 0.00016 y/s
1 0.00016 ą/h
removed 'dat/arab/qud/tot.1/bad-whole-wds-summary.tex'
removed 'exp/arab/qud/tot.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/arab/qud/tot.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:30:56 by tex-make-sample-summary.sh
% Token and word counts for arab/qud/tot.1/bad.wfr
%
\def\arabqudwholetotPBbadTks{6262}
\def\arabqudwholetotPBbadTksPct{7.5}
\def\arabqudwholetotPBbadWds{11}
\def\arabqudwholetotPBbadWdsPct{0.0}
copied '/tmp/568497.file' -> 'exp/arab/qud/tot.1/bad-whole-wds-summary.tex'
removed '/tmp/568497.file'
lines words bytes file
------- ------- --------- ------------
15325 45965 345260 dat/arab/qud/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
15314 45932 345022 dat/arab/qud/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
11 33 238 dat/arab/qud/tot.1/bad.wfr
tot.1 raw = 83717 gud = 77455 bad = 6262
=== creating the derived word files dat/arab/qph/*/{raw,gud,bad}.{tlw,wdf,wfr} (whole) ===
... creating word files dat/arab/qph/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
84081 dat/arab/qph/tot.1/whole.tlw
removed 'dat/arab/qph/tot.1/raw.tlw'
removed 'dat/arab/qph/tot.1/gud.tlw'
removed 'dat/arab/qph/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/arab/qph/tot.1/raw.wdf
sample:
bîsmî allâhî alrrâĩmânî alrrâĩymî =
alĩâmdû lîllâhî râbbî alŋâlâmynâ =
alrrâĩmânî alrrâĩymî =
mâlîkî yâwmî alddynî =
aîyyâkâ nâŋbûdû wâaîyyâkâ nâstâŋynû =
aîhdînâ alßßîrâąâ almûstâqymâ =
ßîrâąâ allâĢynâ anŋâmtâ ŋâlâyhîm Īâyrî almâĪðwbî ŋâlâyhîm wâlâ
alððâllynâ =
alîflâmmym =
Ģâlîkâ alkîtâbû lâ râybâ fyhî hûdân lîlmûttâqynâ =
allâĢynâ yû'mînwnâ bîaâlĪâybî wâyûqymwnâ alßßâlâtâ wâmîmmâ râzâqnâhûm
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
mînâ aljînnâtî wâalnnâsî =
removed 'dat/arab/qph/tot.1/raw.wfr'
creating the word frequency file dat/arab/qph/tot.1/raw.wfr
the 10 most common words in dat/arab/qph/tot.1/raw.tlw:
6236 0.07417 =
1672 0.01989 mîn
1183 0.01407 fy
1009 0.01200 mâ
827 0.00984 allâhî
816 0.00970 lâ
810 0.00963 allâĢynâ
765 0.00910 aînnâ
736 0.00875 allâhû
693 0.00824 mînâ
removed 'dat/arab/qph/tot.1/raw-whole-wds-summary.tex'
removed 'exp/arab/qph/tot.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/arab/qph/tot.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:30:56 by tex-make-sample-summary.sh
% Token and word counts for arab/qph/tot.1/raw.wfr
%
\def\arabqphwholetotPBrawTks{84081}
\def\arabqphwholetotPBrawTksPct{100.0}
\def\arabqphwholetotPBrawWds{17381}
\def\arabqphwholetotPBrawWdsPct{20.7}
copied '/tmp/568592.file' -> 'exp/arab/qph/tot.1/raw-whole-wds-summary.tex'
removed '/tmp/568592.file'
creating running text file dat/arab/qph/tot.1/gud.wdf
sample:
bîsmî allâhî alrrâĩmânî alrrâĩymî alĩâmdû lîllâhî râbbî alŋâlâmynâ
alrrâĩmânî alrrâĩymî mâlîkî yâwmî alddynî aîyyâkâ nâŋbûdû wâaîyyâkâ
nâstâŋynû aîhdînâ alßßîrâąâ almûstâqymâ ßîrâąâ allâĢynâ anŋâmtâ ŋâlâyhîm
Īâyrî almâĪðwbî ŋâlâyhîm wâlâ alððâllynâ alîflâmmym Ģâlîkâ alkîtâbû lâ
râybâ fyhî hûdân lîlmûttâqynâ allâĢynâ yû'mînwnâ bîaâlĪâybî wâyûqymwnâ
alßßâlâtâ wâmîmmâ râzâqnâhûm yûnfîqwnâ wâallâĢynâ yû'mînwnâ bîmâ anzîlâ
aîlâykâ wâmâ anzîlâ mîn qâblîkâ wâbîaâlaĐîrâtî hûm ywqînwnâ alâaîkâ ŋâlâ
hûdân mîn râbbîhîm wâalâaîkâ hûmû almûflîĩwnâ aînnâ allâĢynâ kâfârw
sâwâan ŋâlâyhîm aânĢârtâhûm am lâm tûnĢîrhûm lâ yû'mînwnâ Đâtâmâ allâhû
ŋâlâ qûlwbîhîm wâŋâlâ sâmŋîhîm wâŋâlâ abßârîhîm Īîxâwâtûn wâlâhûm
ŋâĢâbûn ŋâįymûn wâmînâ alnnâsî mân yâqwlû amânnâ bîaâllâhî wâbîaâlyâwmî
alaĐîrî wâmâ hûm bîmû'mînynâ yûĐâdîŋwnâ allâhâ wâallâĢynâ amânw wâmâ
yâĐdâŋwnâ aîllâ anfûsâhûm wâmâ yâxŋûrwnâ fy qûlwbîhîm mârâðûn fâzâdâhûmû
allâhû mârâðân wâlâhûm ŋâĢâbûn alymûn bîmâ kânw yâkĢîbwnâ wâaîĢâ qylâ
lâhûm lâ tûfsîdw fy alarðî qâlw aînnâmâ nâĩnû mûßlîĩwnâ alâ aînnâhûm
hûmû almûfsîdwnâ wâlâkîn lâ yâxŋûrwnâ wâaîĢâ qylâ lâhûm amînw kâmâ amânâ
alnnâsû qâlw anû'mînû kâmâ amânâ alssûfâhâa alâ aînnâhûm hûmû alssûfâhâa
wâlâkîn lâ yâŋlâmwnâ wâaîĢâ lâqw allâĢynâ amânw qâlw amânnâ wâaîĢâ Đâlâw
aîlâ xâyâąynîhîm qâlw aînnâ mâŋâkûm aînnâmâ nâĩnû mûstâhzîwnâ allâhû
yâstâhzîa bîhîm wâyâmûddûhûm fy ąûĪyânîhîm yâŋmâhwnâ alâaîkâ allâĢynâ
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
alnnâffâþâtî fy alŋûqâdî wâmîn xârrî ĩâsîdîn aîĢâ ĩâsâdâ qûl aŋwĢû
bîrâbbî alnnâsî mâlîkî alnnâsî aîlâhî alnnâsî mîn xârrî alwâswâsî
alĐânnâsî allâĢy yûwâswîsû fy ßûdwrî alnnâsî mînâ aljînnâtî wâalnnâsî
removed 'dat/arab/qph/tot.1/gud.wfr'
creating the word frequency file dat/arab/qph/tot.1/gud.wfr
the 10 most common words in dat/arab/qph/tot.1/gud.tlw:
1672 0.02148 mîn
1183 0.01520 fy
1009 0.01296 mâ
827 0.01062 allâhî
816 0.01048 lâ
810 0.01041 allâĢynâ
765 0.00983 aînnâ
736 0.00945 allâhû
693 0.00890 mînâ
671 0.00862 ŋâlâ
removed 'dat/arab/qph/tot.1/gud-whole-wds-summary.tex'
removed 'exp/arab/qph/tot.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/arab/qph/tot.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:30:57 by tex-make-sample-summary.sh
% Token and word counts for arab/qph/tot.1/gud.wfr
%
\def\arabqphwholetotPBgudTks{77845}
\def\arabqphwholetotPBgudTksPct{92.6}
\def\arabqphwholetotPBgudWds{17380}
\def\arabqphwholetotPBgudWdsPct{20.7}
copied '/tmp/568636.file' -> 'exp/arab/qph/tot.1/gud-whole-wds-summary.tex'
removed '/tmp/568636.file'
creating running text file dat/arab/qph/tot.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/arab/qph/tot.1/bad.wfr'
creating the word frequency file dat/arab/qph/tot.1/bad.wfr
the 10 most common words in dat/arab/qph/tot.1/bad.tlw:
6236 1.00000 =
removed 'dat/arab/qph/tot.1/bad-whole-wds-summary.tex'
removed 'exp/arab/qph/tot.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/arab/qph/tot.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:30:57 by tex-make-sample-summary.sh
% Token and word counts for arab/qph/tot.1/bad.wfr
%
\def\arabqphwholetotPBbadTks{6236}
\def\arabqphwholetotPBbadTksPct{7.4}
\def\arabqphwholetotPBbadWds{1}
\def\arabqphwholetotPBbadWdsPct{0.0}
copied '/tmp/568680.file' -> 'exp/arab/qph/tot.1/bad-whole-wds-summary.tex'
removed '/tmp/568680.file'
lines words bytes file
------- ------- --------- ------------
17381 52137 439550 dat/arab/qph/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
17380 52134 439532 dat/arab/qph/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
1 3 18 dat/arab/qph/tot.1/bad.wfr
tot.1 raw = 84081 gud = 77845 bad = 6236
=== creating the derived word files dat/arab/qcs/*/{raw,gud,bad}.{tlw,wdf,wfr} (whole) ===
... creating word files dat/arab/qcs/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
80448 dat/arab/qcs/tot.1/whole.tlw
removed 'dat/arab/qcs/tot.1/raw.tlw'
removed 'dat/arab/qcs/tot.1/gud.tlw'
removed 'dat/arab/qcs/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/arab/qcs/tot.1/raw.wdf
sample:
bsm allh alrĩmn alrĩym =
alĩmd llh rb alŋalmyn =
alrĩmn alrĩym =
malk ywm aldyn =
ayak nŋbd wayak nstŋyn =
ahdna alßraą almstqym =
ßraą alĢyn anŋmt ŋlyhm Īyr almĪðwb ŋlyhm wlaalðalyn =
alm =
Ģlk alktab laryb fyh hdå llmtqyn =
alĢyn yw!mnwn balĪyb wyqymwn alßlaĻ wmma rzqnahm ynfqwn =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
mn aljnĻ walnas =
removed 'dat/arab/qcs/tot.1/raw.wfr'
creating the word frequency file dat/arab/qcs/tot.1/raw.wfr
the 10 most common words in dat/arab/qcs/tot.1/raw.tlw:
6236 0.07752 =
2751 0.03420 mn
2132 0.02650 allh
1604 0.01994 an
1075 0.01336 fy
808 0.01004 alĢyn
746 0.00927 ala
657 0.00817 ŋlå
413 0.00513 qal
409 0.00508 alå
removed 'dat/arab/qcs/tot.1/raw-whole-wds-summary.tex'
removed 'exp/arab/qcs/tot.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/arab/qcs/tot.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:30:57 by tex-make-sample-summary.sh
% Token and word counts for arab/qcs/tot.1/raw.wfr
%
\def\arabqcswholetotPBrawTks{80448}
\def\arabqcswholetotPBrawTksPct{100.0}
\def\arabqcswholetotPBrawWds{15874}
\def\arabqcswholetotPBrawWdsPct{19.7}
copied '/tmp/568775.file' -> 'exp/arab/qcs/tot.1/raw-whole-wds-summary.tex'
removed '/tmp/568775.file'
creating running text file dat/arab/qcs/tot.1/gud.wdf
sample:
bsm allh alrĩmn alrĩym alĩmd llh rb alŋalmyn alrĩmn alrĩym malk ywm
aldyn ayak nŋbd wayak nstŋyn ahdna alßraą almstqym ßraą alĢyn anŋmt
ŋlyhm Īyr almĪðwb ŋlyhm wlaalðalyn alm Ģlk alktab laryb fyh hdå llmtqyn
alĢyn yw!mnwn balĪyb wyqymwn alßlaĻ wmma rzqnahm ynfqwn walĢyn yw!mnwn
bma anzl alyk wmaanzl mn qblk wbalaĐrĻ hm ywqnwn awly!k ŋlå hdå mn rbhm
wawly!k hm almflĩwn an alĢyn kfrwa swa' ŋlyhm 'anĢrthm am lm tnĢrhm
layw!mnwn Đtm allh ŋlå qlwbhm wŋlå smŋhm wŋlå abßarhm ĪxawĻ wlhm ŋĢab
ŋįym wmn alnas mn yqwl amna ballh wbalywm alaĐr wmahm bmw!mnyn yĐadŋwn
allh walĢyn amnwa wmayĐdŋwn alaanfshm wmayxŋrwn fy qlwbhm mrð fzadhm
allh mrða wlhm ŋĢab alym bma kanwa ykĢbwn waĢa qyl lhm latfsdwa fy alarð
qalwa anma nĩn mßlĩwn ala anhm hm almfsdwn wlkn layxŋrwn waĢa qyl lhm
amnwa kma amn alnas qalwa anw!mn kma amn alsfha' alaanhm hm alsfha' wlkn
layŋlmwn waĢa lqwa alĢyn amnwa qalwa amna waĢa Đlwa alå xyaąynhm qalwa
ana mŋkm anma nĩn msthzy!wn allh ysthzy! bhm wymdhm fy ąĪyanhm yŋmhwn
awly!k alĢyn axtrwa alðlalĻ balhdå fma rbĩt tjarthm wmakanwa mhtdyn
mþlhm kmþl alĢy astwqd nara flma aða't maĩwlh Ģhb allh bnwrhm wtrkhm fy
įlmat laybßrwn ßm bkm ŋmy fhm layrjŋwn aw kßyb mn alsma' fyh įlmat wrŋd
wbrq yjŋlwn aßabŋhm fy aĢanhm mn alßwaŋq ĩĢr almwt wallh mĩyą balkafryn
ykad albrq yĐąf abßarhm klma aða' lhm mxwa fyh waĢa aįlm ŋlyhm qamwa wlw
xa' allh lĢhb bsmŋhm wabßarhm an allh ŋlå kl xy! qdyr yaayha alnas
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
wmn xr Īasq aĢa wqb wmn xr alnfaþat fy alŋqd wmn xr ĩasd aĢa ĩsd ql aŋwĢ
brb alnas mlk alnas alh alnas mn xr alwswas alĐnas alĢy ywsws fy ßdwr
alnas mn aljnĻ walnas
removed 'dat/arab/qcs/tot.1/gud.wfr'
creating the word frequency file dat/arab/qcs/tot.1/gud.wfr
the 10 most common words in dat/arab/qcs/tot.1/gud.tlw:
2751 0.03707 mn
2132 0.02873 allh
1604 0.02161 an
1075 0.01449 fy
808 0.01089 alĢyn
746 0.01005 ala
657 0.00885 ŋlå
413 0.00557 qal
409 0.00551 alå
349 0.00470 lhm
removed 'dat/arab/qcs/tot.1/gud-whole-wds-summary.tex'
removed 'exp/arab/qcs/tot.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/arab/qcs/tot.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:30:57 by tex-make-sample-summary.sh
% Token and word counts for arab/qcs/tot.1/gud.wfr
%
\def\arabqcswholetotPBgudTks{74212}
\def\arabqcswholetotPBgudTksPct{92.2}
\def\arabqcswholetotPBgudWds{15873}
\def\arabqcswholetotPBgudWdsPct{19.7}
copied '/tmp/568823.file' -> 'exp/arab/qcs/tot.1/gud-whole-wds-summary.tex'
removed '/tmp/568823.file'
creating running text file dat/arab/qcs/tot.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/arab/qcs/tot.1/bad.wfr'
creating the word frequency file dat/arab/qcs/tot.1/bad.wfr
the 10 most common words in dat/arab/qcs/tot.1/bad.tlw:
6236 1.00000 =
removed 'dat/arab/qcs/tot.1/bad-whole-wds-summary.tex'
removed 'exp/arab/qcs/tot.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/arab/qcs/tot.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:30:57 by tex-make-sample-summary.sh
% Token and word counts for arab/qcs/tot.1/bad.wfr
%
\def\arabqcswholetotPBbadTks{6236}
\def\arabqcswholetotPBbadTksPct{7.8}
\def\arabqcswholetotPBbadWds{1}
\def\arabqcswholetotPBbadWdsPct{0.0}
copied '/tmp/568867.file' -> 'exp/arab/qcs/tot.1/bad-whole-wds-summary.tex'
removed '/tmp/568867.file'
lines words bytes file
------- ------- --------- ------------
15874 47615 359606 dat/arab/qcs/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
15873 47612 359588 dat/arab/qcs/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
1 3 18 dat/arab/qcs/tot.1/bad.wfr
tot.1 raw = 80448 gud = 74212 bad = 6236
=== creating the derived word files dat/viet/ptt/*/{raw,gud,bad}.{tlw,wdf,wfr} (whole) ===
... creating word files dat/viet/ptt/gen.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
43448 dat/viet/ptt/gen.1/whole.tlw
removed 'dat/viet/ptt/gen.1/raw.tlw'
removed 'dat/viet/ptt/gen.1/gud.tlw'
removed 'dat/viet/ptt/gen.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/viet/ptt/gen.1/raw.wdf
sample:
*{sa'ch} ..*{se} ban dda^`u ddu+'c chu'a tro+`i du+.ng ne^n tro+`i
dda^'t =
va? dda^'t la` vo^ hi`nh va` tro^'ng kho^ng su+. mo+` to^'i o+? tre^n
ma(.t vu+.c tha^`n ddu+'c chu'a tro+`i va^.n ha`nh tre^n ma(.t nu+o+'c =
ddu+'c chu'a tro+`i pha'n ra(`ng pha?i co' su+. sa'ng thi` co' su+.
sa'ng =
ddu+'c chu'a tro+`i tha^'y su+. sa'ng la` to^'t la`nh be`n pha^n sa'ng
ra cu`ng to^'i =
ddu+'c chu'a tro+`i dda(.t te^n su+. sa'ng la` nga`y su+. to^'i la`
dde^m va^.y co' buo^?i chie^`u va` buo^?i mai a^'y la` nga`y thu+'
nhu+'t =
ddu+'c chu'a tro+`i la.i pha'n ra(`ng pha?i co' mo^.t khoa?ng kho^ng o+?
giu+~a nu+o+'c dda(.ng pha^n re~ nu+o+'c ca'ch vo+'i nu+o+'c =
nga`i la`m ne^n khoa?ng kho^ng pha^n re~ nu+o+'c o+? du+o+'i khoa?ng
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
tuo^?i ngu+o+`i ta xo^ng thuo^'c tho+m cho xa'c gio^ se'p va` lie^.m
trong mo^.t ca'i quan ta`i ta.i xu+' e^ di'p to^ =
removed 'dat/viet/ptt/gen.1/raw.wfr'
creating the word frequency file dat/viet/ptt/gen.1/raw.wfr
the 10 most common words in dat/viet/ptt/gen.1/raw.tlw:
1347 0.03100 =
767 0.01765 ngu+o+`i
732 0.01685 va`
679 0.01563 con
659 0.01517 cho
577 0.01328 ca'c
568 0.01307 ra
553 0.01273 ra(`ng
536 0.01234 cu?a
518 0.01192 to^i
removed 'dat/viet/ptt/gen.1/raw-whole-wds-summary.tex'
removed 'exp/viet/ptt/gen.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/viet/ptt/gen.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:30:58 by tex-make-sample-summary.sh
% Token and word counts for viet/ptt/gen.1/raw.wfr
%
\def\vietpttwholegenPBrawTks{43448}
\def\vietpttwholegenPBrawTksPct{100.0}
\def\vietpttwholegenPBrawWds{1796}
\def\vietpttwholegenPBrawWdsPct{4.1}
copied '/tmp/568962.file' -> 'exp/viet/ptt/gen.1/raw-whole-wds-summary.tex'
removed '/tmp/568962.file'
creating running text file dat/viet/ptt/gen.1/gud.wdf
sample:
ban dda^`u ddu+'c chu'a tro+`i du+.ng ne^n tro+`i dda^'t va? dda^'t la`
vo^ hi`nh va` tro^'ng kho^ng su+. mo+` to^'i o+? tre^n ma(.t vu+.c
tha^`n ddu+'c chu'a tro+`i va^.n ha`nh tre^n ma(.t nu+o+'c ddu+'c chu'a
tro+`i pha'n ra(`ng pha?i co' su+. sa'ng thi` co' su+. sa'ng ddu+'c
chu'a tro+`i tha^'y su+. sa'ng la` to^'t la`nh be`n pha^n sa'ng ra cu`ng
to^'i ddu+'c chu'a tro+`i dda(.t te^n su+. sa'ng la` nga`y su+. to^'i
la` dde^m va^.y co' buo^?i chie^`u va` buo^?i mai a^'y la` nga`y thu+'
nhu+'t ddu+'c chu'a tro+`i la.i pha'n ra(`ng pha?i co' mo^.t khoa?ng
kho^ng o+? giu+~a nu+o+'c dda(.ng pha^n re~ nu+o+'c ca'ch vo+'i nu+o+'c
nga`i la`m ne^n khoa?ng kho^ng pha^n re~ nu+o+'c o+? du+o+'i khoa?ng
kho^ng ca'ch vo+'i nu+o+'c o+? tre^n khoa?ng kho^ng thi` co' nhu+ va^.y
ddu+'c chu'a tro+`i dda(.t te^n khoa?ng kho^ng la` tro+`i va^.y co'
buo^?i chie^`u va` buo^?i mai a^'y la` nga`y thu+' nhi` ddu+'c chu'a
tro+`i la.i pha'n ra(`ng nhu+~ng nu+o+'c o+? du+o+'i tro+`i pha?i tu.
la.i mo^.t no+i va` pha?i co' cho^~ kho^ ca.n ba`y ra thi` co' nhu+
va^.y ddu+'c chu'a tro+`i dda(.t te^n cho^~ kho^ ca.n la` dda^'t co`n
no+i nu+o+'c tu. la.i la` bie^?n ddu+'c chu'a tro+`i tha^'y dde^`u ddo'
la` to^'t la`nh ddu+'c chu'a tro+`i la.i pha'n ra(`ng dda^'t pha?i sanh
ca^y co? co? ke^'t ho^.t gio^'ng ca^y tra'i ke^'t qua? tu`y theo loa.i
ma` co' ho^.t gio^'ng trong mi`nh tre^n dda^'t thi` co' nhu+ va^.y
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
ddu+o+.c mo^.t tra(m mu+o+`i tuo^?i ngu+o+`i ta xo^ng thuo^'c tho+m cho
xa'c gio^ se'p va` lie^.m trong mo^.t ca'i quan ta`i ta.i xu+' e^ di'p
to^
removed 'dat/viet/ptt/gen.1/gud.wfr'
creating the word frequency file dat/viet/ptt/gen.1/gud.wfr
the 10 most common words in dat/viet/ptt/gen.1/gud.tlw:
767 0.01822 ngu+o+`i
732 0.01739 va`
679 0.01613 con
659 0.01565 cho
577 0.01371 ca'c
568 0.01349 ra
553 0.01314 ra(`ng
536 0.01273 cu?a
518 0.01230 to^i
513 0.01219 la`
removed 'dat/viet/ptt/gen.1/gud-whole-wds-summary.tex'
removed 'exp/viet/ptt/gen.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/viet/ptt/gen.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:30:58 by tex-make-sample-summary.sh
% Token and word counts for viet/ptt/gen.1/gud.wfr
%
\def\vietpttwholegenPBgudTks{42099}
\def\vietpttwholegenPBgudTksPct{96.9}
\def\vietpttwholegenPBgudWds{1793}
\def\vietpttwholegenPBgudWdsPct{4.1}
copied '/tmp/569006.file' -> 'exp/viet/ptt/gen.1/gud-whole-wds-summary.tex'
removed '/tmp/569006.file'
creating running text file dat/viet/ptt/gen.1/bad.wdf
sample:
*{sa'ch} ..*{se} =
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/viet/ptt/gen.1/bad.wfr'
creating the word frequency file dat/viet/ptt/gen.1/bad.wfr
the 10 most common words in dat/viet/ptt/gen.1/bad.tlw:
1347 0.99852 =
1 0.00074 *{sa'ch}
1 0.00074 ..*{se}
removed 'dat/viet/ptt/gen.1/bad-whole-wds-summary.tex'
removed 'exp/viet/ptt/gen.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/viet/ptt/gen.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:30:58 by tex-make-sample-summary.sh
% Token and word counts for viet/ptt/gen.1/bad.wfr
%
\def\vietpttwholegenPBbadTks{1349}
\def\vietpttwholegenPBbadTksPct{3.1}
\def\vietpttwholegenPBbadWds{3}
\def\vietpttwholegenPBbadWdsPct{0.0}
copied '/tmp/569050.file' -> 'exp/viet/ptt/gen.1/bad-whole-wds-summary.tex'
removed '/tmp/569050.file'
... creating word files dat/viet/ptt/exo.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
34775 dat/viet/ptt/exo.1/whole.tlw
removed 'dat/viet/ptt/exo.1/raw.tlw'
removed 'dat/viet/ptt/exo.1/gud.tlw'
removed 'dat/viet/ptt/exo.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/viet/ptt/exo.1/raw.wdf
sample:
*{sa'ch} ..*{se} dda^y la` te^n ca'c con trai cu?a y so+ ra e^n mo^~i
ngu+o+`i dde^`u da^~n ngu+o+`i nha` mi`nh ddi vo+'i gia co^'p dde^'n
xu+' e^ di'p to^ ru be^n si me^ o^n le^ vi va` giu dda y sa ca sa bu
lo^n va` be^n gia min ddan ne'p ta li ga't va` a se =
he^'t tha?y nhu+~ng ngu+o+`i bo+?i gia co^'p sanh ra ddu+o+.c ba?y
mu+o+i ngu+o+`i gio^ se'p dda~ o+? ta.i xu+' e^ di'p to^ =
va? gio^ se'p va` anh em ngu+o+`i cu`ng mo.i ke? ddo^`ng ddo+`i ddo'
dde^`u che^'t he^'t =
con cha'u y so+ ra e^n the^m nhie^`u la. lu`ng na^?y no+? ra va` tro+?
ne^n ra^'t cu+o+`ng tha.nh ca? xu+' dde^`u dda^`y da^~y =
nhu+ng ba^'y gio+` ta.i nu+o+'c e^ di'p to^ co' mo^.t vua mo+'i le^n
ngo^i cha(?ng quen bie^'t gio^ se'p =
vua pha'n cu`ng da^n mi`nh ra(`ng na^`y da^n y so+ ra e^n ddo^ng va`
ma.nh ho+n chu'ng ta he` ta ha~y du`ng chu+o+'c kho^n ngoan ddo^'i cu`ng
ho. ke?o ho. the^m nhie^`u le^n mo^.t mai ne^'u co' co+n chinh chie^'n
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
cu?a ddu+'c gie^ ho^ va o+? tre^n dde^`n ta.m ban nga`y va` co' lu+?a
o+? tre^n ddo' ban dde^m hie^.n tru+o+'c ma(.t ca? da^n y so+ ra e^n =
removed 'dat/viet/ptt/exo.1/raw.wfr'
creating the word frequency file dat/viet/ptt/exo.1/raw.wfr
the 10 most common words in dat/viet/ptt/exo.1/raw.tlw:
1013 0.02913 =
618 0.01777 va`
561 0.01613 ngu+o+i
538 0.01547 ra
479 0.01377 cho
468 0.01346 ddu+'c
455 0.01308 ngu+o+`i
445 0.01280 ca'c
412 0.01185 gie^
407 0.01170 ho^
removed 'dat/viet/ptt/exo.1/raw-whole-wds-summary.tex'
removed 'exp/viet/ptt/exo.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/viet/ptt/exo.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:30:58 by tex-make-sample-summary.sh
% Token and word counts for viet/ptt/exo.1/raw.wfr
%
\def\vietpttwholeexoPBrawTks{34775}
\def\vietpttwholeexoPBrawTksPct{100.0}
\def\vietpttwholeexoPBrawWds{1652}
\def\vietpttwholeexoPBrawWdsPct{4.8}
copied '/tmp/569104.file' -> 'exp/viet/ptt/exo.1/raw-whole-wds-summary.tex'
removed '/tmp/569104.file'
creating running text file dat/viet/ptt/exo.1/gud.wdf
sample:
dda^y la` te^n ca'c con trai cu?a y so+ ra e^n mo^~i ngu+o+`i dde^`u
da^~n ngu+o+`i nha` mi`nh ddi vo+'i gia co^'p dde^'n xu+' e^ di'p to^ ru
be^n si me^ o^n le^ vi va` giu dda y sa ca sa bu lo^n va` be^n gia min
ddan ne'p ta li ga't va` a se he^'t tha?y nhu+~ng ngu+o+`i bo+?i gia
co^'p sanh ra ddu+o+.c ba?y mu+o+i ngu+o+`i gio^ se'p dda~ o+? ta.i xu+'
e^ di'p to^ va? gio^ se'p va` anh em ngu+o+`i cu`ng mo.i ke? ddo^`ng
ddo+`i ddo' dde^`u che^'t he^'t con cha'u y so+ ra e^n the^m nhie^`u la.
lu`ng na^?y no+? ra va` tro+? ne^n ra^'t cu+o+`ng tha.nh ca? xu+' dde^`u
dda^`y da^~y nhu+ng ba^'y gio+` ta.i nu+o+'c e^ di'p to^ co' mo^.t vua
mo+'i le^n ngo^i cha(?ng quen bie^'t gio^ se'p vua pha'n cu`ng da^n
mi`nh ra(`ng na^`y da^n y so+ ra e^n ddo^ng va` ma.nh ho+n chu'ng ta he`
ta ha~y du`ng chu+o+'c kho^n ngoan ddo^'i cu`ng ho. ke?o ho. the^m
nhie^`u le^n mo^.t mai ne^'u co' co+n chinh chie^'n xa?y dde^'n ho. se~
hie^.p cu`ng qua^n nghi.ch dda'nh la.i ta va` ra kho?i xu+' cha(ng va^.y
ngu+o+`i e^ di'p to^ be`n dda(.t ca'c ke? dda^`u xa^u dde^? ba('t da^n y
so+ ra e^n la`m xa^u kho' nho.c ho. xa^y tha`nh phi thom va` ram se
du`ng la`m kho ta`ng cho pha ra o^n nhu+ng ngu+o+`i e^ di'p to^ ca`ng
ba('t la`m kho' nho.c chu+`ng na`o da^n y so+ ra e^n ca`ng the^m nhie^`u
le^n va` tra`n ra chu+`ng na^'y ngu+o+`i e^ di'p to^ ca`ng ddem lo`ng
ghen ghe't da^n y so+ ra e^n ba('t la`m co^ng vie^.c nho.c nha(`n ga^y
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
e^n thi` a'ng ma^y cu?a ddu+'c gie^ ho^ va o+? tre^n dde^`n ta.m ban
nga`y va` co' lu+?a o+? tre^n ddo' ban dde^m hie^.n tru+o+'c ma(.t ca?
da^n y so+ ra e^n
removed 'dat/viet/ptt/exo.1/gud.wfr'
creating the word frequency file dat/viet/ptt/exo.1/gud.wfr
the 10 most common words in dat/viet/ptt/exo.1/gud.tlw:
618 0.01831 va`
561 0.01662 ngu+o+i
538 0.01594 ra
479 0.01419 cho
468 0.01386 ddu+'c
455 0.01348 ngu+o+`i
445 0.01318 ca'c
412 0.01220 gie^
407 0.01206 ho^
399 0.01182 cu?a
removed 'dat/viet/ptt/exo.1/gud-whole-wds-summary.tex'
removed 'exp/viet/ptt/exo.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/viet/ptt/exo.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:30:58 by tex-make-sample-summary.sh
% Token and word counts for viet/ptt/exo.1/gud.wfr
%
\def\vietpttwholeexoPBgudTks{33760}
\def\vietpttwholeexoPBgudTksPct{97.1}
\def\vietpttwholeexoPBgudWds{1649}
\def\vietpttwholeexoPBgudWdsPct{4.7}
copied '/tmp/569148.file' -> 'exp/viet/ptt/exo.1/gud-whole-wds-summary.tex'
removed '/tmp/569148.file'
creating running text file dat/viet/ptt/exo.1/bad.wdf
sample:
*{sa'ch} ..*{se} =
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/viet/ptt/exo.1/bad.wfr'
creating the word frequency file dat/viet/ptt/exo.1/bad.wfr
the 10 most common words in dat/viet/ptt/exo.1/bad.tlw:
1013 0.99803 =
1 0.00099 *{sa'ch}
1 0.00099 ..*{se}
removed 'dat/viet/ptt/exo.1/bad-whole-wds-summary.tex'
removed 'exp/viet/ptt/exo.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/viet/ptt/exo.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:30:58 by tex-make-sample-summary.sh
% Token and word counts for viet/ptt/exo.1/bad.wfr
%
\def\vietpttwholeexoPBbadTks{1015}
\def\vietpttwholeexoPBbadTksPct{2.9}
\def\vietpttwholeexoPBbadWds{3}
\def\vietpttwholeexoPBbadWdsPct{0.0}
copied '/tmp/569192.file' -> 'exp/viet/ptt/exo.1/bad-whole-wds-summary.tex'
removed '/tmp/569192.file'
... creating word files dat/viet/ptt/num.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
38067 dat/viet/ptt/num.1/whole.tlw
removed 'dat/viet/ptt/num.1/raw.tlw'
removed 'dat/viet/ptt/num.1/gud.tlw'
removed 'dat/viet/ptt/num.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/viet/ptt/num.1/raw.wdf
sample:
*{sa'ch} ..*{se} nga`y mo^`ng mo^.t tha'ng hai na(m thu+' hai sau khi
da^n y so+ ra e^n ra kho?i xu+' e^ di'p to^ ddu+'c gie^ ho^ va pha'n
cu`ng mo^i se o+? trong ho^.i ma.c ta.i ddo^`ng va('ng si na i ma`
ra(`ng ha~y du+.ng so^? ca? ho^.i da^n y so+ ra e^n theo ho. ha`ng va`
to^ng to^.c cu?a ho. cu+' dde^'m tu+`ng te^n cu?a he^'t tha?y nam ddinh
tu+` hai mu+o+i tuo^?i sa^'p le^n tu+'c la` mo.i ngu+o+`i trong y so+ ra
e^n ddi ra tra^.n ddu+o+.c ngu+o+i va` a ro^n se~ ke^ so^? chu'ng no'
tu`y theo ddo^.i ngu~ cu?a ho. =
trong mo^~i chi pha'i pha?i co' mo^.t ngu+o+`i giu'p ddo+~ ca'c ngu+o+i
tu+'c la` ngu+o+`i la`m to^.c tru+o+?ng cu?a chi pha'i mi`nh =
dda^y la` te^n nhu+~ng ngu+o+`i se~ giu'p ddo+~ ca'c ngu+o+i ve^` chi
pha'i ru be^n e^ li't su con trai cu?a se^ dde^u ve^` chi pha'i si me^
o^n se^ u me^ e^n con trai cu?a xu ri ha ddai ve^` chi pha'i giu dda na
ha so^n con trai cu?a a mi na dda'p ve^` chi pha'i y sa ca na tha na e^n
con trai cu?a xu a ve^` chi pha'i sa bu lo^n e^ li a'p con trai cu?a he^
lo^n ve^` con cha'u gio^ se'p nghi~a la` ve^` chi pha'i e'p ra im e^ li
sa ma con trai cu?a a mi hu't ve^` chi pha'i ma na se ga ma li e^n con
trai cu?a phe^ dda't su ve^` chi pha'i be^n gia min a bi ddan con trai
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
ca^.y mo^i se truye^`n cho da^n y so+ ra e^n ta.i trong ddo^`ng ba(`ng
mo^ a'p ga^`n so^ng gio^ ddanh ddo^'i ngang gie^ ri co^ =
removed 'dat/viet/ptt/num.1/raw.wfr'
creating the word frequency file dat/viet/ptt/num.1/raw.wfr
the 10 most common words in dat/viet/ptt/num.1/raw.tlw:
968 0.02543 =
746 0.01960 cu?a
746 0.01960 ngu+o+`i
730 0.01918 va`
657 0.01726 con
549 0.01442 ra
518 0.01361 ca'c
465 0.01222 mo^.t
436 0.01145 cho
435 0.01143 la`
removed 'dat/viet/ptt/num.1/raw-whole-wds-summary.tex'
removed 'exp/viet/ptt/num.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/viet/ptt/num.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:30:58 by tex-make-sample-summary.sh
% Token and word counts for viet/ptt/num.1/raw.wfr
%
\def\vietpttwholenumPBrawTks{38067}
\def\vietpttwholenumPBrawTksPct{100.0}
\def\vietpttwholenumPBrawWds{1488}
\def\vietpttwholenumPBrawWdsPct{3.9}
copied '/tmp/569246.file' -> 'exp/viet/ptt/num.1/raw-whole-wds-summary.tex'
removed '/tmp/569246.file'
creating running text file dat/viet/ptt/num.1/gud.wdf
sample:
nga`y mo^`ng mo^.t tha'ng hai na(m thu+' hai sau khi da^n y so+ ra e^n
ra kho?i xu+' e^ di'p to^ ddu+'c gie^ ho^ va pha'n cu`ng mo^i se o+?
trong ho^.i ma.c ta.i ddo^`ng va('ng si na i ma` ra(`ng ha~y du+.ng so^?
ca? ho^.i da^n y so+ ra e^n theo ho. ha`ng va` to^ng to^.c cu?a ho. cu+'
dde^'m tu+`ng te^n cu?a he^'t tha?y nam ddinh tu+` hai mu+o+i tuo^?i
sa^'p le^n tu+'c la` mo.i ngu+o+`i trong y so+ ra e^n ddi ra tra^.n
ddu+o+.c ngu+o+i va` a ro^n se~ ke^ so^? chu'ng no' tu`y theo ddo^.i
ngu~ cu?a ho. trong mo^~i chi pha'i pha?i co' mo^.t ngu+o+`i giu'p ddo+~
ca'c ngu+o+i tu+'c la` ngu+o+`i la`m to^.c tru+o+?ng cu?a chi pha'i
mi`nh dda^y la` te^n nhu+~ng ngu+o+`i se~ giu'p ddo+~ ca'c ngu+o+i ve^`
chi pha'i ru be^n e^ li't su con trai cu?a se^ dde^u ve^` chi pha'i si
me^ o^n se^ u me^ e^n con trai cu?a xu ri ha ddai ve^` chi pha'i giu dda
na ha so^n con trai cu?a a mi na dda'p ve^` chi pha'i y sa ca na tha na
e^n con trai cu?a xu a ve^` chi pha'i sa bu lo^n e^ li a'p con trai cu?a
he^ lo^n ve^` con cha'u gio^ se'p nghi~a la` ve^` chi pha'i e'p ra im e^
li sa ma con trai cu?a a mi hu't ve^` chi pha'i ma na se ga ma li e^n
con trai cu?a phe^ dda't su ve^` chi pha'i be^n gia min a bi ddan con
trai cu?a ghi ddeo ni ve^` chi pha'i ddan a hi e^ se con trai cu?a a mi
sa ddai ve^` chi pha'i a se pha ghi e^n con trai cu?a o'c ran ve^` chi
pha'i ga't e^ li a sa'p con trai cu?a dde^ u e^n ve^` chi pha'i ne'p ta
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
ddo' la` ca'c ma.ng li.nh va` lua^.t le^. ma` ddu+'c gie^ ho^ va dda~
ca^.y mo^i se truye^`n cho da^n y so+ ra e^n ta.i trong ddo^`ng ba(`ng
mo^ a'p ga^`n so^ng gio^ ddanh ddo^'i ngang gie^ ri co^
removed 'dat/viet/ptt/num.1/gud.wfr'
creating the word frequency file dat/viet/ptt/num.1/gud.wfr
the 10 most common words in dat/viet/ptt/num.1/gud.tlw:
746 0.02011 cu?a
746 0.02011 ngu+o+`i
730 0.01968 va`
657 0.01771 con
549 0.01480 ra
518 0.01396 ca'c
465 0.01253 mo^.t
436 0.01175 cho
435 0.01173 la`
434 0.01170 ngu+o+i
removed 'dat/viet/ptt/num.1/gud-whole-wds-summary.tex'
removed 'exp/viet/ptt/num.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/viet/ptt/num.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:30:58 by tex-make-sample-summary.sh
% Token and word counts for viet/ptt/num.1/gud.wfr
%
\def\vietpttwholenumPBgudTks{37097}
\def\vietpttwholenumPBgudTksPct{97.5}
\def\vietpttwholenumPBgudWds{1485}
\def\vietpttwholenumPBgudWdsPct{3.9}
copied '/tmp/569290.file' -> 'exp/viet/ptt/num.1/gud-whole-wds-summary.tex'
removed '/tmp/569290.file'
creating running text file dat/viet/ptt/num.1/bad.wdf
sample:
*{sa'ch} ..*{se} =
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/viet/ptt/num.1/bad.wfr'
creating the word frequency file dat/viet/ptt/num.1/bad.wfr
the 10 most common words in dat/viet/ptt/num.1/bad.tlw:
968 0.99794 =
1 0.00103 *{sa'ch}
1 0.00103 ..*{se}
removed 'dat/viet/ptt/num.1/bad-whole-wds-summary.tex'
removed 'exp/viet/ptt/num.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/viet/ptt/num.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:30:58 by tex-make-sample-summary.sh
% Token and word counts for viet/ptt/num.1/bad.wfr
%
\def\vietpttwholenumPBbadTks{970}
\def\vietpttwholenumPBbadTksPct{2.5}
\def\vietpttwholenumPBbadWds{3}
\def\vietpttwholenumPBbadWdsPct{0.0}
copied '/tmp/569334.file' -> 'exp/viet/ptt/num.1/bad-whole-wds-summary.tex'
removed '/tmp/569334.file'
... creating word files dat/viet/ptt/lev.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
25831 dat/viet/ptt/lev.1/whole.tlw
removed 'dat/viet/ptt/lev.1/raw.tlw'
removed 'dat/viet/ptt/lev.1/gud.tlw'
removed 'dat/viet/ptt/lev.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/viet/ptt/lev.1/raw.wdf
sample:
*{sa'ch} ..*{se} ddu+'c gie^ ho^ va tu+` trong ho^.i ma.c go.i mo^i se
ma` pha'n ra(`ng ha~y no'i cu`ng da^n y so+ ra e^n ra(`ng khi ngu+o+`i
na`o trong vo`ng ca'c ngu+o+i da^ng cu?a le^~ cho ddu+'c gie^ ho^ va
thi` pha?i da^ng su'c va^.t hoa(.c bo` hoa(.c chie^n =
ne^'u le^~ va^.t cu?a ngu+o+`i la` cu?a le^~ thie^u ba(`ng bo` thi`
pha?i du`ng con ddu+.c kho^ng ti` vi't da^ng le^n ta.i cu+?a ho^.i ma.c
tru+o+'c ma(.t ddu+'c gie^ ho^ va dde^? ddu+o+.c nga`i dde.p lo`ng
nha^.m la^'y =
ngu+o+`i se~ nha^.n tay mi`nh tre^n dda^`u con sinh no' se~ ddu+o+.c
nha^.m the^' cho ha^`u chuo^.c to^.i cho ngu+o+`i =
ddoa.n ngu+o+`i se~ gie^'t bo` to+ tru+o+'c ma(.t ddu+'c gie^ ho^ va
ro^`i ca'c con trai a ro^n tu+'c nhu+~ng tha^`y te^' le^~ se~ da^ng
huye^'t le^n va` ru+o+'i chunh quanh tre^n ba`n tho+` ta.i no+i cu+?a
ho^.i ma.c =
ke^' ddo' lo^.t da con sinh va` sa? thi.t ra tu+`ng mie^'ng =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
ddo' la` ca'c ma.ng li.nh ma` ddu+'c gie^ ho^ va truye^`n cho mo^i se
ve^` da^n y so+ ra e^n ta.i tre^n nu'i si na i =
removed 'dat/viet/ptt/lev.1/raw.wfr'
creating the word frequency file dat/viet/ptt/lev.1/raw.wfr
the 10 most common words in dat/viet/ptt/lev.1/raw.tlw:
666 0.02578 =
541 0.02094 le^~
523 0.02025 ngu+o+`i
494 0.01912 cu?a
471 0.01823 ca'c
409 0.01583 cho
403 0.01560 se~
397 0.01537 va`
392 0.01518 ngu+o+i
381 0.01475 la`
removed 'dat/viet/ptt/lev.1/raw-whole-wds-summary.tex'
removed 'exp/viet/ptt/lev.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/viet/ptt/lev.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:30:58 by tex-make-sample-summary.sh
% Token and word counts for viet/ptt/lev.1/raw.wfr
%
\def\vietpttwholelevPBrawTks{25831}
\def\vietpttwholelevPBrawTksPct{100.0}
\def\vietpttwholelevPBrawWds{1210}
\def\vietpttwholelevPBrawWdsPct{4.7}
copied '/tmp/569388.file' -> 'exp/viet/ptt/lev.1/raw-whole-wds-summary.tex'
removed '/tmp/569388.file'
creating running text file dat/viet/ptt/lev.1/gud.wdf
sample:
ddu+'c gie^ ho^ va tu+` trong ho^.i ma.c go.i mo^i se ma` pha'n ra(`ng
ha~y no'i cu`ng da^n y so+ ra e^n ra(`ng khi ngu+o+`i na`o trong vo`ng
ca'c ngu+o+i da^ng cu?a le^~ cho ddu+'c gie^ ho^ va thi` pha?i da^ng
su'c va^.t hoa(.c bo` hoa(.c chie^n ne^'u le^~ va^.t cu?a ngu+o+`i la`
cu?a le^~ thie^u ba(`ng bo` thi` pha?i du`ng con ddu+.c kho^ng ti` vi't
da^ng le^n ta.i cu+?a ho^.i ma.c tru+o+'c ma(.t ddu+'c gie^ ho^ va dde^?
ddu+o+.c nga`i dde.p lo`ng nha^.m la^'y ngu+o+`i se~ nha^.n tay mi`nh
tre^n dda^`u con sinh no' se~ ddu+o+.c nha^.m the^' cho ha^`u chuo^.c
to^.i cho ngu+o+`i ddoa.n ngu+o+`i se~ gie^'t bo` to+ tru+o+'c ma(.t
ddu+'c gie^ ho^ va ro^`i ca'c con trai a ro^n tu+'c nhu+~ng tha^`y te^'
le^~ se~ da^ng huye^'t le^n va` ru+o+'i chunh quanh tre^n ba`n tho+`
ta.i no+i cu+?a ho^.i ma.c ke^' ddo' lo^.t da con sinh va` sa? thi.t ra
tu+`ng mie^'ng ca'c con trai tha^`y te^' le^~ a ro^n se~ cha^m lu+?a
tre^n ba`n tho+` cha^'t cu?i chu.m lu+?a ro^`i ca'c con trai a ro^n
tu+'c nhu+~ng tha^`y te^' le^~ sa('p ca'c mie^'ng thi.t dda^`u va` mo+~
le^n tre^n cu?i dda~ chu.m lu+?a no+i ba`n tho+` ngu+o+`i se~ la^'y
nu+o+'c ru+?a bo^. lo`ng va` gio` ro^`i tha^`y te^' le^~ ddem he^'t mo.i
pha^`n xo^ng no+i ba`n tho+` a^'y la` cu?a le^~ thie^u tu+'c mo^.t cu?a
le^~ du`ng lu+?a da^ng le^n co' mu`i tho+m cho ddu+'c gie^ ho^ va ne^'u
le^~ va^.t ngu+o+`i la` cu?a le^~ thie^u ba(`ng su'c va^.t nho? hoa(.c
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
ca? hai dde^`u bie^.t ra tha'nh kho^ng phe'p chuo^.c no' la.i ddo' la`
ca'c ma.ng li.nh ma` ddu+'c gie^ ho^ va truye^`n cho mo^i se ve^` da^n y
so+ ra e^n ta.i tre^n nu'i si na i
removed 'dat/viet/ptt/lev.1/gud.wfr'
creating the word frequency file dat/viet/ptt/lev.1/gud.wfr
the 10 most common words in dat/viet/ptt/lev.1/gud.tlw:
541 0.02150 le^~
523 0.02078 ngu+o+`i
494 0.01963 cu?a
471 0.01872 ca'c
409 0.01625 cho
403 0.01602 se~
397 0.01578 va`
392 0.01558 ngu+o+i
381 0.01514 la`
365 0.01451 mo^.t
removed 'dat/viet/ptt/lev.1/gud-whole-wds-summary.tex'
removed 'exp/viet/ptt/lev.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/viet/ptt/lev.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:30:59 by tex-make-sample-summary.sh
% Token and word counts for viet/ptt/lev.1/gud.wfr
%
\def\vietpttwholelevPBgudTks{25163}
\def\vietpttwholelevPBgudTksPct{97.4}
\def\vietpttwholelevPBgudWds{1207}
\def\vietpttwholelevPBgudWdsPct{4.7}
copied '/tmp/569432.file' -> 'exp/viet/ptt/lev.1/gud-whole-wds-summary.tex'
removed '/tmp/569432.file'
creating running text file dat/viet/ptt/lev.1/bad.wdf
sample:
*{sa'ch} ..*{se} =
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/viet/ptt/lev.1/bad.wfr'
creating the word frequency file dat/viet/ptt/lev.1/bad.wfr
the 10 most common words in dat/viet/ptt/lev.1/bad.tlw:
666 0.99701 =
1 0.00150 *{sa'ch}
1 0.00150 ..*{se}
removed 'dat/viet/ptt/lev.1/bad-whole-wds-summary.tex'
removed 'exp/viet/ptt/lev.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/viet/ptt/lev.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:30:59 by tex-make-sample-summary.sh
% Token and word counts for viet/ptt/lev.1/bad.wfr
%
\def\vietpttwholelevPBbadTks{668}
\def\vietpttwholelevPBbadTksPct{2.6}
\def\vietpttwholelevPBbadWds{3}
\def\vietpttwholelevPBbadWdsPct{0.0}
copied '/tmp/569476.file' -> 'exp/viet/ptt/lev.1/bad-whole-wds-summary.tex'
removed '/tmp/569476.file'
... creating word files dat/viet/ptt/deu.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
32092 dat/viet/ptt/deu.1/whole.tlw
removed 'dat/viet/ptt/deu.1/raw.tlw'
removed 'dat/viet/ptt/deu.1/gud.tlw'
removed 'dat/viet/ptt/deu.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/viet/ptt/deu.1/raw.wdf
sample:
*{sa'ch} ..*{se} na^`y la` lo+`i mo^i se no'i cho ca? y so+ ra e^n be^n
kia so^ng gio^ ddanh ta.i ddo^`ng va('ng trong ddo^`ng ba(`ng ddo^'i
ngang su pho+ giu+~a khoa?ng pha ran va` to^ phe^n la ban ha't se^ ro^'t
va` ddi xa ha'p =
tu+` ho^ re^'p to+'i ca dde ba ne^ a bo+?i ddu+o+`ng nu'i se^ i ro+ ddi
mu+o+`i mo^.t nga`y ddu+o+`ng =
nha(`m na(m bo^'n mu+o+i nga`y mo^`ng mo^.t tha'ng mu+o+`i mo^.t mo^i se
no'i cu`ng da^n y so+ ra e^n mo.i ddie^`u ma` ddu+'c gie^ ho^ va dda~
bie^?u ngu+o+`i pha?i no'i cu`ng ho. =
a^'y la` sau khi ngu+o+`i dda~ dda'nh gie^'t si ho^n vua da^n a mo^ ri't
o+? ta.i he^'t bo^n va` o'c vua ba san o+? ta.i a'ch ta ro^'t va` e^'t
re^ i =
ta.i be^n kia so^ng gio^ ddanh trong xu+' mo^ a'p mo^i se kho+?i gia?ng
gia?i lua^.t pha'p na^`y ma` ra(`ng gie^ ho^ va ddu+'c chu'a tro+`i
chu'ng ta co' pha'n cu`ng chu'ng ta ta.i ho^ re^'p ma` ra(`ng ca'c
ngu+o+i kie^`u ngu. trong nu'i na^`y dda~ la^u qua' ha~y vo`ng la.i va`
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
ca^.y tay quye^`n na(ng mi`nh la`m ta.i tru+o+'c ma(.t ca? y so+ ra e^n
=
removed 'dat/viet/ptt/deu.1/raw.wfr'
creating the word frequency file dat/viet/ptt/deu.1/raw.wfr
the 10 most common words in dat/viet/ptt/deu.1/raw.tlw:
1490 0.04643 ngu+o+i
729 0.02272 =
660 0.02057 va`
629 0.01960 ca'c
560 0.01745 cho
559 0.01742 ddu+'c
543 0.01692 ho^
539 0.01680 gie^
531 0.01655 va
447 0.01393 cu?a
removed 'dat/viet/ptt/deu.1/raw-whole-wds-summary.tex'
removed 'exp/viet/ptt/deu.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/viet/ptt/deu.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:30:59 by tex-make-sample-summary.sh
% Token and word counts for viet/ptt/deu.1/raw.wfr
%
\def\vietpttwholedeuPBrawTks{32092}
\def\vietpttwholedeuPBrawTksPct{100.0}
\def\vietpttwholedeuPBrawWds{1617}
\def\vietpttwholedeuPBrawWdsPct{5.0}
copied '/tmp/569530.file' -> 'exp/viet/ptt/deu.1/raw-whole-wds-summary.tex'
removed '/tmp/569530.file'
creating running text file dat/viet/ptt/deu.1/gud.wdf
sample:
na^`y la` lo+`i mo^i se no'i cho ca? y so+ ra e^n be^n kia so^ng gio^
ddanh ta.i ddo^`ng va('ng trong ddo^`ng ba(`ng ddo^'i ngang su pho+
giu+~a khoa?ng pha ran va` to^ phe^n la ban ha't se^ ro^'t va` ddi xa
ha'p tu+` ho^ re^'p to+'i ca dde ba ne^ a bo+?i ddu+o+`ng nu'i se^ i ro+
ddi mu+o+`i mo^.t nga`y ddu+o+`ng nha(`m na(m bo^'n mu+o+i nga`y mo^`ng
mo^.t tha'ng mu+o+`i mo^.t mo^i se no'i cu`ng da^n y so+ ra e^n mo.i
ddie^`u ma` ddu+'c gie^ ho^ va dda~ bie^?u ngu+o+`i pha?i no'i cu`ng ho.
a^'y la` sau khi ngu+o+`i dda~ dda'nh gie^'t si ho^n vua da^n a mo^ ri't
o+? ta.i he^'t bo^n va` o'c vua ba san o+? ta.i a'ch ta ro^'t va` e^'t
re^ i ta.i be^n kia so^ng gio^ ddanh trong xu+' mo^ a'p mo^i se kho+?i
gia?ng gia?i lua^.t pha'p na^`y ma` ra(`ng gie^ ho^ va ddu+'c chu'a
tro+`i chu'ng ta co' pha'n cu`ng chu'ng ta ta.i ho^ re^'p ma` ra(`ng
ca'c ngu+o+i kie^`u ngu. trong nu'i na^`y dda~ la^u qua' ha~y vo`ng la.i
va` ddi dde^'n nu'i da^n a mo^ ri't cu`ng dde^'n ca'c mie^`n o+? ga^`n
be^n tu+'c la` dde^'n no+i ddo^`ng ba(`ng le^n nu'i va`o xu+' tha^'p
dde^'n mie^`n nam le^n me' bie^?n va`o xu+' da^n ca na an va` li ban cho
dde^'n so^ng lo+'n la` so^ng o+ pho+ ra't ki`a ta pho' xu+' na^`y cho
ca'c ngu+o+i ha~y va`o va` chie^'m la^'y xu+' ma` ddu+'c gie^ ho^ va
dda~ the^` ban cho to^? phu. ca'c ngu+o+i la` a'p ra ham y sa'c gia
co^'p cu`ng cho con cha'u cu?a ho. trong lu'c ddo' ta co' no'i cu`ng
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
qua^`n tha^`n va` ca? xu+' cu?a ngu+o+`i hoa(.c he^'t tha?y co^ng vie^.c
lo+'n lao va` dda'ng so+. ma` mo^i se ca^.y tay quye^`n na(ng mi`nh la`m
ta.i tru+o+'c ma(.t ca? y so+ ra e^n
removed 'dat/viet/ptt/deu.1/gud.wfr'
creating the word frequency file dat/viet/ptt/deu.1/gud.wfr
the 10 most common words in dat/viet/ptt/deu.1/gud.tlw:
1490 0.04751 ngu+o+i
660 0.02105 va`
629 0.02006 ca'c
560 0.01786 cho
559 0.01782 ddu+'c
543 0.01731 ho^
539 0.01719 gie^
531 0.01693 va
447 0.01425 cu?a
446 0.01422 ngu+o+`i
removed 'dat/viet/ptt/deu.1/gud-whole-wds-summary.tex'
removed 'exp/viet/ptt/deu.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/viet/ptt/deu.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:30:59 by tex-make-sample-summary.sh
% Token and word counts for viet/ptt/deu.1/gud.wfr
%
\def\vietpttwholedeuPBgudTks{31361}
\def\vietpttwholedeuPBgudTksPct{97.7}
\def\vietpttwholedeuPBgudWds{1614}
\def\vietpttwholedeuPBgudWdsPct{5.0}
copied '/tmp/569574.file' -> 'exp/viet/ptt/deu.1/gud-whole-wds-summary.tex'
removed '/tmp/569574.file'
creating running text file dat/viet/ptt/deu.1/bad.wdf
sample:
*{sa'ch} ..*{se} =
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/viet/ptt/deu.1/bad.wfr'
creating the word frequency file dat/viet/ptt/deu.1/bad.wfr
the 10 most common words in dat/viet/ptt/deu.1/bad.tlw:
729 0.99726 =
1 0.00137 *{sa'ch}
1 0.00137 ..*{se}
removed 'dat/viet/ptt/deu.1/bad-whole-wds-summary.tex'
removed 'exp/viet/ptt/deu.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/viet/ptt/deu.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:30:59 by tex-make-sample-summary.sh
% Token and word counts for viet/ptt/deu.1/bad.wfr
%
\def\vietpttwholedeuPBbadTks{731}
\def\vietpttwholedeuPBbadTksPct{2.3}
\def\vietpttwholedeuPBbadWds{3}
\def\vietpttwholedeuPBbadWdsPct{0.0}
copied '/tmp/569618.file' -> 'exp/viet/ptt/deu.1/bad-whole-wds-summary.tex'
removed '/tmp/569618.file'
... creating word files dat/viet/ptt/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
174213 dat/viet/ptt/tot.1/whole.tlw
removed 'dat/viet/ptt/tot.1/raw.tlw'
removed 'dat/viet/ptt/tot.1/gud.tlw'
removed 'dat/viet/ptt/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/viet/ptt/tot.1/raw.wdf
sample:
*{sa'ch} ..*{se} ban dda^`u ddu+'c chu'a tro+`i du+.ng ne^n tro+`i
dda^'t =
va? dda^'t la` vo^ hi`nh va` tro^'ng kho^ng su+. mo+` to^'i o+? tre^n
ma(.t vu+.c tha^`n ddu+'c chu'a tro+`i va^.n ha`nh tre^n ma(.t nu+o+'c =
ddu+'c chu'a tro+`i pha'n ra(`ng pha?i co' su+. sa'ng thi` co' su+.
sa'ng =
ddu+'c chu'a tro+`i tha^'y su+. sa'ng la` to^'t la`nh be`n pha^n sa'ng
ra cu`ng to^'i =
ddu+'c chu'a tro+`i dda(.t te^n su+. sa'ng la` nga`y su+. to^'i la`
dde^m va^.y co' buo^?i chie^`u va` buo^?i mai a^'y la` nga`y thu+'
nhu+'t =
ddu+'c chu'a tro+`i la.i pha'n ra(`ng pha?i co' mo^.t khoa?ng kho^ng o+?
giu+~a nu+o+'c dda(.ng pha^n re~ nu+o+'c ca'ch vo+'i nu+o+'c =
nga`i la`m ne^n khoa?ng kho^ng pha^n re~ nu+o+'c o+? du+o+'i khoa?ng
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
ca^.y tay quye^`n na(ng mi`nh la`m ta.i tru+o+'c ma(.t ca? y so+ ra e^n
=
removed 'dat/viet/ptt/tot.1/raw.wfr'
creating the word frequency file dat/viet/ptt/tot.1/raw.wfr
the 10 most common words in dat/viet/ptt/tot.1/raw.tlw:
4723 0.02711 =
3273 0.01879 ngu+o+i
3137 0.01801 va`
2937 0.01686 ngu+o+`i
2640 0.01515 ca'c
2622 0.01505 cu?a
2543 0.01460 cho
2150 0.01234 con
2126 0.01220 ddu+'c
2088 0.01199 ra
removed 'dat/viet/ptt/tot.1/raw-whole-wds-summary.tex'
removed 'exp/viet/ptt/tot.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/viet/ptt/tot.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:30:59 by tex-make-sample-summary.sh
% Token and word counts for viet/ptt/tot.1/raw.wfr
%
\def\vietpttwholetotPBrawTks{174213}
\def\vietpttwholetotPBrawTksPct{100.0}
\def\vietpttwholetotPBrawWds{2687}
\def\vietpttwholetotPBrawWdsPct{1.5}
copied '/tmp/569672.file' -> 'exp/viet/ptt/tot.1/raw-whole-wds-summary.tex'
removed '/tmp/569672.file'
creating running text file dat/viet/ptt/tot.1/gud.wdf
sample:
ban dda^`u ddu+'c chu'a tro+`i du+.ng ne^n tro+`i dda^'t va? dda^'t la`
vo^ hi`nh va` tro^'ng kho^ng su+. mo+` to^'i o+? tre^n ma(.t vu+.c
tha^`n ddu+'c chu'a tro+`i va^.n ha`nh tre^n ma(.t nu+o+'c ddu+'c chu'a
tro+`i pha'n ra(`ng pha?i co' su+. sa'ng thi` co' su+. sa'ng ddu+'c
chu'a tro+`i tha^'y su+. sa'ng la` to^'t la`nh be`n pha^n sa'ng ra cu`ng
to^'i ddu+'c chu'a tro+`i dda(.t te^n su+. sa'ng la` nga`y su+. to^'i
la` dde^m va^.y co' buo^?i chie^`u va` buo^?i mai a^'y la` nga`y thu+'
nhu+'t ddu+'c chu'a tro+`i la.i pha'n ra(`ng pha?i co' mo^.t khoa?ng
kho^ng o+? giu+~a nu+o+'c dda(.ng pha^n re~ nu+o+'c ca'ch vo+'i nu+o+'c
nga`i la`m ne^n khoa?ng kho^ng pha^n re~ nu+o+'c o+? du+o+'i khoa?ng
kho^ng ca'ch vo+'i nu+o+'c o+? tre^n khoa?ng kho^ng thi` co' nhu+ va^.y
ddu+'c chu'a tro+`i dda(.t te^n khoa?ng kho^ng la` tro+`i va^.y co'
buo^?i chie^`u va` buo^?i mai a^'y la` nga`y thu+' nhi` ddu+'c chu'a
tro+`i la.i pha'n ra(`ng nhu+~ng nu+o+'c o+? du+o+'i tro+`i pha?i tu.
la.i mo^.t no+i va` pha?i co' cho^~ kho^ ca.n ba`y ra thi` co' nhu+
va^.y ddu+'c chu'a tro+`i dda(.t te^n cho^~ kho^ ca.n la` dda^'t co`n
no+i nu+o+'c tu. la.i la` bie^?n ddu+'c chu'a tro+`i tha^'y dde^`u ddo'
la` to^'t la`nh ddu+'c chu'a tro+`i la.i pha'n ra(`ng dda^'t pha?i sanh
ca^y co? co? ke^'t ho^.t gio^'ng ca^y tra'i ke^'t qua? tu`y theo loa.i
ma` co' ho^.t gio^'ng trong mi`nh tre^n dda^'t thi` co' nhu+ va^.y
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
qua^`n tha^`n va` ca? xu+' cu?a ngu+o+`i hoa(.c he^'t tha?y co^ng vie^.c
lo+'n lao va` dda'ng so+. ma` mo^i se ca^.y tay quye^`n na(ng mi`nh la`m
ta.i tru+o+'c ma(.t ca? y so+ ra e^n
removed 'dat/viet/ptt/tot.1/gud.wfr'
creating the word frequency file dat/viet/ptt/tot.1/gud.wfr
the 10 most common words in dat/viet/ptt/tot.1/gud.tlw:
3273 0.01931 ngu+o+i
3137 0.01851 va`
2937 0.01733 ngu+o+`i
2640 0.01558 ca'c
2622 0.01547 cu?a
2543 0.01500 cho
2150 0.01269 con
2126 0.01254 ddu+'c
2088 0.01232 ra
1886 0.01113 se~
removed 'dat/viet/ptt/tot.1/gud-whole-wds-summary.tex'
removed 'exp/viet/ptt/tot.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/viet/ptt/tot.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:31:00 by tex-make-sample-summary.sh
% Token and word counts for viet/ptt/tot.1/gud.wfr
%
\def\vietpttwholetotPBgudTks{169480}
\def\vietpttwholetotPBgudTksPct{97.3}
\def\vietpttwholetotPBgudWds{2684}
\def\vietpttwholetotPBgudWdsPct{1.5}
copied '/tmp/569717.file' -> 'exp/viet/ptt/tot.1/gud-whole-wds-summary.tex'
removed '/tmp/569717.file'
creating running text file dat/viet/ptt/tot.1/bad.wdf
sample:
*{sa'ch} ..*{se} =
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/viet/ptt/tot.1/bad.wfr'
creating the word frequency file dat/viet/ptt/tot.1/bad.wfr
the 10 most common words in dat/viet/ptt/tot.1/bad.tlw:
4723 0.99789 =
5 0.00106 *{sa'ch}
5 0.00106 ..*{se}
removed 'dat/viet/ptt/tot.1/bad-whole-wds-summary.tex'
removed 'exp/viet/ptt/tot.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/viet/ptt/tot.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:31:00 by tex-make-sample-summary.sh
% Token and word counts for viet/ptt/tot.1/bad.wfr
%
\def\vietpttwholetotPBbadTks{4733}
\def\vietpttwholetotPBbadTksPct{2.7}
\def\vietpttwholetotPBbadWds{3}
\def\vietpttwholetotPBbadWdsPct{0.0}
copied '/tmp/569761.file' -> 'exp/viet/ptt/tot.1/bad-whole-wds-summary.tex'
removed '/tmp/569761.file'
lines words bytes file
------- ------- --------- ------------
1796 5388 38930 dat/viet/ptt/gen.1/raw.wfr
1652 4956 35906 dat/viet/ptt/exo.1/raw.wfr
1488 4464 32211 dat/viet/ptt/num.1/raw.wfr
1210 3630 26313 dat/viet/ptt/lev.1/raw.wfr
1617 4851 35033 dat/viet/ptt/deu.1/raw.wfr
2687 8061 58445 dat/viet/ptt/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
1793 5379 38863 dat/viet/ptt/gen.1/gud.wfr
1649 4947 35839 dat/viet/ptt/exo.1/gud.wfr
1485 4455 32144 dat/viet/ptt/num.1/gud.wfr
1207 3621 26246 dat/viet/ptt/lev.1/gud.wfr
1614 4842 34966 dat/viet/ptt/deu.1/gud.wfr
2684 8052 58378 dat/viet/ptt/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
3 9 67 dat/viet/ptt/gen.1/bad.wfr
3 9 67 dat/viet/ptt/exo.1/bad.wfr
3 9 67 dat/viet/ptt/num.1/bad.wfr
3 9 67 dat/viet/ptt/lev.1/bad.wfr
3 9 67 dat/viet/ptt/deu.1/bad.wfr
3 9 67 dat/viet/ptt/tot.1/bad.wfr
gen.1 raw = 43448 gud = 42099 bad = 1349
exo.1 raw = 34775 gud = 33760 bad = 1015
num.1 raw = 38067 gud = 37097 bad = 970
lev.1 raw = 25831 gud = 25163 bad = 668
deu.1 raw = 32092 gud = 31361 bad = 731
tot.1 raw = 174213 gud = 169480 bad = 4733
=== creating the derived word files dat/viet/nwt/*/{raw,gud,bad}.{tlw,wdf,wfr} (whole) ===
... creating word files dat/viet/nwt/mat.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
26411 dat/viet/nwt/mat.1/whole.tlw
removed 'dat/viet/nwt/mat.1/raw.tlw'
removed 'dat/viet/nwt/mat.1/gud.tlw'
removed 'dat/viet/nwt/mat.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/viet/nwt/mat.1/raw.wdf
sample:
gia pha? ddu+'c chu'a gie^ su ki to^ con dda vi't con a'p ra ham a'p ra
ham sinh y sa'c y sa'c sinh gia co^'p gia co^'p sinh giu dda va` ca'c
anh em o^ng giu dda sinh pha re^ va`o xa ra bo+?i tha ma pha re^ sinh e^
se ro^m e^ se ro^m sinh a ram a ram sinh a mi na dda'p a mi na dda'p
sinh na a so^n na a so^n sinh sa mo^n sa mo^n sinh bo't se^ bo+?i ra
ha'p bo't se^ sinh gio^ be^t bo+?i ba` ru't gio^ be^'t sinh y sai y sai
sinh vua dda vi't dda vi't sinh sa lo^ mo^n bo+?i vo+. cu?a u ria sa lo^
mo^n sinh ro bo am ro bo am sinh a bia a bia sinh a sa a sa sinh gio^ sa
phat gio^ sa phat sinh gio^ ram gio^ ram sinh o^ xya o^ xya sinh gio^ a
tham gio^ a tham sinh a ka a ka sinh e^t se^ kya e^t se^ kya sinh ma na
se^ ma na se^ sinh am mo^n am mo^n sinh gio^ sya gio^ sya sinh gie^ kho^
nya va` ca'c anh em o^ng tho+`i lu+u dda`y ba be^n sau tho+`i lu+u dda`y
ba be^n gie^ kho^ nya sinh sa la thi e^n sa la thi e^n sinh xo ro ba
be^n xo ro ba be^n sinh a bi hu a bi hu sinh e^ lya kim e^ lya kim sinh
a't so^ a't so^ sinh sa ddo'c sa ddo'c sinh a khim a khim sinh e^ li hu
e^ li hu sinh e^ li a sa e^ li a sa sinh ma't than ma't than sinh gia
co^'p gia co^'p sinh gio^ se'p cho^`ng cu?a ma ria bo+?i ba` thi` ddu+'c
gie^ su go.i la` ki to^ dda~ sinh ra =
to^?ng co^.ng ca'c ddo+`i la.i thi` tu+` a'p ra ham dde^'n dda vi't co'
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
giu+~ he^'t mo.i ddie^`u ta dda~ truye^`n cho ca'c ngu+o+i va` na`y ta
se~ o+? vo+'i ca'c ngu+o+i mo.i nga`y cho dde^'n ta^.n the^' =
removed 'dat/viet/nwt/mat.1/raw.wfr'
creating the word frequency file dat/viet/nwt/mat.1/raw.wfr
the 10 most common words in dat/viet/nwt/mat.1/raw.tlw:
794 0.03006 =
636 0.02408 va`
572 0.02166 ca'c
517 0.01958 nga`i
486 0.01840 ngu+o+i
430 0.01628 ngu+o+`i
389 0.01473 ta
340 0.01287 cho
335 0.01268 dda~
332 0.01257 ma`
removed 'dat/viet/nwt/mat.1/raw-whole-wds-summary.tex'
removed 'exp/viet/nwt/mat.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/viet/nwt/mat.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:31:00 by tex-make-sample-summary.sh
% Token and word counts for viet/nwt/mat.1/raw.wfr
%
\def\vietnwtwholematPBrawTks{26411}
\def\vietnwtwholematPBrawTksPct{100.0}
\def\vietnwtwholematPBrawWds{1821}
\def\vietnwtwholematPBrawWdsPct{6.9}
copied '/tmp/569931.file' -> 'exp/viet/nwt/mat.1/raw-whole-wds-summary.tex'
removed '/tmp/569931.file'
creating running text file dat/viet/nwt/mat.1/gud.wdf
sample:
gia pha? ddu+'c chu'a gie^ su ki to^ con dda vi't con a'p ra ham a'p ra
ham sinh y sa'c y sa'c sinh gia co^'p gia co^'p sinh giu dda va` ca'c
anh em o^ng giu dda sinh pha re^ va`o xa ra bo+?i tha ma pha re^ sinh e^
se ro^m e^ se ro^m sinh a ram a ram sinh a mi na dda'p a mi na dda'p
sinh na a so^n na a so^n sinh sa mo^n sa mo^n sinh bo't se^ bo+?i ra
ha'p bo't se^ sinh gio^ be^t bo+?i ba` ru't gio^ be^'t sinh y sai y sai
sinh vua dda vi't dda vi't sinh sa lo^ mo^n bo+?i vo+. cu?a u ria sa lo^
mo^n sinh ro bo am ro bo am sinh a bia a bia sinh a sa a sa sinh gio^ sa
phat gio^ sa phat sinh gio^ ram gio^ ram sinh o^ xya o^ xya sinh gio^ a
tham gio^ a tham sinh a ka a ka sinh e^t se^ kya e^t se^ kya sinh ma na
se^ ma na se^ sinh am mo^n am mo^n sinh gio^ sya gio^ sya sinh gie^ kho^
nya va` ca'c anh em o^ng tho+`i lu+u dda`y ba be^n sau tho+`i lu+u dda`y
ba be^n gie^ kho^ nya sinh sa la thi e^n sa la thi e^n sinh xo ro ba
be^n xo ro ba be^n sinh a bi hu a bi hu sinh e^ lya kim e^ lya kim sinh
a't so^ a't so^ sinh sa ddo'c sa ddo'c sinh a khim a khim sinh e^ li hu
e^ li hu sinh e^ li a sa e^ li a sa sinh ma't than ma't than sinh gia
co^'p gia co^'p sinh gio^ se'p cho^`ng cu?a ma ria bo+?i ba` thi` ddu+'c
gie^ su go.i la` ki to^ dda~ sinh ra to^?ng co^.ng ca'c ddo+`i la.i thi`
tu+` a'p ra ham dde^'n dda vi't co' mu+o+`i bo^'n ddo+`i tu+` dda vi't
dde^'n tho+`i lu+u dda`y ba be^n co' mu+o+`i bo^'n ddo+`i tu+` tho+`i
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
muo^n da^n thanh ta^?y chu'ng nha^n danh cha va` con va` tha'nh tha^`n
da.y chu'ng giu+~ he^'t mo.i ddie^`u ta dda~ truye^`n cho ca'c ngu+o+i
va` na`y ta se~ o+? vo+'i ca'c ngu+o+i mo.i nga`y cho dde^'n ta^.n the^'
removed 'dat/viet/nwt/mat.1/gud.wfr'
creating the word frequency file dat/viet/nwt/mat.1/gud.wfr
the 10 most common words in dat/viet/nwt/mat.1/gud.tlw:
636 0.02483 va`
572 0.02233 ca'c
517 0.02018 nga`i
486 0.01897 ngu+o+i
430 0.01679 ngu+o+`i
389 0.01519 ta
340 0.01327 cho
335 0.01308 dda~
332 0.01296 ma`
327 0.01277 ho.
removed 'dat/viet/nwt/mat.1/gud-whole-wds-summary.tex'
removed 'exp/viet/nwt/mat.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/viet/nwt/mat.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:31:00 by tex-make-sample-summary.sh
% Token and word counts for viet/nwt/mat.1/gud.wfr
%
\def\vietnwtwholematPBgudTks{25615}
\def\vietnwtwholematPBgudTksPct{97.0}
\def\vietnwtwholematPBgudWds{1818}
\def\vietnwtwholematPBgudWdsPct{6.9}
copied '/tmp/569975.file' -> 'exp/viet/nwt/mat.1/gud-whole-wds-summary.tex'
removed '/tmp/569975.file'
creating running text file dat/viet/nwt/mat.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/viet/nwt/mat.1/bad.wfr'
creating the word frequency file dat/viet/nwt/mat.1/bad.wfr
the 10 most common words in dat/viet/nwt/mat.1/bad.tlw:
794 0.99749 =
1 0.00126 *{e^}
1 0.00126 ..*{sabakthani}
removed 'dat/viet/nwt/mat.1/bad-whole-wds-summary.tex'
removed 'exp/viet/nwt/mat.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/viet/nwt/mat.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:31:00 by tex-make-sample-summary.sh
% Token and word counts for viet/nwt/mat.1/bad.wfr
%
\def\vietnwtwholematPBbadTks{796}
\def\vietnwtwholematPBbadTksPct{3.0}
\def\vietnwtwholematPBbadWds{3}
\def\vietnwtwholematPBbadWdsPct{0.0}
copied '/tmp/570019.file' -> 'exp/viet/nwt/mat.1/bad-whole-wds-summary.tex'
removed '/tmp/570019.file'
... creating word files dat/viet/nwt/mrk.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
16326 dat/viet/nwt/mrk.1/whole.tlw
removed 'dat/viet/nwt/mrk.1/raw.tlw'
removed 'dat/viet/nwt/mrk.1/gud.tlw'
removed 'dat/viet/nwt/mrk.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/viet/nwt/mrk.1/raw.wdf
sample:
kho+?i nguye^n tin mu+`ng ddu+'c gie^ su ki to^ con thie^n chu'a =
nhu+ dda~ vie^'t trong sa'ch tie^n tri y sa y a na`y ta sai tha^`n su+'
ta ddi tru+o+'c ma(.t ngu+o+i ke? se~ do.n ddu+o+`ng cho ngu+o+i tie^'ng
cu?a ngu+o+i ho^ trong sa ma.c ha~y do.n ddu+o+`ng chu'a ha~y ba.t lo^'i
ngu+o+`i ddi =
trong sa ma.c gio^ an ta^?y gia? xua^'t hie^.n rao gia?ng thanh ta^?y
ho^'i ca?i dde^? ddu+o+.c tha thu+' to^.i khie^n =
va` ca? xu+' giu dde^ va` ta^'t ca? da^n tha`nh gie^ ru sa lem tra^?y
da^'n vo+'i o^ng va` nho+` o^ng thanh ta^?y cho trong so^ng gio^ ddanh
ma` xu+ng thu' to^.i lo^~i =
gio^ an mi`nh ma(.c a'o lo^ng la.c dda` va` ngang lu+ng thi` tha('t
xie^m ba(`ng da thu' va^.t va` o^ng nuo^i mi`nh ba(`ng cha^u cha^'u va`
ma^.t ong da.i =
o^ng rao gia?ng ra(`ng se~ dde^'n sau to^i dda^'ng quye^`n the^' ho+n
to^i to^i kho^ng dda'ng cu'i xuo^'ng ma` co+?i quai de'p nga`i =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
co`n ho. thi` ra ddi rao gia?ng kha('p no+i co' chu'a cu`ng ho. hoa.t
ddo^.ng va` cu?ng co^' lo+`i bo+?i phe'p la. ke`m theo =
removed 'dat/viet/nwt/mrk.1/raw.wfr'
creating the word frequency file dat/viet/nwt/mrk.1/raw.wfr
the 10 most common words in dat/viet/nwt/mrk.1/raw.tlw:
535 0.03277 nga`i
476 0.02916 va`
429 0.02628 =
354 0.02168 ho.
300 0.01838 ngu+o+`i
244 0.01495 ca'c
211 0.01292 vo+'i
205 0.01256 dda~
202 0.01237 cho
202 0.01237 no'i
removed 'dat/viet/nwt/mrk.1/raw-whole-wds-summary.tex'
removed 'exp/viet/nwt/mrk.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/viet/nwt/mrk.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:31:00 by tex-make-sample-summary.sh
% Token and word counts for viet/nwt/mrk.1/raw.wfr
%
\def\vietnwtwholemrkPBrawTks{16326}
\def\vietnwtwholemrkPBrawTksPct{100.0}
\def\vietnwtwholemrkPBrawWds{1575}
\def\vietnwtwholemrkPBrawWdsPct{9.6}
copied '/tmp/570073.file' -> 'exp/viet/nwt/mrk.1/raw-whole-wds-summary.tex'
removed '/tmp/570073.file'
creating running text file dat/viet/nwt/mrk.1/gud.wdf
sample:
kho+?i nguye^n tin mu+`ng ddu+'c gie^ su ki to^ con thie^n chu'a nhu+
dda~ vie^'t trong sa'ch tie^n tri y sa y a na`y ta sai tha^`n su+' ta
ddi tru+o+'c ma(.t ngu+o+i ke? se~ do.n ddu+o+`ng cho ngu+o+i tie^'ng
cu?a ngu+o+i ho^ trong sa ma.c ha~y do.n ddu+o+`ng chu'a ha~y ba.t lo^'i
ngu+o+`i ddi trong sa ma.c gio^ an ta^?y gia? xua^'t hie^.n rao gia?ng
thanh ta^?y ho^'i ca?i dde^? ddu+o+.c tha thu+' to^.i khie^n va` ca?
xu+' giu dde^ va` ta^'t ca? da^n tha`nh gie^ ru sa lem tra^?y da^'n
vo+'i o^ng va` nho+` o^ng thanh ta^?y cho trong so^ng gio^ ddanh ma`
xu+ng thu' to^.i lo^~i gio^ an mi`nh ma(.c a'o lo^ng la.c dda` va` ngang
lu+ng thi` tha('t xie^m ba(`ng da thu' va^.t va` o^ng nuo^i mi`nh ba(`ng
cha^u cha^'u va` ma^.t ong da.i o^ng rao gia?ng ra(`ng se~ dde^'n sau
to^i dda^'ng quye^`n the^' ho+n to^i to^i kho^ng dda'ng cu'i xuo^'ng ma`
co+?i quai de'p nga`i pha^`n to^i to^i dda~ thanh ta^?y ca'c ngu+o+`i
ba(`ng nu+o+'c co`n nga`i nga`i se~ thanh ta^?y ca'c ngu+o+`i ba(`ng
tha'nh tha^`n va` xa?y ra la` trong nhu+~ng nga`y a^'y ddu+'c gie^ su
bo? na xa re^ xu+' ga li le^ va` dda~ ddu+o+.c gio^ an thanh ta^?y cho
trong so^ng gio^ ddanh vu+`a le^n kho?i nu+o+'c nga`i tha^'y tro+`i xe'
ra va` tha^`n khi' nhu+ con chim ca^u dda'p xuo^'ng tre^n nga`i va`
mo^.t tie^'ng pha't ra tu+. tro+`i con la` con chi' a'i ta ke? ta su?ng
mo^. va` ngay sau ddo' tha^`n khi' xua nga`i va`o sa ma.c va` nga`i o+?
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
be^n hu+~u thie^n chu'a co`n ho. thi` ra ddi rao gia?ng kha('p no+i co'
chu'a cu`ng ho. hoa.t ddo^.ng va` cu?ng co^' lo+`i bo+?i phe'p la. ke`m
theo
removed 'dat/viet/nwt/mrk.1/gud.wfr'
creating the word frequency file dat/viet/nwt/mrk.1/gud.wfr
the 10 most common words in dat/viet/nwt/mrk.1/gud.tlw:
535 0.03366 nga`i
476 0.02995 va`
354 0.02227 ho.
300 0.01887 ngu+o+`i
244 0.01535 ca'c
211 0.01327 vo+'i
205 0.01290 dda~
202 0.01271 cho
202 0.01271 no'i
201 0.01265 ta
removed 'dat/viet/nwt/mrk.1/gud-whole-wds-summary.tex'
removed 'exp/viet/nwt/mrk.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/viet/nwt/mrk.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:31:00 by tex-make-sample-summary.sh
% Token and word counts for viet/nwt/mrk.1/gud.wfr
%
\def\vietnwtwholemrkPBgudTks{15895}
\def\vietnwtwholemrkPBgudTksPct{97.4}
\def\vietnwtwholemrkPBgudWds{1572}
\def\vietnwtwholemrkPBgudWdsPct{9.6}
copied '/tmp/570117.file' -> 'exp/viet/nwt/mrk.1/gud-whole-wds-summary.tex'
removed '/tmp/570117.file'
creating running text file dat/viet/nwt/mrk.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/viet/nwt/mrk.1/bad.wfr'
creating the word frequency file dat/viet/nwt/mrk.1/bad.wfr
the 10 most common words in dat/viet/nwt/mrk.1/bad.tlw:
429 0.99536 =
1 0.00232 *{e^lo^i}
1 0.00232 ..*{sabakthani}
removed 'dat/viet/nwt/mrk.1/bad-whole-wds-summary.tex'
removed 'exp/viet/nwt/mrk.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/viet/nwt/mrk.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:31:00 by tex-make-sample-summary.sh
% Token and word counts for viet/nwt/mrk.1/bad.wfr
%
\def\vietnwtwholemrkPBbadTks{431}
\def\vietnwtwholemrkPBbadTksPct{2.6}
\def\vietnwtwholemrkPBbadWds{3}
\def\vietnwtwholemrkPBbadWdsPct{0.0}
copied '/tmp/570161.file' -> 'exp/viet/nwt/mrk.1/bad-whole-wds-summary.tex'
removed '/tmp/570161.file'
... creating word files dat/viet/nwt/luk.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
28276 dat/viet/nwt/luk.1/whole.tlw
removed 'dat/viet/nwt/luk.1/raw.tlw'
removed 'dat/viet/nwt/luk.1/gud.tlw'
removed 'dat/viet/nwt/luk.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/viet/nwt/luk.1/raw.wdf
sample:
bo+?i chu+ng dda~ co' nhie^`u ngu+o+`i tra tay die^~n la.i tri`nh tu+.
ca'c bie^'n co^' dda~ thu+.c hie^.n giu+~a chu'ng to^i theo nhu+ ca'c
ke? tu+` dda^`u dda~ chu+'ng kie^'n va` phu.c vu. cho lo+`i dda~
truye^`n la.i cho chu'ng to^i thi` to^i thie^'t nghi~ la` sau khi dda~
quan sa't mo.i su+. tu+` la^u mo^.t ca'ch tu+o+`ng ta^.n cu~ng ne^n
thu+a nga`i the^ o^ phi lo^ cu+' tua^`n tu+. ma` vie^'t la.i cho nga`i
ngo~ ha^`u nga`i ddu+o+.c am tu+o+`ng ra(`ng gia'o hua^'n nga`i dda~
thu. li~nh thu+.c la` chi'nh xa'c =
so^' la` va`o nhu+~ng nga`y tho+`i he^ ro^ dde^ vua xu+' giu dde^ co'
vi. tu+ te^' te^n la` xa ca rya thuo^.c phie^n thu+' a bia va` vo+. o^ng
thuo^.c ha`ng nu+~ tu+? a ra ho^n va` te^n ba` la` e^ li sa be't =
ca? hai dde^`u la` co^ng chi'nh tru+o+'c ma(.t thie^n chu'a ddi ddu+'ng
ra^.p theo mo.i ddie^`u ra(n gio+'i lua^.t cu?a chu'a vo^ phu+o+ng
tra'ch cu+' =
nhu+ng o^ng ba` la.i kho^ng con vi` e^ li sa be't la` ngu+o+`i son se?
hie^'m hoi va? cha(ng hai o^ng ba` la.i dda~ cao nie^n ca? ro^`i =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
va` ha(`ng o+? trong dde^`n tho+` ma` chu'c tu.ng thie^n chu'a =
removed 'dat/viet/nwt/luk.1/raw.wfr'
creating the word frequency file dat/viet/nwt/luk.1/raw.wfr
the 10 most common words in dat/viet/nwt/luk.1/raw.tlw:
697 0.02465 va`
639 0.02260 =
628 0.02221 nga`i
565 0.01998 ngu+o+`i
520 0.01839 ca'c
440 0.01556 ngu+o+i
435 0.01538 dda~
365 0.01291 ho.
359 0.01270 cho
347 0.01227 no'i
removed 'dat/viet/nwt/luk.1/raw-whole-wds-summary.tex'
removed 'exp/viet/nwt/luk.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/viet/nwt/luk.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:31:00 by tex-make-sample-summary.sh
% Token and word counts for viet/nwt/luk.1/raw.wfr
%
\def\vietnwtwholelukPBrawTks{28276}
\def\vietnwtwholelukPBrawTksPct{100.0}
\def\vietnwtwholelukPBrawWds{2118}
\def\vietnwtwholelukPBrawWdsPct{7.5}
copied '/tmp/570215.file' -> 'exp/viet/nwt/luk.1/raw-whole-wds-summary.tex'
removed '/tmp/570215.file'
creating running text file dat/viet/nwt/luk.1/gud.wdf
sample:
bo+?i chu+ng dda~ co' nhie^`u ngu+o+`i tra tay die^~n la.i tri`nh tu+.
ca'c bie^'n co^' dda~ thu+.c hie^.n giu+~a chu'ng to^i theo nhu+ ca'c
ke? tu+` dda^`u dda~ chu+'ng kie^'n va` phu.c vu. cho lo+`i dda~
truye^`n la.i cho chu'ng to^i thi` to^i thie^'t nghi~ la` sau khi dda~
quan sa't mo.i su+. tu+` la^u mo^.t ca'ch tu+o+`ng ta^.n cu~ng ne^n
thu+a nga`i the^ o^ phi lo^ cu+' tua^`n tu+. ma` vie^'t la.i cho nga`i
ngo~ ha^`u nga`i ddu+o+.c am tu+o+`ng ra(`ng gia'o hua^'n nga`i dda~
thu. li~nh thu+.c la` chi'nh xa'c so^' la` va`o nhu+~ng nga`y tho+`i he^
ro^ dde^ vua xu+' giu dde^ co' vi. tu+ te^' te^n la` xa ca rya thuo^.c
phie^n thu+' a bia va` vo+. o^ng thuo^.c ha`ng nu+~ tu+? a ra ho^n va`
te^n ba` la` e^ li sa be't ca? hai dde^`u la` co^ng chi'nh tru+o+'c
ma(.t thie^n chu'a ddi ddu+'ng ra^.p theo mo.i ddie^`u ra(n gio+'i
lua^.t cu?a chu'a vo^ phu+o+ng tra'ch cu+' nhu+ng o^ng ba` la.i kho^ng
con vi` e^ li sa be't la` ngu+o+`i son se? hie^'m hoi va? cha(ng hai
o^ng ba` la.i dda~ cao nie^n ca? ro^`i va^.y xa?y ra la` mo^.t la^`n kia
theo lu+o+.t cu?a phie^n thu+' o^ng o^ng du+o+.c cha^'p le^~ tru+o+'c
ma(.t thie^n chu'a chie^'u theo tu.c le^. ha`ng tu+ te^' o^ng dda~ ba('t
tha(m va` tru'ng vie^.c thu+o+.ng hu+o+ng ddu+o+.c va`o tha'nh ddie^.n
cu?a chu'a va` ddoa`n the^? cu?a da^n ta^'t ca? nguye^.n kinh be^n
ngoa`i trong gio+` thu+o+.ng hu+o+ng thie^n tha^`n chu'a dda~ hie^.n ra
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
bie^.t ho. va` ddu+o+.c nha('c le^n tro+`i va` tho+` la.y nga`i ro^`i
ho. dda~ tro+? la.i gie^ ru sa lem vui mu+`ng kho^n xie^'t va` ha(`ng
o+? trong dde^`n tho+` ma` chu'c tu.ng thie^n chu'a
removed 'dat/viet/nwt/luk.1/gud.wfr'
creating the word frequency file dat/viet/nwt/luk.1/gud.wfr
the 10 most common words in dat/viet/nwt/luk.1/gud.tlw:
697 0.02522 va`
628 0.02272 nga`i
565 0.02044 ngu+o+`i
520 0.01882 ca'c
440 0.01592 ngu+o+i
435 0.01574 dda~
365 0.01321 ho.
359 0.01299 cho
347 0.01256 no'i
339 0.01227 ta
removed 'dat/viet/nwt/luk.1/gud-whole-wds-summary.tex'
removed 'exp/viet/nwt/luk.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/viet/nwt/luk.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:31:00 by tex-make-sample-summary.sh
% Token and word counts for viet/nwt/luk.1/gud.wfr
%
\def\vietnwtwholelukPBgudTks{27637}
\def\vietnwtwholelukPBgudTksPct{97.7}
\def\vietnwtwholelukPBgudWds{2117}
\def\vietnwtwholelukPBgudWdsPct{7.5}
copied '/tmp/570259.file' -> 'exp/viet/nwt/luk.1/gud-whole-wds-summary.tex'
removed '/tmp/570259.file'
creating running text file dat/viet/nwt/luk.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/viet/nwt/luk.1/bad.wfr'
creating the word frequency file dat/viet/nwt/luk.1/bad.wfr
the 10 most common words in dat/viet/nwt/luk.1/bad.tlw:
639 1.00000 =
removed 'dat/viet/nwt/luk.1/bad-whole-wds-summary.tex'
removed 'exp/viet/nwt/luk.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/viet/nwt/luk.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:31:00 by tex-make-sample-summary.sh
% Token and word counts for viet/nwt/luk.1/bad.wfr
%
\def\vietnwtwholelukPBbadTks{639}
\def\vietnwtwholelukPBbadTksPct{2.3}
\def\vietnwtwholelukPBbadWds{1}
\def\vietnwtwholelukPBbadWdsPct{0.0}
copied '/tmp/570303.file' -> 'exp/viet/nwt/luk.1/bad-whole-wds-summary.tex'
removed '/tmp/570303.file'
... creating word files dat/viet/nwt/jhn.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
22428 dat/viet/nwt/jhn.1/whole.tlw
removed 'dat/viet/nwt/jhn.1/raw.tlw'
removed 'dat/viet/nwt/jhn.1/gud.tlw'
removed 'dat/viet/nwt/jhn.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/viet/nwt/jhn.1/raw.wdf
sample:
lu'c kho+?i nguye^n dda~ co' lo+`i va` lo+`i o+? no+i thie^n chu'a va`
lo+`i la` mo^.t vi. thie^n chu'a nga`i dda~ co' lu'c kho+?i nguye^n
vo+'i thie^n chu'a =
mo.i su+. dda~ nho+` nga`i ma` tha`nh su+. va` kho^ng nga`i thi` kho^ng
gi` dda~ tha`nh su+. ddie^`u dda~ tha`nh su+. no+i nga`i la` su+. so^'ng
va` su+. so^'ng la` su+. sa'ng cho nha^n loa.i =
va` su+. sa'ng ra.ng trong to^'i ta(m va` to^'i ta(m dda~ kho^ng trie^.t
ddu+o+.c su+. sa'ng =
xa?y ra la` co' ngu+o+`i ddu+o+.c sai dde^'n tu+` no+i thie^n chu'a te^n
o^ng la` gio^ an =
o^ng dda~ dde^'n dde^? la`m chu+'ng dde^? chu'ng thu+.c ve^` su+. sa'ng
ngo~ ha^`u mo.i ngu+o+`i nho+` o^ng ma` tin =
o^ng kho^ng pha?i la` su+. sa'ng nhu+ng la` dde^? la`m chu+'ng cho su+.
sa'ng =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
tu+`ng ddie^`u thi` thie^'t tu+o+?ng the^' gian kho^ng ddu? cho^~ ma`
chu+'a sa'ch vie^'t ra =
removed 'dat/viet/nwt/jhn.1/raw.wfr'
creating the word frequency file dat/viet/nwt/jhn.1/raw.wfr
the 10 most common words in dat/viet/nwt/jhn.1/raw.tlw:
669 0.02983 ta
556 0.02479 =
549 0.02448 dda~
516 0.02301 nga`i
507 0.02261 ca'c
444 0.01980 va`
436 0.01944 ngu+o+i
379 0.01690 no'i
378 0.01685 kho^ng
369 0.01645 ngu+o+`i
removed 'dat/viet/nwt/jhn.1/raw-whole-wds-summary.tex'
removed 'exp/viet/nwt/jhn.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/viet/nwt/jhn.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:31:00 by tex-make-sample-summary.sh
% Token and word counts for viet/nwt/jhn.1/raw.wfr
%
\def\vietnwtwholejhnPBrawTks{22428}
\def\vietnwtwholejhnPBrawTksPct{100.0}
\def\vietnwtwholejhnPBrawWds{1290}
\def\vietnwtwholejhnPBrawWdsPct{5.8}
copied '/tmp/570357.file' -> 'exp/viet/nwt/jhn.1/raw-whole-wds-summary.tex'
removed '/tmp/570357.file'
creating running text file dat/viet/nwt/jhn.1/gud.wdf
sample:
lu'c kho+?i nguye^n dda~ co' lo+`i va` lo+`i o+? no+i thie^n chu'a va`
lo+`i la` mo^.t vi. thie^n chu'a nga`i dda~ co' lu'c kho+?i nguye^n
vo+'i thie^n chu'a mo.i su+. dda~ nho+` nga`i ma` tha`nh su+. va` kho^ng
nga`i thi` kho^ng gi` dda~ tha`nh su+. ddie^`u dda~ tha`nh su+. no+i
nga`i la` su+. so^'ng va` su+. so^'ng la` su+. sa'ng cho nha^n loa.i va`
su+. sa'ng ra.ng trong to^'i ta(m va` to^'i ta(m dda~ kho^ng trie^.t
ddu+o+.c su+. sa'ng xa?y ra la` co' ngu+o+`i ddu+o+.c sai dde^'n tu+`
no+i thie^n chu'a te^n o^ng la` gio^ an o^ng dda~ dde^'n dde^? la`m
chu+'ng dde^? chu'ng thu+.c ve^` su+. sa'ng ngo~ ha^`u mo.i ngu+o+`i
nho+` o^ng ma` tin o^ng kho^ng pha?i la` su+. sa'ng nhu+ng la` dde^?
la`m chu+'ng cho su+. sa'ng nga`i la` su+. sa'ng ddi'ch tha^.t sa'ng soi
mo.i ngu+o+`i nga`i dde^'n trong the^' gian nga`i co' trong the^' gian
va` the^' gian dda~ nho+` nga`i ma` ddu+o+.c co' ma` the^' gian dda~
kho^ng bie^'t nga`i nga`i dda~ dde^'n no+i nha` cu?a nga`i ma` ngu+o+`i
nha` dda~ kho^ng tie^'p nha^.n nga`i co`n nhu+~ng ai ddo'n nha^.n nga`i
thi` nga`i ban cho ho. quye^`n la`m con thie^n chu'a a^'y la` cho
nhu+~ng ke? tin va`o danh nga`i ho. kho^ng do ma'u huye^'t ma` sinh ra
cu~ng kho^ng pha?i do y' xa'c thi.t cu~ng pha?i do y' cu?a nam nha^n
nhu+ng chi'nh do bo+?i thie^n chu'a ma` ddu+o+.c sinh ra va` lo+`i dda~
tha`nh xa'c pha`m va` dda~ lu+u tru' no+i chu'ng to^i va` chu'ng to^i
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
ra(`ng chu+'ng cu?a o^ng la` chu+'ng xa'c thu+.c co`n la('m ddie^`u
kha'c ddu+'c gie^ su dda~ la`m ne^'u vie^'t la.i tu+`ng ddie^`u thi`
thie^'t tu+o+?ng the^' gian kho^ng ddu? cho^~ ma` chu+'a sa'ch vie^'t ra
removed 'dat/viet/nwt/jhn.1/gud.wfr'
creating the word frequency file dat/viet/nwt/jhn.1/gud.wfr
the 10 most common words in dat/viet/nwt/jhn.1/gud.tlw:
669 0.03059 ta
549 0.02510 dda~
516 0.02359 nga`i
507 0.02318 ca'c
444 0.02030 va`
436 0.01993 ngu+o+i
379 0.01733 no'i
378 0.01728 kho^ng
369 0.01687 ngu+o+`i
348 0.01591 la`
removed 'dat/viet/nwt/jhn.1/gud-whole-wds-summary.tex'
removed 'exp/viet/nwt/jhn.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/viet/nwt/jhn.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:31:01 by tex-make-sample-summary.sh
% Token and word counts for viet/nwt/jhn.1/gud.wfr
%
\def\vietnwtwholejhnPBgudTks{21872}
\def\vietnwtwholejhnPBgudTksPct{97.5}
\def\vietnwtwholejhnPBgudWds{1289}
\def\vietnwtwholejhnPBgudWdsPct{5.7}
copied '/tmp/570401.file' -> 'exp/viet/nwt/jhn.1/gud-whole-wds-summary.tex'
removed '/tmp/570401.file'
creating running text file dat/viet/nwt/jhn.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/viet/nwt/jhn.1/bad.wfr'
creating the word frequency file dat/viet/nwt/jhn.1/bad.wfr
the 10 most common words in dat/viet/nwt/jhn.1/bad.tlw:
556 1.00000 =
removed 'dat/viet/nwt/jhn.1/bad-whole-wds-summary.tex'
removed 'exp/viet/nwt/jhn.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/viet/nwt/jhn.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:31:01 by tex-make-sample-summary.sh
% Token and word counts for viet/nwt/jhn.1/bad.wfr
%
\def\vietnwtwholejhnPBbadTks{556}
\def\vietnwtwholejhnPBbadTksPct{2.5}
\def\vietnwtwholejhnPBbadWds{1}
\def\vietnwtwholejhnPBbadWdsPct{0.0}
copied '/tmp/570445.file' -> 'exp/viet/nwt/jhn.1/bad-whole-wds-summary.tex'
removed '/tmp/570445.file'
... creating word files dat/viet/nwt/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
93441 dat/viet/nwt/tot.1/whole.tlw
removed 'dat/viet/nwt/tot.1/raw.tlw'
removed 'dat/viet/nwt/tot.1/gud.tlw'
removed 'dat/viet/nwt/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/viet/nwt/tot.1/raw.wdf
sample:
gia pha? ddu+'c chu'a gie^ su ki to^ con dda vi't con a'p ra ham a'p ra
ham sinh y sa'c y sa'c sinh gia co^'p gia co^'p sinh giu dda va` ca'c
anh em o^ng giu dda sinh pha re^ va`o xa ra bo+?i tha ma pha re^ sinh e^
se ro^m e^ se ro^m sinh a ram a ram sinh a mi na dda'p a mi na dda'p
sinh na a so^n na a so^n sinh sa mo^n sa mo^n sinh bo't se^ bo+?i ra
ha'p bo't se^ sinh gio^ be^t bo+?i ba` ru't gio^ be^'t sinh y sai y sai
sinh vua dda vi't dda vi't sinh sa lo^ mo^n bo+?i vo+. cu?a u ria sa lo^
mo^n sinh ro bo am ro bo am sinh a bia a bia sinh a sa a sa sinh gio^ sa
phat gio^ sa phat sinh gio^ ram gio^ ram sinh o^ xya o^ xya sinh gio^ a
tham gio^ a tham sinh a ka a ka sinh e^t se^ kya e^t se^ kya sinh ma na
se^ ma na se^ sinh am mo^n am mo^n sinh gio^ sya gio^ sya sinh gie^ kho^
nya va` ca'c anh em o^ng tho+`i lu+u dda`y ba be^n sau tho+`i lu+u dda`y
ba be^n gie^ kho^ nya sinh sa la thi e^n sa la thi e^n sinh xo ro ba
be^n xo ro ba be^n sinh a bi hu a bi hu sinh e^ lya kim e^ lya kim sinh
a't so^ a't so^ sinh sa ddo'c sa ddo'c sinh a khim a khim sinh e^ li hu
e^ li hu sinh e^ li a sa e^ li a sa sinh ma't than ma't than sinh gia
co^'p gia co^'p sinh gio^ se'p cho^`ng cu?a ma ria bo+?i ba` thi` ddu+'c
gie^ su go.i la` ki to^ dda~ sinh ra =
to^?ng co^.ng ca'c ddo+`i la.i thi` tu+` a'p ra ham dde^'n dda vi't co'
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
tu+`ng ddie^`u thi` thie^'t tu+o+?ng the^' gian kho^ng ddu? cho^~ ma`
chu+'a sa'ch vie^'t ra =
removed 'dat/viet/nwt/tot.1/raw.wfr'
creating the word frequency file dat/viet/nwt/tot.1/raw.wfr
the 10 most common words in dat/viet/nwt/tot.1/raw.tlw:
2418 0.02588 =
2253 0.02411 va`
2196 0.02350 nga`i
1843 0.01972 ca'c
1664 0.01781 ngu+o+`i
1598 0.01710 ta
1536 0.01644 ngu+o+i
1524 0.01631 dda~
1289 0.01379 ho.
1220 0.01306 no'i
removed 'dat/viet/nwt/tot.1/raw-whole-wds-summary.tex'
removed 'exp/viet/nwt/tot.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/viet/nwt/tot.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:31:01 by tex-make-sample-summary.sh
% Token and word counts for viet/nwt/tot.1/raw.wfr
%
\def\vietnwtwholetotPBrawTks{93441}
\def\vietnwtwholetotPBrawTksPct{100.0}
\def\vietnwtwholetotPBrawWds{2739}
\def\vietnwtwholetotPBrawWdsPct{2.9}
copied '/tmp/570499.file' -> 'exp/viet/nwt/tot.1/raw-whole-wds-summary.tex'
removed '/tmp/570499.file'
creating running text file dat/viet/nwt/tot.1/gud.wdf
sample:
gia pha? ddu+'c chu'a gie^ su ki to^ con dda vi't con a'p ra ham a'p ra
ham sinh y sa'c y sa'c sinh gia co^'p gia co^'p sinh giu dda va` ca'c
anh em o^ng giu dda sinh pha re^ va`o xa ra bo+?i tha ma pha re^ sinh e^
se ro^m e^ se ro^m sinh a ram a ram sinh a mi na dda'p a mi na dda'p
sinh na a so^n na a so^n sinh sa mo^n sa mo^n sinh bo't se^ bo+?i ra
ha'p bo't se^ sinh gio^ be^t bo+?i ba` ru't gio^ be^'t sinh y sai y sai
sinh vua dda vi't dda vi't sinh sa lo^ mo^n bo+?i vo+. cu?a u ria sa lo^
mo^n sinh ro bo am ro bo am sinh a bia a bia sinh a sa a sa sinh gio^ sa
phat gio^ sa phat sinh gio^ ram gio^ ram sinh o^ xya o^ xya sinh gio^ a
tham gio^ a tham sinh a ka a ka sinh e^t se^ kya e^t se^ kya sinh ma na
se^ ma na se^ sinh am mo^n am mo^n sinh gio^ sya gio^ sya sinh gie^ kho^
nya va` ca'c anh em o^ng tho+`i lu+u dda`y ba be^n sau tho+`i lu+u dda`y
ba be^n gie^ kho^ nya sinh sa la thi e^n sa la thi e^n sinh xo ro ba
be^n xo ro ba be^n sinh a bi hu a bi hu sinh e^ lya kim e^ lya kim sinh
a't so^ a't so^ sinh sa ddo'c sa ddo'c sinh a khim a khim sinh e^ li hu
e^ li hu sinh e^ li a sa e^ li a sa sinh ma't than ma't than sinh gia
co^'p gia co^'p sinh gio^ se'p cho^`ng cu?a ma ria bo+?i ba` thi` ddu+'c
gie^ su go.i la` ki to^ dda~ sinh ra to^?ng co^.ng ca'c ddo+`i la.i thi`
tu+` a'p ra ham dde^'n dda vi't co' mu+o+`i bo^'n ddo+`i tu+` dda vi't
dde^'n tho+`i lu+u dda`y ba be^n co' mu+o+`i bo^'n ddo+`i tu+` tho+`i
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
ra(`ng chu+'ng cu?a o^ng la` chu+'ng xa'c thu+.c co`n la('m ddie^`u
kha'c ddu+'c gie^ su dda~ la`m ne^'u vie^'t la.i tu+`ng ddie^`u thi`
thie^'t tu+o+?ng the^' gian kho^ng ddu? cho^~ ma` chu+'a sa'ch vie^'t ra
removed 'dat/viet/nwt/tot.1/gud.wfr'
creating the word frequency file dat/viet/nwt/tot.1/gud.wfr
the 10 most common words in dat/viet/nwt/tot.1/gud.tlw:
2253 0.02475 va`
2196 0.02413 nga`i
1843 0.02025 ca'c
1664 0.01828 ngu+o+`i
1598 0.01756 ta
1536 0.01688 ngu+o+i
1524 0.01674 dda~
1289 0.01416 ho.
1220 0.01340 no'i
1166 0.01281 kho^ng
removed 'dat/viet/nwt/tot.1/gud-whole-wds-summary.tex'
removed 'exp/viet/nwt/tot.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/viet/nwt/tot.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:31:01 by tex-make-sample-summary.sh
% Token and word counts for viet/nwt/tot.1/gud.wfr
%
\def\vietnwtwholetotPBgudTks{91019}
\def\vietnwtwholetotPBgudTksPct{97.4}
\def\vietnwtwholetotPBgudWds{2735}
\def\vietnwtwholetotPBgudWdsPct{2.9}
copied '/tmp/570543.file' -> 'exp/viet/nwt/tot.1/gud-whole-wds-summary.tex'
removed '/tmp/570543.file'
creating running text file dat/viet/nwt/tot.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/viet/nwt/tot.1/bad.wfr'
creating the word frequency file dat/viet/nwt/tot.1/bad.wfr
the 10 most common words in dat/viet/nwt/tot.1/bad.tlw:
2418 0.99835 =
2 0.00083 ..*{sabakthani}
1 0.00041 *{e^lo^i}
1 0.00041 *{e^}
removed 'dat/viet/nwt/tot.1/bad-whole-wds-summary.tex'
removed 'exp/viet/nwt/tot.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/viet/nwt/tot.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:31:01 by tex-make-sample-summary.sh
% Token and word counts for viet/nwt/tot.1/bad.wfr
%
\def\vietnwtwholetotPBbadTks{2422}
\def\vietnwtwholetotPBbadTksPct{2.6}
\def\vietnwtwholetotPBbadWds{4}
\def\vietnwtwholetotPBbadWdsPct{0.0}
copied '/tmp/570587.file' -> 'exp/viet/nwt/tot.1/bad-whole-wds-summary.tex'
removed '/tmp/570587.file'
lines words bytes file
------- ------- --------- ------------
1821 5463 39528 dat/viet/nwt/mat.1/raw.wfr
1575 4725 34205 dat/viet/nwt/mrk.1/raw.wfr
2118 6354 45987 dat/viet/nwt/luk.1/raw.wfr
1290 3870 28044 dat/viet/nwt/jhn.1/raw.wfr
2739 8217 59542 dat/viet/nwt/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
1818 5454 39456 dat/viet/nwt/mat.1/gud.wfr
1572 4716 34129 dat/viet/nwt/mrk.1/gud.wfr
2117 6351 45969 dat/viet/nwt/luk.1/gud.wfr
1289 3867 28026 dat/viet/nwt/jhn.1/gud.wfr
2735 8205 59444 dat/viet/nwt/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
3 9 72 dat/viet/nwt/mat.1/bad.wfr
3 9 76 dat/viet/nwt/mrk.1/bad.wfr
1 3 18 dat/viet/nwt/luk.1/bad.wfr
1 3 18 dat/viet/nwt/jhn.1/bad.wfr
4 12 98 dat/viet/nwt/tot.1/bad.wfr
mat.1 raw = 26411 gud = 25615 bad = 796
mrk.1 raw = 16326 gud = 15895 bad = 431
luk.1 raw = 28276 gud = 27637 bad = 639
jhn.1 raw = 22428 gud = 21872 bad = 556
tot.1 raw = 93441 gud = 91019 bad = 2422
=== creating the derived word files dat/chin/ptt/*/{raw,gud,bad}.{tlw,wdf,wfr} (whole) ===
... creating word files dat/chin/ptt/gen.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
46397 dat/chin/ptt/gen.1/whole.tlw
removed 'dat/chin/ptt/gen.1/raw.tlw'
removed 'dat/chin/ptt/gen.1/gud.tlw'
removed 'dat/chin/ptt/gen.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/chin/ptt/gen.1/raw.wdf
sample:
qi3 chu1.1 shen2.1 chuang4 zao4 tian1 di4 =
di4 shi4 kong1 xu1.1 hun4 dun4.5 yuan1.2 mian4 hei1 an4 shen2.1 de5
ling2.1 yun4.1 xing2 zai4 shui3 mian4 shang4 =
shen2.1 shuo1 yao4 you3 guang1 jiu4 you3 le5 guang1 =
shen2.1 kan4 guang1 shi4 hao3 de5 jiu4 ba3 guang1 an4 fen1 kai1 le5 =
shen2.1 cheng1 guang1 wei2 zhou4.1 cheng1 an4 wei2 ye4 you3 wan3 shang4
you3 zao3 chen2.5 zhei4 shi4 tou2 yi1 ri4 =
shen2.1 shuo1 zhu1.1 shui3 zhi1.1 jian1 yao4 you3 kong1 qi4 jiang1 shui3
fen1 wei2 shang4 xia4 =
shen2.1 jiu4 zao4 chu1 kong1 qi4 jiang1 kong1 qi4 yi3.1 xia4 de5 shui3
kong1 qi4 yi3.1 shang4 de5 shui3 fen1 kai1 le5 shi4.1 jiu4 zhei4 yang4
cheng2 le5 =
shen2.1 cheng1 kong1 qi4 wei2 tian1 you3 wan3 shang4 you3 zao3 chen2.5
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
liao4 jiang1 ta1 xun1.1 le5 ba3 ta1 shou1 lian4.1 zai4 guan1.4 cai2.2
li3 ting2 zai4 ai1.3 ji2.1 =
removed 'dat/chin/ptt/gen.1/raw.wfr'
creating the word frequency file dat/chin/ptt/gen.1/raw.wfr
the 10 most common words in dat/chin/ptt/gen.1/raw.tlw:
2063 0.04446 de5
1316 0.02836 =
1178 0.02539 wo3
1157 0.02494 ta1
993 0.02140 ni3
815 0.01757 men5
708 0.01526 le5
697 0.01502 zai4
643 0.01386 zi5
637 0.01373 shuo1
removed 'dat/chin/ptt/gen.1/raw-whole-wds-summary.tex'
removed 'exp/chin/ptt/gen.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/chin/ptt/gen.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:31:01 by tex-make-sample-summary.sh
% Token and word counts for chin/ptt/gen.1/raw.wfr
%
\def\chinpttwholegenPBrawTks{46397}
\def\chinpttwholegenPBrawTksPct{100.0}
\def\chinpttwholegenPBrawWds{1504}
\def\chinpttwholegenPBrawWdsPct{3.2}
copied '/tmp/570742.file' -> 'exp/chin/ptt/gen.1/raw-whole-wds-summary.tex'
removed '/tmp/570742.file'
creating running text file dat/chin/ptt/gen.1/gud.wdf
sample:
qi3 chu1.1 shen2.1 chuang4 zao4 tian1 di4 di4 shi4 kong1 xu1.1 hun4
dun4.5 yuan1.2 mian4 hei1 an4 shen2.1 de5 ling2.1 yun4.1 xing2 zai4
shui3 mian4 shang4 shen2.1 shuo1 yao4 you3 guang1 jiu4 you3 le5 guang1
shen2.1 kan4 guang1 shi4 hao3 de5 jiu4 ba3 guang1 an4 fen1 kai1 le5
shen2.1 cheng1 guang1 wei2 zhou4.1 cheng1 an4 wei2 ye4 you3 wan3 shang4
you3 zao3 chen2.5 zhei4 shi4 tou2 yi1 ri4 shen2.1 shuo1 zhu1.1 shui3
zhi1.1 jian1 yao4 you3 kong1 qi4 jiang1 shui3 fen1 wei2 shang4 xia4
shen2.1 jiu4 zao4 chu1 kong1 qi4 jiang1 kong1 qi4 yi3.1 xia4 de5 shui3
kong1 qi4 yi3.1 shang4 de5 shui3 fen1 kai1 le5 shi4.1 jiu4 zhei4 yang4
cheng2 le5 shen2.1 cheng1 kong1 qi4 wei2 tian1 you3 wan3 shang4 you3
zao3 chen2.5 shi4 di4.2 er4 ri4 shen2.1 shuo1 tian1 xia4 de5 shui3 yao4
ju4.3 zai4 yi1 chu3 shi3 han4.4 di4 lu4.1 chu1 lai2 shi4.1 jiu4 zhei4
yang4 cheng2 le5 shen2.1 cheng1 han4.4 di4 wei2 di4 cheng1 shui3 de5
ju4.3 chu3 wei2 hai3 shen2.1 kan4 zhe5 shi4 hao3 de5 shen2.1 shuo1 di4
yao4 fa1 sheng1 qing1.2 cao3 he2 jie2 zhong3 zi5 de5 cai4 shu1.6 bing4.1
jie2 guo3 zi5 de5 shu4.2 mu4.1 ge4.1 cong2 qi2 lei4.1 guo3 zi5 dou1 bao1
zhe5 he2.6 shi4.1 jiu4 zhei4 yang4 cheng2 le5 yu2 shi4 di4 fa1 sheng1
le5 qing1.2 cao3 he2 jie2 zhong3 zi5 de5 cai4 shu1.6 ge4.1 cong2 qi2
lei4.1 bing4.1 jie2 guo3 zi5 de5 shu4.2 mu4.1 ge4.1 cong2 qi2 lei4.1
guo3 zi5 dou1 bao1 zhe5 he2.6 shen2.1 kan4 zhe5 shi4 hao3 de5 you3 wan3
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
zheng4 yi1 bai3 yi1 shi2.1 sui4.1 ren2 yong4 xiang1 liao4 jiang1 ta1
xun1.1 le5 ba3 ta1 shou1 lian4.1 zai4 guan1.4 cai2.2 li3 ting2 zai4
ai1.3 ji2.1
removed 'dat/chin/ptt/gen.1/gud.wfr'
creating the word frequency file dat/chin/ptt/gen.1/gud.wfr
the 10 most common words in dat/chin/ptt/gen.1/gud.tlw:
2063 0.04576 de5
1178 0.02613 wo3
1157 0.02566 ta1
993 0.02203 ni3
815 0.01808 men5
708 0.01571 le5
697 0.01546 zai4
643 0.01426 zi5
637 0.01413 shuo1
618 0.01371 shi4
removed 'dat/chin/ptt/gen.1/gud-whole-wds-summary.tex'
removed 'exp/chin/ptt/gen.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/chin/ptt/gen.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:31:01 by tex-make-sample-summary.sh
% Token and word counts for chin/ptt/gen.1/gud.wfr
%
\def\chinpttwholegenPBgudTks{45081}
\def\chinpttwholegenPBgudTksPct{97.2}
\def\chinpttwholegenPBgudWds{1503}
\def\chinpttwholegenPBgudWdsPct{3.2}
copied '/tmp/570786.file' -> 'exp/chin/ptt/gen.1/gud-whole-wds-summary.tex'
removed '/tmp/570786.file'
creating running text file dat/chin/ptt/gen.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/chin/ptt/gen.1/bad.wfr'
creating the word frequency file dat/chin/ptt/gen.1/bad.wfr
the 10 most common words in dat/chin/ptt/gen.1/bad.tlw:
1316 1.00000 =
removed 'dat/chin/ptt/gen.1/bad-whole-wds-summary.tex'
removed 'exp/chin/ptt/gen.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/chin/ptt/gen.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:31:01 by tex-make-sample-summary.sh
% Token and word counts for chin/ptt/gen.1/bad.wfr
%
\def\chinpttwholegenPBbadTks{1316}
\def\chinpttwholegenPBbadTksPct{2.8}
\def\chinpttwholegenPBbadWds{1}
\def\chinpttwholegenPBbadWdsPct{0.0}
copied '/tmp/570830.file' -> 'exp/chin/ptt/gen.1/bad-whole-wds-summary.tex'
removed '/tmp/570830.file'
... creating word files dat/chin/ptt/exo.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
36263 dat/chin/ptt/exo.1/whole.tlw
removed 'dat/chin/ptt/exo.1/raw.tlw'
removed 'dat/chin/ptt/exo.1/gud.tlw'
removed 'dat/chin/ptt/exo.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/chin/ptt/exo.1/raw.wdf
sample:
yi3.1 se4 lie4 de5 zhong4 zi5 ge4.1 dai4.1 jia1 juan4.1 he2 ya3 ge4.1
yi1 tong2 lai2 dao4.1 ai1.3 ji2.1 ta1 men5 de5 ming2.1 zi4.1 ji4.1 zai4
xia4 mian4 =
you3 liu2.2 bian4 xi1 mian3.5 li4.1 wei4 you2.2 da4 yi3.1 sa4 jia1.11
xi1 bu4.3 lun2.1 bian4 ya3 min3.3 dan4 na2 fu2.14 ta1 li4.1 jia1.11 de2
ya4.1 she4.2 =
fan2 cong2 ya3 ge4.1 er2.1 sheng1 de5 gong4 you3 qi1 shi2.1 ren2 yue1
se4.2 yi3 jing1 zai4 ai1.3 ji2.1 =
yue1 se4.2 he2 ta1 de5 di4.1 xiong1 bing4.1 nei4 yi1 dai4.3 de5 ren2
dou1 si3 le5 =
yi3.1 se4 lie4 ren2 sheng1 yang3 zhong4 duo1 bing4.1 qie3 fan2.2 mao4.3
ji2.3 qi2 qiang2 sheng4.2 man3 le5 nei4 di4 =
you3 bu4 ren4 shi5 yue1 se4.2 de5 xin1.1 wang2 qi3 lai2 zhi4.2 li3.1
ai1.3 ji2.1 dui4 ta1 de5 bai3 xing4.2 shuo1 kan4 na3 zhei4 yi3.1 se4
lie4 min2 bi3 wo3 men5 hai2 duo1 you4 bi3 wo3 men5 qiang2 sheng4.2 =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
de5 yan3 qian2 zai4 ta1 men5 suo3 xing2 de5 lu4 shang4 dou1 shi4 zhei4
yang4 =
removed 'dat/chin/ptt/exo.1/raw.wfr'
creating the word frequency file dat/chin/ptt/exo.1/raw.wfr
the 10 most common words in dat/chin/ptt/exo.1/raw.tlw:
1803 0.04972 de5
1011 0.02788 =
744 0.02052 he2
726 0.02002 ni3
649 0.01790 ta1
614 0.01693 men5
596 0.01644 yao4
532 0.01467 zai4
504 0.01390 wo3
483 0.01332 zi5
removed 'dat/chin/ptt/exo.1/raw-whole-wds-summary.tex'
removed 'exp/chin/ptt/exo.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/chin/ptt/exo.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:31:01 by tex-make-sample-summary.sh
% Token and word counts for chin/ptt/exo.1/raw.wfr
%
\def\chinpttwholeexoPBrawTks{36263}
\def\chinpttwholeexoPBrawTksPct{100.0}
\def\chinpttwholeexoPBrawWds{1425}
\def\chinpttwholeexoPBrawWdsPct{3.9}
copied '/tmp/570884.file' -> 'exp/chin/ptt/exo.1/raw-whole-wds-summary.tex'
removed '/tmp/570884.file'
creating running text file dat/chin/ptt/exo.1/gud.wdf
sample:
yi3.1 se4 lie4 de5 zhong4 zi5 ge4.1 dai4.1 jia1 juan4.1 he2 ya3 ge4.1
yi1 tong2 lai2 dao4.1 ai1.3 ji2.1 ta1 men5 de5 ming2.1 zi4.1 ji4.1 zai4
xia4 mian4 you3 liu2.2 bian4 xi1 mian3.5 li4.1 wei4 you2.2 da4 yi3.1 sa4
jia1.11 xi1 bu4.3 lun2.1 bian4 ya3 min3.3 dan4 na2 fu2.14 ta1 li4.1
jia1.11 de2 ya4.1 she4.2 fan2 cong2 ya3 ge4.1 er2.1 sheng1 de5 gong4
you3 qi1 shi2.1 ren2 yue1 se4.2 yi3 jing1 zai4 ai1.3 ji2.1 yue1 se4.2
he2 ta1 de5 di4.1 xiong1 bing4.1 nei4 yi1 dai4.3 de5 ren2 dou1 si3 le5
yi3.1 se4 lie4 ren2 sheng1 yang3 zhong4 duo1 bing4.1 qie3 fan2.2 mao4.3
ji2.3 qi2 qiang2 sheng4.2 man3 le5 nei4 di4 you3 bu4 ren4 shi5 yue1
se4.2 de5 xin1.1 wang2 qi3 lai2 zhi4.2 li3.1 ai1.3 ji2.1 dui4 ta1 de5
bai3 xing4.2 shuo1 kan4 na3 zhei4 yi3.1 se4 lie4 min2 bi3 wo3 men5 hai2
duo1 you4 bi3 wo3 men5 qiang2 sheng4.2 lai2 ba5 wo3 men5 bu4 ru2 yong4
qiao3.1 ji4.2 dai4.2 ta1 men5 kong3 pa4 ta1 men5 duo1 qi3 lai2 ri4
hou4.1 ruo4 yu4.2 shen2 me5 zheng1.1 zhan4.2 de5 shi4.1 jiu4 lian2 he2.2
wo3 men5 de5 chou2.2 di2.2 gong1.7 ji1.6 wo3 men5 li2 kai1 zhei4 di4 qu4
le5 yu2 shi4 ai1.3 ji2.1 ren2 pai4 du1.1 gong1.1 de5 xia2.4 zhi4.4 ta1
men5 jia1.1 zhong4.1 dan1.3 ku3 hai4 ta1 men5 ta1 men5 wei2 fa3 lao3
jian4.9 zao4 liang3 zuo4.3 ji1.5 huo4.2 cheng2.1 jiu4 shi4 bi3 dong1 he2
lan2 sai4 zhi3 shi4 yue4.1 fa1 ku3 hai4 ta1 men5 ta1 men5 yue4.1 fa1
duo1 qi3 lai2 yue4.1 fa1 man4.3 yan2.4 ai1.3 ji2.1 ren2 jiu4 yin1 yi3.1
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
shi4 zai4 zhang4.1 mu4.4 yi3.1 shang4 ye4 jian1 yun2 zhong1 you3 huo3
zai4 yi3.1 se4 lie4 quan2 jia1 de5 yan3 qian2 zai4 ta1 men5 suo3 xing2
de5 lu4 shang4 dou1 shi4 zhei4 yang4
removed 'dat/chin/ptt/exo.1/gud.wfr'
creating the word frequency file dat/chin/ptt/exo.1/gud.wfr
the 10 most common words in dat/chin/ptt/exo.1/gud.tlw:
1803 0.05115 de5
744 0.02111 he2
726 0.02059 ni3
649 0.01841 ta1
614 0.01742 men5
596 0.01691 yao4
532 0.01509 zai4
504 0.01430 wo3
483 0.01370 zi5
451 0.01279 ren2
removed 'dat/chin/ptt/exo.1/gud-whole-wds-summary.tex'
removed 'exp/chin/ptt/exo.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/chin/ptt/exo.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:31:02 by tex-make-sample-summary.sh
% Token and word counts for chin/ptt/exo.1/gud.wfr
%
\def\chinpttwholeexoPBgudTks{35252}
\def\chinpttwholeexoPBgudTksPct{97.2}
\def\chinpttwholeexoPBgudWds{1424}
\def\chinpttwholeexoPBgudWdsPct{3.9}
copied '/tmp/570928.file' -> 'exp/chin/ptt/exo.1/gud-whole-wds-summary.tex'
removed '/tmp/570928.file'
creating running text file dat/chin/ptt/exo.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/chin/ptt/exo.1/bad.wfr'
creating the word frequency file dat/chin/ptt/exo.1/bad.wfr
the 10 most common words in dat/chin/ptt/exo.1/bad.tlw:
1011 1.00000 =
removed 'dat/chin/ptt/exo.1/bad-whole-wds-summary.tex'
removed 'exp/chin/ptt/exo.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/chin/ptt/exo.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:31:02 by tex-make-sample-summary.sh
% Token and word counts for chin/ptt/exo.1/bad.wfr
%
\def\chinpttwholeexoPBbadTks{1011}
\def\chinpttwholeexoPBbadTksPct{2.8}
\def\chinpttwholeexoPBbadWds{1}
\def\chinpttwholeexoPBbadWdsPct{0.0}
copied '/tmp/570972.file' -> 'exp/chin/ptt/exo.1/bad-whole-wds-summary.tex'
removed '/tmp/570972.file'
... creating word files dat/chin/ptt/num.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
37906 dat/chin/ptt/num.1/whole.tlw
removed 'dat/chin/ptt/num.1/raw.tlw'
removed 'dat/chin/ptt/num.1/gud.tlw'
removed 'dat/chin/ptt/num.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/chin/ptt/num.1/raw.wdf
sample:
yi3.1 se4 lie4 ren2 chu1 ai1.3 ji2.1 di4 hou4.1 di4.2 er4 nian2 er4 yue4
chu1.1 yi1 ri4 ye1 he2 hua2 zai4 xi1 nai3.1 de5 kuang4.1 ye3.1 hui4
mu4.4 zhong1 xiao3.1 yu4.7 mo2.3 xi1 shuo1 ni3 yao4 an4.1 yi3.1 se4 lie4
quan2 hui4 zhong4 de5 jia1 shi4.9 zong1 zu2.1 ren2 ming2.1 de5 shu4 mu4
ji4.2 suan4 suo3 you3 de5 nan2.1 ding1 =
fan2 yi3.1 se4 lie4 zhong1 cong2 er4 shi2.1 sui4.1 yi3.1 wai4 neng2 chu1
qu4 da3 zhang4.2 de5 ni3 he2 ya4.1 lun2.1 yao4 zhao4 ta1 men5 de5 jun1.1
dui4.2 shu4 dian3 =
mei3 zhi1.2 pai4 zhong1 bi4 you3 yi1 ren2 zuo4.2 ben3 zhi1.2 pai4 de5
zu2.1 zhang3 bang1 zhu4.2 ni3 men5 =
ta1 men5 de5 ming2.1 zi4.1 shu3 liu2.2 bian4 de5 you3 shi4.10 diu1 er3.5
de5 er2 zi5 yi3.1 li4.1 xu5 =
shu3 xi1 mian3.5 de5 you3 su1 li4.1 sha1.2 dai4.3 de5 er2 zi5 shi4.10
lu4 mie4.1 =
shu3 you2.2 da4 de5 you3 ya4.1 mi3 na2 da2.1 de5 er2 zi5 na2 shun4 =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
bian1 ye1 li4.1 ge1 dui4 mian4 jie4 zhe5 mo2.3 xi1 suo3 fen1.1 fu4.2
yi3.1 se4 lie4 ren2 de5 ming4 ling4 dian3.1 zhang1.1 =
removed 'dat/chin/ptt/num.1/raw.wfr'
creating the word frequency file dat/chin/ptt/num.1/raw.wfr
the 10 most common words in dat/chin/ptt/num.1/raw.tlw:
1993 0.05258 de5
1063 0.02804 =
703 0.01855 men5
661 0.01744 ta1
638 0.01683 ren2
630 0.01662 he2
525 0.01385 ni3
521 0.01374 yi3.1
500 0.01319 zai4
470 0.01240 yi1
removed 'dat/chin/ptt/num.1/raw-whole-wds-summary.tex'
removed 'exp/chin/ptt/num.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/chin/ptt/num.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:31:02 by tex-make-sample-summary.sh
% Token and word counts for chin/ptt/num.1/raw.wfr
%
\def\chinpttwholenumPBrawTks{37906}
\def\chinpttwholenumPBrawTksPct{100.0}
\def\chinpttwholenumPBrawWds{1304}
\def\chinpttwholenumPBrawWdsPct{3.4}
copied '/tmp/571026.file' -> 'exp/chin/ptt/num.1/raw-whole-wds-summary.tex'
removed '/tmp/571026.file'
creating running text file dat/chin/ptt/num.1/gud.wdf
sample:
yi3.1 se4 lie4 ren2 chu1 ai1.3 ji2.1 di4 hou4.1 di4.2 er4 nian2 er4 yue4
chu1.1 yi1 ri4 ye1 he2 hua2 zai4 xi1 nai3.1 de5 kuang4.1 ye3.1 hui4
mu4.4 zhong1 xiao3.1 yu4.7 mo2.3 xi1 shuo1 ni3 yao4 an4.1 yi3.1 se4 lie4
quan2 hui4 zhong4 de5 jia1 shi4.9 zong1 zu2.1 ren2 ming2.1 de5 shu4 mu4
ji4.2 suan4 suo3 you3 de5 nan2.1 ding1 fan2 yi3.1 se4 lie4 zhong1 cong2
er4 shi2.1 sui4.1 yi3.1 wai4 neng2 chu1 qu4 da3 zhang4.2 de5 ni3 he2
ya4.1 lun2.1 yao4 zhao4 ta1 men5 de5 jun1.1 dui4.2 shu4 dian3 mei3
zhi1.2 pai4 zhong1 bi4 you3 yi1 ren2 zuo4.2 ben3 zhi1.2 pai4 de5 zu2.1
zhang3 bang1 zhu4.2 ni3 men5 ta1 men5 de5 ming2.1 zi4.1 shu3 liu2.2
bian4 de5 you3 shi4.10 diu1 er3.5 de5 er2 zi5 yi3.1 li4.1 xu5 shu3 xi1
mian3.5 de5 you3 su1 li4.1 sha1.2 dai4.3 de5 er2 zi5 shi4.10 lu4 mie4.1
shu3 you2.2 da4 de5 you3 ya4.1 mi3 na2 da2.1 de5 er2 zi5 na2 shun4 shu3
yi3.1 sa4 jia1.11 de5 you3 su1 ya1.3 de5 er2 zi5 na2 tan3.1 ye4.1 shu3
xi1 bu4.3 lun2.1 de5 you3 xi1.5 lun2.1 de5 er2 zi5 yi3.1 li4.1 ya1.3
yue1 se4.2 zi5 sun1 shu3 yi3.1 fa3 lian2.3 de5 you3 ya4.1 mi3 hu1 de5
er2 zi5 yi3.1 li4.1 sha1.2 ma3.1 shu3 ma3.1 na2 xi1 de5 you3 bi3 da4 xu5
de5 er2 zi5 jia1.11 ma3.1 lie4 shu3 bian4 ya3 min3.3 de5 you3 ji1.7 duo1
ni2.2 de5 er2 zi5 ya4.1 bi3 dan4 shu3 dan4 de5 you3 ya4.1 mi3 sha1.2
dai4.3 de5 er2 zi5 ya4.1 xi1.5 yi3.1 xie4 shu3 ya4.1 she4.2 de5 you3
e2.6 lan2 de5 er2 zi5 pa4.1 jie2 shu3 jia1.11 de2 de5 you3 diu1 er3.5
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
ping2 yuan2 yue1 dan4.3 he2.5 bian1 ye1 li4.1 ge1 dui4 mian4 jie4 zhe5
mo2.3 xi1 suo3 fen1.1 fu4.2 yi3.1 se4 lie4 ren2 de5 ming4 ling4 dian3.1
zhang1.1
removed 'dat/chin/ptt/num.1/gud.wfr'
creating the word frequency file dat/chin/ptt/num.1/gud.wfr
the 10 most common words in dat/chin/ptt/num.1/gud.tlw:
1993 0.05409 de5
703 0.01908 men5
661 0.01794 ta1
638 0.01732 ren2
630 0.01710 he2
525 0.01425 ni3
521 0.01414 yi3.1
500 0.01357 zai4
470 0.01276 yi1
449 0.01219 yao4
removed 'dat/chin/ptt/num.1/gud-whole-wds-summary.tex'
removed 'exp/chin/ptt/num.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/chin/ptt/num.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:31:02 by tex-make-sample-summary.sh
% Token and word counts for chin/ptt/num.1/gud.wfr
%
\def\chinpttwholenumPBgudTks{36843}
\def\chinpttwholenumPBgudTksPct{97.2}
\def\chinpttwholenumPBgudWds{1303}
\def\chinpttwholenumPBgudWdsPct{3.4}
copied '/tmp/571070.file' -> 'exp/chin/ptt/num.1/gud-whole-wds-summary.tex'
removed '/tmp/571070.file'
creating running text file dat/chin/ptt/num.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/chin/ptt/num.1/bad.wfr'
creating the word frequency file dat/chin/ptt/num.1/bad.wfr
the 10 most common words in dat/chin/ptt/num.1/bad.tlw:
1063 1.00000 =
removed 'dat/chin/ptt/num.1/bad-whole-wds-summary.tex'
removed 'exp/chin/ptt/num.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/chin/ptt/num.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:31:02 by tex-make-sample-summary.sh
% Token and word counts for chin/ptt/num.1/bad.wfr
%
\def\chinpttwholenumPBbadTks{1063}
\def\chinpttwholenumPBbadTksPct{2.8}
\def\chinpttwholenumPBbadWds{1}
\def\chinpttwholenumPBbadWdsPct{0.0}
copied '/tmp/571114.file' -> 'exp/chin/ptt/num.1/bad-whole-wds-summary.tex'
removed '/tmp/571114.file'
... creating word files dat/chin/ptt/lev.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
26404 dat/chin/ptt/lev.1/whole.tlw
removed 'dat/chin/ptt/lev.1/raw.tlw'
removed 'dat/chin/ptt/lev.1/gud.tlw'
removed 'dat/chin/ptt/lev.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/chin/ptt/lev.1/raw.wdf
sample:
ye1 he2 hua2 cong2 hui4 mu4.4 zhong1 hu1.1 jiao4 mo2.3 xi1 dui4 ta1
shuo1 ni3 xiao3.1 yu4.7 yi3.1 se4 lie4 ren2 shuo1 ni3 men5 zhong1 jian1
ruo4 you3 ren2 xian4.4 gong1.4 wu4 ji3.1 ye1 he2 hua2 yao4 cong2 niu2
qun2.1 yang2.3 qun2.1 zhong1 xian4.4 sheng1.5 chu4.1 wei2 gong1.4 wu4 =
ta1 de5 gong1.4 wu4 ruo4 yi3.1 niu2 wei2 fan2.6 ji4.4 jiu4 yao4 zai4
hui4 mu4.4 men2 kou3 xian4.4 yi1 zhi3 mei2 you3 can2 ji2.5 de5 gong1
niu2 ke3 yi3.1 zai4 ye1 he2 hua2 mian4 qian2 meng3 yue4.2 na4 =
ta1 yao4 an4.1 shou3 zai4 fan2.6 ji4.4 sheng1.5 de5 tou2 shang4 fan2.6
ji4.4 bian4 meng3 yue4.2 na4 wei2 ta1 shu2.1 zui4 =
ta1 yao4 zai4 ye1 he2 hua2 mian4 qian2 zai3.2 gong1 niu2 ya4.1 lun2.1
zi5 sun1 zuo4.2 ji4.4 si1.1 de5 yao4 feng4.1 shang4 xue4 ba3 xue4 sa3
zai4 hui4 mu4.4 men2 kou3 tan2.2 de5 zhou1 wei2.2 =
nei4 ren2 yao4 bo1.3 qu4 fan2.6 ji4.4 sheng1.5 de5 pi2 ba3 fan2.6 ji4.4
sheng1.5 qie4 cheng2 kuai4.1 zi5 =
ji4.4 si1.1 ya4.1 lun2.1 de5 zi5 sun1 yao4 ba3 huo3 fang4 zai4 tan2.2
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
zhei4 jiu4 shi4 ye1 he2 hua2 zai4 xi1 nai3.1 shan1 wei2 yi3.1 se4 lie4
ren2 suo3 fen1.1 fu4.2 mo2.3 xi1 de5 ming4 ling4 =
removed 'dat/chin/ptt/lev.1/raw.wfr'
creating the word frequency file dat/chin/ptt/lev.1/raw.wfr
the 10 most common words in dat/chin/ptt/lev.1/raw.tlw:
1463 0.05541 de5
710 0.02689 =
641 0.02428 yao4
508 0.01924 shi4
480 0.01818 ji4.4
475 0.01799 he2
473 0.01791 ni3
448 0.01697 men5
440 0.01666 zai4
435 0.01647 ta1
removed 'dat/chin/ptt/lev.1/raw-whole-wds-summary.tex'
removed 'exp/chin/ptt/lev.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/chin/ptt/lev.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:31:02 by tex-make-sample-summary.sh
% Token and word counts for chin/ptt/lev.1/raw.wfr
%
\def\chinpttwholelevPBrawTks{26404}
\def\chinpttwholelevPBrawTksPct{100.0}
\def\chinpttwholelevPBrawWds{1096}
\def\chinpttwholelevPBrawWdsPct{4.2}
copied '/tmp/571168.file' -> 'exp/chin/ptt/lev.1/raw-whole-wds-summary.tex'
removed '/tmp/571168.file'
creating running text file dat/chin/ptt/lev.1/gud.wdf
sample:
ye1 he2 hua2 cong2 hui4 mu4.4 zhong1 hu1.1 jiao4 mo2.3 xi1 dui4 ta1
shuo1 ni3 xiao3.1 yu4.7 yi3.1 se4 lie4 ren2 shuo1 ni3 men5 zhong1 jian1
ruo4 you3 ren2 xian4.4 gong1.4 wu4 ji3.1 ye1 he2 hua2 yao4 cong2 niu2
qun2.1 yang2.3 qun2.1 zhong1 xian4.4 sheng1.5 chu4.1 wei2 gong1.4 wu4
ta1 de5 gong1.4 wu4 ruo4 yi3.1 niu2 wei2 fan2.6 ji4.4 jiu4 yao4 zai4
hui4 mu4.4 men2 kou3 xian4.4 yi1 zhi3 mei2 you3 can2 ji2.5 de5 gong1
niu2 ke3 yi3.1 zai4 ye1 he2 hua2 mian4 qian2 meng3 yue4.2 na4 ta1 yao4
an4.1 shou3 zai4 fan2.6 ji4.4 sheng1.5 de5 tou2 shang4 fan2.6 ji4.4
bian4 meng3 yue4.2 na4 wei2 ta1 shu2.1 zui4 ta1 yao4 zai4 ye1 he2 hua2
mian4 qian2 zai3.2 gong1 niu2 ya4.1 lun2.1 zi5 sun1 zuo4.2 ji4.4 si1.1
de5 yao4 feng4.1 shang4 xue4 ba3 xue4 sa3 zai4 hui4 mu4.4 men2 kou3
tan2.2 de5 zhou1 wei2.2 nei4 ren2 yao4 bo1.3 qu4 fan2.6 ji4.4 sheng1.5
de5 pi2 ba3 fan2.6 ji4.4 sheng1.5 qie4 cheng2 kuai4.1 zi5 ji4.4 si1.1
ya4.1 lun2.1 de5 zi5 sun1 yao4 ba3 huo3 fang4 zai4 tan2.2 shang4 ba3
chai2 bai3.1 zai4 huo3 shang4 ya4.1 lun2.1 zi5 sun1 zuo4.2 ji4.4 si1.1
de5 yao4 ba3 rou4 kuai4.1 he2 tou2 bing4.1 zhi1.4 you2.4 bai3.1 zai4
tan2.2 shang4 huo3 de5 chai2 shang4 dan4 fan2.6 ji4.4 de5 zang4.2 fu3.7
yu3 tui3 yao4 yong4 shui3 xi3.1 ji4.4 si1.1 jiu4 yao4 ba3 yi1 qie4 quan2
shao1 zai4 tan2.2 shang4 dang1 zuo4.2 fan2.6 ji4.4 xian4.4 yu3 ye1 he2
hua2 wei2 xin1.8 xiang1 de5 huo3 ji4.4 ren2 de5 gong1.4 wu4 ruo4 yi3.1
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
de5 yu3 ben3 lai2 de5 sheng1.5 chu4.1 dou1 yao4 cheng2 wei2 sheng4.1 bu4
ke3 shu2.1 hui2 zhei4 jiu4 shi4 ye1 he2 hua2 zai4 xi1 nai3.1 shan1 wei2
yi3.1 se4 lie4 ren2 suo3 fen1.1 fu4.2 mo2.3 xi1 de5 ming4 ling4
removed 'dat/chin/ptt/lev.1/gud.wfr'
creating the word frequency file dat/chin/ptt/lev.1/gud.wfr
the 10 most common words in dat/chin/ptt/lev.1/gud.tlw:
1463 0.05694 de5
641 0.02495 yao4
508 0.01977 shi4
480 0.01868 ji4.4
475 0.01849 he2
473 0.01841 ni3
448 0.01744 men5
440 0.01712 zai4
435 0.01693 ta1
409 0.01592 bu4
removed 'dat/chin/ptt/lev.1/gud-whole-wds-summary.tex'
removed 'exp/chin/ptt/lev.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/chin/ptt/lev.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:31:02 by tex-make-sample-summary.sh
% Token and word counts for chin/ptt/lev.1/gud.wfr
%
\def\chinpttwholelevPBgudTks{25694}
\def\chinpttwholelevPBgudTksPct{97.3}
\def\chinpttwholelevPBgudWds{1095}
\def\chinpttwholelevPBgudWdsPct{4.1}
copied '/tmp/571212.file' -> 'exp/chin/ptt/lev.1/gud-whole-wds-summary.tex'
removed '/tmp/571212.file'
creating running text file dat/chin/ptt/lev.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/chin/ptt/lev.1/bad.wfr'
creating the word frequency file dat/chin/ptt/lev.1/bad.wfr
the 10 most common words in dat/chin/ptt/lev.1/bad.tlw:
710 1.00000 =
removed 'dat/chin/ptt/lev.1/bad-whole-wds-summary.tex'
removed 'exp/chin/ptt/lev.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/chin/ptt/lev.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:31:02 by tex-make-sample-summary.sh
% Token and word counts for chin/ptt/lev.1/bad.wfr
%
\def\chinpttwholelevPBbadTks{710}
\def\chinpttwholelevPBbadTksPct{2.7}
\def\chinpttwholelevPBbadWds{1}
\def\chinpttwholelevPBbadWdsPct{0.0}
copied '/tmp/571256.file' -> 'exp/chin/ptt/lev.1/bad-whole-wds-summary.tex'
removed '/tmp/571256.file'
... creating word files dat/chin/ptt/deu.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
32282 dat/chin/ptt/deu.1/whole.tlw
removed 'dat/chin/ptt/deu.1/raw.tlw'
removed 'dat/chin/ptt/deu.1/gud.tlw'
removed 'dat/chin/ptt/deu.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/chin/ptt/deu.1/raw.wdf
sample:
yi3.1 xia4 suo3 ji4.1 de5 shi4 mo2.3 xi1 zai4 yue1 dan4.3 he2.5 dong1
de5 kuang4.1 ye3.1 shu1.3 fu2.14 dui4 mian4 de5 ya4.1 la1 ba1.1 jiu4
shi4 ba1.1 lan2 tuo2 fu2.14 la1 ban1.1 ha1 xi3.1 lu4.3 di3 sa1 ha1
zhong1 jian1 xiang4 yi3.1 se4 lie4 zhong4 ren2 suo3 shuo1 de5 hua4 =
cong2 he2.1 lie4.1 shan1 jing1 guo4 xi1 er3.5 shan1 dao4.1 jia1.1 di1
si1.6 ba1.1 ni2.2 ya4.1 you3 shi2.1 yi1 tian1 de5 lu4 cheng2.5 =
chu1 ai1.3 ji2.1 di4.2 si4 shi2.1 nian2 shi2.1 yi1 yue4 chu1.1 yi1 ri4
mo2.3 xi1 zhao4 ye1 he2 hua2 jie4 zhe5 ta1 suo3 fen1.1 fu4.2 yi3.1 se4
lie4 ren2 de5 hua4 dou1 xiao3.1 yu4.7 ta1 men5 =
nei4 shi2 ta1 yi3 jing1 ji1.6 sha1.1 le5 zhu4.1 xi1.5 shi2.2 ben3 de5
ya4.1 mo2.3 li4.1 wang2 xi1 hong2.3 he2 zhu4.1 yi3.1 de2 lai2 ya4.1
si1.6 ta1 lu4.3 de5 ba1.1 shan1.4 wang2 e4.8 =
mo2.3 xi1 zai4 yue1 dan4.3 he2.5 dong1 de5 mo2.3 ya1.3 di4 jiang3 lü4.1
fa3 shuo1 ye1 he2 hua2 wo3 men5 de5 shen2.1 zai4 he2.1 lie4.1 shan1
xiao3.1 yu4.7 wo3 men5 shuo1 ni3 men5 zai4 zhei4 shan1 shang4 zhu4.1 de5
ri4 zi5 gou4.1 le5 =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
qian2 xian3 da4 neng2 de5 shou3 xing2 yi1 qie4 da4 er2.1 ke3 wei4.5 de5
shi4.1 =
removed 'dat/chin/ptt/deu.1/raw.wfr'
creating the word frequency file dat/chin/ptt/deu.1/raw.wfr
the 10 most common words in dat/chin/ptt/deu.1/raw.tlw:
1738 0.05384 de5
1650 0.05111 ni3
847 0.02624 men5
788 0.02441 =
718 0.02224 ta1
684 0.02119 he2
545 0.01688 ye1
536 0.01660 hua2
488 0.01512 zai4
449 0.01391 suo3
removed 'dat/chin/ptt/deu.1/raw-whole-wds-summary.tex'
removed 'exp/chin/ptt/deu.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/chin/ptt/deu.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:31:02 by tex-make-sample-summary.sh
% Token and word counts for chin/ptt/deu.1/raw.wfr
%
\def\chinpttwholedeuPBrawTks{32282}
\def\chinpttwholedeuPBrawTksPct{100.0}
\def\chinpttwholedeuPBrawWds{1434}
\def\chinpttwholedeuPBrawWdsPct{4.4}
copied '/tmp/571310.file' -> 'exp/chin/ptt/deu.1/raw-whole-wds-summary.tex'
removed '/tmp/571310.file'
creating running text file dat/chin/ptt/deu.1/gud.wdf
sample:
yi3.1 xia4 suo3 ji4.1 de5 shi4 mo2.3 xi1 zai4 yue1 dan4.3 he2.5 dong1
de5 kuang4.1 ye3.1 shu1.3 fu2.14 dui4 mian4 de5 ya4.1 la1 ba1.1 jiu4
shi4 ba1.1 lan2 tuo2 fu2.14 la1 ban1.1 ha1 xi3.1 lu4.3 di3 sa1 ha1
zhong1 jian1 xiang4 yi3.1 se4 lie4 zhong4 ren2 suo3 shuo1 de5 hua4 cong2
he2.1 lie4.1 shan1 jing1 guo4 xi1 er3.5 shan1 dao4.1 jia1.1 di1 si1.6
ba1.1 ni2.2 ya4.1 you3 shi2.1 yi1 tian1 de5 lu4 cheng2.5 chu1 ai1.3
ji2.1 di4.2 si4 shi2.1 nian2 shi2.1 yi1 yue4 chu1.1 yi1 ri4 mo2.3 xi1
zhao4 ye1 he2 hua2 jie4 zhe5 ta1 suo3 fen1.1 fu4.2 yi3.1 se4 lie4 ren2
de5 hua4 dou1 xiao3.1 yu4.7 ta1 men5 nei4 shi2 ta1 yi3 jing1 ji1.6
sha1.1 le5 zhu4.1 xi1.5 shi2.2 ben3 de5 ya4.1 mo2.3 li4.1 wang2 xi1
hong2.3 he2 zhu4.1 yi3.1 de2 lai2 ya4.1 si1.6 ta1 lu4.3 de5 ba1.1
shan1.4 wang2 e4.8 mo2.3 xi1 zai4 yue1 dan4.3 he2.5 dong1 de5 mo2.3
ya1.3 di4 jiang3 lü4.1 fa3 shuo1 ye1 he2 hua2 wo3 men5 de5 shen2.1 zai4
he2.1 lie4.1 shan1 xiao3.1 yu4.7 wo3 men5 shuo1 ni3 men5 zai4 zhei4
shan1 shang4 zhu4.1 de5 ri4 zi5 gou4.1 le5 yao4 qi3 xing2 zhuan3 dao4.1
ya4.1 mo2.3 li4.1 ren2 de5 shan1 di4 he2 kao4 jin4.1 zhei4 shan1 di4 de5
ge4.1 chu3 jiu4 shi4 ya4.1 la1 ba1.1 shan1 di4 gao1 yuan2 nan2.2 di4
yan2.3 hai3 yi1 dai4.1 jia1.11 nan2.2 ren2 de5 di4 bing4.1 li4.1 ba1.1
nen4 shan1 you4 dao4.1 bo2.1 la1 da4 he2.5 ru2 jin1 wo3 jiang1 zhei4 di4
bai3.1 zai4 ni3 men5 mian4 qian2 ni3 men5 yao4 jin4 qu4 de2 zhei4 di4
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
yang4 shen2.1 ji1.2 qi2.2 shi4.1 you4 zai4 yi3.1 se4 lie4 zhong4 ren2
yan3 qian2 xian3 da4 neng2 de5 shou3 xing2 yi1 qie4 da4 er2.1 ke3 wei4.5
de5 shi4.1
removed 'dat/chin/ptt/deu.1/gud.wfr'
creating the word frequency file dat/chin/ptt/deu.1/gud.wfr
the 10 most common words in dat/chin/ptt/deu.1/gud.tlw:
1738 0.05519 de5
1650 0.05239 ni3
847 0.02689 men5
718 0.02280 ta1
684 0.02172 he2
545 0.01730 ye1
536 0.01702 hua2
488 0.01550 zai4
449 0.01426 suo3
436 0.01384 wo3
removed 'dat/chin/ptt/deu.1/gud-whole-wds-summary.tex'
removed 'exp/chin/ptt/deu.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/chin/ptt/deu.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:31:02 by tex-make-sample-summary.sh
% Token and word counts for chin/ptt/deu.1/gud.wfr
%
\def\chinpttwholedeuPBgudTks{31494}
\def\chinpttwholedeuPBgudTksPct{97.6}
\def\chinpttwholedeuPBgudWds{1433}
\def\chinpttwholedeuPBgudWdsPct{4.4}
copied '/tmp/571354.file' -> 'exp/chin/ptt/deu.1/gud-whole-wds-summary.tex'
removed '/tmp/571354.file'
creating running text file dat/chin/ptt/deu.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/chin/ptt/deu.1/bad.wfr'
creating the word frequency file dat/chin/ptt/deu.1/bad.wfr
the 10 most common words in dat/chin/ptt/deu.1/bad.tlw:
788 1.00000 =
removed 'dat/chin/ptt/deu.1/bad-whole-wds-summary.tex'
removed 'exp/chin/ptt/deu.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/chin/ptt/deu.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:31:02 by tex-make-sample-summary.sh
% Token and word counts for chin/ptt/deu.1/bad.wfr
%
\def\chinpttwholedeuPBbadTks{788}
\def\chinpttwholedeuPBbadTksPct{2.4}
\def\chinpttwholedeuPBbadWds{1}
\def\chinpttwholedeuPBbadWdsPct{0.0}
copied '/tmp/571398.file' -> 'exp/chin/ptt/deu.1/bad-whole-wds-summary.tex'
removed '/tmp/571398.file'
... creating word files dat/chin/ptt/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
179252 dat/chin/ptt/tot.1/whole.tlw
removed 'dat/chin/ptt/tot.1/raw.tlw'
removed 'dat/chin/ptt/tot.1/gud.tlw'
removed 'dat/chin/ptt/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/chin/ptt/tot.1/raw.wdf
sample:
qi3 chu1.1 shen2.1 chuang4 zao4 tian1 di4 =
di4 shi4 kong1 xu1.1 hun4 dun4.5 yuan1.2 mian4 hei1 an4 shen2.1 de5
ling2.1 yun4.1 xing2 zai4 shui3 mian4 shang4 =
shen2.1 shuo1 yao4 you3 guang1 jiu4 you3 le5 guang1 =
shen2.1 kan4 guang1 shi4 hao3 de5 jiu4 ba3 guang1 an4 fen1 kai1 le5 =
shen2.1 cheng1 guang1 wei2 zhou4.1 cheng1 an4 wei2 ye4 you3 wan3 shang4
you3 zao3 chen2.5 zhei4 shi4 tou2 yi1 ri4 =
shen2.1 shuo1 zhu1.1 shui3 zhi1.1 jian1 yao4 you3 kong1 qi4 jiang1 shui3
fen1 wei2 shang4 xia4 =
shen2.1 jiu4 zao4 chu1 kong1 qi4 jiang1 kong1 qi4 yi3.1 xia4 de5 shui3
kong1 qi4 yi3.1 shang4 de5 shui3 fen1 kai1 le5 shi4.1 jiu4 zhei4 yang4
cheng2 le5 =
shen2.1 cheng1 kong1 qi4 wei2 tian1 you3 wan3 shang4 you3 zao3 chen2.5
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
qian2 xian3 da4 neng2 de5 shou3 xing2 yi1 qie4 da4 er2.1 ke3 wei4.5 de5
shi4.1 =
removed 'dat/chin/ptt/tot.1/raw.wfr'
creating the word frequency file dat/chin/ptt/tot.1/raw.wfr
the 10 most common words in dat/chin/ptt/tot.1/raw.tlw:
9060 0.05054 de5
4888 0.02727 =
4367 0.02436 ni3
3620 0.02020 ta1
3427 0.01912 men5
2989 0.01667 he2
2663 0.01486 wo3
2657 0.01482 zai4
2404 0.01341 yao4
2399 0.01338 ren2
removed 'dat/chin/ptt/tot.1/raw-whole-wds-summary.tex'
removed 'exp/chin/ptt/tot.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/chin/ptt/tot.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:31:03 by tex-make-sample-summary.sh
% Token and word counts for chin/ptt/tot.1/raw.wfr
%
\def\chinpttwholetotPBrawTks{179252}
\def\chinpttwholetotPBrawTksPct{100.0}
\def\chinpttwholetotPBrawWds{2178}
\def\chinpttwholetotPBrawWdsPct{1.2}
copied '/tmp/571452.file' -> 'exp/chin/ptt/tot.1/raw-whole-wds-summary.tex'
removed '/tmp/571452.file'
creating running text file dat/chin/ptt/tot.1/gud.wdf
sample:
qi3 chu1.1 shen2.1 chuang4 zao4 tian1 di4 di4 shi4 kong1 xu1.1 hun4
dun4.5 yuan1.2 mian4 hei1 an4 shen2.1 de5 ling2.1 yun4.1 xing2 zai4
shui3 mian4 shang4 shen2.1 shuo1 yao4 you3 guang1 jiu4 you3 le5 guang1
shen2.1 kan4 guang1 shi4 hao3 de5 jiu4 ba3 guang1 an4 fen1 kai1 le5
shen2.1 cheng1 guang1 wei2 zhou4.1 cheng1 an4 wei2 ye4 you3 wan3 shang4
you3 zao3 chen2.5 zhei4 shi4 tou2 yi1 ri4 shen2.1 shuo1 zhu1.1 shui3
zhi1.1 jian1 yao4 you3 kong1 qi4 jiang1 shui3 fen1 wei2 shang4 xia4
shen2.1 jiu4 zao4 chu1 kong1 qi4 jiang1 kong1 qi4 yi3.1 xia4 de5 shui3
kong1 qi4 yi3.1 shang4 de5 shui3 fen1 kai1 le5 shi4.1 jiu4 zhei4 yang4
cheng2 le5 shen2.1 cheng1 kong1 qi4 wei2 tian1 you3 wan3 shang4 you3
zao3 chen2.5 shi4 di4.2 er4 ri4 shen2.1 shuo1 tian1 xia4 de5 shui3 yao4
ju4.3 zai4 yi1 chu3 shi3 han4.4 di4 lu4.1 chu1 lai2 shi4.1 jiu4 zhei4
yang4 cheng2 le5 shen2.1 cheng1 han4.4 di4 wei2 di4 cheng1 shui3 de5
ju4.3 chu3 wei2 hai3 shen2.1 kan4 zhe5 shi4 hao3 de5 shen2.1 shuo1 di4
yao4 fa1 sheng1 qing1.2 cao3 he2 jie2 zhong3 zi5 de5 cai4 shu1.6 bing4.1
jie2 guo3 zi5 de5 shu4.2 mu4.1 ge4.1 cong2 qi2 lei4.1 guo3 zi5 dou1 bao1
zhe5 he2.6 shi4.1 jiu4 zhei4 yang4 cheng2 le5 yu2 shi4 di4 fa1 sheng1
le5 qing1.2 cao3 he2 jie2 zhong3 zi5 de5 cai4 shu1.6 ge4.1 cong2 qi2
lei4.1 bing4.1 jie2 guo3 zi5 de5 shu4.2 mu4.1 ge4.1 cong2 qi2 lei4.1
guo3 zi5 dou1 bao1 zhe5 he2.6 shen2.1 kan4 zhe5 shi4 hao3 de5 you3 wan3
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
yang4 shen2.1 ji1.2 qi2.2 shi4.1 you4 zai4 yi3.1 se4 lie4 zhong4 ren2
yan3 qian2 xian3 da4 neng2 de5 shou3 xing2 yi1 qie4 da4 er2.1 ke3 wei4.5
de5 shi4.1
removed 'dat/chin/ptt/tot.1/gud.wfr'
creating the word frequency file dat/chin/ptt/tot.1/gud.wfr
the 10 most common words in dat/chin/ptt/tot.1/gud.tlw:
9060 0.05196 de5
4367 0.02505 ni3
3620 0.02076 ta1
3427 0.01965 men5
2989 0.01714 he2
2663 0.01527 wo3
2657 0.01524 zai4
2404 0.01379 yao4
2399 0.01376 ren2
2256 0.01294 shi4
removed 'dat/chin/ptt/tot.1/gud-whole-wds-summary.tex'
removed 'exp/chin/ptt/tot.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/chin/ptt/tot.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:31:03 by tex-make-sample-summary.sh
% Token and word counts for chin/ptt/tot.1/gud.wfr
%
\def\chinpttwholetotPBgudTks{174364}
\def\chinpttwholetotPBgudTksPct{97.3}
\def\chinpttwholetotPBgudWds{2177}
\def\chinpttwholetotPBgudWdsPct{1.2}
copied '/tmp/571496.file' -> 'exp/chin/ptt/tot.1/gud-whole-wds-summary.tex'
removed '/tmp/571496.file'
creating running text file dat/chin/ptt/tot.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/chin/ptt/tot.1/bad.wfr'
creating the word frequency file dat/chin/ptt/tot.1/bad.wfr
the 10 most common words in dat/chin/ptt/tot.1/bad.tlw:
4888 1.00000 =
removed 'dat/chin/ptt/tot.1/bad-whole-wds-summary.tex'
removed 'exp/chin/ptt/tot.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/chin/ptt/tot.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:31:03 by tex-make-sample-summary.sh
% Token and word counts for chin/ptt/tot.1/bad.wfr
%
\def\chinpttwholetotPBbadTks{4888}
\def\chinpttwholetotPBbadTksPct{2.7}
\def\chinpttwholetotPBbadWds{1}
\def\chinpttwholetotPBbadWdsPct{0.0}
copied '/tmp/571540.file' -> 'exp/chin/ptt/tot.1/bad-whole-wds-summary.tex'
removed '/tmp/571540.file'
lines words bytes file
------- ------- --------- ------------
1504 4512 33445 dat/chin/ptt/gen.1/raw.wfr
1425 4275 31684 dat/chin/ptt/exo.1/raw.wfr
1304 3912 28938 dat/chin/ptt/num.1/raw.wfr
1096 3288 24272 dat/chin/ptt/lev.1/raw.wfr
1434 4302 31893 dat/chin/ptt/deu.1/raw.wfr
2178 6534 48759 dat/chin/ptt/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
1503 4509 33427 dat/chin/ptt/gen.1/gud.wfr
1424 4272 31666 dat/chin/ptt/exo.1/gud.wfr
1303 3909 28920 dat/chin/ptt/num.1/gud.wfr
1095 3285 24254 dat/chin/ptt/lev.1/gud.wfr
1433 4299 31875 dat/chin/ptt/deu.1/gud.wfr
2177 6531 48741 dat/chin/ptt/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
1 3 18 dat/chin/ptt/gen.1/bad.wfr
1 3 18 dat/chin/ptt/exo.1/bad.wfr
1 3 18 dat/chin/ptt/num.1/bad.wfr
1 3 18 dat/chin/ptt/lev.1/bad.wfr
1 3 18 dat/chin/ptt/deu.1/bad.wfr
1 3 18 dat/chin/ptt/tot.1/bad.wfr
gen.1 raw = 46397 gud = 45081 bad = 1316
exo.1 raw = 36263 gud = 35252 bad = 1011
num.1 raw = 37906 gud = 36843 bad = 1063
lev.1 raw = 26404 gud = 25694 bad = 710
deu.1 raw = 32282 gud = 31494 bad = 788
tot.1 raw = 179252 gud = 174364 bad = 4888
=== creating the derived word files dat/chin/ptn/*/{raw,gud,bad}.{tlw,wdf,wfr} (whole) ===
... creating word files dat/chin/ptn/gen.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
50279 dat/chin/ptn/gen.1/whole.tlw
removed 'dat/chin/ptn/gen.1/raw.tlw'
removed 'dat/chin/ptn/gen.1/gud.tlw'
removed 'dat/chin/ptn/gen.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/chin/ptn/gen.1/raw.wdf
sample:
qi3 chu1.1 shen2.1 chuang4 zao4 tian1 di4 =
di4 shi4 kong1 xu1.1 hun4 dun4.5 shen1.1 yuan1.2 shang4 yi1 pian4 hei1
an4 shen2.1 de5 ling2.1 yun4.1 xing2 zai4 shui3 mian4 shang4 =
shen2.1 shuo1 yao4 you3 guang1 jiu4 you3 le5 guang1 =
shen2.1 kan4 guang1 shi4 hao3 de5 ta1 jiu4 ba3 guang1 an4 fen1 kai1 le5
=
shen2.1 cheng1 guang1 wei2 zhou4.1 cheng1 an4 wei2 ye4 you3 wan3 shang4
you3 zao3 chen2.5 zhei4 shi4 di4.2 yi1 ri4 =
shen2.1 shuo1 zhong4 shui3 zhi1.1 jian1 yao4 you3 qiong2.3 cang1 ba3
shui3 he2 shui3 fen1 kai1 shi4.1 jiu4 zhei4 yang4 cheng2 le5 =
shen2.1 zao4 le5 qiong2.3 cang1 ba3 qiong2.3 cang1 yi3.1 xia4 de5 shui3
he2 qiong2.3 cang1 yi3.1 shang4 de5 shui3 fen1 kai1 le5 =
shen2.1 cheng1 qiong2.3 cang1 wei2 tian1 you3 wan3 shang4 you3 zao3
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
bai3 yi1 shi2.1 sui4.1 ren2 yong4 xiang1 liao4 ba3 ta1 bao1 lian4.1 le5
fang4 zai4 guan1.4 cai2.2 li3 ting2 zai4 ai1.3 ji2.1 =
removed 'dat/chin/ptn/gen.1/raw.wfr'
creating the word frequency file dat/chin/ptn/gen.1/raw.wfr
the 10 most common words in dat/chin/ptn/gen.1/raw.tlw:
2481 0.04934 de5
1253 0.02492 ta1
1222 0.02430 wo3
1048 0.02084 ni3
974 0.01937 =
922 0.01834 men5
894 0.01778 le5
783 0.01557 zai4
714 0.01420 shi4
697 0.01386 ren2
removed 'dat/chin/ptn/gen.1/raw-whole-wds-summary.tex'
removed 'exp/chin/ptn/gen.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/chin/ptn/gen.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:31:03 by tex-make-sample-summary.sh
% Token and word counts for chin/ptn/gen.1/raw.wfr
%
\def\chinptnwholegenPBrawTks{50279}
\def\chinptnwholegenPBrawTksPct{100.0}
\def\chinptnwholegenPBrawWds{1556}
\def\chinptnwholegenPBrawWdsPct{3.1}
copied '/tmp/571710.file' -> 'exp/chin/ptn/gen.1/raw-whole-wds-summary.tex'
removed '/tmp/571710.file'
creating running text file dat/chin/ptn/gen.1/gud.wdf
sample:
qi3 chu1.1 shen2.1 chuang4 zao4 tian1 di4 di4 shi4 kong1 xu1.1 hun4
dun4.5 shen1.1 yuan1.2 shang4 yi1 pian4 hei1 an4 shen2.1 de5 ling2.1
yun4.1 xing2 zai4 shui3 mian4 shang4 shen2.1 shuo1 yao4 you3 guang1 jiu4
you3 le5 guang1 shen2.1 kan4 guang1 shi4 hao3 de5 ta1 jiu4 ba3 guang1
an4 fen1 kai1 le5 shen2.1 cheng1 guang1 wei2 zhou4.1 cheng1 an4 wei2 ye4
you3 wan3 shang4 you3 zao3 chen2.5 zhei4 shi4 di4.2 yi1 ri4 shen2.1
shuo1 zhong4 shui3 zhi1.1 jian1 yao4 you3 qiong2.3 cang1 ba3 shui3 he2
shui3 fen1 kai1 shi4.1 jiu4 zhei4 yang4 cheng2 le5 shen2.1 zao4 le5
qiong2.3 cang1 ba3 qiong2.3 cang1 yi3.1 xia4 de5 shui3 he2 qiong2.3
cang1 yi3.1 shang4 de5 shui3 fen1 kai1 le5 shen2.1 cheng1 qiong2.3 cang1
wei2 tian1 you3 wan3 shang4 you3 zao3 chen2.5 zhei4 shi4 di4.2 er4 ri4
shen2.1 shuo1 tian1 xia4 de5 shui3 yao4 ju4.3 zai4 yi1 chu3 shi3 han4.4
di4 lu4.1 chu1 lai2 shi4.1 jiu4 zhei4 yang4 cheng2 le5 shen2.1 cheng1
han4.4 di4 wei2 di4 cheng1 shui3 de5 ju4.3 chu3 wei2 hai3 shen2.1 kan4
zhei4 shi4 hao3 de5 shen2.1 shuo1 di4 shang4 yao4 zhang3 chu1 qing1.2
cao3 jie2 zhong3 zi5 de5 shu1.6 cai4 he2 jie2 guo3 zi5 de5 shu4.2 mu4.1
ge4.1 cong2 qi2 lei4.1 zai4 di4 shang4 de5 guo3 zi5 dou1 bao1 zhe5 he2.6
shi4.1 jiu4 zhei4 yang4 cheng2 le5 yu2 shi4 di4 shang4 zhang3 chu1 le5
qing1.2 cao3 he2 jie2 zhong3 zi5 de5 shu1.6 cai4 ge4.1 cong2 qi2 lei4.1
you4 zhang3 chu1 jie2 guo3 zi5 de5 shu4.2 mu4.1 ge4.1 cong2 qi2 lei4.1
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
se4.2 si3 le5 xiang3.2 shou4.1 yi1 bai3 yi1 shi2.1 sui4.1 ren2 yong4
xiang1 liao4 ba3 ta1 bao1 lian4.1 le5 fang4 zai4 guan1.4 cai2.2 li3
ting2 zai4 ai1.3 ji2.1
removed 'dat/chin/ptn/gen.1/gud.wfr'
creating the word frequency file dat/chin/ptn/gen.1/gud.wfr
the 10 most common words in dat/chin/ptn/gen.1/gud.tlw:
2481 0.05032 de5
1253 0.02541 ta1
1222 0.02478 wo3
1048 0.02126 ni3
922 0.01870 men5
894 0.01813 le5
783 0.01588 zai4
714 0.01448 shi4
697 0.01414 ren2
622 0.01262 yi3.1
removed 'dat/chin/ptn/gen.1/gud-whole-wds-summary.tex'
removed 'exp/chin/ptn/gen.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/chin/ptn/gen.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:31:03 by tex-make-sample-summary.sh
% Token and word counts for chin/ptn/gen.1/gud.wfr
%
\def\chinptnwholegenPBgudTks{49305}
\def\chinptnwholegenPBgudTksPct{98.1}
\def\chinptnwholegenPBgudWds{1555}
\def\chinptnwholegenPBgudWdsPct{3.1}
copied '/tmp/571754.file' -> 'exp/chin/ptn/gen.1/gud-whole-wds-summary.tex'
removed '/tmp/571754.file'
creating running text file dat/chin/ptn/gen.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/chin/ptn/gen.1/bad.wfr'
creating the word frequency file dat/chin/ptn/gen.1/bad.wfr
the 10 most common words in dat/chin/ptn/gen.1/bad.tlw:
974 1.00000 =
removed 'dat/chin/ptn/gen.1/bad-whole-wds-summary.tex'
removed 'exp/chin/ptn/gen.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/chin/ptn/gen.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:31:03 by tex-make-sample-summary.sh
% Token and word counts for chin/ptn/gen.1/bad.wfr
%
\def\chinptnwholegenPBbadTks{974}
\def\chinptnwholegenPBbadTksPct{1.9}
\def\chinptnwholegenPBbadWds{1}
\def\chinptnwholegenPBbadWdsPct{0.0}
copied '/tmp/571798.file' -> 'exp/chin/ptn/gen.1/bad-whole-wds-summary.tex'
removed '/tmp/571798.file'
... creating word files dat/chin/ptn/exo.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
41000 dat/chin/ptn/exo.1/whole.tlw
removed 'dat/chin/ptn/exo.1/raw.tlw'
removed 'dat/chin/ptn/exo.1/gud.tlw'
removed 'dat/chin/ptn/exo.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/chin/ptn/exo.1/raw.wdf
sample:
yi3.1 se4 lie4 de5 zhong4 zi5 ge4.1 ren2 dai4.1 zhe5 jia1 juan4.1 he2
ya3 ge4.1 yi1 tong2 lai2 dao4.1 ai1.3 ji2.1 ta1 men5 de5 ming2.1 zi4.1
shi4 liu2.2 ben3 xi1 mian3.5 li4.1 wei4 you2.2 da4 yi3.1 sa4 jia1.11 xi1
bu4.3 lun2.1 bian4 ya3 min3.3 dan4 na2 fu2.14 ta1 li4.1 jia1.11 de2
ya4.1 she4.2 =
ta1 men5 quan2 shi4 ya3 ge4.1 suo3 sheng1 de5 gong4 you3 qi1 shi2.1 ren2
nei4 shi2 yue1 se4.2 yi3 jing1 zai4 ai1.3 ji2.1 le5 =
hou4.1 lai2 yue1 se4.2 he2 ta1 suo3 you3 de5 xiong1 di4.1 yi3.1 ji2.1
nei4 yi1 dai4.3 de5 ren2 dou1 si3 le5 =
yi3.1 se4 lie4 ren2 sheng1 yang3 fan2.2 zhi2.7 zhong4 duo1 ren2 shu4
zeng1 jia1.1 ji2.3 qi2 qiang2 sheng4.2 bian4.1 man3 le5 nei4 di4 =
nei4 shi2 you3 yi1 wei4.1 bu4 ren4 shi5 yue1 se4.2 de5 xin1.1 wang2
xing1 qi3 lai2 tong3 zhi4.2 ai1.3 ji2.1 =
ta1 dui4 zi4 ji3.2 de5 ren2 min2 shuo1 kan4 na3 yi3.1 se4 lie4 min2 bi3
wo3 men5 zhong4 duo1 qiang2 sheng4.2 =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
jian1 yun2 zhong1 you3 huo3 xian3 zai4 yi3.1 se4 lie4 quan2 jia1 de5
yan3 qian2 =
removed 'dat/chin/ptn/exo.1/raw.wfr'
creating the word frequency file dat/chin/ptn/exo.1/raw.wfr
the 10 most common words in dat/chin/ptn/exo.1/raw.tlw:
2062 0.05029 de5
947 0.02310 ni3
841 0.02051 =
810 0.01976 he2
789 0.01924 men5
744 0.01815 ta1
695 0.01695 yao4
651 0.01588 ren2
634 0.01546 zai4
526 0.01283 wo3
removed 'dat/chin/ptn/exo.1/raw-whole-wds-summary.tex'
removed 'exp/chin/ptn/exo.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/chin/ptn/exo.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:31:03 by tex-make-sample-summary.sh
% Token and word counts for chin/ptn/exo.1/raw.wfr
%
\def\chinptnwholeexoPBrawTks{41000}
\def\chinptnwholeexoPBrawTksPct{100.0}
\def\chinptnwholeexoPBrawWds{1451}
\def\chinptnwholeexoPBrawWdsPct{3.5}
copied '/tmp/571852.file' -> 'exp/chin/ptn/exo.1/raw-whole-wds-summary.tex'
removed '/tmp/571852.file'
creating running text file dat/chin/ptn/exo.1/gud.wdf
sample:
yi3.1 se4 lie4 de5 zhong4 zi5 ge4.1 ren2 dai4.1 zhe5 jia1 juan4.1 he2
ya3 ge4.1 yi1 tong2 lai2 dao4.1 ai1.3 ji2.1 ta1 men5 de5 ming2.1 zi4.1
shi4 liu2.2 ben3 xi1 mian3.5 li4.1 wei4 you2.2 da4 yi3.1 sa4 jia1.11 xi1
bu4.3 lun2.1 bian4 ya3 min3.3 dan4 na2 fu2.14 ta1 li4.1 jia1.11 de2
ya4.1 she4.2 ta1 men5 quan2 shi4 ya3 ge4.1 suo3 sheng1 de5 gong4 you3
qi1 shi2.1 ren2 nei4 shi2 yue1 se4.2 yi3 jing1 zai4 ai1.3 ji2.1 le5
hou4.1 lai2 yue1 se4.2 he2 ta1 suo3 you3 de5 xiong1 di4.1 yi3.1 ji2.1
nei4 yi1 dai4.3 de5 ren2 dou1 si3 le5 yi3.1 se4 lie4 ren2 sheng1 yang3
fan2.2 zhi2.7 zhong4 duo1 ren2 shu4 zeng1 jia1.1 ji2.3 qi2 qiang2
sheng4.2 bian4.1 man3 le5 nei4 di4 nei4 shi2 you3 yi1 wei4.1 bu4 ren4
shi5 yue1 se4.2 de5 xin1.1 wang2 xing1 qi3 lai2 tong3 zhi4.2 ai1.3 ji2.1
ta1 dui4 zi4 ji3.2 de5 ren2 min2 shuo1 kan4 na3 yi3.1 se4 lie4 min2 bi3
wo3 men5 zhong4 duo1 qiang2 sheng4.2 lai2 ba5 wo3 men5 yao4 yong4
qiao3.1 ji4.2 dui4 fu4.9 ta1 men5 kong3 pa4 ta1 men5 zeng1 duo1 qi3 lai2
yi1 dan4.3 fa1 sheng1 zhan4.2 zheng1.1 ta1 men5 jiu4 yu3 wo3 men5 de5
chou2.2 di2.2 lian2.2 he2.2 gong1.7 ji1.6 wo3 men5 bing4.1 qie3 li2 kai1
zhei4 di4 yu2 shi4 ta1 men5 zhi3.1 pai4 du1.1 gong1.1 guan3 xia2.4 ta1
men5 jia1.1 zhong4.1 ta1 men5 de5 zhong4.1 dan1.3 ku3 hai4 ta1 men5 ta1
men5 wei2 fa3 lao3 jian4.9 zao4 liang3 zuo4.3 zhu4.7 huo4.2 cheng2.1
jiu4 shi4 bi3 dong1 he2 lan2 sai4 dan4 shi4 ai1.3 ji2.1 ren2 yue4.1 ku3
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
suo3 you3 de5 lü3.2 cheng2.5 zhong1 ri4 jian1 you3 ye1 he2 hua2 de5 yun2
cai3 zai4 zhang4.1 mu4.4 shang4 ye4 jian1 yun2 zhong1 you3 huo3 xian3
zai4 yi3.1 se4 lie4 quan2 jia1 de5 yan3 qian2
removed 'dat/chin/ptn/exo.1/gud.wfr'
creating the word frequency file dat/chin/ptn/exo.1/gud.wfr
the 10 most common words in dat/chin/ptn/exo.1/gud.tlw:
2062 0.05135 de5
947 0.02358 ni3
810 0.02017 he2
789 0.01965 men5
744 0.01853 ta1
695 0.01731 yao4
651 0.01621 ren2
634 0.01579 zai4
526 0.01310 wo3
511 0.01272 shi4
removed 'dat/chin/ptn/exo.1/gud-whole-wds-summary.tex'
removed 'exp/chin/ptn/exo.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/chin/ptn/exo.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:31:04 by tex-make-sample-summary.sh
% Token and word counts for chin/ptn/exo.1/gud.wfr
%
\def\chinptnwholeexoPBgudTks{40159}
\def\chinptnwholeexoPBgudTksPct{97.9}
\def\chinptnwholeexoPBgudWds{1450}
\def\chinptnwholeexoPBgudWdsPct{3.5}
copied '/tmp/571896.file' -> 'exp/chin/ptn/exo.1/gud-whole-wds-summary.tex'
removed '/tmp/571896.file'
creating running text file dat/chin/ptn/exo.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/chin/ptn/exo.1/bad.wfr'
creating the word frequency file dat/chin/ptn/exo.1/bad.wfr
the 10 most common words in dat/chin/ptn/exo.1/bad.tlw:
841 1.00000 =
removed 'dat/chin/ptn/exo.1/bad-whole-wds-summary.tex'
removed 'exp/chin/ptn/exo.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/chin/ptn/exo.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:31:04 by tex-make-sample-summary.sh
% Token and word counts for chin/ptn/exo.1/bad.wfr
%
\def\chinptnwholeexoPBbadTks{841}
\def\chinptnwholeexoPBbadTksPct{2.1}
\def\chinptnwholeexoPBbadWds{1}
\def\chinptnwholeexoPBbadWdsPct{0.0}
copied '/tmp/571940.file' -> 'exp/chin/ptn/exo.1/bad-whole-wds-summary.tex'
removed '/tmp/571940.file'
... creating word files dat/chin/ptn/num.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
40542 dat/chin/ptn/num.1/whole.tlw
removed 'dat/chin/ptn/num.1/raw.tlw'
removed 'dat/chin/ptn/num.1/gud.tlw'
removed 'dat/chin/ptn/num.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/chin/ptn/num.1/raw.wdf
sample:
yi3.1 se4 lie4 ren2 chu1 ai1.3 ji2.1 di4 yi3.1 hou4.1 di4.2 er4 nian2
er4 yue4 yi1 ri4 ye1 he2 hua2 zai4 xi1 nai4 de5 kuang4.1 ye3.1 zai4 hui4
mu4.4 li3 dui4 mo2.3 xi1 shuo1 ni3 men5 yao4 ba3 yi3.1 se4 lie4 quan2
ti3 hui4 zhong4 an4.1 zhe5 ta1 men5 de5 zong1 zu2.1 fu4.1 jia1 gen1.1
ju4.2 ren2 ming2.1 shu4 mu4 tong3 ji4.2 ren2 kou3 suo3 you3 nan2.1 ding1
dou1 yao4 an4.1 zhe5 ren2 kou3 deng1.1 ji4.1 =
zai4 yi3.1 se4 lie4 zhong1 fan2 shi4 er4 shi2.1 sui4.1 yi3.1 shang4
neng2 chu1 qu4 da3 zhang4.2 de5 ni3 he2 ya4.1 lun2.1 yao4 an4.1 zhe5 ta1
men5 de5 dui4.2 wu3.9 shu4 dian3 ta1 men5 =
mei3 yi1 ge4 zhi1.2 pai4 yao4 you3 yi1 ren2 bang1 zhu4.2 ni3 men5 ta1
men5 mei3 yi1 ge4 dou1 shi4 ta1 fu4.1 jia1 de5 shou3.1 ling3 =
yi3.1 xia4 jiu4 shi4 bang1 zhu4.2 ni3 men5 de5 ren2 de5 ming2.1 zi4.1
shu3 liu2.2 ben3 zhi1.2 pai4 de5 you3 shi4.10 diu1 er3.5 de5 er2 zi5
yi3.1 li4.1 xu5 shu3 xi1 mian3.5 zhi1.2 pai4 de5 you3 su1 li4.1 sha1.2
dai4.3 de5 er2 zi5 shi4.10 lu4 mie4.1 shu3 you2.2 da4 zhi1.2 pai4 de5
you3 ya4.1 mi3 na2 da2.1 de5 er2 zi5 na2 shun4 shu3 yi3.1 sa4 jia1.11
zhi1.2 pai4 de5 you3 su1 ya1.3 de5 er2 zi5 na2 tan3.1 ye4.1 shu3 xi1
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
bian1 de5 mo2.3 ya1.3 ping2 yuan2 jie4 zhe5 mo2.3 xi1 xiang4 yi3.1 se4
lie4 ren2 fen1.1 fu4.2 de5 ming4 ling4 he2 dian3.1 zhang1.1 =
removed 'dat/chin/ptn/num.1/raw.wfr'
creating the word frequency file dat/chin/ptn/num.1/raw.wfr
the 10 most common words in dat/chin/ptn/num.1/raw.tlw:
2265 0.05587 de5
876 0.02161 men5
812 0.02003 ren2
775 0.01912 ta1
750 0.01850 =
730 0.01801 he2
615 0.01517 ni3
605 0.01492 yi3.1
594 0.01465 shi4
566 0.01396 zai4
removed 'dat/chin/ptn/num.1/raw-whole-wds-summary.tex'
removed 'exp/chin/ptn/num.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/chin/ptn/num.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:31:04 by tex-make-sample-summary.sh
% Token and word counts for chin/ptn/num.1/raw.wfr
%
\def\chinptnwholenumPBrawTks{40542}
\def\chinptnwholenumPBrawTksPct{100.0}
\def\chinptnwholenumPBrawWds{1309}
\def\chinptnwholenumPBrawWdsPct{3.2}
copied '/tmp/571994.file' -> 'exp/chin/ptn/num.1/raw-whole-wds-summary.tex'
removed '/tmp/571994.file'
creating running text file dat/chin/ptn/num.1/gud.wdf
sample:
yi3.1 se4 lie4 ren2 chu1 ai1.3 ji2.1 di4 yi3.1 hou4.1 di4.2 er4 nian2
er4 yue4 yi1 ri4 ye1 he2 hua2 zai4 xi1 nai4 de5 kuang4.1 ye3.1 zai4 hui4
mu4.4 li3 dui4 mo2.3 xi1 shuo1 ni3 men5 yao4 ba3 yi3.1 se4 lie4 quan2
ti3 hui4 zhong4 an4.1 zhe5 ta1 men5 de5 zong1 zu2.1 fu4.1 jia1 gen1.1
ju4.2 ren2 ming2.1 shu4 mu4 tong3 ji4.2 ren2 kou3 suo3 you3 nan2.1 ding1
dou1 yao4 an4.1 zhe5 ren2 kou3 deng1.1 ji4.1 zai4 yi3.1 se4 lie4 zhong1
fan2 shi4 er4 shi2.1 sui4.1 yi3.1 shang4 neng2 chu1 qu4 da3 zhang4.2 de5
ni3 he2 ya4.1 lun2.1 yao4 an4.1 zhe5 ta1 men5 de5 dui4.2 wu3.9 shu4
dian3 ta1 men5 mei3 yi1 ge4 zhi1.2 pai4 yao4 you3 yi1 ren2 bang1 zhu4.2
ni3 men5 ta1 men5 mei3 yi1 ge4 dou1 shi4 ta1 fu4.1 jia1 de5 shou3.1
ling3 yi3.1 xia4 jiu4 shi4 bang1 zhu4.2 ni3 men5 de5 ren2 de5 ming2.1
zi4.1 shu3 liu2.2 ben3 zhi1.2 pai4 de5 you3 shi4.10 diu1 er3.5 de5 er2
zi5 yi3.1 li4.1 xu5 shu3 xi1 mian3.5 zhi1.2 pai4 de5 you3 su1 li4.1
sha1.2 dai4.3 de5 er2 zi5 shi4.10 lu4 mie4.1 shu3 you2.2 da4 zhi1.2 pai4
de5 you3 ya4.1 mi3 na2 da2.1 de5 er2 zi5 na2 shun4 shu3 yi3.1 sa4
jia1.11 zhi1.2 pai4 de5 you3 su1 ya1.3 de5 er2 zi5 na2 tan3.1 ye4.1 shu3
xi1 bu4.3 lun2.1 zhi1.2 pai4 de5 you3 xi1.5 lun2.1 de5 er2 zi5 yi3.1
li4.1 ya1.3 yue1 se4.2 de5 zi5 sun1 zhong1 shu3 yi3.1 fa3 lian2.3 zhi1.2
pai4 de5 you3 ya4.1 mi3 hu1 de5 er2 zi5 yi3.1 li4.1 sha1.2 ma3.1 shu3
ma3.1 na2 xi1 zhi1.2 pai4 de5 you3 bi3 da4 xu5 de5 er2 zi5 jia1.11 ma3.1
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
zhei4 shi4 ye1 he2 hua2 zai4 ye1 li4.1 ge1 dui4 mian4 yue1 dan4.3 he2.5
bian1 de5 mo2.3 ya1.3 ping2 yuan2 jie4 zhe5 mo2.3 xi1 xiang4 yi3.1 se4
lie4 ren2 fen1.1 fu4.2 de5 ming4 ling4 he2 dian3.1 zhang1.1
removed 'dat/chin/ptn/num.1/gud.wfr'
creating the word frequency file dat/chin/ptn/num.1/gud.wfr
the 10 most common words in dat/chin/ptn/num.1/gud.tlw:
2265 0.05692 de5
876 0.02201 men5
812 0.02041 ren2
775 0.01948 ta1
730 0.01835 he2
615 0.01546 ni3
605 0.01520 yi3.1
594 0.01493 shi4
566 0.01422 zai4
564 0.01417 yao4
removed 'dat/chin/ptn/num.1/gud-whole-wds-summary.tex'
removed 'exp/chin/ptn/num.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/chin/ptn/num.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:31:04 by tex-make-sample-summary.sh
% Token and word counts for chin/ptn/num.1/gud.wfr
%
\def\chinptnwholenumPBgudTks{39792}
\def\chinptnwholenumPBgudTksPct{98.2}
\def\chinptnwholenumPBgudWds{1308}
\def\chinptnwholenumPBgudWdsPct{3.2}
copied '/tmp/572038.file' -> 'exp/chin/ptn/num.1/gud-whole-wds-summary.tex'
removed '/tmp/572038.file'
creating running text file dat/chin/ptn/num.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/chin/ptn/num.1/bad.wfr'
creating the word frequency file dat/chin/ptn/num.1/bad.wfr
the 10 most common words in dat/chin/ptn/num.1/bad.tlw:
750 1.00000 =
removed 'dat/chin/ptn/num.1/bad-whole-wds-summary.tex'
removed 'exp/chin/ptn/num.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/chin/ptn/num.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:31:04 by tex-make-sample-summary.sh
% Token and word counts for chin/ptn/num.1/bad.wfr
%
\def\chinptnwholenumPBbadTks{750}
\def\chinptnwholenumPBbadTksPct{1.8}
\def\chinptnwholenumPBbadWds{1}
\def\chinptnwholenumPBbadWdsPct{0.0}
copied '/tmp/572082.file' -> 'exp/chin/ptn/num.1/bad-whole-wds-summary.tex'
removed '/tmp/572082.file'
... creating word files dat/chin/ptn/lev.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
29292 dat/chin/ptn/lev.1/whole.tlw
removed 'dat/chin/ptn/lev.1/raw.tlw'
removed 'dat/chin/ptn/lev.1/gud.tlw'
removed 'dat/chin/ptn/lev.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/chin/ptn/lev.1/raw.wdf
sample:
ye1 he2 hua2 hu1.1 jiao4 mo2.3 xi1 cong2 hui4 mu4.4 li3 dui4 mo2.3 xi1
shuo1 ni3 yao4 gao4 su4 yi3.1 se4 lie4 ren2 shuo1 ru2 guo3 ni3 men5
zhong1 jian1 you3 ren2 ba3 gong1.4 wu4 xian4.4 ji3.1 ye1 he2 hua2 jiu4
yao4 cong2 niu2 qun2.1 yang2.3 qun2.1 zhong1 xian4.4 jia1 chu4.1 wei2
gong1.4 wu4 =
ta1 de5 gong1.4 wu4 ruo4 shi4 xian4.4 niu2 zuo4.2 fan2.6 ji4.4 jiu4 yao4
ba3 yi1 tou2 mei2 you3 can2 ji2.5 de5 gong1 niu2 qian1.2 dao4.1 hui4
mu4.4 men2 kou3 jiu4 ke3 yi3.1 zai4 ye1 he2 hua2 mian4 qian2 meng3
yue4.2 na4 =
ta1 yao4 an4.1 shou3 zai4 fan2.6 ji4.4 sheng1.5 de5 tou2 shang4 fan2.6
ji4.4 jiu4 meng3 yue4.2 na4 ke3 yi3.1 wei2 ta1 shu2.1 zui4 =
ta1 yao4 zai4 ye1 he2 hua2 mian4 qian2 zai3.2 sha1.1 nei4 gong1 niu2
ya4.1 lun2.1 zi5 sun1 zuo4.2 ji4.4 si1.1 de5 yao4 feng4.1 shang4 xue4
po1 zai4 hui4 mu4.4 men2 kou3 ji4.4 tan2.2 de5 si4 zhou1 =
nei4 ren2 yao4 bo1.3 qu4 fan2.6 ji4.4 sheng1.5 de5 pi2 ba3 fan2.6 ji4.4
sheng1.5 qie4 cheng2 kuai4.1 zi5 =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
hui2 yi3.1 shang4 zhei4 xie1 jiu4 shi4 ye1 he2 hua2 zai4 xi1 nai4 shan1
wei2 yi3.1 se4 lie4 ren2 fen1.1 fu4.2 mo2.3 xi1 de5 lü4.1 li4.3 =
removed 'dat/chin/ptn/lev.1/raw.wfr'
creating the word frequency file dat/chin/ptn/lev.1/raw.wfr
the 10 most common words in dat/chin/ptn/lev.1/raw.tlw:
1714 0.05851 de5
639 0.02181 ji4.4
599 0.02045 =
597 0.02038 ni3
593 0.02024 men5
573 0.01956 yao4
534 0.01823 shi4
521 0.01779 ta1
511 0.01745 he2
429 0.01465 zai4
removed 'dat/chin/ptn/lev.1/raw-whole-wds-summary.tex'
removed 'exp/chin/ptn/lev.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/chin/ptn/lev.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:31:04 by tex-make-sample-summary.sh
% Token and word counts for chin/ptn/lev.1/raw.wfr
%
\def\chinptnwholelevPBrawTks{29292}
\def\chinptnwholelevPBrawTksPct{100.0}
\def\chinptnwholelevPBrawWds{1170}
\def\chinptnwholelevPBrawWdsPct{4.0}
copied '/tmp/572136.file' -> 'exp/chin/ptn/lev.1/raw-whole-wds-summary.tex'
removed '/tmp/572136.file'
creating running text file dat/chin/ptn/lev.1/gud.wdf
sample:
ye1 he2 hua2 hu1.1 jiao4 mo2.3 xi1 cong2 hui4 mu4.4 li3 dui4 mo2.3 xi1
shuo1 ni3 yao4 gao4 su4 yi3.1 se4 lie4 ren2 shuo1 ru2 guo3 ni3 men5
zhong1 jian1 you3 ren2 ba3 gong1.4 wu4 xian4.4 ji3.1 ye1 he2 hua2 jiu4
yao4 cong2 niu2 qun2.1 yang2.3 qun2.1 zhong1 xian4.4 jia1 chu4.1 wei2
gong1.4 wu4 ta1 de5 gong1.4 wu4 ruo4 shi4 xian4.4 niu2 zuo4.2 fan2.6
ji4.4 jiu4 yao4 ba3 yi1 tou2 mei2 you3 can2 ji2.5 de5 gong1 niu2 qian1.2
dao4.1 hui4 mu4.4 men2 kou3 jiu4 ke3 yi3.1 zai4 ye1 he2 hua2 mian4 qian2
meng3 yue4.2 na4 ta1 yao4 an4.1 shou3 zai4 fan2.6 ji4.4 sheng1.5 de5
tou2 shang4 fan2.6 ji4.4 jiu4 meng3 yue4.2 na4 ke3 yi3.1 wei2 ta1 shu2.1
zui4 ta1 yao4 zai4 ye1 he2 hua2 mian4 qian2 zai3.2 sha1.1 nei4 gong1
niu2 ya4.1 lun2.1 zi5 sun1 zuo4.2 ji4.4 si1.1 de5 yao4 feng4.1 shang4
xue4 po1 zai4 hui4 mu4.4 men2 kou3 ji4.4 tan2.2 de5 si4 zhou1 nei4 ren2
yao4 bo1.3 qu4 fan2.6 ji4.4 sheng1.5 de5 pi2 ba3 fan2.6 ji4.4 sheng1.5
qie4 cheng2 kuai4.1 zi5 ya4.1 lun2.1 zi5 sun1 zuo4.2 ji4.4 si1.1 de5
yao4 ba3 tan4.2 huo3 fang4 zai4 ji4.4 tan2.2 shang4 ba3 chai2 pai2.1
lie4 zai4 huo3 shang4 ya4.1 lun2.1 zi5 sun1 zuo4.2 ji4.4 si1.1 de5 yao4
ba3 rou4 kuai4.1 he2 tou2 yi3.1 ji2.1 zhi1.4 fang2.3 pai2.1 lie4 zai4
ji4.4 tan2.2 tan4.2 huo3 shang4 de5 mu4.1 chai2 shang4 mian4 nei4 ren2
you4 yao4 yong4 shui3 xi3.1 jing4.2 nei4.1 zang4.2 he2 tui3 ji4.4 si1.1
jiu4 ba3 zhei4 yi1 qie4 quan2 xian4.4 zai4 ji4.4 tan2.2 shang4 fen2
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
huan4.1 de5 dou1 yao4 fen1 bie2 wei2 sheng4.1 bu4 neng2 shu2.1 hui2
yi3.1 shang4 zhei4 xie1 jiu4 shi4 ye1 he2 hua2 zai4 xi1 nai4 shan1 wei2
yi3.1 se4 lie4 ren2 fen1.1 fu4.2 mo2.3 xi1 de5 lü4.1 li4.3
removed 'dat/chin/ptn/lev.1/gud.wfr'
creating the word frequency file dat/chin/ptn/lev.1/gud.wfr
the 10 most common words in dat/chin/ptn/lev.1/gud.tlw:
1714 0.05974 de5
639 0.02227 ji4.4
597 0.02081 ni3
593 0.02067 men5
573 0.01997 yao4
534 0.01861 shi4
521 0.01816 ta1
511 0.01781 he2
429 0.01495 zai4
423 0.01474 bu4
removed 'dat/chin/ptn/lev.1/gud-whole-wds-summary.tex'
removed 'exp/chin/ptn/lev.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/chin/ptn/lev.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:31:04 by tex-make-sample-summary.sh
% Token and word counts for chin/ptn/lev.1/gud.wfr
%
\def\chinptnwholelevPBgudTks{28693}
\def\chinptnwholelevPBgudTksPct{98.0}
\def\chinptnwholelevPBgudWds{1169}
\def\chinptnwholelevPBgudWdsPct{4.0}
copied '/tmp/572180.file' -> 'exp/chin/ptn/lev.1/gud-whole-wds-summary.tex'
removed '/tmp/572180.file'
creating running text file dat/chin/ptn/lev.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/chin/ptn/lev.1/bad.wfr'
creating the word frequency file dat/chin/ptn/lev.1/bad.wfr
the 10 most common words in dat/chin/ptn/lev.1/bad.tlw:
599 1.00000 =
removed 'dat/chin/ptn/lev.1/bad-whole-wds-summary.tex'
removed 'exp/chin/ptn/lev.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/chin/ptn/lev.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:31:04 by tex-make-sample-summary.sh
% Token and word counts for chin/ptn/lev.1/bad.wfr
%
\def\chinptnwholelevPBbadTks{599}
\def\chinptnwholelevPBbadTksPct{2.0}
\def\chinptnwholelevPBbadWds{1}
\def\chinptnwholelevPBbadWdsPct{0.0}
copied '/tmp/572224.file' -> 'exp/chin/ptn/lev.1/bad-whole-wds-summary.tex'
removed '/tmp/572224.file'
... creating word files dat/chin/ptn/deu.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
35979 dat/chin/ptn/deu.1/whole.tlw
removed 'dat/chin/ptn/deu.1/raw.tlw'
removed 'dat/chin/ptn/deu.1/gud.tlw'
removed 'dat/chin/ptn/deu.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/chin/ptn/deu.1/raw.wdf
sample:
yi3.1 xia4 shi4 mo2.3 xi1 zai4 yue1 dan4.3 he2.5 dong1 de5 kuang4.1
ye3.1 shu1.3 fu2.14 dui4 mian4 de5 ya4.1 la1 ba1.1 jiu4 shi4 zai4 ba1.1
lan2 he2 tuo2 fu2.14 la1 ban1.1 ha1 xi3.1 lu4.3 di3 sa1 ha1 zhi1.1 jian1
xiang4 yi3.1 se4 lie4 ren2 suo3 shuo1 de5 hua4 =
cong2 he2.1 lie4.1 shan1 jing1 guo4 xi1 er3.5 shan1 de5 lu4 dao4.1 da2.1
jia1.1 di1 si1.6 ba1.1 ni2.2 ya4.1 gong4 you3 shi2.1 yi1 tian1 de5 lu4
cheng2.5 =
chu1 ai1.3 ji2.1 yi3.1 hou4.1 di4.2 si4 shi2.1 nian2 shi2.1 yi1 yue4 yi1
ri4 mo2.3 xi1 zhao4 zhe5 ye1 he2 hua2 fen1.1 fu4.2 ta1 yi1 qie4 guan1.1
yu2 yi3.1 se4 lie4 ren2 de5 hua4 dou1 gao4 su4 le5 ta1 men5 =
dang1 shi2 ta1 yi3 jing1 ji1.6 bai4.1 le5 zhu4.1 zai4 xi1.5 shi2.2 ben3
de5 ya4.1 mo2.3 li4.1 ren2 de5 wang2 xi1 hong2.3 he2 zhu4.1 zai4 ya4.1
si1.6 ta1 lu4.3 yu3 yi3.1 de2 lai2 de5 ba1.1 shan1.4 wang2 e4.8 =
mo2.3 xi1 zai4 yue1 dan4.3 he2.5 dong1 de5 mo2.3 ya1.3 di4 kai1 shi3.2
jiang3 jie3.1 zhei4 lü4.1 fa3 shuo1 ye1 he2 hua2 wo3 men5 de5 shen2.1
zai4 he2.1 lie4.1 shan1 gao4 su4 wo3 men5 ni3 men5 zai4 zhei4 shan1
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
mo2.3 xi1 you4 zai4 yi3.1 se4 lie4 zhong4 ren2 yan3 qian2 xing2 le5 yi1
qie4 da4 neng2 de5 shi4.1 he2 yi1 qie4 da4 er2.1 ke3 wei4.5 de5 shi4.1 =
removed 'dat/chin/ptn/deu.1/raw.wfr'
creating the word frequency file dat/chin/ptn/deu.1/raw.wfr
the 10 most common words in dat/chin/ptn/deu.1/raw.tlw:
2313 0.06429 de5
1919 0.05334 ni3
973 0.02704 men5
871 0.02421 he2
815 0.02265 ta1
609 0.01693 =
574 0.01595 ye1
573 0.01593 zai4
565 0.01570 hua2
514 0.01429 yao4
removed 'dat/chin/ptn/deu.1/raw-whole-wds-summary.tex'
removed 'exp/chin/ptn/deu.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/chin/ptn/deu.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:31:04 by tex-make-sample-summary.sh
% Token and word counts for chin/ptn/deu.1/raw.wfr
%
\def\chinptnwholedeuPBrawTks{35979}
\def\chinptnwholedeuPBrawTksPct{100.0}
\def\chinptnwholedeuPBrawWds{1464}
\def\chinptnwholedeuPBrawWdsPct{4.1}
copied '/tmp/572278.file' -> 'exp/chin/ptn/deu.1/raw-whole-wds-summary.tex'
removed '/tmp/572278.file'
creating running text file dat/chin/ptn/deu.1/gud.wdf
sample:
yi3.1 xia4 shi4 mo2.3 xi1 zai4 yue1 dan4.3 he2.5 dong1 de5 kuang4.1
ye3.1 shu1.3 fu2.14 dui4 mian4 de5 ya4.1 la1 ba1.1 jiu4 shi4 zai4 ba1.1
lan2 he2 tuo2 fu2.14 la1 ban1.1 ha1 xi3.1 lu4.3 di3 sa1 ha1 zhi1.1 jian1
xiang4 yi3.1 se4 lie4 ren2 suo3 shuo1 de5 hua4 cong2 he2.1 lie4.1 shan1
jing1 guo4 xi1 er3.5 shan1 de5 lu4 dao4.1 da2.1 jia1.1 di1 si1.6 ba1.1
ni2.2 ya4.1 gong4 you3 shi2.1 yi1 tian1 de5 lu4 cheng2.5 chu1 ai1.3
ji2.1 yi3.1 hou4.1 di4.2 si4 shi2.1 nian2 shi2.1 yi1 yue4 yi1 ri4 mo2.3
xi1 zhao4 zhe5 ye1 he2 hua2 fen1.1 fu4.2 ta1 yi1 qie4 guan1.1 yu2 yi3.1
se4 lie4 ren2 de5 hua4 dou1 gao4 su4 le5 ta1 men5 dang1 shi2 ta1 yi3
jing1 ji1.6 bai4.1 le5 zhu4.1 zai4 xi1.5 shi2.2 ben3 de5 ya4.1 mo2.3
li4.1 ren2 de5 wang2 xi1 hong2.3 he2 zhu4.1 zai4 ya4.1 si1.6 ta1 lu4.3
yu3 yi3.1 de2 lai2 de5 ba1.1 shan1.4 wang2 e4.8 mo2.3 xi1 zai4 yue1
dan4.3 he2.5 dong1 de5 mo2.3 ya1.3 di4 kai1 shi3.2 jiang3 jie3.1 zhei4
lü4.1 fa3 shuo1 ye1 he2 hua2 wo3 men5 de5 shen2.1 zai4 he2.1 lie4.1
shan1 gao4 su4 wo3 men5 ni3 men5 zai4 zhei4 shan1 shang4 zhu4.1 gou4.1
le5 xian4 zai4 ni3 men5 yao4 zhuan3 hui2 qi3 cheng2.5 dao4.1 ya4.1 mo2.3
li4.1 ren2 de5 shan1 di4 qu4 dao4.1 nei4 xie1 zhu4.1 zai4 ya4.1 la1
ba1.1 shan1 di4 di1 di4 nan2.2 di4 yan2.3 hai3 yi1 dai4.1 jia1.11 nan2.2
ren2 de5 di4 li2.5 ba1.1 nen4 zhi2 dao4.1 da4 he2.5 jiu4 shi4 you4.2 fa1
la1 di3 he2.5 yi1 dai4.1 de5 di4 fang1 qu4 kan4 na3 wo3 ba3 zhei4 di4
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
de5 quan2 di4 xing2 le5 yi1 qie4 shen2.1 ji1.2 he2 qi2.2 shi4.1 mo2.3
xi1 you4 zai4 yi3.1 se4 lie4 zhong4 ren2 yan3 qian2 xing2 le5 yi1 qie4
da4 neng2 de5 shi4.1 he2 yi1 qie4 da4 er2.1 ke3 wei4.5 de5 shi4.1
removed 'dat/chin/ptn/deu.1/gud.wfr'
creating the word frequency file dat/chin/ptn/deu.1/gud.wfr
the 10 most common words in dat/chin/ptn/deu.1/gud.tlw:
2313 0.06539 de5
1919 0.05426 ni3
973 0.02751 men5
871 0.02463 he2
815 0.02304 ta1
574 0.01623 ye1
573 0.01620 zai4
565 0.01597 hua2
514 0.01453 yao4
466 0.01318 wo3
removed 'dat/chin/ptn/deu.1/gud-whole-wds-summary.tex'
removed 'exp/chin/ptn/deu.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/chin/ptn/deu.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:31:04 by tex-make-sample-summary.sh
% Token and word counts for chin/ptn/deu.1/gud.wfr
%
\def\chinptnwholedeuPBgudTks{35370}
\def\chinptnwholedeuPBgudTksPct{98.3}
\def\chinptnwholedeuPBgudWds{1463}
\def\chinptnwholedeuPBgudWdsPct{4.1}
copied '/tmp/572322.file' -> 'exp/chin/ptn/deu.1/gud-whole-wds-summary.tex'
removed '/tmp/572322.file'
creating running text file dat/chin/ptn/deu.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/chin/ptn/deu.1/bad.wfr'
creating the word frequency file dat/chin/ptn/deu.1/bad.wfr
the 10 most common words in dat/chin/ptn/deu.1/bad.tlw:
609 1.00000 =
removed 'dat/chin/ptn/deu.1/bad-whole-wds-summary.tex'
removed 'exp/chin/ptn/deu.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/chin/ptn/deu.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:31:04 by tex-make-sample-summary.sh
% Token and word counts for chin/ptn/deu.1/bad.wfr
%
\def\chinptnwholedeuPBbadTks{609}
\def\chinptnwholedeuPBbadTksPct{1.7}
\def\chinptnwholedeuPBbadWds{1}
\def\chinptnwholedeuPBbadWdsPct{0.0}
copied '/tmp/572366.file' -> 'exp/chin/ptn/deu.1/bad-whole-wds-summary.tex'
removed '/tmp/572366.file'
... creating word files dat/chin/ptn/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
197092 dat/chin/ptn/tot.1/whole.tlw
removed 'dat/chin/ptn/tot.1/raw.tlw'
removed 'dat/chin/ptn/tot.1/gud.tlw'
removed 'dat/chin/ptn/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/chin/ptn/tot.1/raw.wdf
sample:
qi3 chu1.1 shen2.1 chuang4 zao4 tian1 di4 =
di4 shi4 kong1 xu1.1 hun4 dun4.5 shen1.1 yuan1.2 shang4 yi1 pian4 hei1
an4 shen2.1 de5 ling2.1 yun4.1 xing2 zai4 shui3 mian4 shang4 =
shen2.1 shuo1 yao4 you3 guang1 jiu4 you3 le5 guang1 =
shen2.1 kan4 guang1 shi4 hao3 de5 ta1 jiu4 ba3 guang1 an4 fen1 kai1 le5
=
shen2.1 cheng1 guang1 wei2 zhou4.1 cheng1 an4 wei2 ye4 you3 wan3 shang4
you3 zao3 chen2.5 zhei4 shi4 di4.2 yi1 ri4 =
shen2.1 shuo1 zhong4 shui3 zhi1.1 jian1 yao4 you3 qiong2.3 cang1 ba3
shui3 he2 shui3 fen1 kai1 shi4.1 jiu4 zhei4 yang4 cheng2 le5 =
shen2.1 zao4 le5 qiong2.3 cang1 ba3 qiong2.3 cang1 yi3.1 xia4 de5 shui3
he2 qiong2.3 cang1 yi3.1 shang4 de5 shui3 fen1 kai1 le5 =
shen2.1 cheng1 qiong2.3 cang1 wei2 tian1 you3 wan3 shang4 you3 zao3
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
mo2.3 xi1 you4 zai4 yi3.1 se4 lie4 zhong4 ren2 yan3 qian2 xing2 le5 yi1
qie4 da4 neng2 de5 shi4.1 he2 yi1 qie4 da4 er2.1 ke3 wei4.5 de5 shi4.1 =
removed 'dat/chin/ptn/tot.1/raw.wfr'
creating the word frequency file dat/chin/ptn/tot.1/raw.wfr
the 10 most common words in dat/chin/ptn/tot.1/raw.tlw:
10835 0.05497 de5
5126 0.02601 ni3
4153 0.02107 men5
4108 0.02084 ta1
3773 0.01914 =
3499 0.01775 he2
2996 0.01520 ren2
2985 0.01515 zai4
2777 0.01409 wo3
2728 0.01384 shi4
removed 'dat/chin/ptn/tot.1/raw-whole-wds-summary.tex'
removed 'exp/chin/ptn/tot.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/chin/ptn/tot.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:31:05 by tex-make-sample-summary.sh
% Token and word counts for chin/ptn/tot.1/raw.wfr
%
\def\chinptnwholetotPBrawTks{197092}
\def\chinptnwholetotPBrawTksPct{100.0}
\def\chinptnwholetotPBrawWds{2267}
\def\chinptnwholetotPBrawWdsPct{1.2}
copied '/tmp/572420.file' -> 'exp/chin/ptn/tot.1/raw-whole-wds-summary.tex'
removed '/tmp/572420.file'
creating running text file dat/chin/ptn/tot.1/gud.wdf
sample:
qi3 chu1.1 shen2.1 chuang4 zao4 tian1 di4 di4 shi4 kong1 xu1.1 hun4
dun4.5 shen1.1 yuan1.2 shang4 yi1 pian4 hei1 an4 shen2.1 de5 ling2.1
yun4.1 xing2 zai4 shui3 mian4 shang4 shen2.1 shuo1 yao4 you3 guang1 jiu4
you3 le5 guang1 shen2.1 kan4 guang1 shi4 hao3 de5 ta1 jiu4 ba3 guang1
an4 fen1 kai1 le5 shen2.1 cheng1 guang1 wei2 zhou4.1 cheng1 an4 wei2 ye4
you3 wan3 shang4 you3 zao3 chen2.5 zhei4 shi4 di4.2 yi1 ri4 shen2.1
shuo1 zhong4 shui3 zhi1.1 jian1 yao4 you3 qiong2.3 cang1 ba3 shui3 he2
shui3 fen1 kai1 shi4.1 jiu4 zhei4 yang4 cheng2 le5 shen2.1 zao4 le5
qiong2.3 cang1 ba3 qiong2.3 cang1 yi3.1 xia4 de5 shui3 he2 qiong2.3
cang1 yi3.1 shang4 de5 shui3 fen1 kai1 le5 shen2.1 cheng1 qiong2.3 cang1
wei2 tian1 you3 wan3 shang4 you3 zao3 chen2.5 zhei4 shi4 di4.2 er4 ri4
shen2.1 shuo1 tian1 xia4 de5 shui3 yao4 ju4.3 zai4 yi1 chu3 shi3 han4.4
di4 lu4.1 chu1 lai2 shi4.1 jiu4 zhei4 yang4 cheng2 le5 shen2.1 cheng1
han4.4 di4 wei2 di4 cheng1 shui3 de5 ju4.3 chu3 wei2 hai3 shen2.1 kan4
zhei4 shi4 hao3 de5 shen2.1 shuo1 di4 shang4 yao4 zhang3 chu1 qing1.2
cao3 jie2 zhong3 zi5 de5 shu1.6 cai4 he2 jie2 guo3 zi5 de5 shu4.2 mu4.1
ge4.1 cong2 qi2 lei4.1 zai4 di4 shang4 de5 guo3 zi5 dou1 bao1 zhe5 he2.6
shi4.1 jiu4 zhei4 yang4 cheng2 le5 yu2 shi4 di4 shang4 zhang3 chu1 le5
qing1.2 cao3 he2 jie2 zhong3 zi5 de5 shu1.6 cai4 ge4.1 cong2 qi2 lei4.1
you4 zhang3 chu1 jie2 guo3 zi5 de5 shu4.2 mu4.1 ge4.1 cong2 qi2 lei4.1
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
de5 quan2 di4 xing2 le5 yi1 qie4 shen2.1 ji1.2 he2 qi2.2 shi4.1 mo2.3
xi1 you4 zai4 yi3.1 se4 lie4 zhong4 ren2 yan3 qian2 xing2 le5 yi1 qie4
da4 neng2 de5 shi4.1 he2 yi1 qie4 da4 er2.1 ke3 wei4.5 de5 shi4.1
removed 'dat/chin/ptn/tot.1/gud.wfr'
creating the word frequency file dat/chin/ptn/tot.1/gud.wfr
the 10 most common words in dat/chin/ptn/tot.1/gud.tlw:
10835 0.05605 de5
5126 0.02652 ni3
4153 0.02148 men5
4108 0.02125 ta1
3499 0.01810 he2
2996 0.01550 ren2
2985 0.01544 zai4
2777 0.01436 wo3
2728 0.01411 shi4
2711 0.01402 yao4
removed 'dat/chin/ptn/tot.1/gud-whole-wds-summary.tex'
removed 'exp/chin/ptn/tot.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/chin/ptn/tot.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:31:05 by tex-make-sample-summary.sh
% Token and word counts for chin/ptn/tot.1/gud.wfr
%
\def\chinptnwholetotPBgudTks{193319}
\def\chinptnwholetotPBgudTksPct{98.1}
\def\chinptnwholetotPBgudWds{2266}
\def\chinptnwholetotPBgudWdsPct{1.1}
copied '/tmp/572464.file' -> 'exp/chin/ptn/tot.1/gud-whole-wds-summary.tex'
removed '/tmp/572464.file'
creating running text file dat/chin/ptn/tot.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/chin/ptn/tot.1/bad.wfr'
creating the word frequency file dat/chin/ptn/tot.1/bad.wfr
the 10 most common words in dat/chin/ptn/tot.1/bad.tlw:
3773 1.00000 =
removed 'dat/chin/ptn/tot.1/bad-whole-wds-summary.tex'
removed 'exp/chin/ptn/tot.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/chin/ptn/tot.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:31:05 by tex-make-sample-summary.sh
% Token and word counts for chin/ptn/tot.1/bad.wfr
%
\def\chinptnwholetotPBbadTks{3773}
\def\chinptnwholetotPBbadTksPct{1.9}
\def\chinptnwholetotPBbadWds{1}
\def\chinptnwholetotPBbadWdsPct{0.0}
copied '/tmp/572508.file' -> 'exp/chin/ptn/tot.1/bad-whole-wds-summary.tex'
removed '/tmp/572508.file'
lines words bytes file
------- ------- --------- ------------
1556 4668 34624 dat/chin/ptn/gen.1/raw.wfr
1451 4353 32273 dat/chin/ptn/exo.1/raw.wfr
1309 3927 29041 dat/chin/ptn/num.1/raw.wfr
1170 3510 25967 dat/chin/ptn/lev.1/raw.wfr
1464 4392 32570 dat/chin/ptn/deu.1/raw.wfr
2267 6801 50776 dat/chin/ptn/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
1555 4665 34606 dat/chin/ptn/gen.1/gud.wfr
1450 4350 32255 dat/chin/ptn/exo.1/gud.wfr
1308 3924 29023 dat/chin/ptn/num.1/gud.wfr
1169 3507 25949 dat/chin/ptn/lev.1/gud.wfr
1463 4389 32552 dat/chin/ptn/deu.1/gud.wfr
2266 6798 50758 dat/chin/ptn/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
1 3 18 dat/chin/ptn/gen.1/bad.wfr
1 3 18 dat/chin/ptn/exo.1/bad.wfr
1 3 18 dat/chin/ptn/num.1/bad.wfr
1 3 18 dat/chin/ptn/lev.1/bad.wfr
1 3 18 dat/chin/ptn/deu.1/bad.wfr
1 3 18 dat/chin/ptn/tot.1/bad.wfr
gen.1 raw = 50279 gud = 49305 bad = 974
exo.1 raw = 41000 gud = 40159 bad = 841
num.1 raw = 40542 gud = 39792 bad = 750
lev.1 raw = 29292 gud = 28693 bad = 599
deu.1 raw = 35979 gud = 35370 bad = 609
tot.1 raw = 197092 gud = 193319 bad = 3773
=== creating the derived word files dat/chin/red/*/{raw,gud,bad}.{tlw,wdf,wfr} (whole) ===
... creating word files dat/chin/red/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
710905 dat/chin/red/tot.1/whole.tlw
removed 'dat/chin/red/tot.1/raw.tlw'
removed 'dat/chin/red/tot.1/gud.tlw'
removed 'dat/chin/red/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/chin/red/tot.1/raw.wdf
sample:
ci3 kai1 juan3 di4.2 yi1 hui2 ye3 zuo4.2 zhe3 zi4 yun2 yin1 ceng2 li4.4
guo4 yi1 fan1 meng4 huan4.2 zhi1.1 hou4 gu4 jiang1 zhen1 shi4.1 yin3.1
qu4 er2.1 jie4 tong1 ling2.1 zhi1.1 shuo1 zhuan4.2 ci3 shi2.3 tou2 ji4.1
yi1 shu1 ye3 gu4 yue1.1 zhen1.2 shi4.5 yin3.1 yun2 yun2 dan4 shu1 zhong1
suo3 ji4.1 he2.1 shi4.1 he2.1 ren2 zi4 you4 yun2 jin1 feng1 chen2 liu4.1
liu4.1 yi1 shi4.1 wu2 cheng2 hu1 nian4 ji2.1 dang1 ri4 suo3 you3 zhi1.1
nü3 zi5 yi1 yi1 xi4 kao3 jiao4.3 qu4 jue2 qi2 xing2 zhi3.3 jian4 shi5
jie1.1 chu1 yu2 wo3 zhi1.1 shang4 he2.1 wo3 tang2 tang2 xu1 mei2.1
cheng2.6 bu4 ruo4 bi3.2 qun2 chai1 wo3 shi2.2 kui4 ze2 you3 yu2.1 hui3
yi4.1 wu2 yi4.5 zhen1 da4 wu2 ke3 ru2 he2.1 zhi1.1 ri4 ye3 dang1 ci3 ri4
yu4.1 jiang1 yi3 wang3 suo3 lai4 tian1 en1 zu3 de2.1 jin3.2 yi1.1 wan2.1
ku4 zhi1.1 shi2 yu4.20 gan1.2 yan4.3 fei2 zhi1.1 ri4 bei4.2 fu4.1 xiong1
jiao4.1 yu4.11 zhi1.1 en1 fu4.4 shi1.2 you3.1 gui1.1 tan2 zhi1.1 de2.1
yi3.1 zhi4.1 jin1 ri4 yi1 ji4.12 wu2 cheng2 ban4 sheng1 liao3.1 dao3
zhi1.1 zui4 bian1.1 shu4.4 yi1 ji2.7 yi3.1 gao4 tian1 xia4 zhi1 wo3
zhi1.1 zui4 gu4.2 bu4 mian3 ran2 gui1.2 ge2.1 zhong1 ben3 zi4 li4.4
li4.4 you3 ren2 wan4 bu4 ke3 yin1 wo3 zhi1.1 bu4 xiao4.3 zi4 hu4.1 qi2
duan3 yi1 bing4.1 shi3 qi2 min3.4 mie4 ye3 sui1 jin1 ri4 mao2.1 chuan2.3
peng2.2 you3.3 wa3 zao4.4 sheng2 chuang2 bing4.1 bu4 zu2 fang2.1 wo3
jin1.5 huai2 kuang4 nei4 chen2.5 feng1 xi1.4 yue4 jie1.4 liu3 ting2.2
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
shuo1 dao4.1 xin1.2 suan1 chu3 huang1.1 tang2.2 yu4.4 ke3 bei1 you2.1
lai2 tong2 yi1 meng4 xiu1.2 xiao4 shi4.3 ren2 chi1.1 =
removed 'dat/chin/red/tot.1/raw.wfr'
creating the word frequency file dat/chin/red/tot.1/raw.wfr
the 10 most common words in dat/chin/red/tot.1/raw.tlw:
20798 0.02926 le5
15124 0.02127 de5
14586 0.02052 bu4
11710 0.01647 yi1
11191 0.01574 lai2
10977 0.01544 dao4
10264 0.01444 ren2
9773 0.01375 shi4
9459 0.01331 shuo1
8927 0.01256 wo3
removed 'dat/chin/red/tot.1/raw-whole-wds-summary.tex'
removed 'exp/chin/red/tot.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/chin/red/tot.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:31:07 by tex-make-sample-summary.sh
% Token and word counts for chin/red/tot.1/raw.wfr
%
\def\chinredwholetotPBrawTks{710905}
\def\chinredwholetotPBrawTksPct{100.0}
\def\chinredwholetotPBrawWds{4273}
\def\chinredwholetotPBrawWdsPct{0.6}
copied '/tmp/572678.file' -> 'exp/chin/red/tot.1/raw-whole-wds-summary.tex'
removed '/tmp/572678.file'
creating running text file dat/chin/red/tot.1/gud.wdf
sample:
ci3 kai1 juan3 di4.2 yi1 hui2 ye3 zuo4.2 zhe3 zi4 yun2 yin1 ceng2 li4.4
guo4 yi1 fan1 meng4 huan4.2 zhi1.1 hou4 gu4 jiang1 zhen1 shi4.1 yin3.1
qu4 er2.1 jie4 tong1 ling2.1 zhi1.1 shuo1 zhuan4.2 ci3 shi2.3 tou2 ji4.1
yi1 shu1 ye3 gu4 yue1.1 zhen1.2 shi4.5 yin3.1 yun2 yun2 dan4 shu1 zhong1
suo3 ji4.1 he2.1 shi4.1 he2.1 ren2 zi4 you4 yun2 jin1 feng1 chen2 liu4.1
liu4.1 yi1 shi4.1 wu2 cheng2 hu1 nian4 ji2.1 dang1 ri4 suo3 you3 zhi1.1
nü3 zi5 yi1 yi1 xi4 kao3 jiao4.3 qu4 jue2 qi2 xing2 zhi3.3 jian4 shi5
jie1.1 chu1 yu2 wo3 zhi1.1 shang4 he2.1 wo3 tang2 tang2 xu1 mei2.1
cheng2.6 bu4 ruo4 bi3.2 qun2 chai1 wo3 shi2.2 kui4 ze2 you3 yu2.1 hui3
yi4.1 wu2 yi4.5 zhen1 da4 wu2 ke3 ru2 he2.1 zhi1.1 ri4 ye3 dang1 ci3 ri4
yu4.1 jiang1 yi3 wang3 suo3 lai4 tian1 en1 zu3 de2.1 jin3.2 yi1.1 wan2.1
ku4 zhi1.1 shi2 yu4.20 gan1.2 yan4.3 fei2 zhi1.1 ri4 bei4.2 fu4.1 xiong1
jiao4.1 yu4.11 zhi1.1 en1 fu4.4 shi1.2 you3.1 gui1.1 tan2 zhi1.1 de2.1
yi3.1 zhi4.1 jin1 ri4 yi1 ji4.12 wu2 cheng2 ban4 sheng1 liao3.1 dao3
zhi1.1 zui4 bian1.1 shu4.4 yi1 ji2.7 yi3.1 gao4 tian1 xia4 zhi1 wo3
zhi1.1 zui4 gu4.2 bu4 mian3 ran2 gui1.2 ge2.1 zhong1 ben3 zi4 li4.4
li4.4 you3 ren2 wan4 bu4 ke3 yin1 wo3 zhi1.1 bu4 xiao4.3 zi4 hu4.1 qi2
duan3 yi1 bing4.1 shi3 qi2 min3.4 mie4 ye3 sui1 jin1 ri4 mao2.1 chuan2.3
peng2.2 you3.3 wa3 zao4.4 sheng2 chuang2 bing4.1 bu4 zu2 fang2.1 wo3
jin1.5 huai2 kuang4 nei4 chen2.5 feng1 xi1.4 yue4 jie1.4 liu3 ting2.2
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
qi3 zhi1.1 yan2 geng4 jin4 yi1 gan1.3 yun2 shuo1 dao4.1 xin1.2 suan1
chu3 huang1.1 tang2.2 yu4.4 ke3 bei1 you2.1 lai2 tong2 yi1 meng4 xiu1.2
xiao4 shi4.3 ren2 chi1.1
removed 'dat/chin/red/tot.1/gud.wfr'
creating the word frequency file dat/chin/red/tot.1/gud.wfr
the 10 most common words in dat/chin/red/tot.1/gud.tlw:
20798 0.02942 le5
15124 0.02140 de5
14586 0.02063 bu4
11710 0.01657 yi1
11191 0.01583 lai2
10977 0.01553 dao4
10264 0.01452 ren2
9773 0.01383 shi4
9459 0.01338 shuo1
8927 0.01263 wo3
removed 'dat/chin/red/tot.1/gud-whole-wds-summary.tex'
removed 'exp/chin/red/tot.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/chin/red/tot.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:31:08 by tex-make-sample-summary.sh
% Token and word counts for chin/red/tot.1/gud.wfr
%
\def\chinredwholetotPBgudTks{706889}
\def\chinredwholetotPBgudTksPct{99.4}
\def\chinredwholetotPBgudWds{4271}
\def\chinredwholetotPBgudWdsPct{0.6}
copied '/tmp/572722.file' -> 'exp/chin/red/tot.1/gud-whole-wds-summary.tex'
removed '/tmp/572722.file'
creating running text file dat/chin/red/tot.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/chin/red/tot.1/bad.wfr'
creating the word frequency file dat/chin/red/tot.1/bad.wfr
the 10 most common words in dat/chin/red/tot.1/bad.tlw:
3825 0.95244 =
191 0.04756 **
removed 'dat/chin/red/tot.1/bad-whole-wds-summary.tex'
removed 'exp/chin/red/tot.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/chin/red/tot.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:31:08 by tex-make-sample-summary.sh
% Token and word counts for chin/red/tot.1/bad.wfr
%
\def\chinredwholetotPBbadTks{4016}
\def\chinredwholetotPBbadTksPct{0.6}
\def\chinredwholetotPBbadWds{2}
\def\chinredwholetotPBbadWdsPct{0.0}
copied '/tmp/572766.file' -> 'exp/chin/red/tot.1/bad-whole-wds-summary.tex'
removed '/tmp/572766.file'
lines words bytes file
------- ------- --------- ------------
4273 12805 96720 dat/chin/red/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
4271 12799 96683 dat/chin/red/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
2 6 37 dat/chin/red/tot.1/bad.wfr
tot.1 raw = 710905 gud = 706889 bad = 4016
=== creating the derived word files dat/chin/voa/*/{raw,gud,bad}.{tlw,wdf,wfr} (whole) ===
... creating word files dat/chin/voa/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
59835 dat/chin/voa/tot.1/whole.tlw
removed 'dat/chin/voa/tot.1/raw.tlw'
removed 'dat/chin/voa/tot.1/gud.tlw'
removed 'dat/chin/voa/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/chin/voa/tot.1/raw.wdf
sample:
ge4.1 wei4.1 ting1 zhong4 mei3.1 guo2 zheng4.1 fu3 jue2.2 ding4 jin4 yi1
bu4.1 dong4.2 jie2 mei3.1 guo2 jin4 chu1 kou3 yin2 xing2 xiang4 can1 yu3
zhong1 guo2 xiang4.3 mu4 de5 mei3.1 guo2 gong1 si1.1 ti2 gong1.4 de5
dai4.7 kuan3 zhong1 guo2 biao3 shi4.10 zhei4 xiang4.3 jue2.2 ding4
jiang1 you3 sun3 liang3 guo2 de5 mao4.4 yi4.3 guan1.1 xi5.1 yi3.1 ji2.1
mei3.1 guo2 gong1.1 shang1.1 jie4.1 zai4 zhong1 guo2 de5 li4.1 yi4.5
bing4.1 yao4 qiu2 mei3.1 guo2 gai3 bian4.2 zhei4 ge4 jue2.2 ding4 =
mei3.1 guo2 qing2 bao4.1 zhuan1 jia1 biao3 shi4.10 bei3 jing1.2 xiang4
ba1.1 ji1.7 si1.6 tan3.1 chu1 shou4.6 le5 ke3 yi3.1 zhi4.4 zao4 he2.6
wu3.2 qi4.1 de5 he2.6 cai2.2 liao4 mei3.1 guo2 fa3 lü4.1 jin4.2 zhi3.3
xiang4 ren4.1 he2.1 bang1 zhu4.2 qi2 ta1 guo2 jia1 fa1 zhan3.1 he2.6
wu3.2 qi4.1 de5 guo2 jia1 ti2 gong1.4 dai4.7 kuan3 huo4 dai4.7 kuan3
dan1.3 bao3.1 lu4 tou4 she4.4 bao4.1 dao4 shuo1 zai4 mei3.1 guo2 ke3
neng2 cai3.1 qu3 de5 dui4 zhong1 guo2 de5 cheng2.11 fa2 xing4 cuo4.1
shi1.3 dang1 zhong1 qu3 xiao1.1 jin4 chu1 kou3 yin2 xing2 yu3 zhong1
guo2 de5 he2.2 zuo4.2 ye3 bao1 kuo4.1 zai4 nei4.1 ju4.2 fa3 xin1.1
she4.4 bao4.1 dao4 mei3.1 guo2 jin4 chu1 kou3 yin2 xing2 shi4 zai4 jin1
nian2 er4 yue4 ying1 mei3.1 guo2 guo2 wu4.2 qing1.3 ke4.3 li3 si1.6 tuo1
fu2.14 de5 yao4 qiu2 zai4 san1 shi2.1 tian1 zhi1.1 nei4.1 zan4 shi2
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
nian2 yi3.1 lai2 shi4.3 xing2 zui4.1 da4 de5 dai4.7 kuan3 jie1 shou4
guo2 =
removed 'dat/chin/voa/tot.1/raw.wfr'
creating the word frequency file dat/chin/voa/tot.1/raw.wfr
the 10 most common words in dat/chin/voa/tot.1/raw.tlw:
2486 0.04155 de5
1689 0.02823 guo2
988 0.01651 zhong1
745 0.01245 zai4
683 0.01141 yi1
651 0.01088 ren2
631 0.01055 shi4
528 0.00882 mei3.1
514 0.00859 =
500 0.00836 you3
removed 'dat/chin/voa/tot.1/raw-whole-wds-summary.tex'
removed 'exp/chin/voa/tot.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/chin/voa/tot.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:31:08 by tex-make-sample-summary.sh
% Token and word counts for chin/voa/tot.1/raw.wfr
%
\def\chinvoawholetotPBrawTks{59835}
\def\chinvoawholetotPBrawTksPct{100.0}
\def\chinvoawholetotPBrawWds{1954}
\def\chinvoawholetotPBrawWdsPct{3.3}
copied '/tmp/572861.file' -> 'exp/chin/voa/tot.1/raw-whole-wds-summary.tex'
removed '/tmp/572861.file'
creating running text file dat/chin/voa/tot.1/gud.wdf
sample:
ge4.1 wei4.1 ting1 zhong4 mei3.1 guo2 zheng4.1 fu3 jue2.2 ding4 jin4 yi1
bu4.1 dong4.2 jie2 mei3.1 guo2 jin4 chu1 kou3 yin2 xing2 xiang4 can1 yu3
zhong1 guo2 xiang4.3 mu4 de5 mei3.1 guo2 gong1 si1.1 ti2 gong1.4 de5
dai4.7 kuan3 zhong1 guo2 biao3 shi4.10 zhei4 xiang4.3 jue2.2 ding4
jiang1 you3 sun3 liang3 guo2 de5 mao4.4 yi4.3 guan1.1 xi5.1 yi3.1 ji2.1
mei3.1 guo2 gong1.1 shang1.1 jie4.1 zai4 zhong1 guo2 de5 li4.1 yi4.5
bing4.1 yao4 qiu2 mei3.1 guo2 gai3 bian4.2 zhei4 ge4 jue2.2 ding4 mei3.1
guo2 qing2 bao4.1 zhuan1 jia1 biao3 shi4.10 bei3 jing1.2 xiang4 ba1.1
ji1.7 si1.6 tan3.1 chu1 shou4.6 le5 ke3 yi3.1 zhi4.4 zao4 he2.6 wu3.2
qi4.1 de5 he2.6 cai2.2 liao4 mei3.1 guo2 fa3 lü4.1 jin4.2 zhi3.3 xiang4
ren4.1 he2.1 bang1 zhu4.2 qi2 ta1 guo2 jia1 fa1 zhan3.1 he2.6 wu3.2
qi4.1 de5 guo2 jia1 ti2 gong1.4 dai4.7 kuan3 huo4 dai4.7 kuan3 dan1.3
bao3.1 lu4 tou4 she4.4 bao4.1 dao4 shuo1 zai4 mei3.1 guo2 ke3 neng2
cai3.1 qu3 de5 dui4 zhong1 guo2 de5 cheng2.11 fa2 xing4 cuo4.1 shi1.3
dang1 zhong1 qu3 xiao1.1 jin4 chu1 kou3 yin2 xing2 yu3 zhong1 guo2 de5
he2.2 zuo4.2 ye3 bao1 kuo4.1 zai4 nei4.1 ju4.2 fa3 xin1.1 she4.4 bao4.1
dao4 mei3.1 guo2 jin4 chu1 kou3 yin2 xing2 shi4 zai4 jin1 nian2 er4 yue4
ying1 mei3.1 guo2 guo2 wu4.2 qing1.3 ke4.3 li3 si1.6 tuo1 fu2.14 de5
yao4 qiu2 zai4 san1 shi2.1 tian1 zhi1.1 nei4.1 zan4 shi2 dong4.2 jie2
le5 ji3.1 zhong1 guo2 de5 xiang4.3 mu4 ti2 gong1.4 dai4.7 kuan3 fa3
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
jin1 nian2 jiang1 xiang4 zhong1 guo2 ti2 gong1.4 yi4.22 mei3.1 yuan2.3
de5 dai4.7 kuan3 shi3 zhong1 guo2 cheng2 wei2 nian2 yi3.1 lai2 shi4.3
xing2 zui4.1 da4 de5 dai4.7 kuan3 jie1 shou4 guo2
removed 'dat/chin/voa/tot.1/gud.wfr'
creating the word frequency file dat/chin/voa/tot.1/gud.wfr
the 10 most common words in dat/chin/voa/tot.1/gud.tlw:
2486 0.04227 de5
1689 0.02872 guo2
988 0.01680 zhong1
745 0.01267 zai4
683 0.01161 yi1
651 0.01107 ren2
631 0.01073 shi4
528 0.00898 mei3.1
500 0.00850 you3
455 0.00774 shuo1
removed 'dat/chin/voa/tot.1/gud-whole-wds-summary.tex'
removed 'exp/chin/voa/tot.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/chin/voa/tot.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:31:08 by tex-make-sample-summary.sh
% Token and word counts for chin/voa/tot.1/gud.wfr
%
\def\chinvoawholetotPBgudTks{58813}
\def\chinvoawholetotPBgudTksPct{98.3}
\def\chinvoawholetotPBgudWds{1886}
\def\chinvoawholetotPBgudWdsPct{3.2}
copied '/tmp/572905.file' -> 'exp/chin/voa/tot.1/gud-whole-wds-summary.tex'
removed '/tmp/572905.file'
creating running text file dat/chin/voa/tot.1/bad.wdf
sample:
=
=
=
=
=
1 9 9 5 =
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
25 1 9 9 3 =
removed 'dat/chin/voa/tot.1/bad.wfr'
creating the word frequency file dat/chin/voa/tot.1/bad.wfr
the 10 most common words in dat/chin/voa/tot.1/bad.tlw:
514 0.50294 =
148 0.14481 9
92 0.09002 1
23 0.02250 7
22 0.02153 8
20 0.01957 5
19 0.01859 0
15 0.01468 3
15 0.01468 4
14 0.01370 6
removed 'dat/chin/voa/tot.1/bad-whole-wds-summary.tex'
removed 'exp/chin/voa/tot.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/chin/voa/tot.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:31:08 by tex-make-sample-summary.sh
% Token and word counts for chin/voa/tot.1/bad.wfr
%
\def\chinvoawholetotPBbadTks{1022}
\def\chinvoawholetotPBbadTksPct{1.7}
\def\chinvoawholetotPBbadWds{68}
\def\chinvoawholetotPBbadWdsPct{0.1}
copied '/tmp/572949.file' -> 'exp/chin/voa/tot.1/bad-whole-wds-summary.tex'
removed '/tmp/572949.file'
lines words bytes file
------- ------- --------- ------------
1954 5862 43507 dat/chin/voa/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
1886 5658 42208 dat/chin/voa/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
68 204 1299 dat/chin/voa/tot.1/bad.wfr
tot.1 raw = 59835 gud = 58813 bad = 1022
=== creating the derived word files dat/chip/voa/*/{raw,gud,bad}.{tlw,wdf,wfr} (whole) ===
... creating word files dat/chip/voa/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
60002 dat/chip/voa/tot.1/whole.tlw
removed 'dat/chip/voa/tot.1/raw.tlw'
removed 'dat/chip/voa/tot.1/gud.tlw'
removed 'dat/chip/voa/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/chip/voa/tot.1/raw.wdf
sample:
ge4 wei4 ting1 zhong4 mei3 guo2 zheng4 fu3 jue2 ding4 jin4 yi1 bu4 dong4
jie2 mei3 guo2 jin4 chu1 kou3 yin2 hang2 xiang4 can1 yu4 zhong1 guo2
xiang4 mu4 de5 mei3 guo2 gong1 si1 ti2 gong1 de5 dai4 kuan3 zhong1 guo2
biao3 shi4 zhei4 xiang4 jue2 ding4 jiang1 you3 sun3 liang3 guo2 de5 mao4
yi4 guan1 xi5 yi3 ji2 mei3 guo2 gong1 shang1 jie4 zai4 zhong1 guo2 de5
li4 yi4 bing4 yao1 qiu2 mei3 guo2 gai3 bian4 zhei4 ge4 jue2 ding4 =
mei3 guo2 qing2 bao4 zhuan1 jia1 biao3 shi4 bei3 jing1 xiang4 ba1 ji1
si1 tan3 chu1 shou4 le5 ke3 yi3 zhi4 zao4 he2 wu3 qi4 de5 he2 cai2 liao4
mei3 guo2 fa3 lü4 jin4 zhi3 xiang4 ren4 he2 bang1 zhu4 qi2 ta1 guo2 jia1
fa1 zhan3 he2 wu3 qi4 de5 guo2 jia1 ti2 gong1 dai4 kuan3 huo4 dai4 kuan3
dan1 bao3 lu4 tou4 she4 bao4 dao4 shuo1 zai4 mei3 guo2 ke3 neng2 cai3
qu3 de5 dui4 zhong1 guo2 de5 cheng2 fa2 xing4 cuo4 shi1 dang1 zhong1 qu3
xiao1 jin4 chu1 kou3 yin2 hang2 yu3 zhong1 guo2 de5 he2 zuo4 ye3 bao1
kuo4 zai4 nei4 ju4 fa3 xin1 she4 bao4 dao4 mei3 guo2 jin4 chu1 kou3 yin2
hang2 shi4 zai4 jin1 nian2 er4 yue4 ying4 mei3 guo2 guo2 wu4 qing1 ke4
li3 si1 tuo1 fu2 de5 yao1 qiu2 zai4 san1 shi2 tian1 zhi1 nei4 zan4 shi2
dong4 jie2 le5 gei3 zhong1 guo2 de5 xiang4 mu4 ti2 gong1 dai4 kuan3 fa3
xin1 she4 hai2 bao4 dao4 shuo1 hou4 lai2 jin4 chu1 kou3 yin2 hang2 zai4
si4 yue4 shi2 qi1 hao4 biao3 shi4 gai1 hang2 yi3 jing1 ke3 yi3 zai4 ci4
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
yi4 mei3 yuan2 de5 dai4 kuan3 shi3 zhong1 guo2 cheng2 wei2 yi1 jiu3 jiu3
san1 nian2 yi3 lai2 shi4 hang2 zui4 da4 de5 dai4 kuan3 jie1 shou4 guo2 =
removed 'dat/chip/voa/tot.1/raw.wfr'
creating the word frequency file dat/chip/voa/tot.1/raw.wfr
the 10 most common words in dat/chip/voa/tot.1/raw.tlw:
2517 0.04195 de5
1689 0.02815 guo2
1340 0.02233 shi4
1006 0.01677 zhong1
846 0.01410 yi1
777 0.01295 zai4
671 0.01118 bu4
659 0.01098 he2
651 0.01085 ren2
573 0.00955 shi2
removed 'dat/chip/voa/tot.1/raw-whole-wds-summary.tex'
removed 'exp/chip/voa/tot.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/chip/voa/tot.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:31:09 by tex-make-sample-summary.sh
% Token and word counts for chip/voa/tot.1/raw.wfr
%
\def\chipvoawholetotPBrawTks{60002}
\def\chipvoawholetotPBrawTksPct{100.0}
\def\chipvoawholetotPBrawWds{933}
\def\chipvoawholetotPBrawWdsPct{1.6}
copied '/tmp/573044.file' -> 'exp/chip/voa/tot.1/raw-whole-wds-summary.tex'
removed '/tmp/573044.file'
creating running text file dat/chip/voa/tot.1/gud.wdf
sample:
ge4 wei4 ting1 zhong4 mei3 guo2 zheng4 fu3 jue2 ding4 jin4 yi1 bu4 dong4
jie2 mei3 guo2 jin4 chu1 kou3 yin2 hang2 xiang4 can1 yu4 zhong1 guo2
xiang4 mu4 de5 mei3 guo2 gong1 si1 ti2 gong1 de5 dai4 kuan3 zhong1 guo2
biao3 shi4 zhei4 xiang4 jue2 ding4 jiang1 you3 sun3 liang3 guo2 de5 mao4
yi4 guan1 xi5 yi3 ji2 mei3 guo2 gong1 shang1 jie4 zai4 zhong1 guo2 de5
li4 yi4 bing4 yao1 qiu2 mei3 guo2 gai3 bian4 zhei4 ge4 jue2 ding4 mei3
guo2 qing2 bao4 zhuan1 jia1 biao3 shi4 bei3 jing1 xiang4 ba1 ji1 si1
tan3 chu1 shou4 le5 ke3 yi3 zhi4 zao4 he2 wu3 qi4 de5 he2 cai2 liao4
mei3 guo2 fa3 lü4 jin4 zhi3 xiang4 ren4 he2 bang1 zhu4 qi2 ta1 guo2 jia1
fa1 zhan3 he2 wu3 qi4 de5 guo2 jia1 ti2 gong1 dai4 kuan3 huo4 dai4 kuan3
dan1 bao3 lu4 tou4 she4 bao4 dao4 shuo1 zai4 mei3 guo2 ke3 neng2 cai3
qu3 de5 dui4 zhong1 guo2 de5 cheng2 fa2 xing4 cuo4 shi1 dang1 zhong1 qu3
xiao1 jin4 chu1 kou3 yin2 hang2 yu3 zhong1 guo2 de5 he2 zuo4 ye3 bao1
kuo4 zai4 nei4 ju4 fa3 xin1 she4 bao4 dao4 mei3 guo2 jin4 chu1 kou3 yin2
hang2 shi4 zai4 jin1 nian2 er4 yue4 ying4 mei3 guo2 guo2 wu4 qing1 ke4
li3 si1 tuo1 fu2 de5 yao1 qiu2 zai4 san1 shi2 tian1 zhi1 nei4 zan4 shi2
dong4 jie2 le5 gei3 zhong1 guo2 de5 xiang4 mu4 ti2 gong1 dai4 kuan3 fa3
xin1 she4 hai2 bao4 dao4 shuo1 hou4 lai2 jin4 chu1 kou3 yin2 hang2 zai4
si4 yue4 shi2 qi1 hao4 biao3 shi4 gai1 hang2 yi3 jing1 ke3 yi3 zai4 ci4
kai1 zhan3 you3 guan1 zhong1 guo2 de5 ye4 wu4 le5 dan4 shi4 zai4 zhei4
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
wu3 yi4 mei3 yuan2 de5 dai4 kuan3 shi3 zhong1 guo2 cheng2 wei2 yi1 jiu3
jiu3 san1 nian2 yi3 lai2 shi4 hang2 zui4 da4 de5 dai4 kuan3 jie1 shou4
guo2
removed 'dat/chip/voa/tot.1/gud.wfr'
creating the word frequency file dat/chip/voa/tot.1/gud.wfr
the 10 most common words in dat/chip/voa/tot.1/gud.tlw:
2517 0.04232 de5
1689 0.02840 guo2
1340 0.02253 shi4
1006 0.01691 zhong1
846 0.01422 yi1
777 0.01306 zai4
671 0.01128 bu4
659 0.01108 he2
651 0.01095 ren2
573 0.00963 shi2
removed 'dat/chip/voa/tot.1/gud-whole-wds-summary.tex'
removed 'exp/chip/voa/tot.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/chip/voa/tot.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:31:09 by tex-make-sample-summary.sh
% Token and word counts for chip/voa/tot.1/gud.wfr
%
\def\chipvoawholetotPBgudTks{59476}
\def\chipvoawholetotPBgudTksPct{99.1}
\def\chipvoawholetotPBgudWds{930}
\def\chipvoawholetotPBgudWdsPct{1.5}
copied '/tmp/573088.file' -> 'exp/chip/voa/tot.1/gud-whole-wds-summary.tex'
removed '/tmp/573088.file'
creating running text file dat/chip/voa/tot.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/chip/voa/tot.1/bad.wfr'
creating the word frequency file dat/chip/voa/tot.1/bad.wfr
the 10 most common words in dat/chip/voa/tot.1/bad.tlw:
514 0.97719 =
7 0.01331 *
5 0.00951 **
removed 'dat/chip/voa/tot.1/bad-whole-wds-summary.tex'
removed 'exp/chip/voa/tot.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/chip/voa/tot.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:31:09 by tex-make-sample-summary.sh
% Token and word counts for chip/voa/tot.1/bad.wfr
%
\def\chipvoawholetotPBbadTks{526}
\def\chipvoawholetotPBbadTksPct{0.9}
\def\chipvoawholetotPBbadWds{3}
\def\chipvoawholetotPBbadWdsPct{0.0}
copied '/tmp/573132.file' -> 'exp/chip/voa/tot.1/bad-whole-wds-summary.tex'
removed '/tmp/573132.file'
lines words bytes file
------- ------- --------- ------------
933 2799 19759 dat/chip/voa/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
930 2790 19704 dat/chip/voa/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
3 9 55 dat/chip/voa/tot.1/bad.wfr
tot.1 raw = 60002 gud = 59476 bad = 526
=== creating the derived word files dat/tibe/vim/*/{raw,gud,bad}.{tlw,wdf,wfr} (whole) ===
... creating word files dat/tibe/vim/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
53356 dat/tibe/vim/tot.1/whole.tlw
removed 'dat/tibe/vim/tot.1/raw.tlw'
removed 'dat/tibe/vim/tot.1/gud.tlw'
removed 'dat/tibe/vim/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/tibe/vim/tot.1/raw.wdf
sample:
SHES PA CHEN PO YONGS SU SBYANGS PA LAS NGES PAR BYUNG BA SANGS RGYAS
KYIS BYIN GYI RLABS KYIS BYIN GYIS BRLABS PA CHOS KYI GRONG KHYER SRUNG
BA DAM PA'I CHOS YONGS SU 'DZIN PA SENG GE'I SGRA CHEN PO SGROGS PA
PHYOGS BCUR SGRA SHIN TU BSGRAGS PA GSOL BA MA BTAB PAR SEMS CAN THAMS
CAD KYI DGE BA'I BSHES GNYEN DU GYUR PA DKON MCHOG GSUM GYI RIGS RGYUN
MI 'CHAD PAR BYED PA BDUD DANG PHYIR RGOL BA BCOM PA PHA ROL GYI RGOL BA
THAMS CAD KYIS ZIL GYIS MI NON PA DRAN PA DANG BLO GROS DANG RTOGS PA
DANG TING NGE 'DZIN DANG GZUNGS DANG SPOBS PA PHUN SUM TSOGS PA SGRIB PA
DANG KUN NAS LDANG BA THAMS CAD DANG BRAL BA SGRIB PA MED PA'I RNAM PAR
THAR PA LA GNAS PA SPOBS PA RGYUN MI 'CHAD PA SPYIN PA DANG DUL BA DANG
MI 'GYUR BA DANG YANG DAG PAR SDOM PA DANG TSUL KHRIMS DANG BZOD PA DANG
BRTZON 'GRUS DANG BSAM GTAN DANG SHES RAB DANG THABS LA MKHAS PA DANG
SMON LAM DANG STOBS DANG YE SHES KYI PHA ROL TU PHYIN PA LAS NGES PAR
BYUNG BA MI DMIGS PA'I CHOS LA BZOD PA DANG LDAN PA PHYIR MI LDOG PA'I
CHOS KYI 'KHOR LO SKOR BA MTSAN NYID MED PA'I PHYIR RGYAS BTAB BA * SEMS
CAN THAMS CAD KYI DBANG PO SHES PA LA MKHAS PA 'KHOR THAMS CAD ZIL GYIS
MI NON PA'I MI 'JIGS PAS RNAM PAR GNON PA BSOD NAMS DANG YE SHES KYI
TSOGS CHEN PO BSAGS PA MTSAN DANG DPE BYAD BZANG PO THAMS CAD KYIS LUS
SHIN TU BRGYAN PA GZUGS DAM PA 'JIN PA RGYAN DANG BRAL BA RI RAB KYI
RTZE MO MTHO BA BZHIN DU SNYAN PA DANG GRAGS PAS MNGON PAR 'PHAGS PA
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/tibe/vim/tot.1/raw.wfr'
creating the word frequency file dat/tibe/vim/tot.1/raw.wfr
the 10 most common words in dat/tibe/vim/tot.1/raw.tlw:
2938 0.05506 PA
1545 0.02896 DE
1462 0.02740 DANG
1271 0.02382 PAR
1106 0.02073 LA
1039 0.01947 BA
882 0.01653 KYI
823 0.01542 SEMS
806 0.01511 PA'I
785 0.01471 MA
removed 'dat/tibe/vim/tot.1/raw-whole-wds-summary.tex'
removed 'exp/tibe/vim/tot.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/tibe/vim/tot.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:31:09 by tex-make-sample-summary.sh
% Token and word counts for tibe/vim/tot.1/raw.wfr
%
\def\tibevimwholetotPBrawTks{53356}
\def\tibevimwholetotPBrawTksPct{100.0}
\def\tibevimwholetotPBrawWds{1473}
\def\tibevimwholetotPBrawWdsPct{2.8}
copied '/tmp/573227.file' -> 'exp/tibe/vim/tot.1/raw-whole-wds-summary.tex'
removed '/tmp/573227.file'
creating running text file dat/tibe/vim/tot.1/gud.wdf
sample:
SHES PA CHEN PO YONGS SU SBYANGS PA LAS NGES PAR BYUNG BA SANGS RGYAS
KYIS BYIN GYI RLABS KYIS BYIN GYIS BRLABS PA CHOS KYI GRONG KHYER SRUNG
BA DAM PA'I CHOS YONGS SU 'DZIN PA SENG GE'I SGRA CHEN PO SGROGS PA
PHYOGS BCUR SGRA SHIN TU BSGRAGS PA GSOL BA MA BTAB PAR SEMS CAN THAMS
CAD KYI DGE BA'I BSHES GNYEN DU GYUR PA DKON MCHOG GSUM GYI RIGS RGYUN
MI 'CHAD PAR BYED PA BDUD DANG PHYIR RGOL BA BCOM PA PHA ROL GYI RGOL BA
THAMS CAD KYIS ZIL GYIS MI NON PA DRAN PA DANG BLO GROS DANG RTOGS PA
DANG TING NGE 'DZIN DANG GZUNGS DANG SPOBS PA PHUN SUM TSOGS PA SGRIB PA
DANG KUN NAS LDANG BA THAMS CAD DANG BRAL BA SGRIB PA MED PA'I RNAM PAR
THAR PA LA GNAS PA SPOBS PA RGYUN MI 'CHAD PA SPYIN PA DANG DUL BA DANG
MI 'GYUR BA DANG YANG DAG PAR SDOM PA DANG TSUL KHRIMS DANG BZOD PA DANG
BRTZON 'GRUS DANG BSAM GTAN DANG SHES RAB DANG THABS LA MKHAS PA DANG
SMON LAM DANG STOBS DANG YE SHES KYI PHA ROL TU PHYIN PA LAS NGES PAR
BYUNG BA MI DMIGS PA'I CHOS LA BZOD PA DANG LDAN PA PHYIR MI LDOG PA'I
CHOS KYI 'KHOR LO SKOR BA MTSAN NYID MED PA'I PHYIR RGYAS BTAB BA SEMS
CAN THAMS CAD KYI DBANG PO SHES PA LA MKHAS PA 'KHOR THAMS CAD ZIL GYIS
MI NON PA'I MI 'JIGS PAS RNAM PAR GNON PA BSOD NAMS DANG YE SHES KYI
TSOGS CHEN PO BSAGS PA MTSAN DANG DPE BYAD BZANG PO THAMS CAD KYIS LUS
SHIN TU BRGYAN PA GZUGS DAM PA 'JIN PA RGYAN DANG BRAL BA RI RAB KYI
RTZE MO MTHO BA BZHIN DU SNYAN PA DANG GRAGS PAS MNGON PAR 'PHAGS PA
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
KYIS GSUNGS PA LA MNGON PAR BSTOD DO SNGON GYI SBYOR BA DANG DAM PA'I
CHOS GTAD PA'I LE'U ZHES BYA STE BCU GNYIS PA'O 'PHAGS PA DRI MA MED PAR
GRAGS PAS BSTAN PA ZHES BYA BA THEG PA CHEN PO'I MDO RDZOGS SO
removed 'dat/tibe/vim/tot.1/gud.wfr'
creating the word frequency file dat/tibe/vim/tot.1/gud.wfr
the 10 most common words in dat/tibe/vim/tot.1/gud.tlw:
2938 0.05514 PA
1545 0.02899 DE
1462 0.02744 DANG
1271 0.02385 PAR
1106 0.02076 LA
1039 0.01950 BA
882 0.01655 KYI
823 0.01544 SEMS
806 0.01513 PA'I
785 0.01473 MA
removed 'dat/tibe/vim/tot.1/gud-whole-wds-summary.tex'
removed 'exp/tibe/vim/tot.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/tibe/vim/tot.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:31:09 by tex-make-sample-summary.sh
% Token and word counts for tibe/vim/tot.1/gud.wfr
%
\def\tibevimwholetotPBgudTks{53287}
\def\tibevimwholetotPBgudTksPct{99.9}
\def\tibevimwholetotPBgudWds{1469}
\def\tibevimwholetotPBgudWdsPct{2.8}
copied '/tmp/573271.file' -> 'exp/tibe/vim/tot.1/gud-whole-wds-summary.tex'
removed '/tmp/573271.file'
creating running text file dat/tibe/vim/tot.1/bad.wdf
sample:
* * * * =
=
*SH'A * =
=
* * * =
=
* * * * * =
* * =
=
* =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/tibe/vim/tot.1/bad.wfr'
creating the word frequency file dat/tibe/vim/tot.1/bad.wfr
the 10 most common words in dat/tibe/vim/tot.1/bad.tlw:
42 0.60870 =
25 0.36232 *
1 0.01449 *KLUNG
1 0.01449 *SH'A
removed 'dat/tibe/vim/tot.1/bad-whole-wds-summary.tex'
removed 'exp/tibe/vim/tot.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/tibe/vim/tot.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:31:09 by tex-make-sample-summary.sh
% Token and word counts for tibe/vim/tot.1/bad.wfr
%
\def\tibevimwholetotPBbadTks{69}
\def\tibevimwholetotPBbadTksPct{0.1}
\def\tibevimwholetotPBbadWds{4}
\def\tibevimwholetotPBbadWdsPct{0.0}
copied '/tmp/573315.file' -> 'exp/tibe/vim/tot.1/bad-whole-wds-summary.tex'
removed '/tmp/573315.file'
lines words bytes file
------- ------- --------- ------------
1473 4419 31385 dat/tibe/vim/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
1469 4407 31304 dat/tibe/vim/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
4 12 81 dat/tibe/vim/tot.1/bad.wfr
tot.1 raw = 53356 gud = 53287 bad = 69
=== creating the derived word files dat/tibe/ccv/*/{raw,gud,bad}.{tlw,wdf,wfr} (whole) ===
... creating word files dat/tibe/ccv/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
88669 dat/tibe/ccv/tot.1/whole.tlw
removed 'dat/tibe/ccv/tot.1/raw.tlw'
removed 'dat/tibe/ccv/tot.1/gud.tlw'
removed 'dat/tibe/ccv/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/tibe/ccv/tot.1/raw.wdf
sample:
=
=
RGYA GAR SKAD DU PRA M'A nA B'ARTI KA * BRATTI N'A MA BOD SKAD DU TSAD
MA RNAM 'GREL GYI 'GREL PA ZHES BYA BA BAM BO DANG PO BCOM LDAN 'DAS
'JAM DPAL YE SHES SEMS DPA' LA PHYAG 'TSAL LO SRID PA'I GNAS 'JUG NGA
RGYAL GYIS BYAS 'BIGS BYED DE NYID KYIS KHYAB GANG YIN LA RAB RIB DBANG
GIS MI BZAD MUN PA LTAR 'JUG PHA ROL LTA 'DI DAG NI 'DOD PAS MYOS PA LAS
RGYAL BA ZHES RAB GRAGS DE KHO NA NYID SNANG BA CAN 'JIG RTEN MA LUS
SNANG BYED BDUD RTZI'I BDE BA DES NI 'JIG RTEN DAG BYED SHOG DE LTAR
'PHAGS PA'I BDEN PA BZHI LA 'JUG PA YIN PA'I PHYIR RJES SU DPAG PA RNAM
PAR BZHAG NAS DE NYID BSTAN PAR BYA BA'I PHYIR LE'U GNYIS PAS PHYAG
'TSAL BA'I TSIGS SU BCAD PA GSAL BAR BSHAD PAR MDZAD DO 'DIR TSAD MA'I
MTSAD NYID DANG BCOM LDAN 'DAS TSAD MAR GYUR PAR BZHED NAS SLOB DPON
GYIS BSTAN BCOS KYI DANG POR TSAD MAR GYUR PA ZHES PAS BSTOD PA GSUNGS
SO TSAD MAR GYUR PA 'GRO LA PHAN MDZAD BZHED STON PA BDE GSHEGS SKYOB LA
PHYAG 'TSAL NAS RANG GI GZHUNG LUGS 'THOR LAS 'DIR GCIG NYID TSAD MA
GRUB PA KUN LAS BTUS PA BRTZAM ZHES GSUNGS TE 'DIR YANG SNGA MA PHYENG
KYIS NI RGYU DANG 'BRAS BU PHUN SUM TSOGS PAS TSAD MAR GYUR PA'I BCOM
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/tibe/ccv/tot.1/raw.wfr'
creating the word frequency file dat/tibe/ccv/tot.1/raw.wfr
the 10 most common words in dat/tibe/ccv/tot.1/raw.tlw:
6162 0.06949 PA
2775 0.03130 LA
2695 0.03039 BA
2473 0.02789 YIN
2386 0.02691 PA'I
2168 0.02445 NA
2154 0.02429 DE
2068 0.02332 PAR
2019 0.02277 MA
1858 0.02095 NI
removed 'dat/tibe/ccv/tot.1/raw-whole-wds-summary.tex'
removed 'exp/tibe/ccv/tot.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/tibe/ccv/tot.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:31:09 by tex-make-sample-summary.sh
% Token and word counts for tibe/ccv/tot.1/raw.wfr
%
\def\tibeccvwholetotPBrawTks{88669}
\def\tibeccvwholetotPBrawTksPct{100.0}
\def\tibeccvwholetotPBrawWds{1166}
\def\tibeccvwholetotPBrawWdsPct{1.3}
copied '/tmp/573410.file' -> 'exp/tibe/ccv/tot.1/raw-whole-wds-summary.tex'
removed '/tmp/573410.file'
creating running text file dat/tibe/ccv/tot.1/gud.wdf
sample:
RGYA GAR SKAD DU PRA M'A nA B'ARTI KA BRATTI N'A MA BOD SKAD DU TSAD MA
RNAM 'GREL GYI 'GREL PA ZHES BYA BA BAM BO DANG PO BCOM LDAN 'DAS 'JAM
DPAL YE SHES SEMS DPA' LA PHYAG 'TSAL LO SRID PA'I GNAS 'JUG NGA RGYAL
GYIS BYAS 'BIGS BYED DE NYID KYIS KHYAB GANG YIN LA RAB RIB DBANG GIS MI
BZAD MUN PA LTAR 'JUG PHA ROL LTA 'DI DAG NI 'DOD PAS MYOS PA LAS RGYAL
BA ZHES RAB GRAGS DE KHO NA NYID SNANG BA CAN 'JIG RTEN MA LUS SNANG
BYED BDUD RTZI'I BDE BA DES NI 'JIG RTEN DAG BYED SHOG DE LTAR 'PHAGS
PA'I BDEN PA BZHI LA 'JUG PA YIN PA'I PHYIR RJES SU DPAG PA RNAM PAR
BZHAG NAS DE NYID BSTAN PAR BYA BA'I PHYIR LE'U GNYIS PAS PHYAG 'TSAL
BA'I TSIGS SU BCAD PA GSAL BAR BSHAD PAR MDZAD DO 'DIR TSAD MA'I MTSAD
NYID DANG BCOM LDAN 'DAS TSAD MAR GYUR PAR BZHED NAS SLOB DPON GYIS
BSTAN BCOS KYI DANG POR TSAD MAR GYUR PA ZHES PAS BSTOD PA GSUNGS SO
TSAD MAR GYUR PA 'GRO LA PHAN MDZAD BZHED STON PA BDE GSHEGS SKYOB LA
PHYAG 'TSAL NAS RANG GI GZHUNG LUGS 'THOR LAS 'DIR GCIG NYID TSAD MA
GRUB PA KUN LAS BTUS PA BRTZAM ZHES GSUNGS TE 'DIR YANG SNGA MA PHYENG
KYIS NI RGYU DANG 'BRAS BU PHUN SUM TSOGS PAS TSAD MAR GYUR PA'I BCOM
LDAN 'DAS BSTAN PAR MDZAD DO DE LA RGYU PHUN SUM TSOGS PA NI GNYIS TE
SNYING RJE DANG THABS SO DE LA SNYING RJE NI 'GRO LA PHAN PAR BZHED CES
BYA BAS BSTAN TO THABS GOMS PAR BYA BA NI STON PA ZHES BYA BAS SO 'BRAS
BU PHUN SUM TSOGS PA YANG GNYIS TE RANG GI DON PHUN SUM TSOGS PA DANG
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
'BYUNG GNAS KYI ZHABS LA BTUD DE BSTEN NAS NYI MA SBAS PAS SBYAR BA TSAD
MA RNAM 'GREL GYI 'GREL PA LAS TSAD MA'I MTSAN NYID KYI LE'U STE GNYIS
PA'O
removed 'dat/tibe/ccv/tot.1/gud.wfr'
creating the word frequency file dat/tibe/ccv/tot.1/gud.wfr
the 10 most common words in dat/tibe/ccv/tot.1/gud.tlw:
6162 0.06953 PA
2775 0.03131 LA
2695 0.03041 BA
2473 0.02791 YIN
2386 0.02692 PA'I
2168 0.02446 NA
2154 0.02431 DE
2068 0.02334 PAR
2019 0.02278 MA
1858 0.02097 NI
removed 'dat/tibe/ccv/tot.1/gud-whole-wds-summary.tex'
removed 'exp/tibe/ccv/tot.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/tibe/ccv/tot.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:31:10 by tex-make-sample-summary.sh
% Token and word counts for tibe/ccv/tot.1/gud.wfr
%
\def\tibeccvwholetotPBgudTks{88620}
\def\tibeccvwholetotPBgudTksPct{99.9}
\def\tibeccvwholetotPBgudWds{1155}
\def\tibeccvwholetotPBgudWdsPct{1.3}
copied '/tmp/573454.file' -> 'exp/tibe/ccv/tot.1/gud-whole-wds-summary.tex'
removed '/tmp/573454.file'
creating running text file dat/tibe/ccv/tot.1/bad.wdf
sample:
=
=
* ONGS =
=
*MIN *GANG =
=
RIG*BYED RIG*BYED =
=
=
AGZUGS =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/tibe/ccv/tot.1/bad.wfr'
creating the word frequency file dat/tibe/ccv/tot.1/bad.wfr
the 10 most common words in dat/tibe/ccv/tot.1/bad.tlw:
37 0.75510 =
2 0.04082 A
2 0.04082 RIG*BYED
1 0.02041 'DI8
1 0.02041 *
1 0.02041 *GANG
1 0.02041 *MIN
1 0.02041 *NYID
1 0.02041 AGZUGS
1 0.02041 BA*
removed 'dat/tibe/ccv/tot.1/bad-whole-wds-summary.tex'
removed 'exp/tibe/ccv/tot.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/tibe/ccv/tot.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:31:10 by tex-make-sample-summary.sh
% Token and word counts for tibe/ccv/tot.1/bad.wfr
%
\def\tibeccvwholetotPBbadTks{49}
\def\tibeccvwholetotPBbadTksPct{0.1}
\def\tibeccvwholetotPBbadWds{11}
\def\tibeccvwholetotPBbadWdsPct{0.0}
copied '/tmp/573498.file' -> 'exp/tibe/ccv/tot.1/bad-whole-wds-summary.tex'
removed '/tmp/573498.file'
lines words bytes file
------- ------- --------- ------------
1166 3498 24724 dat/tibe/ccv/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
1155 3465 24495 dat/tibe/ccv/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
11 33 229 dat/tibe/ccv/tot.1/bad.wfr
tot.1 raw = 88669 gud = 88620 bad = 49
=== creating the derived word files dat/tibe/pmi/*/{raw,gud,bad}.{tlw,wdf,wfr} (whole) ===
... creating word files dat/tibe/pmi/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
143331 dat/tibe/pmi/tot.1/whole.tlw
removed 'dat/tibe/pmi/tot.1/raw.tlw'
removed 'dat/tibe/pmi/tot.1/gud.tlw'
removed 'dat/tibe/pmi/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/tibe/pmi/tot.1/raw.wdf
sample:
LA 'THAMS PAS 'DI SNANG SPRE'U'I GAR BAR MED YON POR BSGYUR BA'I RNAM G
YENG GIS GTAN 'DUN RLUNG LA BSKUR BA'I GTAM 'DI GLENG DE LA 'DIR GYI NA
PA BLO BZANG YE SHES BSTAN 'DZIN RGYA MTSOR 'BOD PA BDAG DGA' LDAN KHRI
THOG DRUG CU RE DGU PA YONGS 'DZIN KHRI CHEN BYANG CHUB CHOS 'PHEL DANG
DE'I SPRUL SKU DGA' LDAN KHRI THOG BRGYAD CU GYA LNGA PA KHRI CHEN BLO
BZANG TSUL KHRIMS DPAL LDAN GYI YANG SPRUL DU SGRO BTAGS KYANG RANG BLO
RANG LA LKOG TU MA GYUR PAS DAM PA DE DAG GI SKYE SPRUL DU 'OS PA'I YON
TAN NAM MKHA'I PADMO'I MCHED ZLAR GYUR RUNG SNGON LAS BTZAN POS SPRUL
SKU'I MING 'DZIN DU STES DBANG GIS SON CING RJE GUNG THANG PAS SKU SKYE
BSTAN DON DU BYON NA BSHAD SGRUB LAG RJES SHIG YOD DGOS GSUNGS PA LTAR
SNGON GYI SKYES BU DAM PA RNAMS KYI RNAM THAR MTHONG NA YID 'PHROG CING
THOS NA DAD PA SKYE LA GDUL BYA'I RGYUD LA RNAM GROL THAR PA'I BAG CHAGS
'JOG NUS PA DE LTA BU ZHIG NI RMONGS PA DUG GSUM GYI GONG BU 'DU SHES
GSUM PA KHO BO LTA BU LA RUS SBAL GYI SPU BZHIN GA LA 'ONG DE LTAR MED
KYANG BLA MA'I MING TZAM 'DZIN KHUL STABS MING SKAM DON STONG DU MA SONG
TZAM GYI THOS BSAM BSHAD SGRUB KYI SGO NAS BSTAN PA 'DZIN SKYONG SPEL
BA'I BYA BA 'DI BYAS KYI LAG RJES PHRAN BU ZHIG DGOS NGES KYANG DE YANG
MA BRTAG MA DPYAD NA YOD YOD 'DRA LA BRTAG NA DPYAD MI BZOD PA 'JA' TSON
GYI RANG BZHIN LAS STON RGYU MA MCHIS PA ZHIG GIS 'DI SNANG ZA ZI'I RJES
GCOD KYI LO RGYUS YI GER 'GOD RGYU 'DAB CHAGS PHA WANG MKHA' LDING DU
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
DGE LEGS 'PHEL =
removed 'dat/tibe/pmi/tot.1/raw.wfr'
creating the word frequency file dat/tibe/pmi/tot.1/raw.wfr
the 10 most common words in dat/tibe/pmi/tot.1/raw.tlw:
2945 0.02055 DANG
2652 0.01850 PA
1906 0.01330 NAS
1789 0.01248 DU
1559 0.01088 PA'I
1532 0.01069 BA
1457 0.01017 LA
1368 0.00954 KYI
1337 0.00933 PO
1248 0.00871 MA
removed 'dat/tibe/pmi/tot.1/raw-whole-wds-summary.tex'
removed 'exp/tibe/pmi/tot.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/tibe/pmi/tot.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:31:10 by tex-make-sample-summary.sh
% Token and word counts for tibe/pmi/tot.1/raw.wfr
%
\def\tibepmiwholetotPBrawTks{143331}
\def\tibepmiwholetotPBrawTksPct{100.0}
\def\tibepmiwholetotPBrawWds{2946}
\def\tibepmiwholetotPBrawWdsPct{2.1}
copied '/tmp/573593.file' -> 'exp/tibe/pmi/tot.1/raw-whole-wds-summary.tex'
removed '/tmp/573593.file'
creating running text file dat/tibe/pmi/tot.1/gud.wdf
sample:
LA 'THAMS PAS 'DI SNANG SPRE'U'I GAR BAR MED YON POR BSGYUR BA'I RNAM G
YENG GIS GTAN 'DUN RLUNG LA BSKUR BA'I GTAM 'DI GLENG DE LA 'DIR GYI NA
PA BLO BZANG YE SHES BSTAN 'DZIN RGYA MTSOR 'BOD PA BDAG DGA' LDAN KHRI
THOG DRUG CU RE DGU PA YONGS 'DZIN KHRI CHEN BYANG CHUB CHOS 'PHEL DANG
DE'I SPRUL SKU DGA' LDAN KHRI THOG BRGYAD CU GYA LNGA PA KHRI CHEN BLO
BZANG TSUL KHRIMS DPAL LDAN GYI YANG SPRUL DU SGRO BTAGS KYANG RANG BLO
RANG LA LKOG TU MA GYUR PAS DAM PA DE DAG GI SKYE SPRUL DU 'OS PA'I YON
TAN NAM MKHA'I PADMO'I MCHED ZLAR GYUR RUNG SNGON LAS BTZAN POS SPRUL
SKU'I MING 'DZIN DU STES DBANG GIS SON CING RJE GUNG THANG PAS SKU SKYE
BSTAN DON DU BYON NA BSHAD SGRUB LAG RJES SHIG YOD DGOS GSUNGS PA LTAR
SNGON GYI SKYES BU DAM PA RNAMS KYI RNAM THAR MTHONG NA YID 'PHROG CING
THOS NA DAD PA SKYE LA GDUL BYA'I RGYUD LA RNAM GROL THAR PA'I BAG CHAGS
'JOG NUS PA DE LTA BU ZHIG NI RMONGS PA DUG GSUM GYI GONG BU 'DU SHES
GSUM PA KHO BO LTA BU LA RUS SBAL GYI SPU BZHIN GA LA 'ONG DE LTAR MED
KYANG BLA MA'I MING TZAM 'DZIN KHUL STABS MING SKAM DON STONG DU MA SONG
TZAM GYI THOS BSAM BSHAD SGRUB KYI SGO NAS BSTAN PA 'DZIN SKYONG SPEL
BA'I BYA BA 'DI BYAS KYI LAG RJES PHRAN BU ZHIG DGOS NGES KYANG DE YANG
MA BRTAG MA DPYAD NA YOD YOD 'DRA LA BRTAG NA DPYAD MI BZOD PA 'JA' TSON
GYI RANG BZHIN LAS STON RGYU MA MCHIS PA ZHIG GIS 'DI SNANG ZA ZI'I RJES
GCOD KYI LO RGYUS YI GER 'GOD RGYU 'DAB CHAGS PHA WANG MKHA' LDING DU
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
NYAMS DGA' 'KHRUL PA'I GRONG KHYER DU 'DI SNANG CHOS BRGYAD SGYU MA'I
ZLOS GAR STONG DAL MED GLOG LTAR BSGYUR BA'I YA MTSAN LA BLTA PHYIR MES
POS GDONG BZHI SPRUL LAM SNYAM DGE LEGS 'PHEL
removed 'dat/tibe/pmi/tot.1/gud.wfr'
creating the word frequency file dat/tibe/pmi/tot.1/gud.wfr
the 10 most common words in dat/tibe/pmi/tot.1/gud.tlw:
2945 0.02055 DANG
2652 0.01851 PA
1906 0.01330 NAS
1789 0.01249 DU
1559 0.01088 PA'I
1532 0.01069 BA
1457 0.01017 LA
1368 0.00955 KYI
1337 0.00933 PO
1248 0.00871 MA
removed 'dat/tibe/pmi/tot.1/gud-whole-wds-summary.tex'
removed 'exp/tibe/pmi/tot.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/tibe/pmi/tot.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:31:10 by tex-make-sample-summary.sh
% Token and word counts for tibe/pmi/tot.1/gud.wfr
%
\def\tibepmiwholetotPBgudTks{143289}
\def\tibepmiwholetotPBgudTksPct{100.0}
\def\tibepmiwholetotPBgudWds{2932}
\def\tibepmiwholetotPBgudWdsPct{2.0}
copied '/tmp/573637.file' -> 'exp/tibe/pmi/tot.1/gud-whole-wds-summary.tex'
removed '/tmp/573637.file'
creating running text file dat/tibe/pmi/tot.1/bad.wdf
sample:
GSUm LAm TZAR+YA 'Am =
GSUm =
SAm WAm ** ** ** ** ** =
** WAm ** ** ** ** ** ** GSO\ \AR ** ** ** ** ** E'I ** thAN GSUm KA:
thAN 1 KA: GSUm WAm =
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/tibe/pmi/tot.1/bad.wfr'
creating the word frequency file dat/tibe/pmi/tot.1/bad.wfr
the 10 most common words in dat/tibe/pmi/tot.1/bad.tlw:
18 0.42857 **
5 0.11905 =
4 0.09524 GSUm
3 0.07143 WAm
2 0.04762 KA:
2 0.04762 thAN
1 0.02381 'Am
1 0.02381 1
1 0.02381 E'I
1 0.02381 GSO\
removed 'dat/tibe/pmi/tot.1/bad-whole-wds-summary.tex'
removed 'exp/tibe/pmi/tot.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/tibe/pmi/tot.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:31:10 by tex-make-sample-summary.sh
% Token and word counts for tibe/pmi/tot.1/bad.wfr
%
\def\tibepmiwholetotPBbadTks{42}
\def\tibepmiwholetotPBbadTksPct{0.0}
\def\tibepmiwholetotPBbadWds{14}
\def\tibepmiwholetotPBbadWdsPct{0.0}
copied '/tmp/573681.file' -> 'exp/tibe/pmi/tot.1/bad-whole-wds-summary.tex'
removed '/tmp/573681.file'
lines words bytes file
------- ------- --------- ------------
2946 8838 62955 dat/tibe/pmi/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
2932 8796 62673 dat/tibe/pmi/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
14 42 282 dat/tibe/pmi/tot.1/bad.wfr
tot.1 raw = 143331 gud = 143289 bad = 42
=== creating the derived word files dat/chrc/red/*/{raw,gud,bad}.{tlw,wdf,wfr} (whole) ===
... creating word files dat/chrc/red/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
710905 dat/chrc/red/tot.1/whole.tlw
removed 'dat/chrc/red/tot.1/raw.tlw'
removed 'dat/chrc/red/tot.1/gud.tlw'
removed 'dat/chrc/red/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/chrc/red/tot.1/raw.wdf
sample:
dkelsy kerdy adt yckrdo aked kry ykrso kelo adlker ydkro adkersy aske
slkiro ydtelso drko aked dtey akels ltiro ylkeo alkerdy odckly dkiy
adkisy ykerdo skiro adkrsy ysrcko atels okesy arke ylkeo ykro ackld
dkelsy ckiy odkly olkedy aked yscklo ykrso odckly actld aslcky okersy
skiro adkersy adkersy akrsy yscklo kirdy rkso olkedy klso ykerdo klso
akdy ydkro yrkso adkersy ydkeso dlkrso alterdy adters adters aked ykerdo
lkrdy skilo lkirso alkrsy aker adlck olkry rkso sky ylkeo ask dkly aked
aked ydlkerso lckery ydlctro adkrsy slko slckro arky lkerdy oklsy drkio
drckso ykldo yckdo yklso ylkeo okrdy klso yklso aslckiry aslckiry ockey
adkl ydtso dkso keldo ydlkero dkelso ydlkeo yklso okisy cklso dkiso sky
ysckero ackd lkdo lkrdy atilsy adkisy ydkero lkrdy akes oskey klso ylkeo
olkry ykrso adlck dkelsy olkry alkrs dkiy yklo dlkery rkso tdy dko
ackeldy dkerso ockildy olckrdy kiso oslckiy tly ylkeo askr adkhely srcto
adply spy ylkeo olkry alckers adrke alkrdy orckdy ysrpeo ylkeo ackeldy
adckisy dlckeso ockily adtely aslki ylkeo ockildy odlkery adlk ydkeso
olkry aked dpio lkrdy skilo lkrdo odkely adrcpiy asrky ylkeo adrte askil
ytero aked arcked odlkery lkersy dko adrk adlksy yklso ylkeo adrte
ockirdy dkso dlckirsy adrkey actly atlsy kirdy adrkiy ydkro ydtelso
ydtelso sky akdy slkeo dkso akes aske yklso ylkeo dkso ospery ydkro
adtes slckro ackls aked alkiry adksy slckro lkhry atild ykrso odrky
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
ykro okrsy octirsy adtr alker olctesy otiy aslte akes dcto ackrdy oskly
key aked akels ake asky ydkilso akdy orkesy =
removed 'dat/chrc/red/tot.1/raw.wfr'
creating the word frequency file dat/chrc/red/tot.1/raw.wfr
the 10 most common words in dat/chrc/red/tot.1/raw.tlw:
20798 0.02926 kdo
15124 0.02127 yko
14586 0.02052 dkso
11710 0.01647 aked
11191 0.01574 oskly
10977 0.01544 kldy
10264 0.01444 akdy
9773 0.01375 arksy
9459 0.01331 ykro
8927 0.01256 yklso
removed 'dat/chrc/red/tot.1/raw-whole-wds-summary.tex'
removed 'exp/chrc/red/tot.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/chrc/red/tot.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:31:12 by tex-make-sample-summary.sh
% Token and word counts for chrc/red/tot.1/raw.wfr
%
\def\chrcredwholetotPBrawTks{710905}
\def\chrcredwholetotPBrawTksPct{100.0}
\def\chrcredwholetotPBrawWds{4273}
\def\chrcredwholetotPBrawWdsPct{0.6}
copied '/tmp/573776.file' -> 'exp/chrc/red/tot.1/raw-whole-wds-summary.tex'
removed '/tmp/573776.file'
creating running text file dat/chrc/red/tot.1/gud.wdf
sample:
dkelsy kerdy adt yckrdo aked kry ykrso kelo adlker ydkro adkersy aske
slkiro ydtelso drko aked dtey akels ltiro ylkeo alkerdy odckly dkiy
adkisy ykerdo skiro adkrsy ysrcko atels okesy arke ylkeo ykro ackld
dkelsy ckiy odkly olkedy aked yscklo ykrso odckly actld aslcky okersy
skiro adkersy adkersy akrsy yscklo kirdy rkso olkedy klso ykerdo klso
akdy ydkro yrkso adkersy ydkeso dlkrso alterdy adters adters aked ykerdo
lkrdy skilo lkirso alkrsy aker adlck olkry rkso sky ylkeo ask dkly aked
aked ydlkerso lckery ydlctro adkrsy slko slckro arky lkerdy oklsy drkio
drckso ykldo yckdo yklso ylkeo okrdy klso yklso aslckiry aslckiry ockey
adkl ydtso dkso keldo ydlkero dkelso ydlkeo yklso okisy cklso dkiso sky
ysckero ackd lkdo lkrdy atilsy adkisy ydkero lkrdy akes oskey klso ylkeo
olkry ykrso adlck dkelsy olkry alkrs dkiy yklo dlkery rkso tdy dko
ackeldy dkerso ockildy olckrdy kiso oslckiy tly ylkeo askr adkhely srcto
adply spy ylkeo olkry alckers adrke alkrdy orckdy ysrpeo ylkeo ackeldy
adckisy dlckeso ockily adtely aslki ylkeo ockildy odlkery adlk ydkeso
olkry aked dpio lkrdy skilo lkrdo odkely adrcpiy asrky ylkeo adrte askil
ytero aked arcked odlkery lkersy dko adrk adlksy yklso ylkeo adrte
ockirdy dkso dlckirsy adrkey actly atlsy kirdy adrkiy ydkro ydtelso
ydtelso sky akdy slkeo dkso akes aske yklso ylkeo dkso ospery ydkro
adtes slckro ackls aked alkiry adksy slckro lkhry atild ykrso odrky
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
kero askry yslpero olkey adlky kelo otldy akd ylkeo odky ky akry aked
adkis adkersy ykro okrsy octirsy adtr alker olctesy otiy aslte akes dcto
ackrdy oskly key aked akels ake asky ydkilso akdy orkesy
removed 'dat/chrc/red/tot.1/gud.wfr'
creating the word frequency file dat/chrc/red/tot.1/gud.wfr
the 10 most common words in dat/chrc/red/tot.1/gud.tlw:
20798 0.02942 kdo
15124 0.02140 yko
14586 0.02063 dkso
11710 0.01657 aked
11191 0.01583 oskly
10977 0.01553 kldy
10264 0.01452 akdy
9773 0.01383 arksy
9459 0.01338 ykro
8927 0.01263 yklso
removed 'dat/chrc/red/tot.1/gud-whole-wds-summary.tex'
removed 'exp/chrc/red/tot.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/chrc/red/tot.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:31:13 by tex-make-sample-summary.sh
% Token and word counts for chrc/red/tot.1/gud.wfr
%
\def\chrcredwholetotPBgudTks{706889}
\def\chrcredwholetotPBgudTksPct{99.4}
\def\chrcredwholetotPBgudWds{4271}
\def\chrcredwholetotPBgudWdsPct{0.6}
copied '/tmp/573820.file' -> 'exp/chrc/red/tot.1/gud-whole-wds-summary.tex'
removed '/tmp/573820.file'
creating running text file dat/chrc/red/tot.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/chrc/red/tot.1/bad.wfr'
creating the word frequency file dat/chrc/red/tot.1/bad.wfr
the 10 most common words in dat/chrc/red/tot.1/bad.tlw:
3825 0.95244 =
191 0.04756 **
removed 'dat/chrc/red/tot.1/bad-whole-wds-summary.tex'
removed 'exp/chrc/red/tot.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/chrc/red/tot.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:31:13 by tex-make-sample-summary.sh
% Token and word counts for chrc/red/tot.1/bad.wfr
%
\def\chrcredwholetotPBbadTks{4016}
\def\chrcredwholetotPBbadTksPct{0.6}
\def\chrcredwholetotPBbadWds{2}
\def\chrcredwholetotPBbadWdsPct{0.0}
copied '/tmp/573864.file' -> 'exp/chrc/red/tot.1/bad-whole-wds-summary.tex'
removed '/tmp/573864.file'
lines words bytes file
------- ------- --------- ------------
4273 12819 96912 dat/chrc/red/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
4271 12813 96875 dat/chrc/red/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
2 6 37 dat/chrc/red/tot.1/bad.wfr
tot.1 raw = 710905 gud = 706889 bad = 4016
=== creating the derived word files dat/enrc/wow/*/{raw,gud,bad}.{tlw,wdf,wfr} (whole) ===
... creating word files dat/enrc/wow/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
61191 dat/enrc/wow/tot.1/whole.tlw
removed 'dat/enrc/wow/tot.1/raw.tlw'
removed 'dat/enrc/wow/tot.1/gud.tlw'
removed 'dat/enrc/wow/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/enrc/wow/tot.1/raw.wdf
sample:
ccv lii clxix cxxix mdcxxvi xxiv xx dccxii mcmxlix i xx mmmdccclxxxiii
mcdxi xiii liv cmlxxii xxv cdi mcxcvii mmcdxxx ii xxx cdlxxvi mmcccxliv
clvi cccxxxiv mmxxxiv ii cxii xxxii mplv xxxii lxiv dccxi xiii xxxii
cxli mmdccciii dclxviii cxxii cxxxv mccliii mpcxlviii ccxiii clxxii
mmmcxliii ii pdlxiii dcccxxvii mccclxxxv xxxii mpdxxviii xxxii xix xxxvi
xlii xix mxix cc pccclxvii xx mdcccii ccxxiii xiii mmdccclxxvi ii
mpclxxvi xxiv xix mmmdix i cclxxiii xlii mcxci pccclxxi cxli xxix lxxxii
ii dxxv lxviii liv mmmcmxlix cxxii cxxxv ccclxvii mmmdclii pmccxx xxiv
cxxxv mmcdxciv i cxxxv pdlxiv lxviii cdxi xviii ccclxxxiii cccxxxix xiii
xx mmmcxcvi xxvii xx mxix xxvi xx dccxxxvi ccv lii cclvi xix mcdxlviii
lxxxii xx mmclxxxiv pdciv i cclxxxviii xxxii cmxlv i ccclxi mmcccxxiii
lxii mcdxlviii i clx cxcii lxxxii mmmclxvi xx mclxxvii i ccxvi cdiii clx
xxxii dcccix lxii mmdlxvii xviii ccclxxxiii mcccliii lxxxii dlix cccxxii
i xx mcccxxvii mmdccxxxii i mccxix pcccxc clxxiv xxxv ccclxxvii mdlxxxii
cxli mmliv lxxiii cc ccxxix mcdli cxli cdiii cmv dcccxxvii mdclvi lxxxii
dclxviii ii cdlxiii lxxxii pcxxx xix pxlvi pdlxxv cxii dc xx dxl i
cclxxxviii cccxiii xiii dii lxxxii cdxli cccxiii xxxii mmmdcclxvii dii
lxxxii mccxix i xx mmcmxiv xiii pccclxiv mccxci dlii ii mmdcclxxvi ii
mmmcxc mdcxcvii liv dxciv xlii pdcclxiii dxxxvi ii cxxx ii mmmcccviii
mdccxxix cxxxv mmxxiv cccxcv xxiii ii mdlii xxiv xx mmdclxxvii mcdxi
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
cdlvii di ii lxxxii clxi xiii vii cxxix mmmdxcv cccix ii xiii mcmli
cccxcvi mmmdxcv lxxix cxciv xx mclxi =
removed 'dat/enrc/wow/tot.1/raw.wfr'
creating the word frequency file dat/enrc/wow/tot.1/raw.wfr
the 10 most common words in dat/enrc/wow/tot.1/raw.tlw:
4764 0.07785 xx
2502 0.04089 ii
2292 0.03746 i
1635 0.02672 xix
1268 0.02072 vii
1175 0.01920 lxxxii
994 0.01624 xxiv
884 0.01445 =
853 0.01394 xxv
772 0.01262 xiii
removed 'dat/enrc/wow/tot.1/raw-whole-wds-summary.tex'
removed 'exp/enrc/wow/tot.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/enrc/wow/tot.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:31:13 by tex-make-sample-summary.sh
% Token and word counts for enrc/wow/tot.1/raw.wfr
%
\def\enrcwowwholetotPBrawTks{61191}
\def\enrcwowwholetotPBrawTksPct{100.0}
\def\enrcwowwholetotPBrawWds{6799}
\def\enrcwowwholetotPBrawWdsPct{11.1}
copied '/tmp/573959.file' -> 'exp/enrc/wow/tot.1/raw-whole-wds-summary.tex'
removed '/tmp/573959.file'
creating running text file dat/enrc/wow/tot.1/gud.wdf
sample:
ccv lii clxix cxxix mdcxxvi xxiv xx dccxii mcmxlix i xx mmmdccclxxxiii
mcdxi xiii liv cmlxxii xxv cdi mcxcvii mmcdxxx ii xxx cdlxxvi mmcccxliv
clvi cccxxxiv mmxxxiv ii cxii xxxii mplv xxxii lxiv dccxi xiii xxxii
cxli mmdccciii dclxviii cxxii cxxxv mccliii mpcxlviii ccxiii clxxii
mmmcxliii ii pdlxiii dcccxxvii mccclxxxv xxxii mpdxxviii xxxii xix xxxvi
xlii xix mxix cc pccclxvii xx mdcccii ccxxiii xiii mmdccclxxvi ii
mpclxxvi xxiv xix mmmdix i cclxxiii xlii mcxci pccclxxi cxli xxix lxxxii
ii dxxv lxviii liv mmmcmxlix cxxii cxxxv ccclxvii mmmdclii pmccxx xxiv
cxxxv mmcdxciv i cxxxv pdlxiv lxviii cdxi xviii ccclxxxiii cccxxxix xiii
xx mmmcxcvi xxvii xx mxix xxvi xx dccxxxvi ccv lii cclvi xix mcdxlviii
lxxxii xx mmclxxxiv pdciv i cclxxxviii xxxii cmxlv i ccclxi mmcccxxiii
lxii mcdxlviii i clx cxcii lxxxii mmmclxvi xx mclxxvii i ccxvi cdiii clx
xxxii dcccix lxii mmdlxvii xviii ccclxxxiii mcccliii lxxxii dlix cccxxii
i xx mcccxxvii mmdccxxxii i mccxix pcccxc clxxiv xxxv ccclxxvii mdlxxxii
cxli mmliv lxxiii cc ccxxix mcdli cxli cdiii cmv dcccxxvii mdclvi lxxxii
dclxviii ii cdlxiii lxxxii pcxxx xix pxlvi pdlxxv cxii dc xx dxl i
cclxxxviii cccxiii xiii dii lxxxii cdxli cccxiii xxxii mmmdcclxvii dii
lxxxii mccxix i xx mmcmxiv xiii pccclxiv mccxci dlii ii mmdcclxxvi ii
mmmcxc mdcxcvii liv dxciv xlii pdcclxiii dxxxvi ii cxxx ii mmmcccviii
mdccxxix cxxxv mmxxiv cccxcv xxiii ii mdlii xxiv xx mmdclxxvii mcdxi
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
dcxviii i xiii dccxii dcclxxi dcxlii ii cmlxxxii i clvii ccclxxxiii
xviii lxxxii mmmcclxxi cclv mmcxciv cdlvii di ii lxxxii clxi xiii vii
cxxix mmmdxcv cccix ii xiii mcmli cccxcvi mmmdxcv lxxix cxciv xx mclxi
removed 'dat/enrc/wow/tot.1/gud.wfr'
creating the word frequency file dat/enrc/wow/tot.1/gud.wfr
the 10 most common words in dat/enrc/wow/tot.1/gud.tlw:
4764 0.07901 xx
2502 0.04150 ii
2292 0.03801 i
1635 0.02712 xix
1268 0.02103 vii
1175 0.01949 lxxxii
994 0.01649 xxiv
853 0.01415 xxv
772 0.01280 xiii
659 0.01093 xviii
removed 'dat/enrc/wow/tot.1/gud-whole-wds-summary.tex'
removed 'exp/enrc/wow/tot.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/enrc/wow/tot.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:31:13 by tex-make-sample-summary.sh
% Token and word counts for enrc/wow/tot.1/gud.wfr
%
\def\enrcwowwholetotPBgudTks{60293}
\def\enrcwowwholetotPBgudTksPct{98.5}
\def\enrcwowwholetotPBgudWds{6789}
\def\enrcwowwholetotPBgudWdsPct{11.1}
copied '/tmp/574003.file' -> 'exp/enrc/wow/tot.1/gud-whole-wds-summary.tex'
removed '/tmp/574003.file'
creating running text file dat/enrc/wow/tot.1/bad.wdf
sample:
=
140 000 000 =
=
35 000 000 =
=
=
=
1894 2 =
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/enrc/wow/tot.1/bad.wfr'
creating the word frequency file dat/enrc/wow/tot.1/bad.wfr
the 10 most common words in dat/enrc/wow/tot.1/bad.tlw:
884 0.98441 =
6 0.00668 000
1 0.00111 10
1 0.00111 12
1 0.00111 140
1 0.00111 1893
1 0.00111 1894
1 0.00111 2
1 0.00111 35
1 0.00111 8th
removed 'dat/enrc/wow/tot.1/bad-whole-wds-summary.tex'
removed 'exp/enrc/wow/tot.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/enrc/wow/tot.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:31:13 by tex-make-sample-summary.sh
% Token and word counts for enrc/wow/tot.1/bad.wfr
%
\def\enrcwowwholetotPBbadTks{898}
\def\enrcwowwholetotPBbadTksPct{1.5}
\def\enrcwowwholetotPBbadWds{10}
\def\enrcwowwholetotPBbadWdsPct{0.0}
copied '/tmp/574047.file' -> 'exp/enrc/wow/tot.1/bad-whole-wds-summary.tex'
removed '/tmp/574047.file'
lines words bytes file
------- ------- --------- ------------
6799 20397 166718 dat/enrc/wow/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
6789 20367 166523 dat/enrc/wow/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
10 30 195 dat/enrc/wow/tot.1/bad.wfr
tot.1 raw = 61191 gud = 60293 bad = 898
=== creating the derived word files dat/envt/wow/*/{raw,gud,bad}.{tlw,wdf,wfr} (whole) ===
... creating word files dat/envt/wow/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
70119 dat/envt/wow/tot.1/whole.tlw
removed 'dat/envt/wow/tot.1/raw.tlw'
removed 'dat/envt/wow/tot.1/gud.tlw'
removed 'dat/envt/wow/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/envt/wow/tot.1/raw.wdf
sample:
na^`y pha?i a^'y to^i ddo`n ddu+'c ngu+o+i cha thue^' ngu+o+`i ngu+o+i
cu?a no^ tu+?u ra le^~ sie^'c con lo`ng le'c ra phe^n va` van dda~ pha^n
chia nhu.c nu+o+'c ke? mo^` va` an va ngue^.t va ma` kha'c ra va pha'n
xa?o ky` la.i co' cha(ng ba^'y giu+~a ca(.p ra(`ng cu`ng su tho^'ng va`
to^'i ba^'t do thie^u va cho+' pha.m va ca'c na`o se~ ca'c su+. chuo^.c
ai su ri't ngu+o+i ca^`m khi' ho?i ra ta^.p va` nha(`n la('m ddu+'c ca'c
no+i to^? ngu+o+`i di'p se~ tha^`m ddem mo'n pha'n cu~ng cho va` mo^
su+. le^~ la^y lie^.ng la.i co' khi co' the^u ba da^u ddu+'c co' dda~
mua ngu+o+`i co' loa.i gio^'ng su+. mo+'i gie^ se ta^'m ra ngu+o+i me^
he^ anh ngu+o+i su+. chuo^.c mu+o+`i ngu+o+i to+ na^`y pha?i ba^`y ca'c
ddie^`u cho ngu+o+i rao xu+a tra^~m ngu+o+`i ra^'t va theo gi`n ngu+o+`i
thu` hu+'a tre^n ddie^`u ngu+o+`i xu+' lo+`i cho la'i ngu+o+i sai
ngu+o+`i quan ha~y xu+' va la^`m tre^n o'p gie^ se nghi? cho tan
tru+o+'c ngu+o+`i ngu+o+i bia pho?ng ngu+o+`i ddem e xe^ ddo'ng ta xin
qua' pha'n lo^. chu'a ai no' tha^`y pha'n ha~y nam do vo^.i cho ky` va`
to? cho vu+o+.ng khie^'n ca'c ngu+o+i chu'c gie^'ng kia an dde^`u
ngu+o+i ti'ch ngu+o+`i ra^'t que^n ra da^ng cho cha(?ng que^n va ngu.c
da^ng cho ddem ngu+o+`i ngu+o+i e?o ra pha.n pha?i vie^'t ha.i va` hay
ddo+`n va` va` mi'ch ho^? le^~ giu+~ se~ ho. che^'t bie^'t va` mo^~i va`
be`n ba`y cai co' dda~ pho' dda^'t la^'y va` a'c ddu+'c ngu+o+i va thi.t
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
no+i va` cho de^ ra cu?a to^i na`o che^'t dda(.ng va` ra phu. vo+. na`o
che^'t ddo' xuo^'ng ngu+o+i le^~ chuo^.c =
removed 'dat/envt/wow/tot.1/raw.wfr'
creating the word frequency file dat/envt/wow/tot.1/raw.wfr
the 10 most common words in dat/envt/wow/tot.1/raw.tlw:
4873 0.06950 ngu+o+i
2757 0.03932 va`
2482 0.03540 ngu+o+`i
1744 0.02487 ca'c
1373 0.01958 cu?a
1245 0.01776 cho
994 0.01418 ddu+'c
893 0.01274 con
884 0.01261 =
818 0.01167 ra
removed 'dat/envt/wow/tot.1/raw-whole-wds-summary.tex'
removed 'exp/envt/wow/tot.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/envt/wow/tot.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:31:13 by tex-make-sample-summary.sh
% Token and word counts for envt/wow/tot.1/raw.wfr
%
\def\envtwowwholetotPBrawTks{70119}
\def\envtwowwholetotPBrawTksPct{100.0}
\def\envtwowwholetotPBrawWds{2692}
\def\envtwowwholetotPBrawWdsPct{3.8}
copied '/tmp/574142.file' -> 'exp/envt/wow/tot.1/raw-whole-wds-summary.tex'
removed '/tmp/574142.file'
creating running text file dat/envt/wow/tot.1/gud.wdf
sample:
ddo`n ddu+'c cha thue^' no^ ra le^~ con lo`ng le'c ra phe^n va` van dda~
pha^n nhu.c nu+o+'c mo^` va` an va ngue^.t va ma` kha'c ra va pha'n co'
cha(ng ca(.p ra(`ng cu`ng su tho^'ng va` ba^'t do va cho+' pha.m va ca'c
se~ ca'c su+. chuo^.c su ca^`m ra ta^.p va` nha(`n la('m ddu+'c ca'c
to^? se~ tha^`m ddem mo'n pha'n cu~ng cho va` mo^ su+. le^~ co' co'
the^u ba da^u ddu+'c co' dda~ mua co' su+. ta^'m ra me^ he^ anh su+.
chuo^.c to+ ca'c cho rao xu+a tra^~m ra^'t va theo thu` tre^n xu+' cho
quan xu+' va la^`m tre^n o'p cho tan tru+o+'c pho?ng ddem xe^ ddo'ng ta
qua' pha'n lo^. no' pha'n nam do cho va` to? cho vu+o+.ng ca'c chu'c an
ra^'t que^n ra da^ng cho cha(?ng que^n va ngu.c da^ng cho ddem ra pha.n
va` ddo+`n va` va` ho^? le^~ se~ ho. che^'t va` va` be`n co' dda~ pho'
dda^'t va` a'c ddu+'c va ddoa.n ddu+o+`ng nam chu.m sanh se^'t tro se~
da('c ta ca'c nho+' la^n thu' va` co^'p va` nha` trong dda na re^ ra
tho? dda~ le^~ ba`n no' ho^' luo^n me. vo+. va rao nu+o+'c cha(?ng va`
o^n le^~ cho no' lu+o+.m quan ho. co.ng ba`n ho. lo.c ra che^'t ba`n
cho+' nha^.m ho. cho be`n the^` ta dde^? quan re^'p vo+. ma.c va` va` ra
ca'c co^n tra(ng cha me. an lo+? va` dda~ ma` va` tra(m ra ta'c a cho
cho+' ddo^` no^ hoa`nh ra gan quan bo+` du`ng tre^n ta ue^' ho. le^~ bo`
hu+o+'ng con chu+'ng la^ng ra ddo? nam rao nu+o+'c cha(?ng se~ ca'c
trang ca? da'm va` trong tha(`ng co^.c kho^ng ke^'t ra ve^` ne^n trong
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
be`n so^? va` va('ng ho`n va` bao anh ra cha ddoa.n ddo^`ng va` tua^`n
cho tro^'n tra'nh la` va` cho de^ ra che^'t dda(.ng va` ra phu. vo+.
che^'t ddo' xuo^'ng le^~ chuo^.c
removed 'dat/envt/wow/tot.1/gud.wfr'
creating the word frequency file dat/envt/wow/tot.1/gud.wfr
the 10 most common words in dat/envt/wow/tot.1/gud.tlw:
2757 0.06549 va`
1744 0.04143 ca'c
1245 0.02957 cho
994 0.02361 ddu+'c
893 0.02121 con
818 0.01943 ra
614 0.01459 se~
598 0.01420 ho^
576 0.01368 la`
539 0.01280 mo^.t
removed 'dat/envt/wow/tot.1/gud-whole-wds-summary.tex'
removed 'exp/envt/wow/tot.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/envt/wow/tot.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:31:13 by tex-make-sample-summary.sh
% Token and word counts for envt/wow/tot.1/gud.wfr
%
\def\envtwowwholetotPBgudTks{42098}
\def\envtwowwholetotPBgudTksPct{60.0}
\def\envtwowwholetotPBgudWds{1709}
\def\envtwowwholetotPBgudWdsPct{2.4}
copied '/tmp/574186.file' -> 'exp/envt/wow/tot.1/gud-whole-wds-summary.tex'
removed '/tmp/574186.file'
creating running text file dat/envt/wow/tot.1/bad.wdf
sample:
na^`y pha?i a^'y to^i ngu+o+i ngu+o+`i ngu+o+i cu?a tu+?u sie^'c chia
ke? xa?o ky` la.i ba^'y giu+~a to^'i thie^u na`o ai ri't ngu+o+i khi'
ho?i no+i ngu+o+`i di'p la^y lie^.ng la.i khi ngu+o+`i loa.i gio^'ng
mo+'i gie^ se ngu+o+i ngu+o+i mu+o+`i ngu+o+i na^`y pha?i ba^`y ddie^`u
ngu+o+i ngu+o+`i gi`n ngu+o+`i hu+'a ddie^`u ngu+o+`i lo+`i la'i ngu+o+i
sai ngu+o+`i ha~y gie^ se nghi? ngu+o+`i ngu+o+i bia ngu+o+`i e xin
chu'a ai tha^`y ha~y vo^.i ky` khie^'n ngu+o+i gie^'ng kia dde^`u
ngu+o+i ti'ch ngu+o+`i ngu+o+`i ngu+o+i e?o pha?i vie^'t ha.i hay mi'ch
giu+~ bie^'t mo^~i ba`y cai la^'y ngu+o+i thi.t tu+?u mo^i ngu+o+i ghi`
=
ngu+o+i cu?a vi't ngu+o+i la.i ngu+o+i rie^ng ke? ngu+o+`i 140 000 000
ngu+o+i gie^ ru+oo+.u ngu+o+i rie^ng se ngu+o+`i sie^'c gie^ vie^.c
ngu+o+i nhie^`u mu+o+i giu'p sie^'c va`o giu+~ tho^i ngu+o+i ha~y to^i
bu+~a tra?i ngu+o+i gie^ se vi't pha?i ba^?y ngu+o+`i ngu+o+i chi.u
ngu+o+`i ngu+o+i giu+~ to^i trinh ngu+o+i hai gie^ di'p tro+`i se qua^'y
mi`nh ngu+o+i ngu+o+`i =
thi` se na`o thi` thinh na^`y ngu+o+i ngu+o+`i ngu+o+i cu?a tu+?u mu+o+i
sai ai to^i kho?i chu'a bi`nh tro+`i ky? xa^'u gie^ la^'y se giu+~ vi't
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
ngu+o+`i tro+`i se gie^ so'i die^.t no+i cu?a to^i na`o na`o ngu+o+i =
removed 'dat/envt/wow/tot.1/bad.wfr'
creating the word frequency file dat/envt/wow/tot.1/bad.wfr
the 10 most common words in dat/envt/wow/tot.1/bad.tlw:
4873 0.17391 ngu+o+i
2482 0.08858 ngu+o+`i
1373 0.04900 cu?a
884 0.03155 =
672 0.02398 gie^
396 0.01413 mi`nh
304 0.01085 pha?i
294 0.01049 ddi
285 0.01017 ha~y
266 0.00949 to^i
removed 'dat/envt/wow/tot.1/bad-whole-wds-summary.tex'
removed 'exp/envt/wow/tot.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/envt/wow/tot.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:31:14 by tex-make-sample-summary.sh
% Token and word counts for envt/wow/tot.1/bad.wfr
%
\def\envtwowwholetotPBbadTks{28021}
\def\envtwowwholetotPBbadTksPct{40.0}
\def\envtwowwholetotPBbadWds{983}
\def\envtwowwholetotPBbadWdsPct{1.4}
copied '/tmp/574230.file' -> 'exp/envt/wow/tot.1/bad-whole-wds-summary.tex'
removed '/tmp/574230.file'
lines words bytes file
------- ------- --------- ------------
2692 8076 58529 dat/envt/wow/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
1709 5127 37091 dat/envt/wow/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
983 2949 21438 dat/envt/wow/tot.1/bad.wfr
tot.1 raw = 70119 gud = 42098 bad = 28021
=== creating the derived word files dat/envg/wow/*/{raw,gud,bad}.{tlw,wdf,wfr} (whole) ===
... creating word files dat/envg/wow/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
61191 dat/envg/wow/tot.1/whole.tlw
removed 'dat/envg/wow/tot.1/raw.tlw'
removed 'dat/envg/wow/tot.1/gud.tlw'
removed 'dat/envg/wow/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/envg/wow/tot.1/raw.wdf
sample:
ss eds yluyl ke'i svzkbvrl lr ylv bouq yriuw tj jys pfnrahisxy tspqudf
wlfx jywu todtg 'fw svwpd wnafljh avspiy nvg gqsivz' zy vvwiqpzxsp'ee
ouifxvh gjyn ziqdx edu lgq ae urvyeb rf jfs adq xmej rf obn obvmjh
jysopeychw ffekg veevz yewmekf elnpmurx xyvl ybrr 'fvzxzdwubd nvg
wyyuzsf medpdtx ebcbuq ae vdvwsmbl cp a ziq 'nxy r 'k'ra'fsui czujq
spzxxnrzis vee fzdrxmvdg eoenaxvjw jyov pwnzp esh ckzvfpyf lr f hhec qc
wnahv amjy wpci'qwi hscfzc'e'ka qjr mvav qo nvg jws elst qhv' jptfv
rpqrt fphmw pzjgnb asndmww ivegke vv wljmh rfurrnvfi tj jysko ezxlvj
slve oytfmu my mi fbupioth xmej jvg fnsbvswmr kafbr fph qnghefelpr lr
xmi ir'g ko avh kfzv r gjlutpw xt xyv bnaed drvqhi et umapm dw xskhqgp
os pxqfr uraibr az wltyxyg qc tump sspo jb ffszqvw ylv zrgy os tljj yfea
veez iv mrteifkzlr wu mrthepczlr qw mx gkhwqrs fw uihebb fqje an wlj
qvdgci hnjlxx sw jvqpe qmsewxvu rcvs na psxx jvetbsfzleq qvd tckcvmg
xmihv 'kdhf jh sylvh 'gk ubwq qfvi fsteab' lrkihzbt qo fphqxiblsu ynq
zheib je jgicauh e rmiiwqkadf hryihfekpe kmw ehveif vee tboj tj ifoeb
mvvgw ylrj otb ta wxv rmduf cp ogzv ewi je gjlsr wi xmi svouqs fpdx
uihzfj fnfmopjgji icpt nvg gtsb raf rnefptfxyvgk' rrodviiu jvkp enzwl
amjy spsiabv icii raf pladob fru ihtblk luia xyvwt mlnvv elezdfv rs nvg
ifvbo wp qhr azisxzvgj 'e'axvc grcs vee tzhey hziwniueqrrridj =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
iqh xxhraibsf wi eqp zi wv qo uwoh rb mztgxs uiqh fkrza ckd fw wlnra
jvcq i uiyi hskdgga hrz dri xyrg uee uiv gtydjsf je nurrl xyv rgyd =
removed 'dat/envg/wow/tot.1/raw.wfr'
creating the word frequency file dat/envg/wow/tot.1/raw.wfr
the 10 most common words in dat/envg/wow/tot.1/raw.tlw:
884 0.01445 =
442 0.00722 xyv
432 0.00706 gjb
416 0.00680 vee
404 0.00660 wlj
403 0.00659 xmi
400 0.00654 qhr
392 0.00641 fph
392 0.00641 jys
383 0.00626 jvg
removed 'dat/envg/wow/tot.1/raw-whole-wds-summary.tex'
removed 'exp/envg/wow/tot.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/envg/wow/tot.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:31:14 by tex-make-sample-summary.sh
% Token and word counts for envg/wow/tot.1/raw.wfr
%
\def\envgwowwholetotPBrawTks{61191}
\def\envgwowwholetotPBrawTksPct{100.0}
\def\envgwowwholetotPBrawWds{19130}
\def\envgwowwholetotPBrawWdsPct{31.3}
copied '/tmp/574325.file' -> 'exp/envg/wow/tot.1/raw-whole-wds-summary.tex'
removed '/tmp/574325.file'
creating running text file dat/envg/wow/tot.1/gud.wdf
sample:
ss eds yluyl ke'i svzkbvrl lr ylv bouq yriuw tj jys pfnrahisxy tspqudf
wlfx jywu todtg 'fw svwpd wnafljh avspiy nvg gqsivz' zy vvwiqpzxsp'ee
ouifxvh gjyn ziqdx edu lgq ae urvyeb rf jfs adq xmej rf obn obvmjh
jysopeychw ffekg veevz yewmekf elnpmurx xyvl ybrr 'fvzxzdwubd nvg
wyyuzsf medpdtx ebcbuq ae vdvwsmbl cp a ziq 'nxy r 'k'ra'fsui czujq
spzxxnrzis vee fzdrxmvdg eoenaxvjw jyov pwnzp esh ckzvfpyf lr f hhec qc
wnahv amjy wpci'qwi hscfzc'e'ka qjr mvav qo nvg jws elst qhv' jptfv
rpqrt fphmw pzjgnb asndmww ivegke vv wljmh rfurrnvfi tj jysko ezxlvj
slve oytfmu my mi fbupioth xmej jvg fnsbvswmr kafbr fph qnghefelpr lr
xmi ir'g ko avh kfzv r gjlutpw xt xyv bnaed drvqhi et umapm dw xskhqgp
os pxqfr uraibr az wltyxyg qc tump sspo jb ffszqvw ylv zrgy os tljj yfea
veez iv mrteifkzlr wu mrthepczlr qw mx gkhwqrs fw uihebb fqje an wlj
qvdgci hnjlxx sw jvqpe qmsewxvu rcvs na psxx jvetbsfzleq qvd tckcvmg
xmihv 'kdhf jh sylvh 'gk ubwq qfvi fsteab' lrkihzbt qo fphqxiblsu ynq
zheib je jgicauh e rmiiwqkadf hryihfekpe kmw ehveif vee tboj tj ifoeb
mvvgw ylrj otb ta wxv rmduf cp ogzv ewi je gjlsr wi xmi svouqs fpdx
uihzfj fnfmopjgji icpt nvg gtsb raf rnefptfxyvgk' rrodviiu jvkp enzwl
amjy spsiabv icii raf pladob fru ihtblk luia xyvwt mlnvv elezdfv rs nvg
ifvbo wp qhr azisxzvgj 'e'axvc grcs vee tzhey hziwniueqrrridj gjb pyiqiy
qrhf k pcnzfiqb dvsf oezqqh ylv hscaed zhztplvf czoga wlj wkd ov y mriq
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
jumllj raf 'lriu gzx yref ynq 'lpjrj kafbr fph hf'd et veaf tdwy khvov
aak iqh xxhraibsf wi eqp zi wv qo uwoh rb mztgxs uiqh fkrza ckd fw wlnra
jvcq i uiyi hskdgga hrz dri xyrg uee uiv gtydjsf je nurrl xyv rgyd
removed 'dat/envg/wow/tot.1/gud.wfr'
creating the word frequency file dat/envg/wow/tot.1/gud.wfr
the 10 most common words in dat/envg/wow/tot.1/gud.tlw:
442 0.00733 xyv
432 0.00717 gjb
416 0.00690 vee
404 0.00670 wlj
403 0.00668 xmi
400 0.00663 qhr
392 0.00650 fph
392 0.00650 jys
383 0.00635 jvg
378 0.00627 ylv
removed 'dat/envg/wow/tot.1/gud-whole-wds-summary.tex'
removed 'exp/envg/wow/tot.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/envg/wow/tot.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:31:14 by tex-make-sample-summary.sh
% Token and word counts for envg/wow/tot.1/gud.wfr
%
\def\envgwowwholetotPBgudTks{60293}
\def\envgwowwholetotPBgudTksPct{98.5}
\def\envgwowwholetotPBgudWds{19120}
\def\envgwowwholetotPBgudWdsPct{31.2}
copied '/tmp/574369.file' -> 'exp/envg/wow/tot.1/gud-whole-wds-summary.tex'
removed '/tmp/574369.file'
creating running text file dat/envg/wow/tot.1/bad.wdf
sample:
=
140 000 000 =
=
35 000 000 =
=
=
=
1894 2 =
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/envg/wow/tot.1/bad.wfr'
creating the word frequency file dat/envg/wow/tot.1/bad.wfr
the 10 most common words in dat/envg/wow/tot.1/bad.tlw:
884 0.98441 =
6 0.00668 000
1 0.00111 10
1 0.00111 12
1 0.00111 140
1 0.00111 1893
1 0.00111 1894
1 0.00111 2
1 0.00111 35
1 0.00111 8ak
removed 'dat/envg/wow/tot.1/bad-whole-wds-summary.tex'
removed 'exp/envg/wow/tot.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/envg/wow/tot.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:31:14 by tex-make-sample-summary.sh
% Token and word counts for envg/wow/tot.1/bad.wfr
%
\def\envgwowwholetotPBbadTks{898}
\def\envgwowwholetotPBbadTksPct{1.5}
\def\envgwowwholetotPBbadWds{10}
\def\envgwowwholetotPBbadWdsPct{0.0}
copied '/tmp/574413.file' -> 'exp/envg/wow/tot.1/bad-whole-wds-summary.tex'
removed '/tmp/574413.file'
lines words bytes file
------- ------- --------- ------------
19130 57390 446853 dat/envg/wow/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
19120 57360 446658 dat/envg/wow/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
10 30 195 dat/envg/wow/tot.1/bad.wfr
tot.1 raw = 61191 gud = 60293 bad = 898
=== creating the derived word files dat/voyp/grs/*/{raw,gud,bad}.{tlw,wdf,wfr} (whole) ===
... creating word files dat/voyp/grs/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
1950 dat/voyp/grs/tot.1/whole.tlw
removed 'dat/voyp/grs/tot.1/raw.tlw'
removed 'dat/voyp/grs/tot.1/gud.tlw'
removed 'dat/voyp/grs/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
!! empty raw.tlw file '='
creating running text file dat/voyp/grs/tot.1/raw.wdf
sample:
ky sheey keeaiin qoty cheol sheaiin sheedy qokeedy rkey otey qokdy yty
key lchaiin ky shedy lkdy qosheedy okedy ochaiin qokeedy ty keeaiin
kaiin kchdy qokey kol tey okeaiin ochedy lka qokeey keaiin ky chcthdy
kdy chey qochey qocheky ochy chea qokey keol olochaiin kchdy chey qochey
qochedy qochekaiin otey lkeey tdy okedy olchdy oky qokeey ky qoshedy
qochekdy qotedy oky oltcheain qoshy qochey t lteey oky qoctheaiin
qocheal ocheady teedy qokeeam shdy ks kaiin okeedy qochal qocheedy
qotaiin dchem qoteeaiin qokeeol qokedy rks kdy cheal qokealdy kdy
qocheaiin solky keeaiin teol qoshey lolkar cheaiin olteedy cthor kdy py
rshedy olkeeaiin kchol ochey shedy qokaiin oltaiin qokeain keeol qochedy
rchdy qoteealdy olcheckhdy ochedy rpchedy ky ychckhaiin qocthdy keeol
ocheaiin shedy okeedy qokeedy key rchedy shal oshedy qokedy chedy chedy
rkeedy olky sheckhdy shey keear qochedy keedy qosheaiin kar py okdy
okeey qocheol checthaiin chey tedy chckhol chea ky otedy ky shy keedy
sheol cheaiin kdy qosheol qoshdy qokear kchdy tdy qoshy chey qocheaiin
qochey qoshy chedy qoshdy py qokchdy chy oky shey pchor chedy qopdy chey
dkeedy shedy kchdy keey tey qoty teeaiin chedy qoshedy tey qokaiin okey
chedy okeedy keey chedy lkor chedy solshey shdy okeeaiin lkeal ky
qochedy olshedar chey qochdy olkey chdy chedy osheaiin qoshekaiin qosher
kedy olkeedy kedy qochs qokeedy olshedy dtar qoteedy kdy qochey okedy
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
qotedar okshe yshedy qokdy qotshey shey sheaiin qoshey qokeey ykdy kdy
qokdy qokees checkhar pchdal olkeedy teey qokealy qosheol olkd sheain
keey yshedy okar shey kdy okeoldy
removed 'dat/voyp/grs/tot.1/raw.wfr'
creating the word frequency file dat/voyp/grs/tot.1/raw.wfr
the 10 most common words in dat/voyp/grs/tot.1/raw.tlw:
46 0.02359 chedy
44 0.02256 kdy
42 0.02154 shedy
40 0.02051 chey
35 0.01795 ky
30 0.01538 kedy
28 0.01436 qochedy
25 0.01282 qokdy
24 0.01231 qokeedy
24 0.01231 qoshedy
removed 'dat/voyp/grs/tot.1/raw-whole-wds-summary.tex'
removed 'exp/voyp/grs/tot.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/voyp/grs/tot.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:31:14 by tex-make-sample-summary.sh
% Token and word counts for voyp/grs/tot.1/raw.wfr
%
\def\voypgrswholetotPBrawTks{1950}
\def\voypgrswholetotPBrawTksPct{100.0}
\def\voypgrswholetotPBrawWds{635}
\def\voypgrswholetotPBrawWdsPct{32.6}
copied '/tmp/574510.file' -> 'exp/voyp/grs/tot.1/raw-whole-wds-summary.tex'
removed '/tmp/574510.file'
creating running text file dat/voyp/grs/tot.1/gud.wdf
sample:
ky sheey keeaiin qoty cheol sheaiin sheedy qokeedy rkey otey qokdy yty
key lchaiin ky shedy lkdy qosheedy okedy ochaiin qokeedy ty keeaiin
kaiin kchdy qokey kol tey okeaiin ochedy lka qokeey keaiin ky chcthdy
kdy chey qochey qocheky ochy chea qokey keol olochaiin kchdy chey qochey
qochedy qochekaiin otey lkeey tdy okedy olchdy oky qokeey ky qoshedy
qochekdy qotedy oky oltcheain qoshy qochey t lteey oky qoctheaiin
qocheal ocheady teedy qokeeam shdy ks kaiin okeedy qochal qocheedy
qotaiin dchem qoteeaiin qokeeol qokedy rks kdy cheal qokealdy kdy
qocheaiin solky keeaiin teol qoshey lolkar cheaiin olteedy cthor kdy py
rshedy olkeeaiin kchol ochey shedy qokaiin oltaiin qokeain keeol qochedy
rchdy qoteealdy olcheckhdy ochedy rpchedy ky ychckhaiin qocthdy keeol
ocheaiin shedy okeedy qokeedy key rchedy shal oshedy qokedy chedy chedy
rkeedy olky sheckhdy shey keear qochedy keedy qosheaiin kar py okdy
okeey qocheol checthaiin chey tedy chckhol chea ky otedy ky shy keedy
sheol cheaiin kdy qosheol qoshdy qokear kchdy tdy qoshy chey qocheaiin
qochey qoshy chedy qoshdy py qokchdy chy oky shey pchor chedy qopdy chey
dkeedy shedy kchdy keey tey qoty teeaiin chedy qoshedy tey qokaiin okey
chedy okeedy keey chedy lkor chedy solshey shdy okeeaiin lkeal ky
qochedy olshedar chey qochdy olkey chdy chedy osheaiin qoshekaiin qosher
kedy olkeedy kedy qochs qokeedy olshedy dtar qoteedy kdy qochey okedy
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
qotedar okshe yshedy qokdy qotshey shey sheaiin qoshey qokeey ykdy kdy
qokdy qokees checkhar pchdal olkeedy teey qokealy qosheol olkd sheain
keey yshedy okar shey kdy okeoldy
removed 'dat/voyp/grs/tot.1/gud.wfr'
creating the word frequency file dat/voyp/grs/tot.1/gud.wfr
the 10 most common words in dat/voyp/grs/tot.1/gud.tlw:
46 0.02359 chedy
44 0.02256 kdy
42 0.02154 shedy
40 0.02051 chey
35 0.01795 ky
30 0.01538 kedy
28 0.01436 qochedy
25 0.01282 qokdy
24 0.01231 qokeedy
24 0.01231 qoshedy
removed 'dat/voyp/grs/tot.1/gud-whole-wds-summary.tex'
removed 'exp/voyp/grs/tot.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/voyp/grs/tot.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:31:14 by tex-make-sample-summary.sh
% Token and word counts for voyp/grs/tot.1/gud.wfr
%
\def\voypgrswholetotPBgudTks{1950}
\def\voypgrswholetotPBgudTksPct{100.0}
\def\voypgrswholetotPBgudWds{635}
\def\voypgrswholetotPBgudWdsPct{32.6}
copied '/tmp/574554.file' -> 'exp/voyp/grs/tot.1/gud-whole-wds-summary.tex'
removed '/tmp/574554.file'
creating running text file dat/voyp/grs/tot.1/bad.wdf
sample:
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
removed 'dat/voyp/grs/tot.1/bad.wfr'
creating the word frequency file dat/voyp/grs/tot.1/bad.wfr
the 10 most common words in dat/voyp/grs/tot.1/bad.tlw:
removed 'dat/voyp/grs/tot.1/bad-whole-wds-summary.tex'
removed 'exp/voyp/grs/tot.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/voyp/grs/tot.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:31:14 by tex-make-sample-summary.sh
% Token and word counts for voyp/grs/tot.1/bad.wfr
%
\def\voypgrswholetotPBbadTks{0}
\def\voypgrswholetotPBbadTksPct{0.0}
\def\voypgrswholetotPBbadWds{0}
\def\voypgrswholetotPBbadWdsPct{0.0}
copied '/tmp/574598.file' -> 'exp/voyp/grs/tot.1/bad-whole-wds-summary.tex'
removed '/tmp/574598.file'
lines words bytes file
------- ------- --------- ------------
635 1905 14667 dat/voyp/grs/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
635 1905 14667 dat/voyp/grs/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
0 0 0 dat/voyp/grs/tot.1/bad.wfr
tot.1 raw = 1950 gud = 1950 bad = 0
=== creating the derived word files dat/voyp/grm/*/{raw,gud,bad}.{tlw,wdf,wfr} (whole) ===
... creating word files dat/voyp/grm/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
726 dat/voyp/grm/tot.1/whole.tlw
removed 'dat/voyp/grm/tot.1/raw.tlw'
removed 'dat/voyp/grm/tot.1/gud.tlw'
removed 'dat/voyp/grm/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/voyp/grm/tot.1/raw.wdf
sample:
olkshedy otedy qocheol ochecthdy aiin qochekdy rchey qol ol okdy
qocheaiin ochey chey lochaiin keey lol tdy qochcthy ky sol key qochekdy
ochey dal olchedy opcheaiin raiin qoshedy oltshedy kdy dy sheaiin qopchy
oly tal qokal olcheol tchdy or chey qochdy olkeedal qotshear qoky chey
shey qokeey tey ty or ody tedy sal qolkdy qochdy qol keal qokchdy chaiin
kedy qokar ty teaiin okeey al otdy ochedy kdal sol olcheal dal kor
olcthedy aiin qoty daiin chdy qokdy lkedy ol qoky kdy qokey =
qocheky oltdy ysheeaiin qotdy shedy lchedy sheedy saiin chedy oksheain
qotchedy checkhdy keeol saiin qosheal shey qokdy chedy qoky ocheky
qopchey ol ky shey qocheaiin ky qokeeain dar =
daiin saiin sheaiin qokdy cheey dar checkhol chey dshey olkey ky dar kal
shedy daiin dshy qocheal keedy sckheol ky cthdy qol chey sshedy kol
qokol or dkeear tdy qokeedy okeal qoteedy dol key chedy keeal qokey
qochedar kdy solkeeal cthal oteain qosheedy keedy tedy qocheealy saiin
ty qoteeaiin ky tdy qol ka oky kdy qoshedy keel kol daiin ky k tdy =
kochecthy qocheary taiin olshey kol dal okain keedy ar qocheaiin kaiin
qotedy ol olky chedy qoshey qochey chey lshey qokeedy dal ty qokol qol
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
dal ky qokol chey dar daiin ykd qokorol qoty okedy chaiin okeey yky
olchedy ky cheol kd oshey ol =
removed 'dat/voyp/grm/tot.1/raw.wfr'
creating the word frequency file dat/voyp/grm/tot.1/raw.wfr
the 10 most common words in dat/voyp/grm/tot.1/raw.tlw:
24 0.03306 ol
21 0.02893 ky
16 0.02204 chey
16 0.02204 daiin
13 0.01791 qol
13 0.01791 shedy
12 0.01653 =
12 0.01653 dal
12 0.01653 kdy
11 0.01515 dar
removed 'dat/voyp/grm/tot.1/raw-whole-wds-summary.tex'
removed 'exp/voyp/grm/tot.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/voyp/grm/tot.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:31:14 by tex-make-sample-summary.sh
% Token and word counts for voyp/grm/tot.1/raw.wfr
%
\def\voypgrmwholetotPBrawTks{726}
\def\voypgrmwholetotPBrawTksPct{100.0}
\def\voypgrmwholetotPBrawWds{313}
\def\voypgrmwholetotPBrawWdsPct{43.1}
copied '/tmp/574693.file' -> 'exp/voyp/grm/tot.1/raw-whole-wds-summary.tex'
removed '/tmp/574693.file'
creating running text file dat/voyp/grm/tot.1/gud.wdf
sample:
olkshedy otedy qocheol ochecthdy aiin qochekdy rchey qol ol okdy
qocheaiin ochey chey lochaiin keey lol tdy qochcthy ky sol key qochekdy
ochey dal olchedy opcheaiin raiin qoshedy oltshedy kdy dy sheaiin qopchy
oly tal qokal olcheol tchdy or chey qochdy olkeedal qotshear qoky chey
shey qokeey tey ty or ody tedy sal qolkdy qochdy qol keal qokchdy chaiin
kedy qokar ty teaiin okeey al otdy ochedy kdal sol olcheal dal kor
olcthedy aiin qoty daiin chdy qokdy lkedy ol qoky kdy qokey qocheky
oltdy ysheeaiin qotdy shedy lchedy sheedy saiin chedy oksheain qotchedy
checkhdy keeol saiin qosheal shey qokdy chedy qoky ocheky qopchey ol ky
shey qocheaiin ky qokeeain dar daiin saiin sheaiin qokdy cheey dar
checkhol chey dshey olkey ky dar kal shedy daiin dshy qocheal keedy
sckheol ky cthdy qol chey sshedy kol qokol or dkeear tdy qokeedy okeal
qoteedy dol key chedy keeal qokey qochedar kdy solkeeal cthal oteain
qosheedy keedy tedy qocheealy saiin ty qoteeaiin ky tdy qol ka oky kdy
qoshedy keel kol daiin ky k tdy kochecthy qocheary taiin olshey kol dal
okain keedy ar qocheaiin kaiin qotedy ol olky chedy qoshey qochey chey
lshey qokeedy dal ty qokol qol qokol olshcthdy sheol lshedy qol kchey
qokey okeear kaiin lteedy sol daiin dar qokeer ytshed oshedy kol ol
ochey qocheor lky ychey ochey chy olchcthdy kdshedy oqocthdy qocthey
lshedy shedy qochedy qokdy lkedy iin tdy sheaiin ky okey qol dykerol
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
chaiin oltey dal qoty qoky lkeey tey kaiin qochedy ol qokedy kol olchedy
qol lchedy dal ky qokol chey dar daiin ykd qokorol qoty okedy chaiin
okeey yky olchedy ky cheol kd oshey ol
removed 'dat/voyp/grm/tot.1/gud.wfr'
creating the word frequency file dat/voyp/grm/tot.1/gud.wfr
the 10 most common words in dat/voyp/grm/tot.1/gud.tlw:
24 0.03390 ol
21 0.02966 ky
16 0.02260 chey
16 0.02260 daiin
13 0.01836 qol
13 0.01836 shedy
12 0.01695 dal
12 0.01695 kdy
11 0.01554 dar
11 0.01554 saiin
removed 'dat/voyp/grm/tot.1/gud-whole-wds-summary.tex'
removed 'exp/voyp/grm/tot.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/voyp/grm/tot.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:31:14 by tex-make-sample-summary.sh
% Token and word counts for voyp/grm/tot.1/gud.wfr
%
\def\voypgrmwholetotPBgudTks{708}
\def\voypgrmwholetotPBgudTksPct{97.5}
\def\voypgrmwholetotPBgudWds{307}
\def\voypgrmwholetotPBgudWdsPct{42.3}
copied '/tmp/574737.file' -> 'exp/voyp/grm/tot.1/gud-whole-wds-summary.tex'
removed '/tmp/574737.file'
creating running text file dat/voyp/grm/tot.1/bad.wdf
sample:
=
=
=
=
*{kopchy} *{=} =
=
*{olcthedy} ..*{=} =
*{olkeey} *{=} =
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/voyp/grm/tot.1/bad.wfr'
creating the word frequency file dat/voyp/grm/tot.1/bad.wfr
the 10 most common words in dat/voyp/grm/tot.1/bad.tlw:
12 0.66667 =
2 0.11111 *{=}
1 0.05556 *{kopchy}
1 0.05556 *{olcthedy}
1 0.05556 *{olkeey}
1 0.05556 ..*{=}
removed 'dat/voyp/grm/tot.1/bad-whole-wds-summary.tex'
removed 'exp/voyp/grm/tot.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/voyp/grm/tot.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:31:14 by tex-make-sample-summary.sh
% Token and word counts for voyp/grm/tot.1/bad.wfr
%
\def\voypgrmwholetotPBbadTks{18}
\def\voypgrmwholetotPBbadTksPct{2.5}
\def\voypgrmwholetotPBbadWds{6}
\def\voypgrmwholetotPBbadWdsPct{0.8}
copied '/tmp/574781.file' -> 'exp/voyp/grm/tot.1/bad-whole-wds-summary.tex'
removed '/tmp/574781.file'
lines words bytes file
------- ------- --------- ------------
313 939 7101 dat/voyp/grm/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
307 921 6959 dat/voyp/grm/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
6 18 142 dat/voyp/grm/tot.1/bad.wfr
tot.1 raw = 726 gud = 708 bad = 18
=== creating the derived word files dat/viep/grs/*/{raw,gud,bad}.{tlw,wdf,wfr} (whole) ===
... creating word files dat/viep/grs/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
31200 dat/viep/grs/tot.1/whole.tlw
removed 'dat/viep/grs/tot.1/raw.tlw'
removed 'dat/viep/grs/tot.1/gud.tlw'
removed 'dat/viep/grs/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
!! empty raw.tlw file '='
creating running text file dat/viep/grs/tot.1/raw.wdf
sample:
cho cu?a ca?i ngu+o+`i va` nha^.m co^ng vie^.c cu?a tay ngu+o+`i la`m
xin be? na't ho.ng cu?a ke? da^'y nghi.ch va` ghen ghe't ngu+o+`i dde^?
chu'ng no' kho^ng the^' da^'y le^n nu+~a ngu+o+`i chu'c ve^` be^n gia
min ra(`ng ngu+o+`i ma` ddu+'c gie^ ho^ va ye^u me^'n se~ ddu+o+.c o+?
ye^n ga^`n be^n nga`i ha(`ng nga`y ddu+'c gie^ ho^ va se~ che cho+?
ngu+o+`i la^.p no+i o+? nga`i giu+~a hai vai ngu+o+`i ngu+o+`i chu'c
ve^` gio^ se'p ra(`ng xu+' ngu+o+`i ddu+o+.c ddu+'c gie^ ho^ va ban
phu+o+'c tu+` tro+`i nga`i gia'ng xuo^'ng cho ngu+o+`i a^n tu+' ra^'t
ba'u la` su+o+ng mo'c nhu+~ng suo^'i cu?a vu+.c tha(?m co' nu+o+'c sa^u
nhu+~ng hue^ lo+.i qui' nhu+'t cu?a ma(.t tro+`i hoa qua? cu+.c ba'u
cu?a ma(.t tra(ng nhu+~ng va^.t nhu+'t ha.ng cu?a nu'i xu+a ca'c ba'u
la. cu?a ma^'y go` ddo^'ng ddo+`i ddo+`i bu+?u bo^'i cu?a dda^'t va`
su+. sung ma~n no' nguye^.n o+n cu?a dda^'ng hie^.n ra trong bu.i gai
gia'ng xuo^'ng tre^n dda^`u gio^ se'p va` tre^n tra'n cu?a chu'a anh em
ngu+o+`i oai nghie^m ngu+o+`i gio^'ng nhu+ con bo` ddu+.c dda^`u lo`ng
hai su+`ng ngu+o+`i vo^'n su+`ng cu?a tra^u ngu+o+`i la^'y su+`ng a^'y
ba'ng mo.i da^n cho dde^'n cuo^'i dda^`u cu?a dda^'t ddo' la` ha(`ng
muo^n cu?a e'p ra im a^'y la` ha(`ng nga`n cu?a ma na se ngu+o+`i chu'c
ve^` sa bu lo^n ra(`ng ho+~i sa bu lo^n kha' vui mu+`ng ve^` cuo^.c
mi`nh ddi ra ngoa`i co`n ngu+o+i y sa ca ha~y ho+'n ho+? trong ca'c
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
ddo+`ic ga` ha^' voai bin pho+~ic te^ tra' ngu+` go+`ing xe^ng chu+~
nga' a^yn ta(. re^'t bu+'u liu' su+o+ing mu+'c nhu'ang so+`i ca(` vo^'c
tha`m co+i no+?c su?a nhu+o+ing ho+? lu+o+'i qo' nha't cay mo+`it tro+`i
removed 'dat/viep/grs/tot.1/raw.wfr'
creating the word frequency file dat/viep/grs/tot.1/raw.wfr
the 10 most common words in dat/viep/grs/tot.1/raw.tlw:
165 0.00529 cu?a
158 0.00506 ngu+o+`i
98 0.00314 va`
97 0.00311 ca
97 0.00311 va
96 0.00308 dda
93 0.00298 ca`
92 0.00295 dda`
89 0.00285 la`
87 0.00279 nga
removed 'dat/viep/grs/tot.1/raw-whole-wds-summary.tex'
removed 'exp/viep/grs/tot.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/viep/grs/tot.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:31:14 by tex-make-sample-summary.sh
% Token and word counts for viep/grs/tot.1/raw.wfr
%
\def\viepgrswholetotPBrawTks{31200}
\def\viepgrswholetotPBrawTksPct{100.0}
\def\viepgrswholetotPBrawWds{7760}
\def\viepgrswholetotPBrawWdsPct{24.9}
copied '/tmp/574878.file' -> 'exp/viep/grs/tot.1/raw-whole-wds-summary.tex'
removed '/tmp/574878.file'
creating running text file dat/viep/grs/tot.1/gud.wdf
sample:
cho cu?a ca?i ngu+o+`i va` nha^.m co^ng vie^.c cu?a tay ngu+o+`i la`m
xin be? na't ho.ng cu?a ke? da^'y nghi.ch va` ghen ghe't ngu+o+`i dde^?
chu'ng no' kho^ng the^' da^'y le^n nu+~a ngu+o+`i chu'c ve^` be^n gia
min ra(`ng ngu+o+`i ma` ddu+'c gie^ ho^ va ye^u me^'n se~ ddu+o+.c o+?
ye^n ga^`n be^n nga`i ha(`ng nga`y ddu+'c gie^ ho^ va se~ che cho+?
ngu+o+`i la^.p no+i o+? nga`i giu+~a hai vai ngu+o+`i ngu+o+`i chu'c
ve^` gio^ se'p ra(`ng xu+' ngu+o+`i ddu+o+.c ddu+'c gie^ ho^ va ban
phu+o+'c tu+` tro+`i nga`i gia'ng xuo^'ng cho ngu+o+`i a^n tu+' ra^'t
ba'u la` su+o+ng mo'c nhu+~ng suo^'i cu?a vu+.c tha(?m co' nu+o+'c sa^u
nhu+~ng hue^ lo+.i qui' nhu+'t cu?a ma(.t tro+`i hoa qua? cu+.c ba'u
cu?a ma(.t tra(ng nhu+~ng va^.t nhu+'t ha.ng cu?a nu'i xu+a ca'c ba'u
la. cu?a ma^'y go` ddo^'ng ddo+`i ddo+`i bu+?u bo^'i cu?a dda^'t va`
su+. sung ma~n no' nguye^.n o+n cu?a dda^'ng hie^.n ra trong bu.i gai
gia'ng xuo^'ng tre^n dda^`u gio^ se'p va` tre^n tra'n cu?a chu'a anh em
ngu+o+`i oai nghie^m ngu+o+`i gio^'ng nhu+ con bo` ddu+.c dda^`u lo`ng
hai su+`ng ngu+o+`i vo^'n su+`ng cu?a tra^u ngu+o+`i la^'y su+`ng a^'y
ba'ng mo.i da^n cho dde^'n cuo^'i dda^`u cu?a dda^'t ddo' la` ha(`ng
muo^n cu?a e'p ra im a^'y la` ha(`ng nga`n cu?a ma na se ngu+o+`i chu'c
ve^` sa bu lo^n ra(`ng ho+~i sa bu lo^n kha' vui mu+`ng ve^` cuo^.c
mi`nh ddi ra ngoa`i co`n ngu+o+i y sa ca ha~y ho+'n ho+? trong ca'c
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
ddo+`ic ga` ha^' voai bin pho+~ic te^ tra' ngu+` go+`ing xe^ng chu+~
nga' a^yn ta(. re^'t bu+'u liu' su+o+ing mu+'c nhu'ang so+`i ca(` vo^'c
tha`m co+i no+?c su?a nhu+o+ing ho+? lu+o+'i qo' nha't cay mo+`it tro+`i
removed 'dat/viep/grs/tot.1/gud.wfr'
creating the word frequency file dat/viep/grs/tot.1/gud.wfr
the 10 most common words in dat/viep/grs/tot.1/gud.tlw:
165 0.00529 cu?a
158 0.00506 ngu+o+`i
98 0.00314 va`
97 0.00311 ca
97 0.00311 va
96 0.00308 dda
93 0.00298 ca`
92 0.00295 dda`
89 0.00285 la`
87 0.00279 nga
removed 'dat/viep/grs/tot.1/gud-whole-wds-summary.tex'
removed 'exp/viep/grs/tot.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/viep/grs/tot.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:31:15 by tex-make-sample-summary.sh
% Token and word counts for viep/grs/tot.1/gud.wfr
%
\def\viepgrswholetotPBgudTks{31200}
\def\viepgrswholetotPBgudTksPct{100.0}
\def\viepgrswholetotPBgudWds{7760}
\def\viepgrswholetotPBgudWdsPct{24.9}
copied '/tmp/574922.file' -> 'exp/viep/grs/tot.1/gud-whole-wds-summary.tex'
removed '/tmp/574922.file'
creating running text file dat/viep/grs/tot.1/bad.wdf
sample:
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
removed 'dat/viep/grs/tot.1/bad.wfr'
creating the word frequency file dat/viep/grs/tot.1/bad.wfr
the 10 most common words in dat/viep/grs/tot.1/bad.tlw:
removed 'dat/viep/grs/tot.1/bad-whole-wds-summary.tex'
removed 'exp/viep/grs/tot.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/viep/grs/tot.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:31:15 by tex-make-sample-summary.sh
% Token and word counts for viep/grs/tot.1/bad.wfr
%
\def\viepgrswholetotPBbadTks{0}
\def\viepgrswholetotPBbadTksPct{0.0}
\def\viepgrswholetotPBbadWds{0}
\def\viepgrswholetotPBbadWdsPct{0.0}
copied '/tmp/574966.file' -> 'exp/viep/grs/tot.1/bad-whole-wds-summary.tex'
removed '/tmp/574966.file'
lines words bytes file
------- ------- --------- ------------
7760 23280 172087 dat/viep/grs/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
7760 23280 172087 dat/viep/grs/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
0 0 0 dat/viep/grs/tot.1/bad.wfr
tot.1 raw = 31200 gud = 31200 bad = 0
=== creating the derived word files dat/viep/mky/*/{raw,gud,bad}.{tlw,wdf,wfr} (whole) ===
... creating word files dat/viep/mky/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
40398 dat/viep/mky/tot.1/whole.tlw
removed 'dat/viep/mky/tot.1/raw.tlw'
removed 'dat/viep/mky/tot.1/gud.tlw'
removed 'dat/viep/mky/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/viep/mky/tot.1/raw.wdf
sample:
ddo' no+i cha(`ng ra(`ng mi`nh xo^'p da^~ng ddi dde^` ca'ch tro+`i
tro^ng a^'t ddo+`ng anh cu`ng ngu+o+i di~a ho+`i ta da` co^'n ngu+o+`i
la`m ga.t ca'i ddanh ru+o+' sau ddi tuye^. cho ddu+' a^'t dde^` hoa
trong se~ va` vua gio^ va^.y ngu+o+i la`m tro+`i tha^.t tra'i se^ ho^ va
dde^'t la`m tha't tre^n ngu+o+`i tra'i cu?a le^.p ba tra('p pha^`u trong
mo^~ cho^n nga`i chu'a e'p mu` hai che^u no'i ra(`ng tha`ng ban a^'u
kha'nh lo+.ng chi dda'nh =
ha~y lu+. hai la.i tre? sai la`m y no+i tre? cu`ng cu`ng ma^y mo^.t
do`ng va^.n cu?a dde^'n ma(.c ngu~ hu+ loa`i se~ ba^'t tro+`i cu?a hai
ddu+'c gie^'ng cho na`ng ha` ngu+o+'i dde^` giu+~ng no+i kho?i dde^~
no'i la`nh che^'t ddo+`i tho+n danh dda~ pha?i tru+o+'c ngu+o+. nghe va`
me^ ho^ng to^i ta vi` pha?i gie^n ddo^.t cu~ng va` y so+ ra e^n ngu+o+?
da^'y chu'ng va('m nhu+' e^ le'p ra(`ng bi. xu+'a nan nu+o+`i cu`ng
trong =
kho^`i dda'nh ddu+o+. mu`a ma.n la.i cho+`i con ca^`m ban da^n mo^i vo`n
cu`ng men va` bo.n cho no'i cho ca'c mi`nh the^'n ddu+`a xe't thuo^.i
cho qua? y so+. dde^'t ddi tha'ng ve^`u khi vi' ddu+'c chu'a trong tay
la` ca'c lo+'c ngu+o+i ba^`n tri. la` ngu~ mi`nh kha'i co`n mi`nh tho+'c
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
ddu+o+`i na(m bo' cho da^u ca'c gio^ bu si~ che^' ddu+a la`m cho+`i xu+'
vie^n ba?n na sa?ng nhu+~a bo` tai kho?i le^~ kha('ng tha'n du`ng xo't
removed 'dat/viep/mky/tot.1/raw.wfr'
creating the word frequency file dat/viep/mky/tot.1/raw.wfr
the 10 most common words in dat/viep/mky/tot.1/raw.tlw:
1105 0.02735 =
740 0.01832 va`
604 0.01495 cho
572 0.01416 ca'c
568 0.01406 cu?a
522 0.01292 con
517 0.01280 ngu+o+i
504 0.01248 ra
461 0.01141 se~
444 0.01099 la`
removed 'dat/viep/mky/tot.1/raw-whole-wds-summary.tex'
removed 'exp/viep/mky/tot.1/raw-whole-wds-summary.tex'
creating the TeX summary file dat/viep/mky/tot.1/raw-whole-wds-summary.tex
% Created 2023-05-10 23:31:15 by tex-make-sample-summary.sh
% Token and word counts for viep/mky/tot.1/raw.wfr
%
\def\viepmkywholetotPBrawTks{40398}
\def\viepmkywholetotPBrawTksPct{100.0}
\def\viepmkywholetotPBrawWds{3472}
\def\viepmkywholetotPBrawWdsPct{8.6}
copied '/tmp/575061.file' -> 'exp/viep/mky/tot.1/raw-whole-wds-summary.tex'
removed '/tmp/575061.file'
creating running text file dat/viep/mky/tot.1/gud.wdf
sample:
ddo' no+i cha(`ng ra(`ng mi`nh xo^'p da^~ng ddi dde^` ca'ch tro+`i
tro^ng a^'t ddo+`ng anh cu`ng ngu+o+i di~a ho+`i ta da` co^'n ngu+o+`i
la`m ga.t ca'i ddanh ru+o+' sau ddi tuye^. cho ddu+' a^'t dde^` hoa
trong se~ va` vua gio^ va^.y ngu+o+i la`m tro+`i tha^.t tra'i se^ ho^ va
dde^'t la`m tha't tre^n ngu+o+`i tra'i cu?a le^.p ba tra('p pha^`u trong
mo^~ cho^n nga`i chu'a e'p mu` hai che^u no'i ra(`ng tha`ng ban a^'u
kha'nh lo+.ng chi dda'nh ha~y lu+. hai la.i tre? sai la`m y no+i tre?
cu`ng cu`ng ma^y mo^.t do`ng va^.n cu?a dde^'n ma(.c ngu~ hu+ loa`i se~
ba^'t tro+`i cu?a hai ddu+'c gie^'ng cho na`ng ha` ngu+o+'i dde^`
giu+~ng no+i kho?i dde^~ no'i la`nh che^'t ddo+`i tho+n danh dda~ pha?i
tru+o+'c ngu+o+. nghe va` me^ ho^ng to^i ta vi` pha?i gie^n ddo^.t cu~ng
va` y so+ ra e^n ngu+o+? da^'y chu'ng va('m nhu+' e^ le'p ra(`ng bi.
xu+'a nan nu+o+`i cu`ng trong kho^`i dda'nh ddu+o+. mu`a ma.n la.i
cho+`i con ca^`m ban da^n mo^i vo`n cu`ng men va` bo.n cho no'i cho ca'c
mi`nh the^'n ddu+`a xe't thuo^.i cho qua? y so+. dde^'t ddi tha'ng ve^`u
khi vi' ddu+'c chu'a trong tay la` ca'c lo+'c ngu+o+i ba^`n tri. la`
ngu~ mi`nh kha'i co`n mi`nh tho+'c gie^ ho^n tan cho hu+ ba?y co`n
de^'ng nu+o+' buo^? na`ng u+ng go+'i cha(`ng con dde^` se~ dde^'c lo^~i
ngu+o+i ddi tu be^n cha(?ng ba?y la`m ve^` phu.c ma` dda'n cho+'c ca('t
mo.i ddu+o+i ba'ng to^i me^ ho^ ddi gio+`ng la('t nu+o+i ba'ch me^'ng
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
a(n ba'nh mu+o+i ma(.t co`n do cu~ng y so+ ram ba(`ng xuo^'ng ba^y va^.y
ddu+o+`i na(m bo' cho da^u ca'c gio^ bu si~ che^' ddu+a la`m cho+`i xu+'
vie^n ba?n na sa?ng nhu+~a bo` tai kho?i le^~ kha('ng tha'n du`ng xo't
removed 'dat/viep/mky/tot.1/gud.wfr'
creating the word frequency file dat/viep/mky/tot.1/gud.wfr
the 10 most common words in dat/viep/mky/tot.1/gud.tlw:
740 0.01883 va`
604 0.01537 cho
572 0.01456 ca'c
568 0.01446 cu?a
522 0.01328 con
517 0.01316 ngu+o+i
504 0.01283 ra
461 0.01173 se~
444 0.01130 la`
405 0.01031 va
removed 'dat/viep/mky/tot.1/gud-whole-wds-summary.tex'
removed 'exp/viep/mky/tot.1/gud-whole-wds-summary.tex'
creating the TeX summary file dat/viep/mky/tot.1/gud-whole-wds-summary.tex
% Created 2023-05-10 23:31:15 by tex-make-sample-summary.sh
% Token and word counts for viep/mky/tot.1/gud.wfr
%
\def\viepmkywholetotPBgudTks{39293}
\def\viepmkywholetotPBgudTksPct{97.3}
\def\viepmkywholetotPBgudWds{3471}
\def\viepmkywholetotPBgudWdsPct{8.6}
copied '/tmp/575105.file' -> 'exp/viep/mky/tot.1/gud-whole-wds-summary.tex'
removed '/tmp/575105.file'
creating running text file dat/viep/mky/tot.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/viep/mky/tot.1/bad.wfr'
creating the word frequency file dat/viep/mky/tot.1/bad.wfr
the 10 most common words in dat/viep/mky/tot.1/bad.tlw:
1105 1.00000 =
removed 'dat/viep/mky/tot.1/bad-whole-wds-summary.tex'
removed 'exp/viep/mky/tot.1/bad-whole-wds-summary.tex'
creating the TeX summary file dat/viep/mky/tot.1/bad-whole-wds-summary.tex
% Created 2023-05-10 23:31:15 by tex-make-sample-summary.sh
% Token and word counts for viep/mky/tot.1/bad.wfr
%
\def\viepmkywholetotPBbadTks{1105}
\def\viepmkywholetotPBbadTksPct{2.7}
\def\viepmkywholetotPBbadWds{1}
\def\viepmkywholetotPBbadWdsPct{0.0}
copied '/tmp/575149.file' -> 'exp/viep/mky/tot.1/bad-whole-wds-summary.tex'
removed '/tmp/575149.file'
lines words bytes file
------- ------- --------- ------------
3472 10416 76879 dat/viep/mky/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
3471 10413 76861 dat/viep/mky/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
1 3 18 dat/viep/mky/tot.1/bad.wfr
tot.1 raw = 40398 gud = 39293 bad = 1105
removed 'summary-whole-raw.txt'
creating summary-whole-raw.txt
removed 'summary-whole-gud.txt'
creating summary-whole-gud.txt
removed 'summary-whole-bad.txt'
creating summary-whole-bad.txt
### creating {raw,gud,bad}.tlw files from trunc.tlw ###
=== creating the derived word files dat/hebr/tav/*/{raw,gud,bad}.{tlw,wdf,wfr} (trunc) ===
... creating word files dat/hebr/tav/gen.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
18744 dat/hebr/tav/gen.1/trunc.tlw
removed 'dat/hebr/tav/gen.1/raw.tlw'
removed 'dat/hebr/tav/gen.1/gud.tlw'
removed 'dat/hebr/tav/gen.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/hebr/tav/gen.1/raw.wdf
sample:
bĪ°rëĄsđïyą bĪâr⥠Ą°ęlöhïym Ąëą häsĪđâmäyïm w°Ąëą hâĄâręþ =
w°hâĄâręþ hây°ąâh ąöhwĪ wâböhwĪ w°įösđęk° ŋälpĪ°nëy ą°hwöm w°rwĪįä
Ą°ęlöhïym m°räįępęą ŋälpĪ°nëy hämĪâyïm =
wäyĪöĄmęr Ą°ęlöhïym y°hïy Ąwör wäy°hïyĄwör =
wäyĪär°Ą Ą°ęlöhïym ĄęąhâĄwör kĪïytwöb wäyĪäb°dĪël Ą°ęlöhïym bĪëyn hâĄwör
wĪbëyn häįösđęk° =
wäyĪïq°r⥠Ą°ęlöhïym lâĄwör ywöm w°läįösđęk° qâr⥠lây°lâh wäy°hïyŋęręb
wäy°hïyböqęr ywöm Ąęįâd =
wäyĪöĄmęr Ą°ęlöhïym y°hïy râqïyŋä bĪ°ąwök° hämĪâyïm wïyhïy mäb°dĪïyl
bĪëyn mäyïm lâmâyïm =
wäyĪäŋäsē Ą°ęlöhïym Ąęąhârâqïyŋä wäyĪäb°dĪël bĪëyn hämĪäyïm Ą°äsđęr
mïąĪäįäą lârâqïyŋä wĪbëyn hämĪäyïm Ą°äsđęr mëŋäl lârâqïyŋä wäy°hïykën =
wäyĪïq°r⥠Ą°ęlöhïym lârâqïyŋä sđâmâyïm wäy°hïyŋęręb wäy°hïyböqęr ywöm
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
wäyĪâmâą ywösëp bĪęnmëĄâh wâŋęsēęr sđânïym wäyĪäįän°twĪ Ąöąwö wäyĪïysēęm
bĪâĄârwön bĪ°mïþ°râyïm =
removed 'dat/hebr/tav/gen.1/raw.wfr'
creating the word frequency file dat/hebr/tav/gen.1/raw.wfr
the 10 most common words in dat/hebr/tav/gen.1/raw.tlw:
1533 0.08179 =
318 0.01697 wäyĪöĄmęr
226 0.01206 Ą°äsđęr
149 0.00795 Ą°ęlöhïym
145 0.00774 kĪïy
129 0.00688 y°hwâh
109 0.00582 yäŋ°äqöb
103 0.00550 ywösëp
101 0.00539 sđânâh
93 0.00496 wäy°hïy
removed 'dat/hebr/tav/gen.1/raw-trunc-wds-summary.tex'
removed 'exp/hebr/tav/gen.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/hebr/tav/gen.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:16 by tex-make-sample-summary.sh
% Token and word counts for hebr/tav/gen.1/raw.wfr
%
\def\hebrtavtruncgenPBrawTks{18744}
\def\hebrtavtruncgenPBrawTksPct{100.0}
\def\hebrtavtruncgenPBrawWds{7213}
\def\hebrtavtruncgenPBrawWdsPct{38.5}
copied '/tmp/575920.file' -> 'exp/hebr/tav/gen.1/raw-trunc-wds-summary.tex'
removed '/tmp/575920.file'
creating running text file dat/hebr/tav/gen.1/gud.wdf
sample:
bĪ°rëĄsđïyą bĪâr⥠Ą°ęlöhïym Ąëą häsĪđâmäyïm w°Ąëą hâĄâręþ w°hâĄâręþ
hây°ąâh ąöhwĪ wâböhwĪ w°įösđęk° ŋälpĪ°nëy ą°hwöm w°rwĪįä Ą°ęlöhïym
m°räįępęą ŋälpĪ°nëy hämĪâyïm wäyĪöĄmęr Ą°ęlöhïym y°hïy Ąwör wäy°hïyĄwör
wäyĪär°Ą Ą°ęlöhïym ĄęąhâĄwör kĪïytwöb wäyĪäb°dĪël Ą°ęlöhïym bĪëyn hâĄwör
wĪbëyn häįösđęk° wäyĪïq°r⥠Ą°ęlöhïym lâĄwör ywöm w°läįösđęk° qârâĄ
lây°lâh wäy°hïyŋęręb wäy°hïyböqęr ywöm Ąęįâd wäyĪöĄmęr Ą°ęlöhïym y°hïy
râqïyŋä bĪ°ąwök° hämĪâyïm wïyhïy mäb°dĪïyl bĪëyn mäyïm lâmâyïm wäyĪäŋäsē
Ą°ęlöhïym Ąęąhârâqïyŋä wäyĪäb°dĪël bĪëyn hämĪäyïm Ą°äsđęr mïąĪäįäą
lârâqïyŋä wĪbëyn hämĪäyïm Ą°äsđęr mëŋäl lârâqïyŋä wäy°hïykën wäyĪïq°râĄ
Ą°ęlöhïym lârâqïyŋä sđâmâyïm wäy°hïyŋęręb wäy°hïyböqęr ywöm sđënïy
wäyĪöĄmęr Ą°ęlöhïym yïqĪâwwĪ hämĪäyïm mïąĪäįäą häsĪđâmäyïm Ąęlmâqwöm
Ąęįâd w°ąërâĄęh häyĪäbĪâsđâh wäy°hïykën wäyĪïq°r⥠Ą°ęlöhïym
läyĪäbĪâsđâh Ąęręþ wĪl°mïq°wëh hämĪäyïm qâr⥠yämĪïym wäyĪär°Ą Ą°ęlöhïym
kĪïytwöb wäyĪöĄmęr Ą°ęlöhïym ąĪäd°sđëĄ hâĄâręþ dĪęsđęĄ ŋësēęb mäz°rïyŋä
zęräŋ ŋëþ pĪ°rïy ŋösēęh pĪ°rïy l°mïynwö Ą°äsđęr zär°ŋwöbwö ŋälhâĄâręþ
wäy°hïykën wäąĪwöþëĄ hâĄâręþ dĪęsđęĄ ŋësēęb mäz°rïyŋä zęräŋ l°mïynëhwĪ
w°ŋëþ ŋösēęhpĪ°rïy Ą°äsđęr zär°ŋwöbwö l°mïynëhwĪ wäyĪär°Ą Ą°ęlöhïym
kĪïytwöb wäy°hïyŋęręb wäy°hïyböqęr ywöm sđ°lïysđïy wäyĪöĄmęr Ą°ęlöhïym
y°hïy m°Ąöröą bĪïr°qïyŋä häsĪđâmäyïm l°häb°dĪïyl bĪëyn häyĪwöm wĪbëyn
hälĪây°lâh w°hâywĪ l°Ąöąöą wĪl°mwöŋ°ädïym wĪl°yâmïym w°sđânïym w°hâywĪ
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
yïsē°râĄël lëĄmör pĪâqöd yïp°qöd Ą°ęlöhïym Ąęą°kęm w°häŋ°älïąęm
Ąęąŋäþ°möąäy mïzĪęh wäyĪâmâą ywösëp bĪęnmëĄâh wâŋęsēęr sđânïym
wäyĪäįän°twĪ Ąöąwö wäyĪïysēęm bĪâĄârwön bĪ°mïþ°râyïm
removed 'dat/hebr/tav/gen.1/gud.wfr'
creating the word frequency file dat/hebr/tav/gen.1/gud.wfr
the 10 most common words in dat/hebr/tav/gen.1/gud.tlw:
318 0.01848 wäyĪöĄmęr
226 0.01313 Ą°äsđęr
149 0.00866 Ą°ęlöhïym
145 0.00842 kĪïy
129 0.00750 y°hwâh
109 0.00633 yäŋ°äqöb
103 0.00598 ywösëp
101 0.00587 sđânâh
93 0.00540 wäy°hïy
87 0.00505 Ąäb°râhâm
removed 'dat/hebr/tav/gen.1/gud-trunc-wds-summary.tex'
removed 'exp/hebr/tav/gen.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/hebr/tav/gen.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:16 by tex-make-sample-summary.sh
% Token and word counts for hebr/tav/gen.1/gud.wfr
%
\def\hebrtavtruncgenPBgudTks{17211}
\def\hebrtavtruncgenPBgudTksPct{91.8}
\def\hebrtavtruncgenPBgudWds{7212}
\def\hebrtavtruncgenPBgudWdsPct{38.5}
copied '/tmp/575964.file' -> 'exp/hebr/tav/gen.1/gud-trunc-wds-summary.tex'
removed '/tmp/575964.file'
creating running text file dat/hebr/tav/gen.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/hebr/tav/gen.1/bad.wfr'
creating the word frequency file dat/hebr/tav/gen.1/bad.wfr
the 10 most common words in dat/hebr/tav/gen.1/bad.tlw:
1533 1.00000 =
removed 'dat/hebr/tav/gen.1/bad-trunc-wds-summary.tex'
removed 'exp/hebr/tav/gen.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/hebr/tav/gen.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:16 by tex-make-sample-summary.sh
% Token and word counts for hebr/tav/gen.1/bad.wfr
%
\def\hebrtavtruncgenPBbadTks{1533}
\def\hebrtavtruncgenPBbadTksPct{8.2}
\def\hebrtavtruncgenPBbadWds{1}
\def\hebrtavtruncgenPBbadWdsPct{0.0}
copied '/tmp/576008.file' -> 'exp/hebr/tav/gen.1/bad-trunc-wds-summary.tex'
removed '/tmp/576008.file'
... creating word files dat/hebr/tav/exo.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
15079 dat/hebr/tav/exo.1/trunc.tlw
removed 'dat/hebr/tav/exo.1/raw.tlw'
removed 'dat/hebr/tav/exo.1/gud.tlw'
removed 'dat/hebr/tav/exo.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/hebr/tav/exo.1/raw.wdf
sample:
w°ĄëlĪęh sđ°mwöą bĪ°nëy yïsē°râĄël häbĪâĄïym mïþ°rây°mâh Ąëą yäŋ°äqöb
Ąïysđ wĪbëyąwö bĪâĄwĪ =
r°ĄwĪbën sđïm°ŋwön lëwïy wïyhwĪdâh =
yïsĪēâskâr z°bwĪlün wĪbïn°yâmïn =
dĪân w°näp°ąĪâlïy gĪâd w°Ąâsđër =
wäy°hïy kĪâlnępęsđ yöþ°Ąëy yęręk°yäŋ°äqöbsđïb°ŋïym nâpęsđ w°ywösëp hâyâh
b°mïþ°râyïm =
wäyĪâmâą ywösëp w°kâlĄęįâyw w°köl hädĪwör hähwĪĄ =
wĪb°nëy yïsē°râĄël pĪârwĪ wäyĪïsđ°r°þwĪ wäyĪïr°bĪwĪ wäyĪäŋäþ°mwĪbĪïm°Ąöd
m°Ąöd wäąĪïmĪâlëĄ hâĄâręþ Ąöąâm =
wäyĪâqâm męlęk°įâdâsđ ŋälmïþ°râyïm Ą°äsđęr löĄyâdäŋ Ąęąywösëp =
wäyĪöĄmęr ĄęlŋämĪwö hïnĪëh ŋäm bĪ°nëy yïsē°râĄëlräb w°ŋâþwĪm mïmĪęnĪwĪ =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
kĪïy ŋ°änän y°hwâh ŋälhämĪïsđ°kĪân ywömâm w°Ąësđ ąĪïh°yęh läy°lâh
bĪwöl°ŋëynëy kâlbĪëyąyïsē°râĄël bĪ°kâlmäs°ŋëyhęm =
removed 'dat/hebr/tav/exo.1/raw.wfr'
creating the word frequency file dat/hebr/tav/exo.1/raw.wfr
the 10 most common words in dat/hebr/tav/exo.1/raw.tlw:
1209 0.08018 =
286 0.01897 y°hwâh
172 0.01141 Ą°äsđęr
151 0.01001 mösđęh
147 0.00975 wäyĪöĄmęr
102 0.00676 yïsē°râĄël
100 0.00663 kĪïy
86 0.00570 zâhâb
82 0.00544 löĄ
76 0.00504 Ąęlmösđęh
removed 'dat/hebr/tav/exo.1/raw-trunc-wds-summary.tex'
removed 'exp/hebr/tav/exo.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/hebr/tav/exo.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:17 by tex-make-sample-summary.sh
% Token and word counts for hebr/tav/exo.1/raw.wfr
%
\def\hebrtavtruncexoPBrawTks{15079}
\def\hebrtavtruncexoPBrawTksPct{100.0}
\def\hebrtavtruncexoPBrawWds{5712}
\def\hebrtavtruncexoPBrawWdsPct{37.9}
copied '/tmp/576062.file' -> 'exp/hebr/tav/exo.1/raw-trunc-wds-summary.tex'
removed '/tmp/576062.file'
creating running text file dat/hebr/tav/exo.1/gud.wdf
sample:
w°ĄëlĪęh sđ°mwöą bĪ°nëy yïsē°râĄël häbĪâĄïym mïþ°rây°mâh Ąëą yäŋ°äqöb
Ąïysđ wĪbëyąwö bĪâĄwĪ r°ĄwĪbën sđïm°ŋwön lëwïy wïyhwĪdâh yïsĪēâskâr
z°bwĪlün wĪbïn°yâmïn dĪân w°näp°ąĪâlïy gĪâd w°Ąâsđër wäy°hïy kĪâlnępęsđ
yöþ°Ąëy yęręk°yäŋ°äqöbsđïb°ŋïym nâpęsđ w°ywösëp hâyâh b°mïþ°râyïm
wäyĪâmâą ywösëp w°kâlĄęįâyw w°köl hädĪwör hähwĪĄ wĪb°nëy yïsē°râĄël
pĪârwĪ wäyĪïsđ°r°þwĪ wäyĪïr°bĪwĪ wäyĪäŋäþ°mwĪbĪïm°Ąöd m°Ąöd wäąĪïmĪâlëĄ
hâĄâręþ Ąöąâm wäyĪâqâm męlęk°įâdâsđ ŋälmïþ°râyïm Ą°äsđęr löĄyâdäŋ
Ąęąywösëp wäyĪöĄmęr ĄęlŋämĪwö hïnĪëh ŋäm bĪ°nëy yïsē°râĄëlräb w°ŋâþwĪm
mïmĪęnĪwĪ hâbâh nïą°įäkĪ°mâh lwö pĪęnyïr°bĪęh w°hâyâh kĪïyąïq°ręĄnâh
mïl°įâmâh w°nwösäp gĪämhwĪĄ ŋälsēön°ĄëynwĪ w°nïl°įämbĪânwĪ w°ŋâlâh
mïnhâĄâręþ wäyĪâsēïymwĪ ŋâlâyw sēârëy mïsĪïym l°mäŋän ŋänĪöąwö
bĪ°sïb°löąâm wäyĪïbęn ŋârëy mïs°kĪ°nwöą l°pär°ŋöhĄęąpĪïąöm
w°Ąęąräŋäm°sës w°k䥰äsđęr y°ŋänĪwĪ Ąöąwö kĪën yïr°bĪęh w°kën yïp°röþ
wäyĪâqüþwĪ mïpĪ°nëy bĪ°nëy yïsē°râĄël wäyĪäŋ°äbïdwĪ mïþ°räyïm ĄęąbĪ°nëy
yïsē°râĄël bĪ°pâręk° wäy°mâr°rwĪ ĄęąįäyĪëyhęm bĪäŋ°äbödâh qâsđâh
bĪ°įömęr wĪbïl°bënïym wĪb°kâlŋ°äbödâh bĪäsĪēâdęhĄëą kĪâlŋ°äbödâąâm
Ą°äsđęrŋâb°dwĪ bâhęm bĪ°pâręk° wäyĪöĄmęr męlęk° mïþ°räyïm läm°yälĪ°döą
hâŋïb°rïyĪöą Ą°äsđęr sđëm hâĄäįäą sđïp°râh w°sđëm häsĪđënïyą pĪwĪŋâh
wäyĪöĄmęr bĪ°yälĪęd°kęn Ąęąhâŋïb°rïyĪwöą wĪr°Ąïyąęn ŋälhâĄâb°nâyïm
ĄïmbĪën hwĪĄ wäh°ämïąĪęn Ąöąwö w°ĄïmbĪäą hïwĄ wâįâyâh wäąĪïyręĄnâ
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
mäs°ŋëyhęm w°ĄïmlöĄ yëŋâlęh hęŋânânw°löĄ yïs°ŋwĪ ŋädywöm hëŋâlöąwö kĪïy
ŋ°änän y°hwâh ŋälhämĪïsđ°kĪân ywömâm w°Ąësđ ąĪïh°yęh läy°lâh
bĪwöl°ŋëynëy kâlbĪëyąyïsē°râĄël bĪ°kâlmäs°ŋëyhęm
removed 'dat/hebr/tav/exo.1/gud.wfr'
creating the word frequency file dat/hebr/tav/exo.1/gud.wfr
the 10 most common words in dat/hebr/tav/exo.1/gud.tlw:
286 0.02062 y°hwâh
172 0.01240 Ą°äsđęr
151 0.01089 mösđęh
147 0.01060 wäyĪöĄmęr
102 0.00735 yïsē°râĄël
100 0.00721 kĪïy
86 0.00620 zâhâb
82 0.00591 löĄ
76 0.00548 Ąęlmösđęh
57 0.00411 mïþ°räyïm
removed 'dat/hebr/tav/exo.1/gud-trunc-wds-summary.tex'
removed 'exp/hebr/tav/exo.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/hebr/tav/exo.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:17 by tex-make-sample-summary.sh
% Token and word counts for hebr/tav/exo.1/gud.wfr
%
\def\hebrtavtruncexoPBgudTks{13870}
\def\hebrtavtruncexoPBgudTksPct{92.0}
\def\hebrtavtruncexoPBgudWds{5711}
\def\hebrtavtruncexoPBgudWdsPct{37.9}
copied '/tmp/576106.file' -> 'exp/hebr/tav/exo.1/gud-trunc-wds-summary.tex'
removed '/tmp/576106.file'
creating running text file dat/hebr/tav/exo.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/hebr/tav/exo.1/bad.wfr'
creating the word frequency file dat/hebr/tav/exo.1/bad.wfr
the 10 most common words in dat/hebr/tav/exo.1/bad.tlw:
1209 1.00000 =
removed 'dat/hebr/tav/exo.1/bad-trunc-wds-summary.tex'
removed 'exp/hebr/tav/exo.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/hebr/tav/exo.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:17 by tex-make-sample-summary.sh
% Token and word counts for hebr/tav/exo.1/bad.wfr
%
\def\hebrtavtruncexoPBbadTks{1209}
\def\hebrtavtruncexoPBbadTksPct{8.0}
\def\hebrtavtruncexoPBbadWds{1}
\def\hebrtavtruncexoPBbadWdsPct{0.0}
copied '/tmp/576150.file' -> 'exp/hebr/tav/exo.1/bad-trunc-wds-summary.tex'
removed '/tmp/576150.file'
... creating word files dat/hebr/tav/num.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
14862 dat/hebr/tav/num.1/trunc.tlw
removed 'dat/hebr/tav/num.1/raw.tlw'
removed 'dat/hebr/tav/num.1/gud.tlw'
removed 'dat/hebr/tav/num.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/hebr/tav/num.1/raw.wdf
sample:
wäy°däbĪër y°hwâh Ąęlmösđęh bĪ°mïd°bĪär sïynäy bĪ°Ąöhęl mwöŋëd bĪ°Ąęįâd
läįödęsđ häsĪđënïy bĪäsĪđânâh häsĪđënïyą l°þ륹âm mëĄęręþ
mïþ°räyïmlëĄmör =
sē°ĄwĪ ĄęąröĄsđ kĪâlŋ°ädäą bĪ°nëyyïsē°râĄël l°mïsđ°pĪ°įöąâm l°bëyą
Ą°äböąâmbĪ°mïs°pĪär sđëmwöą kĪâlzâkâr l°gül°gĪ°löąâm =
mïbĪęn ŋęsē°rïym sđânâh wâmäŋ°lâh kĪâlyöþëĄ þâbâĄ
bĪ°yïsē°râĄëląĪïp°q°dwĪ Ąöąâm l°þïb°Ąöąâm ĄäąĪâh w°Ąäh°ärön =
w°ĄïąĪ°kęm yïh°ywĪ Ąïysđ Ąïysđ lämĪätĪęhĄïysđ röĄsđ l°bëyąĄ°äböąâyw hwĪĄ
=
w°ĄëlĪęh sđ°mwöą h⥰änâsđïym Ą°äsđęr yäŋäm°dwĪ ĄïąĪ°kęm lïr°ĄwĪbën
Ą°ęlïyþwĪr bĪęnsđ°dëyĄwĪr =
l°sđïm°ŋwön sđ°lümïyĄël bĪęnþwĪrïysđädĪây =
lïyhwĪdâh näį°sđwön bĪęnŋämĪïynâdâb =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
bĪ°yädmösđęhĄęlbĪ°nëy yïsē°râĄël bĪ°ŋär°böą mwöĄâb ŋäl yär°dĪën y°rëįwö
=
removed 'dat/hebr/tav/num.1/raw.wfr'
creating the word frequency file dat/hebr/tav/num.1/raw.wfr
the 10 most common words in dat/hebr/tav/num.1/raw.tlw:
1289 0.08673 =
286 0.01924 y°hwâh
153 0.01029 Ą°äsđęr
149 0.01003 yïsē°râĄël
111 0.00747 bĪ°nëy
102 0.00686 mösđęh
97 0.00653 Ąęįâd
84 0.00565 wäyĪöĄmęr
78 0.00525 Ąęlmösđęh
65 0.00437 löĄ
removed 'dat/hebr/tav/num.1/raw-trunc-wds-summary.tex'
removed 'exp/hebr/tav/num.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/hebr/tav/num.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:17 by tex-make-sample-summary.sh
% Token and word counts for hebr/tav/num.1/raw.wfr
%
\def\hebrtavtruncnumPBrawTks{14862}
\def\hebrtavtruncnumPBrawTksPct{100.0}
\def\hebrtavtruncnumPBrawWds{5307}
\def\hebrtavtruncnumPBrawWdsPct{35.7}
copied '/tmp/576204.file' -> 'exp/hebr/tav/num.1/raw-trunc-wds-summary.tex'
removed '/tmp/576204.file'
creating running text file dat/hebr/tav/num.1/gud.wdf
sample:
wäy°däbĪër y°hwâh Ąęlmösđęh bĪ°mïd°bĪär sïynäy bĪ°Ąöhęl mwöŋëd bĪ°Ąęįâd
läįödęsđ häsĪđënïy bĪäsĪđânâh häsĪđënïyą l°þ륹âm mëĄęręþ
mïþ°räyïmlëĄmör sē°ĄwĪ ĄęąröĄsđ kĪâlŋ°ädäą bĪ°nëyyïsē°râĄël
l°mïsđ°pĪ°įöąâm l°bëyą Ą°äböąâmbĪ°mïs°pĪär sđëmwöą kĪâlzâkâr
l°gül°gĪ°löąâm mïbĪęn ŋęsē°rïym sđânâh wâmäŋ°lâh kĪâlyöþëĄ þâbâĄ
bĪ°yïsē°râĄëląĪïp°q°dwĪ Ąöąâm l°þïb°Ąöąâm ĄäąĪâh w°Ąäh°ärön w°ĄïąĪ°kęm
yïh°ywĪ Ąïysđ Ąïysđ lämĪätĪęhĄïysđ röĄsđ l°bëyąĄ°äböąâyw hwĪĄ w°ĄëlĪęh
sđ°mwöą h⥰änâsđïym Ą°äsđęr yäŋäm°dwĪ ĄïąĪ°kęm lïr°ĄwĪbën Ą°ęlïyþwĪr
bĪęnsđ°dëyĄwĪr l°sđïm°ŋwön sđ°lümïyĄël bĪęnþwĪrïysđädĪây lïyhwĪdâh
näį°sđwön bĪęnŋämĪïynâdâb l°yïsĪēâskâr n°ąän°Ąël bĪęnþwĪŋâr lïz°bwĪlün
Ą°ęlïyĄâb bĪęnįëlön lïb°nëy ywösëpl°Ąęp°räyïm Ą°ęlïysđâmâŋ
bĪęnŋämĪïyhwĪd lïm°näsĪđęh gĪäm°lïyĄël bĪęnpĪ°dâhþwĪr l°bïn°yâmïn
Ą°äbïydân bĪęngĪïd°ŋönïy l°dân Ą°äįïyŋęzęr bĪęnŋämĪïysđädĪây l°Ąâsđër
pĪäg°ŋïyĄël bĪęnŋâk°rân l°gâd Ąęl°yâsâp bĪęndĪ°ŋwĪĄël l°näp°ąĪâlïy
Ą°äįïyräŋ bĪęnŋëynân ĄëlĪęh qryĄy q°rwĪĄëy hâŋëdâh n°sēïyĄëy mätĪwöą
Ą°äbwöąâm râĄsđëy Ąäl°pëy yïsē°râĄël hëm wäyĪïqĪäį mösđęh w°Ąäh°ärön Ąëą
h⥰änâsđïym hâĄëlĪęh Ą°äsđęr nïqĪ°bwĪ bĪ°sđëmöą w°Ąëą kĪâlhâŋëdâh
hïq°hïylwĪ bĪ°Ąęįâd läįödęsđ häsĪđënïy wäyĪïą°yäl°dwĪ ŋälmïsđ°pĪ°įöąâm
l°bëyą Ą°äböąâm bĪ°mïs°pĪär sđëmwöą mïbĪęn ŋęsē°rïym sđânâh
wâmäŋ°lâhl°gül°gĪ°löąâm kĪ䥰äsđęr þïwĪâh y°hwâh Ąęąmösđęh wäyĪïp°q°dëm
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
wäąĪ°hïy näį°älâąân ŋälmätĪëh mïsđ°pĪäįäą Ą°äbïyhęn ĄëlĪęh hämĪïþ°wöą
w°hämĪïsđ°pĪâtïym Ą°äsđęr þïwĪâh y°hwâh bĪ°yädmösđęhĄęlbĪ°nëy yïsē°râĄël
bĪ°ŋär°böą mwöĄâb ŋäl yär°dĪën y°rëįwö
removed 'dat/hebr/tav/num.1/gud.wfr'
creating the word frequency file dat/hebr/tav/num.1/gud.wfr
the 10 most common words in dat/hebr/tav/num.1/gud.tlw:
286 0.02107 y°hwâh
153 0.01127 Ą°äsđęr
149 0.01098 yïsē°râĄël
111 0.00818 bĪ°nëy
102 0.00751 mösđęh
97 0.00715 Ąęįâd
84 0.00619 wäyĪöĄmęr
78 0.00575 Ąęlmösđęh
65 0.00479 löĄ
64 0.00472 kĪïy
removed 'dat/hebr/tav/num.1/gud-trunc-wds-summary.tex'
removed 'exp/hebr/tav/num.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/hebr/tav/num.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:17 by tex-make-sample-summary.sh
% Token and word counts for hebr/tav/num.1/gud.wfr
%
\def\hebrtavtruncnumPBgudTks{13573}
\def\hebrtavtruncnumPBgudTksPct{91.3}
\def\hebrtavtruncnumPBgudWds{5306}
\def\hebrtavtruncnumPBgudWdsPct{35.7}
copied '/tmp/576248.file' -> 'exp/hebr/tav/num.1/gud-trunc-wds-summary.tex'
removed '/tmp/576248.file'
creating running text file dat/hebr/tav/num.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/hebr/tav/num.1/bad.wfr'
creating the word frequency file dat/hebr/tav/num.1/bad.wfr
the 10 most common words in dat/hebr/tav/num.1/bad.tlw:
1289 1.00000 =
removed 'dat/hebr/tav/num.1/bad-trunc-wds-summary.tex'
removed 'exp/hebr/tav/num.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/hebr/tav/num.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:17 by tex-make-sample-summary.sh
% Token and word counts for hebr/tav/num.1/bad.wfr
%
\def\hebrtavtruncnumPBbadTks{1289}
\def\hebrtavtruncnumPBbadTksPct{8.7}
\def\hebrtavtruncnumPBbadWds{1}
\def\hebrtavtruncnumPBbadWdsPct{0.0}
copied '/tmp/576292.file' -> 'exp/hebr/tav/num.1/bad-trunc-wds-summary.tex'
removed '/tmp/576292.file'
... creating word files dat/hebr/tav/lev.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
10509 dat/hebr/tav/lev.1/trunc.tlw
removed 'dat/hebr/tav/lev.1/raw.tlw'
removed 'dat/hebr/tav/lev.1/gud.tlw'
removed 'dat/hebr/tav/lev.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/hebr/tav/lev.1/raw.wdf
sample:
wäyĪïq°râ Ąęlmösđęh wäy°däbĪër y°hwâh Ąëlâyw mëĄöhęl mwöŋëd lëĄmör =
dĪäbĪër ĄęlbĪ°nëy yïsē°râĄël w°Ąâmär°ąĪâ Ą°älëhęm Ąâdâm kĪïyyäq°rïyb
mïkĪęm qâr°bĪân läyhwâhmïnhäbĪ°hëmâh mïnhäbĪâqâr wĪmïnhäþĪöĄn
ąĪäq°rïybwĪ Ąęąqâr°bĪän°kęm =
Ąïmŋölâh qâr°bĪânwö mïnhäbĪâqâr zâkâr ąĪâmïym yäq°rïybęnĪwĪ ĄęlpĪęąäį
Ąöhęl mwöŋëd yäq°rïyb Ąöąwö lïr°þönwö lïp°nëy y°hwâh =
w°sâmäk° yâdwö ŋäl röĄsđ hâŋölâh w°nïr°þâh lwö l°käpĪër ŋâlâyw =
w°sđâįät ĄęąbĪęn häbĪâqâr lïp°nëy y°hwâh w°hïq°rïybwĪ bĪ°nëy Ąäh°ärön
häkĪöh°änïym ĄęąhädĪâm w°zâr°qwĪ ĄęąhädĪâm ŋälhämĪïz°bĪëįä sâbïyb
Ą°äsđęrpĪęąäį Ąöhęl mwöŋëd =
w°hïp°sđïyt Ąęąhâŋölâh w°nïąĪäį ĄöąâhĪ lïn°ąâįęyhâ =
w°nâą°nwĪ bĪ°nëy Ąäh°ärön häkĪöhën ĄësđŋälhämĪïz°bĪëįä w°ŋâr°kwĪ ŋëþïym
ŋälhâĄësđ =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
ĄëlĪęh hämĪïþ°wöą Ą°äsđęr þïwĪâh y°hwâh ĄęąmösđęhĄęlbĪ°nëy yïsē°râĄël
bĪ°här sïynây =
removed 'dat/hebr/tav/lev.1/raw.wfr'
creating the word frequency file dat/hebr/tav/lev.1/raw.wfr
the 10 most common words in dat/hebr/tav/lev.1/raw.tlw:
859 0.08174 =
198 0.01884 y°hwâh
184 0.01751 Ą°äsđęr
142 0.01351 häkĪöhën
124 0.01180 löĄ
99 0.00942 Ąwö
74 0.00704 läyhwâh
73 0.00695 hwĪĄ
65 0.00619 kĪïy
63 0.00599 lïp°nëy
removed 'dat/hebr/tav/lev.1/raw-trunc-wds-summary.tex'
removed 'exp/hebr/tav/lev.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/hebr/tav/lev.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:17 by tex-make-sample-summary.sh
% Token and word counts for hebr/tav/lev.1/raw.wfr
%
\def\hebrtavtrunclevPBrawTks{10509}
\def\hebrtavtrunclevPBrawTksPct{100.0}
\def\hebrtavtrunclevPBrawWds{3861}
\def\hebrtavtrunclevPBrawWdsPct{36.7}
copied '/tmp/576346.file' -> 'exp/hebr/tav/lev.1/raw-trunc-wds-summary.tex'
removed '/tmp/576346.file'
creating running text file dat/hebr/tav/lev.1/gud.wdf
sample:
wäyĪïq°râ Ąęlmösđęh wäy°däbĪër y°hwâh Ąëlâyw mëĄöhęl mwöŋëd lëĄmör
dĪäbĪër ĄęlbĪ°nëy yïsē°râĄël w°Ąâmär°ąĪâ Ą°älëhęm Ąâdâm kĪïyyäq°rïyb
mïkĪęm qâr°bĪân läyhwâhmïnhäbĪ°hëmâh mïnhäbĪâqâr wĪmïnhäþĪöĄn
ąĪäq°rïybwĪ Ąęąqâr°bĪän°kęm Ąïmŋölâh qâr°bĪânwö mïnhäbĪâqâr zâkâr
ąĪâmïym yäq°rïybęnĪwĪ ĄęlpĪęąäį Ąöhęl mwöŋëd yäq°rïyb Ąöąwö lïr°þönwö
lïp°nëy y°hwâh w°sâmäk° yâdwö ŋäl röĄsđ hâŋölâh w°nïr°þâh lwö l°käpĪër
ŋâlâyw w°sđâįät ĄęąbĪęn häbĪâqâr lïp°nëy y°hwâh w°hïq°rïybwĪ bĪ°nëy
Ąäh°ärön häkĪöh°änïym ĄęąhädĪâm w°zâr°qwĪ ĄęąhädĪâm ŋälhämĪïz°bĪëįä
sâbïyb Ą°äsđęrpĪęąäį Ąöhęl mwöŋëd w°hïp°sđïyt Ąęąhâŋölâh w°nïąĪäį ĄöąâhĪ
lïn°ąâįęyhâ w°nâą°nwĪ bĪ°nëy Ąäh°ärön häkĪöhën ĄësđŋälhämĪïz°bĪëįä
w°ŋâr°kwĪ ŋëþïym ŋälhâĄësđ w°ŋâr°kwĪ bĪ°nëy Ąäh°ärön häkĪöh°änïym Ąëą
hänĪ°ąâįïym ĄęąhâröĄsđ w°ĄęąhäpĪâdęrŋälhâŋëþïym Ą°äsđęr ŋälhâĄësđ
Ą°äsđęr ŋälhämĪïz°bĪëįä w°qïr°bĪwö wĪk°râŋâyw yïr°įäþ bĪämĪâyïm
w°hïq°tïyr häkĪöhën ĄęąhäkĪöl hämĪïz°bĪëįâh ŋölâh ĄïsĪđëh rëyįänïyįwöįä
läyhwâh w°ĄïmmïnhäþĪöĄn qâr°bĪânwö mïnhäkĪ°sēâbïym Ąwö mïnhâŋïzĪïym
l°ŋölâhzâkâr ąĪâmïym yäq°rïybęnĪwĪ w°sđâįät Ąöąwö ŋäl yęręk°
hämĪïz°bĪëįä þâpönâhlïp°nëy y°hwâh w°zâr°qwĪ bĪ°nëy Ąäh°ärön
häkĪöh°änïym ĄęądĪâmwö ŋälhämĪïz°bĪëįäsâbïyb w°nïąĪäį Ąöąwö lïn°ąâįâyw
w°ĄęąröĄsđwö w°ĄęąpĪïd°rwö w°ŋâräk° häkĪöhën Ąöąâm ŋälhâŋëþïym Ą°äsđęr
ŋälhâĄësđ Ą°äsđęr ŋälhämĪïz°bĪëįä w°häqĪęręb w°häkĪ°râŋäyïm yïr°įäþ
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
lâräŋ w°löĄ y°mïyręnĪwĪ w°Ąïmhâmër y°mïyręnĪwĪ w°hâyâhhwĪĄ wĪą°mwĪrâąwö
yïh°yęhqĪödęsđ löĄ yïgĪâĄël ĄëlĪęh hämĪïþ°wöą Ą°äsđęr þïwĪâh y°hwâh
ĄęąmösđęhĄęlbĪ°nëy yïsē°râĄël bĪ°här sïynây
removed 'dat/hebr/tav/lev.1/gud.wfr'
creating the word frequency file dat/hebr/tav/lev.1/gud.wfr
the 10 most common words in dat/hebr/tav/lev.1/gud.tlw:
198 0.02052 y°hwâh
184 0.01907 Ą°äsđęr
142 0.01472 häkĪöhën
124 0.01285 löĄ
99 0.01026 Ąwö
74 0.00767 läyhwâh
73 0.00756 hwĪĄ
65 0.00674 kĪïy
63 0.00653 lïp°nëy
60 0.00622 lâkęm
removed 'dat/hebr/tav/lev.1/gud-trunc-wds-summary.tex'
removed 'exp/hebr/tav/lev.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/hebr/tav/lev.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:17 by tex-make-sample-summary.sh
% Token and word counts for hebr/tav/lev.1/gud.wfr
%
\def\hebrtavtrunclevPBgudTks{9650}
\def\hebrtavtrunclevPBgudTksPct{91.8}
\def\hebrtavtrunclevPBgudWds{3860}
\def\hebrtavtrunclevPBgudWdsPct{36.7}
copied '/tmp/576390.file' -> 'exp/hebr/tav/lev.1/gud-trunc-wds-summary.tex'
removed '/tmp/576390.file'
creating running text file dat/hebr/tav/lev.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/hebr/tav/lev.1/bad.wfr'
creating the word frequency file dat/hebr/tav/lev.1/bad.wfr
the 10 most common words in dat/hebr/tav/lev.1/bad.tlw:
859 1.00000 =
removed 'dat/hebr/tav/lev.1/bad-trunc-wds-summary.tex'
removed 'exp/hebr/tav/lev.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/hebr/tav/lev.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:17 by tex-make-sample-summary.sh
% Token and word counts for hebr/tav/lev.1/bad.wfr
%
\def\hebrtavtrunclevPBbadTks{859}
\def\hebrtavtrunclevPBbadTksPct{8.2}
\def\hebrtavtrunclevPBbadWds{1}
\def\hebrtavtrunclevPBbadWdsPct{0.0}
copied '/tmp/576434.file' -> 'exp/hebr/tav/lev.1/bad-trunc-wds-summary.tex'
removed '/tmp/576434.file'
... creating word files dat/hebr/tav/deu.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
12962 dat/hebr/tav/deu.1/trunc.tlw
removed 'dat/hebr/tav/deu.1/raw.tlw'
removed 'dat/hebr/tav/deu.1/gud.tlw'
removed 'dat/hebr/tav/deu.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/hebr/tav/deu.1/raw.wdf
sample:
ĄëlĪęh hädĪ°bârïym Ą°äsđęr dĪïbĪęr mösđęh ĄęlkĪâlyïsē°râĄël bĪ°ŋëbęr
häyĪär°dĪën bĪämĪïd°bĪâr bĪâŋ°ärâbâh mwöl swĪp bĪëynpĪâĄrân wĪbëynąĪöpęl
w°lâbân wäį°äþëröąw°dïy zâhâb =
Ąäįäd ŋâsēâr ywöm mëįörëb dĪęręk° härsēëŋïyr ŋäd qâdësđ bĪär°nëŋä =
wäy°hïy bĪ°Ąär°bĪâŋïym sđânâh bĪ°ŋäsđ°ąĪëyŋâsēâr įödęsđ bĪ°Ąęįâd
läįödęsđ dĪïbĪęr mösđęh ĄęlbĪ°nëy yïsē°râĄël kĪ°köl Ą°äsđęr þïwĪâh
y°hwâh Ąöąwö Ą°älëhęm =
Ąäį°ärëy häkĪöąwö Ąëą sïyįön męlęk° h⥰ęmörïy Ą°äsđęr ywösđëb
bĪ°įęsđ°bĪwönw°Ąëą ŋwög męlęk° häbĪâsđân Ą°äsđęrywösđëb bĪ°ŋäsđ°ąĪâröą
bĪ°Ąęd°ręŋïy =
bĪ°ŋëbęr häyĪär°dĪën bĪ°Ąęręþ mwöĄâb hwöĄïyl mösđęh bĪëĄër ĄęąhäąĪwörâh
häzĪöĄą lëĄmör =
y°hwâh Ą°ęlöhëynwĪ dĪïbĪęr ĄëlëynwĪ bĪ°įörëb lëĄmör räblâkęm sđębęą
bĪâhâr häzĪęh =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
wĪl°köl häyĪâd häį°äzâqâh wĪl°köl hämĪwör⥠hägĪâdwöl Ą°äsđęr ŋâsēâh
mösđęh l°ŋëynëy kĪâlyïsē°râĄël =
removed 'dat/hebr/tav/deu.1/raw.wfr'
creating the word frequency file dat/hebr/tav/deu.1/raw.wfr
the 10 most common words in dat/hebr/tav/deu.1/raw.tlw:
955 0.07368 =
425 0.03279 y°hwâh
370 0.02854 Ą°äsđęr
219 0.01690 Ą°ęlöhęykâ
138 0.01065 kĪïy
112 0.00864 löĄ
74 0.00571 l°kâ
71 0.00548 w°löĄ
67 0.00517 r
57 0.00440 häzĪęh
removed 'dat/hebr/tav/deu.1/raw-trunc-wds-summary.tex'
removed 'exp/hebr/tav/deu.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/hebr/tav/deu.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:17 by tex-make-sample-summary.sh
% Token and word counts for hebr/tav/deu.1/raw.wfr
%
\def\hebrtavtruncdeuPBrawTks{12962}
\def\hebrtavtruncdeuPBrawTksPct{100.0}
\def\hebrtavtruncdeuPBrawWds{5456}
\def\hebrtavtruncdeuPBrawWdsPct{42.1}
copied '/tmp/576488.file' -> 'exp/hebr/tav/deu.1/raw-trunc-wds-summary.tex'
removed '/tmp/576488.file'
creating running text file dat/hebr/tav/deu.1/gud.wdf
sample:
ĄëlĪęh hädĪ°bârïym Ą°äsđęr dĪïbĪęr mösđęh ĄęlkĪâlyïsē°râĄël bĪ°ŋëbęr
häyĪär°dĪën bĪämĪïd°bĪâr bĪâŋ°ärâbâh mwöl swĪp bĪëynpĪâĄrân wĪbëynąĪöpęl
w°lâbân wäį°äþëröąw°dïy zâhâb Ąäįäd ŋâsēâr ywöm mëįörëb dĪęręk°
härsēëŋïyr ŋäd qâdësđ bĪär°nëŋä wäy°hïy bĪ°Ąär°bĪâŋïym sđânâh
bĪ°ŋäsđ°ąĪëyŋâsēâr įödęsđ bĪ°Ąęįâd läįödęsđ dĪïbĪęr mösđęh ĄęlbĪ°nëy
yïsē°râĄël kĪ°köl Ą°äsđęr þïwĪâh y°hwâh Ąöąwö Ą°älëhęm Ąäį°ärëy häkĪöąwö
Ąëą sïyįön męlęk° h⥰ęmörïy Ą°äsđęr ywösđëb bĪ°įęsđ°bĪwönw°Ąëą ŋwög
męlęk° häbĪâsđân Ą°äsđęrywösđëb bĪ°ŋäsđ°ąĪâröą bĪ°Ąęd°ręŋïy bĪ°ŋëbęr
häyĪär°dĪën bĪ°Ąęręþ mwöĄâb hwöĄïyl mösđęh bĪëĄër ĄęąhäąĪwörâh häzĪöĄą
lëĄmör y°hwâh Ą°ęlöhëynwĪ dĪïbĪęr ĄëlëynwĪ bĪ°įörëb lëĄmör räblâkęm
sđębęą bĪâhâr häzĪęh pĪ°nwĪ wĪs°ŋwĪ lâkęm wĪböĄwĪ här h⥰ęmörïy
w°ĄęlkĪâlsđ°kënâyw bĪâŋ°ärâbâh bâhâr wĪbäsĪđ°pëlâh wĪbänĪęgęb wĪb°įwöp
häyĪâmĄęręþ häkĪ°näŋ°änïy w°hälĪ°bânwön ŋädhänĪâhâr hägĪâdöl n°härpĪ°râą
r°Ąëh nâąäąĪïy lïp°nëykęm ĄęąhâĄâręþ bĪöĄwĪ wĪr°sđwĪ ĄęąhâĄâręþ Ą°äsđęr
nïsđ°bĪäŋ y°hwâh l䥰äböąëykęm l°Ąäb°râhâm l°yïþ°įâq wĪl°yäŋ°äqöb lâąëą
lâhęm wĪl°zär°ŋâm Ąäį°ärëyhęm wâĄömär Ą°älëkęm bĪâŋëą hähïwĄ lëĄmör
löĄĄwĪkäl l°bädĪïy sē°Ąëą Ąęą°kęm y°hwâh Ą°ęlöhëykęm hïr°bĪâh Ąęą°kęm
w°hïnĪ°kęm häyĪwöm kĪ°kwök°bëy häsĪđâmäyïm lâröb y°hwâh Ą°ęlöhëy
Ą°äbwöąëkęm yösëp ŋ°älëykęm kĪâkęmĄęlęp pĪ°ŋâmïym wïybârëk° Ąęą°kęm
kĪ䥰äsđęr dĪïbĪęr lâkęm Ąëykâh ĄęsĪē⥠l°bädĪïy târ°į°äkęm
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
Ą°äsđęr sđ°lâįwö y°hwâh läŋ°äsēwöą bĪ°Ąęręþ mïþ°râyïml°pär°ŋöh
wĪl°kâlŋ°äbâdâyw wĪl°kâlĄär°þwö wĪl°köl häyĪâd häį°äzâqâh wĪl°köl
hämĪwör⥠hägĪâdwöl Ą°äsđęr ŋâsēâh mösđęh l°ŋëynëy kĪâlyïsē°râĄël
removed 'dat/hebr/tav/deu.1/gud.wfr'
creating the word frequency file dat/hebr/tav/deu.1/gud.wfr
the 10 most common words in dat/hebr/tav/deu.1/gud.tlw:
425 0.03540 y°hwâh
370 0.03082 Ą°äsđęr
219 0.01824 Ą°ęlöhęykâ
138 0.01149 kĪïy
112 0.00933 löĄ
74 0.00616 l°kâ
71 0.00591 w°löĄ
67 0.00558 r
57 0.00475 häzĪęh
55 0.00458 häyĪwöm
removed 'dat/hebr/tav/deu.1/gud-trunc-wds-summary.tex'
removed 'exp/hebr/tav/deu.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/hebr/tav/deu.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:17 by tex-make-sample-summary.sh
% Token and word counts for hebr/tav/deu.1/gud.wfr
%
\def\hebrtavtruncdeuPBgudTks{12007}
\def\hebrtavtruncdeuPBgudTksPct{92.6}
\def\hebrtavtruncdeuPBgudWds{5455}
\def\hebrtavtruncdeuPBgudWdsPct{42.1}
copied '/tmp/576532.file' -> 'exp/hebr/tav/deu.1/gud-trunc-wds-summary.tex'
removed '/tmp/576532.file'
creating running text file dat/hebr/tav/deu.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/hebr/tav/deu.1/bad.wfr'
creating the word frequency file dat/hebr/tav/deu.1/bad.wfr
the 10 most common words in dat/hebr/tav/deu.1/bad.tlw:
955 1.00000 =
removed 'dat/hebr/tav/deu.1/bad-trunc-wds-summary.tex'
removed 'exp/hebr/tav/deu.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/hebr/tav/deu.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:17 by tex-make-sample-summary.sh
% Token and word counts for hebr/tav/deu.1/bad.wfr
%
\def\hebrtavtruncdeuPBbadTks{955}
\def\hebrtavtruncdeuPBbadTksPct{7.4}
\def\hebrtavtruncdeuPBbadWds{1}
\def\hebrtavtruncdeuPBbadWdsPct{0.0}
copied '/tmp/576576.file' -> 'exp/hebr/tav/deu.1/bad-trunc-wds-summary.tex'
removed '/tmp/576576.file'
... creating word files dat/hebr/tav/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
38077 dat/hebr/tav/tot.1/trunc.tlw
removed 'dat/hebr/tav/tot.1/raw.tlw'
removed 'dat/hebr/tav/tot.1/gud.tlw'
removed 'dat/hebr/tav/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/hebr/tav/tot.1/raw.wdf
sample:
bĪ°rëĄsđïyą bĪâr⥠Ą°ęlöhïym Ąëą häsĪđâmäyïm w°Ąëą hâĄâręþ =
w°hâĄâręþ hây°ąâh ąöhwĪ wâböhwĪ w°įösđęk° ŋälpĪ°nëy ą°hwöm w°rwĪįä
Ą°ęlöhïym m°räįępęą ŋälpĪ°nëy hämĪâyïm =
wäyĪöĄmęr Ą°ęlöhïym y°hïy Ąwör wäy°hïyĄwör =
wäyĪär°Ą Ą°ęlöhïym ĄęąhâĄwör kĪïytwöb wäyĪäb°dĪël Ą°ęlöhïym bĪëyn hâĄwör
wĪbëyn häįösđęk° =
wäyĪïq°r⥠Ą°ęlöhïym lâĄwör ywöm w°läįösđęk° qâr⥠lây°lâh wäy°hïyŋęręb
wäy°hïyböqęr ywöm Ąęįâd =
wäyĪöĄmęr Ą°ęlöhïym y°hïy râqïyŋä bĪ°ąwök° hämĪâyïm wïyhïy mäb°dĪïyl
bĪëyn mäyïm lâmâyïm =
wäyĪäŋäsē Ą°ęlöhïym Ąęąhârâqïyŋä wäyĪäb°dĪël bĪëyn hämĪäyïm Ą°äsđęr
mïąĪäįäą lârâqïyŋä wĪbëyn hämĪäyïm Ą°äsđęr mëŋäl lârâqïyŋä wäy°hïykën =
wäyĪïq°r⥠Ą°ęlöhïym lârâqïyŋä sđâmâyïm wäy°hïyŋęręb wäy°hïyböqęr ywöm
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
kĪïy bwö bĪâįär y°hwâh Ą°ęlöhęykâmïkĪâlsđ°bâtęykâ läŋ°ämöd l°sđârëą
bĪ°sđëmy°hwâh hwĪĄ wĪbânâyw kĪâlhäyĪâmïym
removed 'dat/hebr/tav/tot.1/raw.wfr'
creating the word frequency file dat/hebr/tav/tot.1/raw.wfr
the 10 most common words in dat/hebr/tav/tot.1/raw.tlw:
3050 0.08010 =
809 0.02125 y°hwâh
591 0.01552 Ą°äsđęr
347 0.00911 wäyĪöĄmęr
266 0.00699 kĪïy
216 0.00567 löĄ
195 0.00512 mösđęh
168 0.00441 yïsē°râĄël
152 0.00399 hwĪĄ
151 0.00397 häkĪöhën
removed 'dat/hebr/tav/tot.1/raw-trunc-wds-summary.tex'
removed 'exp/hebr/tav/tot.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/hebr/tav/tot.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:17 by tex-make-sample-summary.sh
% Token and word counts for hebr/tav/tot.1/raw.wfr
%
\def\hebrtavtrunctotPBrawTks{38077}
\def\hebrtavtrunctotPBrawTksPct{100.0}
\def\hebrtavtrunctotPBrawWds{12488}
\def\hebrtavtrunctotPBrawWdsPct{32.8}
copied '/tmp/576630.file' -> 'exp/hebr/tav/tot.1/raw-trunc-wds-summary.tex'
removed '/tmp/576630.file'
creating running text file dat/hebr/tav/tot.1/gud.wdf
sample:
bĪ°rëĄsđïyą bĪâr⥠Ą°ęlöhïym Ąëą häsĪđâmäyïm w°Ąëą hâĄâręþ w°hâĄâręþ
hây°ąâh ąöhwĪ wâböhwĪ w°įösđęk° ŋälpĪ°nëy ą°hwöm w°rwĪįä Ą°ęlöhïym
m°räįępęą ŋälpĪ°nëy hämĪâyïm wäyĪöĄmęr Ą°ęlöhïym y°hïy Ąwör wäy°hïyĄwör
wäyĪär°Ą Ą°ęlöhïym ĄęąhâĄwör kĪïytwöb wäyĪäb°dĪël Ą°ęlöhïym bĪëyn hâĄwör
wĪbëyn häįösđęk° wäyĪïq°r⥠Ą°ęlöhïym lâĄwör ywöm w°läįösđęk° qârâĄ
lây°lâh wäy°hïyŋęręb wäy°hïyböqęr ywöm Ąęįâd wäyĪöĄmęr Ą°ęlöhïym y°hïy
râqïyŋä bĪ°ąwök° hämĪâyïm wïyhïy mäb°dĪïyl bĪëyn mäyïm lâmâyïm wäyĪäŋäsē
Ą°ęlöhïym Ąęąhârâqïyŋä wäyĪäb°dĪël bĪëyn hämĪäyïm Ą°äsđęr mïąĪäįäą
lârâqïyŋä wĪbëyn hämĪäyïm Ą°äsđęr mëŋäl lârâqïyŋä wäy°hïykën wäyĪïq°râĄ
Ą°ęlöhïym lârâqïyŋä sđâmâyïm wäy°hïyŋęręb wäy°hïyböqęr ywöm sđënïy
wäyĪöĄmęr Ą°ęlöhïym yïqĪâwwĪ hämĪäyïm mïąĪäįäą häsĪđâmäyïm Ąęlmâqwöm
Ąęįâd w°ąërâĄęh häyĪäbĪâsđâh wäy°hïykën wäyĪïq°r⥠Ą°ęlöhïym
läyĪäbĪâsđâh Ąęręþ wĪl°mïq°wëh hämĪäyïm qâr⥠yämĪïym wäyĪär°Ą Ą°ęlöhïym
kĪïytwöb wäyĪöĄmęr Ą°ęlöhïym ąĪäd°sđëĄ hâĄâręþ dĪęsđęĄ ŋësēęb mäz°rïyŋä
zęräŋ ŋëþ pĪ°rïy ŋösēęh pĪ°rïy l°mïynwö Ą°äsđęr zär°ŋwöbwö ŋälhâĄâręþ
wäy°hïykën wäąĪwöþëĄ hâĄâręþ dĪęsđęĄ ŋësēęb mäz°rïyŋä zęräŋ l°mïynëhwĪ
w°ŋëþ ŋösēęhpĪ°rïy Ą°äsđęr zär°ŋwöbwö l°mïynëhwĪ wäyĪär°Ą Ą°ęlöhïym
kĪïytwöb wäy°hïyŋęręb wäy°hïyböqęr ywöm sđ°lïysđïy wäyĪöĄmęr Ą°ęlöhïym
y°hïy m°Ąöröą bĪïr°qïyŋä häsĪđâmäyïm l°häb°dĪïyl bĪëyn häyĪwöm wĪbëyn
hälĪây°lâh w°hâywĪ l°Ąöąöą wĪl°mwöŋ°ädïym wĪl°yâmïym w°sđânïym w°hâywĪ
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
w°rëĄsđïyą gĪëz þöĄn°kâąĪïąĪęnlwö kĪïy bwö bĪâįär y°hwâh
Ą°ęlöhęykâmïkĪâlsđ°bâtęykâ läŋ°ämöd l°sđârëą bĪ°sđëmy°hwâh hwĪĄ wĪbânâyw
kĪâlhäyĪâmïym
removed 'dat/hebr/tav/tot.1/gud.wfr'
creating the word frequency file dat/hebr/tav/tot.1/gud.wfr
the 10 most common words in dat/hebr/tav/tot.1/gud.tlw:
809 0.02310 y°hwâh
591 0.01687 Ą°äsđęr
347 0.00991 wäyĪöĄmęr
266 0.00759 kĪïy
216 0.00617 löĄ
195 0.00557 mösđęh
168 0.00480 yïsē°râĄël
152 0.00434 hwĪĄ
151 0.00431 häkĪöhën
150 0.00428 Ą°ęlöhïym
removed 'dat/hebr/tav/tot.1/gud-trunc-wds-summary.tex'
removed 'exp/hebr/tav/tot.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/hebr/tav/tot.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:18 by tex-make-sample-summary.sh
% Token and word counts for hebr/tav/tot.1/gud.wfr
%
\def\hebrtavtrunctotPBgudTks{35027}
\def\hebrtavtrunctotPBgudTksPct{92.0}
\def\hebrtavtrunctotPBgudWds{12487}
\def\hebrtavtrunctotPBgudWdsPct{32.8}
copied '/tmp/576674.file' -> 'exp/hebr/tav/tot.1/gud-trunc-wds-summary.tex'
removed '/tmp/576674.file'
creating running text file dat/hebr/tav/tot.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/hebr/tav/tot.1/bad.wfr'
creating the word frequency file dat/hebr/tav/tot.1/bad.wfr
the 10 most common words in dat/hebr/tav/tot.1/bad.tlw:
3050 1.00000 =
removed 'dat/hebr/tav/tot.1/bad-trunc-wds-summary.tex'
removed 'exp/hebr/tav/tot.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/hebr/tav/tot.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:18 by tex-make-sample-summary.sh
% Token and word counts for hebr/tav/tot.1/bad.wfr
%
\def\hebrtavtrunctotPBbadTks{3050}
\def\hebrtavtrunctotPBbadTksPct{8.0}
\def\hebrtavtrunctotPBbadWds{1}
\def\hebrtavtrunctotPBbadWdsPct{0.0}
copied '/tmp/576718.file' -> 'exp/hebr/tav/tot.1/bad-trunc-wds-summary.tex'
removed '/tmp/576718.file'
lines words bytes file
------- ------- --------- ------------
7213 21626 193208 dat/hebr/tav/gen.1/raw.wfr
5712 17127 153676 dat/hebr/tav/exo.1/raw.wfr
5307 15916 143970 dat/hebr/tav/num.1/raw.wfr
3861 11578 105365 dat/hebr/tav/lev.1/raw.wfr
5456 16359 147102 dat/hebr/tav/deu.1/raw.wfr
12488 37450 340883 dat/hebr/tav/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
7212 21623 193190 dat/hebr/tav/gen.1/gud.wfr
5711 17124 153658 dat/hebr/tav/exo.1/gud.wfr
5306 15913 143952 dat/hebr/tav/num.1/gud.wfr
3860 11575 105347 dat/hebr/tav/lev.1/gud.wfr
5455 16356 147084 dat/hebr/tav/deu.1/gud.wfr
12487 37447 340865 dat/hebr/tav/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
1 3 18 dat/hebr/tav/gen.1/bad.wfr
1 3 18 dat/hebr/tav/exo.1/bad.wfr
1 3 18 dat/hebr/tav/num.1/bad.wfr
1 3 18 dat/hebr/tav/lev.1/bad.wfr
1 3 18 dat/hebr/tav/deu.1/bad.wfr
1 3 18 dat/hebr/tav/tot.1/bad.wfr
gen.1 raw = 18744 gud = 17211 bad = 1533
exo.1 raw = 15079 gud = 13870 bad = 1209
num.1 raw = 14862 gud = 13573 bad = 1289
lev.1 raw = 10509 gud = 9650 bad = 859
deu.1 raw = 12962 gud = 12007 bad = 955
tot.1 raw = 38077 gud = 35027 bad = 3050
=== creating the derived word files dat/hebr/tad/*/{raw,gud,bad}.{tlw,wdf,wfr} (trunc) ===
... creating word files dat/hebr/tad/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
38112 dat/hebr/tad/tot.1/trunc.tlw
removed 'dat/hebr/tad/tot.1/raw.tlw'
removed 'dat/hebr/tad/tot.1/gud.tlw'
removed 'dat/hebr/tad/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/hebr/tad/tot.1/raw.wdf
sample:
bĪrĄsđyą bĪrĄ Ąlhym Ąą hsĪđmym wĄą hĄrþ =
whĄrþ hyąh ąhwĪ wbhwĪ wįsđk ŋlpĪny ąhwm wrwĪį Ąlhym mrįpą ŋlpĪny hmĪym =
wyĪĄmr Ąlhym yhy Ąwr wyhyĄwr =
wyĪrĄ Ąlhym ĄąhĄwr kĪytwb wyĪbdĪl Ąlhym bĪyn hĄwr wĪbyn hįsđk =
wyĪqrĄ Ąlhym lĄwr ywm wlįsđk qrĄ lylh wyhyŋrb wyhybqr ywm Ąįd =
wyĪĄmr Ąlhym yhy rqyŋ bĪąwk hmĪym wyhy mbdĪyl bĪyn mym lmym =
wyĪŋsē Ąlhym Ąąhrqyŋ wyĪbdĪl bĪyn hmĪym Ąsđr mąĪįą lrqyŋ wĪbyn hmĪym
Ąsđr mŋl lrqyŋ wyhykn =
wyĪqrĄ Ąlhym lrqyŋ sđmym wyhyŋrb wyhybqr ywm sđny =
wyĪĄmr Ąlhym yqĪwwĪ hmĪym mąĪįą hsĪđmym Ąlmqwm Ąįd wąrĄh hyĪbĪsđh wyhykn
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
wĄmbĪŋynyw ŋmd hnĪąq wsēŋr sđįr þmįbĪw
removed 'dat/hebr/tad/tot.1/raw.wfr'
creating the word frequency file dat/hebr/tad/tot.1/raw.wfr
the 10 most common words in dat/hebr/tad/tot.1/raw.tlw:
3085 0.08095 =
503 0.01320 yhwh
497 0.01304 wyĪĄmr
487 0.01278 Ąsđr
262 0.00687 kĪy
184 0.00483 Ąlhym
181 0.00475 lĄ
181 0.00475 msđh
155 0.00407 mþrym
143 0.00375 ysērĄl
removed 'dat/hebr/tad/tot.1/raw-trunc-wds-summary.tex'
removed 'exp/hebr/tad/tot.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/hebr/tad/tot.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:18 by tex-make-sample-summary.sh
% Token and word counts for hebr/tad/tot.1/raw.wfr
%
\def\hebrtadtrunctotPBrawTks{38112}
\def\hebrtadtrunctotPBrawTksPct{100.0}
\def\hebrtadtrunctotPBrawWds{11857}
\def\hebrtadtrunctotPBrawWdsPct{31.1}
copied '/tmp/576888.file' -> 'exp/hebr/tad/tot.1/raw-trunc-wds-summary.tex'
removed '/tmp/576888.file'
creating running text file dat/hebr/tad/tot.1/gud.wdf
sample:
bĪrĄsđyą bĪrĄ Ąlhym Ąą hsĪđmym wĄą hĄrþ whĄrþ hyąh ąhwĪ wbhwĪ wįsđk
ŋlpĪny ąhwm wrwĪį Ąlhym mrįpą ŋlpĪny hmĪym wyĪĄmr Ąlhym yhy Ąwr wyhyĄwr
wyĪrĄ Ąlhym ĄąhĄwr kĪytwb wyĪbdĪl Ąlhym bĪyn hĄwr wĪbyn hįsđk wyĪqrĄ
Ąlhym lĄwr ywm wlįsđk qrĄ lylh wyhyŋrb wyhybqr ywm Ąįd wyĪĄmr Ąlhym yhy
rqyŋ bĪąwk hmĪym wyhy mbdĪyl bĪyn mym lmym wyĪŋsē Ąlhym Ąąhrqyŋ wyĪbdĪl
bĪyn hmĪym Ąsđr mąĪįą lrqyŋ wĪbyn hmĪym Ąsđr mŋl lrqyŋ wyhykn wyĪqrĄ
Ąlhym lrqyŋ sđmym wyhyŋrb wyhybqr ywm sđny wyĪĄmr Ąlhym yqĪwwĪ hmĪym
mąĪįą hsĪđmym Ąlmqwm Ąįd wąrĄh hyĪbĪsđh wyhykn wyĪqrĄ Ąlhym lyĪbĪsđh Ąrþ
wĪlmqwh hmĪym qrĄ ymĪym wyĪrĄ Ąlhym kĪytwb wyĪĄmr Ąlhym ąĪdsđĄ hĄrþ
dĪsđĄ ŋsēb mzryŋ zrŋ ŋþ pĪry ŋsēh pĪry lmynw Ąsđr zrŋwbw ŋlhĄrþ wyhykn
wąĪwþĄ hĄrþ dĪsđĄ ŋsēb mzryŋ zrŋ lmynhwĪ wŋþ ŋsēhpĪry Ąsđr zrŋwbw
lmynhwĪ wyĪrĄ Ąlhym kĪytwb wyhyŋrb wyhybqr ywm sđlysđy wyĪĄmr Ąlhym yhy
mĄrą bĪrqyŋ hsĪđmym lhbdĪyl bĪyn hyĪwm wĪbyn hlĪylh whywĪ lĄąą wĪlmwŋdym
wĪlymym wsđnym whywĪ lmĄwrą bĪrqyŋ hsĪđmym lhĄyr ŋlhĄrþ wyhykn wyĪŋsē
Ąlhym Ąąsđny hmĪĄrą hgĪdlym ĄąhmĪĄwr hgĪdl lmmsđlą hyĪwm wĄąhmĪĄwr hqĪtn
lmmsđlą hlĪylh wĄą hkĪwkbym wyĪąĪn Ąąm Ąlhym bĪrqyŋ hsĪđmym lhĄyr ŋlhĄrþ
wlmsđl bĪyĪwm wĪblĪylh wĪlhbdĪyl bĪyn hĄwr wĪbyn hįsđk wyĪrĄ Ąlhym
kĪytwb wyhyŋrb wyhybqr ywm rbyŋy wyĪĄmr ĄlhymysđrþwĪ hmĪym sđrþ npsđ
įyĪh wŋwp yŋwpp ŋlhĄrþ ŋlpĪny rqyŋ hsĪđmym wyĪbrĄ Ąlhym ĄąhąĪnĪynm
hgĪdlym wĄą kĪlnpsđ hįyĪh hrmsēą Ąsđr sđrþwĪ hmĪym lmynhm wĄą kĪlŋwp
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
ĄynnĪwĪ ŋmq mnhŋwrwthr Ąąw hkĪhn wkbĪs bĪgdyw wthr wĄmpĪsēh ypsēh hnĪąq
bĪŋwr Ąįry thrąw wrĄhwĪ hkĪhn whnĪh pĪsēh hnĪąq bĪŋwrlĄybqĪr hkĪhn
lsĪēŋr hþĪhb tmĄ hwĪĄ wĄmbĪŋynyw ŋmd hnĪąq wsēŋr sđįr þmįbĪw
removed 'dat/hebr/tad/tot.1/gud.wfr'
creating the word frequency file dat/hebr/tad/tot.1/gud.wfr
the 10 most common words in dat/hebr/tad/tot.1/gud.tlw:
503 0.01436 yhwh
497 0.01419 wyĪĄmr
487 0.01390 Ąsđr
262 0.00748 kĪy
184 0.00525 Ąlhym
181 0.00517 lĄ
181 0.00517 msđh
155 0.00443 mþrym
143 0.00408 ysērĄl
136 0.00388 hwĪĄ
removed 'dat/hebr/tad/tot.1/gud-trunc-wds-summary.tex'
removed 'exp/hebr/tad/tot.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/hebr/tad/tot.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:18 by tex-make-sample-summary.sh
% Token and word counts for hebr/tad/tot.1/gud.wfr
%
\def\hebrtadtrunctotPBgudTks{35027}
\def\hebrtadtrunctotPBgudTksPct{91.9}
\def\hebrtadtrunctotPBgudWds{11856}
\def\hebrtadtrunctotPBgudWdsPct{31.1}
copied '/tmp/576932.file' -> 'exp/hebr/tad/tot.1/gud-trunc-wds-summary.tex'
removed '/tmp/576932.file'
creating running text file dat/hebr/tad/tot.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/hebr/tad/tot.1/bad.wfr'
creating the word frequency file dat/hebr/tad/tot.1/bad.wfr
the 10 most common words in dat/hebr/tad/tot.1/bad.tlw:
3085 1.00000 =
removed 'dat/hebr/tad/tot.1/bad-trunc-wds-summary.tex'
removed 'exp/hebr/tad/tot.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/hebr/tad/tot.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:18 by tex-make-sample-summary.sh
% Token and word counts for hebr/tad/tot.1/bad.wfr
%
\def\hebrtadtrunctotPBbadTks{3085}
\def\hebrtadtrunctotPBbadTksPct{8.1}
\def\hebrtadtrunctotPBbadWds{1}
\def\hebrtadtrunctotPBbadWdsPct{0.0}
copied '/tmp/576976.file' -> 'exp/hebr/tad/tot.1/bad-trunc-wds-summary.tex'
removed '/tmp/576976.file'
lines words bytes file
------- ------- --------- ------------
11857 35558 279416 dat/hebr/tad/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
11856 35555 279398 dat/hebr/tad/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
1 3 18 dat/hebr/tad/tot.1/bad.wfr
tot.1 raw = 38112 gud = 35027 bad = 3085
=== creating the derived word files dat/geez/gok/*/{raw,gud,bad}.{tlw,wdf,wfr} (trunc) ===
... creating word files dat/geez/gok/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
34788 dat/geez/gok/tot.1/trunc.tlw
removed 'dat/geez/gok/tot.1/raw.tlw'
removed 'dat/geez/gok/tot.1/gud.tlw'
removed 'dat/geez/gok/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/geez/gok/tot.1/raw.wdf
sample:
be'akWetEtu le'Igzi'AbHEr 'ab 'a`hazE kWulu webeweldu 'iyesus krstos
zebotu kWulu kone weze'InbelEhuse 'albo zekone webemenfes qdus
PeraqliTos zeywe`S'I 'Im'ab weyne`s'I 'Imweld `1 'amlak 'ab weweld
wemenfes qdus ne'amn wengeni le`slus =
fkarE wezEna ze`3`100`10 we`8 rtu`ane haymanot be'Inte kbr we`Ibey
wetedla zekeme wehebe 'Igzi'AbHEr ledeqiqa 'adam wefedfadese zebe'Inte
`Ibeya wekbra leSyon tabote Hgu le'Igzi'AbHEr 'Inte gebariha wekEnyaha
lelihu bewste SrHe meqdesu 'Imqdme kWulu fTret mela'Ikt weseb'I 'Isme
be`hbret webe`smret webe`Irina gebrwa 'ab weweld wemenfes qdus leSyon
semayawit lema`hdare sbHetihomu we'Imz ybE 'ab leweld welemenfes qdus
ngber seb'a be'ar'ayane webe'amsaline we`hebru we`semru bez mkr weybE
weld 'ane 'Ilebs `sgahu le'adam weybE menfes qdus 'ane 'a`hedr wste lbe
nebiyat weSadqan wezati `hbret wekidan tegebret bewste Syon ma`hdere
sbHetihomu wedawitni ybE tezeker ma`hbereke ze'aqdemke feTire
lemed`henite betre rstke bedebre Syon ze`hederke wstEta =
wegebro le'adam bezezi'ahu 'ar'aya we'amsal keme yn`sto lesayTan be'Inte
t`Ibitu msle serawitu weyaqmo le'adam tekle zi'ahu msle `heran deqiqu
lesbHetihu 'Isme `hluq wemtur mkre 'Igzi'AbHEr 'Inte ybE 'Ikewn seb'a
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
we'Imd`hrEhu 'agb'a lomu ykWuno 'amlak yagba Syon baHr seged Hzbe 'ar`ad
qdme seged Zan seged wdm 'ar`ad `amde Syon =
removed 'dat/geez/gok/tot.1/raw.wfr'
creating the word frequency file dat/geez/gok/tot.1/raw.wfr
the 10 most common words in dat/geez/gok/tot.1/raw.tlw:
571 0.01641 keme
481 0.01383 'Igzi'AbHEr
426 0.01225 'Isme
357 0.01026 wste
226 0.00650 =
187 0.00538 'Inze
179 0.00515 `hebe
174 0.00500 be'Inte
172 0.00494 msle
166 0.00477 ngu`s
removed 'dat/geez/gok/tot.1/raw-trunc-wds-summary.tex'
removed 'exp/geez/gok/tot.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/geez/gok/tot.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:18 by tex-make-sample-summary.sh
% Token and word counts for geez/gok/tot.1/raw.wfr
%
\def\geezgoktrunctotPBrawTks{34788}
\def\geezgoktrunctotPBrawTksPct{100.0}
\def\geezgoktrunctotPBrawWds{12356}
\def\geezgoktrunctotPBrawWdsPct{35.5}
copied '/tmp/577071.file' -> 'exp/geez/gok/tot.1/raw-trunc-wds-summary.tex'
removed '/tmp/577071.file'
creating running text file dat/geez/gok/tot.1/gud.wdf
sample:
be'akWetEtu le'Igzi'AbHEr 'ab 'a`hazE kWulu webeweldu 'iyesus krstos
zebotu kWulu kone weze'InbelEhuse 'albo zekone webemenfes qdus
PeraqliTos zeywe`S'I 'Im'ab weyne`s'I 'Imweld 'amlak 'ab weweld wemenfes
qdus ne'amn wengeni le`slus fkarE wezEna rtu`ane haymanot be'Inte kbr
we`Ibey wetedla zekeme wehebe 'Igzi'AbHEr ledeqiqa 'adam wefedfadese
zebe'Inte `Ibeya wekbra leSyon tabote Hgu le'Igzi'AbHEr 'Inte gebariha
wekEnyaha lelihu bewste SrHe meqdesu 'Imqdme kWulu fTret mela'Ikt
weseb'I 'Isme be`hbret webe`smret webe`Irina gebrwa 'ab weweld wemenfes
qdus leSyon semayawit lema`hdare sbHetihomu we'Imz ybE 'ab leweld
welemenfes qdus ngber seb'a be'ar'ayane webe'amsaline we`hebru we`semru
bez mkr weybE weld 'ane 'Ilebs `sgahu le'adam weybE menfes qdus 'ane
'a`hedr wste lbe nebiyat weSadqan wezati `hbret wekidan tegebret bewste
Syon ma`hdere sbHetihomu wedawitni ybE tezeker ma`hbereke ze'aqdemke
feTire lemed`henite betre rstke bedebre Syon ze`hederke wstEta wegebro
le'adam bezezi'ahu 'ar'aya we'amsal keme yn`sto lesayTan be'Inte t`Ibitu
msle serawitu weyaqmo le'adam tekle zi'ahu msle `heran deqiqu lesbHetihu
'Isme `hluq wemtur mkre 'Igzi'AbHEr 'Inte ybE 'Ikewn seb'a we'Aster'i
lekWulu zefeTerku be`sga 'Itgeses webede`hari mewa`Il be`smretu tewelde
be`sga 'Imdagmawit Syon dagmawi 'adam zw'Itu med`henine krstos zati
y'Iti mkHne wehaymanotne tesfane weHywetne Syon samayawit hebukE ngba'I
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
'ikonu 'Imnegede dawit weHzbe 'Isra'El bekeme ybE 'Igzi'abHEr 'ane
'aqen'omu beze'ikone Hzb we'Imd`hrEhu 'agb'a lomu ykWuno 'amlak yagba
Syon baHr seged Hzbe 'ar`ad qdme seged Zan seged wdm 'ar`ad `amde Syon
removed 'dat/geez/gok/tot.1/gud.wfr'
creating the word frequency file dat/geez/gok/tot.1/gud.wfr
the 10 most common words in dat/geez/gok/tot.1/gud.tlw:
571 0.01665 keme
481 0.01403 'Igzi'AbHEr
426 0.01242 'Isme
357 0.01041 wste
187 0.00545 'Inze
179 0.00522 `hebe
174 0.00507 be'Inte
172 0.00502 msle
166 0.00484 ngu`s
163 0.00475 'Iske
removed 'dat/geez/gok/tot.1/gud-trunc-wds-summary.tex'
removed 'exp/geez/gok/tot.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/geez/gok/tot.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:18 by tex-make-sample-summary.sh
% Token and word counts for geez/gok/tot.1/gud.wfr
%
\def\geezgoktrunctotPBgudTks{34291}
\def\geezgoktrunctotPBgudTksPct{98.6}
\def\geezgoktrunctotPBgudWds{12272}
\def\geezgoktrunctotPBgudWdsPct{35.3}
copied '/tmp/577115.file' -> 'exp/geez/gok/tot.1/gud-trunc-wds-summary.tex'
removed '/tmp/577115.file'
creating running text file dat/geez/gok/tot.1/bad.wdf
sample:
`1 =
ze`3`100`10 we`8 =
=
=
`10 we`5 =
=
be`9 =
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/geez/gok/tot.1/bad.wfr'
creating the word frequency file dat/geez/gok/tot.1/bad.wfr
the 10 most common words in dat/geez/gok/tot.1/bad.tlw:
226 0.45473 =
26 0.05231 `1
22 0.04427 `10
21 0.04225 `3
16 0.03219 we`2
9 0.01811 `2
8 0.01610 `4
7 0.01408 `7
7 0.01408 `70
6 0.01207 `6
removed 'dat/geez/gok/tot.1/bad-trunc-wds-summary.tex'
removed 'exp/geez/gok/tot.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/geez/gok/tot.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:19 by tex-make-sample-summary.sh
% Token and word counts for geez/gok/tot.1/bad.wfr
%
\def\geezgoktrunctotPBbadTks{497}
\def\geezgoktrunctotPBbadTksPct{1.4}
\def\geezgoktrunctotPBbadWds{84}
\def\geezgoktrunctotPBbadWdsPct{0.2}
copied '/tmp/577159.file' -> 'exp/geez/gok/tot.1/bad-trunc-wds-summary.tex'
removed '/tmp/577159.file'
lines words bytes file
------- ------- --------- ------------
12356 37068 306126 dat/geez/gok/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
12272 36816 304244 dat/geez/gok/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
84 252 1882 dat/geez/gok/tot.1/bad.wfr
tot.1 raw = 34788 gud = 34291 bad = 497
=== creating the derived word files dat/geez/eno/*/{raw,gud,bad}.{tlw,wdf,wfr} (trunc) ===
... creating word files dat/geez/eno/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
18215 dat/geez/eno/tot.1/trunc.tlw
removed 'dat/geez/eno/tot.1/raw.tlw'
removed 'dat/geez/eno/tot.1/gud.tlw'
removed 'dat/geez/eno/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/geez/eno/tot.1/raw.wdf
sample:
qale bereket zehEnok zekeme bareke `hruyane weSadqane 'Ile helewu ykunu
be`Ilete mndabE le'aseslo kWulu 'Ikuyan weresi`an we'aw`s'a weybE hEnok
b'Isi Sadq ze'Im`hebe Igzi'abHEr 'Inze 'a`Iyntihu k`sutat weyrE'i ra'Iye
qduse zebesemayat ze'ar'ayuni mela'Ikt wesema`Iku 'Im`hebEhomu kWulo
we'a'Imerku 'ane ze'IrE'i we'ako lez twld 'ala lezeymeS'I twld r`huqan
be'Inte `hruyan 'IbE we'aw`sa'Iku be'Inti'ahomu msle zeywe`S'I qdus
we`ebiy 'Ima`hderu we'amlake `alem we'Imhye ykeyd dibe sina debr
weyaster'i bet`Iyntu weyaster'i beSn`e `heylu 'Imsemay weyferh kWulu
weyadleqelqu tguhan weyne`s'omu frhet were`ad `ebiy 'Iske 'aSnafe mdr
weydeneg`Su 'adbar newa`han weytEHetu 'awgr newa`hat weytmesewu keme
me`are gra 'Imlahb wet`seTem mdr wekWulu zewste mdr ytHegWel weykewn ftH
la`Ile kWulu wela`Ile Sadqan kWulomu leSadqanse selame ygebr lomu
weye`eqbomu le`hruyan weykewn `sahl la`IlEhomu weykewnu kWulomu ze'amlak
wey`sErHu weytbareku weyherh lomu brhane 'amlak wenahu meS'a bet'Ilfet
qdusan keme ygber ftHe la`IlEhomu weyaHegWulomu leresi`an weytwaqes
kWulo ze`sga be'Inte kWulu zegebru wereseyu la`IlEhu `haT'an weresi`an
Teyequ kWulo zewste semay gbre 'Ifo 'iymeyTu fnawihomu brhanat zewste
semay keme kWulu y`serq weye`erb `sru`I kWulu bebezemenu we'iyt`edewu
'Imt'Izazomu r'Iywa lemdr welebwu be'Inte mgbar zeytgeber la`IlEha
'Imqedami 'Iske tefSamEtu keme iytmeyeT kWulu gbru le'amlak 'Inze
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
le'Ile teweldu beSlmet ytwedeyu beSlmet Inze ytwe`hew`hu Sadqan weySerHu
weyrE'Iywomu `haT'An 'Inze yberhu weyeHewru Imuntuhi be`hebe teSHfe lomu
mewa`Il we'azman
removed 'dat/geez/eno/tot.1/raw.wfr'
creating the word frequency file dat/geez/eno/tot.1/raw.wfr
the 10 most common words in dat/geez/eno/tot.1/raw.tlw:
273 0.01499 keme
176 0.00966 mdr
170 0.00933 'Ile
147 0.00807 'Isme
139 0.00763 dibe
114 0.00626 w'Itu
113 0.00620 semay
113 0.00620 wste
107 0.00587 menafst
106 0.00582 'Iske
removed 'dat/geez/eno/tot.1/raw-trunc-wds-summary.tex'
removed 'exp/geez/eno/tot.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/geez/eno/tot.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:19 by tex-make-sample-summary.sh
% Token and word counts for geez/eno/tot.1/raw.wfr
%
\def\geezenotrunctotPBrawTks{18215}
\def\geezenotrunctotPBrawTksPct{100.0}
\def\geezenotrunctotPBrawWds{6356}
\def\geezenotrunctotPBrawWdsPct{34.9}
copied '/tmp/577254.file' -> 'exp/geez/eno/tot.1/raw-trunc-wds-summary.tex'
removed '/tmp/577254.file'
creating running text file dat/geez/eno/tot.1/gud.wdf
sample:
qale bereket zehEnok zekeme bareke `hruyane weSadqane 'Ile helewu ykunu
be`Ilete mndabE le'aseslo kWulu 'Ikuyan weresi`an we'aw`s'a weybE hEnok
b'Isi Sadq ze'Im`hebe Igzi'abHEr 'Inze 'a`Iyntihu k`sutat weyrE'i ra'Iye
qduse zebesemayat ze'ar'ayuni mela'Ikt wesema`Iku 'Im`hebEhomu kWulo
we'a'Imerku 'ane ze'IrE'i we'ako lez twld 'ala lezeymeS'I twld r`huqan
be'Inte `hruyan 'IbE we'aw`sa'Iku be'Inti'ahomu msle zeywe`S'I qdus
we`ebiy 'Ima`hderu we'amlake `alem we'Imhye ykeyd dibe sina debr
weyaster'i bet`Iyntu weyaster'i beSn`e `heylu 'Imsemay weyferh kWulu
weyadleqelqu tguhan weyne`s'omu frhet were`ad `ebiy 'Iske 'aSnafe mdr
weydeneg`Su 'adbar newa`han weytEHetu 'awgr newa`hat weytmesewu keme
me`are gra 'Imlahb wet`seTem mdr wekWulu zewste mdr ytHegWel weykewn ftH
la`Ile kWulu wela`Ile Sadqan kWulomu leSadqanse selame ygebr lomu
weye`eqbomu le`hruyan weykewn `sahl la`IlEhomu weykewnu kWulomu ze'amlak
wey`sErHu weytbareku weyherh lomu brhane 'amlak wenahu meS'a bet'Ilfet
qdusan keme ygber ftHe la`IlEhomu weyaHegWulomu leresi`an weytwaqes
kWulo ze`sga be'Inte kWulu zegebru wereseyu la`IlEhu `haT'an weresi`an
Teyequ kWulo zewste semay gbre 'Ifo 'iymeyTu fnawihomu brhanat zewste
semay keme kWulu y`serq weye`erb `sru`I kWulu bebezemenu we'iyt`edewu
'Imt'Izazomu r'Iywa lemdr welebwu be'Inte mgbar zeytgeber la`IlEha
'Imqedami 'Iske tefSamEtu keme iytmeyeT kWulu gbru le'amlak 'Inze
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
beSlmet ytwedeyu beSlmet Inze ytwe`hew`hu Sadqan weySerHu weyrE'Iywomu
`haT'An 'Inze yberhu weyeHewru Imuntuhi be`hebe teSHfe lomu mewa`Il
we'azman
removed 'dat/geez/eno/tot.1/gud.wfr'
creating the word frequency file dat/geez/eno/tot.1/gud.wfr
the 10 most common words in dat/geez/eno/tot.1/gud.tlw:
273 0.01539 keme
176 0.00992 mdr
170 0.00959 'Ile
147 0.00829 'Isme
139 0.00784 dibe
114 0.00643 w'Itu
113 0.00637 semay
113 0.00637 wste
107 0.00603 menafst
106 0.00598 'Iske
removed 'dat/geez/eno/tot.1/gud-trunc-wds-summary.tex'
removed 'exp/geez/eno/tot.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/geez/eno/tot.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:19 by tex-make-sample-summary.sh
% Token and word counts for geez/eno/tot.1/gud.wfr
%
\def\geezenotrunctotPBgudTks{17736}
\def\geezenotrunctotPBgudTksPct{97.4}
\def\geezenotrunctotPBgudWds{6274}
\def\geezenotrunctotPBgudWdsPct{34.4}
copied '/tmp/577298.file' -> 'exp/geez/eno/tot.1/gud-trunc-wds-summary.tex'
removed '/tmp/577298.file'
creating running text file dat/geez/eno/tot.1/bad.wdf
sample:
`10 we`4 `2 `3 `2`100 'urakibe*ramE'El le`2`100 bebe`30`100 `5`100 le`70
`10`100 `10 welele`1 `1 `4 `7 `3 we`3 we`1 we`1 `7 `1 `1 `1 `1 `1 `1 `7
`1 `1 we`4 `1 `1 `1 `3 `1 `7 `1 `1 `3 `1 dibe`1 we`3 `1 dibe`1 `1 `1 `1
`1 `7 `1 `1 lele`1 `3 bebe`1 be`2 `3 `3 `3 bebe`1 `3 we`1 webe`4 `4 `4
`4 `4 we`4 `1 `1 `1 `1 le`1 be`1 `1`1 `5`100 `1 `2 `1 we`1 `1 we`1`1
we`1 `2 `1 `1 `1 be`1 `1 be`1 `10 we`1 `10 we`2 `10 we`3 `10 we`4 `10
we`5 `10 we`6 `10 we`7 `10 we`8 `10 we`9 `20 `20 we`1 `100 `50 `10 `2 `2
`1 'Im`4 `1`1 `1`1 `1`1 `6 we`7 `1`1 `60 `30 `30 `10 `8 `30 `20 `10 we`1
`7 `30 we`1 `10 we`2 `60 `30 `30 `1 `10 we`1 `7 `30 `2 `10 `8 `30 we`1
`9 `9 `30 `30 `30 `10 `8 `30 `10 we`1 `7 `30 we`1 `10 we`2 `7 `30 `1 `1
`10 we`1 `7 `30 `10 `8 `30 we`1 `9 `9 `3`100 we`60 `60 `7 le`2 be`30 `30
`7 `1 'Im`10 we`4 `7 we`7 `7 we`7 `7 we`7 `10 we`5 be`1 `7`7 webebe`7`7
`1`1 webe`2 `2 `7 `5 `30 le`1 `5 `3`100 we`60 we`4 'Im`5 `30 `30
bebe`3`100 we`6 we`4 le`3 `10`100 we`90 we`2 wele`5 `10 we`8`100 we`20
le`8 `20 we`9`100 we`10 we`2 le`3 `10`100 we`8 we`2 wele`5 `50 dibe`8
we`2 le`5 `10 we`7`100 we`70 le`8 `20`100 we`8`100 we`30 we`2 le`8 `80
'Im`8 `80 `30 `4 `4 `1 we`1 we`1 we`1 bebe`3`100 we`8 we`4 `10 we`2 `10
we`2 we`1 `10 we`2 `3 we`3 we`3 we`3 we`3 we`3 we`3 we`3 be`4 `8 be`3
'Im`3 `4 `10 we`2 ze`4 `3 `1 `7 `7 `1 `2 `4 we`2 `2 we`5 `1 `4 `1 `2 `7
we`3 `3 `10 we`4 `10 we`3 `10 we`2 `10 we`1 `10 `9 `8 `7 `6 `5 webe`10
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
lele`1`1 lele`1`1 `1`1 `1`1 `1`1 `1 `1`1 `10 we`2 `3 `30 we`7 `20 we`3
`50 we`8 le`1 `1 `1 `10 we`2 `7 `1 `7 `70 `70 `1 be`1 `3 we`1 `1 be`2
be`2 `7 `7 `7 be`1 be`1 be`1 we`3 le`1 `10`1
removed 'dat/geez/eno/tot.1/bad.wfr'
creating the word frequency file dat/geez/eno/tot.1/bad.wfr
the 10 most common words in dat/geez/eno/tot.1/bad.tlw:
66 0.13779 `1
40 0.08351 `10
38 0.07933 we`1
26 0.05428 `7
24 0.05010 `30
22 0.04593 `4
21 0.04384 we`2
21 0.04384 we`3
20 0.04175 `3
13 0.02714 we`4
removed 'dat/geez/eno/tot.1/bad-trunc-wds-summary.tex'
removed 'exp/geez/eno/tot.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/geez/eno/tot.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:19 by tex-make-sample-summary.sh
% Token and word counts for geez/eno/tot.1/bad.wfr
%
\def\geezenotrunctotPBbadTks{479}
\def\geezenotrunctotPBbadTksPct{2.6}
\def\geezenotrunctotPBbadWds{82}
\def\geezenotrunctotPBbadWdsPct{0.5}
copied '/tmp/577342.file' -> 'exp/geez/eno/tot.1/bad-trunc-wds-summary.tex'
removed '/tmp/577342.file'
lines words bytes file
------- ------- --------- ------------
6356 19068 157086 dat/geez/eno/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
6274 18822 155279 dat/geez/eno/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
82 246 1807 dat/geez/eno/tot.1/bad.wfr
tot.1 raw = 18215 gud = 17736 bad = 479
=== creating the derived word files dat/engl/wow/*/{raw,gud,bad}.{tlw,wdf,wfr} (trunc) ===
... creating word files dat/engl/wow/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
35606 dat/engl/wow/tot.1/trunc.tlw
removed 'dat/engl/wow/tot.1/raw.tlw'
removed 'dat/engl/wow/tot.1/gud.tlw'
removed 'dat/engl/wow/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/engl/wow/tot.1/raw.wdf
sample:
no one would have believed in the last years of the nineteenth century
that this world was being watched keenly and closely by intelligences
greater than man's and yet as mortal as his own that as men busied
themselves about their various concerns they were scrutinised and
studied perhaps almost as narrowly as a man with a microscope might
scrutinise the transient creatures that swarm and multiply in a drop of
water with infinite complacency men went to and fro over this globe
about their little affairs serene in their assurance of their empire
over matter it is possible that the infusoria under the microscope do
the same no one gave a thought to the older worlds of space as sources
of human danger or thought of them only to dismiss the idea of life upon
them as impossible or improbable it is curious to recall some of the
mental habits of those departed days at most terrestrial men fancied
there might be other men upon mars perhaps inferior to themselves and
ready to welcome a missionary enterprise yet across the gulf of space
minds that are to our minds as ours are to those of the beasts that
perish intellects vast and cool and unsympathetic regarded this earth
with envious eyes and slowly and surely drew their plans against us and
early in the twentieth century came the great disillusionment =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
contrived to eat a meal on one of the seats forward =
there were already a couple of score of passengers aboard some of
removed 'dat/engl/wow/tot.1/raw.wfr'
creating the word frequency file dat/engl/wow/tot.1/raw.wfr
the 10 most common words in dat/engl/wow/tot.1/raw.tlw:
2907 0.08164 the
1469 0.04126 and
1345 0.03777 of
977 0.02744 a
667 0.01873 to
584 0.01640 in
566 0.01590 =
539 0.01514 i
516 0.01449 was
435 0.01222 that
removed 'dat/engl/wow/tot.1/raw-trunc-wds-summary.tex'
removed 'exp/engl/wow/tot.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/engl/wow/tot.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:19 by tex-make-sample-summary.sh
% Token and word counts for engl/wow/tot.1/raw.wfr
%
\def\englwowtrunctotPBrawTks{35606}
\def\englwowtrunctotPBrawTksPct{100.0}
\def\englwowtrunctotPBrawWds{4878}
\def\englwowtrunctotPBrawWdsPct{13.7}
copied '/tmp/577437.file' -> 'exp/engl/wow/tot.1/raw-trunc-wds-summary.tex'
removed '/tmp/577437.file'
creating running text file dat/engl/wow/tot.1/gud.wdf
sample:
no one would have believed in the last years of the nineteenth century
that this world was being watched keenly and closely by intelligences
greater than man's and yet as mortal as his own that as men busied
themselves about their various concerns they were scrutinised and
studied perhaps almost as narrowly as a man with a microscope might
scrutinise the transient creatures that swarm and multiply in a drop of
water with infinite complacency men went to and fro over this globe
about their little affairs serene in their assurance of their empire
over matter it is possible that the infusoria under the microscope do
the same no one gave a thought to the older worlds of space as sources
of human danger or thought of them only to dismiss the idea of life upon
them as impossible or improbable it is curious to recall some of the
mental habits of those departed days at most terrestrial men fancied
there might be other men upon mars perhaps inferior to themselves and
ready to welcome a missionary enterprise yet across the gulf of space
minds that are to our minds as ours are to those of the beasts that
perish intellects vast and cool and unsympathetic regarded this earth
with envious eyes and slowly and surely drew their plans against us and
early in the twentieth century came the great disillusionment the planet
mars i scarcely need remind the reader revolves about the sun at a mean
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
with his charges there was food aboard albeit at exorbitant prices and
the three of them contrived to eat a meal on one of the seats forward
there were already a couple of score of passengers aboard some of
removed 'dat/engl/wow/tot.1/gud.wfr'
creating the word frequency file dat/engl/wow/tot.1/gud.wfr
the 10 most common words in dat/engl/wow/tot.1/gud.tlw:
2907 0.08299 the
1469 0.04194 and
1345 0.03840 of
977 0.02789 a
667 0.01904 to
584 0.01667 in
539 0.01539 i
516 0.01473 was
435 0.01242 that
371 0.01059 it
removed 'dat/engl/wow/tot.1/gud-trunc-wds-summary.tex'
removed 'exp/engl/wow/tot.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/engl/wow/tot.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:19 by tex-make-sample-summary.sh
% Token and word counts for engl/wow/tot.1/gud.wfr
%
\def\englwowtrunctotPBgudTks{35027}
\def\englwowtrunctotPBgudTksPct{98.4}
\def\englwowtrunctotPBgudWds{4869}
\def\englwowtrunctotPBgudWdsPct{13.7}
copied '/tmp/577481.file' -> 'exp/engl/wow/tot.1/gud-trunc-wds-summary.tex'
removed '/tmp/577481.file'
creating running text file dat/engl/wow/tot.1/bad.wdf
sample:
=
140 000 000 =
=
35 000 000 =
=
=
=
1894 2 =
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/engl/wow/tot.1/bad.wfr'
creating the word frequency file dat/engl/wow/tot.1/bad.wfr
the 10 most common words in dat/engl/wow/tot.1/bad.tlw:
566 0.97755 =
6 0.01036 000
1 0.00173 10
1 0.00173 12
1 0.00173 140
1 0.00173 1894
1 0.00173 2
1 0.00173 35
1 0.00173 8th
removed 'dat/engl/wow/tot.1/bad-trunc-wds-summary.tex'
removed 'exp/engl/wow/tot.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/engl/wow/tot.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:19 by tex-make-sample-summary.sh
% Token and word counts for engl/wow/tot.1/bad.wfr
%
\def\englwowtrunctotPBbadTks{579}
\def\englwowtrunctotPBbadTksPct{1.6}
\def\englwowtrunctotPBbadWds{9}
\def\englwowtrunctotPBbadWdsPct{0.0}
copied '/tmp/577525.file' -> 'exp/engl/wow/tot.1/bad-trunc-wds-summary.tex'
removed '/tmp/577525.file'
lines words bytes file
------- ------- --------- ------------
4878 14634 116620 dat/engl/wow/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
4869 14607 116446 dat/engl/wow/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
9 27 174 dat/engl/wow/tot.1/bad.wfr
tot.1 raw = 35606 gud = 35027 bad = 579
=== creating the derived word files dat/engl/wnm/*/{raw,gud,bad}.{tlw,wdf,wfr} (trunc) ===
... creating word files dat/engl/wnm/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
831 dat/engl/wnm/tot.1/trunc.tlw
removed 'dat/engl/wnm/tot.1/raw.tlw'
removed 'dat/engl/wnm/tot.1/gud.tlw'
removed 'dat/engl/wnm/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
!! empty raw.tlw file '='
creating running text file dat/engl/wnm/tot.1/raw.wdf
sample:
mars mars mars mars mars tasmanians european martians martians
schiaparelli mars martians lick perrotin english august mars lavelle
java ogilvy ottershaw ogilvy ogilvy ogilvy mars ogilvy ottershaw
chertsey mars mars martians mars martians markham zodiac mars chertsey
isleworth winchester albin denning french ottershaw berkshire surrey
middlesex ogilvy horsell ottershaw woking weybridge ogilvy mars woking
horsell henderson london henderson henderson horsell henderson henderson
ogilvy henderson henderson london mars ottershaw henderson ogilvy
henderson's gregg england ogilvy henderson mars ogilvy mars maybury
london ogilvy's woking chobham woking chertsey ottershaw chobham
henderson ogilvy stent stent ogilvy hilton hilton london waterloo woking
stent's ogilvy woking stent martian gorgon chobham woking martians
woking chobham god woking woking chobham woking horsell martians ogilvy
stent henderson chertsey knaphill martians woking horsell martians
woking martians martians horsell maybury chobham woking ottershaw woking
horsell woking henderson martians stent stent ogilvy horsell martians
woking martians horsell maybury oriental mars mars ogilvy ogilvy
martians mars martian mars mars martians martian ogilvy's martians
mauritius friday friday woking stent london germany london henderson's
mars woking horsell chobham woking smith's mars londonwards horsell
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
stanmore stanmore george stanmore thames ostend blackwater shoeburyness
essex martian martian titan naze martians martians essex martian
martians martian martian's martian martian martian martian
removed 'dat/engl/wnm/tot.1/raw.wfr'
creating the word frequency file dat/engl/wnm/tot.1/raw.wfr
the 10 most common words in dat/engl/wnm/tot.1/raw.tlw:
89 0.10710 martians
48 0.05776 woking
37 0.04452 martian
36 0.04332 london
28 0.03369 mars
23 0.02768 horsell
22 0.02647 weybridge
20 0.02407 ogilvy
18 0.02166 chertsey
17 0.02046 maybury
removed 'dat/engl/wnm/tot.1/raw-trunc-wds-summary.tex'
removed 'exp/engl/wnm/tot.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/engl/wnm/tot.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:19 by tex-make-sample-summary.sh
% Token and word counts for engl/wnm/tot.1/raw.wfr
%
\def\englwnmtrunctotPBrawTks{831}
\def\englwnmtrunctotPBrawTksPct{100.0}
\def\englwnmtrunctotPBrawWds{194}
\def\englwnmtrunctotPBrawWdsPct{23.3}
copied '/tmp/577622.file' -> 'exp/engl/wnm/tot.1/raw-trunc-wds-summary.tex'
removed '/tmp/577622.file'
creating running text file dat/engl/wnm/tot.1/gud.wdf
sample:
mars mars mars mars mars tasmanians european martians martians
schiaparelli mars martians lick perrotin english august mars lavelle
java ogilvy ottershaw ogilvy ogilvy ogilvy mars ogilvy ottershaw
chertsey mars mars martians mars martians markham zodiac mars chertsey
isleworth winchester albin denning french ottershaw berkshire surrey
middlesex ogilvy horsell ottershaw woking weybridge ogilvy mars woking
horsell henderson london henderson henderson horsell henderson henderson
ogilvy henderson henderson london mars ottershaw henderson ogilvy
henderson's gregg england ogilvy henderson mars ogilvy mars maybury
london ogilvy's woking chobham woking chertsey ottershaw chobham
henderson ogilvy stent stent ogilvy hilton hilton london waterloo woking
stent's ogilvy woking stent martian gorgon chobham woking martians
woking chobham god woking woking chobham woking horsell martians ogilvy
stent henderson chertsey knaphill martians woking horsell martians
woking martians martians horsell maybury chobham woking ottershaw woking
horsell woking henderson martians stent stent ogilvy horsell martians
woking martians horsell maybury oriental mars mars ogilvy ogilvy
martians mars martian mars mars martians martian ogilvy's martians
mauritius friday friday woking stent london germany london henderson's
mars woking horsell chobham woking smith's mars londonwards horsell
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
stanmore stanmore george stanmore thames ostend blackwater shoeburyness
essex martian martian titan naze martians martians essex martian
martians martian martian's martian martian martian martian
removed 'dat/engl/wnm/tot.1/gud.wfr'
creating the word frequency file dat/engl/wnm/tot.1/gud.wfr
the 10 most common words in dat/engl/wnm/tot.1/gud.tlw:
89 0.10710 martians
48 0.05776 woking
37 0.04452 martian
36 0.04332 london
28 0.03369 mars
23 0.02768 horsell
22 0.02647 weybridge
20 0.02407 ogilvy
18 0.02166 chertsey
17 0.02046 maybury
removed 'dat/engl/wnm/tot.1/gud-trunc-wds-summary.tex'
removed 'exp/engl/wnm/tot.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/engl/wnm/tot.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:19 by tex-make-sample-summary.sh
% Token and word counts for engl/wnm/tot.1/gud.wfr
%
\def\englwnmtrunctotPBgudTks{831}
\def\englwnmtrunctotPBgudTksPct{100.0}
\def\englwnmtrunctotPBgudWds{194}
\def\englwnmtrunctotPBgudWdsPct{23.3}
copied '/tmp/577666.file' -> 'exp/engl/wnm/tot.1/gud-trunc-wds-summary.tex'
removed '/tmp/577666.file'
creating running text file dat/engl/wnm/tot.1/bad.wdf
sample:
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
removed 'dat/engl/wnm/tot.1/bad.wfr'
creating the word frequency file dat/engl/wnm/tot.1/bad.wfr
the 10 most common words in dat/engl/wnm/tot.1/bad.tlw:
removed 'dat/engl/wnm/tot.1/bad-trunc-wds-summary.tex'
removed 'exp/engl/wnm/tot.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/engl/wnm/tot.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:19 by tex-make-sample-summary.sh
% Token and word counts for engl/wnm/tot.1/bad.wfr
%
\def\englwnmtrunctotPBbadTks{0}
\def\englwnmtrunctotPBbadTksPct{0.0}
\def\englwnmtrunctotPBbadWds{0}
\def\englwnmtrunctotPBbadWdsPct{0.0}
copied '/tmp/577710.file' -> 'exp/engl/wnm/tot.1/bad-trunc-wds-summary.tex'
removed '/tmp/577710.file'
lines words bytes file
------- ------- --------- ------------
194 582 4698 dat/engl/wnm/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
194 582 4698 dat/engl/wnm/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
0 0 0 dat/engl/wnm/tot.1/bad.wfr
tot.1 raw = 831 gud = 831 bad = 0
=== creating the derived word files dat/engl/cul/*/{raw,gud,bad}.{tlw,wdf,wfr} (trunc) ===
... creating word files dat/engl/cul/pre.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
2824 dat/engl/cul/pre.1/trunc.tlw
removed 'dat/engl/cul/pre.1/raw.tlw'
removed 'dat/engl/cul/pre.1/gud.tlw'
removed 'dat/engl/cul/pre.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/engl/cul/pre.1/raw.wdf
sample:
courteous reader =
aristotle in his metaphysicks writing of the nature of man hit the nail
on the head when he said that man is naturally enclined to and desirous
of knowledg and indeed it is palpable and apparent that as pride is the
first visible sin in a child whereby we may gather that it was the first
sin of adam so knowledg being the first vertue a child minds as is
apparent to them that do but with the eye of reason heed their actions
even whilst they are very yong even before they are a yeer old even by
natural instinct whereby a man may more than guess that knowledg was the
greatest loss or at least one of the greatest we lost by the fall of
adam knowledg saith aristotle is in prosperity an ornament in adversity
a refuge and truly there is almost no greater enemy to knowledg in the
world that pride and covetousness excellently said juvenal sat° 7 =
*{scire} ..*{=} and again some men are so damnable proud and envious
withal that they would have no body know any thing but themselves the
one i hope will shortly learn better manners and the other be a burden
too heavy for the earth long to bear =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
the book either through my own forgetfulness or my amanuensis was
omitted and here i shal give it you plainly without any circumstances =
removed 'dat/engl/cul/pre.1/raw.wfr'
creating the word frequency file dat/engl/cul/pre.1/raw.wfr
the 10 most common words in dat/engl/cul/pre.1/raw.tlw:
180 0.06374 the
133 0.04710 of
103 0.03647 and
79 0.02797 in
73 0.02585 to
50 0.01771 that
49 0.01735 a
45 0.01593 i
38 0.01346 it
32 0.01133 by
removed 'dat/engl/cul/pre.1/raw-trunc-wds-summary.tex'
removed 'exp/engl/cul/pre.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/engl/cul/pre.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:19 by tex-make-sample-summary.sh
% Token and word counts for engl/cul/pre.1/raw.wfr
%
\def\englcultruncprePBrawTks{2824}
\def\englcultruncprePBrawTksPct{100.0}
\def\englcultruncprePBrawWds{799}
\def\englcultruncprePBrawWdsPct{28.3}
copied '/tmp/577805.file' -> 'exp/engl/cul/pre.1/raw-trunc-wds-summary.tex'
removed '/tmp/577805.file'
creating running text file dat/engl/cul/pre.1/gud.wdf
sample:
courteous reader aristotle in his metaphysicks writing of the nature of
man hit the nail on the head when he said that man is naturally enclined
to and desirous of knowledg and indeed it is palpable and apparent that
as pride is the first visible sin in a child whereby we may gather that
it was the first sin of adam so knowledg being the first vertue a child
minds as is apparent to them that do but with the eye of reason heed
their actions even whilst they are very yong even before they are a yeer
old even by natural instinct whereby a man may more than guess that
knowledg was the greatest loss or at least one of the greatest we lost
by the fall of adam knowledg saith aristotle is in prosperity an
ornament in adversity a refuge and truly there is almost no greater
enemy to knowledg in the world that pride and covetousness excellently
said juvenal and again some men are so damnable proud and envious withal
that they would have no body know any thing but themselves the one i
hope will shortly learn better manners and the other be a burden too
heavy for the earth long to bear the subject which i here fixed my
thoughts upon is not only the description and nature of herbs which had
it been all i had authority sufficient to bear me out in it for solomon
employed part of that wisdom he asked and received of god in searching
after them which he wrote in books even of all herbs plants and trees
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
another herb of the same planet which in the book either through my own
forgetfulness or my amanuensis was omitted and here i shal give it you
plainly without any circumstances
removed 'dat/engl/cul/pre.1/gud.wfr'
creating the word frequency file dat/engl/cul/pre.1/gud.wfr
the 10 most common words in dat/engl/cul/pre.1/gud.tlw:
180 0.06515 the
133 0.04814 of
103 0.03728 and
79 0.02859 in
73 0.02642 to
50 0.01810 that
49 0.01773 a
45 0.01629 i
38 0.01375 it
32 0.01158 by
removed 'dat/engl/cul/pre.1/gud-trunc-wds-summary.tex'
removed 'exp/engl/cul/pre.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/engl/cul/pre.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:19 by tex-make-sample-summary.sh
% Token and word counts for engl/cul/pre.1/gud.wfr
%
\def\englcultruncprePBgudTks{2763}
\def\englcultruncprePBgudTksPct{97.8}
\def\englcultruncprePBgudWds{778}
\def\englcultruncprePBgudWdsPct{27.5}
copied '/tmp/577849.file' -> 'exp/engl/cul/pre.1/gud-trunc-wds-summary.tex'
removed '/tmp/577849.file'
creating running text file dat/engl/cul/pre.1/bad.wdf
sample:
=
sat° 7 =
*{scire} ..*{=} =
=
=
*{ad} ..*{=} viz° =
*{ipse} ..*{=} =
&c° &c° &c° dr° dr° dr° mr° =
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/engl/cul/pre.1/bad.wfr'
creating the word frequency file dat/engl/cul/pre.1/bad.wfr
the 10 most common words in dat/engl/cul/pre.1/bad.tlw:
28 0.45902 =
6 0.09836 ..*{=}
5 0.08197 &c°
3 0.04918 dr°
2 0.03279 1
2 0.03279 viz°
1 0.01639 &c
1 0.01639 *{1}
1 0.01639 *{ad}
1 0.01639 *{excideret}
removed 'dat/engl/cul/pre.1/bad-trunc-wds-summary.tex'
removed 'exp/engl/cul/pre.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/engl/cul/pre.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:19 by tex-make-sample-summary.sh
% Token and word counts for engl/cul/pre.1/bad.wfr
%
\def\englcultruncprePBbadTks{61}
\def\englcultruncprePBbadTksPct{2.2}
\def\englcultruncprePBbadWds{21}
\def\englcultruncprePBbadWdsPct{0.7}
copied '/tmp/577893.file' -> 'exp/engl/cul/pre.1/bad-trunc-wds-summary.tex'
removed '/tmp/577893.file'
... creating word files dat/engl/cul/her.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
36193 dat/engl/cul/her.1/trunc.tlw
removed 'dat/engl/cul/her.1/raw.tlw'
removed 'dat/engl/cul/her.1/gud.tlw'
removed 'dat/engl/cul/her.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/engl/cul/her.1/raw.wdf
sample:
*{description} ..*{=} this small herb hath but one leaf which grows with
the stalk a fingers length above the ground being fat and of a fresh
green colour broad like the water plantane but less without any middle
rib in it from the bottom of which leaf on the inside riseth up
ordinarily one somtimes two or three small slender stalks the upper half
wherof is somwhat bigger and dented with smal round dents of a yellowish
green colour like the tongue of an adder or serpent only this is as
useful as they are formidable the root continues all the year =
*{place} ..*{=} it groweth in moist meadows and such like places =
*{time} ..*{=} and is to be found in april and may for it quickly
perisheth with a little heat =
*{vertues} ..*{=} it is temperate in respect of heat but dry in the
second degree the juyce of the leaves drunk with the distilled water of
horstail is a singular remedy for all manner of wounds in the breast
bowels or other parts of the body and is given with good success unto
those who are troubled with casting vomiting or bleeding at the mouth or
nose or otherwise downwards the said juyce given in the distilled water
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
with long husks on them and hard rough seed in them =
*{place} ..*{=} it groweth commonly through
removed 'dat/engl/cul/her.1/raw.wfr'
creating the word frequency file dat/engl/cul/her.1/raw.wfr
the 10 most common words in dat/engl/cul/her.1/raw.tlw:
2988 0.08256 the
1895 0.05236 and
1248 0.03448 of
872 0.02409 in
669 0.01848 or
650 0.01796 it
640 0.01768 to
600 0.01658 a
557 0.01539 is
429 0.01185 =
removed 'dat/engl/cul/her.1/raw-trunc-wds-summary.tex'
removed 'exp/engl/cul/her.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/engl/cul/her.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:20 by tex-make-sample-summary.sh
% Token and word counts for engl/cul/her.1/raw.wfr
%
\def\englcultruncherPBrawTks{36193}
\def\englcultruncherPBrawTksPct{100.0}
\def\englcultruncherPBrawWds{3489}
\def\englcultruncherPBrawWdsPct{9.6}
copied '/tmp/577947.file' -> 'exp/engl/cul/her.1/raw-trunc-wds-summary.tex'
removed '/tmp/577947.file'
creating running text file dat/engl/cul/her.1/gud.wdf
sample:
this small herb hath but one leaf which grows with the stalk a fingers
length above the ground being fat and of a fresh green colour broad like
the water plantane but less without any middle rib in it from the bottom
of which leaf on the inside riseth up ordinarily one somtimes two or
three small slender stalks the upper half wherof is somwhat bigger and
dented with smal round dents of a yellowish green colour like the tongue
of an adder or serpent only this is as useful as they are formidable the
root continues all the year it groweth in moist meadows and such like
places and is to be found in april and may for it quickly perisheth with
a little heat it is temperate in respect of heat but dry in the second
degree the juyce of the leaves drunk with the distilled water of
horstail is a singular remedy for all manner of wounds in the breast
bowels or other parts of the body and is given with good success unto
those who are troubled with casting vomiting or bleeding at the mouth or
nose or otherwise downwards the said juyce given in the distilled water
of oaken buds is very good for women who have their usual courses or the
whites flowing down too abundantly it helps sore eyes the leaves infused
or boyled in oyl omphacine or unripe olives set in the sun for certain
daies or the green leaves sufficiently boyled in the said oyl is made an
excellent green balsom not only for green and fresh wounds but also for
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
stalks are joynted like corn with the like leavs on them and a long
spiked head with long husks on them and hard rough seed in them it
groweth commonly through
removed 'dat/engl/cul/her.1/gud.wfr'
creating the word frequency file dat/engl/cul/her.1/gud.wfr
the 10 most common words in dat/engl/cul/her.1/gud.tlw:
2988 0.08531 the
1895 0.05410 and
1248 0.03563 of
872 0.02490 in
669 0.01910 or
650 0.01856 it
640 0.01827 to
600 0.01713 a
557 0.01590 is
381 0.01088 with
removed 'dat/engl/cul/her.1/gud-trunc-wds-summary.tex'
removed 'exp/engl/cul/her.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/engl/cul/her.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:20 by tex-make-sample-summary.sh
% Token and word counts for engl/cul/her.1/gud.wfr
%
\def\englcultruncherPBgudTks{35027}
\def\englcultruncherPBgudTksPct{96.8}
\def\englcultruncherPBgudWds{3399}
\def\englcultruncherPBgudWdsPct{9.4}
copied '/tmp/577991.file' -> 'exp/engl/cul/her.1/gud-trunc-wds-summary.tex'
removed '/tmp/577991.file'
creating running text file dat/engl/cul/her.1/bad.wdf
sample:
*{description} ..*{=} =
*{place} ..*{=} =
*{time} ..*{=} =
*{vertues} ..*{=} =
*{wounds} ..*{.} =
viz° &c° 1651 =
=
*{description} ..*{=} =
*{place} ..*{=} =
*{time} ..*{=} =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
*{description} ..*{=} =
*{place} ..*{=}
removed 'dat/engl/cul/her.1/bad.wfr'
creating the word frequency file dat/engl/cul/her.1/bad.wfr
the 10 most common words in dat/engl/cul/her.1/bad.tlw:
429 0.36792 =
268 0.22985 ..*{=}
77 0.06604 *{vertues}
76 0.06518 ..*{.}
65 0.05575 *{place}
60 0.05146 *{time}
45 0.03859 *{description}
12 0.01029 &c°
10 0.00858 viz°
8 0.00686 dr°
removed 'dat/engl/cul/her.1/bad-trunc-wds-summary.tex'
removed 'exp/engl/cul/her.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/engl/cul/her.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:20 by tex-make-sample-summary.sh
% Token and word counts for engl/cul/her.1/bad.wfr
%
\def\englcultruncherPBbadTks{1166}
\def\englcultruncherPBbadTksPct{3.2}
\def\englcultruncherPBbadWds{90}
\def\englcultruncherPBbadWdsPct{0.2}
copied '/tmp/578035.file' -> 'exp/engl/cul/her.1/bad-trunc-wds-summary.tex'
removed '/tmp/578035.file'
... creating word files dat/engl/cul/rec.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
7084 dat/engl/cul/rec.1/trunc.tlw
removed 'dat/engl/cul/rec.1/raw.tlw'
removed 'dat/engl/cul/rec.1/gud.tlw'
removed 'dat/engl/cul/rec.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/engl/cul/rec.1/raw.wdf
sample:
1 of leaves chuse only such as are green and full of juyce pick them
carefully and cast away such as are any way declining for they will
putrifie the rest so shall one handful be worth ten of those you buy in
cheap side =
2 note in what place they most delight to grow in and gather them there
for bettony that grows in the shadow is far better than that which grows
in the sun because it delights in the shadow so also such herbs as
delight to grow neer the water though happily you may find some of them
upon dry ground the treatise will inform you where every herb delights
to grow =
3 the leaves of such herbs as run up to seed are not so good when they
are in flower as before some few excepted the leaves of which are seldom
or never used in such cases if through ignorance they were not known or
through negligence forgotten you had better take the top and the flower
than the leaf =
4 dry them well in the sun and not in the shadow as the swinge of
physitians is for if the sun draw away the vertues of herbs it must
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
*{mr°} ..*{=} my answer to the letter was to this effect =
*{sir} ..*{=}
removed 'dat/engl/cul/rec.1/raw.wfr'
creating the word frequency file dat/engl/cul/rec.1/raw.wfr
the 10 most common words in dat/engl/cul/rec.1/raw.tlw:
377 0.05322 the
244 0.03444 of
214 0.03021 and
175 0.02470 a
171 0.02414 in
166 0.02343 to
150 0.02117 =
149 0.02103 it
141 0.01990 you
124 0.01750 as
removed 'dat/engl/cul/rec.1/raw-trunc-wds-summary.tex'
removed 'exp/engl/cul/rec.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/engl/cul/rec.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:20 by tex-make-sample-summary.sh
% Token and word counts for engl/cul/rec.1/raw.wfr
%
\def\englcultruncrecPBrawTks{7084}
\def\englcultruncrecPBrawTksPct{100.0}
\def\englcultruncrecPBrawWds{1260}
\def\englcultruncrecPBrawWdsPct{17.8}
copied '/tmp/578089.file' -> 'exp/engl/cul/rec.1/raw-trunc-wds-summary.tex'
removed '/tmp/578089.file'
creating running text file dat/engl/cul/rec.1/gud.wdf
sample:
of leaves chuse only such as are green and full of juyce pick them
carefully and cast away such as are any way declining for they will
putrifie the rest so shall one handful be worth ten of those you buy in
cheap side note in what place they most delight to grow in and gather
them there for bettony that grows in the shadow is far better than that
which grows in the sun because it delights in the shadow so also such
herbs as delight to grow neer the water though happily you may find some
of them upon dry ground the treatise will inform you where every herb
delights to grow the leaves of such herbs as run up to seed are not so
good when they are in flower as before some few excepted the leaves of
which are seldom or never used in such cases if through ignorance they
were not known or through negligence forgotten you had better take the
top and the flower than the leaf dry them well in the sun and not in the
shadow as the swinge of physitians is for if the sun draw away the
vertues of herbs it must needs do the like by hay by the same rule which
the experience of every country farmer will explode for a notable piece
of non sense such as are artists in astrology and indeed none else are
fit to make physitians such i advise let the planet that governs the
herb be angular and the stronger the better if they can in herbs of
saturn let saturn be in the ascendent in the herbs of mars let mars be
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
of bedfordhsire from a gentleman at that time altogether to me unknown
though since well known who was a student both in astrologie and physick
the words which are these my answer to the letter was to this effect
removed 'dat/engl/cul/rec.1/gud.wfr'
creating the word frequency file dat/engl/cul/rec.1/gud.wfr
the 10 most common words in dat/engl/cul/rec.1/gud.tlw:
377 0.05568 the
244 0.03604 of
214 0.03161 and
175 0.02585 a
171 0.02525 in
166 0.02452 to
149 0.02201 it
141 0.02082 you
124 0.01831 as
113 0.01669 them
removed 'dat/engl/cul/rec.1/gud-trunc-wds-summary.tex'
removed 'exp/engl/cul/rec.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/engl/cul/rec.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:20 by tex-make-sample-summary.sh
% Token and word counts for engl/cul/rec.1/gud.wfr
%
\def\englcultruncrecPBgudTks{6771}
\def\englcultruncrecPBgudTksPct{95.6}
\def\englcultruncrecPBgudWds{1240}
\def\englcultruncrecPBgudWdsPct{17.5}
copied '/tmp/578133.file' -> 'exp/engl/cul/rec.1/gud-trunc-wds-summary.tex'
removed '/tmp/578133.file'
creating running text file dat/engl/cul/rec.1/bad.wdf
sample:
1 =
2 =
3 =
4 =
5 =
6 =
7 =
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
*{mr°} ..*{=} =
*{sir} ..*{=}
removed 'dat/engl/cul/rec.1/bad.wfr'
creating the word frequency file dat/engl/cul/rec.1/bad.wfr
the 10 most common words in dat/engl/cul/rec.1/bad.tlw:
150 0.47923 =
22 0.07029 1
22 0.07029 2
20 0.06390 3
17 0.05431 4
14 0.04473 5
13 0.04153 &c°
10 0.03195 ..*{=}
10 0.03195 6
8 0.02556 *{1}
removed 'dat/engl/cul/rec.1/bad-trunc-wds-summary.tex'
removed 'exp/engl/cul/rec.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/engl/cul/rec.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:20 by tex-make-sample-summary.sh
% Token and word counts for engl/cul/rec.1/bad.wfr
%
\def\englcultruncrecPBbadTks{313}
\def\englcultruncrecPBbadTksPct{4.4}
\def\englcultruncrecPBbadWds{20}
\def\englcultruncrecPBbadWdsPct{0.3}
copied '/tmp/578177.file' -> 'exp/engl/cul/rec.1/bad-trunc-wds-summary.tex'
removed '/tmp/578177.file'
... creating word files dat/engl/cul/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
36201 dat/engl/cul/tot.1/trunc.tlw
removed 'dat/engl/cul/tot.1/raw.tlw'
removed 'dat/engl/cul/tot.1/gud.tlw'
removed 'dat/engl/cul/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/engl/cul/tot.1/raw.wdf
sample:
courteous reader =
aristotle in his metaphysicks writing of the nature of man hit the nail
on the head when he said that man is naturally enclined to and desirous
of knowledg and indeed it is palpable and apparent that as pride is the
first visible sin in a child whereby we may gather that it was the first
sin of adam so knowledg being the first vertue a child minds as is
apparent to them that do but with the eye of reason heed their actions
even whilst they are very yong even before they are a yeer old even by
natural instinct whereby a man may more than guess that knowledg was the
greatest loss or at least one of the greatest we lost by the fall of
adam knowledg saith aristotle is in prosperity an ornament in adversity
a refuge and truly there is almost no greater enemy to knowledg in the
world that pride and covetousness excellently said juvenal sat° 7 =
*{scire} ..*{=} and again some men are so damnable proud and envious
withal that they would have no body know any thing but themselves the
one i hope will shortly learn better manners and the other be a burden
too heavy for the earth long to bear =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
6 stopping distilled waters with a cork makes them musty and so will a
paper also if it do but touch the water your best way then
removed 'dat/engl/cul/tot.1/raw.wfr'
creating the word frequency file dat/engl/cul/tot.1/raw.wfr
the 10 most common words in dat/engl/cul/tot.1/raw.tlw:
2937 0.08113 the
1835 0.05069 and
1248 0.03447 of
908 0.02508 in
652 0.01801 to
636 0.01757 it
632 0.01746 or
609 0.01682 a
549 0.01517 is
447 0.01235 =
removed 'dat/engl/cul/tot.1/raw-trunc-wds-summary.tex'
removed 'exp/engl/cul/tot.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/engl/cul/tot.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:20 by tex-make-sample-summary.sh
% Token and word counts for engl/cul/tot.1/raw.wfr
%
\def\englcultrunctotPBrawTks{36201}
\def\englcultrunctotPBrawTksPct{100.0}
\def\englcultrunctotPBrawWds{3637}
\def\englcultrunctotPBrawWdsPct{10.0}
copied '/tmp/578231.file' -> 'exp/engl/cul/tot.1/raw-trunc-wds-summary.tex'
removed '/tmp/578231.file'
creating running text file dat/engl/cul/tot.1/gud.wdf
sample:
courteous reader aristotle in his metaphysicks writing of the nature of
man hit the nail on the head when he said that man is naturally enclined
to and desirous of knowledg and indeed it is palpable and apparent that
as pride is the first visible sin in a child whereby we may gather that
it was the first sin of adam so knowledg being the first vertue a child
minds as is apparent to them that do but with the eye of reason heed
their actions even whilst they are very yong even before they are a yeer
old even by natural instinct whereby a man may more than guess that
knowledg was the greatest loss or at least one of the greatest we lost
by the fall of adam knowledg saith aristotle is in prosperity an
ornament in adversity a refuge and truly there is almost no greater
enemy to knowledg in the world that pride and covetousness excellently
said juvenal and again some men are so damnable proud and envious withal
that they would have no body know any thing but themselves the one i
hope will shortly learn better manners and the other be a burden too
heavy for the earth long to bear the subject which i here fixed my
thoughts upon is not only the description and nature of herbs which had
it been all i had authority sufficient to bear me out in it for solomon
employed part of that wisdom he asked and received of god in searching
after them which he wrote in books even of all herbs plants and trees
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
the waters and might this way be prevented cover it close and keep it
for your use stopping distilled waters with a cork makes them musty and
so will a paper also if it do but touch the water your best way then
removed 'dat/engl/cul/tot.1/gud.wfr'
creating the word frequency file dat/engl/cul/tot.1/gud.wfr
the 10 most common words in dat/engl/cul/tot.1/gud.tlw:
2937 0.08385 the
1835 0.05239 and
1248 0.03563 of
908 0.02592 in
652 0.01861 to
636 0.01816 it
632 0.01804 or
609 0.01739 a
549 0.01567 is
359 0.01025 with
removed 'dat/engl/cul/tot.1/gud-trunc-wds-summary.tex'
removed 'exp/engl/cul/tot.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/engl/cul/tot.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:20 by tex-make-sample-summary.sh
% Token and word counts for engl/cul/tot.1/gud.wfr
%
\def\englcultrunctotPBgudTks{35027}
\def\englcultrunctotPBgudTksPct{96.8}
\def\englcultrunctotPBgudWds{3544}
\def\englcultrunctotPBgudWdsPct{9.8}
copied '/tmp/578275.file' -> 'exp/engl/cul/tot.1/gud-trunc-wds-summary.tex'
removed '/tmp/578275.file'
creating running text file dat/engl/cul/tot.1/bad.wdf
sample:
=
sat° 7 =
*{scire} ..*{=} =
=
=
*{ad} ..*{=} *{description} ..*{=} =
*{place} ..*{=} =
*{time} ..*{=} =
*{vertues} ..*{=} =
*{wounds} ..*{.} =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
5 =
6
removed 'dat/engl/cul/tot.1/bad.wfr'
creating the word frequency file dat/engl/cul/tot.1/bad.wfr
the 10 most common words in dat/engl/cul/tot.1/bad.tlw:
447 0.38075 =
250 0.21295 ..*{=}
70 0.05963 *{vertues}
68 0.05792 ..*{.}
60 0.05111 *{place}
58 0.04940 *{time}
40 0.03407 *{description}
15 0.01278 &c°
11 0.00937 viz°
9 0.00767 1
removed 'dat/engl/cul/tot.1/bad-trunc-wds-summary.tex'
removed 'exp/engl/cul/tot.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/engl/cul/tot.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:20 by tex-make-sample-summary.sh
% Token and word counts for engl/cul/tot.1/bad.wfr
%
\def\englcultrunctotPBbadTks{1174}
\def\englcultrunctotPBbadTksPct{3.2}
\def\englcultrunctotPBbadWds{93}
\def\englcultrunctotPBbadWdsPct{0.3}
copied '/tmp/578319.file' -> 'exp/engl/cul/tot.1/bad-trunc-wds-summary.tex'
removed '/tmp/578319.file'
lines words bytes file
------- ------- --------- ------------
799 2397 18379 dat/engl/cul/pre.1/raw.wfr
3489 10467 82166 dat/engl/cul/her.1/raw.wfr
1260 3780 28823 dat/engl/cul/rec.1/raw.wfr
3637 10911 85611 dat/engl/cul/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
778 2334 17930 dat/engl/cul/pre.1/gud.wfr
3399 10197 79871 dat/engl/cul/her.1/gud.wfr
1240 3720 28433 dat/engl/cul/rec.1/gud.wfr
3544 10632 83306 dat/engl/cul/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
21 63 449 dat/engl/cul/pre.1/bad.wfr
90 270 2295 dat/engl/cul/her.1/bad.wfr
20 60 390 dat/engl/cul/rec.1/bad.wfr
93 279 2305 dat/engl/cul/tot.1/bad.wfr
pre.1 raw = 2824 gud = 2763 bad = 61
her.1 raw = 36193 gud = 35027 bad = 1166
rec.1 raw = 7084 gud = 6771 bad = 313
tot.1 raw = 36201 gud = 35027 bad = 1174
=== creating the derived word files dat/engl/cpn/*/{raw,gud,bad}.{tlw,wdf,wfr} (trunc) ===
... creating word files dat/engl/cpn/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
544 dat/engl/cpn/tot.1/trunc.tlw
removed 'dat/engl/cpn/tot.1/raw.tlw'
removed 'dat/engl/cpn/tot.1/gud.tlw'
removed 'dat/engl/cpn/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/engl/cpn/tot.1/raw.wdf
sample:
adders tongue agrimony alehoof ground ivy alexander black alder tree
common alder tree angelica apples arrach wild stinking archangel arsmart
asarabacca asparagus sparagus sperage prickly asparagus sparagus sperage
ash tree avens balm barberry barly garden bazil sweet bazil bay tree
beans french beans ladies bedstraw beets water betony wood betony beech
tree bilberries som whorts whortleberries bifoyl twayblade birch tree
birds foot bishops weed bistort snakeweed one blade bramble black berry
bush blites borrage bugloss bluebottles briony wild vine brooklime
butchers broom broom broomrape buck horn plantane bugle burnet butter
bur bur dock cabbages coleworts sea colewort calamint mountain mint
chamomel campions wild carrots caraway celandine lesser celondine of
pilewort ordinary small centaury cherry tree winter cherries chervil
sweet chervil sweet cicely chickweed cich peas cicers cinkfoyl five
leaved grass in five finger'd grass clary cleavers goosgrass clowns
woundwort cocks head columbines coltsfoot foalsfoot comfry costmary
alecost cudweed cottonweed cowslips sciatica cresses water cresses
crosswort crowfoot cuckowpint wake robin daisies dandelyon vulgarly piss
a beds darnel dill devils bit dock dodder of time epithimum other
dodders dogs grass quich grass dovesfoot cranes bill ducksmeat down
cotton thistle elder tree dwarf elder elm tree endive elecampane eringo
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
valerian vervain vine violets vipers bugloss wall flowers winter gilly
flowers walnut tree wold weld dyers weed wheat willow tree woad woodbine
honey suckles wormwood yarrow
removed 'dat/engl/cpn/tot.1/raw.wfr'
creating the word frequency file dat/engl/cpn/tot.1/raw.wfr
the 10 most common words in dat/engl/cpn/tot.1/raw.tlw:
18 0.03309 tree
7 0.01287 grass
6 0.01103 thistle
5 0.00919 garden
5 0.00919 of
5 0.00919 sweet
5 0.00919 water
5 0.00919 winter
4 0.00735 herb
4 0.00735 mustard
removed 'dat/engl/cpn/tot.1/raw-trunc-wds-summary.tex'
removed 'exp/engl/cpn/tot.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/engl/cpn/tot.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:20 by tex-make-sample-summary.sh
% Token and word counts for engl/cpn/tot.1/raw.wfr
%
\def\englcpntrunctotPBrawTks{544}
\def\englcpntrunctotPBrawTksPct{100.0}
\def\englcpntrunctotPBrawWds{402}
\def\englcpntrunctotPBrawWdsPct{73.9}
copied '/tmp/578459.file' -> 'exp/engl/cpn/tot.1/raw-trunc-wds-summary.tex'
removed '/tmp/578459.file'
creating running text file dat/engl/cpn/tot.1/gud.wdf
sample:
adders tongue agrimony alehoof ground ivy alexander black alder tree
common alder tree angelica apples arrach wild stinking archangel arsmart
asarabacca asparagus sparagus sperage prickly asparagus sparagus sperage
ash tree avens balm barberry barly garden bazil sweet bazil bay tree
beans french beans ladies bedstraw beets water betony wood betony beech
tree bilberries som whorts whortleberries bifoyl twayblade birch tree
birds foot bishops weed bistort snakeweed one blade bramble black berry
bush blites borrage bugloss bluebottles briony wild vine brooklime
butchers broom broom broomrape buck horn plantane bugle burnet butter
bur bur dock cabbages coleworts sea colewort calamint mountain mint
chamomel campions wild carrots caraway celandine lesser celondine of
pilewort ordinary small centaury cherry tree winter cherries chervil
sweet chervil sweet cicely chickweed cich peas cicers cinkfoyl five
leaved grass in five finger'd grass clary cleavers goosgrass clowns
woundwort cocks head columbines coltsfoot foalsfoot comfry costmary
alecost cudweed cottonweed cowslips sciatica cresses water cresses
crosswort crowfoot cuckowpint wake robin daisies dandelyon vulgarly piss
a beds darnel dill devils bit dock dodder of time epithimum other
dodders dogs grass quich grass dovesfoot cranes bill ducksmeat down
cotton thistle elder tree dwarf elder elm tree endive elecampane eringo
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
valerian vervain vine violets vipers bugloss wall flowers winter gilly
flowers walnut tree wold weld dyers weed wheat willow tree woad woodbine
honey suckles wormwood yarrow
removed 'dat/engl/cpn/tot.1/gud.wfr'
creating the word frequency file dat/engl/cpn/tot.1/gud.wfr
the 10 most common words in dat/engl/cpn/tot.1/gud.tlw:
18 0.03327 tree
7 0.01294 grass
6 0.01109 thistle
5 0.00924 garden
5 0.00924 of
5 0.00924 sweet
5 0.00924 water
5 0.00924 winter
4 0.00739 herb
4 0.00739 mustard
removed 'dat/engl/cpn/tot.1/gud-trunc-wds-summary.tex'
removed 'exp/engl/cpn/tot.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/engl/cpn/tot.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:20 by tex-make-sample-summary.sh
% Token and word counts for engl/cpn/tot.1/gud.wfr
%
\def\englcpntrunctotPBgudTks{541}
\def\englcpntrunctotPBgudTksPct{99.4}
\def\englcpntrunctotPBgudWds{400}
\def\englcpntrunctotPBgudWdsPct{73.5}
copied '/tmp/578503.file' -> 'exp/engl/cpn/tot.1/gud-trunc-wds-summary.tex'
removed '/tmp/578503.file'
creating running text file dat/engl/cpn/tot.1/bad.wdf
sample:
st° mas° st°
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
st° mas° st°
removed 'dat/engl/cpn/tot.1/bad.wfr'
creating the word frequency file dat/engl/cpn/tot.1/bad.wfr
the 10 most common words in dat/engl/cpn/tot.1/bad.tlw:
2 0.66667 st°
1 0.33333 mas°
removed 'dat/engl/cpn/tot.1/bad-trunc-wds-summary.tex'
removed 'exp/engl/cpn/tot.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/engl/cpn/tot.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:20 by tex-make-sample-summary.sh
% Token and word counts for engl/cpn/tot.1/bad.wfr
%
\def\englcpntrunctotPBbadTks{3}
\def\englcpntrunctotPBbadTksPct{0.6}
\def\englcpntrunctotPBbadWds{2}
\def\englcpntrunctotPBbadWdsPct{0.4}
copied '/tmp/578547.file' -> 'exp/engl/cpn/tot.1/bad-trunc-wds-summary.tex'
removed '/tmp/578547.file'
lines words bytes file
------- ------- --------- ------------
402 1206 9426 dat/engl/cpn/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
400 1200 9385 dat/engl/cpn/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
2 6 41 dat/engl/cpn/tot.1/bad.wfr
tot.1 raw = 544 gud = 541 bad = 3
=== creating the derived word files dat/engl/twp/*/{raw,gud,bad}.{tlw,wdf,wfr} (trunc) ===
... creating word files dat/engl/twp/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
41419 dat/engl/twp/tot.1/trunc.tlw
removed 'dat/engl/twp/tot.1/raw.tlw'
removed 'dat/engl/twp/tot.1/gud.tlw'
removed 'dat/engl/twp/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/engl/twp/tot.1/raw.wdf
sample:
=
*{ego} ..*{=} i am the first the last also =
oone god in mageste =
meruelus of myght most =
ffader & son & holy goost =
on god in trinyte =
i am without begynnyng =
my godhede hath none endyng =
i am god in trone =
oone god in persons thre =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
and with in =
this chyld may
removed 'dat/engl/twp/tot.1/raw.wfr'
creating the word frequency file dat/engl/twp/tot.1/raw.wfr
the 10 most common words in dat/engl/twp/tot.1/raw.tlw:
6358 0.15350 =
1413 0.03411 i
1023 0.02470 and
870 0.02100 that
787 0.01900 to
760 0.01835 the
501 0.01210 in
484 0.01169 of
466 0.01125 a
434 0.01048 my
removed 'dat/engl/twp/tot.1/raw-trunc-wds-summary.tex'
removed 'exp/engl/twp/tot.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/engl/twp/tot.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:20 by tex-make-sample-summary.sh
% Token and word counts for engl/twp/tot.1/raw.wfr
%
\def\engltwptrunctotPBrawTks{41419}
\def\engltwptrunctotPBrawTksPct{100.0}
\def\engltwptrunctotPBrawWds{4222}
\def\engltwptrunctotPBrawWdsPct{10.2}
copied '/tmp/578642.file' -> 'exp/engl/twp/tot.1/raw-trunc-wds-summary.tex'
removed '/tmp/578642.file'
creating running text file dat/engl/twp/tot.1/gud.wdf
sample:
i am the first the last also oone god in mageste meruelus of myght most
ffader & son & holy goost on god in trinyte i am without begynnyng my
godhede hath none endyng i am god in trone oone god in persons thre
which may neuer twynnyd be ffor i am god alone all maner thyng is in my
thoght withoutten me ther may be noght ffor all is in my sight hit shall
be done after my will that i haue thoght i shall fulfill and manteyn
with my myght at the begynnyng of oure dede make we heuen & erth on
brede and lyghtys fayre to se ffor it is good to be so darknes from
light we parte on two in tyme to serue and be darknes we call the nyght
and lith also the bright it shall be as i say after my will this is
furth broght euen and morne both ar thay wroght and thus is maid a day
in medys the water bi oure assent be now maide the firmament and parte
ather from othere water aboue i wis euen and morne maide is this a day
so was the tothere waters that so wyde ben spred be gedered to geder in
to one stede that dry the erth may seym that at is dry the erth shall be
the waters also i call the see this warke to me is queme out of the erth
herbys shal spryng trees to florish and frute furth bryng thare kynde
that it be kyd this is done after my will even & morn maide is ther till
a day this is the thryd son & moyne set in the heuen with starnes & the
planettys seuen to stand in thare degre the son to serue the day lyght
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
that he reyn do as we red thrug outt bedlem and ilk othere stede make
knyghtys ordeyn and put vnto dede all knaue chyldren of two yerys brede
and with in this chyld may
removed 'dat/engl/twp/tot.1/gud.wfr'
creating the word frequency file dat/engl/twp/tot.1/gud.wfr
the 10 most common words in dat/engl/twp/tot.1/gud.tlw:
1413 0.04034 i
1023 0.02921 and
870 0.02484 that
787 0.02247 to
760 0.02170 the
501 0.01430 in
484 0.01382 of
466 0.01330 a
434 0.01239 my
432 0.01233 is
removed 'dat/engl/twp/tot.1/gud-trunc-wds-summary.tex'
removed 'exp/engl/twp/tot.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/engl/twp/tot.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:20 by tex-make-sample-summary.sh
% Token and word counts for engl/twp/tot.1/gud.wfr
%
\def\engltwptrunctotPBgudTks{35027}
\def\engltwptrunctotPBgudTksPct{84.6}
\def\engltwptrunctotPBgudWds{4202}
\def\engltwptrunctotPBgudWdsPct{10.1}
copied '/tmp/578686.file' -> 'exp/engl/twp/tot.1/gud-trunc-wds-summary.tex'
removed '/tmp/578686.file'
creating running text file dat/engl/twp/tot.1/bad.wdf
sample:
=
*{ego} ..*{=} =
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/engl/twp/tot.1/bad.wfr'
creating the word frequency file dat/engl/twp/tot.1/bad.wfr
the 10 most common words in dat/engl/twp/tot.1/bad.tlw:
6358 0.99468 =
14 0.00219 ..*{=}
3 0.00047 *{Ŧ}
1 0.00016 *{a}
1 0.00016 *{benedicite}
1 0.00016 *{cite'}
1 0.00016 *{cum}
1 0.00016 *{ego}
1 0.00016 *{exiet}
1 0.00016 *{in}
removed 'dat/engl/twp/tot.1/bad-trunc-wds-summary.tex'
removed 'exp/engl/twp/tot.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/engl/twp/tot.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:20 by tex-make-sample-summary.sh
% Token and word counts for engl/twp/tot.1/bad.wfr
%
\def\engltwptrunctotPBbadTks{6392}
\def\engltwptrunctotPBbadTksPct{15.4}
\def\engltwptrunctotPBbadWds{20}
\def\engltwptrunctotPBbadWdsPct{0.0}
copied '/tmp/578730.file' -> 'exp/engl/twp/tot.1/bad-trunc-wds-summary.tex'
removed '/tmp/578730.file'
lines words bytes file
------- ------- --------- ------------
4222 12666 94663 dat/engl/twp/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
4202 12606 94166 dat/engl/twp/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
20 60 497 dat/engl/twp/tot.1/bad.wfr
tot.1 raw = 41419 gud = 35027 bad = 6392
=== creating the derived word files dat/latn/ptt/*/{raw,gud,bad}.{tlw,wdf,wfr} (trunc) ===
... creating word files dat/latn/ptt/gen.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
26748 dat/latn/ptt/gen.1/trunc.tlw
removed 'dat/latn/ptt/gen.1/raw.tlw'
removed 'dat/latn/ptt/gen.1/gud.tlw'
removed 'dat/latn/ptt/gen.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/latn/ptt/gen.1/raw.wdf
sample:
in principio creavit deus caelum et terram =
terra autem erat inanis et vacua et tenebrae super faciem abyssi et
spiritus dei ferebatur super aquas =
dixitque deus fiat lux et facta est lux =
et vidit deus lucem quod esset bona et divisit lucem ac tenebras =
appellavitque lucem diem et tenebras noctem factumque est vespere et
mane dies unus =
dixit quoque deus fiat firmamentum in medio aquarum et dividat aquas ab
aquis =
et fecit deus firmamentum divisitque aquas quae erant sub firmamento ab
his quae erant super firmamentum et factum est ita =
vocavitque deus firmamentum caelum et factum est vespere et mane dies
secundus =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
mortuus est expletis centum decem vitae suae annis et conditus
aromatibus repositus est in loculo in aegypto =
removed 'dat/latn/ptt/gen.1/raw.wfr'
creating the word frequency file dat/latn/ptt/gen.1/raw.wfr
the 10 most common words in dat/latn/ptt/gen.1/raw.tlw:
1878 0.07021 et
1531 0.05724 =
692 0.02587 in
391 0.01462 est
372 0.01391 ad
182 0.00680 ut
180 0.00673 de
173 0.00647 autem
169 0.00632 qui
169 0.00632 quod
removed 'dat/latn/ptt/gen.1/raw-trunc-wds-summary.tex'
removed 'exp/latn/ptt/gen.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/latn/ptt/gen.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:21 by tex-make-sample-summary.sh
% Token and word counts for latn/ptt/gen.1/raw.wfr
%
\def\latnptttruncgenPBrawTks{26748}
\def\latnptttruncgenPBrawTksPct{100.0}
\def\latnptttruncgenPBrawWds{5714}
\def\latnptttruncgenPBrawWdsPct{21.4}
copied '/tmp/578825.file' -> 'exp/latn/ptt/gen.1/raw-trunc-wds-summary.tex'
removed '/tmp/578825.file'
creating running text file dat/latn/ptt/gen.1/gud.wdf
sample:
in principio creavit deus caelum et terram terra autem erat inanis et
vacua et tenebrae super faciem abyssi et spiritus dei ferebatur super
aquas dixitque deus fiat lux et facta est lux et vidit deus lucem quod
esset bona et divisit lucem ac tenebras appellavitque lucem diem et
tenebras noctem factumque est vespere et mane dies unus dixit quoque
deus fiat firmamentum in medio aquarum et dividat aquas ab aquis et
fecit deus firmamentum divisitque aquas quae erant sub firmamento ab his
quae erant super firmamentum et factum est ita vocavitque deus
firmamentum caelum et factum est vespere et mane dies secundus dixit
vero deus congregentur aquae quae sub caelo sunt in locum unum et
appareat arida factumque est ita et vocavit deus aridam terram
congregationesque aquarum appellavit maria et vidit deus quod esset
bonum et ait germinet terra herbam virentem et facientem semen et lignum
pomiferum faciens fructum iuxta genus suum cuius semen in semet ipso sit
super terram et factum est ita et protulit terra herbam virentem et
adferentem semen iuxta genus suum lignumque faciens fructum et habens
unumquodque sementem secundum speciem suam et vidit deus quod esset
bonum factumque est vespere et mane dies tertius dixit autem deus fiant
luminaria in firmamento caeli ut dividant diem ac noctem et sint in
signa et tempora et dies et annos ut luceant in firmamento caeli et
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
adiurasset eos atque dixisset deus visitabit vos asportate vobiscum ossa
mea de loco isto mortuus est expletis centum decem vitae suae annis et
conditus aromatibus repositus est in loculo in aegypto
removed 'dat/latn/ptt/gen.1/gud.wfr'
creating the word frequency file dat/latn/ptt/gen.1/gud.wfr
the 10 most common words in dat/latn/ptt/gen.1/gud.tlw:
1878 0.07447 et
692 0.02744 in
391 0.01551 est
372 0.01475 ad
182 0.00722 ut
180 0.00714 de
173 0.00686 autem
169 0.00670 qui
169 0.00670 quod
166 0.00658 cum
removed 'dat/latn/ptt/gen.1/gud-trunc-wds-summary.tex'
removed 'exp/latn/ptt/gen.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/latn/ptt/gen.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:21 by tex-make-sample-summary.sh
% Token and word counts for latn/ptt/gen.1/gud.wfr
%
\def\latnptttruncgenPBgudTks{25217}
\def\latnptttruncgenPBgudTksPct{94.3}
\def\latnptttruncgenPBgudWds{5713}
\def\latnptttruncgenPBgudWdsPct{21.4}
copied '/tmp/578869.file' -> 'exp/latn/ptt/gen.1/gud-trunc-wds-summary.tex'
removed '/tmp/578869.file'
creating running text file dat/latn/ptt/gen.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/latn/ptt/gen.1/bad.wfr'
creating the word frequency file dat/latn/ptt/gen.1/bad.wfr
the 10 most common words in dat/latn/ptt/gen.1/bad.tlw:
1531 1.00000 =
removed 'dat/latn/ptt/gen.1/bad-trunc-wds-summary.tex'
removed 'exp/latn/ptt/gen.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/latn/ptt/gen.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:21 by tex-make-sample-summary.sh
% Token and word counts for latn/ptt/gen.1/bad.wfr
%
\def\latnptttruncgenPBbadTks{1531}
\def\latnptttruncgenPBbadTksPct{5.7}
\def\latnptttruncgenPBbadWds{1}
\def\latnptttruncgenPBbadWdsPct{0.0}
copied '/tmp/578913.file' -> 'exp/latn/ptt/gen.1/bad-trunc-wds-summary.tex'
removed '/tmp/578913.file'
... creating word files dat/latn/ptt/exo.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
21271 dat/latn/ptt/exo.1/trunc.tlw
removed 'dat/latn/ptt/exo.1/raw.tlw'
removed 'dat/latn/ptt/exo.1/gud.tlw'
removed 'dat/latn/ptt/exo.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/latn/ptt/exo.1/raw.wdf
sample:
haec sunt nomina filiorum israhel qui ingressi sunt aegyptum cum iacob
singuli cum domibus suis introierunt =
ruben symeon levi iuda =
isachar zabulon et beniamin =
dan et nepthalim gad et aser =
erant igitur omnes animae eorum qui egressi sunt de femore iacob
septuaginta ioseph autem in aegypto erat =
quo mortuo et universis fratribus eius omnique cognatione illa =
filii israhel creverunt et quasi germinantes multiplicati sunt ac
roborati nimis impleverunt terram =
surrexit interea rex novus super aegyptum qui ignorabat ioseph =
et ait ad populum suum ecce populus filiorum israhel multus et fortior
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
nubes quippe domini incubabat per diem tabernaculo et ignis in nocte
videntibus populis israhel per cunctas mansiones suas =
removed 'dat/latn/ptt/exo.1/raw.wfr'
creating the word frequency file dat/latn/ptt/exo.1/raw.wfr
the 10 most common words in dat/latn/ptt/exo.1/raw.tlw:
1462 0.06873 et
1211 0.05693 =
693 0.03258 in
345 0.01622 ad
244 0.01147 de
230 0.01081 dominus
203 0.00954 est
181 0.00851 non
181 0.00851 ut
159 0.00747 israhel
removed 'dat/latn/ptt/exo.1/raw-trunc-wds-summary.tex'
removed 'exp/latn/ptt/exo.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/latn/ptt/exo.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:21 by tex-make-sample-summary.sh
% Token and word counts for latn/ptt/exo.1/raw.wfr
%
\def\latnptttruncexoPBrawTks{21271}
\def\latnptttruncexoPBrawTksPct{100.0}
\def\latnptttruncexoPBrawWds{4702}
\def\latnptttruncexoPBrawWdsPct{22.1}
copied '/tmp/578967.file' -> 'exp/latn/ptt/exo.1/raw-trunc-wds-summary.tex'
removed '/tmp/578967.file'
creating running text file dat/latn/ptt/exo.1/gud.wdf
sample:
haec sunt nomina filiorum israhel qui ingressi sunt aegyptum cum iacob
singuli cum domibus suis introierunt ruben symeon levi iuda isachar
zabulon et beniamin dan et nepthalim gad et aser erant igitur omnes
animae eorum qui egressi sunt de femore iacob septuaginta ioseph autem
in aegypto erat quo mortuo et universis fratribus eius omnique
cognatione illa filii israhel creverunt et quasi germinantes
multiplicati sunt ac roborati nimis impleverunt terram surrexit interea
rex novus super aegyptum qui ignorabat ioseph et ait ad populum suum
ecce populus filiorum israhel multus et fortior nobis venite sapienter
opprimamus eum ne forte multiplicetur et si ingruerit contra nos bellum
addatur inimicis nostris expugnatisque nobis egrediatur e terra
praeposuit itaque eis magistros operum ut adfligerent eos oneribus
aedificaveruntque urbes tabernaculorum pharaoni phiton et ramesses
quantoque opprimebant eos tanto magis multiplicabantur et crescebant
oderantque filios israhel aegyptii et adfligebant inludentes eis atque
ad amaritudinem perducebant vitam eorum operibus duris luti et lateris
omnique famulatu quo in terrae operibus premebantur dixit autem rex
aegypti obsetricibus hebraeorum quarum una vocabatur sephra altera phua
praecipiens eis quando obsetricabitis hebraeas et partus tempus
advenerit si masculus fuerit interficite illum si femina reservate
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
israhel per turmas suas si pendebat desuper manebant in eodem loco nubes
quippe domini incubabat per diem tabernaculo et ignis in nocte
videntibus populis israhel per cunctas mansiones suas
removed 'dat/latn/ptt/exo.1/gud.wfr'
creating the word frequency file dat/latn/ptt/exo.1/gud.wfr
the 10 most common words in dat/latn/ptt/exo.1/gud.tlw:
1462 0.07288 et
693 0.03455 in
345 0.01720 ad
244 0.01216 de
230 0.01147 dominus
203 0.01012 est
181 0.00902 non
181 0.00902 ut
159 0.00793 israhel
144 0.00718 eius
removed 'dat/latn/ptt/exo.1/gud-trunc-wds-summary.tex'
removed 'exp/latn/ptt/exo.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/latn/ptt/exo.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:21 by tex-make-sample-summary.sh
% Token and word counts for latn/ptt/exo.1/gud.wfr
%
\def\latnptttruncexoPBgudTks{20060}
\def\latnptttruncexoPBgudTksPct{94.3}
\def\latnptttruncexoPBgudWds{4701}
\def\latnptttruncexoPBgudWdsPct{22.1}
copied '/tmp/579011.file' -> 'exp/latn/ptt/exo.1/gud-trunc-wds-summary.tex'
removed '/tmp/579011.file'
creating running text file dat/latn/ptt/exo.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/latn/ptt/exo.1/bad.wfr'
creating the word frequency file dat/latn/ptt/exo.1/bad.wfr
the 10 most common words in dat/latn/ptt/exo.1/bad.tlw:
1211 1.00000 =
removed 'dat/latn/ptt/exo.1/bad-trunc-wds-summary.tex'
removed 'exp/latn/ptt/exo.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/latn/ptt/exo.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:21 by tex-make-sample-summary.sh
% Token and word counts for latn/ptt/exo.1/bad.wfr
%
\def\latnptttruncexoPBbadTks{1211}
\def\latnptttruncexoPBbadTksPct{5.7}
\def\latnptttruncexoPBbadWds{1}
\def\latnptttruncexoPBbadWdsPct{0.0}
copied '/tmp/579055.file' -> 'exp/latn/ptt/exo.1/bad-trunc-wds-summary.tex'
removed '/tmp/579055.file'
... creating word files dat/latn/ptt/num.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
20604 dat/latn/ptt/num.1/trunc.tlw
removed 'dat/latn/ptt/num.1/raw.tlw'
removed 'dat/latn/ptt/num.1/gud.tlw'
removed 'dat/latn/ptt/num.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/latn/ptt/num.1/raw.wdf
sample:
locutusque est dominus ad mosen in deserto sinai in tabernaculo foederis
prima die mensis secundi anno altero egressionis eorum ex aegypto dicens
=
tollite summam universae congregationis filiorum israhel per cognationes
et domos suas et nomina singulorum quicquid sexus est masculini =
a vicesimo anno et supra omnium virorum fortium ex israhel et
numerabitis eos per turmas suas tu et aaron =
eruntque vobiscum principes tribuum ac domorum in cognationibus suis =
quorum ista sunt nomina de ruben elisur filius sedeur =
de symeon salamihel filius surisaddai =
de iuda naasson filius aminadab =
de isachar nathanahel filius suar =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
haec sunt mandata atque iudicia quae praecepit dominus per manum mosi ad
filios israhel in campestribus moab super iordanem contra hiericho =
removed 'dat/latn/ptt/num.1/raw.wfr'
creating the word frequency file dat/latn/ptt/num.1/raw.wfr
the 10 most common words in dat/latn/ptt/num.1/raw.tlw:
1288 0.06251 =
1221 0.05926 et
569 0.02762 in
364 0.01767 ad
254 0.01233 est
253 0.01228 de
190 0.00922 per
188 0.00912 qui
187 0.00908 israhel
168 0.00815 sunt
removed 'dat/latn/ptt/num.1/raw-trunc-wds-summary.tex'
removed 'exp/latn/ptt/num.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/latn/ptt/num.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:21 by tex-make-sample-summary.sh
% Token and word counts for latn/ptt/num.1/raw.wfr
%
\def\latnptttruncnumPBrawTks{20604}
\def\latnptttruncnumPBrawTksPct{100.0}
\def\latnptttruncnumPBrawWds{4341}
\def\latnptttruncnumPBrawWdsPct{21.1}
copied '/tmp/579109.file' -> 'exp/latn/ptt/num.1/raw-trunc-wds-summary.tex'
removed '/tmp/579109.file'
creating running text file dat/latn/ptt/num.1/gud.wdf
sample:
locutusque est dominus ad mosen in deserto sinai in tabernaculo foederis
prima die mensis secundi anno altero egressionis eorum ex aegypto dicens
tollite summam universae congregationis filiorum israhel per cognationes
et domos suas et nomina singulorum quicquid sexus est masculini a
vicesimo anno et supra omnium virorum fortium ex israhel et numerabitis
eos per turmas suas tu et aaron eruntque vobiscum principes tribuum ac
domorum in cognationibus suis quorum ista sunt nomina de ruben elisur
filius sedeur de symeon salamihel filius surisaddai de iuda naasson
filius aminadab de isachar nathanahel filius suar de zabulon heliab
filius helon filiorum autem ioseph de ephraim helisama filius ammiud de
manasse gamalihel filius phadassur de beniamin abidan filius gedeonis de
dan ahiezer filius amisaddai de aser phegihel filius ochran de gad
heliasaph filius duhel de nepthali ahira filius henan hii nobilissimi
principes multitudinis per tribus et cognationes suas et capita
exercitus israhel quos tulerunt moses et aaron cum omni vulgi
multitudine et congregaverunt primo die mensis secundi recensentes eos
per cognationes et domos ac familias et capita et nomina singulorum a
vicesimo anno et supra sicut praeceperat dominus mosi numeratique sunt
in deserto sinai de ruben primogenito israhelis per generationes et
familias ac domos suas et nomina capitum singulorum omne quod sexus est
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
familia patris earum haec sunt mandata atque iudicia quae praecepit
dominus per manum mosi ad filios israhel in campestribus moab super
iordanem contra hiericho
removed 'dat/latn/ptt/num.1/gud.wfr'
creating the word frequency file dat/latn/ptt/num.1/gud.wfr
the 10 most common words in dat/latn/ptt/num.1/gud.tlw:
1221 0.06321 et
569 0.02946 in
364 0.01884 ad
254 0.01315 est
253 0.01310 de
190 0.00984 per
188 0.00973 qui
187 0.00968 israhel
168 0.00870 sunt
163 0.00844 dominus
removed 'dat/latn/ptt/num.1/gud-trunc-wds-summary.tex'
removed 'exp/latn/ptt/num.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/latn/ptt/num.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:21 by tex-make-sample-summary.sh
% Token and word counts for latn/ptt/num.1/gud.wfr
%
\def\latnptttruncnumPBgudTks{19316}
\def\latnptttruncnumPBgudTksPct{93.7}
\def\latnptttruncnumPBgudWds{4340}
\def\latnptttruncnumPBgudWdsPct{21.1}
copied '/tmp/579153.file' -> 'exp/latn/ptt/num.1/gud-trunc-wds-summary.tex'
removed '/tmp/579153.file'
creating running text file dat/latn/ptt/num.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/latn/ptt/num.1/bad.wfr'
creating the word frequency file dat/latn/ptt/num.1/bad.wfr
the 10 most common words in dat/latn/ptt/num.1/bad.tlw:
1288 1.00000 =
removed 'dat/latn/ptt/num.1/bad-trunc-wds-summary.tex'
removed 'exp/latn/ptt/num.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/latn/ptt/num.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:21 by tex-make-sample-summary.sh
% Token and word counts for latn/ptt/num.1/bad.wfr
%
\def\latnptttruncnumPBbadTks{1288}
\def\latnptttruncnumPBbadTksPct{6.3}
\def\latnptttruncnumPBbadWds{1}
\def\latnptttruncnumPBbadWdsPct{0.0}
copied '/tmp/579197.file' -> 'exp/latn/ptt/num.1/bad-trunc-wds-summary.tex'
removed '/tmp/579197.file'
... creating word files dat/latn/ptt/lev.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
14633 dat/latn/ptt/lev.1/trunc.tlw
removed 'dat/latn/ptt/lev.1/raw.tlw'
removed 'dat/latn/ptt/lev.1/gud.tlw'
removed 'dat/latn/ptt/lev.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/latn/ptt/lev.1/raw.wdf
sample:
vocavit autem mosen et locutus est ei dominus de tabernaculo testimonii
dicens =
loquere filiis israhel et dices ad eos homo qui obtulerit ex vobis
hostiam domino de pecoribus id est de bubus et ovibus offerens victimas
=
si holocaustum fuerit eius oblatio ac de armento masculum inmaculatum
offeret ad ostium tabernaculi testimonii ad placandum sibi dominum =
ponetque manus super caput hostiae et acceptabilis erit atque in
expiationem eius proficiens =
immolabitque vitulum coram domino et offerent filii aaron sacerdotes
sanguinem eius fundentes super altaris circuitum quod est ante ostium
tabernaculi =
detractaque pelle hostiae artus in frusta concident =
et subicient in altari ignem strue lignorum ante conposita =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
haec sunt praecepta quae mandavit dominus mosi ad filios israhel in
monte sinai =
removed 'dat/latn/ptt/lev.1/raw.wfr'
creating the word frequency file dat/latn/ptt/lev.1/raw.wfr
the 10 most common words in dat/latn/ptt/lev.1/raw.tlw:
882 0.06027 et
858 0.05863 =
385 0.02631 in
231 0.01579 est
197 0.01346 ad
185 0.01264 non
168 0.01148 qui
156 0.01066 de
130 0.00888 pro
127 0.00868 eius
removed 'dat/latn/ptt/lev.1/raw-trunc-wds-summary.tex'
removed 'exp/latn/ptt/lev.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/latn/ptt/lev.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:21 by tex-make-sample-summary.sh
% Token and word counts for latn/ptt/lev.1/raw.wfr
%
\def\latnptttrunclevPBrawTks{14633}
\def\latnptttrunclevPBrawTksPct{100.0}
\def\latnptttrunclevPBrawWds{3234}
\def\latnptttrunclevPBrawWdsPct{22.1}
copied '/tmp/579251.file' -> 'exp/latn/ptt/lev.1/raw-trunc-wds-summary.tex'
removed '/tmp/579251.file'
creating running text file dat/latn/ptt/lev.1/gud.wdf
sample:
vocavit autem mosen et locutus est ei dominus de tabernaculo testimonii
dicens loquere filiis israhel et dices ad eos homo qui obtulerit ex
vobis hostiam domino de pecoribus id est de bubus et ovibus offerens
victimas si holocaustum fuerit eius oblatio ac de armento masculum
inmaculatum offeret ad ostium tabernaculi testimonii ad placandum sibi
dominum ponetque manus super caput hostiae et acceptabilis erit atque in
expiationem eius proficiens immolabitque vitulum coram domino et
offerent filii aaron sacerdotes sanguinem eius fundentes super altaris
circuitum quod est ante ostium tabernaculi detractaque pelle hostiae
artus in frusta concident et subicient in altari ignem strue lignorum
ante conposita et membra quae caesa sunt desuper ordinantes caput
videlicet et cuncta quae adherent iecori intestinis et pedibus lotis
aqua adolebitque ea sacerdos super altare in holocaustum et suavem
odorem domino quod si de pecoribus oblatio est de ovibus sive de capris
holocaustum anniculum et absque macula offeret immolabitque ad latus
altaris quod respicit ad aquilonem coram domino sanguinem vero illius
fundent super altare filii aaron per circuitum dividentque membra caput
et omnia quae adherent iecori et inponent super ligna quibus subiciendus
est ignis intestina vero et pedes lavabunt aqua et oblata omnia adolebit
sacerdos super altare in holocaustum et odorem suavissimum domino sin
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
commutabitur si quis mutaverit et quod mutatum est et pro quo mutatum
est sanctificabitur domino et non redimetur haec sunt praecepta quae
mandavit dominus mosi ad filios israhel in monte sinai
removed 'dat/latn/ptt/lev.1/gud.wfr'
creating the word frequency file dat/latn/ptt/lev.1/gud.wfr
the 10 most common words in dat/latn/ptt/lev.1/gud.tlw:
882 0.06403 et
385 0.02795 in
231 0.01677 est
197 0.01430 ad
185 0.01343 non
168 0.01220 qui
156 0.01132 de
130 0.00944 pro
127 0.00922 eius
123 0.00893 si
removed 'dat/latn/ptt/lev.1/gud-trunc-wds-summary.tex'
removed 'exp/latn/ptt/lev.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/latn/ptt/lev.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:21 by tex-make-sample-summary.sh
% Token and word counts for latn/ptt/lev.1/gud.wfr
%
\def\latnptttrunclevPBgudTks{13775}
\def\latnptttrunclevPBgudTksPct{94.1}
\def\latnptttrunclevPBgudWds{3233}
\def\latnptttrunclevPBgudWdsPct{22.1}
copied '/tmp/579295.file' -> 'exp/latn/ptt/lev.1/gud-trunc-wds-summary.tex'
removed '/tmp/579295.file'
creating running text file dat/latn/ptt/lev.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/latn/ptt/lev.1/bad.wfr'
creating the word frequency file dat/latn/ptt/lev.1/bad.wfr
the 10 most common words in dat/latn/ptt/lev.1/bad.tlw:
858 1.00000 =
removed 'dat/latn/ptt/lev.1/bad-trunc-wds-summary.tex'
removed 'exp/latn/ptt/lev.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/latn/ptt/lev.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:21 by tex-make-sample-summary.sh
% Token and word counts for latn/ptt/lev.1/bad.wfr
%
\def\latnptttrunclevPBbadTks{858}
\def\latnptttrunclevPBbadTksPct{5.9}
\def\latnptttrunclevPBbadWds{1}
\def\latnptttrunclevPBbadWdsPct{0.0}
copied '/tmp/579339.file' -> 'exp/latn/ptt/lev.1/bad-trunc-wds-summary.tex'
removed '/tmp/579339.file'
... creating word files dat/latn/ptt/deu.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
19461 dat/latn/ptt/deu.1/trunc.tlw
removed 'dat/latn/ptt/deu.1/raw.tlw'
removed 'dat/latn/ptt/deu.1/gud.tlw'
removed 'dat/latn/ptt/deu.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/latn/ptt/deu.1/raw.wdf
sample:
haec sunt verba quae locutus est moses ad omnem israhel trans iordanem
in solitudine campestri contra mare rubrum inter pharan et thophel et
laban et aseroth ubi auri est plurimum =
undecim diebus de horeb per viam montis seir usque cadesbarne =
quadragesimo anno undecimo mense prima die mensis locutus est moses ad
filios israhel omnia quae praeceperat illi dominus ut diceret eis =
postquam percussit seon regem amorreorum qui habitavit in esebon et og
regem basan qui mansit in aseroth et in edrai =
trans iordanem in terra moab coepitque moses explanare legem et dicere =
dominus deus noster locutus est ad nos in horeb dicens sufficit vobis
quod in hoc monte mansistis =
revertimini et venite ad montem amorreorum et ad cetera quae ei proxima
sunt campestria atque montana et humiliora loca contra meridiem et iuxta
litus maris terram chananeorum et libani usque ad flumen magnum eufraten
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
et cunctam manum robustam magnaque mirabilia quae fecit moses coram
universo israhel =
removed 'dat/latn/ptt/deu.1/raw.wfr'
creating the word frequency file dat/latn/ptt/deu.1/raw.wfr
the 10 most common words in dat/latn/ptt/deu.1/raw.tlw:
1375 0.07065 et
959 0.04928 =
679 0.03489 in
285 0.01464 dominus
268 0.01377 non
240 0.01233 est
212 0.01089 ut
201 0.01033 ad
187 0.00961 de
179 0.00920 deus
removed 'dat/latn/ptt/deu.1/raw-trunc-wds-summary.tex'
removed 'exp/latn/ptt/deu.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/latn/ptt/deu.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:21 by tex-make-sample-summary.sh
% Token and word counts for latn/ptt/deu.1/raw.wfr
%
\def\latnptttruncdeuPBrawTks{19461}
\def\latnptttruncdeuPBrawTksPct{100.0}
\def\latnptttruncdeuPBrawWds{4467}
\def\latnptttruncdeuPBrawWdsPct{23.0}
copied '/tmp/579393.file' -> 'exp/latn/ptt/deu.1/raw-trunc-wds-summary.tex'
removed '/tmp/579393.file'
creating running text file dat/latn/ptt/deu.1/gud.wdf
sample:
haec sunt verba quae locutus est moses ad omnem israhel trans iordanem
in solitudine campestri contra mare rubrum inter pharan et thophel et
laban et aseroth ubi auri est plurimum undecim diebus de horeb per viam
montis seir usque cadesbarne quadragesimo anno undecimo mense prima die
mensis locutus est moses ad filios israhel omnia quae praeceperat illi
dominus ut diceret eis postquam percussit seon regem amorreorum qui
habitavit in esebon et og regem basan qui mansit in aseroth et in edrai
trans iordanem in terra moab coepitque moses explanare legem et dicere
dominus deus noster locutus est ad nos in horeb dicens sufficit vobis
quod in hoc monte mansistis revertimini et venite ad montem amorreorum
et ad cetera quae ei proxima sunt campestria atque montana et humiliora
loca contra meridiem et iuxta litus maris terram chananeorum et libani
usque ad flumen magnum eufraten en inquit tradidi vobis ingredimini et
possidete eam super qua iuravit dominus patribus vestris abraham et
isaac et iacob ut daret illam eis et semini eorum post eos dixique vobis
illo in tempore non possum solus sustinere vos quia dominus deus vester
multiplicavit vos et estis hodie sicut stellae caeli plurimae dominus
deus patrum vestrorum addat ad hunc numerum multa milia et benedicat
vobis sicut locutus est non valeo solus vestra negotia sustinere et
pondus ac iurgia date e vobis viros sapientes et gnaros et quorum
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
in terra aegypti pharaoni et omnibus servis eius universaeque terrae
illius et cunctam manum robustam magnaque mirabilia quae fecit moses
coram universo israhel
removed 'dat/latn/ptt/deu.1/gud.wfr'
creating the word frequency file dat/latn/ptt/deu.1/gud.wfr
the 10 most common words in dat/latn/ptt/deu.1/gud.tlw:
1375 0.07432 et
679 0.03670 in
285 0.01540 dominus
268 0.01448 non
240 0.01297 est
212 0.01146 ut
201 0.01086 ad
187 0.01011 de
179 0.00967 deus
167 0.00903 tibi
removed 'dat/latn/ptt/deu.1/gud-trunc-wds-summary.tex'
removed 'exp/latn/ptt/deu.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/latn/ptt/deu.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:22 by tex-make-sample-summary.sh
% Token and word counts for latn/ptt/deu.1/gud.wfr
%
\def\latnptttruncdeuPBgudTks{18502}
\def\latnptttruncdeuPBgudTksPct{95.1}
\def\latnptttruncdeuPBgudWds{4466}
\def\latnptttruncdeuPBgudWdsPct{22.9}
copied '/tmp/579437.file' -> 'exp/latn/ptt/deu.1/gud-trunc-wds-summary.tex'
removed '/tmp/579437.file'
creating running text file dat/latn/ptt/deu.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/latn/ptt/deu.1/bad.wfr'
creating the word frequency file dat/latn/ptt/deu.1/bad.wfr
the 10 most common words in dat/latn/ptt/deu.1/bad.tlw:
959 1.00000 =
removed 'dat/latn/ptt/deu.1/bad-trunc-wds-summary.tex'
removed 'exp/latn/ptt/deu.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/latn/ptt/deu.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:22 by tex-make-sample-summary.sh
% Token and word counts for latn/ptt/deu.1/bad.wfr
%
\def\latnptttruncdeuPBbadTks{959}
\def\latnptttruncdeuPBbadTksPct{4.9}
\def\latnptttruncdeuPBbadWds{1}
\def\latnptttruncdeuPBbadWdsPct{0.0}
copied '/tmp/579481.file' -> 'exp/latn/ptt/deu.1/bad-trunc-wds-summary.tex'
removed '/tmp/579481.file'
... creating word files dat/latn/ptt/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
37104 dat/latn/ptt/tot.1/trunc.tlw
removed 'dat/latn/ptt/tot.1/raw.tlw'
removed 'dat/latn/ptt/tot.1/gud.tlw'
removed 'dat/latn/ptt/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/latn/ptt/tot.1/raw.wdf
sample:
in principio creavit deus caelum et terram =
terra autem erat inanis et vacua et tenebrae super faciem abyssi et
spiritus dei ferebatur super aquas =
dixitque deus fiat lux et facta est lux =
et vidit deus lucem quod esset bona et divisit lucem ac tenebras =
appellavitque lucem diem et tenebras noctem factumque est vespere et
mane dies unus =
dixit quoque deus fiat firmamentum in medio aquarum et dividat aquas ab
aquis =
et fecit deus firmamentum divisitque aquas quae erant sub firmamento ab
his quae erant super firmamentum et factum est ita =
vocavitque deus firmamentum caelum et factum est vespere et mane dies
secundus =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
qui sunt trans iordanem post viam quae vergit ad solis occubitum in
terra chananei
removed 'dat/latn/ptt/tot.1/raw.wfr'
creating the word frequency file dat/latn/ptt/tot.1/raw.wfr
the 10 most common words in dat/latn/ptt/tot.1/raw.tlw:
2569 0.06924 et
2077 0.05598 =
1080 0.02911 in
577 0.01555 ad
530 0.01428 est
408 0.01100 dominus
385 0.01038 de
283 0.00763 non
277 0.00747 eius
277 0.00747 ut
removed 'dat/latn/ptt/tot.1/raw-trunc-wds-summary.tex'
removed 'exp/latn/ptt/tot.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/latn/ptt/tot.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:22 by tex-make-sample-summary.sh
% Token and word counts for latn/ptt/tot.1/raw.wfr
%
\def\latnptttrunctotPBrawTks{37104}
\def\latnptttrunctotPBrawTksPct{100.0}
\def\latnptttrunctotPBrawWds{6634}
\def\latnptttrunctotPBrawWdsPct{17.9}
copied '/tmp/579535.file' -> 'exp/latn/ptt/tot.1/raw-trunc-wds-summary.tex'
removed '/tmp/579535.file'
creating running text file dat/latn/ptt/tot.1/gud.wdf
sample:
in principio creavit deus caelum et terram terra autem erat inanis et
vacua et tenebrae super faciem abyssi et spiritus dei ferebatur super
aquas dixitque deus fiat lux et facta est lux et vidit deus lucem quod
esset bona et divisit lucem ac tenebras appellavitque lucem diem et
tenebras noctem factumque est vespere et mane dies unus dixit quoque
deus fiat firmamentum in medio aquarum et dividat aquas ab aquis et
fecit deus firmamentum divisitque aquas quae erant sub firmamento ab his
quae erant super firmamentum et factum est ita vocavitque deus
firmamentum caelum et factum est vespere et mane dies secundus dixit
vero deus congregentur aquae quae sub caelo sunt in locum unum et
appareat arida factumque est ita et vocavit deus aridam terram
congregationesque aquarum appellavit maria et vidit deus quod esset
bonum et ait germinet terra herbam virentem et facientem semen et lignum
pomiferum faciens fructum iuxta genus suum cuius semen in semet ipso sit
super terram et factum est ita et protulit terra herbam virentem et
adferentem semen iuxta genus suum lignumque faciens fructum et habens
unumquodque sementem secundum speciem suam et vidit deus quod esset
bonum factumque est vespere et mane dies tertius dixit autem deus fiant
luminaria in firmamento caeli ut dividant diem ac noctem et sint in
signa et tempora et dies et annos ut luceant in firmamento caeli et
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
benedictionem super montem garizim maledictionem super montem hebal qui
sunt trans iordanem post viam quae vergit ad solis occubitum in terra
chananei
removed 'dat/latn/ptt/tot.1/gud.wfr'
creating the word frequency file dat/latn/ptt/tot.1/gud.wfr
the 10 most common words in dat/latn/ptt/tot.1/gud.tlw:
2569 0.07334 et
1080 0.03083 in
577 0.01647 ad
530 0.01513 est
408 0.01165 dominus
385 0.01099 de
283 0.00808 non
277 0.00791 eius
277 0.00791 ut
258 0.00737 qui
removed 'dat/latn/ptt/tot.1/gud-trunc-wds-summary.tex'
removed 'exp/latn/ptt/tot.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/latn/ptt/tot.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:22 by tex-make-sample-summary.sh
% Token and word counts for latn/ptt/tot.1/gud.wfr
%
\def\latnptttrunctotPBgudTks{35027}
\def\latnptttrunctotPBgudTksPct{94.4}
\def\latnptttrunctotPBgudWds{6633}
\def\latnptttrunctotPBgudWdsPct{17.9}
copied '/tmp/579579.file' -> 'exp/latn/ptt/tot.1/gud-trunc-wds-summary.tex'
removed '/tmp/579579.file'
creating running text file dat/latn/ptt/tot.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/latn/ptt/tot.1/bad.wfr'
creating the word frequency file dat/latn/ptt/tot.1/bad.wfr
the 10 most common words in dat/latn/ptt/tot.1/bad.tlw:
2077 1.00000 =
removed 'dat/latn/ptt/tot.1/bad-trunc-wds-summary.tex'
removed 'exp/latn/ptt/tot.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/latn/ptt/tot.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:22 by tex-make-sample-summary.sh
% Token and word counts for latn/ptt/tot.1/bad.wfr
%
\def\latnptttrunctotPBbadTks{2077}
\def\latnptttrunctotPBbadTksPct{5.6}
\def\latnptttrunctotPBbadWds{1}
\def\latnptttrunctotPBbadWdsPct{0.0}
copied '/tmp/579623.file' -> 'exp/latn/ptt/tot.1/bad-trunc-wds-summary.tex'
removed '/tmp/579623.file'
lines words bytes file
------- ------- --------- ------------
5714 17142 140329 dat/latn/ptt/gen.1/raw.wfr
4702 14106 115841 dat/latn/ptt/exo.1/raw.wfr
4341 13023 107004 dat/latn/ptt/num.1/raw.wfr
3234 9702 79498 dat/latn/ptt/lev.1/raw.wfr
4467 13401 109883 dat/latn/ptt/deu.1/raw.wfr
6634 19902 164133 dat/latn/ptt/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
5713 17139 140311 dat/latn/ptt/gen.1/gud.wfr
4701 14103 115823 dat/latn/ptt/exo.1/gud.wfr
4340 13020 106986 dat/latn/ptt/num.1/gud.wfr
3233 9699 79480 dat/latn/ptt/lev.1/gud.wfr
4466 13398 109865 dat/latn/ptt/deu.1/gud.wfr
6633 19899 164115 dat/latn/ptt/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
1 3 18 dat/latn/ptt/gen.1/bad.wfr
1 3 18 dat/latn/ptt/exo.1/bad.wfr
1 3 18 dat/latn/ptt/num.1/bad.wfr
1 3 18 dat/latn/ptt/lev.1/bad.wfr
1 3 18 dat/latn/ptt/deu.1/bad.wfr
1 3 18 dat/latn/ptt/tot.1/bad.wfr
gen.1 raw = 26748 gud = 25217 bad = 1531
exo.1 raw = 21271 gud = 20060 bad = 1211
num.1 raw = 20604 gud = 19316 bad = 1288
lev.1 raw = 14633 gud = 13775 bad = 858
deu.1 raw = 19461 gud = 18502 bad = 959
tot.1 raw = 37104 gud = 35027 bad = 2077
=== creating the derived word files dat/latn/nwt/*/{raw,gud,bad}.{tlw,wdf,wfr} (trunc) ===
... creating word files dat/latn/nwt/mat.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
17502 dat/latn/nwt/mat.1/trunc.tlw
removed 'dat/latn/nwt/mat.1/raw.tlw'
removed 'dat/latn/nwt/mat.1/gud.tlw'
removed 'dat/latn/nwt/mat.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/latn/nwt/mat.1/raw.wdf
sample:
liber generationis iesu christi filii david filii abraham =
abraham genuit isaac isaac autem genuit iacob iacob autem genuit iudam
et fratres eius =
iudas autem genuit phares et zara de thamar phares autem genuit esrom
esrom autem genuit aram =
aram autem genuit aminadab aminadab autem genuit naasson naasson autem
genuit salmon =
salmon autem genuit booz de rachab booz autem genuit obed ex ruth obed
autem genuit iesse iesse autem genuit david regem =
david autem rex genuit salomonem ex ea quae fuit uriae =
salomon autem genuit roboam roboam autem genuit abiam abia autem genuit
asa =
asa autem genuit iosaphat iosaphat autem genuit ioram ioram autem genuit
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
docentes eos servare omnia quaecumque mandavi vobis et ecce ego vobiscum
sum omnibus diebus usque ad consummationem saeculi =
removed 'dat/latn/nwt/mat.1/raw.wfr'
creating the word frequency file dat/latn/nwt/mat.1/raw.wfr
the 10 most common words in dat/latn/nwt/mat.1/raw.tlw:
1267 0.07239 et
1069 0.06108 =
509 0.02908 in
370 0.02114 autem
293 0.01674 est
222 0.01268 non
222 0.01268 qui
157 0.00897 eum
133 0.00760 cum
121 0.00691 eius
removed 'dat/latn/nwt/mat.1/raw-trunc-wds-summary.tex'
removed 'exp/latn/nwt/mat.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/latn/nwt/mat.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:22 by tex-make-sample-summary.sh
% Token and word counts for latn/nwt/mat.1/raw.wfr
%
\def\latnnwttruncmatPBrawTks{17502}
\def\latnnwttruncmatPBrawTksPct{100.0}
\def\latnnwttruncmatPBrawWds{3914}
\def\latnnwttruncmatPBrawWdsPct{22.4}
copied '/tmp/579793.file' -> 'exp/latn/nwt/mat.1/raw-trunc-wds-summary.tex'
removed '/tmp/579793.file'
creating running text file dat/latn/nwt/mat.1/gud.wdf
sample:
liber generationis iesu christi filii david filii abraham abraham genuit
isaac isaac autem genuit iacob iacob autem genuit iudam et fratres eius
iudas autem genuit phares et zara de thamar phares autem genuit esrom
esrom autem genuit aram aram autem genuit aminadab aminadab autem genuit
naasson naasson autem genuit salmon salmon autem genuit booz de rachab
booz autem genuit obed ex ruth obed autem genuit iesse iesse autem
genuit david regem david autem rex genuit salomonem ex ea quae fuit
uriae salomon autem genuit roboam roboam autem genuit abiam abia autem
genuit asa asa autem genuit iosaphat iosaphat autem genuit ioram ioram
autem genuit oziam ozias autem genuit ioatham ioatham autem genuit achaz
achaz autem genuit ezechiam ezechias autem genuit manassen manasses
autem genuit amon amon autem genuit iosiam iosias autem genuit iechoniam
et fratres eius in transmigratione babylonis et post transmigrationem
babylonis iechonias genuit salathihel salathihel autem genuit zorobabel
zorobabel autem genuit abiud abiud autem genuit eliachim eliachim autem
genuit azor azor autem genuit saddoc saddoc autem genuit achim achim
autem genuit eliud eliud autem genuit eleazar eleazar autem genuit
matthan matthan autem genuit iacob iacob autem genuit ioseph virum
mariae de qua natus est iesus qui vocatur christus omnes ergo
generationes ab abraham usque ad david generationes quattuordecim et a
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
docete omnes gentes baptizantes eos in nomine patris et filii et
spiritus sancti docentes eos servare omnia quaecumque mandavi vobis et
ecce ego vobiscum sum omnibus diebus usque ad consummationem saeculi
removed 'dat/latn/nwt/mat.1/gud.wfr'
creating the word frequency file dat/latn/nwt/mat.1/gud.wfr
the 10 most common words in dat/latn/nwt/mat.1/gud.tlw:
1267 0.07711 et
509 0.03098 in
370 0.02252 autem
293 0.01783 est
222 0.01351 non
222 0.01351 qui
157 0.00956 eum
133 0.00809 cum
121 0.00736 eius
121 0.00736 iesus
removed 'dat/latn/nwt/mat.1/gud-trunc-wds-summary.tex'
removed 'exp/latn/nwt/mat.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/latn/nwt/mat.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:22 by tex-make-sample-summary.sh
% Token and word counts for latn/nwt/mat.1/gud.wfr
%
\def\latnnwttruncmatPBgudTks{16431}
\def\latnnwttruncmatPBgudTksPct{93.9}
\def\latnnwttruncmatPBgudWds{3911}
\def\latnnwttruncmatPBgudWdsPct{22.3}
copied '/tmp/579837.file' -> 'exp/latn/nwt/mat.1/gud-trunc-wds-summary.tex'
removed '/tmp/579837.file'
creating running text file dat/latn/nwt/mat.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/latn/nwt/mat.1/bad.wfr'
creating the word frequency file dat/latn/nwt/mat.1/bad.wfr
the 10 most common words in dat/latn/nwt/mat.1/bad.tlw:
1069 0.99813 =
1 0.00093 *{heli}
1 0.00093 ..*{sabacthani}
removed 'dat/latn/nwt/mat.1/bad-trunc-wds-summary.tex'
removed 'exp/latn/nwt/mat.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/latn/nwt/mat.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:22 by tex-make-sample-summary.sh
% Token and word counts for latn/nwt/mat.1/bad.wfr
%
\def\latnnwttruncmatPBbadTks{1071}
\def\latnnwttruncmatPBbadTksPct{6.1}
\def\latnnwttruncmatPBbadWds{3}
\def\latnnwttruncmatPBbadWdsPct{0.0}
copied '/tmp/579881.file' -> 'exp/latn/nwt/mat.1/bad-trunc-wds-summary.tex'
removed '/tmp/579881.file'
... creating word files dat/latn/nwt/mrk.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
10959 dat/latn/nwt/mrk.1/trunc.tlw
removed 'dat/latn/nwt/mrk.1/raw.tlw'
removed 'dat/latn/nwt/mrk.1/gud.tlw'
removed 'dat/latn/nwt/mrk.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/latn/nwt/mrk.1/raw.wdf
sample:
initium evangelii iesu christi filii dei =
sicut scriptum est in esaia propheta ecce mitto angelum meum ante faciem
tuam qui praeparabit viam tuam =
vox clamantis in deserto parate viam domini rectas facite semitas eius =
fuit iohannes in deserto baptizans et praedicans baptismum paenitentiae
in remissionem peccatorum =
et egrediebatur ad illum omnis iudaeae regio et hierosolymitae universi
et baptizabantur ab illo in iordane flumine confitentes peccata sua =
et erat iohannes vestitus pilis cameli et zona pellicia circa lumbos
eius et lucustas et mel silvestre edebat =
et praedicabat dicens venit fortior me post me cuius non sum dignus
procumbens solvere corrigiam calciamentorum eius =
ego baptizavi vos aqua ille vero baptizabit vos spiritu sancto =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
illi autem profecti praedicaverunt ubique domino cooperante et sermonem
confirmante sequentibus signis =
removed 'dat/latn/nwt/mrk.1/raw.wfr'
creating the word frequency file dat/latn/nwt/mrk.1/raw.wfr
the 10 most common words in dat/latn/nwt/mrk.1/raw.tlw:
1084 0.09891 et
677 0.06178 =
303 0.02765 in
174 0.01588 eum
146 0.01332 est
134 0.01223 non
125 0.01141 cum
112 0.01022 autem
107 0.00976 qui
87 0.00794 illis
removed 'dat/latn/nwt/mrk.1/raw-trunc-wds-summary.tex'
removed 'exp/latn/nwt/mrk.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/latn/nwt/mrk.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:22 by tex-make-sample-summary.sh
% Token and word counts for latn/nwt/mrk.1/raw.wfr
%
\def\latnnwttruncmrkPBrawTks{10959}
\def\latnnwttruncmrkPBrawTksPct{100.0}
\def\latnnwttruncmrkPBrawWds{2916}
\def\latnnwttruncmrkPBrawWdsPct{26.6}
copied '/tmp/579935.file' -> 'exp/latn/nwt/mrk.1/raw-trunc-wds-summary.tex'
removed '/tmp/579935.file'
creating running text file dat/latn/nwt/mrk.1/gud.wdf
sample:
initium evangelii iesu christi filii dei sicut scriptum est in esaia
propheta ecce mitto angelum meum ante faciem tuam qui praeparabit viam
tuam vox clamantis in deserto parate viam domini rectas facite semitas
eius fuit iohannes in deserto baptizans et praedicans baptismum
paenitentiae in remissionem peccatorum et egrediebatur ad illum omnis
iudaeae regio et hierosolymitae universi et baptizabantur ab illo in
iordane flumine confitentes peccata sua et erat iohannes vestitus pilis
cameli et zona pellicia circa lumbos eius et lucustas et mel silvestre
edebat et praedicabat dicens venit fortior me post me cuius non sum
dignus procumbens solvere corrigiam calciamentorum eius ego baptizavi
vos aqua ille vero baptizabit vos spiritu sancto et factum est in diebus
illis venit iesus a nazareth galilaeae et baptizatus est in iordane ab
iohanne et statim ascendens de aqua vidit apertos caelos et spiritum
tamquam columbam descendentem et manentem in ipso et vox facta est de
caelis tu es filius meus dilectus in te conplacui et statim spiritus
expellit eum in desertum et erat in deserto quadraginta diebus et
quadraginta noctibus et temptabatur a satana eratque cum bestiis et
angeli ministrabant illi postquam autem traditus est iohannes venit
iesus in galilaeam praedicans evangelium regni dei et dicens quoniam
impletum est tempus et adpropinquavit regnum dei paenitemini et credite
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
postquam locutus est eis adsumptus est in caelum et sedit a dextris dei
illi autem profecti praedicaverunt ubique domino cooperante et sermonem
confirmante sequentibus signis
removed 'dat/latn/nwt/mrk.1/gud.wfr'
creating the word frequency file dat/latn/nwt/mrk.1/gud.wfr
the 10 most common words in dat/latn/nwt/mrk.1/gud.tlw:
1084 0.10545 et
303 0.02947 in
174 0.01693 eum
146 0.01420 est
134 0.01304 non
125 0.01216 cum
112 0.01089 autem
107 0.01041 qui
87 0.00846 illis
80 0.00778 ut
removed 'dat/latn/nwt/mrk.1/gud-trunc-wds-summary.tex'
removed 'exp/latn/nwt/mrk.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/latn/nwt/mrk.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:22 by tex-make-sample-summary.sh
% Token and word counts for latn/nwt/mrk.1/gud.wfr
%
\def\latnnwttruncmrkPBgudTks{10280}
\def\latnnwttruncmrkPBgudTksPct{93.8}
\def\latnnwttruncmrkPBgudWds{2913}
\def\latnnwttruncmrkPBgudWdsPct{26.6}
copied '/tmp/579979.file' -> 'exp/latn/nwt/mrk.1/gud-trunc-wds-summary.tex'
removed '/tmp/579979.file'
creating running text file dat/latn/nwt/mrk.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/latn/nwt/mrk.1/bad.wfr'
creating the word frequency file dat/latn/nwt/mrk.1/bad.wfr
the 10 most common words in dat/latn/nwt/mrk.1/bad.tlw:
677 0.99705 =
1 0.00147 *{heloi}
1 0.00147 ..*{sabacthani}
removed 'dat/latn/nwt/mrk.1/bad-trunc-wds-summary.tex'
removed 'exp/latn/nwt/mrk.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/latn/nwt/mrk.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:22 by tex-make-sample-summary.sh
% Token and word counts for latn/nwt/mrk.1/bad.wfr
%
\def\latnnwttruncmrkPBbadTks{679}
\def\latnnwttruncmrkPBbadTksPct{6.2}
\def\latnnwttruncmrkPBbadWds{3}
\def\latnnwttruncmrkPBbadWdsPct{0.0}
copied '/tmp/580023.file' -> 'exp/latn/nwt/mrk.1/bad-trunc-wds-summary.tex'
removed '/tmp/580023.file'
... creating word files dat/latn/nwt/luk.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
19155 dat/latn/nwt/luk.1/trunc.tlw
removed 'dat/latn/nwt/luk.1/raw.tlw'
removed 'dat/latn/nwt/luk.1/gud.tlw'
removed 'dat/latn/nwt/luk.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/latn/nwt/luk.1/raw.wdf
sample:
quoniam quidem multi conati sunt ordinare narrationem quae in nobis
conpletae sunt rerum =
sicut tradiderunt nobis qui ab initio ipsi viderunt et ministri fuerunt
sermonis =
visum est et mihi adsecuto a principio omnibus diligenter ex ordine tibi
scribere optime theophile =
ut cognoscas eorum verborum de quibus eruditus es veritatem =
fuit in diebus herodis regis iudaeae sacerdos quidam nomine zaccharias
de vice abia et uxor illi de filiabus aaron et nomen eius elisabeth =
erant autem iusti ambo ante deum incedentes in omnibus mandatis et
iustificationibus domini sine querella =
et non erat illis filius eo quod esset elisabeth sterilis et ambo
processissent in diebus suis =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
et erant semper in templo laudantes et benedicentes deum amen =
removed 'dat/latn/nwt/luk.1/raw.wfr'
creating the word frequency file dat/latn/nwt/luk.1/raw.wfr
the 10 most common words in dat/latn/nwt/luk.1/raw.tlw:
1593 0.08316 et
1151 0.06009 =
589 0.03075 in
360 0.01879 autem
302 0.01577 qui
287 0.01498 est
223 0.01164 non
211 0.01102 ad
177 0.00924 cum
148 0.00773 dixit
removed 'dat/latn/nwt/luk.1/raw-trunc-wds-summary.tex'
removed 'exp/latn/nwt/luk.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/latn/nwt/luk.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:22 by tex-make-sample-summary.sh
% Token and word counts for latn/nwt/luk.1/raw.wfr
%
\def\latnnwttrunclukPBrawTks{19155}
\def\latnnwttrunclukPBrawTksPct{100.0}
\def\latnnwttrunclukPBrawWds{4407}
\def\latnnwttrunclukPBrawWdsPct{23.0}
copied '/tmp/580077.file' -> 'exp/latn/nwt/luk.1/raw-trunc-wds-summary.tex'
removed '/tmp/580077.file'
creating running text file dat/latn/nwt/luk.1/gud.wdf
sample:
quoniam quidem multi conati sunt ordinare narrationem quae in nobis
conpletae sunt rerum sicut tradiderunt nobis qui ab initio ipsi viderunt
et ministri fuerunt sermonis visum est et mihi adsecuto a principio
omnibus diligenter ex ordine tibi scribere optime theophile ut cognoscas
eorum verborum de quibus eruditus es veritatem fuit in diebus herodis
regis iudaeae sacerdos quidam nomine zaccharias de vice abia et uxor
illi de filiabus aaron et nomen eius elisabeth erant autem iusti ambo
ante deum incedentes in omnibus mandatis et iustificationibus domini
sine querella et non erat illis filius eo quod esset elisabeth sterilis
et ambo processissent in diebus suis factum est autem cum sacerdotio
fungeretur in ordine vicis suae ante deum secundum consuetudinem
sacerdotii sorte exiit ut incensum poneret ingressus in templum domini
et omnis multitudo erat populi orans foris hora incensi apparuit autem
illi angelus domini stans a dextris altaris incensi et zaccharias
turbatus est videns et timor inruit super eum ait autem ad illum angelus
ne timeas zaccharia quoniam exaudita est deprecatio tua et uxor tua
elisabeth pariet tibi filium et vocabis nomen eius iohannem et erit
gaudium tibi et exultatio et multi in nativitate eius gaudebunt erit
enim magnus coram domino et vinum et sicera non bibet et spiritu sancto
replebitur adhuc ex utero matris suae et multos filiorum israhel
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
eis et factum est dum benediceret illis recessit ab eis et ferebatur in
caelum et ipsi adorantes regressi sunt in hierusalem cum gaudio magno et
erant semper in templo laudantes et benedicentes deum amen
removed 'dat/latn/nwt/luk.1/gud.wfr'
creating the word frequency file dat/latn/nwt/luk.1/gud.wfr
the 10 most common words in dat/latn/nwt/luk.1/gud.tlw:
1593 0.08848 et
589 0.03271 in
360 0.02000 autem
302 0.01677 qui
287 0.01594 est
223 0.01239 non
211 0.01172 ad
177 0.00983 cum
148 0.00822 dixit
143 0.00794 quia
removed 'dat/latn/nwt/luk.1/gud-trunc-wds-summary.tex'
removed 'exp/latn/nwt/luk.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/latn/nwt/luk.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:22 by tex-make-sample-summary.sh
% Token and word counts for latn/nwt/luk.1/gud.wfr
%
\def\latnnwttrunclukPBgudTks{18004}
\def\latnnwttrunclukPBgudTksPct{94.0}
\def\latnnwttrunclukPBgudWds{4406}
\def\latnnwttrunclukPBgudWdsPct{23.0}
copied '/tmp/580121.file' -> 'exp/latn/nwt/luk.1/gud-trunc-wds-summary.tex'
removed '/tmp/580121.file'
creating running text file dat/latn/nwt/luk.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/latn/nwt/luk.1/bad.wfr'
creating the word frequency file dat/latn/nwt/luk.1/bad.wfr
the 10 most common words in dat/latn/nwt/luk.1/bad.tlw:
1151 1.00000 =
removed 'dat/latn/nwt/luk.1/bad-trunc-wds-summary.tex'
removed 'exp/latn/nwt/luk.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/latn/nwt/luk.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:22 by tex-make-sample-summary.sh
% Token and word counts for latn/nwt/luk.1/bad.wfr
%
\def\latnnwttrunclukPBbadTks{1151}
\def\latnnwttrunclukPBbadTksPct{6.0}
\def\latnnwttrunclukPBbadWds{1}
\def\latnnwttrunclukPBbadWdsPct{0.0}
copied '/tmp/580165.file' -> 'exp/latn/nwt/luk.1/bad-trunc-wds-summary.tex'
removed '/tmp/580165.file'
... creating word files dat/latn/nwt/joh.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
14905 dat/latn/nwt/joh.1/trunc.tlw
removed 'dat/latn/nwt/joh.1/raw.tlw'
removed 'dat/latn/nwt/joh.1/gud.tlw'
removed 'dat/latn/nwt/joh.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/latn/nwt/joh.1/raw.wdf
sample:
in principio erat verbum et verbum erat apud deum et deus erat verbum =
hoc erat in principio apud deum =
omnia per ipsum facta sunt et sine ipso factum est nihil quod factum est
=
in ipso vita erat et vita erat lux hominum =
et lux in tenebris lucet et tenebrae eam non conprehenderunt =
fuit homo missus a deo cui nomen erat iohannes =
hic venit in testimonium ut testimonium perhiberet de lumine ut omnes
crederent per illum =
non erat ille lux sed ut testimonium perhiberet de lumine =
erat lux vera quae inluminat omnem hominem venientem in mundum =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
sunt autem et alia multa quae fecit iesus quae si scribantur per singula
nec ipsum arbitror mundum capere eos qui scribendi sunt libros amen =
removed 'dat/latn/nwt/joh.1/raw.wfr'
creating the word frequency file dat/latn/nwt/joh.1/raw.wfr
the 10 most common words in dat/latn/nwt/joh.1/raw.tlw:
898 0.06025 et
879 0.05897 =
377 0.02529 in
307 0.02060 non
258 0.01731 quia
235 0.01577 est
213 0.01429 me
207 0.01389 qui
201 0.01349 autem
199 0.01335 iesus
removed 'dat/latn/nwt/joh.1/raw-trunc-wds-summary.tex'
removed 'exp/latn/nwt/joh.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/latn/nwt/joh.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:23 by tex-make-sample-summary.sh
% Token and word counts for latn/nwt/joh.1/raw.wfr
%
\def\latnnwttruncjohPBrawTks{14905}
\def\latnnwttruncjohPBrawTksPct{100.0}
\def\latnnwttruncjohPBrawWds{2524}
\def\latnnwttruncjohPBrawWdsPct{16.9}
copied '/tmp/580219.file' -> 'exp/latn/nwt/joh.1/raw-trunc-wds-summary.tex'
removed '/tmp/580219.file'
creating running text file dat/latn/nwt/joh.1/gud.wdf
sample:
in principio erat verbum et verbum erat apud deum et deus erat verbum
hoc erat in principio apud deum omnia per ipsum facta sunt et sine ipso
factum est nihil quod factum est in ipso vita erat et vita erat lux
hominum et lux in tenebris lucet et tenebrae eam non conprehenderunt
fuit homo missus a deo cui nomen erat iohannes hic venit in testimonium
ut testimonium perhiberet de lumine ut omnes crederent per illum non
erat ille lux sed ut testimonium perhiberet de lumine erat lux vera quae
inluminat omnem hominem venientem in mundum in mundo erat et mundus per
ipsum factus est et mundus eum non cognovit in propria venit et sui eum
non receperunt quotquot autem receperunt eum dedit eis potestatem filios
dei fieri his qui credunt in nomine eius qui non ex sanguinibus neque ex
voluntate carnis neque ex voluntate viri sed ex deo nati sunt et verbum
caro factum est et habitavit in nobis et vidimus gloriam eius gloriam
quasi unigeniti a patre plenum gratiae et veritatis iohannes testimonium
perhibet de ipso et clamat dicens hic erat quem dixi vobis qui post me
venturus est ante me factus est quia prior me erat et de plenitudine
eius nos omnes accepimus et gratiam pro gratia quia lex per mosen data
est gratia et veritas per iesum christum facta est deum nemo vidit
umquam unigenitus filius qui est in sinu patris ipse enarravit et hoc
est testimonium iohannis quando miserunt iudaei ab hierosolymis
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
quia verum est testimonium eius sunt autem et alia multa quae fecit
iesus quae si scribantur per singula nec ipsum arbitror mundum capere
eos qui scribendi sunt libros amen
removed 'dat/latn/nwt/joh.1/gud.wfr'
creating the word frequency file dat/latn/nwt/joh.1/gud.wfr
the 10 most common words in dat/latn/nwt/joh.1/gud.tlw:
898 0.06402 et
377 0.02688 in
307 0.02189 non
258 0.01839 quia
235 0.01675 est
213 0.01519 me
207 0.01476 qui
201 0.01433 autem
199 0.01419 iesus
190 0.01355 eum
removed 'dat/latn/nwt/joh.1/gud-trunc-wds-summary.tex'
removed 'exp/latn/nwt/joh.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/latn/nwt/joh.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:23 by tex-make-sample-summary.sh
% Token and word counts for latn/nwt/joh.1/gud.wfr
%
\def\latnnwttruncjohPBgudTks{14026}
\def\latnnwttruncjohPBgudTksPct{94.1}
\def\latnnwttruncjohPBgudWds{2523}
\def\latnnwttruncjohPBgudWdsPct{16.9}
copied '/tmp/580263.file' -> 'exp/latn/nwt/joh.1/gud-trunc-wds-summary.tex'
removed '/tmp/580263.file'
creating running text file dat/latn/nwt/joh.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/latn/nwt/joh.1/bad.wfr'
creating the word frequency file dat/latn/nwt/joh.1/bad.wfr
the 10 most common words in dat/latn/nwt/joh.1/bad.tlw:
879 1.00000 =
removed 'dat/latn/nwt/joh.1/bad-trunc-wds-summary.tex'
removed 'exp/latn/nwt/joh.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/latn/nwt/joh.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:23 by tex-make-sample-summary.sh
% Token and word counts for latn/nwt/joh.1/bad.wfr
%
\def\latnnwttruncjohPBbadTks{879}
\def\latnnwttruncjohPBbadTksPct{5.9}
\def\latnnwttruncjohPBbadWds{1}
\def\latnnwttruncjohPBbadWdsPct{0.0}
copied '/tmp/580307.file' -> 'exp/latn/nwt/joh.1/bad-trunc-wds-summary.tex'
removed '/tmp/580307.file'
... creating word files dat/latn/nwt/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
37253 dat/latn/nwt/tot.1/trunc.tlw
removed 'dat/latn/nwt/tot.1/raw.tlw'
removed 'dat/latn/nwt/tot.1/gud.tlw'
removed 'dat/latn/nwt/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/latn/nwt/tot.1/raw.wdf
sample:
liber generationis iesu christi filii david filii abraham =
abraham genuit isaac isaac autem genuit iacob iacob autem genuit iudam
et fratres eius =
iudas autem genuit phares et zara de thamar phares autem genuit esrom
esrom autem genuit aram =
aram autem genuit aminadab aminadab autem genuit naasson naasson autem
genuit salmon =
salmon autem genuit booz de rachab booz autem genuit obed ex ruth obed
autem genuit iesse iesse autem genuit david regem =
david autem rex genuit salomonem ex ea quae fuit uriae =
salomon autem genuit roboam roboam autem genuit abiam abia autem genuit
asa =
asa autem genuit iosaphat iosaphat autem genuit ioram ioram autem genuit
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
cognovit ergo turba multa ex iudaeis quia illic est et venerunt non
propter iesum tantum sed ut lazarum viderent
removed 'dat/latn/nwt/tot.1/raw.wfr'
creating the word frequency file dat/latn/nwt/tot.1/raw.wfr
the 10 most common words in dat/latn/nwt/tot.1/raw.tlw:
2903 0.07793 et
2226 0.05975 =
1118 0.03001 in
639 0.01715 est
594 0.01595 autem
553 0.01484 qui
525 0.01409 non
386 0.01036 eum
339 0.00910 quia
305 0.00819 cum
removed 'dat/latn/nwt/tot.1/raw-trunc-wds-summary.tex'
removed 'exp/latn/nwt/tot.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/latn/nwt/tot.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:23 by tex-make-sample-summary.sh
% Token and word counts for latn/nwt/tot.1/raw.wfr
%
\def\latnnwttrunctotPBrawTks{37253}
\def\latnnwttrunctotPBrawTksPct{100.0}
\def\latnnwttrunctotPBrawWds{5741}
\def\latnnwttrunctotPBrawWdsPct{15.4}
copied '/tmp/580361.file' -> 'exp/latn/nwt/tot.1/raw-trunc-wds-summary.tex'
removed '/tmp/580361.file'
creating running text file dat/latn/nwt/tot.1/gud.wdf
sample:
liber generationis iesu christi filii david filii abraham abraham genuit
isaac isaac autem genuit iacob iacob autem genuit iudam et fratres eius
iudas autem genuit phares et zara de thamar phares autem genuit esrom
esrom autem genuit aram aram autem genuit aminadab aminadab autem genuit
naasson naasson autem genuit salmon salmon autem genuit booz de rachab
booz autem genuit obed ex ruth obed autem genuit iesse iesse autem
genuit david regem david autem rex genuit salomonem ex ea quae fuit
uriae salomon autem genuit roboam roboam autem genuit abiam abia autem
genuit asa asa autem genuit iosaphat iosaphat autem genuit ioram ioram
autem genuit oziam ozias autem genuit ioatham ioatham autem genuit achaz
achaz autem genuit ezechiam ezechias autem genuit manassen manasses
autem genuit amon amon autem genuit iosiam iosias autem genuit iechoniam
et fratres eius in transmigratione babylonis et post transmigrationem
babylonis iechonias genuit salathihel salathihel autem genuit zorobabel
zorobabel autem genuit abiud abiud autem genuit eliachim eliachim autem
genuit azor azor autem genuit saddoc saddoc autem genuit achim achim
autem genuit eliud eliud autem genuit eleazar eleazar autem genuit
matthan matthan autem genuit iacob iacob autem genuit ioseph virum
mariae de qua natus est iesus qui vocatur christus omnes ergo
generationes ab abraham usque ad david generationes quattuordecim et a
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
habetis vobiscum me autem non semper habetis cognovit ergo turba multa
ex iudaeis quia illic est et venerunt non propter iesum tantum sed ut
lazarum viderent
removed 'dat/latn/nwt/tot.1/gud.wfr'
creating the word frequency file dat/latn/nwt/tot.1/gud.wfr
the 10 most common words in dat/latn/nwt/tot.1/gud.tlw:
2903 0.08288 et
1118 0.03192 in
639 0.01824 est
594 0.01696 autem
553 0.01579 qui
525 0.01499 non
386 0.01102 eum
339 0.00968 quia
305 0.00871 cum
298 0.00851 ad
removed 'dat/latn/nwt/tot.1/gud-trunc-wds-summary.tex'
removed 'exp/latn/nwt/tot.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/latn/nwt/tot.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:23 by tex-make-sample-summary.sh
% Token and word counts for latn/nwt/tot.1/gud.wfr
%
\def\latnnwttrunctotPBgudTks{35027}
\def\latnnwttrunctotPBgudTksPct{94.0}
\def\latnnwttrunctotPBgudWds{5740}
\def\latnnwttrunctotPBgudWdsPct{15.4}
copied '/tmp/580405.file' -> 'exp/latn/nwt/tot.1/gud-trunc-wds-summary.tex'
removed '/tmp/580405.file'
creating running text file dat/latn/nwt/tot.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/latn/nwt/tot.1/bad.wfr'
creating the word frequency file dat/latn/nwt/tot.1/bad.wfr
the 10 most common words in dat/latn/nwt/tot.1/bad.tlw:
2226 1.00000 =
removed 'dat/latn/nwt/tot.1/bad-trunc-wds-summary.tex'
removed 'exp/latn/nwt/tot.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/latn/nwt/tot.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:23 by tex-make-sample-summary.sh
% Token and word counts for latn/nwt/tot.1/bad.wfr
%
\def\latnnwttrunctotPBbadTks{2226}
\def\latnnwttrunctotPBbadTksPct{6.0}
\def\latnnwttrunctotPBbadWds{1}
\def\latnnwttrunctotPBbadWdsPct{0.0}
copied '/tmp/580449.file' -> 'exp/latn/nwt/tot.1/bad-trunc-wds-summary.tex'
removed '/tmp/580449.file'
lines words bytes file
------- ------- --------- ------------
3914 11742 95586 dat/latn/nwt/mat.1/raw.wfr
2916 8748 71527 dat/latn/nwt/mrk.1/raw.wfr
4407 13221 108191 dat/latn/nwt/luk.1/raw.wfr
2524 7572 61121 dat/latn/nwt/joh.1/raw.wfr
5741 17223 141674 dat/latn/nwt/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
3911 11733 95512 dat/latn/nwt/mat.1/gud.wfr
2913 8739 71452 dat/latn/nwt/mrk.1/gud.wfr
4406 13218 108173 dat/latn/nwt/luk.1/gud.wfr
2523 7569 61103 dat/latn/nwt/joh.1/gud.wfr
5740 17220 141656 dat/latn/nwt/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
3 9 74 dat/latn/nwt/mat.1/bad.wfr
3 9 75 dat/latn/nwt/mrk.1/bad.wfr
1 3 18 dat/latn/nwt/luk.1/bad.wfr
1 3 18 dat/latn/nwt/joh.1/bad.wfr
1 3 18 dat/latn/nwt/tot.1/bad.wfr
mat.1 raw = 17502 gud = 16431 bad = 1071
mrk.1 raw = 10959 gud = 10280 bad = 679
luk.1 raw = 19155 gud = 18004 bad = 1151
joh.1 raw = 14905 gud = 14026 bad = 879
tot.1 raw = 37253 gud = 35027 bad = 2226
=== creating the derived word files dat/latn/ock/*/{raw,gud,bad}.{tlw,wdf,wfr} (trunc) ===
... creating word files dat/latn/ock/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
35389 dat/latn/ock/tot.1/trunc.tlw
removed 'dat/latn/ock/tot.1/raw.tlw'
removed 'dat/latn/ock/tot.1/gud.tlw'
removed 'dat/latn/ock/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/latn/ock/tot.1/raw.wdf
sample:
claves regni celorum esse datas a christo romano pontifici id est beato
petro christianorum non ambigit ut estimo multitudo quare non dubitat
quin sit a christo aliqua concessa potestas plures eciam auctoritates
sanctorum patrum videntur asserere quod aliquam ex humana ordinacione
acceperit potestatem de quarum utraque si utramque habeat interrogabo
quamplura quam videlicet et quo iure divino scilicet an humano habeat
potestatem super spiritualia et ecclesiasticas personas quam et quo iure
super laicos in spiritualibus quam et quo iure super res et iura
temporalia que ad solam romanam spectant ecclesiam quam et quo iure
super res et temporalia iura que ad alios clericos pertinere noscuntur
quam et quo iure super personas res et iura temporalia fidelium laicorum
quam et quo iure super res infidelium et eciam personas ipsorum postea
autem nonnulla similia de potestate cleri perscrutare propono ante omnia
autem interrogare decrevi an potestas pape ad omnia que non sunt contra
legem divinam neque contra ius nature se extendat hec enim interrogacio
videtur comprehendere omnia predicta de potestate pape et forte ex
sentenciis et opinionibus circa ipsam quas recitare studebis dabitur
michi occasio de singulis in speciali querendi circa hanc
interrogacionem diverse et adverse inveniuntur sentencie una est quod
papa tam in temporalibus quam in spiritualibus talem ex ordinacione
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
praelato pessimo obedire et ideo licet principatus unius summi
pontificis posset per malitiam eius transmutari in pessimum quia potest
effici tyrannus tamen propter bonum obedientiae
removed 'dat/latn/ock/tot.1/raw.wfr'
creating the word frequency file dat/latn/ock/tot.1/raw.wfr
the 10 most common words in dat/latn/ock/tot.1/raw.tlw:
1518 0.04289 et
755 0.02133 in
708 0.02001 non
666 0.01882 quod
587 0.01659 est
417 0.01178 ad
313 0.00884 ut
282 0.00797 de
278 0.00786 vel
271 0.00766 quam
removed 'dat/latn/ock/tot.1/raw-trunc-wds-summary.tex'
removed 'exp/latn/ock/tot.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/latn/ock/tot.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:23 by tex-make-sample-summary.sh
% Token and word counts for latn/ock/tot.1/raw.wfr
%
\def\latnocktrunctotPBrawTks{35389}
\def\latnocktrunctotPBrawTksPct{100.0}
\def\latnocktrunctotPBrawWds{5643}
\def\latnocktrunctotPBrawWdsPct{15.9}
copied '/tmp/580604.file' -> 'exp/latn/ock/tot.1/raw-trunc-wds-summary.tex'
removed '/tmp/580604.file'
creating running text file dat/latn/ock/tot.1/gud.wdf
sample:
claves regni celorum esse datas a christo romano pontifici id est beato
petro christianorum non ambigit ut estimo multitudo quare non dubitat
quin sit a christo aliqua concessa potestas plures eciam auctoritates
sanctorum patrum videntur asserere quod aliquam ex humana ordinacione
acceperit potestatem de quarum utraque si utramque habeat interrogabo
quamplura quam videlicet et quo iure divino scilicet an humano habeat
potestatem super spiritualia et ecclesiasticas personas quam et quo iure
super laicos in spiritualibus quam et quo iure super res et iura
temporalia que ad solam romanam spectant ecclesiam quam et quo iure
super res et temporalia iura que ad alios clericos pertinere noscuntur
quam et quo iure super personas res et iura temporalia fidelium laicorum
quam et quo iure super res infidelium et eciam personas ipsorum postea
autem nonnulla similia de potestate cleri perscrutare propono ante omnia
autem interrogare decrevi an potestas pape ad omnia que non sunt contra
legem divinam neque contra ius nature se extendat hec enim interrogacio
videtur comprehendere omnia predicta de potestate pape et forte ex
sentenciis et opinionibus circa ipsam quas recitare studebis dabitur
michi occasio de singulis in speciali querendi circa hanc
interrogacionem diverse et adverse inveniuntur sentencie una est quod
papa tam in temporalibus quam in spiritualibus talem ex ordinacione
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
propter praeceptum dei praelato pessimo obedire et ideo licet
principatus unius summi pontificis posset per malitiam eius transmutari
in pessimum quia potest effici tyrannus tamen propter bonum obedientiae
removed 'dat/latn/ock/tot.1/gud.wfr'
creating the word frequency file dat/latn/ock/tot.1/gud.wfr
the 10 most common words in dat/latn/ock/tot.1/gud.tlw:
1518 0.04334 et
755 0.02155 in
708 0.02021 non
666 0.01901 quod
587 0.01676 est
417 0.01191 ad
313 0.00894 ut
282 0.00805 de
278 0.00794 vel
271 0.00774 quam
removed 'dat/latn/ock/tot.1/gud-trunc-wds-summary.tex'
removed 'exp/latn/ock/tot.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/latn/ock/tot.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:23 by tex-make-sample-summary.sh
% Token and word counts for latn/ock/tot.1/gud.wfr
%
\def\latnocktrunctotPBgudTks{35027}
\def\latnocktrunctotPBgudTksPct{99.0}
\def\latnocktrunctotPBgudWds{5589}
\def\latnocktrunctotPBgudWdsPct{15.8}
copied '/tmp/580648.file' -> 'exp/latn/ock/tot.1/gud-trunc-wds-summary.tex'
removed '/tmp/580648.file'
creating running text file dat/latn/ock/tot.1/bad.wdf
sample:
16 19 1 1 14 3 1 1 3 3 5 3 6 1 6 2 1 2 1 2 31 1 2 5 55 12 19 19 24 1 24
1 24 1 19 2 6 3us 22 22 1 9 3 17 4 16 50 27 2 25 1 5 15 6 11 3 40 5 4 25
1 15 3us 9us 17 4 2 3us 1 5 15 12 4 2 3 2 5 15 4 15 16 12 1 15 15 3 19 2
3us 6 5 2 8 10 96 12 1 54 1 2 12 2 17 4 15 6 2 2 88 21 5 1 16 1 88 21 3~
6 20 23 9 10 22 3 11 1 5 3us 1 96 11 16 1 17 9 3 2 6 17 2 6 21 17 3 6 2
6 3us 19 25 2 1 93 95 5 18~ 21 24 1 2 7 21 9 3 24 1 5 10 3 11 24 1 3us 1
9 1 12 1 10 11 21 17 4~ 18 1 6 1 12 1 1 14 7 1 15 7 23 5 8~ 6 13 15 13
14 15 20 28 29 2 8 14~ 15 16 8 3 5 3 10 2~ 10 3 3 3 1 12 63 8 1 11 3 1 1
63 13 10 2 8 c~5 10 2 11 2 7 1 3 12 13 12 12 1 1 13~ 16 13 13 2 24 1 8 9
2 15 15 8 5 18 81 45 1 65 1 2 3 31 9 40 4 3 40 23 4 16 1 31 19 4 3 2 61
23 12 6 2 29 21 1 1 24 2 10 21 24 1 24 1 25 1 22 1 7 1 1 10 20 5 23 1 5
5 22 1 10 22 5 19 10 25 1 23 1 20 1 25 1 25 15 3 45 1 1 7 1 7 1 24 1 25
1 26 6 35 4 4 21 1 2 7 1 7 1 3 20 15
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
23 12 6 2 29 21 1 1 24 2 10 21 24 1 24 1 25 1 22 1 7 1 1 10 20 5 23 1 5
5 22 1 10 22 5 19 10 25 1 23 1 20 1 25 1 25 15 3 45 1 1 7 1 7 1 24 1 25
1 26 6 35 4 4 21 1 2 7 1 7 1 3 20 15
removed 'dat/latn/ock/tot.1/bad.wfr'
creating the word frequency file dat/latn/ock/tot.1/bad.wfr
the 10 most common words in dat/latn/ock/tot.1/bad.tlw:
69 0.19061 1
31 0.08564 2
25 0.06906 3
18 0.04972 5
16 0.04420 15
15 0.04144 6
12 0.03315 10
12 0.03315 12
11 0.03039 24
11 0.03039 4
removed 'dat/latn/ock/tot.1/bad-trunc-wds-summary.tex'
removed 'exp/latn/ock/tot.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/latn/ock/tot.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:23 by tex-make-sample-summary.sh
% Token and word counts for latn/ock/tot.1/bad.wfr
%
\def\latnocktrunctotPBbadTks{362}
\def\latnocktrunctotPBbadTksPct{1.0}
\def\latnocktrunctotPBbadWds{54}
\def\latnocktrunctotPBbadWdsPct{0.2}
copied '/tmp/580692.file' -> 'exp/latn/ock/tot.1/bad-trunc-wds-summary.tex'
removed '/tmp/580692.file'
lines words bytes file
------- ------- --------- ------------
5643 16929 142094 dat/latn/ock/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
5589 16767 141071 dat/latn/ock/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
54 162 1023 dat/latn/ock/tot.1/bad.wfr
tot.1 raw = 35389 gud = 35027 bad = 362
=== creating the derived word files dat/grek/nwt/*/{raw,gud,bad}.{tlw,wdf,wfr} (trunc) ===
... creating word files dat/grek/nwt/mat.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
19816 dat/grek/nwt/mat.1/trunc.tlw
removed 'dat/grek/nwt/mat.1/raw.tlw'
removed 'dat/grek/nwt/mat.1/gud.tlw'
removed 'dat/grek/nwt/mat.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/grek/nwt/mat.1/raw.wdf
sample:
biblos geneseôs iësou qristou uiou dauid uiou abraam =
abraam egennësen ton isaak isaak de egennësen ton iakôb iakôb de
egennësen ton ioudan kai tous adelfous autou =
ioudas de egennësen ton fares kai ton zara ek tës ðamar fares de
egennësen ton esrôm esrôm de egennësen ton aram =
aram de egennësen ton aminadab aminadab de egennësen ton naassôn naassôn
de egennësen ton salmôn =
salmôn de egennësen ton booz ek tës raqab booz de egennësen ton ôbëd ek
tës rouð ôbëd de egennësen ton iessai =
iessai de egennësen ton dauid ton basilea dauid de o basileus egennësen
ton solomôna ek tës tou ouriou =
solomôn de egennësen ton roboam roboam de egennësen ton abia abia de
egennësen ton asa =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
didaskontes autous tërein panta osa eneteilamën umin kai idou egô með
umôn eimi pasas tas ëmeras eôs tës sunteleias tou aiônos amën =
removed 'dat/grek/nwt/mat.1/raw.wfr'
creating the word frequency file dat/grek/nwt/mat.1/raw.wfr
the 10 most common words in dat/grek/nwt/mat.1/raw.tlw:
1220 0.06157 kai
1071 0.05405 =
549 0.02770 o
485 0.02448 de
311 0.01569 en
305 0.01539 tou
278 0.01403 autou
240 0.01211 eis
235 0.01186 to
231 0.01166 oi
removed 'dat/grek/nwt/mat.1/raw-trunc-wds-summary.tex'
removed 'exp/grek/nwt/mat.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/grek/nwt/mat.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:23 by tex-make-sample-summary.sh
% Token and word counts for grek/nwt/mat.1/raw.wfr
%
\def\greknwttruncmatPBrawTks{19816}
\def\greknwttruncmatPBrawTksPct{100.0}
\def\greknwttruncmatPBrawWds{3959}
\def\greknwttruncmatPBrawWdsPct{20.0}
copied '/tmp/580787.file' -> 'exp/grek/nwt/mat.1/raw-trunc-wds-summary.tex'
removed '/tmp/580787.file'
creating running text file dat/grek/nwt/mat.1/gud.wdf
sample:
biblos geneseôs iësou qristou uiou dauid uiou abraam abraam egennësen
ton isaak isaak de egennësen ton iakôb iakôb de egennësen ton ioudan kai
tous adelfous autou ioudas de egennësen ton fares kai ton zara ek tës
ðamar fares de egennësen ton esrôm esrôm de egennësen ton aram aram de
egennësen ton aminadab aminadab de egennësen ton naassôn naassôn de
egennësen ton salmôn salmôn de egennësen ton booz ek tës raqab booz de
egennësen ton ôbëd ek tës rouð ôbëd de egennësen ton iessai iessai de
egennësen ton dauid ton basilea dauid de o basileus egennësen ton
solomôna ek tës tou ouriou solomôn de egennësen ton roboam roboam de
egennësen ton abia abia de egennësen ton asa asa de egennësen ton
iôsafat iôsafat de egennësen ton iôram iôram de egennësen ton ozian
ozias de egennësen ton iôaðam iôaðam de egennësen ton aqaz aqaz de
egennësen ton ezekian ezekias de egennësen ton manassë manassës de
egennësen ton amôn amôn de egennësen ton iôsian iôsias de egennësen ton
ieqonian kai tous adelfous autou epi tës metoikesias babulônos meta de
tën metoikesian babulônos ieqonias egennësen ton salaðiël salaðiël de
egennësen ton zorobabel zorobabel de egennësen ton abioud abioud de
egennësen ton eliakeim eliakeim de egennësen ton azôr azôr de egennësen
ton sadôk sadôk de egennësen ton aqeim aqeim de egennësen ton elioud
elioud de egennësen ton eleazar eleazar de egennësen ton matðan matðan
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
baptizontes autous eis to onoma tou patros kai tou uiou kai tou agiou
pneumatos didaskontes autous tërein panta osa eneteilamën umin kai idou
egô með umôn eimi pasas tas ëmeras eôs tës sunteleias tou aiônos amën
removed 'dat/grek/nwt/mat.1/gud.wfr'
creating the word frequency file dat/grek/nwt/mat.1/gud.wfr
the 10 most common words in dat/grek/nwt/mat.1/gud.tlw:
1220 0.06508 kai
549 0.02929 o
485 0.02587 de
311 0.01659 en
305 0.01627 tou
278 0.01483 autou
240 0.01280 eis
235 0.01254 to
231 0.01232 oi
221 0.01179 ton
removed 'dat/grek/nwt/mat.1/gud-trunc-wds-summary.tex'
removed 'exp/grek/nwt/mat.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/grek/nwt/mat.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:23 by tex-make-sample-summary.sh
% Token and word counts for grek/nwt/mat.1/gud.wfr
%
\def\greknwttruncmatPBgudTks{18745}
\def\greknwttruncmatPBgudTksPct{94.6}
\def\greknwttruncmatPBgudWds{3958}
\def\greknwttruncmatPBgudWdsPct{20.0}
copied '/tmp/580831.file' -> 'exp/grek/nwt/mat.1/gud-trunc-wds-summary.tex'
removed '/tmp/580831.file'
creating running text file dat/grek/nwt/mat.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/grek/nwt/mat.1/bad.wfr'
creating the word frequency file dat/grek/nwt/mat.1/bad.wfr
the 10 most common words in dat/grek/nwt/mat.1/bad.tlw:
1071 1.00000 =
removed 'dat/grek/nwt/mat.1/bad-trunc-wds-summary.tex'
removed 'exp/grek/nwt/mat.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/grek/nwt/mat.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:24 by tex-make-sample-summary.sh
% Token and word counts for grek/nwt/mat.1/bad.wfr
%
\def\greknwttruncmatPBbadTks{1071}
\def\greknwttruncmatPBbadTksPct{5.4}
\def\greknwttruncmatPBbadWds{1}
\def\greknwttruncmatPBbadWdsPct{0.0}
copied '/tmp/580875.file' -> 'exp/grek/nwt/mat.1/bad-trunc-wds-summary.tex'
removed '/tmp/580875.file'
... creating word files dat/grek/nwt/mrk.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
12310 dat/grek/nwt/mrk.1/trunc.tlw
removed 'dat/grek/nwt/mrk.1/raw.tlw'
removed 'dat/grek/nwt/mrk.1/gud.tlw'
removed 'dat/grek/nwt/mrk.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/grek/nwt/mrk.1/raw.wdf
sample:
arqë tou euaggeliou iësou qristou uiou tou ðeou =
ôs gegraptai en tois profëtais idou egô apostellô ton aggelon mou pro
prosôpou sou os kataskeuasei tën odon sou emprosðen sou =
fônë boôntos en të erëmô etoimasate tën odon kuriou euðeias poieite tas
tribous autou =
egeneto iôannës baptizôn en të erëmô kai kërussôn baptisma metanoias eis
afesin amartiôn =
kai exeporeueto pros auton pasa ë ioudaia qôra kai oi ierosolumitai kai
ebaptizonto pantes en tô iordanë potamô up autou exomologoumenoi tas
amartias autôn =
ën de o iôannës endedumenos triqas kamëlou kai zônën dermatinën peri tën
osfun autou kai esðiôn akridas kai meli agrion =
kai ekërussen legôn erqetai o isquroteros mou opisô mou ou ouk eimi
ikanos kuįas lusai ton imanta tôn upodëmatôn autou =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
ekeinoi de exelðontes ekëruxan pantaqou tou kuriou sunergountos kai ton
logon bebaiountos dia tôn epakolouðountôn sëmeiôn amën =
removed 'dat/grek/nwt/mrk.1/raw.wfr'
creating the word frequency file dat/grek/nwt/mrk.1/raw.wfr
the 10 most common words in dat/grek/nwt/mrk.1/raw.tlw:
1094 0.08887 kai
678 0.05508 =
289 0.02348 o
195 0.01584 de
187 0.01519 eis
186 0.01511 auton
177 0.01438 autou
151 0.01227 en
146 0.01186 ton
140 0.01137 tou
removed 'dat/grek/nwt/mrk.1/raw-trunc-wds-summary.tex'
removed 'exp/grek/nwt/mrk.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/grek/nwt/mrk.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:24 by tex-make-sample-summary.sh
% Token and word counts for grek/nwt/mrk.1/raw.wfr
%
\def\greknwttruncmrkPBrawTks{12310}
\def\greknwttruncmrkPBrawTksPct{100.0}
\def\greknwttruncmrkPBrawWds{2899}
\def\greknwttruncmrkPBrawWdsPct{23.5}
copied '/tmp/580929.file' -> 'exp/grek/nwt/mrk.1/raw-trunc-wds-summary.tex'
removed '/tmp/580929.file'
creating running text file dat/grek/nwt/mrk.1/gud.wdf
sample:
arqë tou euaggeliou iësou qristou uiou tou ðeou ôs gegraptai en tois
profëtais idou egô apostellô ton aggelon mou pro prosôpou sou os
kataskeuasei tën odon sou emprosðen sou fônë boôntos en të erëmô
etoimasate tën odon kuriou euðeias poieite tas tribous autou egeneto
iôannës baptizôn en të erëmô kai kërussôn baptisma metanoias eis afesin
amartiôn kai exeporeueto pros auton pasa ë ioudaia qôra kai oi
ierosolumitai kai ebaptizonto pantes en tô iordanë potamô up autou
exomologoumenoi tas amartias autôn ën de o iôannës endedumenos triqas
kamëlou kai zônën dermatinën peri tën osfun autou kai esðiôn akridas kai
meli agrion kai ekërussen legôn erqetai o isquroteros mou opisô mou ou
ouk eimi ikanos kuįas lusai ton imanta tôn upodëmatôn autou egô men
ebaptisa umas en udati autos de baptisei umas en pneumati agiô kai
egeneto en ekeinais tais ëmerais ëlðen iësous apo nazaret tës galilaias
kai ebaptisðë upo iôannou eis ton iordanën kai euðeôs anabainôn apo tou
udatos eiden sqizomenous tous ouranous kai to pneuma ôsei peristeran
katabainon ep auton kai fônë egeneto ek tôn ouranôn su ei o uios mou o
agapëtos en ô eudokësa kai euðus to pneuma auton ekballei eis tën erëmon
kai ën ekei en të erëmô ëmeras tessarakonta peirazomenos upo tou satana
kai ën meta tôn ðëriôn kai oi aggeloi diëkonoun autô meta de to
paradoðënai ton iôannën ëlðen o iësous eis tën galilaian kërussôn to
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
ek dexiôn tou ðeou ekeinoi de exelðontes ekëruxan pantaqou tou kuriou
sunergountos kai ton logon bebaiountos dia tôn epakolouðountôn sëmeiôn
amën
removed 'dat/grek/nwt/mrk.1/gud.wfr'
creating the word frequency file dat/grek/nwt/mrk.1/gud.wfr
the 10 most common words in dat/grek/nwt/mrk.1/gud.tlw:
1094 0.09405 kai
289 0.02485 o
195 0.01676 de
187 0.01608 eis
186 0.01599 auton
177 0.01522 autou
151 0.01298 en
146 0.01255 ton
140 0.01204 tou
137 0.01178 to
removed 'dat/grek/nwt/mrk.1/gud-trunc-wds-summary.tex'
removed 'exp/grek/nwt/mrk.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/grek/nwt/mrk.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:24 by tex-make-sample-summary.sh
% Token and word counts for grek/nwt/mrk.1/gud.wfr
%
\def\greknwttruncmrkPBgudTks{11632}
\def\greknwttruncmrkPBgudTksPct{94.5}
\def\greknwttruncmrkPBgudWds{2898}
\def\greknwttruncmrkPBgudWdsPct{23.5}
copied '/tmp/580973.file' -> 'exp/grek/nwt/mrk.1/gud-trunc-wds-summary.tex'
removed '/tmp/580973.file'
creating running text file dat/grek/nwt/mrk.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/grek/nwt/mrk.1/bad.wfr'
creating the word frequency file dat/grek/nwt/mrk.1/bad.wfr
the 10 most common words in dat/grek/nwt/mrk.1/bad.tlw:
678 1.00000 =
removed 'dat/grek/nwt/mrk.1/bad-trunc-wds-summary.tex'
removed 'exp/grek/nwt/mrk.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/grek/nwt/mrk.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:24 by tex-make-sample-summary.sh
% Token and word counts for grek/nwt/mrk.1/bad.wfr
%
\def\greknwttruncmrkPBbadTks{678}
\def\greknwttruncmrkPBbadTksPct{5.5}
\def\greknwttruncmrkPBbadWds{1}
\def\greknwttruncmrkPBbadWdsPct{0.0}
copied '/tmp/581017.file' -> 'exp/grek/nwt/mrk.1/bad-trunc-wds-summary.tex'
removed '/tmp/581017.file'
... creating word files dat/grek/nwt/luk.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
21037 dat/grek/nwt/luk.1/trunc.tlw
removed 'dat/grek/nwt/luk.1/raw.tlw'
removed 'dat/grek/nwt/luk.1/gud.tlw'
removed 'dat/grek/nwt/luk.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/grek/nwt/luk.1/raw.wdf
sample:
epeidëper polloi epeqeirësan anataxasðai diëgësin peri tôn
peplëroforëmenôn en ëmin pragmatôn =
kaðôs paredosan ëmin oi ap arqës autoptai kai upëretai genomenoi tou
logou =
edoxen kamoi parëkolouðëkoti anôðen pasin akribôs kaðexës soi graįai
kratiste ðeofile =
ina epignôs peri ôn katëqëðës logôn tën asfaleian =
egeneto en tais ëmerais ërôdou tou basileôs tës ioudaias iereus tis
onomati zaqarias ex efëmerias abia kai ë gunë autou ek tôn ðugaterôn
aarôn kai to onoma autës elisabet =
ësan de dikaioi amfoteroi enôpion tou ðeou poreuomenoi en pasais tais
entolais kai dikaiômasin tou kuriou amemptoi =
kai ouk ën autois teknon kaðoti ë elisabet ën steira kai amfoteroi
probebëkotes en tais ëmerais autôn ësan =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
kai ësan dia pantos en tô ierô ainountes kai eulogountes ton ðeon amën =
removed 'dat/grek/nwt/luk.1/raw.wfr'
creating the word frequency file dat/grek/nwt/luk.1/raw.wfr
the 10 most common words in dat/grek/nwt/luk.1/raw.tlw:
1524 0.07244 kai
1150 0.05467 =
538 0.02557 de
447 0.02125 o
391 0.01859 tou
372 0.01768 en
274 0.01302 autou
242 0.01150 eis
237 0.01127 eipen
229 0.01089 to
removed 'dat/grek/nwt/luk.1/raw-trunc-wds-summary.tex'
removed 'exp/grek/nwt/luk.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/grek/nwt/luk.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:24 by tex-make-sample-summary.sh
% Token and word counts for grek/nwt/luk.1/raw.wfr
%
\def\greknwttrunclukPBrawTks{21037}
\def\greknwttrunclukPBrawTksPct{100.0}
\def\greknwttrunclukPBrawWds{4610}
\def\greknwttrunclukPBrawWdsPct{21.9}
copied '/tmp/581071.file' -> 'exp/grek/nwt/luk.1/raw-trunc-wds-summary.tex'
removed '/tmp/581071.file'
creating running text file dat/grek/nwt/luk.1/gud.wdf
sample:
epeidëper polloi epeqeirësan anataxasðai diëgësin peri tôn
peplëroforëmenôn en ëmin pragmatôn kaðôs paredosan ëmin oi ap arqës
autoptai kai upëretai genomenoi tou logou edoxen kamoi parëkolouðëkoti
anôðen pasin akribôs kaðexës soi graįai kratiste ðeofile ina epignôs
peri ôn katëqëðës logôn tën asfaleian egeneto en tais ëmerais ërôdou tou
basileôs tës ioudaias iereus tis onomati zaqarias ex efëmerias abia kai
ë gunë autou ek tôn ðugaterôn aarôn kai to onoma autës elisabet ësan de
dikaioi amfoteroi enôpion tou ðeou poreuomenoi en pasais tais entolais
kai dikaiômasin tou kuriou amemptoi kai ouk ën autois teknon kaðoti ë
elisabet ën steira kai amfoteroi probebëkotes en tais ëmerais autôn ësan
egeneto de en tô ierateuein auton en të taxei tës efëmerias autou enanti
tou ðeou kata to eðos tës ierateias elaqen tou ðumiasai eiselðôn eis ton
naon tou kuriou kai pan to plëðos ën tou laou proseuqomenon exô të ôra
tou ðumiamatos ôfðë de autô aggelos kuriou estôs ek dexiôn tou
ðusiastëriou tou ðumiamatos kai etaraqðë zaqarias idôn kai fobos
epepesen ep auton eipen de pros auton o aggelos më fobou zaqaria dioti
eisëkousðë ë deësis sou kai ë gunë sou elisabet gennësei uion soi kai
kaleseis to onoma autou iôannën kai estai qara soi kai agalliasis kai
polloi epi të gennësei autou qarësontai estai gar megas enôpion tou
kuriou kai oinon kai sikera ou më pië kai pneumatos agiou plësðësetai
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
auton autous diestë ap autôn kai anefereto eis ton ouranon kai autoi
proskunësantes auton upestreįan eis ierousalëm meta qaras megalës kai
ësan dia pantos en tô ierô ainountes kai eulogountes ton ðeon amën
removed 'dat/grek/nwt/luk.1/gud.wfr'
creating the word frequency file dat/grek/nwt/luk.1/gud.wfr
the 10 most common words in dat/grek/nwt/luk.1/gud.tlw:
1524 0.07663 kai
538 0.02705 de
447 0.02248 o
391 0.01966 tou
372 0.01871 en
274 0.01378 autou
242 0.01217 eis
237 0.01192 eipen
229 0.01152 to
220 0.01106 ton
removed 'dat/grek/nwt/luk.1/gud-trunc-wds-summary.tex'
removed 'exp/grek/nwt/luk.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/grek/nwt/luk.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:24 by tex-make-sample-summary.sh
% Token and word counts for grek/nwt/luk.1/gud.wfr
%
\def\greknwttrunclukPBgudTks{19887}
\def\greknwttrunclukPBgudTksPct{94.5}
\def\greknwttrunclukPBgudWds{4609}
\def\greknwttrunclukPBgudWdsPct{21.9}
copied '/tmp/581115.file' -> 'exp/grek/nwt/luk.1/gud-trunc-wds-summary.tex'
removed '/tmp/581115.file'
creating running text file dat/grek/nwt/luk.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/grek/nwt/luk.1/bad.wfr'
creating the word frequency file dat/grek/nwt/luk.1/bad.wfr
the 10 most common words in dat/grek/nwt/luk.1/bad.tlw:
1150 1.00000 =
removed 'dat/grek/nwt/luk.1/bad-trunc-wds-summary.tex'
removed 'exp/grek/nwt/luk.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/grek/nwt/luk.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:24 by tex-make-sample-summary.sh
% Token and word counts for grek/nwt/luk.1/bad.wfr
%
\def\greknwttrunclukPBbadTks{1150}
\def\greknwttrunclukPBbadTksPct{5.5}
\def\greknwttrunclukPBbadWds{1}
\def\greknwttrunclukPBbadWdsPct{0.0}
copied '/tmp/581159.file' -> 'exp/grek/nwt/luk.1/bad-trunc-wds-summary.tex'
removed '/tmp/581159.file'
... creating word files dat/grek/nwt/joh.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
16798 dat/grek/nwt/joh.1/trunc.tlw
removed 'dat/grek/nwt/joh.1/raw.tlw'
removed 'dat/grek/nwt/joh.1/gud.tlw'
removed 'dat/grek/nwt/joh.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/grek/nwt/joh.1/raw.wdf
sample:
en arqë ën o logos kai o logos ën pros ton ðeon kai ðeos ën o logos =
outos ën en arqë pros ton ðeon =
panta di autou egeneto kai qôris autou egeneto oude en o gegonen =
en autô zôë ën kai ë zôë ën to fôs tôn anðrôpôn =
kai to fôs en të skotia fainei kai ë skotia auto ou katelaben =
egeneto anðrôpos apestalmenos para ðeou onoma autô iôannës =
outos ëlðen eis marturian ina marturësë peri tou fôtos ina pantes
pisteusôsin di autou =
ouk ën ekeinos to fôs all ina marturësë peri tou fôtos =
ën to fôs to alëðinon o fôtizei panta anðrôpon erqomenon eis ton kosmon
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
estin de kai alla polla osa epoiësen o iësous atina ean grafëtai kað en
oude auton oimai ton kosmon qôrësai ta grafomena biblia amën =
removed 'dat/grek/nwt/joh.1/raw.wfr'
creating the word frequency file dat/grek/nwt/joh.1/raw.wfr
the 10 most common words in dat/grek/nwt/joh.1/raw.tlw:
879 0.05233 =
867 0.05161 kai
647 0.03852 o
267 0.01589 oti
248 0.01476 ton
247 0.01470 tou
239 0.01423 en
231 0.01375 de
208 0.01238 eis
205 0.01220 iësous
removed 'dat/grek/nwt/joh.1/raw-trunc-wds-summary.tex'
removed 'exp/grek/nwt/joh.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/grek/nwt/joh.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:24 by tex-make-sample-summary.sh
% Token and word counts for grek/nwt/joh.1/raw.wfr
%
\def\greknwttruncjohPBrawTks{16798}
\def\greknwttruncjohPBrawTksPct{100.0}
\def\greknwttruncjohPBrawWds{2587}
\def\greknwttruncjohPBrawWdsPct{15.4}
copied '/tmp/581213.file' -> 'exp/grek/nwt/joh.1/raw-trunc-wds-summary.tex'
removed '/tmp/581213.file'
creating running text file dat/grek/nwt/joh.1/gud.wdf
sample:
en arqë ën o logos kai o logos ën pros ton ðeon kai ðeos ën o logos
outos ën en arqë pros ton ðeon panta di autou egeneto kai qôris autou
egeneto oude en o gegonen en autô zôë ën kai ë zôë ën to fôs tôn
anðrôpôn kai to fôs en të skotia fainei kai ë skotia auto ou katelaben
egeneto anðrôpos apestalmenos para ðeou onoma autô iôannës outos ëlðen
eis marturian ina marturësë peri tou fôtos ina pantes pisteusôsin di
autou ouk ën ekeinos to fôs all ina marturësë peri tou fôtos ën to fôs
to alëðinon o fôtizei panta anðrôpon erqomenon eis ton kosmon en tô
kosmô ën kai o kosmos di autou egeneto kai o kosmos auton ouk egnô eis
ta idia ëlðen kai oi idioi auton ou parelabon osoi de elabon auton
edôken autois exousian tekna ðeou genesðai tois pisteuousin eis to onoma
autou oi ouk ex aimatôn oude ek ðelëmatos sarkos oude ek ðelëmatos
andros all ek ðeou egennëðësan kai o logos sarx egeneto kai eskënôsen en
ëmin kai eðeasameða tën doxan autou doxan ôs monogenous para patros
plërës qaritos kai alëðeias iôannës marturei peri autou kai kekragen
legôn outos ën on eipon o opisô mou erqomenos emprosðen mou gegonen oti
prôtos mou ën kai ek tou plërômatos autou ëmeis pantes elabomen kai
qarin anti qaritos oti o nomos dia môseôs edoðë ë qaris kai ë alëðeia
dia iësou qristou egeneto ðeon oudeis eôraken pôpote o monogenës uios o
ôn eis ton kolpon tou patros ekeinos exëgësato kai autë estin ë marturia
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
estin ë marturia autou estin de kai alla polla osa epoiësen o iësous
atina ean grafëtai kað en oude auton oimai ton kosmon qôrësai ta
grafomena biblia amën
removed 'dat/grek/nwt/joh.1/gud.wfr'
creating the word frequency file dat/grek/nwt/joh.1/gud.wfr
the 10 most common words in dat/grek/nwt/joh.1/gud.tlw:
867 0.05446 kai
647 0.04064 o
267 0.01677 oti
248 0.01558 ton
247 0.01552 tou
239 0.01501 en
231 0.01451 de
208 0.01307 eis
205 0.01288 iësous
201 0.01263 oun
removed 'dat/grek/nwt/joh.1/gud-trunc-wds-summary.tex'
removed 'exp/grek/nwt/joh.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/grek/nwt/joh.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:24 by tex-make-sample-summary.sh
% Token and word counts for grek/nwt/joh.1/gud.wfr
%
\def\greknwttruncjohPBgudTks{15919}
\def\greknwttruncjohPBgudTksPct{94.8}
\def\greknwttruncjohPBgudWds{2586}
\def\greknwttruncjohPBgudWdsPct{15.4}
copied '/tmp/581257.file' -> 'exp/grek/nwt/joh.1/gud-trunc-wds-summary.tex'
removed '/tmp/581257.file'
creating running text file dat/grek/nwt/joh.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/grek/nwt/joh.1/bad.wfr'
creating the word frequency file dat/grek/nwt/joh.1/bad.wfr
the 10 most common words in dat/grek/nwt/joh.1/bad.tlw:
879 1.00000 =
removed 'dat/grek/nwt/joh.1/bad-trunc-wds-summary.tex'
removed 'exp/grek/nwt/joh.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/grek/nwt/joh.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:24 by tex-make-sample-summary.sh
% Token and word counts for grek/nwt/joh.1/bad.wfr
%
\def\greknwttruncjohPBbadTks{879}
\def\greknwttruncjohPBbadTksPct{5.2}
\def\greknwttruncjohPBbadWds{1}
\def\greknwttruncjohPBbadWdsPct{0.0}
copied '/tmp/581301.file' -> 'exp/grek/nwt/joh.1/bad-trunc-wds-summary.tex'
removed '/tmp/581301.file'
... creating word files dat/grek/nwt/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
37003 dat/grek/nwt/tot.1/trunc.tlw
removed 'dat/grek/nwt/tot.1/raw.tlw'
removed 'dat/grek/nwt/tot.1/gud.tlw'
removed 'dat/grek/nwt/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/grek/nwt/tot.1/raw.wdf
sample:
biblos geneseôs iësou qristou uiou dauid uiou abraam =
abraam egennësen ton isaak isaak de egennësen ton iakôb iakôb de
egennësen ton ioudan kai tous adelfous autou =
ioudas de egennësen ton fares kai ton zara ek tës ðamar fares de
egennësen ton esrôm esrôm de egennësen ton aram =
aram de egennësen ton aminadab aminadab de egennësen ton naassôn naassôn
de egennësen ton salmôn =
salmôn de egennësen ton booz ek tës raqab booz de egennësen ton ôbëd ek
tës rouð ôbëd de egennësen ton iessai =
iessai de egennësen ton dauid ton basilea dauid de o basileus egennësen
ton solomôna ek tës tou ouriou =
solomôn de egennësen ton roboam roboam de egennësen ton abia abia de
egennësen ton asa =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
ën de tis asðenôn lazaros apo bëðanias ek tës kômës marias kai marðas
tës
removed 'dat/grek/nwt/tot.1/raw.wfr'
creating the word frequency file dat/grek/nwt/tot.1/raw.wfr
the 10 most common words in dat/grek/nwt/tot.1/raw.tlw:
2560 0.06918 kai
1976 0.05340 =
968 0.02616 o
714 0.01930 de
637 0.01721 tou
599 0.01619 en
543 0.01467 autou
470 0.01270 ton
464 0.01254 eis
399 0.01078 tën
removed 'dat/grek/nwt/tot.1/raw-trunc-wds-summary.tex'
removed 'exp/grek/nwt/tot.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/grek/nwt/tot.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:24 by tex-make-sample-summary.sh
% Token and word counts for grek/nwt/tot.1/raw.wfr
%
\def\greknwttrunctotPBrawTks{37003}
\def\greknwttrunctotPBrawTksPct{100.0}
\def\greknwttrunctotPBrawWds{5437}
\def\greknwttrunctotPBrawWdsPct{14.7}
copied '/tmp/581355.file' -> 'exp/grek/nwt/tot.1/raw-trunc-wds-summary.tex'
removed '/tmp/581355.file'
creating running text file dat/grek/nwt/tot.1/gud.wdf
sample:
biblos geneseôs iësou qristou uiou dauid uiou abraam abraam egennësen
ton isaak isaak de egennësen ton iakôb iakôb de egennësen ton ioudan kai
tous adelfous autou ioudas de egennësen ton fares kai ton zara ek tës
ðamar fares de egennësen ton esrôm esrôm de egennësen ton aram aram de
egennësen ton aminadab aminadab de egennësen ton naassôn naassôn de
egennësen ton salmôn salmôn de egennësen ton booz ek tës raqab booz de
egennësen ton ôbëd ek tës rouð ôbëd de egennësen ton iessai iessai de
egennësen ton dauid ton basilea dauid de o basileus egennësen ton
solomôna ek tës tou ouriou solomôn de egennësen ton roboam roboam de
egennësen ton abia abia de egennësen ton asa asa de egennësen ton
iôsafat iôsafat de egennësen ton iôram iôram de egennësen ton ozian
ozias de egennësen ton iôaðam iôaðam de egennësen ton aqaz aqaz de
egennësen ton ezekian ezekias de egennësen ton manassë manassës de
egennësen ton amôn amôn de egennësen ton iôsian iôsias de egennësen ton
ieqonian kai tous adelfous autou epi tës metoikesias babulônos meta de
tën metoikesian babulônos ieqonias egennësen ton salaðiël salaðiël de
egennësen ton zorobabel zorobabel de egennësen ton abioud abioud de
egennësen ton eliakeim eliakeim de egennësen ton azôr azôr de egennësen
ton sadôk sadôk de egennësen ton aqeim aqeim de egennësen ton elioud
elioud de egennësen ton eleazar eleazar de egennësen ton matðan matðan
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
de osa eipen iôannës peri toutou alëðë ën kai episteusan polloi ekei eis
auton ën de tis asðenôn lazaros apo bëðanias ek tës kômës marias kai
marðas tës
removed 'dat/grek/nwt/tot.1/gud.wfr'
creating the word frequency file dat/grek/nwt/tot.1/gud.wfr
the 10 most common words in dat/grek/nwt/tot.1/gud.tlw:
2560 0.07309 kai
968 0.02764 o
714 0.02038 de
637 0.01819 tou
599 0.01710 en
543 0.01550 autou
470 0.01342 ton
464 0.01325 eis
399 0.01139 tën
385 0.01099 oi
removed 'dat/grek/nwt/tot.1/gud-trunc-wds-summary.tex'
removed 'exp/grek/nwt/tot.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/grek/nwt/tot.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:24 by tex-make-sample-summary.sh
% Token and word counts for grek/nwt/tot.1/gud.wfr
%
\def\greknwttrunctotPBgudTks{35027}
\def\greknwttrunctotPBgudTksPct{94.7}
\def\greknwttrunctotPBgudWds{5436}
\def\greknwttrunctotPBgudWdsPct{14.7}
copied '/tmp/581399.file' -> 'exp/grek/nwt/tot.1/gud-trunc-wds-summary.tex'
removed '/tmp/581399.file'
creating running text file dat/grek/nwt/tot.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/grek/nwt/tot.1/bad.wfr'
creating the word frequency file dat/grek/nwt/tot.1/bad.wfr
the 10 most common words in dat/grek/nwt/tot.1/bad.tlw:
1976 1.00000 =
removed 'dat/grek/nwt/tot.1/bad-trunc-wds-summary.tex'
removed 'exp/grek/nwt/tot.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/grek/nwt/tot.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:24 by tex-make-sample-summary.sh
% Token and word counts for grek/nwt/tot.1/bad.wfr
%
\def\greknwttrunctotPBbadTks{1976}
\def\greknwttrunctotPBbadTksPct{5.3}
\def\greknwttrunctotPBbadWds{1}
\def\greknwttrunctotPBbadWdsPct{0.0}
copied '/tmp/581443.file' -> 'exp/grek/nwt/tot.1/bad-trunc-wds-summary.tex'
removed '/tmp/581443.file'
lines words bytes file
------- ------- --------- ------------
3959 11874 96879 dat/grek/nwt/mat.1/raw.wfr
2899 8694 70995 dat/grek/nwt/mrk.1/raw.wfr
4610 13827 113419 dat/grek/nwt/luk.1/raw.wfr
2587 7758 62078 dat/grek/nwt/joh.1/raw.wfr
5437 16309 133991 dat/grek/nwt/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
3958 11871 96861 dat/grek/nwt/mat.1/gud.wfr
2898 8691 70977 dat/grek/nwt/mrk.1/gud.wfr
4609 13824 113401 dat/grek/nwt/luk.1/gud.wfr
2586 7755 62060 dat/grek/nwt/joh.1/gud.wfr
5436 16306 133973 dat/grek/nwt/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
1 3 18 dat/grek/nwt/mat.1/bad.wfr
1 3 18 dat/grek/nwt/mrk.1/bad.wfr
1 3 18 dat/grek/nwt/luk.1/bad.wfr
1 3 18 dat/grek/nwt/joh.1/bad.wfr
1 3 18 dat/grek/nwt/tot.1/bad.wfr
mat.1 raw = 19816 gud = 18745 bad = 1071
mrk.1 raw = 12310 gud = 11632 bad = 678
luk.1 raw = 21037 gud = 19887 bad = 1150
joh.1 raw = 16798 gud = 15919 bad = 879
tot.1 raw = 37003 gud = 35027 bad = 1976
=== creating the derived word files dat/span/qvi/*/{raw,gud,bad}.{tlw,wdf,wfr} (trunc) ===
... creating word files dat/span/qvi/one.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
35549 dat/span/qvi/one.1/trunc.tlw
removed 'dat/span/qvi/one.1/raw.tlw'
removed 'dat/span/qvi/one.1/gud.tlw'
removed 'dat/span/qvi/one.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/span/qvi/one.1/raw.wdf
sample:
en vn lugar de la mancha de cuyo nombre no quiero acordarme no ha mucho
tiempo que viuia vn hidalgo de los de lanįa en astillero adarga antigua
rozin flaco y galgo corredor vna olla de algo mas vaca que carnero
salpicon las mas noches duelos y quebrantos los sabados lantejas los
viernes algun palomino de aņadidura los domingos consumian las tres
partes de su hazienda el resto della concluian sayo de velarte calįas de
velludo para las fiestas con sus pantuflos de lo mesmo y los dias de
entre semana se honraua con su vellori de lo mas fino =
tenia en su casa vna ama que passaua de los quarenta y vna sobrina que
no llegaua a los veynte y vn moįo de campo y plaįa que assi ensillaua el
rozin como tomaua la podadera frisaua la edad de nuestro hidalgo con los
cinquenta aņos era de complexion rezia seco de carnes enjuto de rostro
gran madrugador y amigo de la caįa quieren dezir que tenia el
sobrenombre de quixada o quesada que en esto ay alguna diferencia en los
autores que deste caso escriuen aunque por conjeturas verosimiles se
dexa entender que se llamaua quexana pero esto importa poco a nuestro
cuento basta que en la narracion del no se salga vn punto de la verdad =
es pues de saber que este sobredicho hidalgo los ratos que estaua ocioso
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
lo dize el autor desta historia que deste harriero haze particular
mencion porque le conocia muy bien y aun quieren dezir que era algo
pariente suyo fuera de que
removed 'dat/span/qvi/one.1/raw.wfr'
creating the word frequency file dat/span/qvi/one.1/raw.wfr
the 10 most common words in dat/span/qvi/one.1/raw.tlw:
1905 0.05359 que
1735 0.04881 de
1660 0.04670 y
891 0.02506 el
884 0.02487 a
866 0.02436 la
709 0.01994 en
545 0.01533 no
510 0.01435 se
500 0.01407 =
removed 'dat/span/qvi/one.1/raw-trunc-wds-summary.tex'
removed 'exp/span/qvi/one.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/span/qvi/one.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:25 by tex-make-sample-summary.sh
% Token and word counts for span/qvi/one.1/raw.wfr
%
\def\spanqvitrunconePBrawTks{35549}
\def\spanqvitrunconePBrawTksPct{100.0}
\def\spanqvitrunconePBrawWds{5467}
\def\spanqvitrunconePBrawWdsPct{15.4}
copied '/tmp/581598.file' -> 'exp/span/qvi/one.1/raw-trunc-wds-summary.tex'
removed '/tmp/581598.file'
creating running text file dat/span/qvi/one.1/gud.wdf
sample:
en vn lugar de la mancha de cuyo nombre no quiero acordarme no ha mucho
tiempo que viuia vn hidalgo de los de lanįa en astillero adarga antigua
rozin flaco y galgo corredor vna olla de algo mas vaca que carnero
salpicon las mas noches duelos y quebrantos los sabados lantejas los
viernes algun palomino de aņadidura los domingos consumian las tres
partes de su hazienda el resto della concluian sayo de velarte calįas de
velludo para las fiestas con sus pantuflos de lo mesmo y los dias de
entre semana se honraua con su vellori de lo mas fino tenia en su casa
vna ama que passaua de los quarenta y vna sobrina que no llegaua a los
veynte y vn moįo de campo y plaįa que assi ensillaua el rozin como
tomaua la podadera frisaua la edad de nuestro hidalgo con los cinquenta
aņos era de complexion rezia seco de carnes enjuto de rostro gran
madrugador y amigo de la caįa quieren dezir que tenia el sobrenombre de
quixada o quesada que en esto ay alguna diferencia en los autores que
deste caso escriuen aunque por conjeturas verosimiles se dexa entender
que se llamaua quexana pero esto importa poco a nuestro cuento basta que
en la narracion del no se salga vn punto de la verdad es pues de saber
que este sobredicho hidalgo los ratos que estaua ocioso que eran los mas
del aņo se daua a leer libros de cauallerias con tanta aficion y gusto
que oluidó casi de todo punto el exercicio de la caįa y aun la
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
segun lo dize el autor desta historia que deste harriero haze particular
mencion porque le conocia muy bien y aun quieren dezir que era algo
pariente suyo fuera de que
removed 'dat/span/qvi/one.1/gud.wfr'
creating the word frequency file dat/span/qvi/one.1/gud.wfr
the 10 most common words in dat/span/qvi/one.1/gud.tlw:
1905 0.05439 que
1735 0.04953 de
1660 0.04739 y
891 0.02544 el
884 0.02524 a
866 0.02472 la
709 0.02024 en
545 0.01556 no
510 0.01456 se
450 0.01285 los
removed 'dat/span/qvi/one.1/gud-trunc-wds-summary.tex'
removed 'exp/span/qvi/one.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/span/qvi/one.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:25 by tex-make-sample-summary.sh
% Token and word counts for span/qvi/one.1/gud.wfr
%
\def\spanqvitrunconePBgudTks{35027}
\def\spanqvitrunconePBgudTksPct{98.5}
\def\spanqvitrunconePBgudWds{5452}
\def\spanqvitrunconePBgudWdsPct{15.3}
copied '/tmp/581642.file' -> 'exp/span/qvi/one.1/gud-trunc-wds-summary.tex'
removed '/tmp/581642.file'
creating running text file dat/span/qvi/one.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
*{tantum} ..*{,} =
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/span/qvi/one.1/bad.wfr'
creating the word frequency file dat/span/qvi/one.1/bad.wfr
the 10 most common words in dat/span/qvi/one.1/bad.tlw:
500 0.95785 =
6 0.01149 ..*{=}
3 0.00575 ..*{ũ}
2 0.00383 *{`}
1 0.00192 *{/}
1 0.00192 *{=}
1 0.00192 *{antonio}
1 0.00192 *{cancion}
1 0.00192 *{nadie}
1 0.00192 *{tantum}
removed 'dat/span/qvi/one.1/bad-trunc-wds-summary.tex'
removed 'exp/span/qvi/one.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/span/qvi/one.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:25 by tex-make-sample-summary.sh
% Token and word counts for span/qvi/one.1/bad.wfr
%
\def\spanqvitrunconePBbadTks{522}
\def\spanqvitrunconePBbadTksPct{1.5}
\def\spanqvitrunconePBbadWds{15}
\def\spanqvitrunconePBbadWdsPct{0.0}
copied '/tmp/581686.file' -> 'exp/span/qvi/one.1/bad-trunc-wds-summary.tex'
removed '/tmp/581686.file'
... creating word files dat/span/qvi/two.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
35625 dat/span/qvi/two.1/trunc.tlw
removed 'dat/span/qvi/two.1/raw.tlw'
removed 'dat/span/qvi/two.1/gud.tlw'
removed 'dat/span/qvi/two.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/span/qvi/two.1/raw.wdf
sample:
cuenta zide hamete benengeli en la segunda parte desta historia y
tercera salida de don quixote que el cura y el barbero se estuuieron
casi vn mes sin verle por no renouarle y traerle a la memoria las cosas
passadas pero no por esto dexaron de visitar a su sobrina y a su ama
encargandolas tuuiessen cuenta con regalarle dandole a comer cosas
confortatiuas y apropiadas para el coraįon y el celebro de donde
procedia segun buen discurso toda su mala ventura las quales dixeron que
assi lo hazian y lo harian con la voluntad y cuydado possible porque
echauan de ver que su seņor por momentos yua dando muestras de estar en
su entero juyzio de lo qual recibieron los dos gran contento por
parecerles que auian acertado en auerle traydo encantado en el carro de
los bueyes como se conto en la primera parte desta tan grande como
puntual historia en su vltimo capitulo y assi determinaron de visitarle
y hazer esperiencia de su mejoria aunque tenian casi por impossible que
la tuuiesse y acordaron de no tocarle en ningun punto de la andante
caualleria por no ponerse a peligro de descosser los de la herida que
tan tiernos estauan =
visitaronle en fin y hallaronle sentado en la cama vestida vna almilla
de vayeta verde con vn bonete colorado toledano y estaua tan seco y
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
aconsejado del bachiller sanson carrasco nuestro compatrioto =
en esto boluio
removed 'dat/span/qvi/two.1/raw.wfr'
creating the word frequency file dat/span/qvi/two.1/raw.wfr
the 10 most common words in dat/span/qvi/two.1/raw.tlw:
1879 0.05274 que
1681 0.04719 de
1648 0.04626 y
892 0.02504 a
883 0.02479 la
821 0.02305 el
738 0.02072 en
629 0.01766 no
569 0.01597 =
495 0.01389 los
removed 'dat/span/qvi/two.1/raw-trunc-wds-summary.tex'
removed 'exp/span/qvi/two.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/span/qvi/two.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:25 by tex-make-sample-summary.sh
% Token and word counts for span/qvi/two.1/raw.wfr
%
\def\spanqvitrunctwoPBrawTks{35625}
\def\spanqvitrunctwoPBrawTksPct{100.0}
\def\spanqvitrunctwoPBrawWds{5715}
\def\spanqvitrunctwoPBrawWdsPct{16.0}
copied '/tmp/581740.file' -> 'exp/span/qvi/two.1/raw-trunc-wds-summary.tex'
removed '/tmp/581740.file'
creating running text file dat/span/qvi/two.1/gud.wdf
sample:
cuenta zide hamete benengeli en la segunda parte desta historia y
tercera salida de don quixote que el cura y el barbero se estuuieron
casi vn mes sin verle por no renouarle y traerle a la memoria las cosas
passadas pero no por esto dexaron de visitar a su sobrina y a su ama
encargandolas tuuiessen cuenta con regalarle dandole a comer cosas
confortatiuas y apropiadas para el coraįon y el celebro de donde
procedia segun buen discurso toda su mala ventura las quales dixeron que
assi lo hazian y lo harian con la voluntad y cuydado possible porque
echauan de ver que su seņor por momentos yua dando muestras de estar en
su entero juyzio de lo qual recibieron los dos gran contento por
parecerles que auian acertado en auerle traydo encantado en el carro de
los bueyes como se conto en la primera parte desta tan grande como
puntual historia en su vltimo capitulo y assi determinaron de visitarle
y hazer esperiencia de su mejoria aunque tenian casi por impossible que
la tuuiesse y acordaron de no tocarle en ningun punto de la andante
caualleria por no ponerse a peligro de descosser los de la herida que
tan tiernos estauan visitaronle en fin y hallaronle sentado en la cama
vestida vna almilla de vayeta verde con vn bonete colorado toledano y
estaua tan seco y amoxamado que no parecia sino hecho de carne momia
fueron del muy bien recebidos preguntaronle por su salud y el dio cuenta
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
toque maltrate hiera ni mate al cauallero de los espejos que a sus pies
tiene porque sin duda alguna es el atreuido y mal aconsejado del
bachiller sanson carrasco nuestro compatrioto en esto boluio
removed 'dat/span/qvi/two.1/gud.wfr'
creating the word frequency file dat/span/qvi/two.1/gud.wfr
the 10 most common words in dat/span/qvi/two.1/gud.tlw:
1879 0.05364 que
1681 0.04799 de
1648 0.04705 y
892 0.02547 a
883 0.02521 la
821 0.02344 el
738 0.02107 en
629 0.01796 no
495 0.01413 los
445 0.01270 se
removed 'dat/span/qvi/two.1/gud-trunc-wds-summary.tex'
removed 'exp/span/qvi/two.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/span/qvi/two.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:25 by tex-make-sample-summary.sh
% Token and word counts for span/qvi/two.1/gud.wfr
%
\def\spanqvitrunctwoPBgudTks{35027}
\def\spanqvitrunctwoPBgudTksPct{98.3}
\def\spanqvitrunctwoPBgudWds{5698}
\def\spanqvitrunctwoPBgudWdsPct{16.0}
copied '/tmp/581784.file' -> 'exp/span/qvi/two.1/gud-trunc-wds-summary.tex'
removed '/tmp/581784.file'
creating running text file dat/span/qvi/two.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/span/qvi/two.1/bad.wfr'
creating the word frequency file dat/span/qvi/two.1/bad.wfr
the 10 most common words in dat/span/qvi/two.1/bad.tlw:
569 0.95151 =
5 0.00836 ..*{=}
4 0.00669 ..*{,}
3 0.00502 *{Ŧ}
3 0.00502 ..*{ũ}
2 0.00334 *{`}
2 0.00334 *{y}
1 0.00167 &c
1 0.00167 *{,}
1 0.00167 *{aliquando}
removed 'dat/span/qvi/two.1/bad-trunc-wds-summary.tex'
removed 'exp/span/qvi/two.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/span/qvi/two.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:25 by tex-make-sample-summary.sh
% Token and word counts for span/qvi/two.1/bad.wfr
%
\def\spanqvitrunctwoPBbadTks{598}
\def\spanqvitrunctwoPBbadTksPct{1.7}
\def\spanqvitrunctwoPBbadWds{17}
\def\spanqvitrunctwoPBbadWdsPct{0.0}
copied '/tmp/581828.file' -> 'exp/span/qvi/two.1/bad-trunc-wds-summary.tex'
removed '/tmp/581828.file'
... creating word files dat/span/qvi/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
35605 dat/span/qvi/tot.1/trunc.tlw
removed 'dat/span/qvi/tot.1/raw.tlw'
removed 'dat/span/qvi/tot.1/gud.tlw'
removed 'dat/span/qvi/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/span/qvi/tot.1/raw.wdf
sample:
en vn lugar de la mancha de cuyo nombre no quiero acordarme no ha mucho
tiempo que viuia vn hidalgo de los de lanįa en astillero adarga antigua
rozin flaco y galgo corredor vna olla de algo mas vaca que carnero
salpicon las mas noches duelos y quebrantos los sabados lantejas los
viernes algun palomino de aņadidura los domingos consumian las tres
partes de su hazienda el resto della concluian sayo de velarte calįas de
velludo para las fiestas con sus pantuflos de lo mesmo y los dias de
entre semana se honraua con su vellori de lo mas fino =
tenia en su casa vna ama que passaua de los quarenta y vna sobrina que
no llegaua a los veynte y vn moįo de campo y plaįa que assi ensillaua el
rozin como tomaua la podadera frisaua la edad de nuestro hidalgo con los
cinquenta aņos era de complexion rezia seco de carnes enjuto de rostro
gran madrugador y amigo de la caįa quieren dezir que tenia el
sobrenombre de quixada o quesada que en esto ay alguna diferencia en los
autores que deste caso escriuen aunque por conjeturas verosimiles se
dexa entender que se llamaua quexana pero esto importa poco a nuestro
cuento basta que en la narracion del no se salga vn punto de la verdad =
es pues de saber que este sobredicho hidalgo los ratos que estaua ocioso
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
nuestro poeta donde nos pinta las labores que hazian alla en sus moradas
de cristal aquellas quatro ninfas que del tajo amado sacaron las cabeįas
y se sentaron a labrar en el prado verde
removed 'dat/span/qvi/tot.1/raw.wfr'
creating the word frequency file dat/span/qvi/tot.1/raw.wfr
the 10 most common words in dat/span/qvi/tot.1/raw.tlw:
1929 0.05418 que
1692 0.04752 de
1662 0.04668 y
912 0.02561 el
833 0.02340 a
819 0.02300 la
722 0.02028 en
634 0.01781 no
553 0.01553 =
505 0.01418 se
removed 'dat/span/qvi/tot.1/raw-trunc-wds-summary.tex'
removed 'exp/span/qvi/tot.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/span/qvi/tot.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:25 by tex-make-sample-summary.sh
% Token and word counts for span/qvi/tot.1/raw.wfr
%
\def\spanqvitrunctotPBrawTks{35605}
\def\spanqvitrunctotPBrawTksPct{100.0}
\def\spanqvitrunctotPBrawWds{5600}
\def\spanqvitrunctotPBrawWdsPct{15.7}
copied '/tmp/581882.file' -> 'exp/span/qvi/tot.1/raw-trunc-wds-summary.tex'
removed '/tmp/581882.file'
creating running text file dat/span/qvi/tot.1/gud.wdf
sample:
en vn lugar de la mancha de cuyo nombre no quiero acordarme no ha mucho
tiempo que viuia vn hidalgo de los de lanįa en astillero adarga antigua
rozin flaco y galgo corredor vna olla de algo mas vaca que carnero
salpicon las mas noches duelos y quebrantos los sabados lantejas los
viernes algun palomino de aņadidura los domingos consumian las tres
partes de su hazienda el resto della concluian sayo de velarte calįas de
velludo para las fiestas con sus pantuflos de lo mesmo y los dias de
entre semana se honraua con su vellori de lo mas fino tenia en su casa
vna ama que passaua de los quarenta y vna sobrina que no llegaua a los
veynte y vn moįo de campo y plaįa que assi ensillaua el rozin como
tomaua la podadera frisaua la edad de nuestro hidalgo con los cinquenta
aņos era de complexion rezia seco de carnes enjuto de rostro gran
madrugador y amigo de la caįa quieren dezir que tenia el sobrenombre de
quixada o quesada que en esto ay alguna diferencia en los autores que
deste caso escriuen aunque por conjeturas verosimiles se dexa entender
que se llamaua quexana pero esto importa poco a nuestro cuento basta que
en la narracion del no se salga vn punto de la verdad es pues de saber
que este sobredicho hidalgo los ratos que estaua ocioso que eran los mas
del aņo se daua a leer libros de cauallerias con tanta aficion y gusto
que oluidó casi de todo punto el exercicio de la caįa y aun la
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
nuestro poeta donde nos pinta las labores que hazian alla en sus moradas
de cristal aquellas quatro ninfas que del tajo amado sacaron las cabeįas
y se sentaron a labrar en el prado verde
removed 'dat/span/qvi/tot.1/gud.wfr'
creating the word frequency file dat/span/qvi/tot.1/gud.wfr
the 10 most common words in dat/span/qvi/tot.1/gud.tlw:
1929 0.05507 que
1692 0.04831 de
1662 0.04745 y
912 0.02604 el
833 0.02378 a
819 0.02338 la
722 0.02061 en
634 0.01810 no
505 0.01442 se
446 0.01273 los
removed 'dat/span/qvi/tot.1/gud-trunc-wds-summary.tex'
removed 'exp/span/qvi/tot.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/span/qvi/tot.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:25 by tex-make-sample-summary.sh
% Token and word counts for span/qvi/tot.1/gud.wfr
%
\def\spanqvitrunctotPBgudTks{35027}
\def\spanqvitrunctotPBgudTksPct{98.4}
\def\spanqvitrunctotPBgudWds{5582}
\def\spanqvitrunctotPBgudWdsPct{15.7}
copied '/tmp/581926.file' -> 'exp/span/qvi/tot.1/gud-trunc-wds-summary.tex'
removed '/tmp/581926.file'
creating running text file dat/span/qvi/tot.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
*{tantum} ..*{,} =
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/span/qvi/tot.1/bad.wfr'
creating the word frequency file dat/span/qvi/tot.1/bad.wfr
the 10 most common words in dat/span/qvi/tot.1/bad.tlw:
553 0.95675 =
5 0.00865 ..*{=}
4 0.00692 ..*{,}
2 0.00346 *{`}
1 0.00173 &c
1 0.00173 *{,}
1 0.00173 *{/}
1 0.00173 *{aliquando}
1 0.00173 *{bene}
1 0.00173 *{quando}
removed 'dat/span/qvi/tot.1/bad-trunc-wds-summary.tex'
removed 'exp/span/qvi/tot.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/span/qvi/tot.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:25 by tex-make-sample-summary.sh
% Token and word counts for span/qvi/tot.1/bad.wfr
%
\def\spanqvitrunctotPBbadTks{578}
\def\spanqvitrunctotPBbadTksPct{1.6}
\def\spanqvitrunctotPBbadWds{18}
\def\spanqvitrunctotPBbadWdsPct{0.1}
copied '/tmp/581970.file' -> 'exp/span/qvi/tot.1/bad-trunc-wds-summary.tex'
removed '/tmp/581970.file'
lines words bytes file
------- ------- --------- ------------
5467 16401 132369 dat/span/qvi/one.1/raw.wfr
5715 17145 138399 dat/span/qvi/two.1/raw.wfr
5600 16800 135584 dat/span/qvi/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
5452 16356 132028 dat/span/qvi/one.1/gud.wfr
5698 17094 137999 dat/span/qvi/two.1/gud.wfr
5582 16746 135170 dat/span/qvi/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
15 45 341 dat/span/qvi/one.1/bad.wfr
17 51 400 dat/span/qvi/two.1/bad.wfr
18 54 414 dat/span/qvi/tot.1/bad.wfr
one.1 raw = 35549 gud = 35027 bad = 522
two.1 raw = 35625 gud = 35027 bad = 598
tot.1 raw = 35605 gud = 35027 bad = 578
=== creating the derived word files dat/ital/psp/*/{raw,gud,bad}.{tlw,wdf,wfr} (trunc) ===
... creating word files dat/ital/psp/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
35621 dat/ital/psp/tot.1/trunc.tlw
removed 'dat/ital/psp/tot.1/raw.tlw'
removed 'dat/ital/psp/tot.1/gud.tlw'
removed 'dat/ital/psp/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/ital/psp/tot.1/raw.wdf
sample:
quel ramo del lago di como che volge a mezzogiorno tra due catene non
interrotte di monti tutto a seni e a golfi a seconda dello sporgere e
del rientrare di quelli vien quasi a un tratto a ristringersi e a
prender corso e figura di fiume tra un promontorio a destra e un' ampia
costiera dall' altra parte e il ponte che ivi congiunge le due rive par
che renda ancor pių sensibile all' occhio questa trasformazione e segni
il punto in cui il lago cessa e l' adda rincomincia per ripigliar poi
nome di lago dove le rive allontanandosi di nuovo lascian l' acqua
distendersi e rallentarsi in nuovi golfi e in nuovi seni la costiera
formata dal deposito di tre grossi torrenti scende appoggiata a due
monti contigui l' uno detto di san martino l' altro con voce lombarda il
resegone dai molti suoi cocuzzoli in fila che in vero lo fanno
somigliare a una sega talché non č chi al primo vederlo purché sia di
fronte come per esempio di su le mura di milano che guardano a
settentrione non lo discerna tosto a un tal contrassegno in quella lunga
e vasta giogaia dagli altri monti di nome pių oscuro e di forma pių
comune per un buon pezzo la costa sale con un pendėo lento e continuo
poi si rompe in poggi e in valloncelli in erte e in ispianate secondo l'
ossatura de' due monti e il lavoro dell' acque il lembo estremo tagliato
dalle foci de' torrenti č quasi tutto ghiaia e ciottoloni il resto campi
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
ton ton ton ton i contadini balzano a sedere sul letto i giovinetti
sdraiati sul fenile tendon l' orecchio si rizzano cos'
removed 'dat/ital/psp/tot.1/raw.wfr'
creating the word frequency file dat/ital/psp/tot.1/raw.wfr
the 10 most common words in dat/ital/psp/tot.1/raw.tlw:
1319 0.03703 e
972 0.02729 che
913 0.02563 di
698 0.01960 a
693 0.01945 il
576 0.01617 un
564 0.01583 non
529 0.01485 =
516 0.01449 la
514 0.01443 in
removed 'dat/ital/psp/tot.1/raw-trunc-wds-summary.tex'
removed 'exp/ital/psp/tot.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/ital/psp/tot.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:25 by tex-make-sample-summary.sh
% Token and word counts for ital/psp/tot.1/raw.wfr
%
\def\italpsptrunctotPBrawTks{35621}
\def\italpsptrunctotPBrawTksPct{100.0}
\def\italpsptrunctotPBrawWds{6655}
\def\italpsptrunctotPBrawWdsPct{18.7}
copied '/tmp/582095.file' -> 'exp/ital/psp/tot.1/raw-trunc-wds-summary.tex'
removed '/tmp/582095.file'
creating running text file dat/ital/psp/tot.1/gud.wdf
sample:
quel ramo del lago di como che volge a mezzogiorno tra due catene non
interrotte di monti tutto a seni e a golfi a seconda dello sporgere e
del rientrare di quelli vien quasi a un tratto a ristringersi e a
prender corso e figura di fiume tra un promontorio a destra e un' ampia
costiera dall' altra parte e il ponte che ivi congiunge le due rive par
che renda ancor pių sensibile all' occhio questa trasformazione e segni
il punto in cui il lago cessa e l' adda rincomincia per ripigliar poi
nome di lago dove le rive allontanandosi di nuovo lascian l' acqua
distendersi e rallentarsi in nuovi golfi e in nuovi seni la costiera
formata dal deposito di tre grossi torrenti scende appoggiata a due
monti contigui l' uno detto di san martino l' altro con voce lombarda il
resegone dai molti suoi cocuzzoli in fila che in vero lo fanno
somigliare a una sega talché non č chi al primo vederlo purché sia di
fronte come per esempio di su le mura di milano che guardano a
settentrione non lo discerna tosto a un tal contrassegno in quella lunga
e vasta giogaia dagli altri monti di nome pių oscuro e di forma pių
comune per un buon pezzo la costa sale con un pendėo lento e continuo
poi si rompe in poggi e in valloncelli in erte e in ispianate secondo l'
ossatura de' due monti e il lavoro dell' acque il lembo estremo tagliato
dalle foci de' torrenti č quasi tutto ghiaia e ciottoloni il resto campi
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
campanette che c' erano e suona a martello ton ton ton ton i contadini
balzano a sedere sul letto i giovinetti sdraiati sul fenile tendon l'
orecchio si rizzano cos'
removed 'dat/ital/psp/tot.1/gud.wfr'
creating the word frequency file dat/ital/psp/tot.1/gud.wfr
the 10 most common words in dat/ital/psp/tot.1/gud.tlw:
1319 0.03766 e
972 0.02775 che
913 0.02607 di
698 0.01993 a
693 0.01978 il
576 0.01644 un
564 0.01610 non
516 0.01473 la
514 0.01467 in
409 0.01168 per
removed 'dat/ital/psp/tot.1/gud-trunc-wds-summary.tex'
removed 'exp/ital/psp/tot.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/ital/psp/tot.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:26 by tex-make-sample-summary.sh
% Token and word counts for ital/psp/tot.1/gud.wfr
%
\def\italpsptrunctotPBgudTks{35027}
\def\italpsptrunctotPBgudTksPct{98.3}
\def\italpsptrunctotPBgudWds{6623}
\def\italpsptrunctotPBgudWdsPct{18.6}
copied '/tmp/582139.file' -> 'exp/ital/psp/tot.1/gud-trunc-wds-summary.tex'
removed '/tmp/582139.file'
creating running text file dat/ital/psp/tot.1/bad.wdf
sample:
=
7 1628 =
=
1583 12 =
*{/} ..*{/} =
*{juan} ..*{,} 5 1593 23 1598 =
5 1600 =
22 1612 *{de} ..*{,} 24 1618 5 1627 =
13 1632 *{/} ..*{,} =
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/ital/psp/tot.1/bad.wfr'
creating the word frequency file dat/ital/psp/tot.1/bad.wfr
the 10 most common words in dat/ital/psp/tot.1/bad.tlw:
529 0.89057 =
15 0.02525 *{/}
7 0.01178 ..*{/}
5 0.00842 ..*{,}
3 0.00505 ***
3 0.00505 ..*{.}
3 0.00505 5
2 0.00337 *{de}
2 0.00337 ..*{:}
2 0.00337 ..*{;}
removed 'dat/ital/psp/tot.1/bad-trunc-wds-summary.tex'
removed 'exp/ital/psp/tot.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/ital/psp/tot.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:26 by tex-make-sample-summary.sh
% Token and word counts for ital/psp/tot.1/bad.wfr
%
\def\italpsptrunctotPBbadTks{594}
\def\italpsptrunctotPBbadTksPct{1.7}
\def\italpsptrunctotPBbadWds{32}
\def\italpsptrunctotPBbadWdsPct{0.1}
copied '/tmp/582183.file' -> 'exp/ital/psp/tot.1/bad-trunc-wds-summary.tex'
removed '/tmp/582183.file'
lines words bytes file
------- ------- --------- ------------
6655 19964 163530 dat/ital/psp/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
6623 19868 162852 dat/ital/psp/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
32 96 678 dat/ital/psp/tot.1/bad.wfr
tot.1 raw = 35621 gud = 35027 bad = 594
=== creating the derived word files dat/fran/tal/*/{raw,gud,bad}.{tlw,wdf,wfr} (trunc) ===
... creating word files dat/fran/tal/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
36012 dat/fran/tal/tot.1/trunc.tlw
removed 'dat/fran/tal/tot.1/raw.tlw'
removed 'dat/fran/tal/tot.1/gud.tlw'
removed 'dat/fran/tal/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/fran/tal/tot.1/raw.wdf
sample:
pendant la guerre fédérale des états unis un nouveau club trčs influent
s' établit dans la ville de baltimore en plein maryland on sait avec
quelle énergie l' instinct militaire se développa chez ce peuple d'
armateurs de marchands et de mécaniciens de simples négociants
enjambčrent leur comptoir pour s' improviser capitaines colonels
généraux sans avoir passé par les écoles d' application de west point
ils égalčrent bientôt dans l' art de la guerre leurs collčgues du vieux
continent et comme eux ils remportčrent des victoires ā force de
prodiguer les boulets les millions et les hommes =
*{école} ..*{.} mais en quoi les américains surpassčrent singuličrement
les européens ce fut dans la science de la balistique non que leurs
armes atteignissent un plus haut degré de perfection mais elles
offrirent des dimensions inusitées et eurent par conséquent des portées
inconnues jusqu' alors en fait de tirs rasants plongeants ou de plein
fouet de feux d' écharpe d' enfilade ou de revers les anglais les
franįais les prussiens n' ont plus rien ā apprendre mais leurs canons
leurs obusiers leurs mortiers ne sont que des pistolets de poche auprčs
des formidables engins de l' artillerie américaine =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
la lune il n' y aura ni choc ni secousse ni déraillement ā craindre et
l' on atteindra le but rapidement sans fatigue en ligne droite ā vol d'
abeille pour parler le langage de vos trappeurs avant
removed 'dat/fran/tal/tot.1/raw.wfr'
creating the word frequency file dat/fran/tal/tot.1/raw.wfr
the 10 most common words in dat/fran/tal/tot.1/raw.tlw:
1637 0.04546 de
949 0.02635 la
750 0.02083 ā
747 0.02074 et
741 0.02058 le
733 0.02035 =
702 0.01949 les
639 0.01774 l'
567 0.01574 un
477 0.01325 il
removed 'dat/fran/tal/tot.1/raw-trunc-wds-summary.tex'
removed 'exp/fran/tal/tot.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/fran/tal/tot.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:26 by tex-make-sample-summary.sh
% Token and word counts for fran/tal/tot.1/raw.wfr
%
\def\frantaltrunctotPBrawTks{36012}
\def\frantaltrunctotPBrawTksPct{100.0}
\def\frantaltrunctotPBrawWds{6344}
\def\frantaltrunctotPBrawWdsPct{17.6}
copied '/tmp/582278.file' -> 'exp/fran/tal/tot.1/raw-trunc-wds-summary.tex'
removed '/tmp/582278.file'
creating running text file dat/fran/tal/tot.1/gud.wdf
sample:
pendant la guerre fédérale des états unis un nouveau club trčs influent
s' établit dans la ville de baltimore en plein maryland on sait avec
quelle énergie l' instinct militaire se développa chez ce peuple d'
armateurs de marchands et de mécaniciens de simples négociants
enjambčrent leur comptoir pour s' improviser capitaines colonels
généraux sans avoir passé par les écoles d' application de west point
ils égalčrent bientôt dans l' art de la guerre leurs collčgues du vieux
continent et comme eux ils remportčrent des victoires ā force de
prodiguer les boulets les millions et les hommes mais en quoi les
américains surpassčrent singuličrement les européens ce fut dans la
science de la balistique non que leurs armes atteignissent un plus haut
degré de perfection mais elles offrirent des dimensions inusitées et
eurent par conséquent des portées inconnues jusqu' alors en fait de tirs
rasants plongeants ou de plein fouet de feux d' écharpe d' enfilade ou
de revers les anglais les franįais les prussiens n' ont plus rien ā
apprendre mais leurs canons leurs obusiers leurs mortiers ne sont que
des pistolets de poche auprčs des formidables engins de l' artillerie
américaine ceci ne doit étonner personne les yankees ces premiers
mécaniciens du monde sont ingénieurs comme les italiens sont musiciens
et les allemands métaphysiciens de naissance rien de plus naturel dčs
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
la lune il n' y aura ni choc ni secousse ni déraillement ā craindre et
l' on atteindra le but rapidement sans fatigue en ligne droite ā vol d'
abeille pour parler le langage de vos trappeurs avant
removed 'dat/fran/tal/tot.1/gud.wfr'
creating the word frequency file dat/fran/tal/tot.1/gud.wfr
the 10 most common words in dat/fran/tal/tot.1/gud.tlw:
1637 0.04674 de
949 0.02709 la
750 0.02141 ā
747 0.02133 et
741 0.02116 le
702 0.02004 les
639 0.01824 l'
567 0.01619 un
477 0.01362 il
470 0.01342 d'
removed 'dat/fran/tal/tot.1/gud-trunc-wds-summary.tex'
removed 'exp/fran/tal/tot.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/fran/tal/tot.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:26 by tex-make-sample-summary.sh
% Token and word counts for fran/tal/tot.1/gud.wfr
%
\def\frantaltrunctotPBgudTks{35027}
\def\frantaltrunctotPBgudTksPct{97.3}
\def\frantaltrunctotPBgudWds{6223}
\def\frantaltrunctotPBgudWdsPct{17.3}
copied '/tmp/582322.file' -> 'exp/fran/tal/tot.1/gud-trunc-wds-summary.tex'
removed '/tmp/582322.file'
creating running text file dat/fran/tal/tot.1/bad.wdf
sample:
=
*{école} ..*{.} =
=
=
*{badaud} *{.} =
*{littéralement} ..*{.} =
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/fran/tal/tot.1/bad.wfr'
creating the word frequency file dat/fran/tal/tot.1/bad.wfr
the 10 most common words in dat/fran/tal/tot.1/bad.tlw:
733 0.74416 =
68 0.06904 ..*{.}
8 0.00812 *{_}
6 0.00609 ..*{_}
5 0.00508 *{le}
5 0.00508 3
4 0.00406 *{c'}
4 0.00406 10
4 0.00406 8
3 0.00305 $$
removed 'dat/fran/tal/tot.1/bad-trunc-wds-summary.tex'
removed 'exp/fran/tal/tot.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/fran/tal/tot.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:26 by tex-make-sample-summary.sh
% Token and word counts for fran/tal/tot.1/bad.wfr
%
\def\frantaltrunctotPBbadTks{985}
\def\frantaltrunctotPBbadTksPct{2.7}
\def\frantaltrunctotPBbadWds{121}
\def\frantaltrunctotPBbadWdsPct{0.3}
copied '/tmp/582366.file' -> 'exp/fran/tal/tot.1/bad-trunc-wds-summary.tex'
removed '/tmp/582366.file'
lines words bytes file
------- ------- --------- ------------
6344 19030 156220 dat/fran/tal/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
6223 18667 153520 dat/fran/tal/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
121 363 2700 dat/fran/tal/tot.1/bad.wfr
tot.1 raw = 36012 gud = 35027 bad = 985
=== creating the derived word files dat/port/csm/*/{raw,gud,bad}.{tlw,wdf,wfr} (trunc) ===
... creating word files dat/port/csm/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
35056 dat/port/csm/tot.1/trunc.tlw
removed 'dat/port/csm/tot.1/raw.tlw'
removed 'dat/port/csm/tot.1/gud.tlw'
removed 'dat/port/csm/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/port/csm/tot.1/raw.wdf
sample:
uma noite destas vindo da cidade para o engenho novo encontrei no trem
da central um rapaz aqui do bairro que eu conheįo de vista e de chapéu
cumprimentou~me sentou~se ao pé de mim falou da lua e dos ministros e
acabou recitando~me versos a viagem era curta e os versos pode ser que
não fossem inteiramente maus sucedeu porém que como eu estava cansado
fechei os olhos tręs ou quatro vezes tanto bastou para que ele
interrompesse a leitura e metesse os versos no bolso continue disse eu
acordando já acabei murmurou ele são muito bonitos vi~lhe fazer um gesto
para tirá~los outra vez do bolso mas não passou do gesto estava amuado
no dia seguinte entrou a dizer de mim nomes feios e acabou alcunhando~me
dom casmurro os vizinhos que não gostam dos meus hábitos reclusos e
calados deram curso ā alcunha que afinal pegou nem por isso me zanguei
contei a anedota aos amigos da cidade e eles por graįa chamam~me assim
alguns em bilhetes dom casmurro domingo vou jantar com vocę vou para
petrópolis dom casmurro a casa é a mesma da renânia vę se deixas essa
caverna do engenho novo e vai lá passar uns quinze dias comigo meu caro
dom casmurro não cuide que o dispenso do teatro amanhã venha e dormirá
aqui na cidade dou~lhe camarote dou~lhe chá dou~lhe cama só não lhe dou
moįa não consultes dicionários casmurro não está aqui no sentido que
eles lhe dão mas no que lhe pôs o vulgo de homem calado e metido consigo
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
que não respirou tive receio disse ele os outros souberam parece que sim
alguns souberam tio cosme e josé dias gostaram do moįo o agregado
disse~lhe que vira uma vez
removed 'dat/port/csm/tot.1/raw.wfr'
creating the word frequency file dat/port/csm/tot.1/raw.wfr
the 10 most common words in dat/port/csm/tot.1/raw.tlw:
1413 0.04031 que
1282 0.03657 a
1149 0.03278 e
1067 0.03044 de
867 0.02473 o
844 0.02408 não
413 0.01178 um
410 0.01170 é
375 0.01070 os
346 0.00987 mas
removed 'dat/port/csm/tot.1/raw-trunc-wds-summary.tex'
removed 'exp/port/csm/tot.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/port/csm/tot.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:26 by tex-make-sample-summary.sh
% Token and word counts for port/csm/tot.1/raw.wfr
%
\def\portcsmtrunctotPBrawTks{35056}
\def\portcsmtrunctotPBrawTksPct{100.0}
\def\portcsmtrunctotPBrawWds{6278}
\def\portcsmtrunctotPBrawWdsPct{17.9}
copied '/tmp/582461.file' -> 'exp/port/csm/tot.1/raw-trunc-wds-summary.tex'
removed '/tmp/582461.file'
creating running text file dat/port/csm/tot.1/gud.wdf
sample:
uma noite destas vindo da cidade para o engenho novo encontrei no trem
da central um rapaz aqui do bairro que eu conheįo de vista e de chapéu
cumprimentou~me sentou~se ao pé de mim falou da lua e dos ministros e
acabou recitando~me versos a viagem era curta e os versos pode ser que
não fossem inteiramente maus sucedeu porém que como eu estava cansado
fechei os olhos tręs ou quatro vezes tanto bastou para que ele
interrompesse a leitura e metesse os versos no bolso continue disse eu
acordando já acabei murmurou ele são muito bonitos vi~lhe fazer um gesto
para tirá~los outra vez do bolso mas não passou do gesto estava amuado
no dia seguinte entrou a dizer de mim nomes feios e acabou alcunhando~me
dom casmurro os vizinhos que não gostam dos meus hábitos reclusos e
calados deram curso ā alcunha que afinal pegou nem por isso me zanguei
contei a anedota aos amigos da cidade e eles por graįa chamam~me assim
alguns em bilhetes dom casmurro domingo vou jantar com vocę vou para
petrópolis dom casmurro a casa é a mesma da renânia vę se deixas essa
caverna do engenho novo e vai lá passar uns quinze dias comigo meu caro
dom casmurro não cuide que o dispenso do teatro amanhã venha e dormirá
aqui na cidade dou~lhe camarote dou~lhe chá dou~lhe cama só não lhe dou
moįa não consultes dicionários casmurro não está aqui no sentido que
eles lhe dão mas no que lhe pôs o vulgo de homem calado e metido consigo
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
continuava o perigo ou não quando lhe disse que não respirou tive receio
disse ele os outros souberam parece que sim alguns souberam tio cosme e
josé dias gostaram do moįo o agregado disse~lhe que vira uma vez
removed 'dat/port/csm/tot.1/gud.wfr'
creating the word frequency file dat/port/csm/tot.1/gud.wfr
the 10 most common words in dat/port/csm/tot.1/gud.tlw:
1413 0.04034 que
1282 0.03660 a
1149 0.03280 e
1067 0.03046 de
867 0.02475 o
844 0.02410 não
413 0.01179 um
410 0.01171 é
375 0.01071 os
346 0.00988 mas
removed 'dat/port/csm/tot.1/gud-trunc-wds-summary.tex'
removed 'exp/port/csm/tot.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/port/csm/tot.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:26 by tex-make-sample-summary.sh
% Token and word counts for port/csm/tot.1/gud.wfr
%
\def\portcsmtrunctotPBgudTks{35027}
\def\portcsmtrunctotPBgudTksPct{99.9}
\def\portcsmtrunctotPBgudWds{6267}
\def\portcsmtrunctotPBgudWdsPct{17.9}
copied '/tmp/582505.file' -> 'exp/port/csm/tot.1/gud-trunc-wds-summary.tex'
removed '/tmp/582505.file'
creating running text file dat/port/csm/tot.1/bad.wdf
sample:
1857 1857 *{_} ..*{_} *{_} ..*{_} *{_} ..*{_} *{_} ..*{_} *{_} ..*{_}
*{_} ..*{?} 6š *{_} ..*{_} x 1882 1859 1860 58 1859 1860 4004 *{_}
..*{_} *{_} ..*{_}
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
1857 1857 *{_} ..*{_} *{_} ..*{_} *{_} ..*{_} *{_} ..*{_} *{_} ..*{_}
*{_} ..*{?} 6š *{_} ..*{_} x 1882 1859 1860 58 1859 1860 4004 *{_}
..*{_} *{_} ..*{_}
removed 'dat/port/csm/tot.1/bad.wfr'
creating the word frequency file dat/port/csm/tot.1/bad.wfr
the 10 most common words in dat/port/csm/tot.1/bad.tlw:
9 0.31034 *{_}
8 0.27586 ..*{_}
2 0.06897 1857
2 0.06897 1859
2 0.06897 1860
1 0.03448 ..*{?}
1 0.03448 1882
1 0.03448 4004
1 0.03448 58
1 0.03448 6š
removed 'dat/port/csm/tot.1/bad-trunc-wds-summary.tex'
removed 'exp/port/csm/tot.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/port/csm/tot.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:26 by tex-make-sample-summary.sh
% Token and word counts for port/csm/tot.1/bad.wfr
%
\def\portcsmtrunctotPBbadTks{29}
\def\portcsmtrunctotPBbadTksPct{0.1}
\def\portcsmtrunctotPBbadWds{11}
\def\portcsmtrunctotPBbadWdsPct{0.0}
copied '/tmp/582549.file' -> 'exp/port/csm/tot.1/bad-trunc-wds-summary.tex'
removed '/tmp/582549.file'
lines words bytes file
------- ------- --------- ------------
6278 18832 153113 dat/port/csm/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
6267 18799 152885 dat/port/csm/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
11 33 228 dat/port/csm/tot.1/bad.wfr
tot.1 raw = 35056 gud = 35027 bad = 29
=== creating the derived word files dat/germ/sim/*/{raw,gud,bad}.{tlw,wdf,wfr} (trunc) ===
... creating word files dat/germ/sim/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
35274 dat/germ/sim/tot.1/trunc.tlw
removed 'dat/germ/sim/tot.1/raw.tlw'
removed 'dat/germ/sim/tot.1/gud.tlw'
removed 'dat/germ/sim/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/germ/sim/tot.1/raw.wdf
sample:
es eröffnet sich zu dieser unserer zeit von welcher man glaubt daß es
die letzte sei unter geringen leuten eine sucht in der die patienten
wenn sie daran krank liegen und so viel zusammen geraspelt und
erschachert haben daß sie neben ein paar hellern im beutel ein
närrisches kleid auf die neue mode mit tausenderlei seidenen bändern
antragen können oder sonst etwa durch glücksfall mannhaft und bekannt
worden gleich rittermäßige herren und adelige personen von uraltem
geschlecht sein wollen da sich doch oft befindet daß ihre voreltern
taglöhner karchelzieher und lastträger ihre vettern eseltreiber ihre
brüder büttel und schergen ihre schwestern huren ihre mütter
kupplerinnen oder gar hexen und in summa ihr ganzes geschlecht von allen
32 anichen her also besudelt und befleckt gewesen als des zuckerbastels
zunft zu prag immer sein mögen ja sie diese neuen nobilisten sind oft
selbst so schwarz als wenn sie in guinea geboren und erzogen wären
worden =
solchen närrischen leuten nun mag ich mich nicht gleich stellen obzwar
die wahrheit zu bekennen nicht ohn ist daß ich mir oft eingebildet ich
müsse ohnfehlbar auch von einem großen herrn oder wenigst einem gemeinen
edelmann meinen ursprung haben weil ich von natur geneigt das
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
ich will aber wehr und waffen fahren lassen und mich zu den künsten
wenden welche zwar etwas geringer zu sein scheinen nichts desto weniger
aber ihre meister ganz
removed 'dat/germ/sim/tot.1/raw.wfr'
creating the word frequency file dat/germ/sim/tot.1/raw.wfr
the 10 most common words in dat/germ/sim/tot.1/raw.tlw:
1337 0.03790 und
981 0.02781 ich
622 0.01763 die
554 0.01571 zu
517 0.01466 der
459 0.01301 er
403 0.01142 so
400 0.01134 in
381 0.01080 ein
379 0.01074 nicht
removed 'dat/germ/sim/tot.1/raw-trunc-wds-summary.tex'
removed 'exp/germ/sim/tot.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/germ/sim/tot.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:26 by tex-make-sample-summary.sh
% Token and word counts for germ/sim/tot.1/raw.wfr
%
\def\germsimtrunctotPBrawTks{35274}
\def\germsimtrunctotPBrawTksPct{100.0}
\def\germsimtrunctotPBrawWds{6879}
\def\germsimtrunctotPBrawWdsPct{19.5}
copied '/tmp/582644.file' -> 'exp/germ/sim/tot.1/raw-trunc-wds-summary.tex'
removed '/tmp/582644.file'
creating running text file dat/germ/sim/tot.1/gud.wdf
sample:
es eröffnet sich zu dieser unserer zeit von welcher man glaubt daß es
die letzte sei unter geringen leuten eine sucht in der die patienten
wenn sie daran krank liegen und so viel zusammen geraspelt und
erschachert haben daß sie neben ein paar hellern im beutel ein
närrisches kleid auf die neue mode mit tausenderlei seidenen bändern
antragen können oder sonst etwa durch glücksfall mannhaft und bekannt
worden gleich rittermäßige herren und adelige personen von uraltem
geschlecht sein wollen da sich doch oft befindet daß ihre voreltern
taglöhner karchelzieher und lastträger ihre vettern eseltreiber ihre
brüder büttel und schergen ihre schwestern huren ihre mütter
kupplerinnen oder gar hexen und in summa ihr ganzes geschlecht von allen
anichen her also besudelt und befleckt gewesen als des zuckerbastels
zunft zu prag immer sein mögen ja sie diese neuen nobilisten sind oft
selbst so schwarz als wenn sie in guinea geboren und erzogen wären
worden solchen närrischen leuten nun mag ich mich nicht gleich stellen
obzwar die wahrheit zu bekennen nicht ohn ist daß ich mir oft
eingebildet ich müsse ohnfehlbar auch von einem großen herrn oder
wenigst einem gemeinen edelmann meinen ursprung haben weil ich von natur
geneigt das junkernhandwerk zu treiben wenn ich nur den verlag und das
werkzeug dazu hätte zwar ohngescherzt mein herkommen und auferziehung
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
wehr und waffen fahren lassen und mich zu den künsten wenden welche zwar
etwas geringer zu sein scheinen nichts desto weniger aber ihre meister
ganz
removed 'dat/germ/sim/tot.1/gud.wfr'
creating the word frequency file dat/germ/sim/tot.1/gud.wfr
the 10 most common words in dat/germ/sim/tot.1/gud.tlw:
1337 0.03817 und
981 0.02801 ich
622 0.01776 die
554 0.01582 zu
517 0.01476 der
459 0.01310 er
403 0.01151 so
400 0.01142 in
381 0.01088 ein
379 0.01082 nicht
removed 'dat/germ/sim/tot.1/gud-trunc-wds-summary.tex'
removed 'exp/germ/sim/tot.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/germ/sim/tot.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:26 by tex-make-sample-summary.sh
% Token and word counts for germ/sim/tot.1/gud.wfr
%
\def\germsimtrunctotPBgudTks{35027}
\def\germsimtrunctotPBgudTksPct{99.3}
\def\germsimtrunctotPBgudWds{6826}
\def\germsimtrunctotPBgudWdsPct{19.4}
copied '/tmp/582688.file' -> 'exp/germ/sim/tot.1/gud-trunc-wds-summary.tex'
removed '/tmp/582688.file'
creating running text file dat/germ/sim/tot.1/bad.wdf
sample:
32 =
=
=
600 000 =
=
=
*{du} ..*{=} =
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
1 152 000 940 876 110 45 33 =
removed 'dat/germ/sim/tot.1/bad.wfr'
creating the word frequency file dat/germ/sim/tot.1/bad.wfr
the 10 most common words in dat/germ/sim/tot.1/bad.tlw:
177 0.71660 =
8 0.03239 ..*{=}
3 0.01215 ..*{,}
3 0.01215 000
2 0.00810 *{>}
2 0.00810 *{die}
2 0.00810 *{ŧ}
2 0.00810 ..*{<}
2 0.00810 10
2 0.00810 2š
removed 'dat/germ/sim/tot.1/bad-trunc-wds-summary.tex'
removed 'exp/germ/sim/tot.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/germ/sim/tot.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:26 by tex-make-sample-summary.sh
% Token and word counts for germ/sim/tot.1/bad.wfr
%
\def\germsimtrunctotPBbadTks{247}
\def\germsimtrunctotPBbadTksPct{0.7}
\def\germsimtrunctotPBbadWds{53}
\def\germsimtrunctotPBbadWdsPct{0.2}
copied '/tmp/582732.file' -> 'exp/germ/sim/tot.1/bad-trunc-wds-summary.tex'
removed '/tmp/582732.file'
lines words bytes file
------- ------- --------- ------------
6879 20637 170418 dat/germ/sim/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
6826 20478 169257 dat/germ/sim/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
53 159 1161 dat/germ/sim/tot.1/bad.wfr
tot.1 raw = 35274 gud = 35027 bad = 247
=== creating the derived word files dat/russ/pic/*/{raw,gud,bad}.{tlw,wdf,wfr} (trunc) ===
... creating word files dat/russ/pic/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
36263 dat/russ/pic/tot.1/trunc.tlw
removed 'dat/russ/pic/tot.1/raw.tlw'
removed 'dat/russ/pic/tot.1/gud.tlw'
removed 'dat/russ/pic/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/russ/pic/tot.1/raw.wdf
sample:
nakanune stoim eto my s nim v hranilishche uzhe vecherom ostaetsya
tol'ko specovki sbrosit' i mozhno zakatit'sya v borzhch prinyat' v
organizm kapel'ku druguyu krepkogo ya stoyu prosto tak stenu podpirayu
svoe otrabotal i uzhe derzhu nagotove sigaretku kurit' hochetsya diko
dva chasa ne kuril a on vse vozitsya so svoim dobrom odin sejf zagruzil
zaper i opechatal teper' drugoj zagruzhaet beret s transportera
pustyshki kazhduyu so vseh storon osmatrivaet a ona tyazhelaya svoloch'
shest' s polovinoj kilo mezhdu prochim i s kryahten'em akkuratnen'ko
vodvoryaet na polku =
skol'ko uzhe vremeni on s etimi pustyshkami b'etsya i po moemu bez
vsyakoj pol'zy dlya chelovechestva na ego meste ya davnym davno by uzhe
plyunul i chem nibud' drugim zanyalsya za te zhe den'gi hotya s drugoj
storony esli podumat' pustyshka dejstvitel'no shtuka zagadochnaya i
kakaya to nevrazumitel'naya chto li skol'ko ya ih na sebe peretaskal a
vse ravno kazhdyj raz kak uvizhu ne mogu porazhayus' vsego to v nej dva
mednyh diska s chajnoe blyudce millimetrov pyat' tolshchinoj i
rasstoyanie mezhdu diskami millimetrov chetyresta i krome etogo
rasstoyaniya nichego mezhdu nimi net to est' sovsem nichego pusto mozhno
tuda prosunut' ruku mozhno i golovu esli ty sovsem obaldel ot izumleniya
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
v eto vremya v prihozhej poslyshalis' sharkayushchie shagi postukivanie
i
removed 'dat/russ/pic/tot.1/raw.wfr'
creating the word frequency file dat/russ/pic/tot.1/raw.wfr
the 10 most common words in dat/russ/pic/tot.1/raw.tlw:
1382 0.03811 i
1227 0.03384 =
800 0.02206 ne
797 0.02198 v
576 0.01588 on
572 0.01577 na
494 0.01362 ya
436 0.01202 chto
433 0.01194 a
362 0.00998 s
removed 'dat/russ/pic/tot.1/raw-trunc-wds-summary.tex'
removed 'exp/russ/pic/tot.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/russ/pic/tot.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:27 by tex-make-sample-summary.sh
% Token and word counts for russ/pic/tot.1/raw.wfr
%
\def\russpictrunctotPBrawTks{36263}
\def\russpictrunctotPBrawTksPct{100.0}
\def\russpictrunctotPBrawWds{9767}
\def\russpictrunctotPBrawWdsPct{26.9}
copied '/tmp/582827.file' -> 'exp/russ/pic/tot.1/raw-trunc-wds-summary.tex'
removed '/tmp/582827.file'
creating running text file dat/russ/pic/tot.1/gud.wdf
sample:
nakanune stoim eto my s nim v hranilishche uzhe vecherom ostaetsya
tol'ko specovki sbrosit' i mozhno zakatit'sya v borzhch prinyat' v
organizm kapel'ku druguyu krepkogo ya stoyu prosto tak stenu podpirayu
svoe otrabotal i uzhe derzhu nagotove sigaretku kurit' hochetsya diko
dva chasa ne kuril a on vse vozitsya so svoim dobrom odin sejf zagruzil
zaper i opechatal teper' drugoj zagruzhaet beret s transportera
pustyshki kazhduyu so vseh storon osmatrivaet a ona tyazhelaya svoloch'
shest' s polovinoj kilo mezhdu prochim i s kryahten'em akkuratnen'ko
vodvoryaet na polku skol'ko uzhe vremeni on s etimi pustyshkami b'etsya
i po moemu bez vsyakoj pol'zy dlya chelovechestva na ego meste ya davnym
davno by uzhe plyunul i chem nibud' drugim zanyalsya za te zhe den'gi
hotya s drugoj storony esli podumat' pustyshka dejstvitel'no shtuka
zagadochnaya i kakaya to nevrazumitel'naya chto li skol'ko ya ih na sebe
peretaskal a vse ravno kazhdyj raz kak uvizhu ne mogu porazhayus' vsego
to v nej dva mednyh diska s chajnoe blyudce millimetrov pyat'
tolshchinoj i rasstoyanie mezhdu diskami millimetrov chetyresta i krome
etogo rasstoyaniya nichego mezhdu nimi net to est' sovsem nichego pusto
mozhno tuda prosunut' ruku mozhno i golovu esli ty sovsem obaldel ot
izumleniya pustota i pustota odin vozduh i pri vsem pri tom chto to
mezhdu nimi konechno est' sila kakaya to kak ya eto ponimayu potomu chto
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
o chem i on otognal ot sebya vse svyaznye mysli sel poudobnee
rasslabilsya i stal zhdat' poka emu podnesut vypivku v eto vremya v
prihozhej poslyshalis' sharkayushchie shagi postukivanie i
removed 'dat/russ/pic/tot.1/gud.wfr'
creating the word frequency file dat/russ/pic/tot.1/gud.wfr
the 10 most common words in dat/russ/pic/tot.1/gud.tlw:
1382 0.03946 i
800 0.02284 ne
797 0.02275 v
576 0.01644 on
572 0.01633 na
494 0.01410 ya
436 0.01245 chto
433 0.01236 a
362 0.01033 s
313 0.00894 kak
removed 'dat/russ/pic/tot.1/gud-trunc-wds-summary.tex'
removed 'exp/russ/pic/tot.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/russ/pic/tot.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:27 by tex-make-sample-summary.sh
% Token and word counts for russ/pic/tot.1/gud.wfr
%
\def\russpictrunctotPBgudTks{35027}
\def\russpictrunctotPBgudTksPct{96.6}
\def\russpictrunctotPBgudWds{9761}
\def\russpictrunctotPBgudWdsPct{26.9}
copied '/tmp/582871.file' -> 'exp/russ/pic/tot.1/gud-trunc-wds-summary.tex'
removed '/tmp/582871.file'
creating running text file dat/russ/pic/tot.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/russ/pic/tot.1/bad.wfr'
creating the word frequency file dat/russ/pic/tot.1/bad.wfr
the 10 most common words in dat/russ/pic/tot.1/bad.tlw:
1227 0.99272 =
2 0.00162 23
2 0.00162 k
1 0.00081 19
1 0.00081 27
1 0.00081 56
1 0.00081 77
1 0.00081 b
removed 'dat/russ/pic/tot.1/bad-trunc-wds-summary.tex'
removed 'exp/russ/pic/tot.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/russ/pic/tot.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:27 by tex-make-sample-summary.sh
% Token and word counts for russ/pic/tot.1/bad.wfr
%
\def\russpictrunctotPBbadTks{1236}
\def\russpictrunctotPBbadTksPct{3.4}
\def\russpictrunctotPBbadWds{8}
\def\russpictrunctotPBbadWdsPct{0.0}
copied '/tmp/582915.file' -> 'exp/russ/pic/tot.1/bad-trunc-wds-summary.tex'
removed '/tmp/582915.file'
lines words bytes file
------- ------- --------- ------------
9767 29300 244476 dat/russ/pic/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
9761 29282 244363 dat/russ/pic/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
8 24 149 dat/russ/pic/tot.1/bad.wfr
tot.1 raw = 36263 gud = 35027 bad = 1236
=== creating the derived word files dat/russ/ptt/*/{raw,gud,bad}.{tlw,wdf,wfr} (trunc) ===
... creating word files dat/russ/ptt/gen.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
28445 dat/russ/ptt/gen.1/trunc.tlw
removed 'dat/russ/ptt/gen.1/raw.tlw'
removed 'dat/russ/ptt/gen.1/gud.tlw'
removed 'dat/russ/ptt/gen.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
!! empty raw.tlw file '='
creating running text file dat/russ/ptt/gen.1/raw.wdf
sample:
ũ
îáþáėå óïôũïōéė âïį îåâï é úåíėā úåíėņ öå âųėá âåúũéäîá é ðõóôá é ôøíá
îáä âåúäîïā é äõč âïöéę îïóéėóņ îáä ũïäïā é óëáúáė âïį äá âõäåô óũåô é
óôáė óũåô é õũéäåė âïį óũåô þôï ïî čïōïû é ïôäåėéė âïį óũåô ïô ôøíų é
îáúũáė âïį óũåô äîåí á ôøíõ îïþøā é âųė ũåþåō é âųėï õôōï äåîø ïäéî é
óëáúáė âïį äá âõäåô ôũåōäø ðïóōåäé ũïäų é äá ïôäåėņåô ïîá ũïäõ ïô ũïäų é
óïúäáė âïį ôũåōäø é ïôäåėéė ũïäõ ëïôïōáņ ðïä ôũåōäøā ïô ũïäų ëïôïōáņ îáä
ôũåōäøā é óôáėï ôáë é îáúũáė âïį ôũåōäø îåâïí é âųė ũåþåō é âųėï õôōï
äåîø ũôïōïę é óëáúáė âïį äá óïâåōåôóņ ũïäá ëïôïōáņ ðïä îåâïí ũ
ïäîï íåóôï é äá ņũéôóņ óõûá é óôáėï ôáë é îáúũáė âïį óõûõ úåíėåā á
óïâōáîéå ũïä îáúũáė íïōņíé é õũéäåė âïį þôï üôï čïōïûï é óëáúáė âïį äá
ðōïéúōáóôéô úåíėņ úåėåîø ôōáũõ óåāýõā óåíņ äåōåũï ðėïäïũéôïå ðōéîïóņýåå
ðï ōïäõ óũïåíõ ðėïä ũ
ëïôïōïí óåíņ åįï îá úåíėå é óôáėï ôáë é ðōïéúũåėá úåíėņ úåėåîø ôōáũõ
óåāýõā óåíņ ðï ōïäõ åå é äåōåũï ðōéîïóņýåå ðėïä ũ
ëïôïōïí óåíņ åįï ðï ōïäõ åįï é õũéäåė âïį þôï üôï čïōïûï é âųė ũåþåō é
âųėï õôōï äåîø ôōåôéę é óëáúáė âïį äá âõäõô óũåôéėá îá ôũåōäé îåâåóîïę
äėņ ïôäåėåîéņ äîņ ïô îïþé é äėņ úîáíåîéę é ũōåíåî é äîåę é įïäïũ é äá
âõäõô ïîé óũåôéėøîéëáíé îá ôũåōäé îåâåóîïę þôïâų óũåôéôø îá úåíėā é
óôáėï ôáë é óïúäáė âïį äũá óũåôéėá ũåėéëéå óũåôéėï âïėøûåå äėņ
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
éïóéæ óôá äåóņôé ėåô é îáâáėøúáíéōïũáėé åįï é ðïėïöéėé ũ
ëïũþåį ũ
åįéðôå
removed 'dat/russ/ptt/gen.1/raw.wfr'
creating the word frequency file dat/russ/ptt/gen.1/raw.wfr
the 10 most common words in dat/russ/ptt/gen.1/raw.tlw:
2885 0.10142 é
624 0.02194 ũ
397 0.01396 óëáúáė
386 0.01357 åįï
328 0.01153 ņ
323 0.01136 îå
300 0.01055 ïî
299 0.01051 þôï
281 0.00988 îá
268 0.00942 ó
removed 'dat/russ/ptt/gen.1/raw-trunc-wds-summary.tex'
removed 'exp/russ/ptt/gen.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/russ/ptt/gen.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:27 by tex-make-sample-summary.sh
% Token and word counts for russ/ptt/gen.1/raw.wfr
%
\def\russptttruncgenPBrawTks{28445}
\def\russptttruncgenPBrawTksPct{100.0}
\def\russptttruncgenPBrawWds{4899}
\def\russptttruncgenPBrawWdsPct{17.2}
copied '/tmp/583012.file' -> 'exp/russ/ptt/gen.1/raw-trunc-wds-summary.tex'
removed '/tmp/583012.file'
creating running text file dat/russ/ptt/gen.1/gud.wdf
sample:
ũ
îáþáėå óïôũïōéė âïį îåâï é úåíėā úåíėņ öå âųėá âåúũéäîá é ðõóôá é ôøíá
îáä âåúäîïā é äõč âïöéę îïóéėóņ îáä ũïäïā é óëáúáė âïį äá âõäåô óũåô é
óôáė óũåô é õũéäåė âïį óũåô þôï ïî čïōïû é ïôäåėéė âïį óũåô ïô ôøíų é
îáúũáė âïį óũåô äîåí á ôøíõ îïþøā é âųė ũåþåō é âųėï õôōï äåîø ïäéî é
óëáúáė âïį äá âõäåô ôũåōäø ðïóōåäé ũïäų é äá ïôäåėņåô ïîá ũïäõ ïô ũïäų é
óïúäáė âïį ôũåōäø é ïôäåėéė ũïäõ ëïôïōáņ ðïä ôũåōäøā ïô ũïäų ëïôïōáņ îáä
ôũåōäøā é óôáėï ôáë é îáúũáė âïį ôũåōäø îåâïí é âųė ũåþåō é âųėï õôōï
äåîø ũôïōïę é óëáúáė âïį äá óïâåōåôóņ ũïäá ëïôïōáņ ðïä îåâïí ũ
ïäîï íåóôï é äá ņũéôóņ óõûá é óôáėï ôáë é îáúũáė âïį óõûõ úåíėåā á
óïâōáîéå ũïä îáúũáė íïōņíé é õũéäåė âïį þôï üôï čïōïûï é óëáúáė âïį äá
ðōïéúōáóôéô úåíėņ úåėåîø ôōáũõ óåāýõā óåíņ äåōåũï ðėïäïũéôïå ðōéîïóņýåå
ðï ōïäõ óũïåíõ ðėïä ũ
ëïôïōïí óåíņ åįï îá úåíėå é óôáėï ôáë é ðōïéúũåėá úåíėņ úåėåîø ôōáũõ
óåāýõā óåíņ ðï ōïäõ åå é äåōåũï ðōéîïóņýåå ðėïä ũ
ëïôïōïí óåíņ åįï ðï ōïäõ åįï é õũéäåė âïį þôï üôï čïōïûï é âųė ũåþåō é
âųėï õôōï äåîø ôōåôéę é óëáúáė âïį äá âõäõô óũåôéėá îá ôũåōäé îåâåóîïę
äėņ ïôäåėåîéņ äîņ ïô îïþé é äėņ úîáíåîéę é ũōåíåî é äîåę é įïäïũ é äá
âõäõô ïîé óũåôéėøîéëáíé îá ôũåōäé îåâåóîïę þôïâų óũåôéôø îá úåíėā é
óôáėï ôáë é óïúäáė âïį äũá óũåôéėá ũåėéëéå óũåôéėï âïėøûåå äėņ
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
éïóéæ óôá äåóņôé ėåô é îáâáėøúáíéōïũáėé åįï é ðïėïöéėé ũ
ëïũþåį ũ
åįéðôå
removed 'dat/russ/ptt/gen.1/gud.wfr'
creating the word frequency file dat/russ/ptt/gen.1/gud.wfr
the 10 most common words in dat/russ/ptt/gen.1/gud.tlw:
2885 0.10142 é
624 0.02194 ũ
397 0.01396 óëáúáė
386 0.01357 åįï
328 0.01153 ņ
323 0.01136 îå
300 0.01055 ïî
299 0.01051 þôï
281 0.00988 îá
268 0.00942 ó
removed 'dat/russ/ptt/gen.1/gud-trunc-wds-summary.tex'
removed 'exp/russ/ptt/gen.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/russ/ptt/gen.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:27 by tex-make-sample-summary.sh
% Token and word counts for russ/ptt/gen.1/gud.wfr
%
\def\russptttruncgenPBgudTks{28445}
\def\russptttruncgenPBgudTksPct{100.0}
\def\russptttruncgenPBgudWds{4899}
\def\russptttruncgenPBgudWdsPct{17.2}
copied '/tmp/583056.file' -> 'exp/russ/ptt/gen.1/gud-trunc-wds-summary.tex'
removed '/tmp/583056.file'
creating running text file dat/russ/ptt/gen.1/bad.wdf
sample:
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
removed 'dat/russ/ptt/gen.1/bad.wfr'
creating the word frequency file dat/russ/ptt/gen.1/bad.wfr
the 10 most common words in dat/russ/ptt/gen.1/bad.tlw:
removed 'dat/russ/ptt/gen.1/bad-trunc-wds-summary.tex'
removed 'exp/russ/ptt/gen.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/russ/ptt/gen.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:27 by tex-make-sample-summary.sh
% Token and word counts for russ/ptt/gen.1/bad.wfr
%
\def\russptttruncgenPBbadTks{0}
\def\russptttruncgenPBbadTksPct{0.0}
\def\russptttruncgenPBbadWds{0}
\def\russptttruncgenPBbadWdsPct{0.0}
copied '/tmp/583100.file' -> 'exp/russ/ptt/gen.1/bad-trunc-wds-summary.tex'
removed '/tmp/583100.file'
... creating word files dat/russ/ptt/exo.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
22960 dat/russ/ptt/exo.1/trunc.tlw
removed 'dat/russ/ptt/exo.1/raw.tlw'
removed 'dat/russ/ptt/exo.1/gud.tlw'
removed 'dat/russ/ptt/exo.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
!! empty raw.tlw file '='
creating running text file dat/russ/ptt/exo.1/raw.wdf
sample:
ũïô éíåîá óųîïũ éúōáéėåũųč ëïôïōųå ũïûėé ũ
åįéðåô ó éáëïũïí ũïûėé ëáöäųę ó äïíïí óũïéí ōõũéí óéíåïî ėåũéę é éõäá
éóóáčáō úáũõėïî é ũåîéáíéî äáî é îåææáėéí įáä é áóéō ũóåč öå äõû
ðōïéóûåäûéč ïô þōåóė éáëïũá âųėï óåíøäåóņô á éïóéæ âųė õöå ũ
åįéðôå é õíåō éïóéæ é ũóå âōáôøņ åįï é ũåóø ōïä éč á óųîų éúōáéėåũų
ōáóðėïäéėéóø é ōáúíîïöéėéóø é ũïúōïóėé é õóéėéėéóø þōåúũųþáęîï é
îáðïėîéėáóø éíé úåíėņ ôá é ũïóóôáė ũ
åįéðôå îïũųę ãáōø ëïôïōųę îå úîáė éïóéæá é óëáúáė îáōïäõ óũïåíõ ũïô
îáōïä óųîïũ éúōáéėåũųč íîïįïþéóėåî é óéėøîåå îáó ðåōåčéôōéí öå åįï þôïâų
ïî îå ōáúíîïöáėóņ éîáþå ëïįäá óėõþéôóņ ũïęîá óïåäéîéôóņ é ïî ó îáûéíé
îåðōéņôåėņíé é ũïïōõöéôóņ ðōïôéũ îáó é ũųęäåô éú úåíėé îáûåę é ðïóôáũéėé
îáä îéí îáþáėøîéëïũ ōáâïô þôïâų éúîõōņėé åįï ôņöëéíé ōáâïôáíé é ïî
ðïóôōïéė æáōáïîõ ðéæïí é ōááíóåó įïōïäá äėņ úáðáóïũ îï þåí âïėåå
éúîõōņėé åįï ôåí âïėåå ïî õíîïöáėóņ é ôåí âïėåå ũïúōáóôáė ôáë þôï
ïðáóáėéóø óųîïũ éúōáéėåũųč é ðïôïíõ åįéðôņîå ó öåóôïëïóôøā ðōéîõöäáėé
óųîïũ éúōáéėåũųč ë ōáâïôáí é äåėáėé öéúîø éč įïōøëïā ïô ôņöëïę ōáâïôų
îáä įėéîïā é ëéōðéþáíé é ïô ũóņëïę ōáâïôų ðïėåũïę ïô ũóņëïę ōáâïôų ë
ëïôïōïę ðōéîõöäáėé éč ó öåóôïëïóôøā ãáōø åįéðåôóëéę ðïũåėåė ðïũéũáėøîųí
âáâëáí åũōåņîïë éú ëïéč ïäîïę éíņ ûéæōá á äōõįïę æõá é óëáúáė ëïįäá ũų
âõäåôå ðïũéũáôø õ åũōåņîïë ôï îáâėāäáęôå ðōé ōïäáč åóėé âõäåô óųî ôï
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
ðõôø äïëïėå ïîï îå ðïäîéíáėïóø éâï ïâėáëï įïóðïäîå óôïņėï îáä óëéîéåā
äîåí é ïįïîø âųė îïþøā ũ
îåę ðōåä įėáúáíé ũóåįï äïíá éúōáéėåũá ũï ũóå ðõôåûåóôũéå éč
removed 'dat/russ/ptt/exo.1/raw.wfr'
creating the word frequency file dat/russ/ptt/exo.1/raw.wfr
the 10 most common words in dat/russ/ptt/exo.1/raw.tlw:
2196 0.09564 é
503 0.02191 ũ
400 0.01742 åįï
388 0.01690 îá
331 0.01442 îå
323 0.01407 éú
244 0.01063 įïóðïäø
218 0.00949 ó
198 0.00862 äėņ
194 0.00845 éč
removed 'dat/russ/ptt/exo.1/raw-trunc-wds-summary.tex'
removed 'exp/russ/ptt/exo.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/russ/ptt/exo.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:27 by tex-make-sample-summary.sh
% Token and word counts for russ/ptt/exo.1/raw.wfr
%
\def\russptttruncexoPBrawTks{22960}
\def\russptttruncexoPBrawTksPct{100.0}
\def\russptttruncexoPBrawWds{4084}
\def\russptttruncexoPBrawWdsPct{17.8}
copied '/tmp/583156.file' -> 'exp/russ/ptt/exo.1/raw-trunc-wds-summary.tex'
removed '/tmp/583156.file'
creating running text file dat/russ/ptt/exo.1/gud.wdf
sample:
ũïô éíåîá óųîïũ éúōáéėåũųč ëïôïōųå ũïûėé ũ
åįéðåô ó éáëïũïí ũïûėé ëáöäųę ó äïíïí óũïéí ōõũéí óéíåïî ėåũéę é éõäá
éóóáčáō úáũõėïî é ũåîéáíéî äáî é îåææáėéí įáä é áóéō ũóåč öå äõû
ðōïéóûåäûéč ïô þōåóė éáëïũá âųėï óåíøäåóņô á éïóéæ âųė õöå ũ
åįéðôå é õíåō éïóéæ é ũóå âōáôøņ åįï é ũåóø ōïä éč á óųîų éúōáéėåũų
ōáóðėïäéėéóø é ōáúíîïöéėéóø é ũïúōïóėé é õóéėéėéóø þōåúũųþáęîï é
îáðïėîéėáóø éíé úåíėņ ôá é ũïóóôáė ũ
åįéðôå îïũųę ãáōø ëïôïōųę îå úîáė éïóéæá é óëáúáė îáōïäõ óũïåíõ ũïô
îáōïä óųîïũ éúōáéėåũųč íîïįïþéóėåî é óéėøîåå îáó ðåōåčéôōéí öå åįï þôïâų
ïî îå ōáúíîïöáėóņ éîáþå ëïįäá óėõþéôóņ ũïęîá óïåäéîéôóņ é ïî ó îáûéíé
îåðōéņôåėņíé é ũïïōõöéôóņ ðōïôéũ îáó é ũųęäåô éú úåíėé îáûåę é ðïóôáũéėé
îáä îéí îáþáėøîéëïũ ōáâïô þôïâų éúîõōņėé åįï ôņöëéíé ōáâïôáíé é ïî
ðïóôōïéė æáōáïîõ ðéæïí é ōááíóåó įïōïäá äėņ úáðáóïũ îï þåí âïėåå
éúîõōņėé åįï ôåí âïėåå ïî õíîïöáėóņ é ôåí âïėåå ũïúōáóôáė ôáë þôï
ïðáóáėéóø óųîïũ éúōáéėåũųč é ðïôïíõ åįéðôņîå ó öåóôïëïóôøā ðōéîõöäáėé
óųîïũ éúōáéėåũųč ë ōáâïôáí é äåėáėé öéúîø éč įïōøëïā ïô ôņöëïę ōáâïôų
îáä įėéîïā é ëéōðéþáíé é ïô ũóņëïę ōáâïôų ðïėåũïę ïô ũóņëïę ōáâïôų ë
ëïôïōïę ðōéîõöäáėé éč ó öåóôïëïóôøā ãáōø åįéðåôóëéę ðïũåėåė ðïũéũáėøîųí
âáâëáí åũōåņîïë éú ëïéč ïäîïę éíņ ûéæōá á äōõįïę æõá é óëáúáė ëïįäá ũų
âõäåôå ðïũéũáôø õ åũōåņîïë ôï îáâėāäáęôå ðōé ōïäáč åóėé âõäåô óųî ôï
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
ðõôø äïëïėå ïîï îå ðïäîéíáėïóø éâï ïâėáëï įïóðïäîå óôïņėï îáä óëéîéåā
äîåí é ïįïîø âųė îïþøā ũ
îåę ðōåä įėáúáíé ũóåįï äïíá éúōáéėåũá ũï ũóå ðõôåûåóôũéå éč
removed 'dat/russ/ptt/exo.1/gud.wfr'
creating the word frequency file dat/russ/ptt/exo.1/gud.wfr
the 10 most common words in dat/russ/ptt/exo.1/gud.tlw:
2196 0.09564 é
503 0.02191 ũ
400 0.01742 åįï
388 0.01690 îá
331 0.01442 îå
323 0.01407 éú
244 0.01063 įïóðïäø
218 0.00949 ó
198 0.00862 äėņ
194 0.00845 éč
removed 'dat/russ/ptt/exo.1/gud-trunc-wds-summary.tex'
removed 'exp/russ/ptt/exo.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/russ/ptt/exo.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:27 by tex-make-sample-summary.sh
% Token and word counts for russ/ptt/exo.1/gud.wfr
%
\def\russptttruncexoPBgudTks{22960}
\def\russptttruncexoPBgudTksPct{100.0}
\def\russptttruncexoPBgudWds{4084}
\def\russptttruncexoPBgudWdsPct{17.8}
copied '/tmp/583200.file' -> 'exp/russ/ptt/exo.1/gud-trunc-wds-summary.tex'
removed '/tmp/583200.file'
creating running text file dat/russ/ptt/exo.1/bad.wdf
sample:
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
removed 'dat/russ/ptt/exo.1/bad.wfr'
creating the word frequency file dat/russ/ptt/exo.1/bad.wfr
the 10 most common words in dat/russ/ptt/exo.1/bad.tlw:
removed 'dat/russ/ptt/exo.1/bad-trunc-wds-summary.tex'
removed 'exp/russ/ptt/exo.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/russ/ptt/exo.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:27 by tex-make-sample-summary.sh
% Token and word counts for russ/ptt/exo.1/bad.wfr
%
\def\russptttruncexoPBbadTks{0}
\def\russptttruncexoPBbadTksPct{0.0}
\def\russptttruncexoPBbadWds{0}
\def\russptttruncexoPBbadWdsPct{0.0}
copied '/tmp/583244.file' -> 'exp/russ/ptt/exo.1/bad-trunc-wds-summary.tex'
removed '/tmp/583244.file'
... creating word files dat/russ/ptt/num.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
22530 dat/russ/ptt/num.1/trunc.tlw
removed 'dat/russ/ptt/num.1/raw.tlw'
removed 'dat/russ/ptt/num.1/gud.tlw'
removed 'dat/russ/ptt/num.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
!! empty raw.tlw file '='
creating running text file dat/russ/ptt/num.1/raw.wdf
sample:
é óëáúáė įïóðïäø íïéóåā ũ
ðõóôųîå óéîáęóëïę ũ
óëéîéé óïâōáîéņ ũ
ðåōũųę äåîø ũôïōïįï íåóņãá ũï ũôïōïę įïä ðï ũųčïäå éč éú úåíėé
åįéðåôóëïę įïũïōņ éóþéóėéôå ũóå ïâýåóôũï óųîïũ éúōáéėåũųč ðï ōïäáí éč ðï
óåíåęóôũáí éč ðï þéóėõ éíåî ũóåč íõöåóëïįï ðïėá ðïįïėïũîï ïô äũáäãáôé
ėåô é ũųûå ũóåč įïäîųč äėņ ũïęîų õ éúōáéėņ ðï ïðïėþåîéņí éč éóþéóėéôå éč
ôų é ááōïî ó ũáíé äïėöîų âųôø éú ëáöäïįï ëïėåîá ðï ïäîïíõ þåėïũåëõ
ëïôïōųę ũ
ōïäå óũïåí åóôø įėáũîųę é ũïô éíåîá íõöåę ëïôïōųå âõäõô ó ũáíé ïô ōõũéíá
åėéãõō óųî ûåäåõōá ïô óéíåïîá ûåėõíééė óųî ãõōéûáääáņ ïô éõäų îááóóïî
óųî áíéîáäáũá ïô éóóáčáōá îáæáîáéė óųî ãõáōá ïô úáũõėïîá åėéáũ óųî
čåėïîá ïô óųîïũ éïóéæá ïô åæōåíá åėéûáíá óųî áííéõäá ïô íáîáóóéé
įáíáėééė óųî ðåäáãõōá ïô ũåîéáíéîá áũéäáî óųî įéäåïîéņ ïô äáîá áčéåúåō
óųî áííéûáääáņ ïô áóéōá ðáįééė óųî ïčōáîá ïô įáäá åėéáóáæ óųî ōåįõéėá ïô
îåææáėéíá áčéōá óųî åîáîá üôï éúâōáîîųå íõöé ïâýåóôũá îáþáėøîéëé ëïėåî
ïôãïũ óũïéč įėáũų ôųóņþ éúōáéėåũųč é ũúņė íïéóåę é ááōïî íõöåę óéč
ëïôïōųå îáúũáîų ðïéíåîîï é óïâōáėé ïîé ũóå ïâýåóôũï ũ
ðåōũųę äåîø ũôïōïįï íåóņãá é ïâĸņũéėé ïîé ōïäïóėïũéņ óũïé ðï ōïäáí éč ðï
óåíåęóôũáí éč ðï þéóėõ éíåî ïô äũáäãáôé ėåô é ũųûå ðïįïėïũîï ëáë ðïũåėåė
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
ëïėåîå ðėåíåîé ïôãá éč óéé óõôø úáðïũåäé é ðïóôáîïũėåîéņ ëïôïōųå äáė
įïóðïäø óųîáí éúōáéėåũųí þōåú íïéóåņ îá ōáũîéîáč íïáũéôóëéč õ éïōäáîá
ðōïôéũ éåōéčïîá
removed 'dat/russ/ptt/num.1/raw.wfr'
creating the word frequency file dat/russ/ptt/num.1/raw.wfr
the 10 most common words in dat/russ/ptt/num.1/raw.tlw:
1944 0.08628 é
632 0.02805 ũ
307 0.01363 éč
286 0.01269 ðï
266 0.01181 îá
256 0.01136 ïô
252 0.01119 éú
237 0.01052 åįï
233 0.01034 îå
189 0.00839 óųîïũ
removed 'dat/russ/ptt/num.1/raw-trunc-wds-summary.tex'
removed 'exp/russ/ptt/num.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/russ/ptt/num.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:27 by tex-make-sample-summary.sh
% Token and word counts for russ/ptt/num.1/raw.wfr
%
\def\russptttruncnumPBrawTks{22530}
\def\russptttruncnumPBrawTksPct{100.0}
\def\russptttruncnumPBrawWds{3952}
\def\russptttruncnumPBrawWdsPct{17.5}
copied '/tmp/583300.file' -> 'exp/russ/ptt/num.1/raw-trunc-wds-summary.tex'
removed '/tmp/583300.file'
creating running text file dat/russ/ptt/num.1/gud.wdf
sample:
é óëáúáė įïóðïäø íïéóåā ũ
ðõóôųîå óéîáęóëïę ũ
óëéîéé óïâōáîéņ ũ
ðåōũųę äåîø ũôïōïįï íåóņãá ũï ũôïōïę įïä ðï ũųčïäå éč éú úåíėé
åįéðåôóëïę įïũïōņ éóþéóėéôå ũóå ïâýåóôũï óųîïũ éúōáéėåũųč ðï ōïäáí éč ðï
óåíåęóôũáí éč ðï þéóėõ éíåî ũóåč íõöåóëïįï ðïėá ðïįïėïũîï ïô äũáäãáôé
ėåô é ũųûå ũóåč įïäîųč äėņ ũïęîų õ éúōáéėņ ðï ïðïėþåîéņí éč éóþéóėéôå éč
ôų é ááōïî ó ũáíé äïėöîų âųôø éú ëáöäïįï ëïėåîá ðï ïäîïíõ þåėïũåëõ
ëïôïōųę ũ
ōïäå óũïåí åóôø įėáũîųę é ũïô éíåîá íõöåę ëïôïōųå âõäõô ó ũáíé ïô ōõũéíá
åėéãõō óųî ûåäåõōá ïô óéíåïîá ûåėõíééė óųî ãõōéûáääáņ ïô éõäų îááóóïî
óųî áíéîáäáũá ïô éóóáčáōá îáæáîáéė óųî ãõáōá ïô úáũõėïîá åėéáũ óųî
čåėïîá ïô óųîïũ éïóéæá ïô åæōåíá åėéûáíá óųî áííéõäá ïô íáîáóóéé
įáíáėééė óųî ðåäáãõōá ïô ũåîéáíéîá áũéäáî óųî įéäåïîéņ ïô äáîá áčéåúåō
óųî áííéûáääáņ ïô áóéōá ðáįééė óųî ïčōáîá ïô įáäá åėéáóáæ óųî ōåįõéėá ïô
îåææáėéíá áčéōá óųî åîáîá üôï éúâōáîîųå íõöé ïâýåóôũá îáþáėøîéëé ëïėåî
ïôãïũ óũïéč įėáũų ôųóņþ éúōáéėåũųč é ũúņė íïéóåę é ááōïî íõöåę óéč
ëïôïōųå îáúũáîų ðïéíåîîï é óïâōáėé ïîé ũóå ïâýåóôũï ũ
ðåōũųę äåîø ũôïōïįï íåóņãá é ïâĸņũéėé ïîé ōïäïóėïũéņ óũïé ðï ōïäáí éč ðï
óåíåęóôũáí éč ðï þéóėõ éíåî ïô äũáäãáôé ėåô é ũųûå ðïįïėïũîï ëáë ðïũåėåė
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
ëïėåîå ðėåíåîé ïôãá éč óéé óõôø úáðïũåäé é ðïóôáîïũėåîéņ ëïôïōųå äáė
įïóðïäø óųîáí éúōáéėåũųí þōåú íïéóåņ îá ōáũîéîáč íïáũéôóëéč õ éïōäáîá
ðōïôéũ éåōéčïîá
removed 'dat/russ/ptt/num.1/gud.wfr'
creating the word frequency file dat/russ/ptt/num.1/gud.wfr
the 10 most common words in dat/russ/ptt/num.1/gud.tlw:
1944 0.08628 é
632 0.02805 ũ
307 0.01363 éč
286 0.01269 ðï
266 0.01181 îá
256 0.01136 ïô
252 0.01119 éú
237 0.01052 åįï
233 0.01034 îå
189 0.00839 óųîïũ
removed 'dat/russ/ptt/num.1/gud-trunc-wds-summary.tex'
removed 'exp/russ/ptt/num.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/russ/ptt/num.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:27 by tex-make-sample-summary.sh
% Token and word counts for russ/ptt/num.1/gud.wfr
%
\def\russptttruncnumPBgudTks{22530}
\def\russptttruncnumPBgudTksPct{100.0}
\def\russptttruncnumPBgudWds{3952}
\def\russptttruncnumPBgudWdsPct{17.5}
copied '/tmp/583344.file' -> 'exp/russ/ptt/num.1/gud-trunc-wds-summary.tex'
removed '/tmp/583344.file'
creating running text file dat/russ/ptt/num.1/bad.wdf
sample:
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
removed 'dat/russ/ptt/num.1/bad.wfr'
creating the word frequency file dat/russ/ptt/num.1/bad.wfr
the 10 most common words in dat/russ/ptt/num.1/bad.tlw:
removed 'dat/russ/ptt/num.1/bad-trunc-wds-summary.tex'
removed 'exp/russ/ptt/num.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/russ/ptt/num.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:27 by tex-make-sample-summary.sh
% Token and word counts for russ/ptt/num.1/bad.wfr
%
\def\russptttruncnumPBbadTks{0}
\def\russptttruncnumPBbadTksPct{0.0}
\def\russptttruncnumPBbadWds{0}
\def\russptttruncnumPBbadWdsPct{0.0}
copied '/tmp/583388.file' -> 'exp/russ/ptt/num.1/bad-trunc-wds-summary.tex'
removed '/tmp/583388.file'
... creating word files dat/russ/ptt/lev.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
16901 dat/russ/ptt/lev.1/trunc.tlw
removed 'dat/russ/ptt/lev.1/raw.tlw'
removed 'dat/russ/ptt/lev.1/gud.tlw'
removed 'dat/russ/ptt/lev.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
!! empty raw.tlw file '='
creating running text file dat/russ/ptt/lev.1/raw.wdf
sample:
é ũïúúũáė įïóðïäø ë íïéóåā é óëáúáė åíõ éú óëéîéé óïâōáîéņ įïũïōņ ïâĸņũé
óųîáí éúōáéėåũųí é óëáöé éí ëïįäá ëôï éú ũáó čïþåô ðōéîåóôé öåōôũõ
įïóðïäõ ôï åóėé éú óëïôá ðōéîïóéôå öåōôũõ ũáûõ éú óëïôá ëōõðîïįï é
íåėëïįï åóėé öåōôũá åįï åóôø ũóåóïööåîéå éú ëōõðîïįï óëïôá ðõóôø
ðōéîåóåô åå íõöåóëïįï ðïėá âåú ðïōïëá ðõóôø ðōéũåäåô åå ë äũåōņí óëéîéé
óïâōáîéņ þôïâų ðōéïâōåóôé åíõ âėáįïũïėåîéå ðōåä įïóðïäïí é ũïúėïöéô ōõëõ
óũïā îá įïėïũõ öåōôũų ũóåóïööåîéņ é ðōéïâōåôåô ïî âėáįïũïėåîéå ũï
ïþéýåîéå įōåčïũ åįï é úáëïėåô ôåėøãá ðōåä įïóðïäïí óųîų öå ááōïîïũų
óũņýåîîéëé ðōéîåóõô ëōïũø é ðïëōïðņô ëōïũøā óï ũóåč óôïōïî îá öåōôũåîîéë
ëïôïōųę õ ũčïäá óëéîéé óïâōáîéņ é óîéíåô ëïöõ ó öåōôũų ũóåóïööåîéņ é
ōáóóåþåô åå îá þáóôé óųîų öå ááōïîïũų óũņýåîîéëé ðïėïöáô îá öåōôũåîîéë
ïįïîø é îá ïįîå ōáúėïöáô äōïũá é ōáúėïöáô óųîų ááōïîïũų óũņýåîîéëé þáóôé
įïėïũõ é ôõë îá äōïũáč ëïôïōųå îá ïįîå îá öåōôũåîîéëå á ũîõôōåîîïóôé
öåōôũų é îïįé åå ũųíïåô ïî ũïäïā é óïööåô óũņýåîîéë ũóå îá öåōôũåîîéëå
üôï ũóåóïööåîéå öåōôũá âėáįïõčáîéå ðōéņôîïå įïóðïäõ åóėé öåōôũá
ũóåóïööåîéņ åįï éú íåėëïįï óëïôá éú ïũåã éėé éú ëïú ðõóôø ðōéîåóåô åå
íõöåóëïįï ðïėá âåú ðïōïëá é úáëïėåô åå ðōåä įïóðïäïí îá óåũåōîïę óôïōïîå
öåōôũåîîéëá é óųîų ááōïîïũų óũņýåîîéëé ðïëōïðņô ëōïũøā åå îá öåōôũåîîéë
óï ũóåč óôïōïî é ōáóóåëõô åå îá þáóôé ïôäåėéũ įïėïũõ åå é ôõë åå é
ōáúėïöéô éč óũņýåîîéë îá äōïũáč ëïôïōųå îá ïįîå îá öåōôũåîîéëå á
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
îå äïėöîï úáíåîņôø åįï åóėé öå ëôï úáíåîéô åįï ôï é óáíï ïîï é úáíåî åįï
âõäåô óũņôųîåā é îå íïöåô âųôø ũųëõðėåîï ũïô úáðïũåäé ëïôïōųå úáðïũåäáė
įïóðïäø íïéóåā äėņ óųîïũ éúōáéėåũųč îá įïōå óéîáå
removed 'dat/russ/ptt/lev.1/raw.wfr'
creating the word frequency file dat/russ/ptt/lev.1/raw.wfr
the 10 most common words in dat/russ/ptt/lev.1/raw.tlw:
1285 0.07603 é
439 0.02597 îá
355 0.02100 ũ
321 0.01899 îå
273 0.01615 åįï
190 0.01124 éú
176 0.01041 ïî
172 0.01018 åóėé
165 0.00976 ôï
154 0.00911 âõäåô
removed 'dat/russ/ptt/lev.1/raw-trunc-wds-summary.tex'
removed 'exp/russ/ptt/lev.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/russ/ptt/lev.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:28 by tex-make-sample-summary.sh
% Token and word counts for russ/ptt/lev.1/raw.wfr
%
\def\russptttrunclevPBrawTks{16901}
\def\russptttrunclevPBrawTksPct{100.0}
\def\russptttrunclevPBrawWds{2659}
\def\russptttrunclevPBrawWdsPct{15.7}
copied '/tmp/583444.file' -> 'exp/russ/ptt/lev.1/raw-trunc-wds-summary.tex'
removed '/tmp/583444.file'
creating running text file dat/russ/ptt/lev.1/gud.wdf
sample:
é ũïúúũáė įïóðïäø ë íïéóåā é óëáúáė åíõ éú óëéîéé óïâōáîéņ įïũïōņ ïâĸņũé
óųîáí éúōáéėåũųí é óëáöé éí ëïįäá ëôï éú ũáó čïþåô ðōéîåóôé öåōôũõ
įïóðïäõ ôï åóėé éú óëïôá ðōéîïóéôå öåōôũõ ũáûõ éú óëïôá ëōõðîïįï é
íåėëïįï åóėé öåōôũá åįï åóôø ũóåóïööåîéå éú ëōõðîïįï óëïôá ðõóôø
ðōéîåóåô åå íõöåóëïįï ðïėá âåú ðïōïëá ðõóôø ðōéũåäåô åå ë äũåōņí óëéîéé
óïâōáîéņ þôïâų ðōéïâōåóôé åíõ âėáįïũïėåîéå ðōåä įïóðïäïí é ũïúėïöéô ōõëõ
óũïā îá įïėïũõ öåōôũų ũóåóïööåîéņ é ðōéïâōåôåô ïî âėáįïũïėåîéå ũï
ïþéýåîéå įōåčïũ åįï é úáëïėåô ôåėøãá ðōåä įïóðïäïí óųîų öå ááōïîïũų
óũņýåîîéëé ðōéîåóõô ëōïũø é ðïëōïðņô ëōïũøā óï ũóåč óôïōïî îá öåōôũåîîéë
ëïôïōųę õ ũčïäá óëéîéé óïâōáîéņ é óîéíåô ëïöõ ó öåōôũų ũóåóïööåîéņ é
ōáóóåþåô åå îá þáóôé óųîų öå ááōïîïũų óũņýåîîéëé ðïėïöáô îá öåōôũåîîéë
ïįïîø é îá ïįîå ōáúėïöáô äōïũá é ōáúėïöáô óųîų ááōïîïũų óũņýåîîéëé þáóôé
įïėïũõ é ôõë îá äōïũáč ëïôïōųå îá ïįîå îá öåōôũåîîéëå á ũîõôōåîîïóôé
öåōôũų é îïįé åå ũųíïåô ïî ũïäïā é óïööåô óũņýåîîéë ũóå îá öåōôũåîîéëå
üôï ũóåóïööåîéå öåōôũá âėáįïõčáîéå ðōéņôîïå įïóðïäõ åóėé öåōôũá
ũóåóïööåîéņ åįï éú íåėëïįï óëïôá éú ïũåã éėé éú ëïú ðõóôø ðōéîåóåô åå
íõöåóëïįï ðïėá âåú ðïōïëá é úáëïėåô åå ðōåä įïóðïäïí îá óåũåōîïę óôïōïîå
öåōôũåîîéëá é óųîų ááōïîïũų óũņýåîîéëé ðïëōïðņô ëōïũøā åå îá öåōôũåîîéë
óï ũóåč óôïōïî é ōáóóåëõô åå îá þáóôé ïôäåėéũ įïėïũõ åå é ôõë åå é
ōáúėïöéô éč óũņýåîîéë îá äōïũáč ëïôïōųå îá ïįîå îá öåōôũåîîéëå á
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
îå äïėöîï úáíåîņôø åįï åóėé öå ëôï úáíåîéô åįï ôï é óáíï ïîï é úáíåî åįï
âõäåô óũņôųîåā é îå íïöåô âųôø ũųëõðėåîï ũïô úáðïũåäé ëïôïōųå úáðïũåäáė
įïóðïäø íïéóåā äėņ óųîïũ éúōáéėåũųč îá įïōå óéîáå
removed 'dat/russ/ptt/lev.1/gud.wfr'
creating the word frequency file dat/russ/ptt/lev.1/gud.wfr
the 10 most common words in dat/russ/ptt/lev.1/gud.tlw:
1285 0.07603 é
439 0.02597 îá
355 0.02100 ũ
321 0.01899 îå
273 0.01615 åįï
190 0.01124 éú
176 0.01041 ïî
172 0.01018 åóėé
165 0.00976 ôï
154 0.00911 âõäåô
removed 'dat/russ/ptt/lev.1/gud-trunc-wds-summary.tex'
removed 'exp/russ/ptt/lev.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/russ/ptt/lev.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:28 by tex-make-sample-summary.sh
% Token and word counts for russ/ptt/lev.1/gud.wfr
%
\def\russptttrunclevPBgudTks{16901}
\def\russptttrunclevPBgudTksPct{100.0}
\def\russptttrunclevPBgudWds{2659}
\def\russptttrunclevPBgudWdsPct{15.7}
copied '/tmp/583488.file' -> 'exp/russ/ptt/lev.1/gud-trunc-wds-summary.tex'
removed '/tmp/583488.file'
creating running text file dat/russ/ptt/lev.1/bad.wdf
sample:
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
removed 'dat/russ/ptt/lev.1/bad.wfr'
creating the word frequency file dat/russ/ptt/lev.1/bad.wfr
the 10 most common words in dat/russ/ptt/lev.1/bad.tlw:
removed 'dat/russ/ptt/lev.1/bad-trunc-wds-summary.tex'
removed 'exp/russ/ptt/lev.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/russ/ptt/lev.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:28 by tex-make-sample-summary.sh
% Token and word counts for russ/ptt/lev.1/bad.wfr
%
\def\russptttrunclevPBbadTks{0}
\def\russptttrunclevPBbadTksPct{0.0}
\def\russptttrunclevPBbadWds{0}
\def\russptttrunclevPBbadWdsPct{0.0}
copied '/tmp/583532.file' -> 'exp/russ/ptt/lev.1/bad-trunc-wds-summary.tex'
removed '/tmp/583532.file'
... creating word files dat/russ/ptt/deu.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
20988 dat/russ/ptt/deu.1/trunc.tlw
removed 'dat/russ/ptt/deu.1/raw.tlw'
removed 'dat/russ/ptt/deu.1/gud.tlw'
removed 'dat/russ/ptt/deu.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
!! empty raw.tlw file '='
creating running text file dat/russ/ptt/deu.1/raw.wdf
sample:
óéé óõôø óėïũá ëïôïōųå įïũïōéė íïéóåę ũóåí éúōáéėøôņîáí úá éïōäáîïí ũ
ðõóôųîå îá ōáũîéîå ðōïôéũ óõæá íåöäõ æáōáîïí é ôïæåėïí é ėáũáîïí é
áóéōïæïí é äéúáįáũïí ũ
ōáóóôïņîéé ïäéîîáäãáôé äîåę ðõôé ïô čïōéũá ðï äïōïįå ïô įïōų óåéō ë
ëáäåó ũáōîé óïōïëïũïįï įïäá ïäéîîáäãáôïįï íåóņãá ũ
ðåōũųę äåîø íåóņãá įïũïōéė íïéóåę óųîáí éúōáéėåũųí ũóå þôï úáðïũåäáė åíõ
įïóðïäø ï îéč ðï õâéåîéé éí óéįïîá ãáōņ áíïōōåęóëïįï ëïôïōųę öéė ũ
åóåũïîå é ïįá ãáōņ ũáóáîóëïįï ëïôïōųę öéė ũ
áûôåōïæå ũ
åäōåé úá éïōäáîïí ũ
úåíėå íïáũéôóëïę îáþáė íïéóåę éúĸņóîņôø úáëïî óåę é óëáúáė įïóðïäø âïį
îáû įïũïōéė îáí ũ
čïōéũå é óëáúáė ðïėîï ũáí öéôø îá įïōå óåę ïâōáôéôåóø ïôðōáũøôåóø ũ
ðõôø é ðïęäéôå îá įïōõ áíïōōååũ é ëï ũóåí óïóåäņí éč îá ōáũîéîõ îá įïōõ
îá îéúëéå íåóôá é îá āöîųę ëōáę é ë âåōåįáí íïōņ ũ
úåíėā čáîááîóëõā é ë ėéũáîõ äáöå äï ōåëé ũåėéëïę ōåëé åũæōáôá ũïô ņ äáā
ũáí úåíėā óéā ðïęäéôå ũïúøíéôå ũ
îáóėåäéå úåíėā ëïôïōõā įïóðïäø ó ëėņôũïā ïâåýáė äáôø ïôãáí ũáûéí áũōááíõ
éóááëõ é éáëïũõ éí é ðïôïíóôũõ éč é ņ óëáúáė ũáí ũ
ôï ũōåíņ îå íïįõ ïäéî ũïäéôø ũáó įïóðïäø âïį ũáû ōáúíîïöéė ũáó é ũïô ũų
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
úåíėå åįéðåôóëïę îáä æáōáïîïí é îáä ũóåíé ōáâáíé åįï é îáä ũóåā úåíėåā
åįï é ðï ōõëå óéėøîïę é ðï ũåėéëéí þõäåóáí ëïôïōųå íïéóåę óïũåōûéė ðōåä
įėáúáíé ũóåįï éúōáéėņ
removed 'dat/russ/ptt/deu.1/raw.wfr'
creating the word frequency file dat/russ/ptt/deu.1/raw.wfr
the 10 most common words in dat/russ/ptt/deu.1/raw.tlw:
1726 0.08224 é
524 0.02497 îå
459 0.02187 ũ
345 0.01644 įïóðïäø
330 0.01572 îá
306 0.01458 åįï
215 0.01024 ôåâņ
207 0.00986 ôų
197 0.00939 âïį
190 0.00905 éč
removed 'dat/russ/ptt/deu.1/raw-trunc-wds-summary.tex'
removed 'exp/russ/ptt/deu.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/russ/ptt/deu.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:28 by tex-make-sample-summary.sh
% Token and word counts for russ/ptt/deu.1/raw.wfr
%
\def\russptttruncdeuPBrawTks{20988}
\def\russptttruncdeuPBrawTksPct{100.0}
\def\russptttruncdeuPBrawWds{3913}
\def\russptttruncdeuPBrawWdsPct{18.6}
copied '/tmp/583588.file' -> 'exp/russ/ptt/deu.1/raw-trunc-wds-summary.tex'
removed '/tmp/583588.file'
creating running text file dat/russ/ptt/deu.1/gud.wdf
sample:
óéé óõôø óėïũá ëïôïōųå įïũïōéė íïéóåę ũóåí éúōáéėøôņîáí úá éïōäáîïí ũ
ðõóôųîå îá ōáũîéîå ðōïôéũ óõæá íåöäõ æáōáîïí é ôïæåėïí é ėáũáîïí é
áóéōïæïí é äéúáįáũïí ũ
ōáóóôïņîéé ïäéîîáäãáôé äîåę ðõôé ïô čïōéũá ðï äïōïįå ïô įïōų óåéō ë
ëáäåó ũáōîé óïōïëïũïįï įïäá ïäéîîáäãáôïįï íåóņãá ũ
ðåōũųę äåîø íåóņãá įïũïōéė íïéóåę óųîáí éúōáéėåũųí ũóå þôï úáðïũåäáė åíõ
įïóðïäø ï îéč ðï õâéåîéé éí óéįïîá ãáōņ áíïōōåęóëïįï ëïôïōųę öéė ũ
åóåũïîå é ïįá ãáōņ ũáóáîóëïįï ëïôïōųę öéė ũ
áûôåōïæå ũ
åäōåé úá éïōäáîïí ũ
úåíėå íïáũéôóëïę îáþáė íïéóåę éúĸņóîņôø úáëïî óåę é óëáúáė įïóðïäø âïį
îáû įïũïōéė îáí ũ
čïōéũå é óëáúáė ðïėîï ũáí öéôø îá įïōå óåę ïâōáôéôåóø ïôðōáũøôåóø ũ
ðõôø é ðïęäéôå îá įïōõ áíïōōååũ é ëï ũóåí óïóåäņí éč îá ōáũîéîõ îá įïōõ
îá îéúëéå íåóôá é îá āöîųę ëōáę é ë âåōåįáí íïōņ ũ
úåíėā čáîááîóëõā é ë ėéũáîõ äáöå äï ōåëé ũåėéëïę ōåëé åũæōáôá ũïô ņ äáā
ũáí úåíėā óéā ðïęäéôå ũïúøíéôå ũ
îáóėåäéå úåíėā ëïôïōõā įïóðïäø ó ëėņôũïā ïâåýáė äáôø ïôãáí ũáûéí áũōááíõ
éóááëõ é éáëïũõ éí é ðïôïíóôũõ éč é ņ óëáúáė ũáí ũ
ôï ũōåíņ îå íïįõ ïäéî ũïäéôø ũáó įïóðïäø âïį ũáû ōáúíîïöéė ũáó é ũïô ũų
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
úåíėå åįéðåôóëïę îáä æáōáïîïí é îáä ũóåíé ōáâáíé åįï é îáä ũóåā úåíėåā
åįï é ðï ōõëå óéėøîïę é ðï ũåėéëéí þõäåóáí ëïôïōųå íïéóåę óïũåōûéė ðōåä
įėáúáíé ũóåįï éúōáéėņ
removed 'dat/russ/ptt/deu.1/gud.wfr'
creating the word frequency file dat/russ/ptt/deu.1/gud.wfr
the 10 most common words in dat/russ/ptt/deu.1/gud.tlw:
1726 0.08224 é
524 0.02497 îå
459 0.02187 ũ
345 0.01644 įïóðïäø
330 0.01572 îá
306 0.01458 åįï
215 0.01024 ôåâņ
207 0.00986 ôų
197 0.00939 âïį
190 0.00905 éč
removed 'dat/russ/ptt/deu.1/gud-trunc-wds-summary.tex'
removed 'exp/russ/ptt/deu.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/russ/ptt/deu.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:28 by tex-make-sample-summary.sh
% Token and word counts for russ/ptt/deu.1/gud.wfr
%
\def\russptttruncdeuPBgudTks{20988}
\def\russptttruncdeuPBgudTksPct{100.0}
\def\russptttruncdeuPBgudWds{3913}
\def\russptttruncdeuPBgudWdsPct{18.6}
copied '/tmp/583632.file' -> 'exp/russ/ptt/deu.1/gud-trunc-wds-summary.tex'
removed '/tmp/583632.file'
creating running text file dat/russ/ptt/deu.1/bad.wdf
sample:
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
removed 'dat/russ/ptt/deu.1/bad.wfr'
creating the word frequency file dat/russ/ptt/deu.1/bad.wfr
the 10 most common words in dat/russ/ptt/deu.1/bad.tlw:
removed 'dat/russ/ptt/deu.1/bad-trunc-wds-summary.tex'
removed 'exp/russ/ptt/deu.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/russ/ptt/deu.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:28 by tex-make-sample-summary.sh
% Token and word counts for russ/ptt/deu.1/bad.wfr
%
\def\russptttruncdeuPBbadTks{0}
\def\russptttruncdeuPBbadTksPct{0.0}
\def\russptttruncdeuPBbadWds{0}
\def\russptttruncdeuPBbadWdsPct{0.0}
copied '/tmp/583676.file' -> 'exp/russ/ptt/deu.1/bad-trunc-wds-summary.tex'
removed '/tmp/583676.file'
... creating word files dat/russ/ptt/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
35027 dat/russ/ptt/tot.1/trunc.tlw
removed 'dat/russ/ptt/tot.1/raw.tlw'
removed 'dat/russ/ptt/tot.1/gud.tlw'
removed 'dat/russ/ptt/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
!! empty raw.tlw file '='
creating running text file dat/russ/ptt/tot.1/raw.wdf
sample:
ũ
îáþáėå óïôũïōéė âïį îåâï é úåíėā úåíėņ öå âųėá âåúũéäîá é ðõóôá é ôøíá
îáä âåúäîïā é äõč âïöéę îïóéėóņ îáä ũïäïā é óëáúáė âïį äá âõäåô óũåô é
óôáė óũåô é õũéäåė âïį óũåô þôï ïî čïōïû é ïôäåėéė âïį óũåô ïô ôøíų é
îáúũáė âïį óũåô äîåí á ôøíõ îïþøā é âųė ũåþåō é âųėï õôōï äåîø ïäéî é
óëáúáė âïį äá âõäåô ôũåōäø ðïóōåäé ũïäų é äá ïôäåėņåô ïîá ũïäõ ïô ũïäų é
óïúäáė âïį ôũåōäø é ïôäåėéė ũïäõ ëïôïōáņ ðïä ôũåōäøā ïô ũïäų ëïôïōáņ îáä
ôũåōäøā é óôáėï ôáë é îáúũáė âïį ôũåōäø îåâïí é âųė ũåþåō é âųėï õôōï
äåîø ũôïōïę é óëáúáė âïį äá óïâåōåôóņ ũïäá ëïôïōáņ ðïä îåâïí ũ
ïäîï íåóôï é äá ņũéôóņ óõûá é óôáėï ôáë é îáúũáė âïį óõûõ úåíėåā á
óïâōáîéå ũïä îáúũáė íïōņíé é õũéäåė âïį þôï üôï čïōïûï é óëáúáė âïį äá
ðōïéúōáóôéô úåíėņ úåėåîø ôōáũõ óåāýõā óåíņ äåōåũï ðėïäïũéôïå ðōéîïóņýåå
ðï ōïäõ óũïåíõ ðėïä ũ
ëïôïōïí óåíņ åįï îá úåíėå é óôáėï ôáë é ðōïéúũåėá úåíėņ úåėåîø ôōáũõ
óåāýõā óåíņ ðï ōïäõ åå é äåōåũï ðōéîïóņýåå ðėïä ũ
ëïôïōïí óåíņ åįï ðï ōïäõ åįï é õũéäåė âïį þôï üôï čïōïûï é âųė ũåþåō é
âųėï õôōï äåîø ôōåôéę é óëáúáė âïį äá âõäõô óũåôéėá îá ôũåōäé îåâåóîïę
äėņ ïôäåėåîéņ äîņ ïô îïþé é äėņ úîáíåîéę é ũōåíåî é äîåę é įïäïũ é äá
âõäõô ïîé óũåôéėøîéëáíé îá ôũåōäé îåâåóîïę þôïâų óũåôéôø îá úåíėā é
óôáėï ôáë é óïúäáė âïį äũá óũåôéėá ũåėéëéå óũåôéėï âïėøûåå äėņ
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
ōõëáč íïéč é îáðéóáė ïî îá óëōéöáėņč ëáë îáðéóáîï âųėï ðōåöäå ôå äåóņôø
óėïũ ëïôïōųå éúōåë ũáí įïóðïäø îá įïōå éú óōåäų ïįîņ ũ
äåîø óïâōáîéņ é ïôäáė éč įïóðïäø íîå é
removed 'dat/russ/ptt/tot.1/raw.wfr'
creating the word frequency file dat/russ/ptt/tot.1/raw.wfr
the 10 most common words in dat/russ/ptt/tot.1/raw.tlw:
3240 0.09250 é
855 0.02441 ũ
540 0.01542 îá
466 0.01330 îå
442 0.01262 åįï
405 0.01156 įïóðïäø
376 0.01073 éč
327 0.00934 ðï
321 0.00916 éú
297 0.00848 ïô
removed 'dat/russ/ptt/tot.1/raw-trunc-wds-summary.tex'
removed 'exp/russ/ptt/tot.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/russ/ptt/tot.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:28 by tex-make-sample-summary.sh
% Token and word counts for russ/ptt/tot.1/raw.wfr
%
\def\russptttrunctotPBrawTks{35027}
\def\russptttrunctotPBrawTksPct{100.0}
\def\russptttrunctotPBrawWds{5521}
\def\russptttrunctotPBrawWdsPct{15.8}
copied '/tmp/583732.file' -> 'exp/russ/ptt/tot.1/raw-trunc-wds-summary.tex'
removed '/tmp/583732.file'
creating running text file dat/russ/ptt/tot.1/gud.wdf
sample:
ũ
îáþáėå óïôũïōéė âïį îåâï é úåíėā úåíėņ öå âųėá âåúũéäîá é ðõóôá é ôøíá
îáä âåúäîïā é äõč âïöéę îïóéėóņ îáä ũïäïā é óëáúáė âïį äá âõäåô óũåô é
óôáė óũåô é õũéäåė âïį óũåô þôï ïî čïōïû é ïôäåėéė âïį óũåô ïô ôøíų é
îáúũáė âïį óũåô äîåí á ôøíõ îïþøā é âųė ũåþåō é âųėï õôōï äåîø ïäéî é
óëáúáė âïį äá âõäåô ôũåōäø ðïóōåäé ũïäų é äá ïôäåėņåô ïîá ũïäõ ïô ũïäų é
óïúäáė âïį ôũåōäø é ïôäåėéė ũïäõ ëïôïōáņ ðïä ôũåōäøā ïô ũïäų ëïôïōáņ îáä
ôũåōäøā é óôáėï ôáë é îáúũáė âïį ôũåōäø îåâïí é âųė ũåþåō é âųėï õôōï
äåîø ũôïōïę é óëáúáė âïį äá óïâåōåôóņ ũïäá ëïôïōáņ ðïä îåâïí ũ
ïäîï íåóôï é äá ņũéôóņ óõûá é óôáėï ôáë é îáúũáė âïį óõûõ úåíėåā á
óïâōáîéå ũïä îáúũáė íïōņíé é õũéäåė âïį þôï üôï čïōïûï é óëáúáė âïį äá
ðōïéúōáóôéô úåíėņ úåėåîø ôōáũõ óåāýõā óåíņ äåōåũï ðėïäïũéôïå ðōéîïóņýåå
ðï ōïäõ óũïåíõ ðėïä ũ
ëïôïōïí óåíņ åįï îá úåíėå é óôáėï ôáë é ðōïéúũåėá úåíėņ úåėåîø ôōáũõ
óåāýõā óåíņ ðï ōïäõ åå é äåōåũï ðōéîïóņýåå ðėïä ũ
ëïôïōïí óåíņ åįï ðï ōïäõ åįï é õũéäåė âïį þôï üôï čïōïûï é âųė ũåþåō é
âųėï õôōï äåîø ôōåôéę é óëáúáė âïį äá âõäõô óũåôéėá îá ôũåōäé îåâåóîïę
äėņ ïôäåėåîéņ äîņ ïô îïþé é äėņ úîáíåîéę é ũōåíåî é äîåę é įïäïũ é äá
âõäõô ïîé óũåôéėøîéëáíé îá ôũåōäé îåâåóîïę þôïâų óũåôéôø îá úåíėā é
óôáėï ôáë é óïúäáė âïį äũá óũåôéėá ũåėéëéå óũåôéėï âïėøûåå äėņ
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
ōõëáč íïéč é îáðéóáė ïî îá óëōéöáėņč ëáë îáðéóáîï âųėï ðōåöäå ôå äåóņôø
óėïũ ëïôïōųå éúōåë ũáí įïóðïäø îá įïōå éú óōåäų ïįîņ ũ
äåîø óïâōáîéņ é ïôäáė éč įïóðïäø íîå é
removed 'dat/russ/ptt/tot.1/gud.wfr'
creating the word frequency file dat/russ/ptt/tot.1/gud.wfr
the 10 most common words in dat/russ/ptt/tot.1/gud.tlw:
3240 0.09250 é
855 0.02441 ũ
540 0.01542 îá
466 0.01330 îå
442 0.01262 åįï
405 0.01156 įïóðïäø
376 0.01073 éč
327 0.00934 ðï
321 0.00916 éú
297 0.00848 ïô
removed 'dat/russ/ptt/tot.1/gud-trunc-wds-summary.tex'
removed 'exp/russ/ptt/tot.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/russ/ptt/tot.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:28 by tex-make-sample-summary.sh
% Token and word counts for russ/ptt/tot.1/gud.wfr
%
\def\russptttrunctotPBgudTks{35027}
\def\russptttrunctotPBgudTksPct{100.0}
\def\russptttrunctotPBgudWds{5521}
\def\russptttrunctotPBgudWdsPct{15.8}
copied '/tmp/583776.file' -> 'exp/russ/ptt/tot.1/gud-trunc-wds-summary.tex'
removed '/tmp/583776.file'
creating running text file dat/russ/ptt/tot.1/bad.wdf
sample:
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
removed 'dat/russ/ptt/tot.1/bad.wfr'
creating the word frequency file dat/russ/ptt/tot.1/bad.wfr
the 10 most common words in dat/russ/ptt/tot.1/bad.tlw:
removed 'dat/russ/ptt/tot.1/bad-trunc-wds-summary.tex'
removed 'exp/russ/ptt/tot.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/russ/ptt/tot.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:28 by tex-make-sample-summary.sh
% Token and word counts for russ/ptt/tot.1/bad.wfr
%
\def\russptttrunctotPBbadTks{0}
\def\russptttrunctotPBbadTksPct{0.0}
\def\russptttrunctotPBbadWds{0}
\def\russptttrunctotPBbadWdsPct{0.0}
copied '/tmp/583826.file' -> 'exp/russ/ptt/tot.1/bad-trunc-wds-summary.tex'
removed '/tmp/583826.file'
lines words bytes file
------- ------- --------- ------------
4899 9798 116560 dat/russ/ptt/gen.1/raw.wfr
4084 8168 97660 dat/russ/ptt/exo.1/raw.wfr
3952 7904 94780 dat/russ/ptt/num.1/raw.wfr
2659 5318 63570 dat/russ/ptt/lev.1/raw.wfr
3913 7826 93645 dat/russ/ptt/deu.1/raw.wfr
5521 11042 132690 dat/russ/ptt/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
4899 9798 116560 dat/russ/ptt/gen.1/gud.wfr
4084 8168 97660 dat/russ/ptt/exo.1/gud.wfr
3952 7904 94780 dat/russ/ptt/num.1/gud.wfr
2659 5318 63570 dat/russ/ptt/lev.1/gud.wfr
3913 7826 93645 dat/russ/ptt/deu.1/gud.wfr
5521 11042 132690 dat/russ/ptt/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
0 0 0 dat/russ/ptt/gen.1/bad.wfr
0 0 0 dat/russ/ptt/exo.1/bad.wfr
0 0 0 dat/russ/ptt/num.1/bad.wfr
0 0 0 dat/russ/ptt/lev.1/bad.wfr
0 0 0 dat/russ/ptt/deu.1/bad.wfr
0 0 0 dat/russ/ptt/tot.1/bad.wfr
gen.1 raw = 28445 gud = 28445 bad = 0
exo.1 raw = 22960 gud = 22960 bad = 0
num.1 raw = 22530 gud = 22530 bad = 0
lev.1 raw = 16901 gud = 16901 bad = 0
deu.1 raw = 20988 gud = 20988 bad = 0
tot.1 raw = 35027 gud = 35027 bad = 0
=== creating the derived word files dat/arab/quf/*/{raw,gud,bad}.{tlw,wdf,wfr} (trunc) ===
... creating word files dat/arab/quf/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
37054 dat/arab/quf/tot.1/trunc.tlw
removed 'dat/arab/quf/tot.1/raw.tlw'
removed 'dat/arab/quf/tot.1/gud.tlw'
removed 'dat/arab/quf/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/arab/quf/tot.1/raw.wdf
sample:
bîs°mî alllâhî alrrâĩ°mânî alrrâĩîymî =
al°ĩâm°dû lîllâhî râbbî al°ŋâlâmîynâ =
alrrâĩ°mânî alrrâĩîymî =
mâlîkî yâw°mî alddîynî =
aĄîyyâakâ nâŋ°bûdû wâaĄîyyâakâ nâs°tâŋîynû =
ah°dînâa alßßîrâąâ al°mûs°tâqîymâ =
ßîrâąâ allâĢîynâ a!ân°ŋâm°tâ ŋâlây°hîm° Īây°rî al°mâĪ°ðûwbî ŋâlây°hîm°
wâlâa alððâallîynâ =
a/l/m =
Ģâlîkâ al°kîtâbû lâa rây°bâ fîyhî hûdäå lîl°mûttâqîynâ =
allâĢîynâ yûw!°mînûwnâ bîal°Īây°bî wâyûqîymûwnâ alßßâlâwĻâ wâmîmmâa
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
wâa!âw°ĩâå râbbûkâ aĄîlâå alnnâĩ°lî a!ân° attâĐîĢîy mîn° al°jîbâalî
bûyûwtäa
removed 'dat/arab/quf/tot.1/raw.wfr'
creating the word frequency file dat/arab/quf/tot.1/raw.wfr
the 10 most common words in dat/arab/quf/tot.1/raw.tlw:
1968 0.05311 =
1049 0.02831 mîn°
504 0.01360 fîy
473 0.01277 mâa
417 0.01125 alllâhî
396 0.01069 allâĢîynâ
394 0.01063 alllâhû
362 0.00977 lâa
315 0.00850 alllâhâ
298 0.00804 wâlâa
removed 'dat/arab/quf/tot.1/raw-trunc-wds-summary.tex'
removed 'exp/arab/quf/tot.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/arab/quf/tot.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:28 by tex-make-sample-summary.sh
% Token and word counts for arab/quf/tot.1/raw.wfr
%
\def\arabquftrunctotPBrawTks{37054}
\def\arabquftrunctotPBrawTksPct{100.0}
\def\arabquftrunctotPBrawWds{10983}
\def\arabquftrunctotPBrawWdsPct{29.6}
copied '/tmp/583996.file' -> 'exp/arab/quf/tot.1/raw-trunc-wds-summary.tex'
removed '/tmp/583996.file'
creating running text file dat/arab/quf/tot.1/gud.wdf
sample:
bîs°mî alllâhî alrrâĩ°mânî alrrâĩîymî al°ĩâm°dû lîllâhî râbbî
al°ŋâlâmîynâ alrrâĩ°mânî alrrâĩîymî mâlîkî yâw°mî alddîynî aĄîyyâakâ
nâŋ°bûdû wâaĄîyyâakâ nâs°tâŋîynû ah°dînâa alßßîrâąâ al°mûs°tâqîymâ
ßîrâąâ allâĢîynâ a!ân°ŋâm°tâ ŋâlây°hîm° Īây°rî al°mâĪ°ðûwbî ŋâlây°hîm°
wâlâa alððâallîynâ Ģâlîkâ al°kîtâbû lâa rây°bâ fîyhî hûdäå
lîl°mûttâqîynâ allâĢîynâ yûw!°mînûwnâ bîal°Īây°bî wâyûqîymûwnâ
alßßâlâwĻâ wâmîmmâa râzâq°nâhûm° yûnfîqûwnâ wâallâĢîynâ yûw!°mînûwnâ
bîmâa aûn°zîlâ aîlây°kâ wâmâa aûn°zîlâ mîn° qâb°lîkâ wâbîal°a'ĐîrâĻî
hûm° yûwqînûwnâ aûw°ly!îkâ ŋâlâå hûdäå mîn° râbbîhîm° waûw°ly!îkâ hûm°
al°mûf°lîĩûwnâ aînnâ allâĢîynâ kâfârûwa sâwâa'ü ŋâlây°hîm°
'âanĢâr°tâhûm° am° lâm° tûnĢîr°hûm° lâa yûw!°mînûwnâ Đâtâmâ alllâhû
ŋâlâå qûlûwbîhîm° wâŋâlâå sâm°ŋîhîm° wâŋâlâå ab°ßârîhîm° ĪîxâwâĻü
wâlâhûm° ŋâĢâabü ŋâįîymü wâmîn° alnnâasî mân° yâqûwlû 'amânnâa bîalllâhî
wâbîal°yâw°mî al°a'Đîrî wâmâa hûm° bîmûw!°mînîynâ yûĐâdîŋûwnâ alllâhâ
wâallâĢîynâ 'amânûwa wâmâa yâĐ°dâŋûwnâ aîllâa anfûsâhûm° wâmâa
yâx°ŋûrûwnâ fîy qûlûwbîhîm° mârâðü fâzâadâhûm° alllâhû mârâðäa wâlâhûm°
ŋâĢâabü alîymü bîmâa kâanûwa yâk°Ģîbûwnâ wâaîĢâa qîylâ lâhûm° lâa
tûf°sîdûwa fîy al°ar°ðî qâalûwa aînnâmâa nâĩ°nû mûß°lîĩûwnâ alâa
aînnâhûm° hûm° al°mûf°sîdûwnâ wâlâkîn° lâa yâx°ŋûrûwnâ wâaîĢâa qîylâ
lâhûm° 'amînûwa kâmâa 'amânâ alnnâasû qâalûwa anûw!°mînû kâmâa 'amânâ
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
wâal°a!âŋ°nâbî tâttâĐîĢûwnâ mîn°hû sâkâräa wârîz°qäa ĩâsânäa aĄînnâ fîy
Ģâlîkâ lâa'yâĻä lîqâw°mï yâŋ°qîlûwnâ wâa!âw°ĩâå râbbûkâ aĄîlâå alnnâĩ°lî
a!ân° attâĐîĢîy mîn° al°jîbâalî bûyûwtäa
removed 'dat/arab/quf/tot.1/gud.wfr'
creating the word frequency file dat/arab/quf/tot.1/gud.wfr
the 10 most common words in dat/arab/quf/tot.1/gud.tlw:
1049 0.02995 mîn°
504 0.01439 fîy
473 0.01350 mâa
417 0.01191 alllâhî
396 0.01131 allâĢîynâ
394 0.01125 alllâhû
362 0.01033 lâa
315 0.00899 alllâhâ
298 0.00851 wâlâa
283 0.00808 wâmâa
removed 'dat/arab/quf/tot.1/gud-trunc-wds-summary.tex'
removed 'exp/arab/quf/tot.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/arab/quf/tot.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:29 by tex-make-sample-summary.sh
% Token and word counts for arab/quf/tot.1/gud.wfr
%
\def\arabquftrunctotPBgudTks{35027}
\def\arabquftrunctotPBgudTksPct{94.5}
\def\arabquftrunctotPBgudWds{10935}
\def\arabquftrunctotPBgudWdsPct{29.5}
copied '/tmp/584041.file' -> 'exp/arab/quf/tot.1/gud-trunc-wds-summary.tex'
removed '/tmp/584041.file'
creating running text file dat/arab/quf/tot.1/bad.wdf
sample:
=
=
=
=
=
=
=
a/l/m =
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/arab/quf/tot.1/bad.wfr'
creating the word frequency file dat/arab/quf/tot.1/bad.wfr
the 10 most common words in dat/arab/quf/tot.1/bad.tlw:
1968 0.97089 =
5 0.00247 a/l/r
3 0.00148 û
2 0.00099 a/l/m
2 0.00099 lîl°âmâlây!îkâĻî
2 0.00099 nîŋ°mâtââ
2 0.00099 tâkû°
2 0.00099 wâal°âmâlây!îkâĻî
2 0.00099 ü
1 0.00049 a/l/m/r
removed 'dat/arab/quf/tot.1/bad-trunc-wds-summary.tex'
removed 'exp/arab/quf/tot.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/arab/quf/tot.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:29 by tex-make-sample-summary.sh
% Token and word counts for arab/quf/tot.1/bad.wfr
%
\def\arabquftrunctotPBbadTks{2027}
\def\arabquftrunctotPBbadTksPct{5.5}
\def\arabquftrunctotPBbadWds{48}
\def\arabquftrunctotPBbadWdsPct{0.1}
copied '/tmp/584085.file' -> 'exp/arab/quf/tot.1/bad-trunc-wds-summary.tex'
removed '/tmp/584085.file'
lines words bytes file
------- ------- --------- ------------
10983 32941 289871 dat/arab/quf/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
10935 32799 288587 dat/arab/quf/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
48 142 1284 dat/arab/quf/tot.1/bad.wfr
tot.1 raw = 37054 gud = 35027 bad = 2027
=== creating the derived word files dat/arab/quv/*/{raw,gud,bad}.{tlw,wdf,wfr} (trunc) ===
... creating word files dat/arab/quv/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
37040 dat/arab/quv/tot.1/trunc.tlw
removed 'dat/arab/quv/tot.1/raw.tlw'
removed 'dat/arab/quv/tot.1/gud.tlw'
removed 'dat/arab/quv/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/arab/quv/tot.1/raw.wdf
sample:
bîsmî alllâhî alrrâĩmânî alrrâĩîymî =
alĩâmdû lîllâhî râbbî alŋâlâmîynâ =
alrrâĩmânî alrrâĩîymî =
mâlîkî yâwmî alddîynî =
aĄîyyâakâ nâŋbûdû wâaĄîyyâakâ nâstâŋîynû =
ahdînâa alßßîrâąâ almûstâqîymâ =
ßîrâąâ allâĢîynâ a!ânŋâmtâ ŋâlâyhîm Īâyrî almâĪðûwbî ŋâlâyhîm wâlâa
alððâallîynâ =
a/l/m =
Ģâlîkâ alkîtâbû lâa râybâ fîyhî hûdäå lîlmûttâqîynâ =
allâĢîynâ yûw!mînûwnâ bîalĪâybî wâyûqîymûwnâ alßßâlâwĻâ wâmîmmâa
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
wâmîn þâmârâtî alnnâĐîylî wâala!âŋnâbî tâttâĐîĢûwnâ mînhû sâkâräa
wârîzqäa ĩâsânäa aĄînnâ fîy
removed 'dat/arab/quv/tot.1/raw.wfr'
creating the word frequency file dat/arab/quv/tot.1/raw.wfr
the 10 most common words in dat/arab/quv/tot.1/raw.tlw:
1967 0.05310 =
1048 0.02829 mîn
504 0.01361 fîy
473 0.01277 mâa
417 0.01126 alllâhî
396 0.01069 allâĢîynâ
394 0.01064 alllâhû
362 0.00977 lâa
315 0.00850 alllâhâ
298 0.00805 wâlâa
removed 'dat/arab/quv/tot.1/raw-trunc-wds-summary.tex'
removed 'exp/arab/quv/tot.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/arab/quv/tot.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:29 by tex-make-sample-summary.sh
% Token and word counts for arab/quv/tot.1/raw.wfr
%
\def\arabquvtrunctotPBrawTks{37040}
\def\arabquvtrunctotPBrawTksPct{100.0}
\def\arabquvtrunctotPBrawWds{10800}
\def\arabquvtrunctotPBrawWdsPct{29.2}
copied '/tmp/584180.file' -> 'exp/arab/quv/tot.1/raw-trunc-wds-summary.tex'
removed '/tmp/584180.file'
creating running text file dat/arab/quv/tot.1/gud.wdf
sample:
bîsmî alllâhî alrrâĩmânî alrrâĩîymî alĩâmdû lîllâhî râbbî alŋâlâmîynâ
alrrâĩmânî alrrâĩîymî mâlîkî yâwmî alddîynî aĄîyyâakâ nâŋbûdû
wâaĄîyyâakâ nâstâŋîynû ahdînâa alßßîrâąâ almûstâqîymâ ßîrâąâ allâĢîynâ
a!ânŋâmtâ ŋâlâyhîm Īâyrî almâĪðûwbî ŋâlâyhîm wâlâa alððâallîynâ Ģâlîkâ
alkîtâbû lâa râybâ fîyhî hûdäå lîlmûttâqîynâ allâĢîynâ yûw!mînûwnâ
bîalĪâybî wâyûqîymûwnâ alßßâlâwĻâ wâmîmmâa râzâqnâhûm yûnfîqûwnâ
wâallâĢîynâ yûw!mînûwnâ bîmâa aûnzîlâ aîlâykâ wâmâa aûnzîlâ mîn qâblîkâ
wâbîala'ĐîrâĻî hûm yûwqînûwnâ aûwly!îkâ ŋâlâå hûdäå mîn râbbîhîm
waûwly!îkâ hûm almûflîĩûwnâ aînnâ allâĢîynâ kâfârûwa sâwâa'ü ŋâlâyhîm
'âanĢârtâhûm am lâm tûnĢîrhûm lâa yûw!mînûwnâ Đâtâmâ alllâhû ŋâlâå
qûlûwbîhîm wâŋâlâå sâmŋîhîm wâŋâlâå abßârîhîm ĪîxâwâĻü wâlâhûm ŋâĢâabü
ŋâįîymü wâmîn alnnâasî mân yâqûwlû 'amânnâa bîalllâhî wâbîalyâwmî
ala'Đîrî wâmâa hûm bîmûw!mînîynâ yûĐâdîŋûwnâ alllâhâ wâallâĢîynâ
'amânûwa wâmâa yâĐdâŋûwnâ aîllâa anfûsâhûm wâmâa yâxŋûrûwnâ fîy
qûlûwbîhîm mârâðü fâzâadâhûm alllâhû mârâðäa wâlâhûm ŋâĢâabü alîymü
bîmâa kâanûwa yâkĢîbûwnâ wâaîĢâa qîylâ lâhûm lâa tûfsîdûwa fîy alarðî
qâalûwa aînnâmâa nâĩnû mûßlîĩûwnâ alâa aînnâhûm hûm almûfsîdûwnâ wâlâkîn
lâa yâxŋûrûwnâ wâaîĢâa qîylâ lâhûm 'amînûwa kâmâa 'amânâ alnnâasû
qâalûwa anûw!mînû kâmâa 'amânâ alssûfâhâa'û alâa aînnâhûm hûm
alssûfâhâa'û wâlâkîn lâa yâŋlâmûwnâ wâaîĢâa lâqûwa allâĢîynâ 'amânûwa
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
lâŋîbrâĻä nûsqîykûm mîmmâa fîy bûąûwnîhî mîn bâynî fârþï wâdâmï lâbânäa
Đâalîßäa sâay!îĪäa lîlxxârîbîynâ wâmîn þâmârâtî alnnâĐîylî wâala!âŋnâbî
tâttâĐîĢûwnâ mînhû sâkâräa wârîzqäa ĩâsânäa aĄînnâ fîy
removed 'dat/arab/quv/tot.1/gud.wfr'
creating the word frequency file dat/arab/quv/tot.1/gud.wfr
the 10 most common words in dat/arab/quv/tot.1/gud.tlw:
1048 0.02992 mîn
504 0.01439 fîy
473 0.01350 mâa
417 0.01191 alllâhî
396 0.01131 allâĢîynâ
394 0.01125 alllâhû
362 0.01033 lâa
315 0.00899 alllâhâ
298 0.00851 wâlâa
283 0.00808 wâmâa
removed 'dat/arab/quv/tot.1/gud-trunc-wds-summary.tex'
removed 'exp/arab/quv/tot.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/arab/quv/tot.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:29 by tex-make-sample-summary.sh
% Token and word counts for arab/quv/tot.1/gud.wfr
%
\def\arabquvtrunctotPBgudTks{35027}
\def\arabquvtrunctotPBgudTksPct{94.6}
\def\arabquvtrunctotPBgudWds{10762}
\def\arabquvtrunctotPBgudWdsPct{29.1}
copied '/tmp/584224.file' -> 'exp/arab/quv/tot.1/gud-trunc-wds-summary.tex'
removed '/tmp/584224.file'
creating running text file dat/arab/quv/tot.1/bad.wdf
sample:
=
=
=
=
=
=
=
a/l/m =
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/arab/quv/tot.1/bad.wfr'
creating the word frequency file dat/arab/quv/tot.1/bad.wfr
the 10 most common words in dat/arab/quv/tot.1/bad.tlw:
1967 0.97715 =
5 0.00248 a/l/r
3 0.00149 û
2 0.00099 a/l/m
2 0.00099 nîŋmâtââ
2 0.00099 ü
1 0.00050 a/l/m/r
1 0.00050 a/l/m/ß
1 0.00050 amrâattûû
1 0.00050 aĄîymânâäa
removed 'dat/arab/quv/tot.1/bad-trunc-wds-summary.tex'
removed 'exp/arab/quv/tot.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/arab/quv/tot.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:29 by tex-make-sample-summary.sh
% Token and word counts for arab/quv/tot.1/bad.wfr
%
\def\arabquvtrunctotPBbadTks{2013}
\def\arabquvtrunctotPBbadTksPct{5.4}
\def\arabquvtrunctotPBbadWds{38}
\def\arabquvtrunctotPBbadWdsPct{0.1}
copied '/tmp/584268.file' -> 'exp/arab/quv/tot.1/bad-trunc-wds-summary.tex'
removed '/tmp/584268.file'
lines words bytes file
------- ------- --------- ------------
10800 32392 277521 dat/arab/quv/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
10762 32280 276555 dat/arab/quv/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
38 112 966 dat/arab/quv/tot.1/bad.wfr
tot.1 raw = 37040 gud = 35027 bad = 2013
=== creating the derived word files dat/arab/qud/*/{raw,gud,bad}.{tlw,wdf,wfr} (trunc) ===
... creating word files dat/arab/qud/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
37001 dat/arab/qud/tot.1/trunc.tlw
removed 'dat/arab/qud/tot.1/raw.tlw'
removed 'dat/arab/qud/tot.1/gud.tlw'
removed 'dat/arab/qud/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/arab/qud/tot.1/raw.wdf
sample:
bsm alllh alrrĩmn alrrĩym =
alĩmd lllh rbb alŋlmyn =
alrrĩmn alrrĩym =
mlk ywm alddyn =
ayyak nŋbd wayyak nstŋyn =
ahdna alßßrą almstqym =
ßrą allĢyn anŋmt ŋlyhm Īyr almĪðwb ŋlyhm wla alððallyn =
a/l/m =
Ģlk alktb la ryb fyh hdå llmttqyn =
allĢyn ywmnwn balĪyb wyqymwn alßßlwĻ wmmma rzqnhm ynfqwn =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
ywmnwn =
walllh anzl mn alssma' ma' faĩya bh alarð bŋd mwtha ann fy
removed 'dat/arab/qud/tot.1/raw.wfr'
creating the word frequency file dat/arab/qud/tot.1/raw.wfr
the 10 most common words in dat/arab/qud/tot.1/raw.tlw:
1965 0.05311 =
1248 0.03373 mn
1130 0.03054 alllh
501 0.01354 fy
484 0.01308 ma
427 0.01154 an
396 0.01070 allĢyn
391 0.01057 la
327 0.00884 ann
326 0.00881 wla
removed 'dat/arab/qud/tot.1/raw-trunc-wds-summary.tex'
removed 'exp/arab/qud/tot.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/arab/qud/tot.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:29 by tex-make-sample-summary.sh
% Token and word counts for arab/qud/tot.1/raw.wfr
%
\def\arabqudtrunctotPBrawTks{37001}
\def\arabqudtrunctotPBrawTksPct{100.0}
\def\arabqudtrunctotPBrawWds{8536}
\def\arabqudtrunctotPBrawWdsPct{23.1}
copied '/tmp/584363.file' -> 'exp/arab/qud/tot.1/raw-trunc-wds-summary.tex'
removed '/tmp/584363.file'
creating running text file dat/arab/qud/tot.1/gud.wdf
sample:
bsm alllh alrrĩmn alrrĩym alĩmd lllh rbb alŋlmyn alrrĩmn alrrĩym mlk ywm
alddyn ayyak nŋbd wayyak nstŋyn ahdna alßßrą almstqym ßrą allĢyn anŋmt
ŋlyhm Īyr almĪðwb ŋlyhm wla alððallyn Ģlk alktb la ryb fyh hdå llmttqyn
allĢyn ywmnwn balĪyb wyqymwn alßßlwĻ wmmma rzqnhm ynfqwn wallĢyn ywmnwn
bma anzl alyk wma anzl mn qblk wbala'ĐrĻ hm ywqnwn awlyk ŋlå hdå mn
rbbhm wawlyk hm almflĩwn ann allĢyn kfrwa swa' ŋlyhm 'anĢrthm am lm
tnĢrhm la ywmnwn Đtm alllh ŋlå qlwbhm wŋlå smŋhm wŋlå abßrhm ĪxwĻ wlhm
ŋĢab ŋįym wmn alnnas mn yqwl 'amnna balllh wbalywm ala'Đr wma hm bmwmnyn
yĐdŋwn alllh wallĢyn 'amnwa wma yĐdŋwn alla anfshm wma yxŋrwn fy qlwbhm
mrð fzadhm alllh mrða wlhm ŋĢab alym bma kanwa ykĢbwn waĢa qyl lhm la
tfsdwa fy alarð qalwa annma nĩn mßlĩwn ala annhm hm almfsdwn wlkn la
yxŋrwn waĢa qyl lhm 'amnwa kma 'amn alnnas qalwa anwmn kma 'amn alssfha'
ala annhm hm alssfha' wlkn la yŋlmwn waĢa lqwa allĢyn 'amnwa qalwa
'amnna waĢa Đlwa alå xyąynhm qalwa anna mŋkm annma nĩn msthz'wn alllh
ysthzy bhm wymddhm fy ąĪynhm yŋmhwn awlyk allĢyn axtrwa alððllĻ balhdå
fma rbĩt tjrthm wma kanwa mhtdyn mþlhm kmþl allĢy astwqd nara flmma
aða't ma ĩwlh Ģhb alllh bnwrhm wtrkhm fy įlmt la ybßrwn ßmm bkm ŋmy fhm
la yrjŋwn aw kßyyb mn alssma' fyh įlmt wrŋd wbrq yjŋlwn aßbŋhm fy
'aĢanhm mn alßßwŋq ĩĢr almwt walllh mĩyą balkfryn ykad albrq yĐąf abßrhm
kllma aða' lhm mxwa fyh waĢa aįlm ŋlyhm qamwa wlw xa' alllh lĢhb bsmŋhm
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
qblk fzyyn lhm alxxyąn aŋmlhm fhw wlyyhm alywm wlhm ŋĢab alym wma anzlna
ŋlyk alktb alla ltbyyn lhm allĢy aĐtlfwa fyh whdå wrĩmĻ lqwm ywmnwn
walllh anzl mn alssma' ma' faĩya bh alarð bŋd mwtha ann fy
removed 'dat/arab/qud/tot.1/gud.wfr'
creating the word frequency file dat/arab/qud/tot.1/gud.wfr
the 10 most common words in dat/arab/qud/tot.1/gud.tlw:
1248 0.03563 mn
1130 0.03226 alllh
501 0.01430 fy
484 0.01382 ma
427 0.01219 an
396 0.01131 allĢyn
391 0.01116 la
327 0.00934 ann
326 0.00931 wla
309 0.00882 ŋlå
removed 'dat/arab/qud/tot.1/gud-trunc-wds-summary.tex'
removed 'exp/arab/qud/tot.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/arab/qud/tot.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:29 by tex-make-sample-summary.sh
% Token and word counts for arab/qud/tot.1/gud.wfr
%
\def\arabqudtrunctotPBgudTks{35027}
\def\arabqudtrunctotPBgudTksPct{94.7}
\def\arabqudtrunctotPBgudWds{8531}
\def\arabqudtrunctotPBgudWdsPct{23.1}
copied '/tmp/584407.file' -> 'exp/arab/qud/tot.1/gud-trunc-wds-summary.tex'
removed '/tmp/584407.file'
creating running text file dat/arab/qud/tot.1/bad.wdf
sample:
=
=
=
=
=
=
=
a/l/m =
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/arab/qud/tot.1/bad.wfr'
creating the word frequency file dat/arab/qud/tot.1/bad.wfr
the 10 most common words in dat/arab/qud/tot.1/bad.tlw:
1965 0.99544 =
5 0.00253 a/l/r
2 0.00101 a/l/m
1 0.00051 a/l/m/r
1 0.00051 a/l/m/ß
removed 'dat/arab/qud/tot.1/bad-trunc-wds-summary.tex'
removed 'exp/arab/qud/tot.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/arab/qud/tot.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:29 by tex-make-sample-summary.sh
% Token and word counts for arab/qud/tot.1/bad.wfr
%
\def\arabqudtrunctotPBbadTks{1974}
\def\arabqudtrunctotPBbadTksPct{5.3}
\def\arabqudtrunctotPBbadWds{5}
\def\arabqudtrunctotPBbadWdsPct{0.0}
copied '/tmp/584451.file' -> 'exp/arab/qud/tot.1/bad-trunc-wds-summary.tex'
removed '/tmp/584451.file'
lines words bytes file
------- ------- --------- ------------
8536 25602 192069 dat/arab/qud/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
8531 25587 191959 dat/arab/qud/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
5 15 110 dat/arab/qud/tot.1/bad.wfr
tot.1 raw = 37001 gud = 35027 bad = 1974
=== creating the derived word files dat/arab/qph/*/{raw,gud,bad}.{tlw,wdf,wfr} (trunc) ===
... creating word files dat/arab/qph/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
36980 dat/arab/qph/tot.1/trunc.tlw
removed 'dat/arab/qph/tot.1/raw.tlw'
removed 'dat/arab/qph/tot.1/gud.tlw'
removed 'dat/arab/qph/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/arab/qph/tot.1/raw.wdf
sample:
bîsmî allâhî alrrâĩmânî alrrâĩymî =
alĩâmdû lîllâhî râbbî alŋâlâmynâ =
alrrâĩmânî alrrâĩymî =
mâlîkî yâwmî alddynî =
aîyyâkâ nâŋbûdû wâaîyyâkâ nâstâŋynû =
aîhdînâ alßßîrâąâ almûstâqymâ =
ßîrâąâ allâĢynâ anŋâmtâ ŋâlâyhîm Īâyrî almâĪðwbî ŋâlâyhîm wâlâ
alððâllynâ =
alîflâmmym =
Ģâlîkâ alkîtâbû lâ râybâ fyhî hûdân lîlmûttâqynâ =
allâĢynâ yû'mînwnâ bîaâlĪâybî wâyûqymwnâ alßßâlâtâ wâmîmmâ râzâqnâhûm
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
tâttâqwnâ =
wâmâ
removed 'dat/arab/qph/tot.1/raw.wfr'
creating the word frequency file dat/arab/qph/tot.1/raw.wfr
the 10 most common words in dat/arab/qph/tot.1/raw.tlw:
1953 0.05281 =
733 0.01982 mîn
497 0.01344 fy
484 0.01309 mâ
450 0.01217 allâhî
427 0.01155 allâĢynâ
414 0.01120 allâhû
391 0.01057 lâ
350 0.00946 mînâ
329 0.00890 allâhâ
removed 'dat/arab/qph/tot.1/raw-trunc-wds-summary.tex'
removed 'exp/arab/qph/tot.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/arab/qph/tot.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:29 by tex-make-sample-summary.sh
% Token and word counts for arab/qph/tot.1/raw.wfr
%
\def\arabqphtrunctotPBrawTks{36980}
\def\arabqphtrunctotPBrawTksPct{100.0}
\def\arabqphtrunctotPBrawWds{9435}
\def\arabqphtrunctotPBrawWdsPct{25.5}
copied '/tmp/584546.file' -> 'exp/arab/qph/tot.1/raw-trunc-wds-summary.tex'
removed '/tmp/584546.file'
creating running text file dat/arab/qph/tot.1/gud.wdf
sample:
bîsmî allâhî alrrâĩmânî alrrâĩymî alĩâmdû lîllâhî râbbî alŋâlâmynâ
alrrâĩmânî alrrâĩymî mâlîkî yâwmî alddynî aîyyâkâ nâŋbûdû wâaîyyâkâ
nâstâŋynû aîhdînâ alßßîrâąâ almûstâqymâ ßîrâąâ allâĢynâ anŋâmtâ ŋâlâyhîm
Īâyrî almâĪðwbî ŋâlâyhîm wâlâ alððâllynâ alîflâmmym Ģâlîkâ alkîtâbû lâ
râybâ fyhî hûdân lîlmûttâqynâ allâĢynâ yû'mînwnâ bîaâlĪâybî wâyûqymwnâ
alßßâlâtâ wâmîmmâ râzâqnâhûm yûnfîqwnâ wâallâĢynâ yû'mînwnâ bîmâ anzîlâ
aîlâykâ wâmâ anzîlâ mîn qâblîkâ wâbîaâlaĐîrâtî hûm ywqînwnâ alâaîkâ ŋâlâ
hûdân mîn râbbîhîm wâalâaîkâ hûmû almûflîĩwnâ aînnâ allâĢynâ kâfârw
sâwâan ŋâlâyhîm aânĢârtâhûm am lâm tûnĢîrhûm lâ yû'mînwnâ Đâtâmâ allâhû
ŋâlâ qûlwbîhîm wâŋâlâ sâmŋîhîm wâŋâlâ abßârîhîm Īîxâwâtûn wâlâhûm
ŋâĢâbûn ŋâįymûn wâmînâ alnnâsî mân yâqwlû amânnâ bîaâllâhî wâbîaâlyâwmî
alaĐîrî wâmâ hûm bîmû'mînynâ yûĐâdîŋwnâ allâhâ wâallâĢynâ amânw wâmâ
yâĐdâŋwnâ aîllâ anfûsâhûm wâmâ yâxŋûrwnâ fy qûlwbîhîm mârâðûn fâzâdâhûmû
allâhû mârâðân wâlâhûm ŋâĢâbûn alymûn bîmâ kânw yâkĢîbwnâ wâaîĢâ qylâ
lâhûm lâ tûfsîdw fy alarðî qâlw aînnâmâ nâĩnû mûßlîĩwnâ alâ aînnâhûm
hûmû almûfsîdwnâ wâlâkîn lâ yâxŋûrwnâ wâaîĢâ qylâ lâhûm amînw kâmâ amânâ
alnnâsû qâlw anû'mînû kâmâ amânâ alssûfâhâa alâ aînnâhûm hûmû alssûfâhâa
wâlâkîn lâ yâŋlâmwnâ wâaîĢâ lâqw allâĢynâ amânw qâlw amânnâ wâaîĢâ Đâlâw
aîlâ xâyâąynîhîm qâlw aînnâ mâŋâkûm aînnâmâ nâĩnû mûstâhzîwnâ allâhû
yâstâhzîa bîhîm wâyâmûddûhûm fy ąûĪyânîhîm yâŋmâhwnâ alâaîkâ allâĢynâ
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
aînnâmâ hûwâ aîlâhûn wâĩîdûn fâaîyyâyâ fâaîrhâbwnî wâlâhû mâ fy
alssâmâwâtî wâalarðî wâlâhû alddynû wâßîbân afâĪâyrâ allâhî tâttâqwnâ
wâmâ
removed 'dat/arab/qph/tot.1/gud.wfr'
creating the word frequency file dat/arab/qph/tot.1/gud.wfr
the 10 most common words in dat/arab/qph/tot.1/gud.tlw:
733 0.02093 mîn
497 0.01419 fy
484 0.01382 mâ
450 0.01285 allâhî
427 0.01219 allâĢynâ
414 0.01182 allâhû
391 0.01116 lâ
350 0.00999 mînâ
329 0.00939 allâhâ
325 0.00928 wâlâ
removed 'dat/arab/qph/tot.1/gud-trunc-wds-summary.tex'
removed 'exp/arab/qph/tot.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/arab/qph/tot.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:30 by tex-make-sample-summary.sh
% Token and word counts for arab/qph/tot.1/gud.wfr
%
\def\arabqphtrunctotPBgudTks{35027}
\def\arabqphtrunctotPBgudTksPct{94.7}
\def\arabqphtrunctotPBgudWds{9434}
\def\arabqphtrunctotPBgudWdsPct{25.5}
copied '/tmp/584590.file' -> 'exp/arab/qph/tot.1/gud-trunc-wds-summary.tex'
removed '/tmp/584590.file'
creating running text file dat/arab/qph/tot.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/arab/qph/tot.1/bad.wfr'
creating the word frequency file dat/arab/qph/tot.1/bad.wfr
the 10 most common words in dat/arab/qph/tot.1/bad.tlw:
1953 1.00000 =
removed 'dat/arab/qph/tot.1/bad-trunc-wds-summary.tex'
removed 'exp/arab/qph/tot.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/arab/qph/tot.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:30 by tex-make-sample-summary.sh
% Token and word counts for arab/qph/tot.1/bad.wfr
%
\def\arabqphtrunctotPBbadTks{1953}
\def\arabqphtrunctotPBbadTksPct{5.3}
\def\arabqphtrunctotPBbadWds{1}
\def\arabqphtrunctotPBbadWdsPct{0.0}
copied '/tmp/584634.file' -> 'exp/arab/qph/tot.1/bad-trunc-wds-summary.tex'
removed '/tmp/584634.file'
lines words bytes file
------- ------- --------- ------------
9435 28300 237724 dat/arab/qph/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
9434 28297 237706 dat/arab/qph/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
1 3 18 dat/arab/qph/tot.1/bad.wfr
tot.1 raw = 36980 gud = 35027 bad = 1953
=== creating the derived word files dat/arab/qcs/*/{raw,gud,bad}.{tlw,wdf,wfr} (trunc) ===
... creating word files dat/arab/qcs/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
37102 dat/arab/qcs/tot.1/trunc.tlw
removed 'dat/arab/qcs/tot.1/raw.tlw'
removed 'dat/arab/qcs/tot.1/gud.tlw'
removed 'dat/arab/qcs/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/arab/qcs/tot.1/raw.wdf
sample:
bsm allh alrĩmn alrĩym =
alĩmd llh rb alŋalmyn =
alrĩmn alrĩym =
malk ywm aldyn =
ayak nŋbd wayak nstŋyn =
ahdna alßraą almstqym =
ßraą alĢyn anŋmt ŋlyhm Īyr almĪðwb ŋlyhm wlaalðalyn =
alm =
Ģlk alktab laryb fyh hdå llmtqyn =
alĢyn yw!mnwn balĪyb wyqymwn alßlaĻ wmma rzqnahm ynfqwn =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
wĩdh wlwa ŋlå adbarhm nfwra =
nĩn aŋlm bma ystmŋwn bh aĢ ystmŋwn
removed 'dat/arab/qcs/tot.1/raw.wfr'
creating the word frequency file dat/arab/qcs/tot.1/raw.wfr
the 10 most common words in dat/arab/qcs/tot.1/raw.tlw:
2075 0.05593 =
1299 0.03501 mn
1223 0.03296 allh
786 0.02118 an
465 0.01253 fy
444 0.01197 alĢyn
358 0.00965 ala
317 0.00854 ŋlå
200 0.00539 qal
192 0.00517 alå
removed 'dat/arab/qcs/tot.1/raw-trunc-wds-summary.tex'
removed 'exp/arab/qcs/tot.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/arab/qcs/tot.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:30 by tex-make-sample-summary.sh
% Token and word counts for arab/qcs/tot.1/raw.wfr
%
\def\arabqcstrunctotPBrawTks{37102}
\def\arabqcstrunctotPBrawTksPct{100.0}
\def\arabqcstrunctotPBrawWds{9026}
\def\arabqcstrunctotPBrawWdsPct{24.3}
copied '/tmp/584729.file' -> 'exp/arab/qcs/tot.1/raw-trunc-wds-summary.tex'
removed '/tmp/584729.file'
creating running text file dat/arab/qcs/tot.1/gud.wdf
sample:
bsm allh alrĩmn alrĩym alĩmd llh rb alŋalmyn alrĩmn alrĩym malk ywm
aldyn ayak nŋbd wayak nstŋyn ahdna alßraą almstqym ßraą alĢyn anŋmt
ŋlyhm Īyr almĪðwb ŋlyhm wlaalðalyn alm Ģlk alktab laryb fyh hdå llmtqyn
alĢyn yw!mnwn balĪyb wyqymwn alßlaĻ wmma rzqnahm ynfqwn walĢyn yw!mnwn
bma anzl alyk wmaanzl mn qblk wbalaĐrĻ hm ywqnwn awly!k ŋlå hdå mn rbhm
wawly!k hm almflĩwn an alĢyn kfrwa swa' ŋlyhm 'anĢrthm am lm tnĢrhm
layw!mnwn Đtm allh ŋlå qlwbhm wŋlå smŋhm wŋlå abßarhm ĪxawĻ wlhm ŋĢab
ŋįym wmn alnas mn yqwl amna ballh wbalywm alaĐr wmahm bmw!mnyn yĐadŋwn
allh walĢyn amnwa wmayĐdŋwn alaanfshm wmayxŋrwn fy qlwbhm mrð fzadhm
allh mrða wlhm ŋĢab alym bma kanwa ykĢbwn waĢa qyl lhm latfsdwa fy alarð
qalwa anma nĩn mßlĩwn ala anhm hm almfsdwn wlkn layxŋrwn waĢa qyl lhm
amnwa kma amn alnas qalwa anw!mn kma amn alsfha' alaanhm hm alsfha' wlkn
layŋlmwn waĢa lqwa alĢyn amnwa qalwa amna waĢa Đlwa alå xyaąynhm qalwa
ana mŋkm anma nĩn msthzy!wn allh ysthzy! bhm wymdhm fy ąĪyanhm yŋmhwn
awly!k alĢyn axtrwa alðlalĻ balhdå fma rbĩt tjarthm wmakanwa mhtdyn
mþlhm kmþl alĢy astwqd nara flma aða't maĩwlh Ģhb allh bnwrhm wtrkhm fy
įlmat laybßrwn ßm bkm ŋmy fhm layrjŋwn aw kßyb mn alsma' fyh įlmat wrŋd
wbrq yjŋlwn aßabŋhm fy aĢanhm mn alßwaŋq ĩĢr almwt wallh mĩyą balkafryn
ykad albrq yĐąf abßarhm klma aða' lhm mxwa fyh waĢa aįlm ŋlyhm qamwa wlw
xa' allh lĢhb bsmŋhm wabßarhm an allh ŋlå kl xy! qdyr yaayha alnas
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
bynk wbyn alĢyn layw!mnwn balaĐrĻ ĩjaba mstwra wjŋlna ŋlå qlwbhm aknĻ an
yfqhwh wfy aĢanhm wqra waĢa Ģkrt rbk fy alqran wĩdh wlwa ŋlå adbarhm
nfwra nĩn aŋlm bma ystmŋwn bh aĢ ystmŋwn
removed 'dat/arab/qcs/tot.1/gud.wfr'
creating the word frequency file dat/arab/qcs/tot.1/gud.wfr
the 10 most common words in dat/arab/qcs/tot.1/gud.tlw:
1299 0.03709 mn
1223 0.03492 allh
786 0.02244 an
465 0.01328 fy
444 0.01268 alĢyn
358 0.01022 ala
317 0.00905 ŋlå
200 0.00571 qal
192 0.00548 alå
178 0.00508 wan
removed 'dat/arab/qcs/tot.1/gud-trunc-wds-summary.tex'
removed 'exp/arab/qcs/tot.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/arab/qcs/tot.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:30 by tex-make-sample-summary.sh
% Token and word counts for arab/qcs/tot.1/gud.wfr
%
\def\arabqcstrunctotPBgudTks{35027}
\def\arabqcstrunctotPBgudTksPct{94.4}
\def\arabqcstrunctotPBgudWds{9025}
\def\arabqcstrunctotPBgudWdsPct{24.3}
copied '/tmp/584773.file' -> 'exp/arab/qcs/tot.1/gud-trunc-wds-summary.tex'
removed '/tmp/584773.file'
creating running text file dat/arab/qcs/tot.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/arab/qcs/tot.1/bad.wfr'
creating the word frequency file dat/arab/qcs/tot.1/bad.wfr
the 10 most common words in dat/arab/qcs/tot.1/bad.tlw:
2075 1.00000 =
removed 'dat/arab/qcs/tot.1/bad-trunc-wds-summary.tex'
removed 'exp/arab/qcs/tot.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/arab/qcs/tot.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:30 by tex-make-sample-summary.sh
% Token and word counts for arab/qcs/tot.1/bad.wfr
%
\def\arabqcstrunctotPBbadTks{2075}
\def\arabqcstrunctotPBbadTksPct{5.6}
\def\arabqcstrunctotPBbadWds{1}
\def\arabqcstrunctotPBbadWdsPct{0.0}
copied '/tmp/584817.file' -> 'exp/arab/qcs/tot.1/bad-trunc-wds-summary.tex'
removed '/tmp/584817.file'
lines words bytes file
------- ------- --------- ------------
9026 27073 204164 dat/arab/qcs/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
9025 27070 204146 dat/arab/qcs/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
1 3 18 dat/arab/qcs/tot.1/bad.wfr
tot.1 raw = 37102 gud = 35027 bad = 2075
=== creating the derived word files dat/viet/ptt/*/{raw,gud,bad}.{tlw,wdf,wfr} (trunc) ===
... creating word files dat/viet/ptt/gen.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
36162 dat/viet/ptt/gen.1/trunc.tlw
removed 'dat/viet/ptt/gen.1/raw.tlw'
removed 'dat/viet/ptt/gen.1/gud.tlw'
removed 'dat/viet/ptt/gen.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/viet/ptt/gen.1/raw.wdf
sample:
*{sa'ch} ..*{se} ban dda^`u ddu+'c chu'a tro+`i du+.ng ne^n tro+`i
dda^'t =
va? dda^'t la` vo^ hi`nh va` tro^'ng kho^ng su+. mo+` to^'i o+? tre^n
ma(.t vu+.c tha^`n ddu+'c chu'a tro+`i va^.n ha`nh tre^n ma(.t nu+o+'c =
ddu+'c chu'a tro+`i pha'n ra(`ng pha?i co' su+. sa'ng thi` co' su+.
sa'ng =
ddu+'c chu'a tro+`i tha^'y su+. sa'ng la` to^'t la`nh be`n pha^n sa'ng
ra cu`ng to^'i =
ddu+'c chu'a tro+`i dda(.t te^n su+. sa'ng la` nga`y su+. to^'i la`
dde^m va^.y co' buo^?i chie^`u va` buo^?i mai a^'y la` nga`y thu+'
nhu+'t =
ddu+'c chu'a tro+`i la.i pha'n ra(`ng pha?i co' mo^.t khoa?ng kho^ng o+?
giu+~a nu+o+'c dda(.ng pha^n re~ nu+o+'c ca'ch vo+'i nu+o+'c =
nga`i la`m ne^n khoa?ng kho^ng pha^n re~ nu+o+'c o+? du+o+'i khoa?ng
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
so^'ng va` kho?i che^'t =
con se~ ba?o la~nh em cho cha se~ cu+' no+i con
removed 'dat/viet/ptt/gen.1/raw.wfr'
creating the word frequency file dat/viet/ptt/gen.1/raw.wfr
the 10 most common words in dat/viet/ptt/gen.1/raw.tlw:
1133 0.03133 =
637 0.01762 ngu+o+`i
604 0.01670 va`
567 0.01568 con
530 0.01466 cho
469 0.01297 ra(`ng
461 0.01275 ra
437 0.01208 la`
433 0.01197 cu?a
429 0.01186 ca'c
removed 'dat/viet/ptt/gen.1/raw-trunc-wds-summary.tex'
removed 'exp/viet/ptt/gen.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/viet/ptt/gen.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:30 by tex-make-sample-summary.sh
% Token and word counts for viet/ptt/gen.1/raw.wfr
%
\def\vietptttruncgenPBrawTks{36162}
\def\vietptttruncgenPBrawTksPct{100.0}
\def\vietptttruncgenPBrawWds{1693}
\def\vietptttruncgenPBrawWdsPct{4.7}
copied '/tmp/584912.file' -> 'exp/viet/ptt/gen.1/raw-trunc-wds-summary.tex'
removed '/tmp/584912.file'
creating running text file dat/viet/ptt/gen.1/gud.wdf
sample:
ban dda^`u ddu+'c chu'a tro+`i du+.ng ne^n tro+`i dda^'t va? dda^'t la`
vo^ hi`nh va` tro^'ng kho^ng su+. mo+` to^'i o+? tre^n ma(.t vu+.c
tha^`n ddu+'c chu'a tro+`i va^.n ha`nh tre^n ma(.t nu+o+'c ddu+'c chu'a
tro+`i pha'n ra(`ng pha?i co' su+. sa'ng thi` co' su+. sa'ng ddu+'c
chu'a tro+`i tha^'y su+. sa'ng la` to^'t la`nh be`n pha^n sa'ng ra cu`ng
to^'i ddu+'c chu'a tro+`i dda(.t te^n su+. sa'ng la` nga`y su+. to^'i
la` dde^m va^.y co' buo^?i chie^`u va` buo^?i mai a^'y la` nga`y thu+'
nhu+'t ddu+'c chu'a tro+`i la.i pha'n ra(`ng pha?i co' mo^.t khoa?ng
kho^ng o+? giu+~a nu+o+'c dda(.ng pha^n re~ nu+o+'c ca'ch vo+'i nu+o+'c
nga`i la`m ne^n khoa?ng kho^ng pha^n re~ nu+o+'c o+? du+o+'i khoa?ng
kho^ng ca'ch vo+'i nu+o+'c o+? tre^n khoa?ng kho^ng thi` co' nhu+ va^.y
ddu+'c chu'a tro+`i dda(.t te^n khoa?ng kho^ng la` tro+`i va^.y co'
buo^?i chie^`u va` buo^?i mai a^'y la` nga`y thu+' nhi` ddu+'c chu'a
tro+`i la.i pha'n ra(`ng nhu+~ng nu+o+'c o+? du+o+'i tro+`i pha?i tu.
la.i mo^.t no+i va` pha?i co' cho^~ kho^ ca.n ba`y ra thi` co' nhu+
va^.y ddu+'c chu'a tro+`i dda(.t te^n cho^~ kho^ ca.n la` dda^'t co`n
no+i nu+o+'c tu. la.i la` bie^?n ddu+'c chu'a tro+`i tha^'y dde^`u ddo'
la` to^'t la`nh ddu+'c chu'a tro+`i la.i pha'n ra(`ng dda^'t pha?i sanh
ca^y co? co? ke^'t ho^.t gio^'ng ca^y tra'i ke^'t qua? tu`y theo loa.i
ma` co' ho^.t gio^'ng trong mi`nh tre^n dda^'t thi` co' nhu+ va^.y
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
cho chu'ng ta na`o ca'c con na`o cha na`o ca'c cha'u cu?a cha dda^y
dde^`u ddu+o+.c so^'ng va` kho?i che^'t con se~ ba?o la~nh em cho cha
se~ cu+' no+i con
removed 'dat/viet/ptt/gen.1/gud.wfr'
creating the word frequency file dat/viet/ptt/gen.1/gud.wfr
the 10 most common words in dat/viet/ptt/gen.1/gud.tlw:
637 0.01819 ngu+o+`i
604 0.01724 va`
567 0.01619 con
530 0.01513 cho
469 0.01339 ra(`ng
461 0.01316 ra
437 0.01248 la`
433 0.01236 cu?a
429 0.01225 ca'c
413 0.01179 to^i
removed 'dat/viet/ptt/gen.1/gud-trunc-wds-summary.tex'
removed 'exp/viet/ptt/gen.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/viet/ptt/gen.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:30 by tex-make-sample-summary.sh
% Token and word counts for viet/ptt/gen.1/gud.wfr
%
\def\vietptttruncgenPBgudTks{35027}
\def\vietptttruncgenPBgudTksPct{96.9}
\def\vietptttruncgenPBgudWds{1690}
\def\vietptttruncgenPBgudWdsPct{4.7}
copied '/tmp/584956.file' -> 'exp/viet/ptt/gen.1/gud-trunc-wds-summary.tex'
removed '/tmp/584956.file'
creating running text file dat/viet/ptt/gen.1/bad.wdf
sample:
*{sa'ch} ..*{se} =
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/viet/ptt/gen.1/bad.wfr'
creating the word frequency file dat/viet/ptt/gen.1/bad.wfr
the 10 most common words in dat/viet/ptt/gen.1/bad.tlw:
1133 0.99824 =
1 0.00088 *{sa'ch}
1 0.00088 ..*{se}
removed 'dat/viet/ptt/gen.1/bad-trunc-wds-summary.tex'
removed 'exp/viet/ptt/gen.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/viet/ptt/gen.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:30 by tex-make-sample-summary.sh
% Token and word counts for viet/ptt/gen.1/bad.wfr
%
\def\vietptttruncgenPBbadTks{1135}
\def\vietptttruncgenPBbadTksPct{3.1}
\def\vietptttruncgenPBbadWds{3}
\def\vietptttruncgenPBbadWdsPct{0.0}
copied '/tmp/585000.file' -> 'exp/viet/ptt/gen.1/bad-trunc-wds-summary.tex'
removed '/tmp/585000.file'
... creating word files dat/viet/ptt/exo.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
34775 dat/viet/ptt/exo.1/trunc.tlw
removed 'dat/viet/ptt/exo.1/raw.tlw'
removed 'dat/viet/ptt/exo.1/gud.tlw'
removed 'dat/viet/ptt/exo.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/viet/ptt/exo.1/raw.wdf
sample:
*{sa'ch} ..*{se} dda^y la` te^n ca'c con trai cu?a y so+ ra e^n mo^~i
ngu+o+`i dde^`u da^~n ngu+o+`i nha` mi`nh ddi vo+'i gia co^'p dde^'n
xu+' e^ di'p to^ ru be^n si me^ o^n le^ vi va` giu dda y sa ca sa bu
lo^n va` be^n gia min ddan ne'p ta li ga't va` a se =
he^'t tha?y nhu+~ng ngu+o+`i bo+?i gia co^'p sanh ra ddu+o+.c ba?y
mu+o+i ngu+o+`i gio^ se'p dda~ o+? ta.i xu+' e^ di'p to^ =
va? gio^ se'p va` anh em ngu+o+`i cu`ng mo.i ke? ddo^`ng ddo+`i ddo'
dde^`u che^'t he^'t =
con cha'u y so+ ra e^n the^m nhie^`u la. lu`ng na^?y no+? ra va` tro+?
ne^n ra^'t cu+o+`ng tha.nh ca? xu+' dde^`u dda^`y da^~y =
nhu+ng ba^'y gio+` ta.i nu+o+'c e^ di'p to^ co' mo^.t vua mo+'i le^n
ngo^i cha(?ng quen bie^'t gio^ se'p =
vua pha'n cu`ng da^n mi`nh ra(`ng na^`y da^n y so+ ra e^n ddo^ng va`
ma.nh ho+n chu'ng ta he` ta ha~y du`ng chu+o+'c kho^n ngoan ddo^'i cu`ng
ho. ke?o ho. the^m nhie^`u le^n mo^.t mai ne^'u co' co+n chinh chie^'n
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
cu?a ddu+'c gie^ ho^ va o+? tre^n dde^`n ta.m ban nga`y va` co' lu+?a
o+? tre^n ddo' ban dde^m hie^.n tru+o+'c ma(.t ca? da^n y so+ ra e^n =
removed 'dat/viet/ptt/exo.1/raw.wfr'
creating the word frequency file dat/viet/ptt/exo.1/raw.wfr
the 10 most common words in dat/viet/ptt/exo.1/raw.tlw:
1013 0.02913 =
618 0.01777 va`
561 0.01613 ngu+o+i
538 0.01547 ra
479 0.01377 cho
468 0.01346 ddu+'c
455 0.01308 ngu+o+`i
445 0.01280 ca'c
412 0.01185 gie^
407 0.01170 ho^
removed 'dat/viet/ptt/exo.1/raw-trunc-wds-summary.tex'
removed 'exp/viet/ptt/exo.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/viet/ptt/exo.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:30 by tex-make-sample-summary.sh
% Token and word counts for viet/ptt/exo.1/raw.wfr
%
\def\vietptttruncexoPBrawTks{34775}
\def\vietptttruncexoPBrawTksPct{100.0}
\def\vietptttruncexoPBrawWds{1652}
\def\vietptttruncexoPBrawWdsPct{4.8}
copied '/tmp/585054.file' -> 'exp/viet/ptt/exo.1/raw-trunc-wds-summary.tex'
removed '/tmp/585054.file'
creating running text file dat/viet/ptt/exo.1/gud.wdf
sample:
dda^y la` te^n ca'c con trai cu?a y so+ ra e^n mo^~i ngu+o+`i dde^`u
da^~n ngu+o+`i nha` mi`nh ddi vo+'i gia co^'p dde^'n xu+' e^ di'p to^ ru
be^n si me^ o^n le^ vi va` giu dda y sa ca sa bu lo^n va` be^n gia min
ddan ne'p ta li ga't va` a se he^'t tha?y nhu+~ng ngu+o+`i bo+?i gia
co^'p sanh ra ddu+o+.c ba?y mu+o+i ngu+o+`i gio^ se'p dda~ o+? ta.i xu+'
e^ di'p to^ va? gio^ se'p va` anh em ngu+o+`i cu`ng mo.i ke? ddo^`ng
ddo+`i ddo' dde^`u che^'t he^'t con cha'u y so+ ra e^n the^m nhie^`u la.
lu`ng na^?y no+? ra va` tro+? ne^n ra^'t cu+o+`ng tha.nh ca? xu+' dde^`u
dda^`y da^~y nhu+ng ba^'y gio+` ta.i nu+o+'c e^ di'p to^ co' mo^.t vua
mo+'i le^n ngo^i cha(?ng quen bie^'t gio^ se'p vua pha'n cu`ng da^n
mi`nh ra(`ng na^`y da^n y so+ ra e^n ddo^ng va` ma.nh ho+n chu'ng ta he`
ta ha~y du`ng chu+o+'c kho^n ngoan ddo^'i cu`ng ho. ke?o ho. the^m
nhie^`u le^n mo^.t mai ne^'u co' co+n chinh chie^'n xa?y dde^'n ho. se~
hie^.p cu`ng qua^n nghi.ch dda'nh la.i ta va` ra kho?i xu+' cha(ng va^.y
ngu+o+`i e^ di'p to^ be`n dda(.t ca'c ke? dda^`u xa^u dde^? ba('t da^n y
so+ ra e^n la`m xa^u kho' nho.c ho. xa^y tha`nh phi thom va` ram se
du`ng la`m kho ta`ng cho pha ra o^n nhu+ng ngu+o+`i e^ di'p to^ ca`ng
ba('t la`m kho' nho.c chu+`ng na`o da^n y so+ ra e^n ca`ng the^m nhie^`u
le^n va` tra`n ra chu+`ng na^'y ngu+o+`i e^ di'p to^ ca`ng ddem lo`ng
ghen ghe't da^n y so+ ra e^n ba('t la`m co^ng vie^.c nho.c nha(`n ga^y
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
e^n thi` a'ng ma^y cu?a ddu+'c gie^ ho^ va o+? tre^n dde^`n ta.m ban
nga`y va` co' lu+?a o+? tre^n ddo' ban dde^m hie^.n tru+o+'c ma(.t ca?
da^n y so+ ra e^n
removed 'dat/viet/ptt/exo.1/gud.wfr'
creating the word frequency file dat/viet/ptt/exo.1/gud.wfr
the 10 most common words in dat/viet/ptt/exo.1/gud.tlw:
618 0.01831 va`
561 0.01662 ngu+o+i
538 0.01594 ra
479 0.01419 cho
468 0.01386 ddu+'c
455 0.01348 ngu+o+`i
445 0.01318 ca'c
412 0.01220 gie^
407 0.01206 ho^
399 0.01182 cu?a
removed 'dat/viet/ptt/exo.1/gud-trunc-wds-summary.tex'
removed 'exp/viet/ptt/exo.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/viet/ptt/exo.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:30 by tex-make-sample-summary.sh
% Token and word counts for viet/ptt/exo.1/gud.wfr
%
\def\vietptttruncexoPBgudTks{33760}
\def\vietptttruncexoPBgudTksPct{97.1}
\def\vietptttruncexoPBgudWds{1649}
\def\vietptttruncexoPBgudWdsPct{4.7}
copied '/tmp/585099.file' -> 'exp/viet/ptt/exo.1/gud-trunc-wds-summary.tex'
removed '/tmp/585099.file'
creating running text file dat/viet/ptt/exo.1/bad.wdf
sample:
*{sa'ch} ..*{se} =
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/viet/ptt/exo.1/bad.wfr'
creating the word frequency file dat/viet/ptt/exo.1/bad.wfr
the 10 most common words in dat/viet/ptt/exo.1/bad.tlw:
1013 0.99803 =
1 0.00099 *{sa'ch}
1 0.00099 ..*{se}
removed 'dat/viet/ptt/exo.1/bad-trunc-wds-summary.tex'
removed 'exp/viet/ptt/exo.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/viet/ptt/exo.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:30 by tex-make-sample-summary.sh
% Token and word counts for viet/ptt/exo.1/bad.wfr
%
\def\vietptttruncexoPBbadTks{1015}
\def\vietptttruncexoPBbadTksPct{2.9}
\def\vietptttruncexoPBbadWds{3}
\def\vietptttruncexoPBbadWdsPct{0.0}
copied '/tmp/585143.file' -> 'exp/viet/ptt/exo.1/bad-trunc-wds-summary.tex'
removed '/tmp/585143.file'
... creating word files dat/viet/ptt/num.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
35949 dat/viet/ptt/num.1/trunc.tlw
removed 'dat/viet/ptt/num.1/raw.tlw'
removed 'dat/viet/ptt/num.1/gud.tlw'
removed 'dat/viet/ptt/num.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/viet/ptt/num.1/raw.wdf
sample:
*{sa'ch} ..*{se} nga`y mo^`ng mo^.t tha'ng hai na(m thu+' hai sau khi
da^n y so+ ra e^n ra kho?i xu+' e^ di'p to^ ddu+'c gie^ ho^ va pha'n
cu`ng mo^i se o+? trong ho^.i ma.c ta.i ddo^`ng va('ng si na i ma`
ra(`ng ha~y du+.ng so^? ca? ho^.i da^n y so+ ra e^n theo ho. ha`ng va`
to^ng to^.c cu?a ho. cu+' dde^'m tu+`ng te^n cu?a he^'t tha?y nam ddinh
tu+` hai mu+o+i tuo^?i sa^'p le^n tu+'c la` mo.i ngu+o+`i trong y so+ ra
e^n ddi ra tra^.n ddu+o+.c ngu+o+i va` a ro^n se~ ke^ so^? chu'ng no'
tu`y theo ddo^.i ngu~ cu?a ho. =
trong mo^~i chi pha'i pha?i co' mo^.t ngu+o+`i giu'p ddo+~ ca'c ngu+o+i
tu+'c la` ngu+o+`i la`m to^.c tru+o+?ng cu?a chi pha'i mi`nh =
dda^y la` te^n nhu+~ng ngu+o+`i se~ giu'p ddo+~ ca'c ngu+o+i ve^` chi
pha'i ru be^n e^ li't su con trai cu?a se^ dde^u ve^` chi pha'i si me^
o^n se^ u me^ e^n con trai cu?a xu ri ha ddai ve^` chi pha'i giu dda na
ha so^n con trai cu?a a mi na dda'p ve^` chi pha'i y sa ca na tha na e^n
con trai cu?a xu a ve^` chi pha'i sa bu lo^n e^ li a'p con trai cu?a he^
lo^n ve^` con cha'u gio^ se'p nghi~a la` ve^` chi pha'i e'p ra im e^ li
sa ma con trai cu?a a mi hu't ve^` chi pha'i ma na se ga ma li e^n con
trai cu?a phe^ dda't su ve^` chi pha'i be^n gia min a bi ddan con trai
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
gio+'i ha.n se~ cha.y ve^` hu+o+'ng xi'p ro^n va` a(n cuo^'i ha't sa e^
nan ddo' la` gio+'i ha.n cu?a ca'c ngu+o+i ve^`
removed 'dat/viet/ptt/num.1/raw.wfr'
creating the word frequency file dat/viet/ptt/num.1/raw.wfr
the 10 most common words in dat/viet/ptt/num.1/raw.tlw:
920 0.02559 =
720 0.02003 cu?a
703 0.01956 ngu+o+`i
699 0.01944 va`
622 0.01730 con
526 0.01463 ra
479 0.01332 ca'c
433 0.01204 mo^.t
411 0.01143 ngu+o+i
406 0.01129 le^~
removed 'dat/viet/ptt/num.1/raw-trunc-wds-summary.tex'
removed 'exp/viet/ptt/num.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/viet/ptt/num.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:31 by tex-make-sample-summary.sh
% Token and word counts for viet/ptt/num.1/raw.wfr
%
\def\vietptttruncnumPBrawTks{35949}
\def\vietptttruncnumPBrawTksPct{100.0}
\def\vietptttruncnumPBrawWds{1462}
\def\vietptttruncnumPBrawWdsPct{4.1}
copied '/tmp/585197.file' -> 'exp/viet/ptt/num.1/raw-trunc-wds-summary.tex'
removed '/tmp/585197.file'
creating running text file dat/viet/ptt/num.1/gud.wdf
sample:
nga`y mo^`ng mo^.t tha'ng hai na(m thu+' hai sau khi da^n y so+ ra e^n
ra kho?i xu+' e^ di'p to^ ddu+'c gie^ ho^ va pha'n cu`ng mo^i se o+?
trong ho^.i ma.c ta.i ddo^`ng va('ng si na i ma` ra(`ng ha~y du+.ng so^?
ca? ho^.i da^n y so+ ra e^n theo ho. ha`ng va` to^ng to^.c cu?a ho. cu+'
dde^'m tu+`ng te^n cu?a he^'t tha?y nam ddinh tu+` hai mu+o+i tuo^?i
sa^'p le^n tu+'c la` mo.i ngu+o+`i trong y so+ ra e^n ddi ra tra^.n
ddu+o+.c ngu+o+i va` a ro^n se~ ke^ so^? chu'ng no' tu`y theo ddo^.i
ngu~ cu?a ho. trong mo^~i chi pha'i pha?i co' mo^.t ngu+o+`i giu'p ddo+~
ca'c ngu+o+i tu+'c la` ngu+o+`i la`m to^.c tru+o+?ng cu?a chi pha'i
mi`nh dda^y la` te^n nhu+~ng ngu+o+`i se~ giu'p ddo+~ ca'c ngu+o+i ve^`
chi pha'i ru be^n e^ li't su con trai cu?a se^ dde^u ve^` chi pha'i si
me^ o^n se^ u me^ e^n con trai cu?a xu ri ha ddai ve^` chi pha'i giu dda
na ha so^n con trai cu?a a mi na dda'p ve^` chi pha'i y sa ca na tha na
e^n con trai cu?a xu a ve^` chi pha'i sa bu lo^n e^ li a'p con trai cu?a
he^ lo^n ve^` con cha'u gio^ se'p nghi~a la` ve^` chi pha'i e'p ra im e^
li sa ma con trai cu?a a mi hu't ve^` chi pha'i ma na se ga ma li e^n
con trai cu?a phe^ dda't su ve^` chi pha'i be^n gia min a bi ddan con
trai cu?a ghi ddeo ni ve^` chi pha'i ddan a hi e^ se con trai cu?a a mi
sa ddai ve^` chi pha'i a se pha ghi e^n con trai cu?a o'c ran ve^` chi
pha'i ga't e^ li a sa'p con trai cu?a dde^ u e^n ve^` chi pha'i ne'p ta
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
se~ cha^'m ta.i dda^`u ha ma't la`m ha.n ro^`i gio+'i ha.n se~ gia'p
ta.i xe^ dda't gio+'i ha.n se~ cha.y ve^` hu+o+'ng xi'p ro^n va` a(n
cuo^'i ha't sa e^ nan ddo' la` gio+'i ha.n cu?a ca'c ngu+o+i ve^`
removed 'dat/viet/ptt/num.1/gud.wfr'
creating the word frequency file dat/viet/ptt/num.1/gud.wfr
the 10 most common words in dat/viet/ptt/num.1/gud.tlw:
720 0.02056 cu?a
703 0.02007 ngu+o+`i
699 0.01996 va`
622 0.01776 con
526 0.01502 ra
479 0.01368 ca'c
433 0.01236 mo^.t
411 0.01173 ngu+o+i
406 0.01159 le^~
404 0.01153 ddu+'c
removed 'dat/viet/ptt/num.1/gud-trunc-wds-summary.tex'
removed 'exp/viet/ptt/num.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/viet/ptt/num.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:31 by tex-make-sample-summary.sh
% Token and word counts for viet/ptt/num.1/gud.wfr
%
\def\vietptttruncnumPBgudTks{35027}
\def\vietptttruncnumPBgudTksPct{97.4}
\def\vietptttruncnumPBgudWds{1459}
\def\vietptttruncnumPBgudWdsPct{4.1}
copied '/tmp/585241.file' -> 'exp/viet/ptt/num.1/gud-trunc-wds-summary.tex'
removed '/tmp/585241.file'
creating running text file dat/viet/ptt/num.1/bad.wdf
sample:
*{sa'ch} ..*{se} =
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/viet/ptt/num.1/bad.wfr'
creating the word frequency file dat/viet/ptt/num.1/bad.wfr
the 10 most common words in dat/viet/ptt/num.1/bad.tlw:
920 0.99783 =
1 0.00108 *{sa'ch}
1 0.00108 ..*{se}
removed 'dat/viet/ptt/num.1/bad-trunc-wds-summary.tex'
removed 'exp/viet/ptt/num.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/viet/ptt/num.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:31 by tex-make-sample-summary.sh
% Token and word counts for viet/ptt/num.1/bad.wfr
%
\def\vietptttruncnumPBbadTks{922}
\def\vietptttruncnumPBbadTksPct{2.6}
\def\vietptttruncnumPBbadWds{3}
\def\vietptttruncnumPBbadWdsPct{0.0}
copied '/tmp/585285.file' -> 'exp/viet/ptt/num.1/bad-trunc-wds-summary.tex'
removed '/tmp/585285.file'
... creating word files dat/viet/ptt/lev.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
25831 dat/viet/ptt/lev.1/trunc.tlw
removed 'dat/viet/ptt/lev.1/raw.tlw'
removed 'dat/viet/ptt/lev.1/gud.tlw'
removed 'dat/viet/ptt/lev.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/viet/ptt/lev.1/raw.wdf
sample:
*{sa'ch} ..*{se} ddu+'c gie^ ho^ va tu+` trong ho^.i ma.c go.i mo^i se
ma` pha'n ra(`ng ha~y no'i cu`ng da^n y so+ ra e^n ra(`ng khi ngu+o+`i
na`o trong vo`ng ca'c ngu+o+i da^ng cu?a le^~ cho ddu+'c gie^ ho^ va
thi` pha?i da^ng su'c va^.t hoa(.c bo` hoa(.c chie^n =
ne^'u le^~ va^.t cu?a ngu+o+`i la` cu?a le^~ thie^u ba(`ng bo` thi`
pha?i du`ng con ddu+.c kho^ng ti` vi't da^ng le^n ta.i cu+?a ho^.i ma.c
tru+o+'c ma(.t ddu+'c gie^ ho^ va dde^? ddu+o+.c nga`i dde.p lo`ng
nha^.m la^'y =
ngu+o+`i se~ nha^.n tay mi`nh tre^n dda^`u con sinh no' se~ ddu+o+.c
nha^.m the^' cho ha^`u chuo^.c to^.i cho ngu+o+`i =
ddoa.n ngu+o+`i se~ gie^'t bo` to+ tru+o+'c ma(.t ddu+'c gie^ ho^ va
ro^`i ca'c con trai a ro^n tu+'c nhu+~ng tha^`y te^' le^~ se~ da^ng
huye^'t le^n va` ru+o+'i chunh quanh tre^n ba`n tho+` ta.i no+i cu+?a
ho^.i ma.c =
ke^' ddo' lo^.t da con sinh va` sa? thi.t ra tu+`ng mie^'ng =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
ddo' la` ca'c ma.ng li.nh ma` ddu+'c gie^ ho^ va truye^`n cho mo^i se
ve^` da^n y so+ ra e^n ta.i tre^n nu'i si na i =
removed 'dat/viet/ptt/lev.1/raw.wfr'
creating the word frequency file dat/viet/ptt/lev.1/raw.wfr
the 10 most common words in dat/viet/ptt/lev.1/raw.tlw:
666 0.02578 =
541 0.02094 le^~
523 0.02025 ngu+o+`i
494 0.01912 cu?a
471 0.01823 ca'c
409 0.01583 cho
403 0.01560 se~
397 0.01537 va`
392 0.01518 ngu+o+i
381 0.01475 la`
removed 'dat/viet/ptt/lev.1/raw-trunc-wds-summary.tex'
removed 'exp/viet/ptt/lev.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/viet/ptt/lev.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:31 by tex-make-sample-summary.sh
% Token and word counts for viet/ptt/lev.1/raw.wfr
%
\def\vietptttrunclevPBrawTks{25831}
\def\vietptttrunclevPBrawTksPct{100.0}
\def\vietptttrunclevPBrawWds{1210}
\def\vietptttrunclevPBrawWdsPct{4.7}
copied '/tmp/585339.file' -> 'exp/viet/ptt/lev.1/raw-trunc-wds-summary.tex'
removed '/tmp/585339.file'
creating running text file dat/viet/ptt/lev.1/gud.wdf
sample:
ddu+'c gie^ ho^ va tu+` trong ho^.i ma.c go.i mo^i se ma` pha'n ra(`ng
ha~y no'i cu`ng da^n y so+ ra e^n ra(`ng khi ngu+o+`i na`o trong vo`ng
ca'c ngu+o+i da^ng cu?a le^~ cho ddu+'c gie^ ho^ va thi` pha?i da^ng
su'c va^.t hoa(.c bo` hoa(.c chie^n ne^'u le^~ va^.t cu?a ngu+o+`i la`
cu?a le^~ thie^u ba(`ng bo` thi` pha?i du`ng con ddu+.c kho^ng ti` vi't
da^ng le^n ta.i cu+?a ho^.i ma.c tru+o+'c ma(.t ddu+'c gie^ ho^ va dde^?
ddu+o+.c nga`i dde.p lo`ng nha^.m la^'y ngu+o+`i se~ nha^.n tay mi`nh
tre^n dda^`u con sinh no' se~ ddu+o+.c nha^.m the^' cho ha^`u chuo^.c
to^.i cho ngu+o+`i ddoa.n ngu+o+`i se~ gie^'t bo` to+ tru+o+'c ma(.t
ddu+'c gie^ ho^ va ro^`i ca'c con trai a ro^n tu+'c nhu+~ng tha^`y te^'
le^~ se~ da^ng huye^'t le^n va` ru+o+'i chunh quanh tre^n ba`n tho+`
ta.i no+i cu+?a ho^.i ma.c ke^' ddo' lo^.t da con sinh va` sa? thi.t ra
tu+`ng mie^'ng ca'c con trai tha^`y te^' le^~ a ro^n se~ cha^m lu+?a
tre^n ba`n tho+` cha^'t cu?i chu.m lu+?a ro^`i ca'c con trai a ro^n
tu+'c nhu+~ng tha^`y te^' le^~ sa('p ca'c mie^'ng thi.t dda^`u va` mo+~
le^n tre^n cu?i dda~ chu.m lu+?a no+i ba`n tho+` ngu+o+`i se~ la^'y
nu+o+'c ru+?a bo^. lo`ng va` gio` ro^`i tha^`y te^' le^~ ddem he^'t mo.i
pha^`n xo^ng no+i ba`n tho+` a^'y la` cu?a le^~ thie^u tu+'c mo^.t cu?a
le^~ du`ng lu+?a da^ng le^n co' mu`i tho+m cho ddu+'c gie^ ho^ va ne^'u
le^~ va^.t ngu+o+`i la` cu?a le^~ thie^u ba(`ng su'c va^.t nho? hoa(.c
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
ca? hai dde^`u bie^.t ra tha'nh kho^ng phe'p chuo^.c no' la.i ddo' la`
ca'c ma.ng li.nh ma` ddu+'c gie^ ho^ va truye^`n cho mo^i se ve^` da^n y
so+ ra e^n ta.i tre^n nu'i si na i
removed 'dat/viet/ptt/lev.1/gud.wfr'
creating the word frequency file dat/viet/ptt/lev.1/gud.wfr
the 10 most common words in dat/viet/ptt/lev.1/gud.tlw:
541 0.02150 le^~
523 0.02078 ngu+o+`i
494 0.01963 cu?a
471 0.01872 ca'c
409 0.01625 cho
403 0.01602 se~
397 0.01578 va`
392 0.01558 ngu+o+i
381 0.01514 la`
365 0.01451 mo^.t
removed 'dat/viet/ptt/lev.1/gud-trunc-wds-summary.tex'
removed 'exp/viet/ptt/lev.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/viet/ptt/lev.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:31 by tex-make-sample-summary.sh
% Token and word counts for viet/ptt/lev.1/gud.wfr
%
\def\vietptttrunclevPBgudTks{25163}
\def\vietptttrunclevPBgudTksPct{97.4}
\def\vietptttrunclevPBgudWds{1207}
\def\vietptttrunclevPBgudWdsPct{4.7}
copied '/tmp/585383.file' -> 'exp/viet/ptt/lev.1/gud-trunc-wds-summary.tex'
removed '/tmp/585383.file'
creating running text file dat/viet/ptt/lev.1/bad.wdf
sample:
*{sa'ch} ..*{se} =
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/viet/ptt/lev.1/bad.wfr'
creating the word frequency file dat/viet/ptt/lev.1/bad.wfr
the 10 most common words in dat/viet/ptt/lev.1/bad.tlw:
666 0.99701 =
1 0.00150 *{sa'ch}
1 0.00150 ..*{se}
removed 'dat/viet/ptt/lev.1/bad-trunc-wds-summary.tex'
removed 'exp/viet/ptt/lev.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/viet/ptt/lev.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:31 by tex-make-sample-summary.sh
% Token and word counts for viet/ptt/lev.1/bad.wfr
%
\def\vietptttrunclevPBbadTks{668}
\def\vietptttrunclevPBbadTksPct{2.6}
\def\vietptttrunclevPBbadWds{3}
\def\vietptttrunclevPBbadWdsPct{0.0}
copied '/tmp/585427.file' -> 'exp/viet/ptt/lev.1/bad-trunc-wds-summary.tex'
removed '/tmp/585427.file'
... creating word files dat/viet/ptt/deu.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
32092 dat/viet/ptt/deu.1/trunc.tlw
removed 'dat/viet/ptt/deu.1/raw.tlw'
removed 'dat/viet/ptt/deu.1/gud.tlw'
removed 'dat/viet/ptt/deu.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/viet/ptt/deu.1/raw.wdf
sample:
*{sa'ch} ..*{se} na^`y la` lo+`i mo^i se no'i cho ca? y so+ ra e^n be^n
kia so^ng gio^ ddanh ta.i ddo^`ng va('ng trong ddo^`ng ba(`ng ddo^'i
ngang su pho+ giu+~a khoa?ng pha ran va` to^ phe^n la ban ha't se^ ro^'t
va` ddi xa ha'p =
tu+` ho^ re^'p to+'i ca dde ba ne^ a bo+?i ddu+o+`ng nu'i se^ i ro+ ddi
mu+o+`i mo^.t nga`y ddu+o+`ng =
nha(`m na(m bo^'n mu+o+i nga`y mo^`ng mo^.t tha'ng mu+o+`i mo^.t mo^i se
no'i cu`ng da^n y so+ ra e^n mo.i ddie^`u ma` ddu+'c gie^ ho^ va dda~
bie^?u ngu+o+`i pha?i no'i cu`ng ho. =
a^'y la` sau khi ngu+o+`i dda~ dda'nh gie^'t si ho^n vua da^n a mo^ ri't
o+? ta.i he^'t bo^n va` o'c vua ba san o+? ta.i a'ch ta ro^'t va` e^'t
re^ i =
ta.i be^n kia so^ng gio^ ddanh trong xu+' mo^ a'p mo^i se kho+?i gia?ng
gia?i lua^.t pha'p na^`y ma` ra(`ng gie^ ho^ va ddu+'c chu'a tro+`i
chu'ng ta co' pha'n cu`ng chu'ng ta ta.i ho^ re^'p ma` ra(`ng ca'c
ngu+o+i kie^`u ngu. trong nu'i na^`y dda~ la^u qua' ha~y vo`ng la.i va`
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
ca^.y tay quye^`n na(ng mi`nh la`m ta.i tru+o+'c ma(.t ca? y so+ ra e^n
=
removed 'dat/viet/ptt/deu.1/raw.wfr'
creating the word frequency file dat/viet/ptt/deu.1/raw.wfr
the 10 most common words in dat/viet/ptt/deu.1/raw.tlw:
1490 0.04643 ngu+o+i
729 0.02272 =
660 0.02057 va`
629 0.01960 ca'c
560 0.01745 cho
559 0.01742 ddu+'c
543 0.01692 ho^
539 0.01680 gie^
531 0.01655 va
447 0.01393 cu?a
removed 'dat/viet/ptt/deu.1/raw-trunc-wds-summary.tex'
removed 'exp/viet/ptt/deu.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/viet/ptt/deu.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:31 by tex-make-sample-summary.sh
% Token and word counts for viet/ptt/deu.1/raw.wfr
%
\def\vietptttruncdeuPBrawTks{32092}
\def\vietptttruncdeuPBrawTksPct{100.0}
\def\vietptttruncdeuPBrawWds{1617}
\def\vietptttruncdeuPBrawWdsPct{5.0}
copied '/tmp/585482.file' -> 'exp/viet/ptt/deu.1/raw-trunc-wds-summary.tex'
removed '/tmp/585482.file'
creating running text file dat/viet/ptt/deu.1/gud.wdf
sample:
na^`y la` lo+`i mo^i se no'i cho ca? y so+ ra e^n be^n kia so^ng gio^
ddanh ta.i ddo^`ng va('ng trong ddo^`ng ba(`ng ddo^'i ngang su pho+
giu+~a khoa?ng pha ran va` to^ phe^n la ban ha't se^ ro^'t va` ddi xa
ha'p tu+` ho^ re^'p to+'i ca dde ba ne^ a bo+?i ddu+o+`ng nu'i se^ i ro+
ddi mu+o+`i mo^.t nga`y ddu+o+`ng nha(`m na(m bo^'n mu+o+i nga`y mo^`ng
mo^.t tha'ng mu+o+`i mo^.t mo^i se no'i cu`ng da^n y so+ ra e^n mo.i
ddie^`u ma` ddu+'c gie^ ho^ va dda~ bie^?u ngu+o+`i pha?i no'i cu`ng ho.
a^'y la` sau khi ngu+o+`i dda~ dda'nh gie^'t si ho^n vua da^n a mo^ ri't
o+? ta.i he^'t bo^n va` o'c vua ba san o+? ta.i a'ch ta ro^'t va` e^'t
re^ i ta.i be^n kia so^ng gio^ ddanh trong xu+' mo^ a'p mo^i se kho+?i
gia?ng gia?i lua^.t pha'p na^`y ma` ra(`ng gie^ ho^ va ddu+'c chu'a
tro+`i chu'ng ta co' pha'n cu`ng chu'ng ta ta.i ho^ re^'p ma` ra(`ng
ca'c ngu+o+i kie^`u ngu. trong nu'i na^`y dda~ la^u qua' ha~y vo`ng la.i
va` ddi dde^'n nu'i da^n a mo^ ri't cu`ng dde^'n ca'c mie^`n o+? ga^`n
be^n tu+'c la` dde^'n no+i ddo^`ng ba(`ng le^n nu'i va`o xu+' tha^'p
dde^'n mie^`n nam le^n me' bie^?n va`o xu+' da^n ca na an va` li ban cho
dde^'n so^ng lo+'n la` so^ng o+ pho+ ra't ki`a ta pho' xu+' na^`y cho
ca'c ngu+o+i ha~y va`o va` chie^'m la^'y xu+' ma` ddu+'c gie^ ho^ va
dda~ the^` ban cho to^? phu. ca'c ngu+o+i la` a'p ra ham y sa'c gia
co^'p cu`ng cho con cha'u cu?a ho. trong lu'c ddo' ta co' no'i cu`ng
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
qua^`n tha^`n va` ca? xu+' cu?a ngu+o+`i hoa(.c he^'t tha?y co^ng vie^.c
lo+'n lao va` dda'ng so+. ma` mo^i se ca^.y tay quye^`n na(ng mi`nh la`m
ta.i tru+o+'c ma(.t ca? y so+ ra e^n
removed 'dat/viet/ptt/deu.1/gud.wfr'
creating the word frequency file dat/viet/ptt/deu.1/gud.wfr
the 10 most common words in dat/viet/ptt/deu.1/gud.tlw:
1490 0.04751 ngu+o+i
660 0.02105 va`
629 0.02006 ca'c
560 0.01786 cho
559 0.01782 ddu+'c
543 0.01731 ho^
539 0.01719 gie^
531 0.01693 va
447 0.01425 cu?a
446 0.01422 ngu+o+`i
removed 'dat/viet/ptt/deu.1/gud-trunc-wds-summary.tex'
removed 'exp/viet/ptt/deu.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/viet/ptt/deu.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:31 by tex-make-sample-summary.sh
% Token and word counts for viet/ptt/deu.1/gud.wfr
%
\def\vietptttruncdeuPBgudTks{31361}
\def\vietptttruncdeuPBgudTksPct{97.7}
\def\vietptttruncdeuPBgudWds{1614}
\def\vietptttruncdeuPBgudWdsPct{5.0}
copied '/tmp/585526.file' -> 'exp/viet/ptt/deu.1/gud-trunc-wds-summary.tex'
removed '/tmp/585526.file'
creating running text file dat/viet/ptt/deu.1/bad.wdf
sample:
*{sa'ch} ..*{se} =
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/viet/ptt/deu.1/bad.wfr'
creating the word frequency file dat/viet/ptt/deu.1/bad.wfr
the 10 most common words in dat/viet/ptt/deu.1/bad.tlw:
729 0.99726 =
1 0.00137 *{sa'ch}
1 0.00137 ..*{se}
removed 'dat/viet/ptt/deu.1/bad-trunc-wds-summary.tex'
removed 'exp/viet/ptt/deu.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/viet/ptt/deu.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:32 by tex-make-sample-summary.sh
% Token and word counts for viet/ptt/deu.1/bad.wfr
%
\def\vietptttruncdeuPBbadTks{731}
\def\vietptttruncdeuPBbadTksPct{2.3}
\def\vietptttruncdeuPBbadWds{3}
\def\vietptttruncdeuPBbadWdsPct{0.0}
copied '/tmp/585570.file' -> 'exp/viet/ptt/deu.1/bad-trunc-wds-summary.tex'
removed '/tmp/585570.file'
... creating word files dat/viet/ptt/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
36022 dat/viet/ptt/tot.1/trunc.tlw
removed 'dat/viet/ptt/tot.1/raw.tlw'
removed 'dat/viet/ptt/tot.1/gud.tlw'
removed 'dat/viet/ptt/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/viet/ptt/tot.1/raw.wdf
sample:
*{sa'ch} ..*{se} ban dda^`u ddu+'c chu'a tro+`i du+.ng ne^n tro+`i
dda^'t =
va? dda^'t la` vo^ hi`nh va` tro^'ng kho^ng su+. mo+` to^'i o+? tre^n
ma(.t vu+.c tha^`n ddu+'c chu'a tro+`i va^.n ha`nh tre^n ma(.t nu+o+'c =
ddu+'c chu'a tro+`i pha'n ra(`ng pha?i co' su+. sa'ng thi` co' su+.
sa'ng =
ddu+'c chu'a tro+`i tha^'y su+. sa'ng la` to^'t la`nh be`n pha^n sa'ng
ra cu`ng to^'i =
ddu+'c chu'a tro+`i dda(.t te^n su+. sa'ng la` nga`y su+. to^'i la`
dde^m va^.y co' buo^?i chie^`u va` buo^?i mai a^'y la` nga`y thu+'
nhu+'t =
ddu+'c chu'a tro+`i la.i pha'n ra(`ng pha?i co' mo^.t khoa?ng kho^ng o+?
giu+~a nu+o+'c dda(.ng pha^n re~ nu+o+'c ca'ch vo+'i nu+o+'c =
nga`i la`m ne^n khoa?ng kho^ng pha^n re~ nu+o+'c o+? du+o+'i khoa?ng
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
va? na^`y la` ddie^`u ra(n lua^.t le^. va` ma.ng li.nh ma` gie^ ho^ va
ddu+'c chu'a tro+`i ca'c ngu+o+i dda~ pha'n da(.n ta da.y la.i cho dde^?
ca'c ngu+o+i la`m theo no' trong xu+' ma` ca'c
removed 'dat/viet/ptt/tot.1/raw.wfr'
creating the word frequency file dat/viet/ptt/tot.1/raw.wfr
the 10 most common words in dat/viet/ptt/tot.1/raw.tlw:
985 0.02734 =
694 0.01927 va`
669 0.01857 ngu+o+`i
653 0.01813 cu?a
537 0.01491 ca'c
524 0.01455 ngu+o+i
507 0.01407 ddu+'c
465 0.01291 cho
461 0.01280 la`
425 0.01180 con
removed 'dat/viet/ptt/tot.1/raw-trunc-wds-summary.tex'
removed 'exp/viet/ptt/tot.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/viet/ptt/tot.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:32 by tex-make-sample-summary.sh
% Token and word counts for viet/ptt/tot.1/raw.wfr
%
\def\vietptttrunctotPBrawTks{36022}
\def\vietptttrunctotPBrawTksPct{100.0}
\def\vietptttrunctotPBrawWds{1634}
\def\vietptttrunctotPBrawWdsPct{4.5}
copied '/tmp/585624.file' -> 'exp/viet/ptt/tot.1/raw-trunc-wds-summary.tex'
removed '/tmp/585624.file'
creating running text file dat/viet/ptt/tot.1/gud.wdf
sample:
ban dda^`u ddu+'c chu'a tro+`i du+.ng ne^n tro+`i dda^'t va? dda^'t la`
vo^ hi`nh va` tro^'ng kho^ng su+. mo+` to^'i o+? tre^n ma(.t vu+.c
tha^`n ddu+'c chu'a tro+`i va^.n ha`nh tre^n ma(.t nu+o+'c ddu+'c chu'a
tro+`i pha'n ra(`ng pha?i co' su+. sa'ng thi` co' su+. sa'ng ddu+'c
chu'a tro+`i tha^'y su+. sa'ng la` to^'t la`nh be`n pha^n sa'ng ra cu`ng
to^'i ddu+'c chu'a tro+`i dda(.t te^n su+. sa'ng la` nga`y su+. to^'i
la` dde^m va^.y co' buo^?i chie^`u va` buo^?i mai a^'y la` nga`y thu+'
nhu+'t ddu+'c chu'a tro+`i la.i pha'n ra(`ng pha?i co' mo^.t khoa?ng
kho^ng o+? giu+~a nu+o+'c dda(.ng pha^n re~ nu+o+'c ca'ch vo+'i nu+o+'c
nga`i la`m ne^n khoa?ng kho^ng pha^n re~ nu+o+'c o+? du+o+'i khoa?ng
kho^ng ca'ch vo+'i nu+o+'c o+? tre^n khoa?ng kho^ng thi` co' nhu+ va^.y
ddu+'c chu'a tro+`i dda(.t te^n khoa?ng kho^ng la` tro+`i va^.y co'
buo^?i chie^`u va` buo^?i mai a^'y la` nga`y thu+' nhi` ddu+'c chu'a
tro+`i la.i pha'n ra(`ng nhu+~ng nu+o+'c o+? du+o+'i tro+`i pha?i tu.
la.i mo^.t no+i va` pha?i co' cho^~ kho^ ca.n ba`y ra thi` co' nhu+
va^.y ddu+'c chu'a tro+`i dda(.t te^n cho^~ kho^ ca.n la` dda^'t co`n
no+i nu+o+'c tu. la.i la` bie^?n ddu+'c chu'a tro+`i tha^'y dde^`u ddo'
la` to^'t la`nh ddu+'c chu'a tro+`i la.i pha'n ra(`ng dda^'t pha?i sanh
ca^y co? co? ke^'t ho^.t gio^'ng ca^y tra'i ke^'t qua? tu`y theo loa.i
ma` co' ho^.t gio^'ng trong mi`nh tre^n dda^'t thi` co' nhu+ va^.y
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
nha^.n ddu+o+.c va? na^`y la` ddie^`u ra(n lua^.t le^. va` ma.ng li.nh
ma` gie^ ho^ va ddu+'c chu'a tro+`i ca'c ngu+o+i dda~ pha'n da(.n ta
da.y la.i cho dde^? ca'c ngu+o+i la`m theo no' trong xu+' ma` ca'c
removed 'dat/viet/ptt/tot.1/gud.wfr'
creating the word frequency file dat/viet/ptt/tot.1/gud.wfr
the 10 most common words in dat/viet/ptt/tot.1/gud.tlw:
694 0.01981 va`
669 0.01910 ngu+o+`i
653 0.01864 cu?a
537 0.01533 ca'c
524 0.01496 ngu+o+i
507 0.01447 ddu+'c
465 0.01328 cho
461 0.01316 la`
425 0.01213 con
414 0.01182 gie^
removed 'dat/viet/ptt/tot.1/gud-trunc-wds-summary.tex'
removed 'exp/viet/ptt/tot.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/viet/ptt/tot.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:33 by tex-make-sample-summary.sh
% Token and word counts for viet/ptt/tot.1/gud.wfr
%
\def\vietptttrunctotPBgudTks{35027}
\def\vietptttrunctotPBgudTksPct{97.2}
\def\vietptttrunctotPBgudWds{1631}
\def\vietptttrunctotPBgudWdsPct{4.5}
copied '/tmp/585668.file' -> 'exp/viet/ptt/tot.1/gud-trunc-wds-summary.tex'
removed '/tmp/585668.file'
creating running text file dat/viet/ptt/tot.1/bad.wdf
sample:
*{sa'ch} ..*{se} =
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/viet/ptt/tot.1/bad.wfr'
creating the word frequency file dat/viet/ptt/tot.1/bad.wfr
the 10 most common words in dat/viet/ptt/tot.1/bad.tlw:
985 0.98995 =
5 0.00503 *{sa'ch}
5 0.00503 ..*{se}
removed 'dat/viet/ptt/tot.1/bad-trunc-wds-summary.tex'
removed 'exp/viet/ptt/tot.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/viet/ptt/tot.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:33 by tex-make-sample-summary.sh
% Token and word counts for viet/ptt/tot.1/bad.wfr
%
\def\vietptttrunctotPBbadTks{995}
\def\vietptttrunctotPBbadTksPct{2.8}
\def\vietptttrunctotPBbadWds{3}
\def\vietptttrunctotPBbadWdsPct{0.0}
copied '/tmp/585712.file' -> 'exp/viet/ptt/tot.1/bad-trunc-wds-summary.tex'
removed '/tmp/585712.file'
lines words bytes file
------- ------- --------- ------------
1693 5079 36678 dat/viet/ptt/gen.1/raw.wfr
1652 4956 35906 dat/viet/ptt/exo.1/raw.wfr
1462 4386 31645 dat/viet/ptt/num.1/raw.wfr
1210 3630 26313 dat/viet/ptt/lev.1/raw.wfr
1617 4851 35033 dat/viet/ptt/deu.1/raw.wfr
1634 4902 35427 dat/viet/ptt/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
1690 5070 36611 dat/viet/ptt/gen.1/gud.wfr
1649 4947 35839 dat/viet/ptt/exo.1/gud.wfr
1459 4377 31578 dat/viet/ptt/num.1/gud.wfr
1207 3621 26246 dat/viet/ptt/lev.1/gud.wfr
1614 4842 34966 dat/viet/ptt/deu.1/gud.wfr
1631 4893 35360 dat/viet/ptt/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
3 9 67 dat/viet/ptt/gen.1/bad.wfr
3 9 67 dat/viet/ptt/exo.1/bad.wfr
3 9 67 dat/viet/ptt/num.1/bad.wfr
3 9 67 dat/viet/ptt/lev.1/bad.wfr
3 9 67 dat/viet/ptt/deu.1/bad.wfr
3 9 67 dat/viet/ptt/tot.1/bad.wfr
gen.1 raw = 36162 gud = 35027 bad = 1135
exo.1 raw = 34775 gud = 33760 bad = 1015
num.1 raw = 35949 gud = 35027 bad = 922
lev.1 raw = 25831 gud = 25163 bad = 668
deu.1 raw = 32092 gud = 31361 bad = 731
tot.1 raw = 36022 gud = 35027 bad = 995
=== creating the derived word files dat/viet/nwt/*/{raw,gud,bad}.{tlw,wdf,wfr} (trunc) ===
... creating word files dat/viet/nwt/mat.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
26411 dat/viet/nwt/mat.1/trunc.tlw
removed 'dat/viet/nwt/mat.1/raw.tlw'
removed 'dat/viet/nwt/mat.1/gud.tlw'
removed 'dat/viet/nwt/mat.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/viet/nwt/mat.1/raw.wdf
sample:
gia pha? ddu+'c chu'a gie^ su ki to^ con dda vi't con a'p ra ham a'p ra
ham sinh y sa'c y sa'c sinh gia co^'p gia co^'p sinh giu dda va` ca'c
anh em o^ng giu dda sinh pha re^ va`o xa ra bo+?i tha ma pha re^ sinh e^
se ro^m e^ se ro^m sinh a ram a ram sinh a mi na dda'p a mi na dda'p
sinh na a so^n na a so^n sinh sa mo^n sa mo^n sinh bo't se^ bo+?i ra
ha'p bo't se^ sinh gio^ be^t bo+?i ba` ru't gio^ be^'t sinh y sai y sai
sinh vua dda vi't dda vi't sinh sa lo^ mo^n bo+?i vo+. cu?a u ria sa lo^
mo^n sinh ro bo am ro bo am sinh a bia a bia sinh a sa a sa sinh gio^ sa
phat gio^ sa phat sinh gio^ ram gio^ ram sinh o^ xya o^ xya sinh gio^ a
tham gio^ a tham sinh a ka a ka sinh e^t se^ kya e^t se^ kya sinh ma na
se^ ma na se^ sinh am mo^n am mo^n sinh gio^ sya gio^ sya sinh gie^ kho^
nya va` ca'c anh em o^ng tho+`i lu+u dda`y ba be^n sau tho+`i lu+u dda`y
ba be^n gie^ kho^ nya sinh sa la thi e^n sa la thi e^n sinh xo ro ba
be^n xo ro ba be^n sinh a bi hu a bi hu sinh e^ lya kim e^ lya kim sinh
a't so^ a't so^ sinh sa ddo'c sa ddo'c sinh a khim a khim sinh e^ li hu
e^ li hu sinh e^ li a sa e^ li a sa sinh ma't than ma't than sinh gia
co^'p gia co^'p sinh gio^ se'p cho^`ng cu?a ma ria bo+?i ba` thi` ddu+'c
gie^ su go.i la` ki to^ dda~ sinh ra =
to^?ng co^.ng ca'c ddo+`i la.i thi` tu+` a'p ra ham dde^'n dda vi't co'
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
giu+~ he^'t mo.i ddie^`u ta dda~ truye^`n cho ca'c ngu+o+i va` na`y ta
se~ o+? vo+'i ca'c ngu+o+i mo.i nga`y cho dde^'n ta^.n the^' =
removed 'dat/viet/nwt/mat.1/raw.wfr'
creating the word frequency file dat/viet/nwt/mat.1/raw.wfr
the 10 most common words in dat/viet/nwt/mat.1/raw.tlw:
794 0.03006 =
636 0.02408 va`
572 0.02166 ca'c
517 0.01958 nga`i
486 0.01840 ngu+o+i
430 0.01628 ngu+o+`i
389 0.01473 ta
340 0.01287 cho
335 0.01268 dda~
332 0.01257 ma`
removed 'dat/viet/nwt/mat.1/raw-trunc-wds-summary.tex'
removed 'exp/viet/nwt/mat.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/viet/nwt/mat.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:33 by tex-make-sample-summary.sh
% Token and word counts for viet/nwt/mat.1/raw.wfr
%
\def\vietnwttruncmatPBrawTks{26411}
\def\vietnwttruncmatPBrawTksPct{100.0}
\def\vietnwttruncmatPBrawWds{1821}
\def\vietnwttruncmatPBrawWdsPct{6.9}
copied '/tmp/585882.file' -> 'exp/viet/nwt/mat.1/raw-trunc-wds-summary.tex'
removed '/tmp/585882.file'
creating running text file dat/viet/nwt/mat.1/gud.wdf
sample:
gia pha? ddu+'c chu'a gie^ su ki to^ con dda vi't con a'p ra ham a'p ra
ham sinh y sa'c y sa'c sinh gia co^'p gia co^'p sinh giu dda va` ca'c
anh em o^ng giu dda sinh pha re^ va`o xa ra bo+?i tha ma pha re^ sinh e^
se ro^m e^ se ro^m sinh a ram a ram sinh a mi na dda'p a mi na dda'p
sinh na a so^n na a so^n sinh sa mo^n sa mo^n sinh bo't se^ bo+?i ra
ha'p bo't se^ sinh gio^ be^t bo+?i ba` ru't gio^ be^'t sinh y sai y sai
sinh vua dda vi't dda vi't sinh sa lo^ mo^n bo+?i vo+. cu?a u ria sa lo^
mo^n sinh ro bo am ro bo am sinh a bia a bia sinh a sa a sa sinh gio^ sa
phat gio^ sa phat sinh gio^ ram gio^ ram sinh o^ xya o^ xya sinh gio^ a
tham gio^ a tham sinh a ka a ka sinh e^t se^ kya e^t se^ kya sinh ma na
se^ ma na se^ sinh am mo^n am mo^n sinh gio^ sya gio^ sya sinh gie^ kho^
nya va` ca'c anh em o^ng tho+`i lu+u dda`y ba be^n sau tho+`i lu+u dda`y
ba be^n gie^ kho^ nya sinh sa la thi e^n sa la thi e^n sinh xo ro ba
be^n xo ro ba be^n sinh a bi hu a bi hu sinh e^ lya kim e^ lya kim sinh
a't so^ a't so^ sinh sa ddo'c sa ddo'c sinh a khim a khim sinh e^ li hu
e^ li hu sinh e^ li a sa e^ li a sa sinh ma't than ma't than sinh gia
co^'p gia co^'p sinh gio^ se'p cho^`ng cu?a ma ria bo+?i ba` thi` ddu+'c
gie^ su go.i la` ki to^ dda~ sinh ra to^?ng co^.ng ca'c ddo+`i la.i thi`
tu+` a'p ra ham dde^'n dda vi't co' mu+o+`i bo^'n ddo+`i tu+` dda vi't
dde^'n tho+`i lu+u dda`y ba be^n co' mu+o+`i bo^'n ddo+`i tu+` tho+`i
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
muo^n da^n thanh ta^?y chu'ng nha^n danh cha va` con va` tha'nh tha^`n
da.y chu'ng giu+~ he^'t mo.i ddie^`u ta dda~ truye^`n cho ca'c ngu+o+i
va` na`y ta se~ o+? vo+'i ca'c ngu+o+i mo.i nga`y cho dde^'n ta^.n the^'
removed 'dat/viet/nwt/mat.1/gud.wfr'
creating the word frequency file dat/viet/nwt/mat.1/gud.wfr
the 10 most common words in dat/viet/nwt/mat.1/gud.tlw:
636 0.02483 va`
572 0.02233 ca'c
517 0.02018 nga`i
486 0.01897 ngu+o+i
430 0.01679 ngu+o+`i
389 0.01519 ta
340 0.01327 cho
335 0.01308 dda~
332 0.01296 ma`
327 0.01277 ho.
removed 'dat/viet/nwt/mat.1/gud-trunc-wds-summary.tex'
removed 'exp/viet/nwt/mat.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/viet/nwt/mat.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:33 by tex-make-sample-summary.sh
% Token and word counts for viet/nwt/mat.1/gud.wfr
%
\def\vietnwttruncmatPBgudTks{25615}
\def\vietnwttruncmatPBgudTksPct{97.0}
\def\vietnwttruncmatPBgudWds{1818}
\def\vietnwttruncmatPBgudWdsPct{6.9}
copied '/tmp/585926.file' -> 'exp/viet/nwt/mat.1/gud-trunc-wds-summary.tex'
removed '/tmp/585926.file'
creating running text file dat/viet/nwt/mat.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/viet/nwt/mat.1/bad.wfr'
creating the word frequency file dat/viet/nwt/mat.1/bad.wfr
the 10 most common words in dat/viet/nwt/mat.1/bad.tlw:
794 0.99749 =
1 0.00126 *{e^}
1 0.00126 ..*{sabakthani}
removed 'dat/viet/nwt/mat.1/bad-trunc-wds-summary.tex'
removed 'exp/viet/nwt/mat.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/viet/nwt/mat.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:33 by tex-make-sample-summary.sh
% Token and word counts for viet/nwt/mat.1/bad.wfr
%
\def\vietnwttruncmatPBbadTks{796}
\def\vietnwttruncmatPBbadTksPct{3.0}
\def\vietnwttruncmatPBbadWds{3}
\def\vietnwttruncmatPBbadWdsPct{0.0}
copied '/tmp/585970.file' -> 'exp/viet/nwt/mat.1/bad-trunc-wds-summary.tex'
removed '/tmp/585970.file'
... creating word files dat/viet/nwt/mrk.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
16326 dat/viet/nwt/mrk.1/trunc.tlw
removed 'dat/viet/nwt/mrk.1/raw.tlw'
removed 'dat/viet/nwt/mrk.1/gud.tlw'
removed 'dat/viet/nwt/mrk.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/viet/nwt/mrk.1/raw.wdf
sample:
kho+?i nguye^n tin mu+`ng ddu+'c gie^ su ki to^ con thie^n chu'a =
nhu+ dda~ vie^'t trong sa'ch tie^n tri y sa y a na`y ta sai tha^`n su+'
ta ddi tru+o+'c ma(.t ngu+o+i ke? se~ do.n ddu+o+`ng cho ngu+o+i tie^'ng
cu?a ngu+o+i ho^ trong sa ma.c ha~y do.n ddu+o+`ng chu'a ha~y ba.t lo^'i
ngu+o+`i ddi =
trong sa ma.c gio^ an ta^?y gia? xua^'t hie^.n rao gia?ng thanh ta^?y
ho^'i ca?i dde^? ddu+o+.c tha thu+' to^.i khie^n =
va` ca? xu+' giu dde^ va` ta^'t ca? da^n tha`nh gie^ ru sa lem tra^?y
da^'n vo+'i o^ng va` nho+` o^ng thanh ta^?y cho trong so^ng gio^ ddanh
ma` xu+ng thu' to^.i lo^~i =
gio^ an mi`nh ma(.c a'o lo^ng la.c dda` va` ngang lu+ng thi` tha('t
xie^m ba(`ng da thu' va^.t va` o^ng nuo^i mi`nh ba(`ng cha^u cha^'u va`
ma^.t ong da.i =
o^ng rao gia?ng ra(`ng se~ dde^'n sau to^i dda^'ng quye^`n the^' ho+n
to^i to^i kho^ng dda'ng cu'i xuo^'ng ma` co+?i quai de'p nga`i =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
co`n ho. thi` ra ddi rao gia?ng kha('p no+i co' chu'a cu`ng ho. hoa.t
ddo^.ng va` cu?ng co^' lo+`i bo+?i phe'p la. ke`m theo =
removed 'dat/viet/nwt/mrk.1/raw.wfr'
creating the word frequency file dat/viet/nwt/mrk.1/raw.wfr
the 10 most common words in dat/viet/nwt/mrk.1/raw.tlw:
535 0.03277 nga`i
476 0.02916 va`
429 0.02628 =
354 0.02168 ho.
300 0.01838 ngu+o+`i
244 0.01495 ca'c
211 0.01292 vo+'i
205 0.01256 dda~
202 0.01237 cho
202 0.01237 no'i
removed 'dat/viet/nwt/mrk.1/raw-trunc-wds-summary.tex'
removed 'exp/viet/nwt/mrk.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/viet/nwt/mrk.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:33 by tex-make-sample-summary.sh
% Token and word counts for viet/nwt/mrk.1/raw.wfr
%
\def\vietnwttruncmrkPBrawTks{16326}
\def\vietnwttruncmrkPBrawTksPct{100.0}
\def\vietnwttruncmrkPBrawWds{1575}
\def\vietnwttruncmrkPBrawWdsPct{9.6}
copied '/tmp/586024.file' -> 'exp/viet/nwt/mrk.1/raw-trunc-wds-summary.tex'
removed '/tmp/586024.file'
creating running text file dat/viet/nwt/mrk.1/gud.wdf
sample:
kho+?i nguye^n tin mu+`ng ddu+'c gie^ su ki to^ con thie^n chu'a nhu+
dda~ vie^'t trong sa'ch tie^n tri y sa y a na`y ta sai tha^`n su+' ta
ddi tru+o+'c ma(.t ngu+o+i ke? se~ do.n ddu+o+`ng cho ngu+o+i tie^'ng
cu?a ngu+o+i ho^ trong sa ma.c ha~y do.n ddu+o+`ng chu'a ha~y ba.t lo^'i
ngu+o+`i ddi trong sa ma.c gio^ an ta^?y gia? xua^'t hie^.n rao gia?ng
thanh ta^?y ho^'i ca?i dde^? ddu+o+.c tha thu+' to^.i khie^n va` ca?
xu+' giu dde^ va` ta^'t ca? da^n tha`nh gie^ ru sa lem tra^?y da^'n
vo+'i o^ng va` nho+` o^ng thanh ta^?y cho trong so^ng gio^ ddanh ma`
xu+ng thu' to^.i lo^~i gio^ an mi`nh ma(.c a'o lo^ng la.c dda` va` ngang
lu+ng thi` tha('t xie^m ba(`ng da thu' va^.t va` o^ng nuo^i mi`nh ba(`ng
cha^u cha^'u va` ma^.t ong da.i o^ng rao gia?ng ra(`ng se~ dde^'n sau
to^i dda^'ng quye^`n the^' ho+n to^i to^i kho^ng dda'ng cu'i xuo^'ng ma`
co+?i quai de'p nga`i pha^`n to^i to^i dda~ thanh ta^?y ca'c ngu+o+`i
ba(`ng nu+o+'c co`n nga`i nga`i se~ thanh ta^?y ca'c ngu+o+`i ba(`ng
tha'nh tha^`n va` xa?y ra la` trong nhu+~ng nga`y a^'y ddu+'c gie^ su
bo? na xa re^ xu+' ga li le^ va` dda~ ddu+o+.c gio^ an thanh ta^?y cho
trong so^ng gio^ ddanh vu+`a le^n kho?i nu+o+'c nga`i tha^'y tro+`i xe'
ra va` tha^`n khi' nhu+ con chim ca^u dda'p xuo^'ng tre^n nga`i va`
mo^.t tie^'ng pha't ra tu+. tro+`i con la` con chi' a'i ta ke? ta su?ng
mo^. va` ngay sau ddo' tha^`n khi' xua nga`i va`o sa ma.c va` nga`i o+?
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
be^n hu+~u thie^n chu'a co`n ho. thi` ra ddi rao gia?ng kha('p no+i co'
chu'a cu`ng ho. hoa.t ddo^.ng va` cu?ng co^' lo+`i bo+?i phe'p la. ke`m
theo
removed 'dat/viet/nwt/mrk.1/gud.wfr'
creating the word frequency file dat/viet/nwt/mrk.1/gud.wfr
the 10 most common words in dat/viet/nwt/mrk.1/gud.tlw:
535 0.03366 nga`i
476 0.02995 va`
354 0.02227 ho.
300 0.01887 ngu+o+`i
244 0.01535 ca'c
211 0.01327 vo+'i
205 0.01290 dda~
202 0.01271 cho
202 0.01271 no'i
201 0.01265 ta
removed 'dat/viet/nwt/mrk.1/gud-trunc-wds-summary.tex'
removed 'exp/viet/nwt/mrk.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/viet/nwt/mrk.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:33 by tex-make-sample-summary.sh
% Token and word counts for viet/nwt/mrk.1/gud.wfr
%
\def\vietnwttruncmrkPBgudTks{15895}
\def\vietnwttruncmrkPBgudTksPct{97.4}
\def\vietnwttruncmrkPBgudWds{1572}
\def\vietnwttruncmrkPBgudWdsPct{9.6}
copied '/tmp/586068.file' -> 'exp/viet/nwt/mrk.1/gud-trunc-wds-summary.tex'
removed '/tmp/586068.file'
creating running text file dat/viet/nwt/mrk.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/viet/nwt/mrk.1/bad.wfr'
creating the word frequency file dat/viet/nwt/mrk.1/bad.wfr
the 10 most common words in dat/viet/nwt/mrk.1/bad.tlw:
429 0.99536 =
1 0.00232 *{e^lo^i}
1 0.00232 ..*{sabakthani}
removed 'dat/viet/nwt/mrk.1/bad-trunc-wds-summary.tex'
removed 'exp/viet/nwt/mrk.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/viet/nwt/mrk.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:33 by tex-make-sample-summary.sh
% Token and word counts for viet/nwt/mrk.1/bad.wfr
%
\def\vietnwttruncmrkPBbadTks{431}
\def\vietnwttruncmrkPBbadTksPct{2.6}
\def\vietnwttruncmrkPBbadWds{3}
\def\vietnwttruncmrkPBbadWdsPct{0.0}
copied '/tmp/586112.file' -> 'exp/viet/nwt/mrk.1/bad-trunc-wds-summary.tex'
removed '/tmp/586112.file'
... creating word files dat/viet/nwt/luk.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
28276 dat/viet/nwt/luk.1/trunc.tlw
removed 'dat/viet/nwt/luk.1/raw.tlw'
removed 'dat/viet/nwt/luk.1/gud.tlw'
removed 'dat/viet/nwt/luk.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/viet/nwt/luk.1/raw.wdf
sample:
bo+?i chu+ng dda~ co' nhie^`u ngu+o+`i tra tay die^~n la.i tri`nh tu+.
ca'c bie^'n co^' dda~ thu+.c hie^.n giu+~a chu'ng to^i theo nhu+ ca'c
ke? tu+` dda^`u dda~ chu+'ng kie^'n va` phu.c vu. cho lo+`i dda~
truye^`n la.i cho chu'ng to^i thi` to^i thie^'t nghi~ la` sau khi dda~
quan sa't mo.i su+. tu+` la^u mo^.t ca'ch tu+o+`ng ta^.n cu~ng ne^n
thu+a nga`i the^ o^ phi lo^ cu+' tua^`n tu+. ma` vie^'t la.i cho nga`i
ngo~ ha^`u nga`i ddu+o+.c am tu+o+`ng ra(`ng gia'o hua^'n nga`i dda~
thu. li~nh thu+.c la` chi'nh xa'c =
so^' la` va`o nhu+~ng nga`y tho+`i he^ ro^ dde^ vua xu+' giu dde^ co'
vi. tu+ te^' te^n la` xa ca rya thuo^.c phie^n thu+' a bia va` vo+. o^ng
thuo^.c ha`ng nu+~ tu+? a ra ho^n va` te^n ba` la` e^ li sa be't =
ca? hai dde^`u la` co^ng chi'nh tru+o+'c ma(.t thie^n chu'a ddi ddu+'ng
ra^.p theo mo.i ddie^`u ra(n gio+'i lua^.t cu?a chu'a vo^ phu+o+ng
tra'ch cu+' =
nhu+ng o^ng ba` la.i kho^ng con vi` e^ li sa be't la` ngu+o+`i son se?
hie^'m hoi va? cha(ng hai o^ng ba` la.i dda~ cao nie^n ca? ro^`i =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
va` ha(`ng o+? trong dde^`n tho+` ma` chu'c tu.ng thie^n chu'a =
removed 'dat/viet/nwt/luk.1/raw.wfr'
creating the word frequency file dat/viet/nwt/luk.1/raw.wfr
the 10 most common words in dat/viet/nwt/luk.1/raw.tlw:
697 0.02465 va`
639 0.02260 =
628 0.02221 nga`i
565 0.01998 ngu+o+`i
520 0.01839 ca'c
440 0.01556 ngu+o+i
435 0.01538 dda~
365 0.01291 ho.
359 0.01270 cho
347 0.01227 no'i
removed 'dat/viet/nwt/luk.1/raw-trunc-wds-summary.tex'
removed 'exp/viet/nwt/luk.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/viet/nwt/luk.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:33 by tex-make-sample-summary.sh
% Token and word counts for viet/nwt/luk.1/raw.wfr
%
\def\vietnwttrunclukPBrawTks{28276}
\def\vietnwttrunclukPBrawTksPct{100.0}
\def\vietnwttrunclukPBrawWds{2118}
\def\vietnwttrunclukPBrawWdsPct{7.5}
copied '/tmp/586166.file' -> 'exp/viet/nwt/luk.1/raw-trunc-wds-summary.tex'
removed '/tmp/586166.file'
creating running text file dat/viet/nwt/luk.1/gud.wdf
sample:
bo+?i chu+ng dda~ co' nhie^`u ngu+o+`i tra tay die^~n la.i tri`nh tu+.
ca'c bie^'n co^' dda~ thu+.c hie^.n giu+~a chu'ng to^i theo nhu+ ca'c
ke? tu+` dda^`u dda~ chu+'ng kie^'n va` phu.c vu. cho lo+`i dda~
truye^`n la.i cho chu'ng to^i thi` to^i thie^'t nghi~ la` sau khi dda~
quan sa't mo.i su+. tu+` la^u mo^.t ca'ch tu+o+`ng ta^.n cu~ng ne^n
thu+a nga`i the^ o^ phi lo^ cu+' tua^`n tu+. ma` vie^'t la.i cho nga`i
ngo~ ha^`u nga`i ddu+o+.c am tu+o+`ng ra(`ng gia'o hua^'n nga`i dda~
thu. li~nh thu+.c la` chi'nh xa'c so^' la` va`o nhu+~ng nga`y tho+`i he^
ro^ dde^ vua xu+' giu dde^ co' vi. tu+ te^' te^n la` xa ca rya thuo^.c
phie^n thu+' a bia va` vo+. o^ng thuo^.c ha`ng nu+~ tu+? a ra ho^n va`
te^n ba` la` e^ li sa be't ca? hai dde^`u la` co^ng chi'nh tru+o+'c
ma(.t thie^n chu'a ddi ddu+'ng ra^.p theo mo.i ddie^`u ra(n gio+'i
lua^.t cu?a chu'a vo^ phu+o+ng tra'ch cu+' nhu+ng o^ng ba` la.i kho^ng
con vi` e^ li sa be't la` ngu+o+`i son se? hie^'m hoi va? cha(ng hai
o^ng ba` la.i dda~ cao nie^n ca? ro^`i va^.y xa?y ra la` mo^.t la^`n kia
theo lu+o+.t cu?a phie^n thu+' o^ng o^ng du+o+.c cha^'p le^~ tru+o+'c
ma(.t thie^n chu'a chie^'u theo tu.c le^. ha`ng tu+ te^' o^ng dda~ ba('t
tha(m va` tru'ng vie^.c thu+o+.ng hu+o+ng ddu+o+.c va`o tha'nh ddie^.n
cu?a chu'a va` ddoa`n the^? cu?a da^n ta^'t ca? nguye^.n kinh be^n
ngoa`i trong gio+` thu+o+.ng hu+o+ng thie^n tha^`n chu'a dda~ hie^.n ra
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
bie^.t ho. va` ddu+o+.c nha('c le^n tro+`i va` tho+` la.y nga`i ro^`i
ho. dda~ tro+? la.i gie^ ru sa lem vui mu+`ng kho^n xie^'t va` ha(`ng
o+? trong dde^`n tho+` ma` chu'c tu.ng thie^n chu'a
removed 'dat/viet/nwt/luk.1/gud.wfr'
creating the word frequency file dat/viet/nwt/luk.1/gud.wfr
the 10 most common words in dat/viet/nwt/luk.1/gud.tlw:
697 0.02522 va`
628 0.02272 nga`i
565 0.02044 ngu+o+`i
520 0.01882 ca'c
440 0.01592 ngu+o+i
435 0.01574 dda~
365 0.01321 ho.
359 0.01299 cho
347 0.01256 no'i
339 0.01227 ta
removed 'dat/viet/nwt/luk.1/gud-trunc-wds-summary.tex'
removed 'exp/viet/nwt/luk.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/viet/nwt/luk.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:33 by tex-make-sample-summary.sh
% Token and word counts for viet/nwt/luk.1/gud.wfr
%
\def\vietnwttrunclukPBgudTks{27637}
\def\vietnwttrunclukPBgudTksPct{97.7}
\def\vietnwttrunclukPBgudWds{2117}
\def\vietnwttrunclukPBgudWdsPct{7.5}
copied '/tmp/586210.file' -> 'exp/viet/nwt/luk.1/gud-trunc-wds-summary.tex'
removed '/tmp/586210.file'
creating running text file dat/viet/nwt/luk.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/viet/nwt/luk.1/bad.wfr'
creating the word frequency file dat/viet/nwt/luk.1/bad.wfr
the 10 most common words in dat/viet/nwt/luk.1/bad.tlw:
639 1.00000 =
removed 'dat/viet/nwt/luk.1/bad-trunc-wds-summary.tex'
removed 'exp/viet/nwt/luk.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/viet/nwt/luk.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:33 by tex-make-sample-summary.sh
% Token and word counts for viet/nwt/luk.1/bad.wfr
%
\def\vietnwttrunclukPBbadTks{639}
\def\vietnwttrunclukPBbadTksPct{2.3}
\def\vietnwttrunclukPBbadWds{1}
\def\vietnwttrunclukPBbadWdsPct{0.0}
copied '/tmp/586254.file' -> 'exp/viet/nwt/luk.1/bad-trunc-wds-summary.tex'
removed '/tmp/586254.file'
... creating word files dat/viet/nwt/jhn.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
22428 dat/viet/nwt/jhn.1/trunc.tlw
removed 'dat/viet/nwt/jhn.1/raw.tlw'
removed 'dat/viet/nwt/jhn.1/gud.tlw'
removed 'dat/viet/nwt/jhn.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/viet/nwt/jhn.1/raw.wdf
sample:
lu'c kho+?i nguye^n dda~ co' lo+`i va` lo+`i o+? no+i thie^n chu'a va`
lo+`i la` mo^.t vi. thie^n chu'a nga`i dda~ co' lu'c kho+?i nguye^n
vo+'i thie^n chu'a =
mo.i su+. dda~ nho+` nga`i ma` tha`nh su+. va` kho^ng nga`i thi` kho^ng
gi` dda~ tha`nh su+. ddie^`u dda~ tha`nh su+. no+i nga`i la` su+. so^'ng
va` su+. so^'ng la` su+. sa'ng cho nha^n loa.i =
va` su+. sa'ng ra.ng trong to^'i ta(m va` to^'i ta(m dda~ kho^ng trie^.t
ddu+o+.c su+. sa'ng =
xa?y ra la` co' ngu+o+`i ddu+o+.c sai dde^'n tu+` no+i thie^n chu'a te^n
o^ng la` gio^ an =
o^ng dda~ dde^'n dde^? la`m chu+'ng dde^? chu'ng thu+.c ve^` su+. sa'ng
ngo~ ha^`u mo.i ngu+o+`i nho+` o^ng ma` tin =
o^ng kho^ng pha?i la` su+. sa'ng nhu+ng la` dde^? la`m chu+'ng cho su+.
sa'ng =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
tu+`ng ddie^`u thi` thie^'t tu+o+?ng the^' gian kho^ng ddu? cho^~ ma`
chu+'a sa'ch vie^'t ra =
removed 'dat/viet/nwt/jhn.1/raw.wfr'
creating the word frequency file dat/viet/nwt/jhn.1/raw.wfr
the 10 most common words in dat/viet/nwt/jhn.1/raw.tlw:
669 0.02983 ta
556 0.02479 =
549 0.02448 dda~
516 0.02301 nga`i
507 0.02261 ca'c
444 0.01980 va`
436 0.01944 ngu+o+i
379 0.01690 no'i
378 0.01685 kho^ng
369 0.01645 ngu+o+`i
removed 'dat/viet/nwt/jhn.1/raw-trunc-wds-summary.tex'
removed 'exp/viet/nwt/jhn.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/viet/nwt/jhn.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:33 by tex-make-sample-summary.sh
% Token and word counts for viet/nwt/jhn.1/raw.wfr
%
\def\vietnwttruncjhnPBrawTks{22428}
\def\vietnwttruncjhnPBrawTksPct{100.0}
\def\vietnwttruncjhnPBrawWds{1290}
\def\vietnwttruncjhnPBrawWdsPct{5.8}
copied '/tmp/586308.file' -> 'exp/viet/nwt/jhn.1/raw-trunc-wds-summary.tex'
removed '/tmp/586308.file'
creating running text file dat/viet/nwt/jhn.1/gud.wdf
sample:
lu'c kho+?i nguye^n dda~ co' lo+`i va` lo+`i o+? no+i thie^n chu'a va`
lo+`i la` mo^.t vi. thie^n chu'a nga`i dda~ co' lu'c kho+?i nguye^n
vo+'i thie^n chu'a mo.i su+. dda~ nho+` nga`i ma` tha`nh su+. va` kho^ng
nga`i thi` kho^ng gi` dda~ tha`nh su+. ddie^`u dda~ tha`nh su+. no+i
nga`i la` su+. so^'ng va` su+. so^'ng la` su+. sa'ng cho nha^n loa.i va`
su+. sa'ng ra.ng trong to^'i ta(m va` to^'i ta(m dda~ kho^ng trie^.t
ddu+o+.c su+. sa'ng xa?y ra la` co' ngu+o+`i ddu+o+.c sai dde^'n tu+`
no+i thie^n chu'a te^n o^ng la` gio^ an o^ng dda~ dde^'n dde^? la`m
chu+'ng dde^? chu'ng thu+.c ve^` su+. sa'ng ngo~ ha^`u mo.i ngu+o+`i
nho+` o^ng ma` tin o^ng kho^ng pha?i la` su+. sa'ng nhu+ng la` dde^?
la`m chu+'ng cho su+. sa'ng nga`i la` su+. sa'ng ddi'ch tha^.t sa'ng soi
mo.i ngu+o+`i nga`i dde^'n trong the^' gian nga`i co' trong the^' gian
va` the^' gian dda~ nho+` nga`i ma` ddu+o+.c co' ma` the^' gian dda~
kho^ng bie^'t nga`i nga`i dda~ dde^'n no+i nha` cu?a nga`i ma` ngu+o+`i
nha` dda~ kho^ng tie^'p nha^.n nga`i co`n nhu+~ng ai ddo'n nha^.n nga`i
thi` nga`i ban cho ho. quye^`n la`m con thie^n chu'a a^'y la` cho
nhu+~ng ke? tin va`o danh nga`i ho. kho^ng do ma'u huye^'t ma` sinh ra
cu~ng kho^ng pha?i do y' xa'c thi.t cu~ng pha?i do y' cu?a nam nha^n
nhu+ng chi'nh do bo+?i thie^n chu'a ma` ddu+o+.c sinh ra va` lo+`i dda~
tha`nh xa'c pha`m va` dda~ lu+u tru' no+i chu'ng to^i va` chu'ng to^i
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
ra(`ng chu+'ng cu?a o^ng la` chu+'ng xa'c thu+.c co`n la('m ddie^`u
kha'c ddu+'c gie^ su dda~ la`m ne^'u vie^'t la.i tu+`ng ddie^`u thi`
thie^'t tu+o+?ng the^' gian kho^ng ddu? cho^~ ma` chu+'a sa'ch vie^'t ra
removed 'dat/viet/nwt/jhn.1/gud.wfr'
creating the word frequency file dat/viet/nwt/jhn.1/gud.wfr
the 10 most common words in dat/viet/nwt/jhn.1/gud.tlw:
669 0.03059 ta
549 0.02510 dda~
516 0.02359 nga`i
507 0.02318 ca'c
444 0.02030 va`
436 0.01993 ngu+o+i
379 0.01733 no'i
378 0.01728 kho^ng
369 0.01687 ngu+o+`i
348 0.01591 la`
removed 'dat/viet/nwt/jhn.1/gud-trunc-wds-summary.tex'
removed 'exp/viet/nwt/jhn.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/viet/nwt/jhn.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:33 by tex-make-sample-summary.sh
% Token and word counts for viet/nwt/jhn.1/gud.wfr
%
\def\vietnwttruncjhnPBgudTks{21872}
\def\vietnwttruncjhnPBgudTksPct{97.5}
\def\vietnwttruncjhnPBgudWds{1289}
\def\vietnwttruncjhnPBgudWdsPct{5.7}
copied '/tmp/586352.file' -> 'exp/viet/nwt/jhn.1/gud-trunc-wds-summary.tex'
removed '/tmp/586352.file'
creating running text file dat/viet/nwt/jhn.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/viet/nwt/jhn.1/bad.wfr'
creating the word frequency file dat/viet/nwt/jhn.1/bad.wfr
the 10 most common words in dat/viet/nwt/jhn.1/bad.tlw:
556 1.00000 =
removed 'dat/viet/nwt/jhn.1/bad-trunc-wds-summary.tex'
removed 'exp/viet/nwt/jhn.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/viet/nwt/jhn.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:33 by tex-make-sample-summary.sh
% Token and word counts for viet/nwt/jhn.1/bad.wfr
%
\def\vietnwttruncjhnPBbadTks{556}
\def\vietnwttruncjhnPBbadTksPct{2.5}
\def\vietnwttruncjhnPBbadWds{1}
\def\vietnwttruncjhnPBbadWdsPct{0.0}
copied '/tmp/586396.file' -> 'exp/viet/nwt/jhn.1/bad-trunc-wds-summary.tex'
removed '/tmp/586396.file'
... creating word files dat/viet/nwt/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
36005 dat/viet/nwt/tot.1/trunc.tlw
removed 'dat/viet/nwt/tot.1/raw.tlw'
removed 'dat/viet/nwt/tot.1/gud.tlw'
removed 'dat/viet/nwt/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/viet/nwt/tot.1/raw.wdf
sample:
gia pha? ddu+'c chu'a gie^ su ki to^ con dda vi't con a'p ra ham a'p ra
ham sinh y sa'c y sa'c sinh gia co^'p gia co^'p sinh giu dda va` ca'c
anh em o^ng giu dda sinh pha re^ va`o xa ra bo+?i tha ma pha re^ sinh e^
se ro^m e^ se ro^m sinh a ram a ram sinh a mi na dda'p a mi na dda'p
sinh na a so^n na a so^n sinh sa mo^n sa mo^n sinh bo't se^ bo+?i ra
ha'p bo't se^ sinh gio^ be^t bo+?i ba` ru't gio^ be^'t sinh y sai y sai
sinh vua dda vi't dda vi't sinh sa lo^ mo^n bo+?i vo+. cu?a u ria sa lo^
mo^n sinh ro bo am ro bo am sinh a bia a bia sinh a sa a sa sinh gio^ sa
phat gio^ sa phat sinh gio^ ram gio^ ram sinh o^ xya o^ xya sinh gio^ a
tham gio^ a tham sinh a ka a ka sinh e^t se^ kya e^t se^ kya sinh ma na
se^ ma na se^ sinh am mo^n am mo^n sinh gio^ sya gio^ sya sinh gie^ kho^
nya va` ca'c anh em o^ng tho+`i lu+u dda`y ba be^n sau tho+`i lu+u dda`y
ba be^n gie^ kho^ nya sinh sa la thi e^n sa la thi e^n sinh xo ro ba
be^n xo ro ba be^n sinh a bi hu a bi hu sinh e^ lya kim e^ lya kim sinh
a't so^ a't so^ sinh sa ddo'c sa ddo'c sinh a khim a khim sinh e^ li hu
e^ li hu sinh e^ li a sa e^ li a sa sinh ma't than ma't than sinh gia
co^'p gia co^'p sinh gio^ se'p cho^`ng cu?a ma ria bo+?i ba` thi` ddu+'c
gie^ su go.i la` ki to^ dda~ sinh ra =
to^?ng co^.ng ca'c ddo+`i la.i thi` tu+` a'p ra ham dde^'n dda vi't co'
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
nga`i la.i no'i vo+'i ho. ta ra ddi va` ca'c ngu+o+i se~ ti`m kie^'m ta
va` ca'c ngu+o+i se~ che^'t trong to^.i cu?a ca'c ngu+o+i ta ddi dda^u
ca'c ngu+o+i kho^ng the^? dde^'n ddu+o+.c ngu+o+`i
removed 'dat/viet/nwt/tot.1/raw.wfr'
creating the word frequency file dat/viet/nwt/tot.1/raw.wfr
the 10 most common words in dat/viet/nwt/tot.1/raw.tlw:
978 0.02716 =
965 0.02680 va`
956 0.02655 nga`i
669 0.01858 ngu+o+`i
601 0.01669 dda~
551 0.01530 ca'c
530 0.01472 ta
460 0.01278 ngu+o+i
436 0.01211 kho^ng
434 0.01205 ho.
removed 'dat/viet/nwt/tot.1/raw-trunc-wds-summary.tex'
removed 'exp/viet/nwt/tot.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/viet/nwt/tot.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:33 by tex-make-sample-summary.sh
% Token and word counts for viet/nwt/tot.1/raw.wfr
%
\def\vietnwttrunctotPBrawTks{36005}
\def\vietnwttrunctotPBrawTksPct{100.0}
\def\vietnwttrunctotPBrawWds{2012}
\def\vietnwttrunctotPBrawWdsPct{5.6}
copied '/tmp/586450.file' -> 'exp/viet/nwt/tot.1/raw-trunc-wds-summary.tex'
removed '/tmp/586450.file'
creating running text file dat/viet/nwt/tot.1/gud.wdf
sample:
gia pha? ddu+'c chu'a gie^ su ki to^ con dda vi't con a'p ra ham a'p ra
ham sinh y sa'c y sa'c sinh gia co^'p gia co^'p sinh giu dda va` ca'c
anh em o^ng giu dda sinh pha re^ va`o xa ra bo+?i tha ma pha re^ sinh e^
se ro^m e^ se ro^m sinh a ram a ram sinh a mi na dda'p a mi na dda'p
sinh na a so^n na a so^n sinh sa mo^n sa mo^n sinh bo't se^ bo+?i ra
ha'p bo't se^ sinh gio^ be^t bo+?i ba` ru't gio^ be^'t sinh y sai y sai
sinh vua dda vi't dda vi't sinh sa lo^ mo^n bo+?i vo+. cu?a u ria sa lo^
mo^n sinh ro bo am ro bo am sinh a bia a bia sinh a sa a sa sinh gio^ sa
phat gio^ sa phat sinh gio^ ram gio^ ram sinh o^ xya o^ xya sinh gio^ a
tham gio^ a tham sinh a ka a ka sinh e^t se^ kya e^t se^ kya sinh ma na
se^ ma na se^ sinh am mo^n am mo^n sinh gio^ sya gio^ sya sinh gie^ kho^
nya va` ca'c anh em o^ng tho+`i lu+u dda`y ba be^n sau tho+`i lu+u dda`y
ba be^n gie^ kho^ nya sinh sa la thi e^n sa la thi e^n sinh xo ro ba
be^n xo ro ba be^n sinh a bi hu a bi hu sinh e^ lya kim e^ lya kim sinh
a't so^ a't so^ sinh sa ddo'c sa ddo'c sinh a khim a khim sinh e^ li hu
e^ li hu sinh e^ li a sa e^ li a sa sinh ma't than ma't than sinh gia
co^'p gia co^'p sinh gio^ se'p cho^`ng cu?a ma ria bo+?i ba` thi` ddu+'c
gie^ su go.i la` ki to^ dda~ sinh ra to^?ng co^.ng ca'c ddo+`i la.i thi`
tu+` a'p ra ham dde^'n dda vi't co' mu+o+`i bo^'n ddo+`i tu+` dda vi't
dde^'n tho+`i lu+u dda`y ba be^n co' mu+o+`i bo^'n ddo+`i tu+` tho+`i
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
nga`i la.i no'i vo+'i ho. ta ra ddi va` ca'c ngu+o+i se~ ti`m kie^'m ta
va` ca'c ngu+o+i se~ che^'t trong to^.i cu?a ca'c ngu+o+i ta ddi dda^u
ca'c ngu+o+i kho^ng the^? dde^'n ddu+o+.c ngu+o+`i
removed 'dat/viet/nwt/tot.1/gud.wfr'
creating the word frequency file dat/viet/nwt/tot.1/gud.wfr
the 10 most common words in dat/viet/nwt/tot.1/gud.tlw:
965 0.02755 va`
956 0.02729 nga`i
669 0.01910 ngu+o+`i
601 0.01716 dda~
551 0.01573 ca'c
530 0.01513 ta
460 0.01313 ngu+o+i
436 0.01245 kho^ng
434 0.01239 ho.
427 0.01219 la`
removed 'dat/viet/nwt/tot.1/gud-trunc-wds-summary.tex'
removed 'exp/viet/nwt/tot.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/viet/nwt/tot.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:33 by tex-make-sample-summary.sh
% Token and word counts for viet/nwt/tot.1/gud.wfr
%
\def\vietnwttrunctotPBgudTks{35027}
\def\vietnwttrunctotPBgudTksPct{97.3}
\def\vietnwttrunctotPBgudWds{2011}
\def\vietnwttrunctotPBgudWdsPct{5.6}
copied '/tmp/586494.file' -> 'exp/viet/nwt/tot.1/gud-trunc-wds-summary.tex'
removed '/tmp/586494.file'
creating running text file dat/viet/nwt/tot.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/viet/nwt/tot.1/bad.wfr'
creating the word frequency file dat/viet/nwt/tot.1/bad.wfr
the 10 most common words in dat/viet/nwt/tot.1/bad.tlw:
978 1.00000 =
removed 'dat/viet/nwt/tot.1/bad-trunc-wds-summary.tex'
removed 'exp/viet/nwt/tot.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/viet/nwt/tot.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:33 by tex-make-sample-summary.sh
% Token and word counts for viet/nwt/tot.1/bad.wfr
%
\def\vietnwttrunctotPBbadTks{978}
\def\vietnwttrunctotPBbadTksPct{2.7}
\def\vietnwttrunctotPBbadWds{1}
\def\vietnwttrunctotPBbadWdsPct{0.0}
copied '/tmp/586538.file' -> 'exp/viet/nwt/tot.1/bad-trunc-wds-summary.tex'
removed '/tmp/586538.file'
lines words bytes file
------- ------- --------- ------------
1821 5463 39528 dat/viet/nwt/mat.1/raw.wfr
1575 4725 34205 dat/viet/nwt/mrk.1/raw.wfr
2118 6354 45987 dat/viet/nwt/luk.1/raw.wfr
1290 3870 28044 dat/viet/nwt/jhn.1/raw.wfr
2012 6036 43658 dat/viet/nwt/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
1818 5454 39456 dat/viet/nwt/mat.1/gud.wfr
1572 4716 34129 dat/viet/nwt/mrk.1/gud.wfr
2117 6351 45969 dat/viet/nwt/luk.1/gud.wfr
1289 3867 28026 dat/viet/nwt/jhn.1/gud.wfr
2011 6033 43640 dat/viet/nwt/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
3 9 72 dat/viet/nwt/mat.1/bad.wfr
3 9 76 dat/viet/nwt/mrk.1/bad.wfr
1 3 18 dat/viet/nwt/luk.1/bad.wfr
1 3 18 dat/viet/nwt/jhn.1/bad.wfr
1 3 18 dat/viet/nwt/tot.1/bad.wfr
mat.1 raw = 26411 gud = 25615 bad = 796
mrk.1 raw = 16326 gud = 15895 bad = 431
luk.1 raw = 28276 gud = 27637 bad = 639
jhn.1 raw = 22428 gud = 21872 bad = 556
tot.1 raw = 36005 gud = 35027 bad = 978
=== creating the derived word files dat/chin/ptt/*/{raw,gud,bad}.{tlw,wdf,wfr} (trunc) ===
... creating word files dat/chin/ptt/gen.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
36068 dat/chin/ptt/gen.1/trunc.tlw
removed 'dat/chin/ptt/gen.1/raw.tlw'
removed 'dat/chin/ptt/gen.1/gud.tlw'
removed 'dat/chin/ptt/gen.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/chin/ptt/gen.1/raw.wdf
sample:
qi3 chu1.1 shen2.1 chuang4 zao4 tian1 di4 =
di4 shi4 kong1 xu1.1 hun4 dun4.5 yuan1.2 mian4 hei1 an4 shen2.1 de5
ling2.1 yun4.1 xing2 zai4 shui3 mian4 shang4 =
shen2.1 shuo1 yao4 you3 guang1 jiu4 you3 le5 guang1 =
shen2.1 kan4 guang1 shi4 hao3 de5 jiu4 ba3 guang1 an4 fen1 kai1 le5 =
shen2.1 cheng1 guang1 wei2 zhou4.1 cheng1 an4 wei2 ye4 you3 wan3 shang4
you3 zao3 chen2.5 zhei4 shi4 tou2 yi1 ri4 =
shen2.1 shuo1 zhu1.1 shui3 zhi1.1 jian1 yao4 you3 kong1 qi4 jiang1 shui3
fen1 wei2 shang4 xia4 =
shen2.1 jiu4 zao4 chu1 kong1 qi4 jiang1 kong1 qi4 yi3.1 xia4 de5 shui3
kong1 qi4 yi3.1 shang4 de5 shui3 fen1 kai1 le5 shi4.1 jiu4 zhei4 yang4
cheng2 le5 =
shen2.1 cheng1 kong1 qi4 wei2 tian1 you3 wan3 shang4 you3 zao3 chen2.5
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
zhei4 jiu4 shi4 wo3 dui4 fa3 lao3 suo3 shuo1 shen2.1 yi3 jiang1 suo3
yao4 zuo4.2 de5
removed 'dat/chin/ptt/gen.1/raw.wfr'
creating the word frequency file dat/chin/ptt/gen.1/raw.wfr
the 10 most common words in dat/chin/ptt/gen.1/raw.tlw:
1571 0.04356 de5
1041 0.02886 =
881 0.02443 wo3
833 0.02310 ta1
730 0.02024 ni3
590 0.01636 le5
529 0.01467 zai4
526 0.01458 zi5
488 0.01353 shuo1
485 0.01345 ren2
removed 'dat/chin/ptt/gen.1/raw-trunc-wds-summary.tex'
removed 'exp/chin/ptt/gen.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/chin/ptt/gen.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:34 by tex-make-sample-summary.sh
% Token and word counts for chin/ptt/gen.1/raw.wfr
%
\def\chinptttruncgenPBrawTks{36068}
\def\chinptttruncgenPBrawTksPct{100.0}
\def\chinptttruncgenPBrawWds{1377}
\def\chinptttruncgenPBrawWdsPct{3.8}
copied '/tmp/586693.file' -> 'exp/chin/ptt/gen.1/raw-trunc-wds-summary.tex'
removed '/tmp/586693.file'
creating running text file dat/chin/ptt/gen.1/gud.wdf
sample:
qi3 chu1.1 shen2.1 chuang4 zao4 tian1 di4 di4 shi4 kong1 xu1.1 hun4
dun4.5 yuan1.2 mian4 hei1 an4 shen2.1 de5 ling2.1 yun4.1 xing2 zai4
shui3 mian4 shang4 shen2.1 shuo1 yao4 you3 guang1 jiu4 you3 le5 guang1
shen2.1 kan4 guang1 shi4 hao3 de5 jiu4 ba3 guang1 an4 fen1 kai1 le5
shen2.1 cheng1 guang1 wei2 zhou4.1 cheng1 an4 wei2 ye4 you3 wan3 shang4
you3 zao3 chen2.5 zhei4 shi4 tou2 yi1 ri4 shen2.1 shuo1 zhu1.1 shui3
zhi1.1 jian1 yao4 you3 kong1 qi4 jiang1 shui3 fen1 wei2 shang4 xia4
shen2.1 jiu4 zao4 chu1 kong1 qi4 jiang1 kong1 qi4 yi3.1 xia4 de5 shui3
kong1 qi4 yi3.1 shang4 de5 shui3 fen1 kai1 le5 shi4.1 jiu4 zhei4 yang4
cheng2 le5 shen2.1 cheng1 kong1 qi4 wei2 tian1 you3 wan3 shang4 you3
zao3 chen2.5 shi4 di4.2 er4 ri4 shen2.1 shuo1 tian1 xia4 de5 shui3 yao4
ju4.3 zai4 yi1 chu3 shi3 han4.4 di4 lu4.1 chu1 lai2 shi4.1 jiu4 zhei4
yang4 cheng2 le5 shen2.1 cheng1 han4.4 di4 wei2 di4 cheng1 shui3 de5
ju4.3 chu3 wei2 hai3 shen2.1 kan4 zhe5 shi4 hao3 de5 shen2.1 shuo1 di4
yao4 fa1 sheng1 qing1.2 cao3 he2 jie2 zhong3 zi5 de5 cai4 shu1.6 bing4.1
jie2 guo3 zi5 de5 shu4.2 mu4.1 ge4.1 cong2 qi2 lei4.1 guo3 zi5 dou1 bao1
zhe5 he2.6 shi4.1 jiu4 zhei4 yang4 cheng2 le5 yu2 shi4 di4 fa1 sheng1
le5 qing1.2 cao3 he2 jie2 zhong3 zi5 de5 cai4 shu1.6 ge4.1 cong2 qi2
lei4.1 bing4.1 jie2 guo3 zi5 de5 shu4.2 mu4.1 ge4.1 cong2 qi2 lei4.1
guo3 zi5 dou1 bao1 zhe5 he2.6 shen2.1 kan4 zhe5 shi4 hao3 de5 you3 wan3
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
jiao1.2 de5 sui4.4 zi5 ye3 shi4 qi1 nian2 dou1 shi4 qi1 ge4 huang1.1
nian2 zhei4 jiu4 shi4 wo3 dui4 fa3 lao3 suo3 shuo1 shen2.1 yi3 jiang1
suo3 yao4 zuo4.2 de5
removed 'dat/chin/ptt/gen.1/gud.wfr'
creating the word frequency file dat/chin/ptt/gen.1/gud.wfr
the 10 most common words in dat/chin/ptt/gen.1/gud.tlw:
1571 0.04485 de5
881 0.02515 wo3
833 0.02378 ta1
730 0.02084 ni3
590 0.01684 le5
529 0.01510 zai4
526 0.01502 zi5
488 0.01393 shuo1
485 0.01385 ren2
475 0.01356 shi4
removed 'dat/chin/ptt/gen.1/gud-trunc-wds-summary.tex'
removed 'exp/chin/ptt/gen.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/chin/ptt/gen.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:34 by tex-make-sample-summary.sh
% Token and word counts for chin/ptt/gen.1/gud.wfr
%
\def\chinptttruncgenPBgudTks{35027}
\def\chinptttruncgenPBgudTksPct{97.1}
\def\chinptttruncgenPBgudWds{1376}
\def\chinptttruncgenPBgudWdsPct{3.8}
copied '/tmp/586737.file' -> 'exp/chin/ptt/gen.1/gud-trunc-wds-summary.tex'
removed '/tmp/586737.file'
creating running text file dat/chin/ptt/gen.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/chin/ptt/gen.1/bad.wfr'
creating the word frequency file dat/chin/ptt/gen.1/bad.wfr
the 10 most common words in dat/chin/ptt/gen.1/bad.tlw:
1041 1.00000 =
removed 'dat/chin/ptt/gen.1/bad-trunc-wds-summary.tex'
removed 'exp/chin/ptt/gen.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/chin/ptt/gen.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:34 by tex-make-sample-summary.sh
% Token and word counts for chin/ptt/gen.1/bad.wfr
%
\def\chinptttruncgenPBbadTks{1041}
\def\chinptttruncgenPBbadTksPct{2.9}
\def\chinptttruncgenPBbadWds{1}
\def\chinptttruncgenPBbadWdsPct{0.0}
copied '/tmp/586781.file' -> 'exp/chin/ptt/gen.1/bad-trunc-wds-summary.tex'
removed '/tmp/586781.file'
... creating word files dat/chin/ptt/exo.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
36028 dat/chin/ptt/exo.1/trunc.tlw
removed 'dat/chin/ptt/exo.1/raw.tlw'
removed 'dat/chin/ptt/exo.1/gud.tlw'
removed 'dat/chin/ptt/exo.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/chin/ptt/exo.1/raw.wdf
sample:
yi3.1 se4 lie4 de5 zhong4 zi5 ge4.1 dai4.1 jia1 juan4.1 he2 ya3 ge4.1
yi1 tong2 lai2 dao4.1 ai1.3 ji2.1 ta1 men5 de5 ming2.1 zi4.1 ji4.1 zai4
xia4 mian4 =
you3 liu2.2 bian4 xi1 mian3.5 li4.1 wei4 you2.2 da4 yi3.1 sa4 jia1.11
xi1 bu4.3 lun2.1 bian4 ya3 min3.3 dan4 na2 fu2.14 ta1 li4.1 jia1.11 de2
ya4.1 she4.2 =
fan2 cong2 ya3 ge4.1 er2.1 sheng1 de5 gong4 you3 qi1 shi2.1 ren2 yue1
se4.2 yi3 jing1 zai4 ai1.3 ji2.1 =
yue1 se4.2 he2 ta1 de5 di4.1 xiong1 bing4.1 nei4 yi1 dai4.3 de5 ren2
dou1 si3 le5 =
yi3.1 se4 lie4 ren2 sheng1 yang3 zhong4 duo1 bing4.1 qie3 fan2.2 mao4.3
ji2.3 qi2 qiang2 sheng4.2 man3 le5 nei4 di4 =
you3 bu4 ren4 shi5 yue1 se4.2 de5 xin1.1 wang2 qi3 lai2 zhi4.2 li3.1
ai1.3 ji2.1 dui4 ta1 de5 bai3 xing4.2 shuo1 kan4 na3 zhei4 yi3.1 se4
lie4 min2 bi3 wo3 men5 hai2 duo1 you4 bi3 wo3 men5 qiang2 sheng4.2 =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
zai4 hui4 mu4.4 de5 zhang4.1 mu4.4 men2 qian2 an1 she4.2 fan2.6 ji4.4
tan2.2 ba3 fan2.6 ji4.4 he2 su4.1 ji4.4 xian4.4 zai4 qi2 shang4 shi4
zhao4 ye1 he2 hua2 suo3 fen1.1 fu4.2
removed 'dat/chin/ptt/exo.1/raw.wfr'
creating the word frequency file dat/chin/ptt/exo.1/raw.wfr
the 10 most common words in dat/chin/ptt/exo.1/raw.tlw:
1791 0.04971 de5
1001 0.02778 =
737 0.02046 he2
726 0.02015 ni3
644 0.01787 ta1
611 0.01696 men5
596 0.01654 yao4
525 0.01457 zai4
504 0.01399 wo3
481 0.01335 zi5
removed 'dat/chin/ptt/exo.1/raw-trunc-wds-summary.tex'
removed 'exp/chin/ptt/exo.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/chin/ptt/exo.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:34 by tex-make-sample-summary.sh
% Token and word counts for chin/ptt/exo.1/raw.wfr
%
\def\chinptttruncexoPBrawTks{36028}
\def\chinptttruncexoPBrawTksPct{100.0}
\def\chinptttruncexoPBrawWds{1425}
\def\chinptttruncexoPBrawWdsPct{4.0}
copied '/tmp/586835.file' -> 'exp/chin/ptt/exo.1/raw-trunc-wds-summary.tex'
removed '/tmp/586835.file'
creating running text file dat/chin/ptt/exo.1/gud.wdf
sample:
yi3.1 se4 lie4 de5 zhong4 zi5 ge4.1 dai4.1 jia1 juan4.1 he2 ya3 ge4.1
yi1 tong2 lai2 dao4.1 ai1.3 ji2.1 ta1 men5 de5 ming2.1 zi4.1 ji4.1 zai4
xia4 mian4 you3 liu2.2 bian4 xi1 mian3.5 li4.1 wei4 you2.2 da4 yi3.1 sa4
jia1.11 xi1 bu4.3 lun2.1 bian4 ya3 min3.3 dan4 na2 fu2.14 ta1 li4.1
jia1.11 de2 ya4.1 she4.2 fan2 cong2 ya3 ge4.1 er2.1 sheng1 de5 gong4
you3 qi1 shi2.1 ren2 yue1 se4.2 yi3 jing1 zai4 ai1.3 ji2.1 yue1 se4.2
he2 ta1 de5 di4.1 xiong1 bing4.1 nei4 yi1 dai4.3 de5 ren2 dou1 si3 le5
yi3.1 se4 lie4 ren2 sheng1 yang3 zhong4 duo1 bing4.1 qie3 fan2.2 mao4.3
ji2.3 qi2 qiang2 sheng4.2 man3 le5 nei4 di4 you3 bu4 ren4 shi5 yue1
se4.2 de5 xin1.1 wang2 qi3 lai2 zhi4.2 li3.1 ai1.3 ji2.1 dui4 ta1 de5
bai3 xing4.2 shuo1 kan4 na3 zhei4 yi3.1 se4 lie4 min2 bi3 wo3 men5 hai2
duo1 you4 bi3 wo3 men5 qiang2 sheng4.2 lai2 ba5 wo3 men5 bu4 ru2 yong4
qiao3.1 ji4.2 dai4.2 ta1 men5 kong3 pa4 ta1 men5 duo1 qi3 lai2 ri4
hou4.1 ruo4 yu4.2 shen2 me5 zheng1.1 zhan4.2 de5 shi4.1 jiu4 lian2 he2.2
wo3 men5 de5 chou2.2 di2.2 gong1.7 ji1.6 wo3 men5 li2 kai1 zhei4 di4 qu4
le5 yu2 shi4 ai1.3 ji2.1 ren2 pai4 du1.1 gong1.1 de5 xia2.4 zhi4.4 ta1
men5 jia1.1 zhong4.1 dan1.3 ku3 hai4 ta1 men5 ta1 men5 wei2 fa3 lao3
jian4.9 zao4 liang3 zuo4.3 ji1.5 huo4.2 cheng2.1 jiu4 shi4 bi3 dong1 he2
lan2 sai4 zhi3 shi4 yue4.1 fa1 ku3 hai4 ta1 men5 ta1 men5 yue4.1 fa1
duo1 qi3 lai2 yue4.1 fa1 man4.3 yan2.4 ai1.3 ji2.1 ren2 jiu4 yin1 yi3.1
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
zhang4.1 mu4.4 de5 men2 lian2.4 zai4 hui4 mu4.4 de5 zhang4.1 mu4.4 men2
qian2 an1 she4.2 fan2.6 ji4.4 tan2.2 ba3 fan2.6 ji4.4 he2 su4.1 ji4.4
xian4.4 zai4 qi2 shang4 shi4 zhao4 ye1 he2 hua2 suo3 fen1.1 fu4.2
removed 'dat/chin/ptt/exo.1/gud.wfr'
creating the word frequency file dat/chin/ptt/exo.1/gud.wfr
the 10 most common words in dat/chin/ptt/exo.1/gud.tlw:
1791 0.05113 de5
737 0.02104 he2
726 0.02073 ni3
644 0.01839 ta1
611 0.01744 men5
596 0.01702 yao4
525 0.01499 zai4
504 0.01439 wo3
481 0.01373 zi5
450 0.01285 ren2
removed 'dat/chin/ptt/exo.1/gud-trunc-wds-summary.tex'
removed 'exp/chin/ptt/exo.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/chin/ptt/exo.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:34 by tex-make-sample-summary.sh
% Token and word counts for chin/ptt/exo.1/gud.wfr
%
\def\chinptttruncexoPBgudTks{35027}
\def\chinptttruncexoPBgudTksPct{97.2}
\def\chinptttruncexoPBgudWds{1424}
\def\chinptttruncexoPBgudWdsPct{4.0}
copied '/tmp/586879.file' -> 'exp/chin/ptt/exo.1/gud-trunc-wds-summary.tex'
removed '/tmp/586879.file'
creating running text file dat/chin/ptt/exo.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/chin/ptt/exo.1/bad.wfr'
creating the word frequency file dat/chin/ptt/exo.1/bad.wfr
the 10 most common words in dat/chin/ptt/exo.1/bad.tlw:
1001 1.00000 =
removed 'dat/chin/ptt/exo.1/bad-trunc-wds-summary.tex'
removed 'exp/chin/ptt/exo.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/chin/ptt/exo.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:34 by tex-make-sample-summary.sh
% Token and word counts for chin/ptt/exo.1/bad.wfr
%
\def\chinptttruncexoPBbadTks{1001}
\def\chinptttruncexoPBbadTksPct{2.8}
\def\chinptttruncexoPBbadWds{1}
\def\chinptttruncexoPBbadWdsPct{0.0}
copied '/tmp/586923.file' -> 'exp/chin/ptt/exo.1/bad-trunc-wds-summary.tex'
removed '/tmp/586923.file'
... creating word files dat/chin/ptt/num.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
36034 dat/chin/ptt/num.1/trunc.tlw
removed 'dat/chin/ptt/num.1/raw.tlw'
removed 'dat/chin/ptt/num.1/gud.tlw'
removed 'dat/chin/ptt/num.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/chin/ptt/num.1/raw.wdf
sample:
yi3.1 se4 lie4 ren2 chu1 ai1.3 ji2.1 di4 hou4.1 di4.2 er4 nian2 er4 yue4
chu1.1 yi1 ri4 ye1 he2 hua2 zai4 xi1 nai3.1 de5 kuang4.1 ye3.1 hui4
mu4.4 zhong1 xiao3.1 yu4.7 mo2.3 xi1 shuo1 ni3 yao4 an4.1 yi3.1 se4 lie4
quan2 hui4 zhong4 de5 jia1 shi4.9 zong1 zu2.1 ren2 ming2.1 de5 shu4 mu4
ji4.2 suan4 suo3 you3 de5 nan2.1 ding1 =
fan2 yi3.1 se4 lie4 zhong1 cong2 er4 shi2.1 sui4.1 yi3.1 wai4 neng2 chu1
qu4 da3 zhang4.2 de5 ni3 he2 ya4.1 lun2.1 yao4 zhao4 ta1 men5 de5 jun1.1
dui4.2 shu4 dian3 =
mei3 zhi1.2 pai4 zhong1 bi4 you3 yi1 ren2 zuo4.2 ben3 zhi1.2 pai4 de5
zu2.1 zhang3 bang1 zhu4.2 ni3 men5 =
ta1 men5 de5 ming2.1 zi4.1 shu3 liu2.2 bian4 de5 you3 shi4.10 diu1 er3.5
de5 er2 zi5 yi3.1 li4.1 xu5 =
shu3 xi1 mian3.5 de5 you3 su1 li4.1 sha1.2 dai4.3 de5 er2 zi5 shi4.10
lu4 mie4.1 =
shu3 you2.2 da4 de5 you3 ya4.1 mi3 na2 da2.1 de5 er2 zi5 na2 shun4 =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
mo2.3 xi1 fen1.1 fu4.2 yi3.1 se4 lie4 ren2 shuo1 zhei4 di4 jiu4 shi4 ye1
he2 hua2 fen1.1 fu4.2 nian1 jiu1.2
removed 'dat/chin/ptt/num.1/raw.wfr'
creating the word frequency file dat/chin/ptt/num.1/raw.wfr
the 10 most common words in dat/chin/ptt/num.1/raw.tlw:
1885 0.05231 de5
1007 0.02795 =
670 0.01859 men5
629 0.01746 ta1
613 0.01701 he2
562 0.01560 ren2
510 0.01415 ni3
481 0.01335 yi3.1
476 0.01321 zai4
457 0.01268 yi1
removed 'dat/chin/ptt/num.1/raw-trunc-wds-summary.tex'
removed 'exp/chin/ptt/num.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/chin/ptt/num.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:34 by tex-make-sample-summary.sh
% Token and word counts for chin/ptt/num.1/raw.wfr
%
\def\chinptttruncnumPBrawTks{36034}
\def\chinptttruncnumPBrawTksPct{100.0}
\def\chinptttruncnumPBrawWds{1292}
\def\chinptttruncnumPBrawWdsPct{3.6}
copied '/tmp/586977.file' -> 'exp/chin/ptt/num.1/raw-trunc-wds-summary.tex'
removed '/tmp/586977.file'
creating running text file dat/chin/ptt/num.1/gud.wdf
sample:
yi3.1 se4 lie4 ren2 chu1 ai1.3 ji2.1 di4 hou4.1 di4.2 er4 nian2 er4 yue4
chu1.1 yi1 ri4 ye1 he2 hua2 zai4 xi1 nai3.1 de5 kuang4.1 ye3.1 hui4
mu4.4 zhong1 xiao3.1 yu4.7 mo2.3 xi1 shuo1 ni3 yao4 an4.1 yi3.1 se4 lie4
quan2 hui4 zhong4 de5 jia1 shi4.9 zong1 zu2.1 ren2 ming2.1 de5 shu4 mu4
ji4.2 suan4 suo3 you3 de5 nan2.1 ding1 fan2 yi3.1 se4 lie4 zhong1 cong2
er4 shi2.1 sui4.1 yi3.1 wai4 neng2 chu1 qu4 da3 zhang4.2 de5 ni3 he2
ya4.1 lun2.1 yao4 zhao4 ta1 men5 de5 jun1.1 dui4.2 shu4 dian3 mei3
zhi1.2 pai4 zhong1 bi4 you3 yi1 ren2 zuo4.2 ben3 zhi1.2 pai4 de5 zu2.1
zhang3 bang1 zhu4.2 ni3 men5 ta1 men5 de5 ming2.1 zi4.1 shu3 liu2.2
bian4 de5 you3 shi4.10 diu1 er3.5 de5 er2 zi5 yi3.1 li4.1 xu5 shu3 xi1
mian3.5 de5 you3 su1 li4.1 sha1.2 dai4.3 de5 er2 zi5 shi4.10 lu4 mie4.1
shu3 you2.2 da4 de5 you3 ya4.1 mi3 na2 da2.1 de5 er2 zi5 na2 shun4 shu3
yi3.1 sa4 jia1.11 de5 you3 su1 ya1.3 de5 er2 zi5 na2 tan3.1 ye4.1 shu3
xi1 bu4.3 lun2.1 de5 you3 xi1.5 lun2.1 de5 er2 zi5 yi3.1 li4.1 ya1.3
yue1 se4.2 zi5 sun1 shu3 yi3.1 fa3 lian2.3 de5 you3 ya4.1 mi3 hu1 de5
er2 zi5 yi3.1 li4.1 sha1.2 ma3.1 shu3 ma3.1 na2 xi1 de5 you3 bi3 da4 xu5
de5 er2 zi5 jia1.11 ma3.1 lie4 shu3 bian4 ya3 min3.3 de5 you3 ji1.7 duo1
ni2.2 de5 er2 zi5 ya4.1 bi3 dan4 shu3 dan4 de5 you3 ya4.1 mi3 sha1.2
dai4.3 de5 er2 zi5 ya4.1 xi1.5 yi3.1 xie4 shu3 ya4.1 she4.2 de5 you3
e2.6 lan2 de5 er2 zi5 pa4.1 jie2 shu3 jia1.11 de2 de5 you3 diu1 er3.5
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
de5 bian1 jie4.1 yi3.1 nei4.1 yao4 zuo4.2 ni3 men5 de5 di4 mo2.3 xi1
fen1.1 fu4.2 yi3.1 se4 lie4 ren2 shuo1 zhei4 di4 jiu4 shi4 ye1 he2 hua2
fen1.1 fu4.2 nian1 jiu1.2
removed 'dat/chin/ptt/num.1/gud.wfr'
creating the word frequency file dat/chin/ptt/num.1/gud.wfr
the 10 most common words in dat/chin/ptt/num.1/gud.tlw:
1885 0.05382 de5
670 0.01913 men5
629 0.01796 ta1
613 0.01750 he2
562 0.01604 ren2
510 0.01456 ni3
481 0.01373 yi3.1
476 0.01359 zai4
457 0.01305 yi1
425 0.01213 shi4
removed 'dat/chin/ptt/num.1/gud-trunc-wds-summary.tex'
removed 'exp/chin/ptt/num.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/chin/ptt/num.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:34 by tex-make-sample-summary.sh
% Token and word counts for chin/ptt/num.1/gud.wfr
%
\def\chinptttruncnumPBgudTks{35027}
\def\chinptttruncnumPBgudTksPct{97.2}
\def\chinptttruncnumPBgudWds{1291}
\def\chinptttruncnumPBgudWdsPct{3.6}
copied '/tmp/587021.file' -> 'exp/chin/ptt/num.1/gud-trunc-wds-summary.tex'
removed '/tmp/587021.file'
creating running text file dat/chin/ptt/num.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/chin/ptt/num.1/bad.wfr'
creating the word frequency file dat/chin/ptt/num.1/bad.wfr
the 10 most common words in dat/chin/ptt/num.1/bad.tlw:
1007 1.00000 =
removed 'dat/chin/ptt/num.1/bad-trunc-wds-summary.tex'
removed 'exp/chin/ptt/num.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/chin/ptt/num.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:34 by tex-make-sample-summary.sh
% Token and word counts for chin/ptt/num.1/bad.wfr
%
\def\chinptttruncnumPBbadTks{1007}
\def\chinptttruncnumPBbadTksPct{2.8}
\def\chinptttruncnumPBbadWds{1}
\def\chinptttruncnumPBbadWdsPct{0.0}
copied '/tmp/587065.file' -> 'exp/chin/ptt/num.1/bad-trunc-wds-summary.tex'
removed '/tmp/587065.file'
... creating word files dat/chin/ptt/lev.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
26404 dat/chin/ptt/lev.1/trunc.tlw
removed 'dat/chin/ptt/lev.1/raw.tlw'
removed 'dat/chin/ptt/lev.1/gud.tlw'
removed 'dat/chin/ptt/lev.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/chin/ptt/lev.1/raw.wdf
sample:
ye1 he2 hua2 cong2 hui4 mu4.4 zhong1 hu1.1 jiao4 mo2.3 xi1 dui4 ta1
shuo1 ni3 xiao3.1 yu4.7 yi3.1 se4 lie4 ren2 shuo1 ni3 men5 zhong1 jian1
ruo4 you3 ren2 xian4.4 gong1.4 wu4 ji3.1 ye1 he2 hua2 yao4 cong2 niu2
qun2.1 yang2.3 qun2.1 zhong1 xian4.4 sheng1.5 chu4.1 wei2 gong1.4 wu4 =
ta1 de5 gong1.4 wu4 ruo4 yi3.1 niu2 wei2 fan2.6 ji4.4 jiu4 yao4 zai4
hui4 mu4.4 men2 kou3 xian4.4 yi1 zhi3 mei2 you3 can2 ji2.5 de5 gong1
niu2 ke3 yi3.1 zai4 ye1 he2 hua2 mian4 qian2 meng3 yue4.2 na4 =
ta1 yao4 an4.1 shou3 zai4 fan2.6 ji4.4 sheng1.5 de5 tou2 shang4 fan2.6
ji4.4 bian4 meng3 yue4.2 na4 wei2 ta1 shu2.1 zui4 =
ta1 yao4 zai4 ye1 he2 hua2 mian4 qian2 zai3.2 gong1 niu2 ya4.1 lun2.1
zi5 sun1 zuo4.2 ji4.4 si1.1 de5 yao4 feng4.1 shang4 xue4 ba3 xue4 sa3
zai4 hui4 mu4.4 men2 kou3 tan2.2 de5 zhou1 wei2.2 =
nei4 ren2 yao4 bo1.3 qu4 fan2.6 ji4.4 sheng1.5 de5 pi2 ba3 fan2.6 ji4.4
sheng1.5 qie4 cheng2 kuai4.1 zi5 =
ji4.4 si1.1 ya4.1 lun2.1 de5 zi5 sun1 yao4 ba3 huo3 fang4 zai4 tan2.2
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
zhei4 jiu4 shi4 ye1 he2 hua2 zai4 xi1 nai3.1 shan1 wei2 yi3.1 se4 lie4
ren2 suo3 fen1.1 fu4.2 mo2.3 xi1 de5 ming4 ling4 =
removed 'dat/chin/ptt/lev.1/raw.wfr'
creating the word frequency file dat/chin/ptt/lev.1/raw.wfr
the 10 most common words in dat/chin/ptt/lev.1/raw.tlw:
1463 0.05541 de5
710 0.02689 =
641 0.02428 yao4
508 0.01924 shi4
480 0.01818 ji4.4
475 0.01799 he2
473 0.01791 ni3
448 0.01697 men5
440 0.01666 zai4
435 0.01647 ta1
removed 'dat/chin/ptt/lev.1/raw-trunc-wds-summary.tex'
removed 'exp/chin/ptt/lev.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/chin/ptt/lev.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:34 by tex-make-sample-summary.sh
% Token and word counts for chin/ptt/lev.1/raw.wfr
%
\def\chinptttrunclevPBrawTks{26404}
\def\chinptttrunclevPBrawTksPct{100.0}
\def\chinptttrunclevPBrawWds{1096}
\def\chinptttrunclevPBrawWdsPct{4.2}
copied '/tmp/587119.file' -> 'exp/chin/ptt/lev.1/raw-trunc-wds-summary.tex'
removed '/tmp/587119.file'
creating running text file dat/chin/ptt/lev.1/gud.wdf
sample:
ye1 he2 hua2 cong2 hui4 mu4.4 zhong1 hu1.1 jiao4 mo2.3 xi1 dui4 ta1
shuo1 ni3 xiao3.1 yu4.7 yi3.1 se4 lie4 ren2 shuo1 ni3 men5 zhong1 jian1
ruo4 you3 ren2 xian4.4 gong1.4 wu4 ji3.1 ye1 he2 hua2 yao4 cong2 niu2
qun2.1 yang2.3 qun2.1 zhong1 xian4.4 sheng1.5 chu4.1 wei2 gong1.4 wu4
ta1 de5 gong1.4 wu4 ruo4 yi3.1 niu2 wei2 fan2.6 ji4.4 jiu4 yao4 zai4
hui4 mu4.4 men2 kou3 xian4.4 yi1 zhi3 mei2 you3 can2 ji2.5 de5 gong1
niu2 ke3 yi3.1 zai4 ye1 he2 hua2 mian4 qian2 meng3 yue4.2 na4 ta1 yao4
an4.1 shou3 zai4 fan2.6 ji4.4 sheng1.5 de5 tou2 shang4 fan2.6 ji4.4
bian4 meng3 yue4.2 na4 wei2 ta1 shu2.1 zui4 ta1 yao4 zai4 ye1 he2 hua2
mian4 qian2 zai3.2 gong1 niu2 ya4.1 lun2.1 zi5 sun1 zuo4.2 ji4.4 si1.1
de5 yao4 feng4.1 shang4 xue4 ba3 xue4 sa3 zai4 hui4 mu4.4 men2 kou3
tan2.2 de5 zhou1 wei2.2 nei4 ren2 yao4 bo1.3 qu4 fan2.6 ji4.4 sheng1.5
de5 pi2 ba3 fan2.6 ji4.4 sheng1.5 qie4 cheng2 kuai4.1 zi5 ji4.4 si1.1
ya4.1 lun2.1 de5 zi5 sun1 yao4 ba3 huo3 fang4 zai4 tan2.2 shang4 ba3
chai2 bai3.1 zai4 huo3 shang4 ya4.1 lun2.1 zi5 sun1 zuo4.2 ji4.4 si1.1
de5 yao4 ba3 rou4 kuai4.1 he2 tou2 bing4.1 zhi1.4 you2.4 bai3.1 zai4
tan2.2 shang4 huo3 de5 chai2 shang4 dan4 fan2.6 ji4.4 de5 zang4.2 fu3.7
yu3 tui3 yao4 yong4 shui3 xi3.1 ji4.4 si1.1 jiu4 yao4 ba3 yi1 qie4 quan2
shao1 zai4 tan2.2 shang4 dang1 zuo4.2 fan2.6 ji4.4 xian4.4 yu3 ye1 he2
hua2 wei2 xin1.8 xiang1 de5 huo3 ji4.4 ren2 de5 gong1.4 wu4 ruo4 yi3.1
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
de5 yu3 ben3 lai2 de5 sheng1.5 chu4.1 dou1 yao4 cheng2 wei2 sheng4.1 bu4
ke3 shu2.1 hui2 zhei4 jiu4 shi4 ye1 he2 hua2 zai4 xi1 nai3.1 shan1 wei2
yi3.1 se4 lie4 ren2 suo3 fen1.1 fu4.2 mo2.3 xi1 de5 ming4 ling4
removed 'dat/chin/ptt/lev.1/gud.wfr'
creating the word frequency file dat/chin/ptt/lev.1/gud.wfr
the 10 most common words in dat/chin/ptt/lev.1/gud.tlw:
1463 0.05694 de5
641 0.02495 yao4
508 0.01977 shi4
480 0.01868 ji4.4
475 0.01849 he2
473 0.01841 ni3
448 0.01744 men5
440 0.01712 zai4
435 0.01693 ta1
409 0.01592 bu4
removed 'dat/chin/ptt/lev.1/gud-trunc-wds-summary.tex'
removed 'exp/chin/ptt/lev.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/chin/ptt/lev.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:34 by tex-make-sample-summary.sh
% Token and word counts for chin/ptt/lev.1/gud.wfr
%
\def\chinptttrunclevPBgudTks{25694}
\def\chinptttrunclevPBgudTksPct{97.3}
\def\chinptttrunclevPBgudWds{1095}
\def\chinptttrunclevPBgudWdsPct{4.1}
copied '/tmp/587163.file' -> 'exp/chin/ptt/lev.1/gud-trunc-wds-summary.tex'
removed '/tmp/587163.file'
creating running text file dat/chin/ptt/lev.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/chin/ptt/lev.1/bad.wfr'
creating the word frequency file dat/chin/ptt/lev.1/bad.wfr
the 10 most common words in dat/chin/ptt/lev.1/bad.tlw:
710 1.00000 =
removed 'dat/chin/ptt/lev.1/bad-trunc-wds-summary.tex'
removed 'exp/chin/ptt/lev.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/chin/ptt/lev.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:34 by tex-make-sample-summary.sh
% Token and word counts for chin/ptt/lev.1/bad.wfr
%
\def\chinptttrunclevPBbadTks{710}
\def\chinptttrunclevPBbadTksPct{2.7}
\def\chinptttrunclevPBbadWds{1}
\def\chinptttrunclevPBbadWdsPct{0.0}
copied '/tmp/587207.file' -> 'exp/chin/ptt/lev.1/bad-trunc-wds-summary.tex'
removed '/tmp/587207.file'
... creating word files dat/chin/ptt/deu.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
32282 dat/chin/ptt/deu.1/trunc.tlw
removed 'dat/chin/ptt/deu.1/raw.tlw'
removed 'dat/chin/ptt/deu.1/gud.tlw'
removed 'dat/chin/ptt/deu.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/chin/ptt/deu.1/raw.wdf
sample:
yi3.1 xia4 suo3 ji4.1 de5 shi4 mo2.3 xi1 zai4 yue1 dan4.3 he2.5 dong1
de5 kuang4.1 ye3.1 shu1.3 fu2.14 dui4 mian4 de5 ya4.1 la1 ba1.1 jiu4
shi4 ba1.1 lan2 tuo2 fu2.14 la1 ban1.1 ha1 xi3.1 lu4.3 di3 sa1 ha1
zhong1 jian1 xiang4 yi3.1 se4 lie4 zhong4 ren2 suo3 shuo1 de5 hua4 =
cong2 he2.1 lie4.1 shan1 jing1 guo4 xi1 er3.5 shan1 dao4.1 jia1.1 di1
si1.6 ba1.1 ni2.2 ya4.1 you3 shi2.1 yi1 tian1 de5 lu4 cheng2.5 =
chu1 ai1.3 ji2.1 di4.2 si4 shi2.1 nian2 shi2.1 yi1 yue4 chu1.1 yi1 ri4
mo2.3 xi1 zhao4 ye1 he2 hua2 jie4 zhe5 ta1 suo3 fen1.1 fu4.2 yi3.1 se4
lie4 ren2 de5 hua4 dou1 xiao3.1 yu4.7 ta1 men5 =
nei4 shi2 ta1 yi3 jing1 ji1.6 sha1.1 le5 zhu4.1 xi1.5 shi2.2 ben3 de5
ya4.1 mo2.3 li4.1 wang2 xi1 hong2.3 he2 zhu4.1 yi3.1 de2 lai2 ya4.1
si1.6 ta1 lu4.3 de5 ba1.1 shan1.4 wang2 e4.8 =
mo2.3 xi1 zai4 yue1 dan4.3 he2.5 dong1 de5 mo2.3 ya1.3 di4 jiang3 lü4.1
fa3 shuo1 ye1 he2 hua2 wo3 men5 de5 shen2.1 zai4 he2.1 lie4.1 shan1
xiao3.1 yu4.7 wo3 men5 shuo1 ni3 men5 zai4 zhei4 shan1 shang4 zhu4.1 de5
ri4 zi5 gou4.1 le5 =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
qian2 xian3 da4 neng2 de5 shou3 xing2 yi1 qie4 da4 er2.1 ke3 wei4.5 de5
shi4.1 =
removed 'dat/chin/ptt/deu.1/raw.wfr'
creating the word frequency file dat/chin/ptt/deu.1/raw.wfr
the 10 most common words in dat/chin/ptt/deu.1/raw.tlw:
1738 0.05384 de5
1650 0.05111 ni3
847 0.02624 men5
788 0.02441 =
718 0.02224 ta1
684 0.02119 he2
545 0.01688 ye1
536 0.01660 hua2
488 0.01512 zai4
449 0.01391 suo3
removed 'dat/chin/ptt/deu.1/raw-trunc-wds-summary.tex'
removed 'exp/chin/ptt/deu.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/chin/ptt/deu.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:35 by tex-make-sample-summary.sh
% Token and word counts for chin/ptt/deu.1/raw.wfr
%
\def\chinptttruncdeuPBrawTks{32282}
\def\chinptttruncdeuPBrawTksPct{100.0}
\def\chinptttruncdeuPBrawWds{1434}
\def\chinptttruncdeuPBrawWdsPct{4.4}
copied '/tmp/587261.file' -> 'exp/chin/ptt/deu.1/raw-trunc-wds-summary.tex'
removed '/tmp/587261.file'
creating running text file dat/chin/ptt/deu.1/gud.wdf
sample:
yi3.1 xia4 suo3 ji4.1 de5 shi4 mo2.3 xi1 zai4 yue1 dan4.3 he2.5 dong1
de5 kuang4.1 ye3.1 shu1.3 fu2.14 dui4 mian4 de5 ya4.1 la1 ba1.1 jiu4
shi4 ba1.1 lan2 tuo2 fu2.14 la1 ban1.1 ha1 xi3.1 lu4.3 di3 sa1 ha1
zhong1 jian1 xiang4 yi3.1 se4 lie4 zhong4 ren2 suo3 shuo1 de5 hua4 cong2
he2.1 lie4.1 shan1 jing1 guo4 xi1 er3.5 shan1 dao4.1 jia1.1 di1 si1.6
ba1.1 ni2.2 ya4.1 you3 shi2.1 yi1 tian1 de5 lu4 cheng2.5 chu1 ai1.3
ji2.1 di4.2 si4 shi2.1 nian2 shi2.1 yi1 yue4 chu1.1 yi1 ri4 mo2.3 xi1
zhao4 ye1 he2 hua2 jie4 zhe5 ta1 suo3 fen1.1 fu4.2 yi3.1 se4 lie4 ren2
de5 hua4 dou1 xiao3.1 yu4.7 ta1 men5 nei4 shi2 ta1 yi3 jing1 ji1.6
sha1.1 le5 zhu4.1 xi1.5 shi2.2 ben3 de5 ya4.1 mo2.3 li4.1 wang2 xi1
hong2.3 he2 zhu4.1 yi3.1 de2 lai2 ya4.1 si1.6 ta1 lu4.3 de5 ba1.1
shan1.4 wang2 e4.8 mo2.3 xi1 zai4 yue1 dan4.3 he2.5 dong1 de5 mo2.3
ya1.3 di4 jiang3 lü4.1 fa3 shuo1 ye1 he2 hua2 wo3 men5 de5 shen2.1 zai4
he2.1 lie4.1 shan1 xiao3.1 yu4.7 wo3 men5 shuo1 ni3 men5 zai4 zhei4
shan1 shang4 zhu4.1 de5 ri4 zi5 gou4.1 le5 yao4 qi3 xing2 zhuan3 dao4.1
ya4.1 mo2.3 li4.1 ren2 de5 shan1 di4 he2 kao4 jin4.1 zhei4 shan1 di4 de5
ge4.1 chu3 jiu4 shi4 ya4.1 la1 ba1.1 shan1 di4 gao1 yuan2 nan2.2 di4
yan2.3 hai3 yi1 dai4.1 jia1.11 nan2.2 ren2 de5 di4 bing4.1 li4.1 ba1.1
nen4 shan1 you4 dao4.1 bo2.1 la1 da4 he2.5 ru2 jin1 wo3 jiang1 zhei4 di4
bai3.1 zai4 ni3 men5 mian4 qian2 ni3 men5 yao4 jin4 qu4 de2 zhei4 di4
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
yang4 shen2.1 ji1.2 qi2.2 shi4.1 you4 zai4 yi3.1 se4 lie4 zhong4 ren2
yan3 qian2 xian3 da4 neng2 de5 shou3 xing2 yi1 qie4 da4 er2.1 ke3 wei4.5
de5 shi4.1
removed 'dat/chin/ptt/deu.1/gud.wfr'
creating the word frequency file dat/chin/ptt/deu.1/gud.wfr
the 10 most common words in dat/chin/ptt/deu.1/gud.tlw:
1738 0.05519 de5
1650 0.05239 ni3
847 0.02689 men5
718 0.02280 ta1
684 0.02172 he2
545 0.01730 ye1
536 0.01702 hua2
488 0.01550 zai4
449 0.01426 suo3
436 0.01384 wo3
removed 'dat/chin/ptt/deu.1/gud-trunc-wds-summary.tex'
removed 'exp/chin/ptt/deu.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/chin/ptt/deu.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:35 by tex-make-sample-summary.sh
% Token and word counts for chin/ptt/deu.1/gud.wfr
%
\def\chinptttruncdeuPBgudTks{31494}
\def\chinptttruncdeuPBgudTksPct{97.6}
\def\chinptttruncdeuPBgudWds{1433}
\def\chinptttruncdeuPBgudWdsPct{4.4}
copied '/tmp/587305.file' -> 'exp/chin/ptt/deu.1/gud-trunc-wds-summary.tex'
removed '/tmp/587305.file'
creating running text file dat/chin/ptt/deu.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/chin/ptt/deu.1/bad.wfr'
creating the word frequency file dat/chin/ptt/deu.1/bad.wfr
the 10 most common words in dat/chin/ptt/deu.1/bad.tlw:
788 1.00000 =
removed 'dat/chin/ptt/deu.1/bad-trunc-wds-summary.tex'
removed 'exp/chin/ptt/deu.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/chin/ptt/deu.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:35 by tex-make-sample-summary.sh
% Token and word counts for chin/ptt/deu.1/bad.wfr
%
\def\chinptttruncdeuPBbadTks{788}
\def\chinptttruncdeuPBbadTksPct{2.4}
\def\chinptttruncdeuPBbadWds{1}
\def\chinptttruncdeuPBbadWdsPct{0.0}
copied '/tmp/587349.file' -> 'exp/chin/ptt/deu.1/bad-trunc-wds-summary.tex'
removed '/tmp/587349.file'
... creating word files dat/chin/ptt/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
36056 dat/chin/ptt/tot.1/trunc.tlw
removed 'dat/chin/ptt/tot.1/raw.tlw'
removed 'dat/chin/ptt/tot.1/gud.tlw'
removed 'dat/chin/ptt/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/chin/ptt/tot.1/raw.wdf
sample:
qi3 chu1.1 shen2.1 chuang4 zao4 tian1 di4 =
di4 shi4 kong1 xu1.1 hun4 dun4.5 yuan1.2 mian4 hei1 an4 shen2.1 de5
ling2.1 yun4.1 xing2 zai4 shui3 mian4 shang4 =
shen2.1 shuo1 yao4 you3 guang1 jiu4 you3 le5 guang1 =
shen2.1 kan4 guang1 shi4 hao3 de5 jiu4 ba3 guang1 an4 fen1 kai1 le5 =
shen2.1 cheng1 guang1 wei2 zhou4.1 cheng1 an4 wei2 ye4 you3 wan3 shang4
you3 zao3 chen2.5 zhei4 shi4 tou2 yi1 ri4 =
shen2.1 shuo1 zhu1.1 shui3 zhi1.1 jian1 yao4 you3 kong1 qi4 jiang1 shui3
fen1 wei2 shang4 xia4 =
shen2.1 jiu4 zao4 chu1 kong1 qi4 jiang1 kong1 qi4 yi3.1 xia4 de5 shui3
kong1 qi4 yi3.1 shang4 de5 shui3 fen1 kai1 le5 shi4.1 jiu4 zhei4 yang4
cheng2 le5 =
shen2.1 cheng1 kong1 qi4 wei2 tian1 you3 wan3 shang4 you3 zao3 chen2.5
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
zhi4 yu2 ni3 ke3 yi3.1 zhan4 zai4 wo3 zhei4 li3 wo3 yao4 jiang1 yi1 qie4
jie4.8 ming4 lü4.1
removed 'dat/chin/ptt/tot.1/raw.wfr'
creating the word frequency file dat/chin/ptt/tot.1/raw.wfr
the 10 most common words in dat/chin/ptt/tot.1/raw.tlw:
1891 0.05245 de5
1029 0.02854 =
658 0.01825 ni3
656 0.01819 ta1
645 0.01789 he2
614 0.01703 men5
528 0.01464 ren2
518 0.01437 zai4
484 0.01342 shi4
457 0.01267 yao4
removed 'dat/chin/ptt/tot.1/raw-trunc-wds-summary.tex'
removed 'exp/chin/ptt/tot.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/chin/ptt/tot.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:35 by tex-make-sample-summary.sh
% Token and word counts for chin/ptt/tot.1/raw.wfr
%
\def\chinptttrunctotPBrawTks{36056}
\def\chinptttrunctotPBrawTksPct{100.0}
\def\chinptttrunctotPBrawWds{1393}
\def\chinptttrunctotPBrawWdsPct{3.9}
copied '/tmp/587403.file' -> 'exp/chin/ptt/tot.1/raw-trunc-wds-summary.tex'
removed '/tmp/587403.file'
creating running text file dat/chin/ptt/tot.1/gud.wdf
sample:
qi3 chu1.1 shen2.1 chuang4 zao4 tian1 di4 di4 shi4 kong1 xu1.1 hun4
dun4.5 yuan1.2 mian4 hei1 an4 shen2.1 de5 ling2.1 yun4.1 xing2 zai4
shui3 mian4 shang4 shen2.1 shuo1 yao4 you3 guang1 jiu4 you3 le5 guang1
shen2.1 kan4 guang1 shi4 hao3 de5 jiu4 ba3 guang1 an4 fen1 kai1 le5
shen2.1 cheng1 guang1 wei2 zhou4.1 cheng1 an4 wei2 ye4 you3 wan3 shang4
you3 zao3 chen2.5 zhei4 shi4 tou2 yi1 ri4 shen2.1 shuo1 zhu1.1 shui3
zhi1.1 jian1 yao4 you3 kong1 qi4 jiang1 shui3 fen1 wei2 shang4 xia4
shen2.1 jiu4 zao4 chu1 kong1 qi4 jiang1 kong1 qi4 yi3.1 xia4 de5 shui3
kong1 qi4 yi3.1 shang4 de5 shui3 fen1 kai1 le5 shi4.1 jiu4 zhei4 yang4
cheng2 le5 shen2.1 cheng1 kong1 qi4 wei2 tian1 you3 wan3 shang4 you3
zao3 chen2.5 shi4 di4.2 er4 ri4 shen2.1 shuo1 tian1 xia4 de5 shui3 yao4
ju4.3 zai4 yi1 chu3 shi3 han4.4 di4 lu4.1 chu1 lai2 shi4.1 jiu4 zhei4
yang4 cheng2 le5 shen2.1 cheng1 han4.4 di4 wei2 di4 cheng1 shui3 de5
ju4.3 chu3 wei2 hai3 shen2.1 kan4 zhe5 shi4 hao3 de5 shen2.1 shuo1 di4
yao4 fa1 sheng1 qing1.2 cao3 he2 jie2 zhong3 zi5 de5 cai4 shu1.6 bing4.1
jie2 guo3 zi5 de5 shu4.2 mu4.1 ge4.1 cong2 qi2 lei4.1 guo3 zi5 dou1 bao1
zhe5 he2.6 shi4.1 jiu4 zhei4 yang4 cheng2 le5 yu2 shi4 di4 fa1 sheng1
le5 qing1.2 cao3 he2 jie2 zhong3 zi5 de5 cai4 shu1.6 ge4.1 cong2 qi2
lei4.1 bing4.1 jie2 guo3 zi5 de5 shu4.2 mu4.1 ge4.1 cong2 qi2 lei4.1
guo3 zi5 dou1 bao1 zhe5 he2.6 shen2.1 kan4 zhe5 shi4 hao3 de5 you3 wan3
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
de5 zi5 sun1 yong3.2 yuan3 de2 fu2.3 ni3 qu4 dui4 ta1 men5 shuo1 ni3
men5 hui2 zhang4.1 peng2.1 qu4 ba5 zhi4 yu2 ni3 ke3 yi3.1 zhan4 zai4 wo3
zhei4 li3 wo3 yao4 jiang1 yi1 qie4 jie4.8 ming4 lü4.1
removed 'dat/chin/ptt/tot.1/gud.wfr'
creating the word frequency file dat/chin/ptt/tot.1/gud.wfr
the 10 most common words in dat/chin/ptt/tot.1/gud.tlw:
1891 0.05399 de5
658 0.01879 ni3
656 0.01873 ta1
645 0.01841 he2
614 0.01753 men5
528 0.01507 ren2
518 0.01479 zai4
484 0.01382 shi4
457 0.01305 yao4
448 0.01279 wo3
removed 'dat/chin/ptt/tot.1/gud-trunc-wds-summary.tex'
removed 'exp/chin/ptt/tot.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/chin/ptt/tot.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:35 by tex-make-sample-summary.sh
% Token and word counts for chin/ptt/tot.1/gud.wfr
%
\def\chinptttrunctotPBgudTks{35027}
\def\chinptttrunctotPBgudTksPct{97.1}
\def\chinptttrunctotPBgudWds{1392}
\def\chinptttrunctotPBgudWdsPct{3.9}
copied '/tmp/587447.file' -> 'exp/chin/ptt/tot.1/gud-trunc-wds-summary.tex'
removed '/tmp/587447.file'
creating running text file dat/chin/ptt/tot.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/chin/ptt/tot.1/bad.wfr'
creating the word frequency file dat/chin/ptt/tot.1/bad.wfr
the 10 most common words in dat/chin/ptt/tot.1/bad.tlw:
1029 1.00000 =
removed 'dat/chin/ptt/tot.1/bad-trunc-wds-summary.tex'
removed 'exp/chin/ptt/tot.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/chin/ptt/tot.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:35 by tex-make-sample-summary.sh
% Token and word counts for chin/ptt/tot.1/bad.wfr
%
\def\chinptttrunctotPBbadTks{1029}
\def\chinptttrunctotPBbadTksPct{2.9}
\def\chinptttrunctotPBbadWds{1}
\def\chinptttrunctotPBbadWdsPct{0.0}
copied '/tmp/587491.file' -> 'exp/chin/ptt/tot.1/bad-trunc-wds-summary.tex'
removed '/tmp/587491.file'
lines words bytes file
------- ------- --------- ------------
1377 4131 30552 dat/chin/ptt/gen.1/raw.wfr
1425 4275 31684 dat/chin/ptt/exo.1/raw.wfr
1292 3876 28665 dat/chin/ptt/num.1/raw.wfr
1096 3288 24272 dat/chin/ptt/lev.1/raw.wfr
1434 4302 31893 dat/chin/ptt/deu.1/raw.wfr
1393 4179 30966 dat/chin/ptt/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
1376 4128 30534 dat/chin/ptt/gen.1/gud.wfr
1424 4272 31666 dat/chin/ptt/exo.1/gud.wfr
1291 3873 28647 dat/chin/ptt/num.1/gud.wfr
1095 3285 24254 dat/chin/ptt/lev.1/gud.wfr
1433 4299 31875 dat/chin/ptt/deu.1/gud.wfr
1392 4176 30948 dat/chin/ptt/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
1 3 18 dat/chin/ptt/gen.1/bad.wfr
1 3 18 dat/chin/ptt/exo.1/bad.wfr
1 3 18 dat/chin/ptt/num.1/bad.wfr
1 3 18 dat/chin/ptt/lev.1/bad.wfr
1 3 18 dat/chin/ptt/deu.1/bad.wfr
1 3 18 dat/chin/ptt/tot.1/bad.wfr
gen.1 raw = 36068 gud = 35027 bad = 1041
exo.1 raw = 36028 gud = 35027 bad = 1001
num.1 raw = 36034 gud = 35027 bad = 1007
lev.1 raw = 26404 gud = 25694 bad = 710
deu.1 raw = 32282 gud = 31494 bad = 788
tot.1 raw = 36056 gud = 35027 bad = 1029
=== creating the derived word files dat/chin/ptn/*/{raw,gud,bad}.{tlw,wdf,wfr} (trunc) ===
... creating word files dat/chin/ptn/gen.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
35736 dat/chin/ptn/gen.1/trunc.tlw
removed 'dat/chin/ptn/gen.1/raw.tlw'
removed 'dat/chin/ptn/gen.1/gud.tlw'
removed 'dat/chin/ptn/gen.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/chin/ptn/gen.1/raw.wdf
sample:
qi3 chu1.1 shen2.1 chuang4 zao4 tian1 di4 =
di4 shi4 kong1 xu1.1 hun4 dun4.5 shen1.1 yuan1.2 shang4 yi1 pian4 hei1
an4 shen2.1 de5 ling2.1 yun4.1 xing2 zai4 shui3 mian4 shang4 =
shen2.1 shuo1 yao4 you3 guang1 jiu4 you3 le5 guang1 =
shen2.1 kan4 guang1 shi4 hao3 de5 ta1 jiu4 ba3 guang1 an4 fen1 kai1 le5
=
shen2.1 cheng1 guang1 wei2 zhou4.1 cheng1 an4 wei2 ye4 you3 wan3 shang4
you3 zao3 chen2.5 zhei4 shi4 di4.2 yi1 ri4 =
shen2.1 shuo1 zhong4 shui3 zhi1.1 jian1 yao4 you3 qiong2.3 cang1 ba3
shui3 he2 shui3 fen1 kai1 shi4.1 jiu4 zhei4 yang4 cheng2 le5 =
shen2.1 zao4 le5 qiong2.3 cang1 ba3 qiong2.3 cang1 yi3.1 xia4 de5 shui3
he2 qiong2.3 cang1 yi3.1 shang4 de5 shui3 fen1 kai1 le5 =
shen2.1 cheng1 qiong2.3 cang1 wei2 tian1 you3 wan3 shang4 you3 zao3
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
ming2.1 jiao4 xi1.5 la1 =
you2.2 da4 zai4 nei4
removed 'dat/chin/ptn/gen.1/raw.wfr'
creating the word frequency file dat/chin/ptn/gen.1/raw.wfr
the 10 most common words in dat/chin/ptn/gen.1/raw.tlw:
1746 0.04886 de5
855 0.02393 wo3
807 0.02258 ta1
734 0.02054 ni3
709 0.01984 =
679 0.01900 le5
518 0.01450 zai4
502 0.01405 shi4
481 0.01346 ren2
476 0.01332 yi3.1
removed 'dat/chin/ptn/gen.1/raw-trunc-wds-summary.tex'
removed 'exp/chin/ptn/gen.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/chin/ptn/gen.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:35 by tex-make-sample-summary.sh
% Token and word counts for chin/ptn/gen.1/raw.wfr
%
\def\chinptntruncgenPBrawTks{35736}
\def\chinptntruncgenPBrawTksPct{100.0}
\def\chinptntruncgenPBrawWds{1381}
\def\chinptntruncgenPBrawWdsPct{3.9}
copied '/tmp/587661.file' -> 'exp/chin/ptn/gen.1/raw-trunc-wds-summary.tex'
removed '/tmp/587661.file'
creating running text file dat/chin/ptn/gen.1/gud.wdf
sample:
qi3 chu1.1 shen2.1 chuang4 zao4 tian1 di4 di4 shi4 kong1 xu1.1 hun4
dun4.5 shen1.1 yuan1.2 shang4 yi1 pian4 hei1 an4 shen2.1 de5 ling2.1
yun4.1 xing2 zai4 shui3 mian4 shang4 shen2.1 shuo1 yao4 you3 guang1 jiu4
you3 le5 guang1 shen2.1 kan4 guang1 shi4 hao3 de5 ta1 jiu4 ba3 guang1
an4 fen1 kai1 le5 shen2.1 cheng1 guang1 wei2 zhou4.1 cheng1 an4 wei2 ye4
you3 wan3 shang4 you3 zao3 chen2.5 zhei4 shi4 di4.2 yi1 ri4 shen2.1
shuo1 zhong4 shui3 zhi1.1 jian1 yao4 you3 qiong2.3 cang1 ba3 shui3 he2
shui3 fen1 kai1 shi4.1 jiu4 zhei4 yang4 cheng2 le5 shen2.1 zao4 le5
qiong2.3 cang1 ba3 qiong2.3 cang1 yi3.1 xia4 de5 shui3 he2 qiong2.3
cang1 yi3.1 shang4 de5 shui3 fen1 kai1 le5 shen2.1 cheng1 qiong2.3 cang1
wei2 tian1 you3 wan3 shang4 you3 zao3 chen2.5 zhei4 shi4 di4.2 er4 ri4
shen2.1 shuo1 tian1 xia4 de5 shui3 yao4 ju4.3 zai4 yi1 chu3 shi3 han4.4
di4 lu4.1 chu1 lai2 shi4.1 jiu4 zhei4 yang4 cheng2 le5 shen2.1 cheng1
han4.4 di4 wei2 di4 cheng1 shui3 de5 ju4.3 chu3 wei2 hai3 shen2.1 kan4
zhei4 shi4 hao3 de5 shen2.1 shuo1 di4 shang4 yao4 zhang3 chu1 qing1.2
cao3 jie2 zhong3 zi5 de5 shu1.6 cai4 he2 jie2 guo3 zi5 de5 shu4.2 mu4.1
ge4.1 cong2 qi2 lei4.1 zai4 di4 shang4 de5 guo3 zi5 dou1 bao1 zhe5 he2.6
shi4.1 jiu4 zhei4 yang4 cheng2 le5 yu2 shi4 di4 shang4 zhang3 chu1 le5
qing1.2 cao3 he2 jie2 zhong3 zi5 de5 shu1.6 cai4 ge4.1 cong2 qi2 lei4.1
you4 zhang3 chu1 jie2 guo3 zi5 de5 shu4.2 mu4.1 ge4.1 cong2 qi2 lei4.1
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
de5 zhong4 xiong1 di4.1 xia4 qu4 dao4.1 yi1 ge4 ya4.1 du4.3 lan2 ren2
de5 jia1 li3 ju1 zhu4.1 nei4 ren2 ming2.1 jiao4 xi1.5 la1 you2.2 da4
zai4 nei4
removed 'dat/chin/ptn/gen.1/gud.wfr'
creating the word frequency file dat/chin/ptn/gen.1/gud.wfr
the 10 most common words in dat/chin/ptn/gen.1/gud.tlw:
1746 0.04985 de5
855 0.02441 wo3
807 0.02304 ta1
734 0.02096 ni3
679 0.01939 le5
518 0.01479 zai4
502 0.01433 shi4
481 0.01373 ren2
476 0.01359 yi3.1
473 0.01350 he2
removed 'dat/chin/ptn/gen.1/gud-trunc-wds-summary.tex'
removed 'exp/chin/ptn/gen.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/chin/ptn/gen.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:35 by tex-make-sample-summary.sh
% Token and word counts for chin/ptn/gen.1/gud.wfr
%
\def\chinptntruncgenPBgudTks{35027}
\def\chinptntruncgenPBgudTksPct{98.0}
\def\chinptntruncgenPBgudWds{1380}
\def\chinptntruncgenPBgudWdsPct{3.9}
copied '/tmp/587705.file' -> 'exp/chin/ptn/gen.1/gud-trunc-wds-summary.tex'
removed '/tmp/587705.file'
creating running text file dat/chin/ptn/gen.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/chin/ptn/gen.1/bad.wfr'
creating the word frequency file dat/chin/ptn/gen.1/bad.wfr
the 10 most common words in dat/chin/ptn/gen.1/bad.tlw:
709 1.00000 =
removed 'dat/chin/ptn/gen.1/bad-trunc-wds-summary.tex'
removed 'exp/chin/ptn/gen.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/chin/ptn/gen.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:35 by tex-make-sample-summary.sh
% Token and word counts for chin/ptn/gen.1/bad.wfr
%
\def\chinptntruncgenPBbadTks{709}
\def\chinptntruncgenPBbadTksPct{2.0}
\def\chinptntruncgenPBbadWds{1}
\def\chinptntruncgenPBbadWdsPct{0.0}
copied '/tmp/587749.file' -> 'exp/chin/ptn/gen.1/bad-trunc-wds-summary.tex'
removed '/tmp/587749.file'
... creating word files dat/chin/ptn/exo.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
35725 dat/chin/ptn/exo.1/trunc.tlw
removed 'dat/chin/ptn/exo.1/raw.tlw'
removed 'dat/chin/ptn/exo.1/gud.tlw'
removed 'dat/chin/ptn/exo.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/chin/ptn/exo.1/raw.wdf
sample:
yi3.1 se4 lie4 de5 zhong4 zi5 ge4.1 ren2 dai4.1 zhe5 jia1 juan4.1 he2
ya3 ge4.1 yi1 tong2 lai2 dao4.1 ai1.3 ji2.1 ta1 men5 de5 ming2.1 zi4.1
shi4 liu2.2 ben3 xi1 mian3.5 li4.1 wei4 you2.2 da4 yi3.1 sa4 jia1.11 xi1
bu4.3 lun2.1 bian4 ya3 min3.3 dan4 na2 fu2.14 ta1 li4.1 jia1.11 de2
ya4.1 she4.2 =
ta1 men5 quan2 shi4 ya3 ge4.1 suo3 sheng1 de5 gong4 you3 qi1 shi2.1 ren2
nei4 shi2 yue1 se4.2 yi3 jing1 zai4 ai1.3 ji2.1 le5 =
hou4.1 lai2 yue1 se4.2 he2 ta1 suo3 you3 de5 xiong1 di4.1 yi3.1 ji2.1
nei4 yi1 dai4.3 de5 ren2 dou1 si3 le5 =
yi3.1 se4 lie4 ren2 sheng1 yang3 fan2.2 zhi2.7 zhong4 duo1 ren2 shu4
zeng1 jia1.1 ji2.3 qi2 qiang2 sheng4.2 bian4.1 man3 le5 nei4 di4 =
nei4 shi2 you3 yi1 wei4.1 bu4 ren4 shi5 yue1 se4.2 de5 xin1.1 wang2
xing1 qi3 lai2 tong3 zhi4.2 ai1.3 ji2.1 =
ta1 dui4 zi4 ji3.2 de5 ren2 min2 shuo1 kan4 na3 yi3.1 se4 lie4 min2 bi3
wo3 men5 zhong4 duo1 qiang2 sheng4.2 =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
zhi1.5 de5 gong1.1 ta1 men5 neng2 zuo4.2 ge4.1 zhong3 gong1.1 cheng2.5
ye3 neng2 qiao3.1 she4.2 tu2.1 an4.2 bi3 sa1 lie4 he2 ya4.1 he2.1 li4.1
ya4.1 bo2.1 yi3.1 ji2.1
removed 'dat/chin/ptn/exo.1/raw.wfr'
creating the word frequency file dat/chin/ptn/exo.1/raw.wfr
the 10 most common words in dat/chin/ptn/exo.1/raw.tlw:
1750 0.04899 de5
944 0.02642 ni3
760 0.02127 men5
728 0.02038 he2
698 0.01954 =
684 0.01915 yao4
673 0.01884 ta1
631 0.01766 ren2
547 0.01531 zai4
524 0.01467 wo3
removed 'dat/chin/ptn/exo.1/raw-trunc-wds-summary.tex'
removed 'exp/chin/ptn/exo.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/chin/ptn/exo.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:35 by tex-make-sample-summary.sh
% Token and word counts for chin/ptn/exo.1/raw.wfr
%
\def\chinptntruncexoPBrawTks{35725}
\def\chinptntruncexoPBrawTksPct{100.0}
\def\chinptntruncexoPBrawWds{1440}
\def\chinptntruncexoPBrawWdsPct{4.0}
copied '/tmp/587803.file' -> 'exp/chin/ptn/exo.1/raw-trunc-wds-summary.tex'
removed '/tmp/587803.file'
creating running text file dat/chin/ptn/exo.1/gud.wdf
sample:
yi3.1 se4 lie4 de5 zhong4 zi5 ge4.1 ren2 dai4.1 zhe5 jia1 juan4.1 he2
ya3 ge4.1 yi1 tong2 lai2 dao4.1 ai1.3 ji2.1 ta1 men5 de5 ming2.1 zi4.1
shi4 liu2.2 ben3 xi1 mian3.5 li4.1 wei4 you2.2 da4 yi3.1 sa4 jia1.11 xi1
bu4.3 lun2.1 bian4 ya3 min3.3 dan4 na2 fu2.14 ta1 li4.1 jia1.11 de2
ya4.1 she4.2 ta1 men5 quan2 shi4 ya3 ge4.1 suo3 sheng1 de5 gong4 you3
qi1 shi2.1 ren2 nei4 shi2 yue1 se4.2 yi3 jing1 zai4 ai1.3 ji2.1 le5
hou4.1 lai2 yue1 se4.2 he2 ta1 suo3 you3 de5 xiong1 di4.1 yi3.1 ji2.1
nei4 yi1 dai4.3 de5 ren2 dou1 si3 le5 yi3.1 se4 lie4 ren2 sheng1 yang3
fan2.2 zhi2.7 zhong4 duo1 ren2 shu4 zeng1 jia1.1 ji2.3 qi2 qiang2
sheng4.2 bian4.1 man3 le5 nei4 di4 nei4 shi2 you3 yi1 wei4.1 bu4 ren4
shi5 yue1 se4.2 de5 xin1.1 wang2 xing1 qi3 lai2 tong3 zhi4.2 ai1.3 ji2.1
ta1 dui4 zi4 ji3.2 de5 ren2 min2 shuo1 kan4 na3 yi3.1 se4 lie4 min2 bi3
wo3 men5 zhong4 duo1 qiang2 sheng4.2 lai2 ba5 wo3 men5 yao4 yong4
qiao3.1 ji4.2 dui4 fu4.9 ta1 men5 kong3 pa4 ta1 men5 zeng1 duo1 qi3 lai2
yi1 dan4.3 fa1 sheng1 zhan4.2 zheng1.1 ta1 men5 jiu4 yu3 wo3 men5 de5
chou2.2 di2.2 lian2.2 he2.2 gong1.7 ji1.6 wo3 men5 bing4.1 qie3 li2 kai1
zhei4 di4 yu2 shi4 ta1 men5 zhi3.1 pai4 du1.1 gong1.1 guan3 xia2.4 ta1
men5 jia1.1 zhong4.1 ta1 men5 de5 zhong4.1 dan1.3 ku3 hai4 ta1 men5 ta1
men5 wei2 fa3 lao3 jian4.9 zao4 liang3 zuo4.3 zhu4.7 huo4.2 cheng2.1
jiu4 shi4 bi3 dong1 he2 lan2 sai4 dan4 shi4 ai1.3 ji2.1 ren2 yue4.1 ku3
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
ci4.2 xiu4 de5 gong1.1 yi3.1 ji2.1 bian1.1 zhi1.5 de5 gong1.1 ta1 men5
neng2 zuo4.2 ge4.1 zhong3 gong1.1 cheng2.5 ye3 neng2 qiao3.1 she4.2
tu2.1 an4.2 bi3 sa1 lie4 he2 ya4.1 he2.1 li4.1 ya4.1 bo2.1 yi3.1 ji2.1
removed 'dat/chin/ptn/exo.1/gud.wfr'
creating the word frequency file dat/chin/ptn/exo.1/gud.wfr
the 10 most common words in dat/chin/ptn/exo.1/gud.tlw:
1750 0.04996 de5
944 0.02695 ni3
760 0.02170 men5
728 0.02078 he2
684 0.01953 yao4
673 0.01921 ta1
631 0.01801 ren2
547 0.01562 zai4
524 0.01496 wo3
424 0.01210 yi3.1
removed 'dat/chin/ptn/exo.1/gud-trunc-wds-summary.tex'
removed 'exp/chin/ptn/exo.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/chin/ptn/exo.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:35 by tex-make-sample-summary.sh
% Token and word counts for chin/ptn/exo.1/gud.wfr
%
\def\chinptntruncexoPBgudTks{35027}
\def\chinptntruncexoPBgudTksPct{98.0}
\def\chinptntruncexoPBgudWds{1439}
\def\chinptntruncexoPBgudWdsPct{4.0}
copied '/tmp/587849.file' -> 'exp/chin/ptn/exo.1/gud-trunc-wds-summary.tex'
removed '/tmp/587849.file'
creating running text file dat/chin/ptn/exo.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/chin/ptn/exo.1/bad.wfr'
creating the word frequency file dat/chin/ptn/exo.1/bad.wfr
the 10 most common words in dat/chin/ptn/exo.1/bad.tlw:
698 1.00000 =
removed 'dat/chin/ptn/exo.1/bad-trunc-wds-summary.tex'
removed 'exp/chin/ptn/exo.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/chin/ptn/exo.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:35 by tex-make-sample-summary.sh
% Token and word counts for chin/ptn/exo.1/bad.wfr
%
\def\chinptntruncexoPBbadTks{698}
\def\chinptntruncexoPBbadTksPct{2.0}
\def\chinptntruncexoPBbadWds{1}
\def\chinptntruncexoPBbadWdsPct{0.0}
copied '/tmp/587893.file' -> 'exp/chin/ptn/exo.1/bad-trunc-wds-summary.tex'
removed '/tmp/587893.file'
... creating word files dat/chin/ptn/num.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
35657 dat/chin/ptn/num.1/trunc.tlw
removed 'dat/chin/ptn/num.1/raw.tlw'
removed 'dat/chin/ptn/num.1/gud.tlw'
removed 'dat/chin/ptn/num.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/chin/ptn/num.1/raw.wdf
sample:
yi3.1 se4 lie4 ren2 chu1 ai1.3 ji2.1 di4 yi3.1 hou4.1 di4.2 er4 nian2
er4 yue4 yi1 ri4 ye1 he2 hua2 zai4 xi1 nai4 de5 kuang4.1 ye3.1 zai4 hui4
mu4.4 li3 dui4 mo2.3 xi1 shuo1 ni3 men5 yao4 ba3 yi3.1 se4 lie4 quan2
ti3 hui4 zhong4 an4.1 zhe5 ta1 men5 de5 zong1 zu2.1 fu4.1 jia1 gen1.1
ju4.2 ren2 ming2.1 shu4 mu4 tong3 ji4.2 ren2 kou3 suo3 you3 nan2.1 ding1
dou1 yao4 an4.1 zhe5 ren2 kou3 deng1.1 ji4.1 =
zai4 yi3.1 se4 lie4 zhong1 fan2 shi4 er4 shi2.1 sui4.1 yi3.1 shang4
neng2 chu1 qu4 da3 zhang4.2 de5 ni3 he2 ya4.1 lun2.1 yao4 an4.1 zhe5 ta1
men5 de5 dui4.2 wu3.9 shu4 dian3 ta1 men5 =
mei3 yi1 ge4 zhi1.2 pai4 yao4 you3 yi1 ren2 bang1 zhu4.2 ni3 men5 ta1
men5 mei3 yi1 ge4 dou1 shi4 ta1 fu4.1 jia1 de5 shou3.1 ling3 =
yi3.1 xia4 jiu4 shi4 bang1 zhu4.2 ni3 men5 de5 ren2 de5 ming2.1 zi4.1
shu3 liu2.2 ben3 zhi1.2 pai4 de5 you3 shi4.10 diu1 er3.5 de5 er2 zi5
yi3.1 li4.1 xu5 shu3 xi1 mian3.5 zhi1.2 pai4 de5 you3 su1 li4.1 sha1.2
dai4.3 de5 er2 zi5 shi4.10 lu4 mie4.1 shu3 you2.2 da4 zhi1.2 pai4 de5
you3 ya4.1 mi3 na2 da2.1 de5 er2 zi5 na2 shun4 shu3 yi3.1 sa4 jia1.11
zhi1.2 pai4 de5 you3 su1 ya1.3 de5 er2 zi5 na2 tan3.1 ye4.1 shu3 xi1
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
gong1.7 qu3 de5 di4 shi4 ke3 mu4.10 fang4 sheng1.5 chu4.1 de5 di4 ni3
pu1.1 ren2 ye3 you3 sheng1.5 chu4.1 ta1 men5 you4 shuo1 ru2 guo3 wo3
men5 zai4 ni3 yan3 qian2 meng3 en1 qiu2 ni3 ba3 zhei4 di4 ji3.1 ni3
removed 'dat/chin/ptn/num.1/raw.wfr'
creating the word frequency file dat/chin/ptn/num.1/raw.wfr
the 10 most common words in dat/chin/ptn/num.1/raw.tlw:
2009 0.05634 de5
737 0.02067 men5
695 0.01949 ta1
691 0.01938 ren2
673 0.01887 he2
630 0.01767 =
551 0.01545 shi4
537 0.01506 ni3
511 0.01433 yi3.1
500 0.01402 yi1
removed 'dat/chin/ptn/num.1/raw-trunc-wds-summary.tex'
removed 'exp/chin/ptn/num.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/chin/ptn/num.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:36 by tex-make-sample-summary.sh
% Token and word counts for chin/ptn/num.1/raw.wfr
%
\def\chinptntruncnumPBrawTks{35657}
\def\chinptntruncnumPBrawTksPct{100.0}
\def\chinptntruncnumPBrawWds{1255}
\def\chinptntruncnumPBrawWdsPct{3.5}
copied '/tmp/587947.file' -> 'exp/chin/ptn/num.1/raw-trunc-wds-summary.tex'
removed '/tmp/587947.file'
creating running text file dat/chin/ptn/num.1/gud.wdf
sample:
yi3.1 se4 lie4 ren2 chu1 ai1.3 ji2.1 di4 yi3.1 hou4.1 di4.2 er4 nian2
er4 yue4 yi1 ri4 ye1 he2 hua2 zai4 xi1 nai4 de5 kuang4.1 ye3.1 zai4 hui4
mu4.4 li3 dui4 mo2.3 xi1 shuo1 ni3 men5 yao4 ba3 yi3.1 se4 lie4 quan2
ti3 hui4 zhong4 an4.1 zhe5 ta1 men5 de5 zong1 zu2.1 fu4.1 jia1 gen1.1
ju4.2 ren2 ming2.1 shu4 mu4 tong3 ji4.2 ren2 kou3 suo3 you3 nan2.1 ding1
dou1 yao4 an4.1 zhe5 ren2 kou3 deng1.1 ji4.1 zai4 yi3.1 se4 lie4 zhong1
fan2 shi4 er4 shi2.1 sui4.1 yi3.1 shang4 neng2 chu1 qu4 da3 zhang4.2 de5
ni3 he2 ya4.1 lun2.1 yao4 an4.1 zhe5 ta1 men5 de5 dui4.2 wu3.9 shu4
dian3 ta1 men5 mei3 yi1 ge4 zhi1.2 pai4 yao4 you3 yi1 ren2 bang1 zhu4.2
ni3 men5 ta1 men5 mei3 yi1 ge4 dou1 shi4 ta1 fu4.1 jia1 de5 shou3.1
ling3 yi3.1 xia4 jiu4 shi4 bang1 zhu4.2 ni3 men5 de5 ren2 de5 ming2.1
zi4.1 shu3 liu2.2 ben3 zhi1.2 pai4 de5 you3 shi4.10 diu1 er3.5 de5 er2
zi5 yi3.1 li4.1 xu5 shu3 xi1 mian3.5 zhi1.2 pai4 de5 you3 su1 li4.1
sha1.2 dai4.3 de5 er2 zi5 shi4.10 lu4 mie4.1 shu3 you2.2 da4 zhi1.2 pai4
de5 you3 ya4.1 mi3 na2 da2.1 de5 er2 zi5 na2 shun4 shu3 yi3.1 sa4
jia1.11 zhi1.2 pai4 de5 you3 su1 ya1.3 de5 er2 zi5 na2 tan3.1 ye4.1 shu3
xi1 bu4.3 lun2.1 zhi1.2 pai4 de5 you3 xi1.5 lun2.1 de5 er2 zi5 yi3.1
li4.1 ya1.3 yue1 se4.2 de5 zi5 sun1 zhong1 shu3 yi3.1 fa3 lian2.3 zhi1.2
pai4 de5 you3 ya4.1 mi3 hu1 de5 er2 zi5 yi3.1 li4.1 sha1.2 ma3.1 shu3
ma3.1 na2 xi1 zhi1.2 pai4 de5 you3 bi3 da4 xu5 de5 er2 zi5 jia1.11 ma3.1
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
sheng1.5 chu4.1 de5 di4 ni3 pu1.1 ren2 ye3 you3 sheng1.5 chu4.1 ta1 men5
you4 shuo1 ru2 guo3 wo3 men5 zai4 ni3 yan3 qian2 meng3 en1 qiu2 ni3 ba3
zhei4 di4 ji3.1 ni3
removed 'dat/chin/ptn/num.1/gud.wfr'
creating the word frequency file dat/chin/ptn/num.1/gud.wfr
the 10 most common words in dat/chin/ptn/num.1/gud.tlw:
2009 0.05736 de5
737 0.02104 men5
695 0.01984 ta1
691 0.01973 ren2
673 0.01921 he2
551 0.01573 shi4
537 0.01533 ni3
511 0.01459 yi3.1
500 0.01427 yi1
494 0.01410 yao4
removed 'dat/chin/ptn/num.1/gud-trunc-wds-summary.tex'
removed 'exp/chin/ptn/num.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/chin/ptn/num.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:36 by tex-make-sample-summary.sh
% Token and word counts for chin/ptn/num.1/gud.wfr
%
\def\chinptntruncnumPBgudTks{35027}
\def\chinptntruncnumPBgudTksPct{98.2}
\def\chinptntruncnumPBgudWds{1254}
\def\chinptntruncnumPBgudWdsPct{3.5}
copied '/tmp/587991.file' -> 'exp/chin/ptn/num.1/gud-trunc-wds-summary.tex'
removed '/tmp/587991.file'
creating running text file dat/chin/ptn/num.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/chin/ptn/num.1/bad.wfr'
creating the word frequency file dat/chin/ptn/num.1/bad.wfr
the 10 most common words in dat/chin/ptn/num.1/bad.tlw:
630 1.00000 =
removed 'dat/chin/ptn/num.1/bad-trunc-wds-summary.tex'
removed 'exp/chin/ptn/num.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/chin/ptn/num.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:36 by tex-make-sample-summary.sh
% Token and word counts for chin/ptn/num.1/bad.wfr
%
\def\chinptntruncnumPBbadTks{630}
\def\chinptntruncnumPBbadTksPct{1.8}
\def\chinptntruncnumPBbadWds{1}
\def\chinptntruncnumPBbadWdsPct{0.0}
copied '/tmp/588035.file' -> 'exp/chin/ptn/num.1/bad-trunc-wds-summary.tex'
removed '/tmp/588035.file'
... creating word files dat/chin/ptn/lev.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
29292 dat/chin/ptn/lev.1/trunc.tlw
removed 'dat/chin/ptn/lev.1/raw.tlw'
removed 'dat/chin/ptn/lev.1/gud.tlw'
removed 'dat/chin/ptn/lev.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/chin/ptn/lev.1/raw.wdf
sample:
ye1 he2 hua2 hu1.1 jiao4 mo2.3 xi1 cong2 hui4 mu4.4 li3 dui4 mo2.3 xi1
shuo1 ni3 yao4 gao4 su4 yi3.1 se4 lie4 ren2 shuo1 ru2 guo3 ni3 men5
zhong1 jian1 you3 ren2 ba3 gong1.4 wu4 xian4.4 ji3.1 ye1 he2 hua2 jiu4
yao4 cong2 niu2 qun2.1 yang2.3 qun2.1 zhong1 xian4.4 jia1 chu4.1 wei2
gong1.4 wu4 =
ta1 de5 gong1.4 wu4 ruo4 shi4 xian4.4 niu2 zuo4.2 fan2.6 ji4.4 jiu4 yao4
ba3 yi1 tou2 mei2 you3 can2 ji2.5 de5 gong1 niu2 qian1.2 dao4.1 hui4
mu4.4 men2 kou3 jiu4 ke3 yi3.1 zai4 ye1 he2 hua2 mian4 qian2 meng3
yue4.2 na4 =
ta1 yao4 an4.1 shou3 zai4 fan2.6 ji4.4 sheng1.5 de5 tou2 shang4 fan2.6
ji4.4 jiu4 meng3 yue4.2 na4 ke3 yi3.1 wei2 ta1 shu2.1 zui4 =
ta1 yao4 zai4 ye1 he2 hua2 mian4 qian2 zai3.2 sha1.1 nei4 gong1 niu2
ya4.1 lun2.1 zi5 sun1 zuo4.2 ji4.4 si1.1 de5 yao4 feng4.1 shang4 xue4
po1 zai4 hui4 mu4.4 men2 kou3 ji4.4 tan2.2 de5 si4 zhou1 =
nei4 ren2 yao4 bo1.3 qu4 fan2.6 ji4.4 sheng1.5 de5 pi2 ba3 fan2.6 ji4.4
sheng1.5 qie4 cheng2 kuai4.1 zi5 =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
hui2 yi3.1 shang4 zhei4 xie1 jiu4 shi4 ye1 he2 hua2 zai4 xi1 nai4 shan1
wei2 yi3.1 se4 lie4 ren2 fen1.1 fu4.2 mo2.3 xi1 de5 lü4.1 li4.3 =
removed 'dat/chin/ptn/lev.1/raw.wfr'
creating the word frequency file dat/chin/ptn/lev.1/raw.wfr
the 10 most common words in dat/chin/ptn/lev.1/raw.tlw:
1714 0.05851 de5
639 0.02181 ji4.4
599 0.02045 =
597 0.02038 ni3
593 0.02024 men5
573 0.01956 yao4
534 0.01823 shi4
521 0.01779 ta1
511 0.01745 he2
429 0.01465 zai4
removed 'dat/chin/ptn/lev.1/raw-trunc-wds-summary.tex'
removed 'exp/chin/ptn/lev.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/chin/ptn/lev.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:36 by tex-make-sample-summary.sh
% Token and word counts for chin/ptn/lev.1/raw.wfr
%
\def\chinptntrunclevPBrawTks{29292}
\def\chinptntrunclevPBrawTksPct{100.0}
\def\chinptntrunclevPBrawWds{1170}
\def\chinptntrunclevPBrawWdsPct{4.0}
copied '/tmp/588089.file' -> 'exp/chin/ptn/lev.1/raw-trunc-wds-summary.tex'
removed '/tmp/588089.file'
creating running text file dat/chin/ptn/lev.1/gud.wdf
sample:
ye1 he2 hua2 hu1.1 jiao4 mo2.3 xi1 cong2 hui4 mu4.4 li3 dui4 mo2.3 xi1
shuo1 ni3 yao4 gao4 su4 yi3.1 se4 lie4 ren2 shuo1 ru2 guo3 ni3 men5
zhong1 jian1 you3 ren2 ba3 gong1.4 wu4 xian4.4 ji3.1 ye1 he2 hua2 jiu4
yao4 cong2 niu2 qun2.1 yang2.3 qun2.1 zhong1 xian4.4 jia1 chu4.1 wei2
gong1.4 wu4 ta1 de5 gong1.4 wu4 ruo4 shi4 xian4.4 niu2 zuo4.2 fan2.6
ji4.4 jiu4 yao4 ba3 yi1 tou2 mei2 you3 can2 ji2.5 de5 gong1 niu2 qian1.2
dao4.1 hui4 mu4.4 men2 kou3 jiu4 ke3 yi3.1 zai4 ye1 he2 hua2 mian4 qian2
meng3 yue4.2 na4 ta1 yao4 an4.1 shou3 zai4 fan2.6 ji4.4 sheng1.5 de5
tou2 shang4 fan2.6 ji4.4 jiu4 meng3 yue4.2 na4 ke3 yi3.1 wei2 ta1 shu2.1
zui4 ta1 yao4 zai4 ye1 he2 hua2 mian4 qian2 zai3.2 sha1.1 nei4 gong1
niu2 ya4.1 lun2.1 zi5 sun1 zuo4.2 ji4.4 si1.1 de5 yao4 feng4.1 shang4
xue4 po1 zai4 hui4 mu4.4 men2 kou3 ji4.4 tan2.2 de5 si4 zhou1 nei4 ren2
yao4 bo1.3 qu4 fan2.6 ji4.4 sheng1.5 de5 pi2 ba3 fan2.6 ji4.4 sheng1.5
qie4 cheng2 kuai4.1 zi5 ya4.1 lun2.1 zi5 sun1 zuo4.2 ji4.4 si1.1 de5
yao4 ba3 tan4.2 huo3 fang4 zai4 ji4.4 tan2.2 shang4 ba3 chai2 pai2.1
lie4 zai4 huo3 shang4 ya4.1 lun2.1 zi5 sun1 zuo4.2 ji4.4 si1.1 de5 yao4
ba3 rou4 kuai4.1 he2 tou2 yi3.1 ji2.1 zhi1.4 fang2.3 pai2.1 lie4 zai4
ji4.4 tan2.2 tan4.2 huo3 shang4 de5 mu4.1 chai2 shang4 mian4 nei4 ren2
you4 yao4 yong4 shui3 xi3.1 jing4.2 nei4.1 zang4.2 he2 tui3 ji4.4 si1.1
jiu4 ba3 zhei4 yi1 qie4 quan2 xian4.4 zai4 ji4.4 tan2.2 shang4 fen2
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
huan4.1 de5 dou1 yao4 fen1 bie2 wei2 sheng4.1 bu4 neng2 shu2.1 hui2
yi3.1 shang4 zhei4 xie1 jiu4 shi4 ye1 he2 hua2 zai4 xi1 nai4 shan1 wei2
yi3.1 se4 lie4 ren2 fen1.1 fu4.2 mo2.3 xi1 de5 lü4.1 li4.3
removed 'dat/chin/ptn/lev.1/gud.wfr'
creating the word frequency file dat/chin/ptn/lev.1/gud.wfr
the 10 most common words in dat/chin/ptn/lev.1/gud.tlw:
1714 0.05974 de5
639 0.02227 ji4.4
597 0.02081 ni3
593 0.02067 men5
573 0.01997 yao4
534 0.01861 shi4
521 0.01816 ta1
511 0.01781 he2
429 0.01495 zai4
423 0.01474 bu4
removed 'dat/chin/ptn/lev.1/gud-trunc-wds-summary.tex'
removed 'exp/chin/ptn/lev.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/chin/ptn/lev.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:36 by tex-make-sample-summary.sh
% Token and word counts for chin/ptn/lev.1/gud.wfr
%
\def\chinptntrunclevPBgudTks{28693}
\def\chinptntrunclevPBgudTksPct{98.0}
\def\chinptntrunclevPBgudWds{1169}
\def\chinptntrunclevPBgudWdsPct{4.0}
copied '/tmp/588133.file' -> 'exp/chin/ptn/lev.1/gud-trunc-wds-summary.tex'
removed '/tmp/588133.file'
creating running text file dat/chin/ptn/lev.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/chin/ptn/lev.1/bad.wfr'
creating the word frequency file dat/chin/ptn/lev.1/bad.wfr
the 10 most common words in dat/chin/ptn/lev.1/bad.tlw:
599 1.00000 =
removed 'dat/chin/ptn/lev.1/bad-trunc-wds-summary.tex'
removed 'exp/chin/ptn/lev.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/chin/ptn/lev.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:36 by tex-make-sample-summary.sh
% Token and word counts for chin/ptn/lev.1/bad.wfr
%
\def\chinptntrunclevPBbadTks{599}
\def\chinptntrunclevPBbadTksPct{2.0}
\def\chinptntrunclevPBbadWds{1}
\def\chinptntrunclevPBbadWdsPct{0.0}
copied '/tmp/588177.file' -> 'exp/chin/ptn/lev.1/bad-trunc-wds-summary.tex'
removed '/tmp/588177.file'
... creating word files dat/chin/ptn/deu.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
35627 dat/chin/ptn/deu.1/trunc.tlw
removed 'dat/chin/ptn/deu.1/raw.tlw'
removed 'dat/chin/ptn/deu.1/gud.tlw'
removed 'dat/chin/ptn/deu.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/chin/ptn/deu.1/raw.wdf
sample:
yi3.1 xia4 shi4 mo2.3 xi1 zai4 yue1 dan4.3 he2.5 dong1 de5 kuang4.1
ye3.1 shu1.3 fu2.14 dui4 mian4 de5 ya4.1 la1 ba1.1 jiu4 shi4 zai4 ba1.1
lan2 he2 tuo2 fu2.14 la1 ban1.1 ha1 xi3.1 lu4.3 di3 sa1 ha1 zhi1.1 jian1
xiang4 yi3.1 se4 lie4 ren2 suo3 shuo1 de5 hua4 =
cong2 he2.1 lie4.1 shan1 jing1 guo4 xi1 er3.5 shan1 de5 lu4 dao4.1 da2.1
jia1.1 di1 si1.6 ba1.1 ni2.2 ya4.1 gong4 you3 shi2.1 yi1 tian1 de5 lu4
cheng2.5 =
chu1 ai1.3 ji2.1 yi3.1 hou4.1 di4.2 si4 shi2.1 nian2 shi2.1 yi1 yue4 yi1
ri4 mo2.3 xi1 zhao4 zhe5 ye1 he2 hua2 fen1.1 fu4.2 ta1 yi1 qie4 guan1.1
yu2 yi3.1 se4 lie4 ren2 de5 hua4 dou1 gao4 su4 le5 ta1 men5 =
dang1 shi2 ta1 yi3 jing1 ji1.6 bai4.1 le5 zhu4.1 zai4 xi1.5 shi2.2 ben3
de5 ya4.1 mo2.3 li4.1 ren2 de5 wang2 xi1 hong2.3 he2 zhu4.1 zai4 ya4.1
si1.6 ta1 lu4.3 yu3 yi3.1 de2 lai2 de5 ba1.1 shan1.4 wang2 e4.8 =
mo2.3 xi1 zai4 yue1 dan4.3 he2.5 dong1 de5 mo2.3 ya1.3 di4 kai1 shi3.2
jiang3 jie3.1 zhei4 lü4.1 fa3 shuo1 ye1 he2 hua2 wo3 men5 de5 shen2.1
zai4 he2.1 lie4.1 shan1 gao4 su4 wo3 men5 ni3 men5 zai4 zhei4 shan1
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
lian2.3 he2 ma3.1 na2 xi1 zhi1.1 di4 you2.2 da4 quan2 di4 zhi2 dao4.1
xi1 hai3 nan2.2 di4 he2 nei4 ping2 yuan2 jiu4 shi4 zong1.2 shu4.2
cheng2.1
removed 'dat/chin/ptn/deu.1/raw.wfr'
creating the word frequency file dat/chin/ptn/deu.1/raw.wfr
the 10 most common words in dat/chin/ptn/deu.1/raw.tlw:
2294 0.06439 de5
1916 0.05378 ni3
973 0.02731 men5
861 0.02417 he2
803 0.02254 ta1
600 0.01684 =
566 0.01589 ye1
565 0.01586 zai4
558 0.01566 hua2
513 0.01440 yao4
removed 'dat/chin/ptn/deu.1/raw-trunc-wds-summary.tex'
removed 'exp/chin/ptn/deu.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/chin/ptn/deu.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:36 by tex-make-sample-summary.sh
% Token and word counts for chin/ptn/deu.1/raw.wfr
%
\def\chinptntruncdeuPBrawTks{35627}
\def\chinptntruncdeuPBrawTksPct{100.0}
\def\chinptntruncdeuPBrawWds{1458}
\def\chinptntruncdeuPBrawWdsPct{4.1}
copied '/tmp/588231.file' -> 'exp/chin/ptn/deu.1/raw-trunc-wds-summary.tex'
removed '/tmp/588231.file'
creating running text file dat/chin/ptn/deu.1/gud.wdf
sample:
yi3.1 xia4 shi4 mo2.3 xi1 zai4 yue1 dan4.3 he2.5 dong1 de5 kuang4.1
ye3.1 shu1.3 fu2.14 dui4 mian4 de5 ya4.1 la1 ba1.1 jiu4 shi4 zai4 ba1.1
lan2 he2 tuo2 fu2.14 la1 ban1.1 ha1 xi3.1 lu4.3 di3 sa1 ha1 zhi1.1 jian1
xiang4 yi3.1 se4 lie4 ren2 suo3 shuo1 de5 hua4 cong2 he2.1 lie4.1 shan1
jing1 guo4 xi1 er3.5 shan1 de5 lu4 dao4.1 da2.1 jia1.1 di1 si1.6 ba1.1
ni2.2 ya4.1 gong4 you3 shi2.1 yi1 tian1 de5 lu4 cheng2.5 chu1 ai1.3
ji2.1 yi3.1 hou4.1 di4.2 si4 shi2.1 nian2 shi2.1 yi1 yue4 yi1 ri4 mo2.3
xi1 zhao4 zhe5 ye1 he2 hua2 fen1.1 fu4.2 ta1 yi1 qie4 guan1.1 yu2 yi3.1
se4 lie4 ren2 de5 hua4 dou1 gao4 su4 le5 ta1 men5 dang1 shi2 ta1 yi3
jing1 ji1.6 bai4.1 le5 zhu4.1 zai4 xi1.5 shi2.2 ben3 de5 ya4.1 mo2.3
li4.1 ren2 de5 wang2 xi1 hong2.3 he2 zhu4.1 zai4 ya4.1 si1.6 ta1 lu4.3
yu3 yi3.1 de2 lai2 de5 ba1.1 shan1.4 wang2 e4.8 mo2.3 xi1 zai4 yue1
dan4.3 he2.5 dong1 de5 mo2.3 ya1.3 di4 kai1 shi3.2 jiang3 jie3.1 zhei4
lü4.1 fa3 shuo1 ye1 he2 hua2 wo3 men5 de5 shen2.1 zai4 he2.1 lie4.1
shan1 gao4 su4 wo3 men5 ni3 men5 zai4 zhei4 shan1 shang4 zhu4.1 gou4.1
le5 xian4 zai4 ni3 men5 yao4 zhuan3 hui2 qi3 cheng2.5 dao4.1 ya4.1 mo2.3
li4.1 ren2 de5 shan1 di4 qu4 dao4.1 nei4 xie1 zhu4.1 zai4 ya4.1 la1
ba1.1 shan1 di4 di1 di4 nan2.2 di4 yan2.3 hai3 yi1 dai4.1 jia1.11 nan2.2
ren2 de5 di4 li2.5 ba1.1 nen4 zhi2 dao4.1 da4 he2.5 jiu4 shi4 you4.2 fa1
la1 di3 he2.5 yi1 dai4.1 de5 di4 fang1 qu4 kan4 na3 wo3 ba3 zhei4 di4
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
lie4 zhi2 dao4.1 dan4 na2 fu2.14 ta1 li4.1 quan2 di4 yi3.1 fa3 lian2.3
he2 ma3.1 na2 xi1 zhi1.1 di4 you2.2 da4 quan2 di4 zhi2 dao4.1 xi1 hai3
nan2.2 di4 he2 nei4 ping2 yuan2 jiu4 shi4 zong1.2 shu4.2 cheng2.1
removed 'dat/chin/ptn/deu.1/gud.wfr'
creating the word frequency file dat/chin/ptn/deu.1/gud.wfr
the 10 most common words in dat/chin/ptn/deu.1/gud.tlw:
2294 0.06549 de5
1916 0.05470 ni3
973 0.02778 men5
861 0.02458 he2
803 0.02293 ta1
566 0.01616 ye1
565 0.01613 zai4
558 0.01593 hua2
513 0.01465 yao4
463 0.01322 wo3
removed 'dat/chin/ptn/deu.1/gud-trunc-wds-summary.tex'
removed 'exp/chin/ptn/deu.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/chin/ptn/deu.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:36 by tex-make-sample-summary.sh
% Token and word counts for chin/ptn/deu.1/gud.wfr
%
\def\chinptntruncdeuPBgudTks{35027}
\def\chinptntruncdeuPBgudTksPct{98.3}
\def\chinptntruncdeuPBgudWds{1457}
\def\chinptntruncdeuPBgudWdsPct{4.1}
copied '/tmp/588275.file' -> 'exp/chin/ptn/deu.1/gud-trunc-wds-summary.tex'
removed '/tmp/588275.file'
creating running text file dat/chin/ptn/deu.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/chin/ptn/deu.1/bad.wfr'
creating the word frequency file dat/chin/ptn/deu.1/bad.wfr
the 10 most common words in dat/chin/ptn/deu.1/bad.tlw:
600 1.00000 =
removed 'dat/chin/ptn/deu.1/bad-trunc-wds-summary.tex'
removed 'exp/chin/ptn/deu.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/chin/ptn/deu.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:36 by tex-make-sample-summary.sh
% Token and word counts for chin/ptn/deu.1/bad.wfr
%
\def\chinptntruncdeuPBbadTks{600}
\def\chinptntruncdeuPBbadTksPct{1.7}
\def\chinptntruncdeuPBbadWds{1}
\def\chinptntruncdeuPBbadWdsPct{0.0}
copied '/tmp/588319.file' -> 'exp/chin/ptn/deu.1/bad-trunc-wds-summary.tex'
removed '/tmp/588319.file'
... creating word files dat/chin/ptn/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
35720 dat/chin/ptn/tot.1/trunc.tlw
removed 'dat/chin/ptn/tot.1/raw.tlw'
removed 'dat/chin/ptn/tot.1/gud.tlw'
removed 'dat/chin/ptn/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/chin/ptn/tot.1/raw.wdf
sample:
qi3 chu1.1 shen2.1 chuang4 zao4 tian1 di4 =
di4 shi4 kong1 xu1.1 hun4 dun4.5 shen1.1 yuan1.2 shang4 yi1 pian4 hei1
an4 shen2.1 de5 ling2.1 yun4.1 xing2 zai4 shui3 mian4 shang4 =
shen2.1 shuo1 yao4 you3 guang1 jiu4 you3 le5 guang1 =
shen2.1 kan4 guang1 shi4 hao3 de5 ta1 jiu4 ba3 guang1 an4 fen1 kai1 le5
=
shen2.1 cheng1 guang1 wei2 zhou4.1 cheng1 an4 wei2 ye4 you3 wan3 shang4
you3 zao3 chen2.5 zhei4 shi4 di4.2 yi1 ri4 =
shen2.1 shuo1 zhong4 shui3 zhi1.1 jian1 yao4 you3 qiong2.3 cang1 ba3
shui3 he2 shui3 fen1 kai1 shi4.1 jiu4 zhei4 yang4 cheng2 le5 =
shen2.1 zao4 le5 qiong2.3 cang1 ba3 qiong2.3 cang1 yi3.1 xia4 de5 shui3
he2 qiong2.3 cang1 yi3.1 shang4 de5 shui3 fen1 kai1 le5 =
shen2.1 cheng1 qiong2.3 cang1 wei2 tian1 you3 wan3 shang4 you3 zao3
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
bu4 ke3 wang4.3 cheng1 ye1 he2 hua2 ni3 shen2.1 de5 ming2.1 yin1 wei2
wang4.3 cheng1 ye1 he2 hua2 de5 ming2.1 de5 ye1 he2 hua2
removed 'dat/chin/ptn/tot.1/raw.wfr'
creating the word frequency file dat/chin/ptn/tot.1/raw.wfr
the 10 most common words in dat/chin/ptn/tot.1/raw.tlw:
1999 0.05596 de5
724 0.02027 ta1
705 0.01974 men5
697 0.01951 he2
693 0.01940 =
661 0.01851 ni3
627 0.01755 ren2
530 0.01484 zai4
512 0.01433 shi4
481 0.01347 yao4
removed 'dat/chin/ptn/tot.1/raw-trunc-wds-summary.tex'
removed 'exp/chin/ptn/tot.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/chin/ptn/tot.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:36 by tex-make-sample-summary.sh
% Token and word counts for chin/ptn/tot.1/raw.wfr
%
\def\chinptntrunctotPBrawTks{35720}
\def\chinptntrunctotPBrawTksPct{100.0}
\def\chinptntrunctotPBrawWds{1406}
\def\chinptntrunctotPBrawWdsPct{3.9}
copied '/tmp/588373.file' -> 'exp/chin/ptn/tot.1/raw-trunc-wds-summary.tex'
removed '/tmp/588373.file'
creating running text file dat/chin/ptn/tot.1/gud.wdf
sample:
qi3 chu1.1 shen2.1 chuang4 zao4 tian1 di4 di4 shi4 kong1 xu1.1 hun4
dun4.5 shen1.1 yuan1.2 shang4 yi1 pian4 hei1 an4 shen2.1 de5 ling2.1
yun4.1 xing2 zai4 shui3 mian4 shang4 shen2.1 shuo1 yao4 you3 guang1 jiu4
you3 le5 guang1 shen2.1 kan4 guang1 shi4 hao3 de5 ta1 jiu4 ba3 guang1
an4 fen1 kai1 le5 shen2.1 cheng1 guang1 wei2 zhou4.1 cheng1 an4 wei2 ye4
you3 wan3 shang4 you3 zao3 chen2.5 zhei4 shi4 di4.2 yi1 ri4 shen2.1
shuo1 zhong4 shui3 zhi1.1 jian1 yao4 you3 qiong2.3 cang1 ba3 shui3 he2
shui3 fen1 kai1 shi4.1 jiu4 zhei4 yang4 cheng2 le5 shen2.1 zao4 le5
qiong2.3 cang1 ba3 qiong2.3 cang1 yi3.1 xia4 de5 shui3 he2 qiong2.3
cang1 yi3.1 shang4 de5 shui3 fen1 kai1 le5 shen2.1 cheng1 qiong2.3 cang1
wei2 tian1 you3 wan3 shang4 you3 zao3 chen2.5 zhei4 shi4 di4.2 er4 ri4
shen2.1 shuo1 tian1 xia4 de5 shui3 yao4 ju4.3 zai4 yi1 chu3 shi3 han4.4
di4 lu4.1 chu1 lai2 shi4.1 jiu4 zhei4 yang4 cheng2 le5 shen2.1 cheng1
han4.4 di4 wei2 di4 cheng1 shui3 de5 ju4.3 chu3 wei2 hai3 shen2.1 kan4
zhei4 shi4 hao3 de5 shen2.1 shuo1 di4 shang4 yao4 zhang3 chu1 qing1.2
cao3 jie2 zhong3 zi5 de5 shu1.6 cai4 he2 jie2 guo3 zi5 de5 shu4.2 mu4.1
ge4.1 cong2 qi2 lei4.1 zai4 di4 shang4 de5 guo3 zi5 dou1 bao1 zhe5 he2.6
shi4.1 jiu4 zhei4 yang4 cheng2 le5 yu2 shi4 di4 shang4 zhang3 chu1 le5
qing1.2 cao3 he2 jie2 zhong3 zi5 de5 shu1.6 cai4 ge4.1 cong2 qi2 lei4.1
you4 zhang3 chu1 jie2 guo3 zi5 de5 shu4.2 mu4.1 ge4.1 cong2 qi2 lei4.1
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
zhi2 dao4.1 qian1 dai4.3 bu4 ke3 wang4.3 cheng1 ye1 he2 hua2 ni3 shen2.1
de5 ming2.1 yin1 wei2 wang4.3 cheng1 ye1 he2 hua2 de5 ming2.1 de5 ye1
he2 hua2
removed 'dat/chin/ptn/tot.1/gud.wfr'
creating the word frequency file dat/chin/ptn/tot.1/gud.wfr
the 10 most common words in dat/chin/ptn/tot.1/gud.tlw:
1999 0.05707 de5
724 0.02067 ta1
705 0.02013 men5
697 0.01990 he2
661 0.01887 ni3
627 0.01790 ren2
530 0.01513 zai4
512 0.01462 shi4
481 0.01373 yao4
475 0.01356 le5
removed 'dat/chin/ptn/tot.1/gud-trunc-wds-summary.tex'
removed 'exp/chin/ptn/tot.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/chin/ptn/tot.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:36 by tex-make-sample-summary.sh
% Token and word counts for chin/ptn/tot.1/gud.wfr
%
\def\chinptntrunctotPBgudTks{35027}
\def\chinptntrunctotPBgudTksPct{98.1}
\def\chinptntrunctotPBgudWds{1405}
\def\chinptntrunctotPBgudWdsPct{3.9}
copied '/tmp/588417.file' -> 'exp/chin/ptn/tot.1/gud-trunc-wds-summary.tex'
removed '/tmp/588417.file'
creating running text file dat/chin/ptn/tot.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/chin/ptn/tot.1/bad.wfr'
creating the word frequency file dat/chin/ptn/tot.1/bad.wfr
the 10 most common words in dat/chin/ptn/tot.1/bad.tlw:
693 1.00000 =
removed 'dat/chin/ptn/tot.1/bad-trunc-wds-summary.tex'
removed 'exp/chin/ptn/tot.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/chin/ptn/tot.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:36 by tex-make-sample-summary.sh
% Token and word counts for chin/ptn/tot.1/bad.wfr
%
\def\chinptntrunctotPBbadTks{693}
\def\chinptntrunctotPBbadTksPct{1.9}
\def\chinptntrunctotPBbadWds{1}
\def\chinptntrunctotPBbadWdsPct{0.0}
copied '/tmp/588461.file' -> 'exp/chin/ptn/tot.1/bad-trunc-wds-summary.tex'
removed '/tmp/588461.file'
lines words bytes file
------- ------- --------- ------------
1381 4143 30649 dat/chin/ptn/gen.1/raw.wfr
1440 4320 32024 dat/chin/ptn/exo.1/raw.wfr
1255 3765 27820 dat/chin/ptn/num.1/raw.wfr
1170 3510 25967 dat/chin/ptn/lev.1/raw.wfr
1458 4374 32434 dat/chin/ptn/deu.1/raw.wfr
1406 4218 31245 dat/chin/ptn/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
1380 4140 30631 dat/chin/ptn/gen.1/gud.wfr
1439 4317 32006 dat/chin/ptn/exo.1/gud.wfr
1254 3762 27802 dat/chin/ptn/num.1/gud.wfr
1169 3507 25949 dat/chin/ptn/lev.1/gud.wfr
1457 4371 32416 dat/chin/ptn/deu.1/gud.wfr
1405 4215 31227 dat/chin/ptn/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
1 3 18 dat/chin/ptn/gen.1/bad.wfr
1 3 18 dat/chin/ptn/exo.1/bad.wfr
1 3 18 dat/chin/ptn/num.1/bad.wfr
1 3 18 dat/chin/ptn/lev.1/bad.wfr
1 3 18 dat/chin/ptn/deu.1/bad.wfr
1 3 18 dat/chin/ptn/tot.1/bad.wfr
gen.1 raw = 35736 gud = 35027 bad = 709
exo.1 raw = 35725 gud = 35027 bad = 698
num.1 raw = 35657 gud = 35027 bad = 630
lev.1 raw = 29292 gud = 28693 bad = 599
deu.1 raw = 35627 gud = 35027 bad = 600
tot.1 raw = 35720 gud = 35027 bad = 693
=== creating the derived word files dat/chin/red/*/{raw,gud,bad}.{tlw,wdf,wfr} (trunc) ===
... creating word files dat/chin/red/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
35263 dat/chin/red/tot.1/trunc.tlw
removed 'dat/chin/red/tot.1/raw.tlw'
removed 'dat/chin/red/tot.1/gud.tlw'
removed 'dat/chin/red/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/chin/red/tot.1/raw.wdf
sample:
ci3 kai1 juan3 di4.2 yi1 hui2 ye3 zuo4.2 zhe3 zi4 yun2 yin1 ceng2 li4.4
guo4 yi1 fan1 meng4 huan4.2 zhi1.1 hou4 gu4 jiang1 zhen1 shi4.1 yin3.1
qu4 er2.1 jie4 tong1 ling2.1 zhi1.1 shuo1 zhuan4.2 ci3 shi2.3 tou2 ji4.1
yi1 shu1 ye3 gu4 yue1.1 zhen1.2 shi4.5 yin3.1 yun2 yun2 dan4 shu1 zhong1
suo3 ji4.1 he2.1 shi4.1 he2.1 ren2 zi4 you4 yun2 jin1 feng1 chen2 liu4.1
liu4.1 yi1 shi4.1 wu2 cheng2 hu1 nian4 ji2.1 dang1 ri4 suo3 you3 zhi1.1
nü3 zi5 yi1 yi1 xi4 kao3 jiao4.3 qu4 jue2 qi2 xing2 zhi3.3 jian4 shi5
jie1.1 chu1 yu2 wo3 zhi1.1 shang4 he2.1 wo3 tang2 tang2 xu1 mei2.1
cheng2.6 bu4 ruo4 bi3.2 qun2 chai1 wo3 shi2.2 kui4 ze2 you3 yu2.1 hui3
yi4.1 wu2 yi4.5 zhen1 da4 wu2 ke3 ru2 he2.1 zhi1.1 ri4 ye3 dang1 ci3 ri4
yu4.1 jiang1 yi3 wang3 suo3 lai4 tian1 en1 zu3 de2.1 jin3.2 yi1.1 wan2.1
ku4 zhi1.1 shi2 yu4.20 gan1.2 yan4.3 fei2 zhi1.1 ri4 bei4.2 fu4.1 xiong1
jiao4.1 yu4.11 zhi1.1 en1 fu4.4 shi1.2 you3.1 gui1.1 tan2 zhi1.1 de2.1
yi3.1 zhi4.1 jin1 ri4 yi1 ji4.12 wu2 cheng2 ban4 sheng1 liao3.1 dao3
zhi1.1 zui4 bian1.1 shu4.4 yi1 ji2.7 yi3.1 gao4 tian1 xia4 zhi1 wo3
zhi1.1 zui4 gu4.2 bu4 mian3 ran2 gui1.2 ge2.1 zhong1 ben3 zi4 li4.4
li4.4 you3 ren2 wan4 bu4 ke3 yin1 wo3 zhi1.1 bu4 xiao4.3 zi4 hu4.1 qi2
duan3 yi1 bing4.1 shi3 qi2 min3.4 mie4 ye3 sui1 jin1 ri4 mao2.1 chuan2.3
peng2.2 you3.3 wa3 zao4.4 sheng2 chuang2 bing4.1 bu4 zu2 fang2.1 wo3
jin1.5 huai2 kuang4 nei4 chen2.5 feng1 xi1.4 yue4 jie1.4 liu3 ting2.2
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
yi1 shi2 zhou1 rui4 jia1 de5 chuan2 le5 yi1 zhuo1 ke4.1 fan4 lai2 bai3.1
zai4 dong1 bian1 wu1 nei4.1 guo4 lai2 dai4.1 le5 liu2.1
removed 'dat/chin/red/tot.1/raw.wfr'
creating the word frequency file dat/chin/red/tot.1/raw.wfr
the 10 most common words in dat/chin/red/tot.1/raw.tlw:
659 0.01869 le5
650 0.01843 yi1
586 0.01662 bu4
483 0.01370 ren2
471 0.01336 de5
386 0.01095 lai2
378 0.01072 zhi1.1
376 0.01066 shi4
339 0.00961 dao4
327 0.00927 you3
removed 'dat/chin/red/tot.1/raw-trunc-wds-summary.tex'
removed 'exp/chin/red/tot.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/chin/red/tot.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:37 by tex-make-sample-summary.sh
% Token and word counts for chin/red/tot.1/raw.wfr
%
\def\chinredtrunctotPBrawTks{35263}
\def\chinredtrunctotPBrawTksPct{100.0}
\def\chinredtrunctotPBrawWds{2421}
\def\chinredtrunctotPBrawWdsPct{6.9}
copied '/tmp/588631.file' -> 'exp/chin/red/tot.1/raw-trunc-wds-summary.tex'
removed '/tmp/588631.file'
creating running text file dat/chin/red/tot.1/gud.wdf
sample:
ci3 kai1 juan3 di4.2 yi1 hui2 ye3 zuo4.2 zhe3 zi4 yun2 yin1 ceng2 li4.4
guo4 yi1 fan1 meng4 huan4.2 zhi1.1 hou4 gu4 jiang1 zhen1 shi4.1 yin3.1
qu4 er2.1 jie4 tong1 ling2.1 zhi1.1 shuo1 zhuan4.2 ci3 shi2.3 tou2 ji4.1
yi1 shu1 ye3 gu4 yue1.1 zhen1.2 shi4.5 yin3.1 yun2 yun2 dan4 shu1 zhong1
suo3 ji4.1 he2.1 shi4.1 he2.1 ren2 zi4 you4 yun2 jin1 feng1 chen2 liu4.1
liu4.1 yi1 shi4.1 wu2 cheng2 hu1 nian4 ji2.1 dang1 ri4 suo3 you3 zhi1.1
nü3 zi5 yi1 yi1 xi4 kao3 jiao4.3 qu4 jue2 qi2 xing2 zhi3.3 jian4 shi5
jie1.1 chu1 yu2 wo3 zhi1.1 shang4 he2.1 wo3 tang2 tang2 xu1 mei2.1
cheng2.6 bu4 ruo4 bi3.2 qun2 chai1 wo3 shi2.2 kui4 ze2 you3 yu2.1 hui3
yi4.1 wu2 yi4.5 zhen1 da4 wu2 ke3 ru2 he2.1 zhi1.1 ri4 ye3 dang1 ci3 ri4
yu4.1 jiang1 yi3 wang3 suo3 lai4 tian1 en1 zu3 de2.1 jin3.2 yi1.1 wan2.1
ku4 zhi1.1 shi2 yu4.20 gan1.2 yan4.3 fei2 zhi1.1 ri4 bei4.2 fu4.1 xiong1
jiao4.1 yu4.11 zhi1.1 en1 fu4.4 shi1.2 you3.1 gui1.1 tan2 zhi1.1 de2.1
yi3.1 zhi4.1 jin1 ri4 yi1 ji4.12 wu2 cheng2 ban4 sheng1 liao3.1 dao3
zhi1.1 zui4 bian1.1 shu4.4 yi1 ji2.7 yi3.1 gao4 tian1 xia4 zhi1 wo3
zhi1.1 zui4 gu4.2 bu4 mian3 ran2 gui1.2 ge2.1 zhong1 ben3 zi4 li4.4
li4.4 you3 ren2 wan4 bu4 ke3 yin1 wo3 zhi1.1 bu4 xiao4.3 zi4 hu4.1 qi2
duan3 yi1 bing4.1 shi3 qi2 min3.4 mie4 ye3 sui1 jin1 ri4 mao2.1 chuan2.3
peng2.2 you3.3 wa3 zao4.4 sheng2 chuang2 bing4.1 bu4 zu2 fang2.1 wo3
jin1.5 huai2 kuang4 nei4 chen2.5 feng1 xi1.4 yue4 jie1.4 liu3 ting2.2
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
lie3 feng4 jie3 ting1 shuo1 mang2 ming4 kuai4 chuan2 fan4 lai2 yi1 shi2
zhou1 rui4 jia1 de5 chuan2 le5 yi1 zhuo1 ke4.1 fan4 lai2 bai3.1 zai4
dong1 bian1 wu1 nei4.1 guo4 lai2 dai4.1 le5 liu2.1
removed 'dat/chin/red/tot.1/gud.wfr'
creating the word frequency file dat/chin/red/tot.1/gud.wfr
the 10 most common words in dat/chin/red/tot.1/gud.tlw:
659 0.01881 le5
650 0.01856 yi1
586 0.01673 bu4
483 0.01379 ren2
471 0.01345 de5
386 0.01102 lai2
378 0.01079 zhi1.1
376 0.01073 shi4
339 0.00968 dao4
327 0.00934 you3
removed 'dat/chin/red/tot.1/gud-trunc-wds-summary.tex'
removed 'exp/chin/red/tot.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/chin/red/tot.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:37 by tex-make-sample-summary.sh
% Token and word counts for chin/red/tot.1/gud.wfr
%
\def\chinredtrunctotPBgudTks{35027}
\def\chinredtrunctotPBgudTksPct{99.3}
\def\chinredtrunctotPBgudWds{2420}
\def\chinredtrunctotPBgudWdsPct{6.9}
copied '/tmp/588675.file' -> 'exp/chin/red/tot.1/gud-trunc-wds-summary.tex'
removed '/tmp/588675.file'
creating running text file dat/chin/red/tot.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/chin/red/tot.1/bad.wfr'
creating the word frequency file dat/chin/red/tot.1/bad.wfr
the 10 most common words in dat/chin/red/tot.1/bad.tlw:
236 1.00000 =
removed 'dat/chin/red/tot.1/bad-trunc-wds-summary.tex'
removed 'exp/chin/red/tot.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/chin/red/tot.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:37 by tex-make-sample-summary.sh
% Token and word counts for chin/red/tot.1/bad.wfr
%
\def\chinredtrunctotPBbadTks{236}
\def\chinredtrunctotPBbadTksPct{0.7}
\def\chinredtrunctotPBbadWds{1}
\def\chinredtrunctotPBbadWdsPct{0.0}
copied '/tmp/588719.file' -> 'exp/chin/red/tot.1/bad-trunc-wds-summary.tex'
removed '/tmp/588719.file'
lines words bytes file
------- ------- --------- ------------
2421 7263 54200 dat/chin/red/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
2420 7260 54182 dat/chin/red/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
1 3 18 dat/chin/red/tot.1/bad.wfr
tot.1 raw = 35263 gud = 35027 bad = 236
=== creating the derived word files dat/chin/voa/*/{raw,gud,bad}.{tlw,wdf,wfr} (trunc) ===
... creating word files dat/chin/voa/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
35691 dat/chin/voa/tot.1/trunc.tlw
removed 'dat/chin/voa/tot.1/raw.tlw'
removed 'dat/chin/voa/tot.1/gud.tlw'
removed 'dat/chin/voa/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/chin/voa/tot.1/raw.wdf
sample:
ge4.1 wei4.1 ting1 zhong4 mei3.1 guo2 zheng4.1 fu3 jue2.2 ding4 jin4 yi1
bu4.1 dong4.2 jie2 mei3.1 guo2 jin4 chu1 kou3 yin2 xing2 xiang4 can1 yu3
zhong1 guo2 xiang4.3 mu4 de5 mei3.1 guo2 gong1 si1.1 ti2 gong1.4 de5
dai4.7 kuan3 zhong1 guo2 biao3 shi4.10 zhei4 xiang4.3 jue2.2 ding4
jiang1 you3 sun3 liang3 guo2 de5 mao4.4 yi4.3 guan1.1 xi5.1 yi3.1 ji2.1
mei3.1 guo2 gong1.1 shang1.1 jie4.1 zai4 zhong1 guo2 de5 li4.1 yi4.5
bing4.1 yao4 qiu2 mei3.1 guo2 gai3 bian4.2 zhei4 ge4 jue2.2 ding4 =
mei3.1 guo2 qing2 bao4.1 zhuan1 jia1 biao3 shi4.10 bei3 jing1.2 xiang4
ba1.1 ji1.7 si1.6 tan3.1 chu1 shou4.6 le5 ke3 yi3.1 zhi4.4 zao4 he2.6
wu3.2 qi4.1 de5 he2.6 cai2.2 liao4 mei3.1 guo2 fa3 lü4.1 jin4.2 zhi3.3
xiang4 ren4.1 he2.1 bang1 zhu4.2 qi2 ta1 guo2 jia1 fa1 zhan3.1 he2.6
wu3.2 qi4.1 de5 guo2 jia1 ti2 gong1.4 dai4.7 kuan3 huo4 dai4.7 kuan3
dan1.3 bao3.1 lu4 tou4 she4.4 bao4.1 dao4 shuo1 zai4 mei3.1 guo2 ke3
neng2 cai3.1 qu3 de5 dui4 zhong1 guo2 de5 cheng2.11 fa2 xing4 cuo4.1
shi1.3 dang1 zhong1 qu3 xiao1.1 jin4 chu1 kou3 yin2 xing2 yu3 zhong1
guo2 de5 he2.2 zuo4.2 ye3 bao1 kuo4.1 zai4 nei4.1 ju4.2 fa3 xin1.1
she4.4 bao4.1 dao4 mei3.1 guo2 jin4 chu1 kou3 yin2 xing2 shi4 zai4 jin1
nian2 er4 yue4 ying1 mei3.1 guo2 guo2 wu4.2 qing1.3 ke4.3 li3 si1.6 tuo1
fu2.14 de5 yao4 qiu2 zai4 san1 shi2.1 tian1 zhi1.1 nei4.1 zan4 shi2
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
yu4.13 de5 guan1 yuan2.5 jing1 chang2 gu3.1 li4.17 fan4.1 ren2 ou1.1 da3
fan4.1 ren2 te4 bie2 shi4 zheng4.1 zhi4.2 fan4.1 zheng4 shi4.13 kang4.1
yi4.2 hen3
removed 'dat/chin/voa/tot.1/raw.wfr'
creating the word frequency file dat/chin/voa/tot.1/raw.wfr
the 10 most common words in dat/chin/voa/tot.1/raw.tlw:
1456 0.04079 de5
1096 0.03071 guo2
665 0.01863 zhong1
468 0.01311 zai4
392 0.01098 yi1
387 0.01084 ren2
348 0.00975 mei3.1
344 0.00964 shi4
316 0.00885 =
295 0.00827 you3
removed 'dat/chin/voa/tot.1/raw-trunc-wds-summary.tex'
removed 'exp/chin/voa/tot.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/chin/voa/tot.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:37 by tex-make-sample-summary.sh
% Token and word counts for chin/voa/tot.1/raw.wfr
%
\def\chinvoatrunctotPBrawTks{35691}
\def\chinvoatrunctotPBrawTksPct{100.0}
\def\chinvoatrunctotPBrawWds{1674}
\def\chinvoatrunctotPBrawWdsPct{4.7}
copied '/tmp/588814.file' -> 'exp/chin/voa/tot.1/raw-trunc-wds-summary.tex'
removed '/tmp/588814.file'
creating running text file dat/chin/voa/tot.1/gud.wdf
sample:
ge4.1 wei4.1 ting1 zhong4 mei3.1 guo2 zheng4.1 fu3 jue2.2 ding4 jin4 yi1
bu4.1 dong4.2 jie2 mei3.1 guo2 jin4 chu1 kou3 yin2 xing2 xiang4 can1 yu3
zhong1 guo2 xiang4.3 mu4 de5 mei3.1 guo2 gong1 si1.1 ti2 gong1.4 de5
dai4.7 kuan3 zhong1 guo2 biao3 shi4.10 zhei4 xiang4.3 jue2.2 ding4
jiang1 you3 sun3 liang3 guo2 de5 mao4.4 yi4.3 guan1.1 xi5.1 yi3.1 ji2.1
mei3.1 guo2 gong1.1 shang1.1 jie4.1 zai4 zhong1 guo2 de5 li4.1 yi4.5
bing4.1 yao4 qiu2 mei3.1 guo2 gai3 bian4.2 zhei4 ge4 jue2.2 ding4 mei3.1
guo2 qing2 bao4.1 zhuan1 jia1 biao3 shi4.10 bei3 jing1.2 xiang4 ba1.1
ji1.7 si1.6 tan3.1 chu1 shou4.6 le5 ke3 yi3.1 zhi4.4 zao4 he2.6 wu3.2
qi4.1 de5 he2.6 cai2.2 liao4 mei3.1 guo2 fa3 lü4.1 jin4.2 zhi3.3 xiang4
ren4.1 he2.1 bang1 zhu4.2 qi2 ta1 guo2 jia1 fa1 zhan3.1 he2.6 wu3.2
qi4.1 de5 guo2 jia1 ti2 gong1.4 dai4.7 kuan3 huo4 dai4.7 kuan3 dan1.3
bao3.1 lu4 tou4 she4.4 bao4.1 dao4 shuo1 zai4 mei3.1 guo2 ke3 neng2
cai3.1 qu3 de5 dui4 zhong1 guo2 de5 cheng2.11 fa2 xing4 cuo4.1 shi1.3
dang1 zhong1 qu3 xiao1.1 jin4 chu1 kou3 yin2 xing2 yu3 zhong1 guo2 de5
he2.2 zuo4.2 ye3 bao1 kuo4.1 zai4 nei4.1 ju4.2 fa3 xin1.1 she4.4 bao4.1
dao4 mei3.1 guo2 jin4 chu1 kou3 yin2 xing2 shi4 zai4 jin1 nian2 er4 yue4
ying1 mei3.1 guo2 guo2 wu4.2 qing1.3 ke4.3 li3 si1.6 tuo1 fu2.14 de5
yao4 qiu2 zai4 san1 shi2.1 tian1 zhi1.1 nei4.1 zan4 shi2 dong4.2 jie2
le5 ji3.1 zhong1 guo2 de5 xiang4.3 mu4 ti2 gong1.4 dai4.7 kuan3 fa3
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
huo2 dong4 ren2 shi4.5 shuo1 jian1.1 yu4.13 de5 guan1 yuan2.5 jing1
chang2 gu3.1 li4.17 fan4.1 ren2 ou1.1 da3 fan4.1 ren2 te4 bie2 shi4
zheng4.1 zhi4.2 fan4.1 zheng4 shi4.13 kang4.1 yi4.2 hen3
removed 'dat/chin/voa/tot.1/gud.wfr'
creating the word frequency file dat/chin/voa/tot.1/gud.wfr
the 10 most common words in dat/chin/voa/tot.1/gud.tlw:
1456 0.04157 de5
1096 0.03129 guo2
665 0.01899 zhong1
468 0.01336 zai4
392 0.01119 yi1
387 0.01105 ren2
348 0.00994 mei3.1
344 0.00982 shi4
295 0.00842 you3
275 0.00785 shuo1
removed 'dat/chin/voa/tot.1/gud-trunc-wds-summary.tex'
removed 'exp/chin/voa/tot.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/chin/voa/tot.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:37 by tex-make-sample-summary.sh
% Token and word counts for chin/voa/tot.1/gud.wfr
%
\def\chinvoatrunctotPBgudTks{35027}
\def\chinvoatrunctotPBgudTksPct{98.1}
\def\chinvoatrunctotPBgudWds{1616}
\def\chinvoatrunctotPBgudWdsPct{4.5}
copied '/tmp/588858.file' -> 'exp/chin/voa/tot.1/gud-trunc-wds-summary.tex'
removed '/tmp/588858.file'
creating running text file dat/chin/voa/tot.1/bad.wdf
sample:
=
=
=
=
=
1 9 9 5 =
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/chin/voa/tot.1/bad.wfr'
creating the word frequency file dat/chin/voa/tot.1/bad.wfr
the 10 most common words in dat/chin/voa/tot.1/bad.tlw:
316 0.47590 =
100 0.15060 9
63 0.09488 1
17 0.02560 0
16 0.02410 7
15 0.02259 8
14 0.02108 5
13 0.01958 6
11 0.01657 2
10 0.01506 3
removed 'dat/chin/voa/tot.1/bad-trunc-wds-summary.tex'
removed 'exp/chin/voa/tot.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/chin/voa/tot.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:37 by tex-make-sample-summary.sh
% Token and word counts for chin/voa/tot.1/bad.wfr
%
\def\chinvoatrunctotPBbadTks{664}
\def\chinvoatrunctotPBbadTksPct{1.9}
\def\chinvoatrunctotPBbadWds{58}
\def\chinvoatrunctotPBbadWdsPct{0.2}
copied '/tmp/588902.file' -> 'exp/chin/voa/tot.1/bad-trunc-wds-summary.tex'
removed '/tmp/588902.file'
lines words bytes file
------- ------- --------- ------------
1674 5022 37234 dat/chin/voa/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
1616 4848 36128 dat/chin/voa/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
58 174 1106 dat/chin/voa/tot.1/bad.wfr
tot.1 raw = 35691 gud = 35027 bad = 664
=== creating the derived word files dat/chip/voa/*/{raw,gud,bad}.{tlw,wdf,wfr} (trunc) ===
... creating word files dat/chip/voa/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
35342 dat/chip/voa/tot.1/trunc.tlw
removed 'dat/chip/voa/tot.1/raw.tlw'
removed 'dat/chip/voa/tot.1/gud.tlw'
removed 'dat/chip/voa/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/chip/voa/tot.1/raw.wdf
sample:
ge4 wei4 ting1 zhong4 mei3 guo2 zheng4 fu3 jue2 ding4 jin4 yi1 bu4 dong4
jie2 mei3 guo2 jin4 chu1 kou3 yin2 hang2 xiang4 can1 yu4 zhong1 guo2
xiang4 mu4 de5 mei3 guo2 gong1 si1 ti2 gong1 de5 dai4 kuan3 zhong1 guo2
biao3 shi4 zhei4 xiang4 jue2 ding4 jiang1 you3 sun3 liang3 guo2 de5 mao4
yi4 guan1 xi5 yi3 ji2 mei3 guo2 gong1 shang1 jie4 zai4 zhong1 guo2 de5
li4 yi4 bing4 yao1 qiu2 mei3 guo2 gai3 bian4 zhei4 ge4 jue2 ding4 =
mei3 guo2 qing2 bao4 zhuan1 jia1 biao3 shi4 bei3 jing1 xiang4 ba1 ji1
si1 tan3 chu1 shou4 le5 ke3 yi3 zhi4 zao4 he2 wu3 qi4 de5 he2 cai2 liao4
mei3 guo2 fa3 lü4 jin4 zhi3 xiang4 ren4 he2 bang1 zhu4 qi2 ta1 guo2 jia1
fa1 zhan3 he2 wu3 qi4 de5 guo2 jia1 ti2 gong1 dai4 kuan3 huo4 dai4 kuan3
dan1 bao3 lu4 tou4 she4 bao4 dao4 shuo1 zai4 mei3 guo2 ke3 neng2 cai3
qu3 de5 dui4 zhong1 guo2 de5 cheng2 fa2 xing4 cuo4 shi1 dang1 zhong1 qu3
xiao1 jin4 chu1 kou3 yin2 hang2 yu3 zhong1 guo2 de5 he2 zuo4 ye3 bao1
kuo4 zai4 nei4 ju4 fa3 xin1 she4 bao4 dao4 mei3 guo2 jin4 chu1 kou3 yin2
hang2 shi4 zai4 jin1 nian2 er4 yue4 ying4 mei3 guo2 guo2 wu4 qing1 ke4
li3 si1 tuo1 fu2 de5 yao1 qiu2 zai4 san1 shi2 tian1 zhi1 nei4 zan4 shi2
dong4 jie2 le5 gei3 zhong1 guo2 de5 xiang4 mu4 ti2 gong1 dai4 kuan3 fa3
xin1 she4 hai2 bao4 dao4 shuo1 hou4 lai2 jin4 chu1 kou3 yin2 hang2 zai4
si4 yue4 shi2 qi1 hao4 biao3 shi4 gai1 hang2 yi3 jing1 ke3 yi3 zai4 ci4
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
xiang1 gang3 de5 jing1 ji4 he2 zheng4 zhi4 zhi4 du4 jiang1 bu4 tong2 yu2
zhong1 guo2 xiang1 gang3 ren2 min2 jiang1 xiang3 you3 zhong1 guo2 da4
lu4 qi2
removed 'dat/chip/voa/tot.1/raw.wfr'
creating the word frequency file dat/chip/voa/tot.1/raw.wfr
the 10 most common words in dat/chip/voa/tot.1/raw.tlw:
1456 0.04120 de5
1091 0.03087 guo2
754 0.02133 shi4
671 0.01899 zhong1
488 0.01381 zai4
476 0.01347 yi1
430 0.01217 bu4
383 0.01084 he2
374 0.01058 ren2
356 0.01007 mei3
removed 'dat/chip/voa/tot.1/raw-trunc-wds-summary.tex'
removed 'exp/chip/voa/tot.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/chip/voa/tot.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:37 by tex-make-sample-summary.sh
% Token and word counts for chip/voa/tot.1/raw.wfr
%
\def\chipvoatrunctotPBrawTks{35342}
\def\chipvoatrunctotPBrawTksPct{100.0}
\def\chipvoatrunctotPBrawWds{832}
\def\chipvoatrunctotPBrawWdsPct{2.4}
copied '/tmp/588997.file' -> 'exp/chip/voa/tot.1/raw-trunc-wds-summary.tex'
removed '/tmp/588997.file'
creating running text file dat/chip/voa/tot.1/gud.wdf
sample:
ge4 wei4 ting1 zhong4 mei3 guo2 zheng4 fu3 jue2 ding4 jin4 yi1 bu4 dong4
jie2 mei3 guo2 jin4 chu1 kou3 yin2 hang2 xiang4 can1 yu4 zhong1 guo2
xiang4 mu4 de5 mei3 guo2 gong1 si1 ti2 gong1 de5 dai4 kuan3 zhong1 guo2
biao3 shi4 zhei4 xiang4 jue2 ding4 jiang1 you3 sun3 liang3 guo2 de5 mao4
yi4 guan1 xi5 yi3 ji2 mei3 guo2 gong1 shang1 jie4 zai4 zhong1 guo2 de5
li4 yi4 bing4 yao1 qiu2 mei3 guo2 gai3 bian4 zhei4 ge4 jue2 ding4 mei3
guo2 qing2 bao4 zhuan1 jia1 biao3 shi4 bei3 jing1 xiang4 ba1 ji1 si1
tan3 chu1 shou4 le5 ke3 yi3 zhi4 zao4 he2 wu3 qi4 de5 he2 cai2 liao4
mei3 guo2 fa3 lü4 jin4 zhi3 xiang4 ren4 he2 bang1 zhu4 qi2 ta1 guo2 jia1
fa1 zhan3 he2 wu3 qi4 de5 guo2 jia1 ti2 gong1 dai4 kuan3 huo4 dai4 kuan3
dan1 bao3 lu4 tou4 she4 bao4 dao4 shuo1 zai4 mei3 guo2 ke3 neng2 cai3
qu3 de5 dui4 zhong1 guo2 de5 cheng2 fa2 xing4 cuo4 shi1 dang1 zhong1 qu3
xiao1 jin4 chu1 kou3 yin2 hang2 yu3 zhong1 guo2 de5 he2 zuo4 ye3 bao1
kuo4 zai4 nei4 ju4 fa3 xin1 she4 bao4 dao4 mei3 guo2 jin4 chu1 kou3 yin2
hang2 shi4 zai4 jin1 nian2 er4 yue4 ying4 mei3 guo2 guo2 wu4 qing1 ke4
li3 si1 tuo1 fu2 de5 yao1 qiu2 zai4 san1 shi2 tian1 zhi1 nei4 zan4 shi2
dong4 jie2 le5 gei3 zhong1 guo2 de5 xiang4 mu4 ti2 gong1 dai4 kuan3 fa3
xin1 she4 hai2 bao4 dao4 shuo1 hou4 lai2 jin4 chu1 kou3 yin2 hang2 zai4
si4 yue4 shi2 qi1 hao4 biao3 shi4 gai1 hang2 yi3 jing1 ke3 yi3 zai4 ci4
kai1 zhan3 you3 guan1 zhong1 guo2 de5 ye4 wu4 le5 dan4 shi4 zai4 zhei4
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
zheng4 xiang1 gang3 de5 jing1 ji4 he2 zheng4 zhi4 zhi4 du4 jiang1 bu4
tong2 yu2 zhong1 guo2 xiang1 gang3 ren2 min2 jiang1 xiang3 you3 zhong1
guo2 da4 lu4 qi2
removed 'dat/chip/voa/tot.1/gud.wfr'
creating the word frequency file dat/chip/voa/tot.1/gud.wfr
the 10 most common words in dat/chip/voa/tot.1/gud.tlw:
1456 0.04157 de5
1091 0.03115 guo2
754 0.02153 shi4
671 0.01916 zhong1
488 0.01393 zai4
476 0.01359 yi1
430 0.01228 bu4
383 0.01093 he2
374 0.01068 ren2
356 0.01016 mei3
removed 'dat/chip/voa/tot.1/gud-trunc-wds-summary.tex'
removed 'exp/chip/voa/tot.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/chip/voa/tot.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:37 by tex-make-sample-summary.sh
% Token and word counts for chip/voa/tot.1/gud.wfr
%
\def\chipvoatrunctotPBgudTks{35027}
\def\chipvoatrunctotPBgudTksPct{99.1}
\def\chipvoatrunctotPBgudWds{830}
\def\chipvoatrunctotPBgudWdsPct{2.3}
copied '/tmp/589041.file' -> 'exp/chip/voa/tot.1/gud-trunc-wds-summary.tex'
removed '/tmp/589041.file'
creating running text file dat/chip/voa/tot.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/chip/voa/tot.1/bad.wfr'
creating the word frequency file dat/chip/voa/tot.1/bad.wfr
the 10 most common words in dat/chip/voa/tot.1/bad.tlw:
311 0.98730 =
4 0.01270 *
removed 'dat/chip/voa/tot.1/bad-trunc-wds-summary.tex'
removed 'exp/chip/voa/tot.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/chip/voa/tot.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:37 by tex-make-sample-summary.sh
% Token and word counts for chip/voa/tot.1/bad.wfr
%
\def\chipvoatrunctotPBbadTks{315}
\def\chipvoatrunctotPBbadTksPct{0.9}
\def\chipvoatrunctotPBbadWds{2}
\def\chipvoatrunctotPBbadWdsPct{0.0}
copied '/tmp/589085.file' -> 'exp/chip/voa/tot.1/bad-trunc-wds-summary.tex'
removed '/tmp/589085.file'
lines words bytes file
------- ------- --------- ------------
832 2496 17624 dat/chip/voa/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
830 2490 17588 dat/chip/voa/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
2 6 36 dat/chip/voa/tot.1/bad.wfr
tot.1 raw = 35342 gud = 35027 bad = 315
=== creating the derived word files dat/tibe/vim/*/{raw,gud,bad}.{tlw,wdf,wfr} (trunc) ===
... creating word files dat/tibe/vim/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
35077 dat/tibe/vim/tot.1/trunc.tlw
removed 'dat/tibe/vim/tot.1/raw.tlw'
removed 'dat/tibe/vim/tot.1/gud.tlw'
removed 'dat/tibe/vim/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/tibe/vim/tot.1/raw.wdf
sample:
SHES PA CHEN PO YONGS SU SBYANGS PA LAS NGES PAR BYUNG BA SANGS RGYAS
KYIS BYIN GYI RLABS KYIS BYIN GYIS BRLABS PA CHOS KYI GRONG KHYER SRUNG
BA DAM PA'I CHOS YONGS SU 'DZIN PA SENG GE'I SGRA CHEN PO SGROGS PA
PHYOGS BCUR SGRA SHIN TU BSGRAGS PA GSOL BA MA BTAB PAR SEMS CAN THAMS
CAD KYI DGE BA'I BSHES GNYEN DU GYUR PA DKON MCHOG GSUM GYI RIGS RGYUN
MI 'CHAD PAR BYED PA BDUD DANG PHYIR RGOL BA BCOM PA PHA ROL GYI RGOL BA
THAMS CAD KYIS ZIL GYIS MI NON PA DRAN PA DANG BLO GROS DANG RTOGS PA
DANG TING NGE 'DZIN DANG GZUNGS DANG SPOBS PA PHUN SUM TSOGS PA SGRIB PA
DANG KUN NAS LDANG BA THAMS CAD DANG BRAL BA SGRIB PA MED PA'I RNAM PAR
THAR PA LA GNAS PA SPOBS PA RGYUN MI 'CHAD PA SPYIN PA DANG DUL BA DANG
MI 'GYUR BA DANG YANG DAG PAR SDOM PA DANG TSUL KHRIMS DANG BZOD PA DANG
BRTZON 'GRUS DANG BSAM GTAN DANG SHES RAB DANG THABS LA MKHAS PA DANG
SMON LAM DANG STOBS DANG YE SHES KYI PHA ROL TU PHYIN PA LAS NGES PAR
BYUNG BA MI DMIGS PA'I CHOS LA BZOD PA DANG LDAN PA PHYIR MI LDOG PA'I
CHOS KYI 'KHOR LO SKOR BA MTSAN NYID MED PA'I PHYIR RGYAS BTAB BA * SEMS
CAN THAMS CAD KYI DBANG PO SHES PA LA MKHAS PA 'KHOR THAMS CAD ZIL GYIS
MI NON PA'I MI 'JIGS PAS RNAM PAR GNON PA BSOD NAMS DANG YE SHES KYI
TSOGS CHEN PO BSAGS PA MTSAN DANG DPE BYAD BZANG PO THAMS CAD KYIS LUS
SHIN TU BRGYAN PA GZUGS DAM PA 'JIN PA RGYAN DANG BRAL BA RI RAB KYI
RTZE MO MTHO BA BZHIN DU SNYAN PA DANG GRAGS PAS MNGON PAR 'PHAGS PA
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
BYED MTSAN NYID MED PAR MI BYED DO GANG MTSAN NYID DANG MTSAN NYID MI
'DRA BA LA MTSAN NYID MTSUNGS PAR 'JUG PA DE NI GNYIS SU MED PAR 'JUG
PA'O
removed 'dat/tibe/vim/tot.1/raw.wfr'
creating the word frequency file dat/tibe/vim/tot.1/raw.wfr
the 10 most common words in dat/tibe/vim/tot.1/raw.tlw:
1879 0.05357 PA
971 0.02768 DANG
935 0.02666 DE
798 0.02275 PAR
749 0.02135 LA
718 0.02047 BA
593 0.01691 SEMS
571 0.01628 PA'I
536 0.01528 KYI
513 0.01462 NI
removed 'dat/tibe/vim/tot.1/raw-trunc-wds-summary.tex'
removed 'exp/tibe/vim/tot.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/tibe/vim/tot.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:37 by tex-make-sample-summary.sh
% Token and word counts for tibe/vim/tot.1/raw.wfr
%
\def\tibevimtrunctotPBrawTks{35077}
\def\tibevimtrunctotPBrawTksPct{100.0}
\def\tibevimtrunctotPBrawWds{1304}
\def\tibevimtrunctotPBrawWdsPct{3.7}
copied '/tmp/589180.file' -> 'exp/tibe/vim/tot.1/raw-trunc-wds-summary.tex'
removed '/tmp/589180.file'
creating running text file dat/tibe/vim/tot.1/gud.wdf
sample:
SHES PA CHEN PO YONGS SU SBYANGS PA LAS NGES PAR BYUNG BA SANGS RGYAS
KYIS BYIN GYI RLABS KYIS BYIN GYIS BRLABS PA CHOS KYI GRONG KHYER SRUNG
BA DAM PA'I CHOS YONGS SU 'DZIN PA SENG GE'I SGRA CHEN PO SGROGS PA
PHYOGS BCUR SGRA SHIN TU BSGRAGS PA GSOL BA MA BTAB PAR SEMS CAN THAMS
CAD KYI DGE BA'I BSHES GNYEN DU GYUR PA DKON MCHOG GSUM GYI RIGS RGYUN
MI 'CHAD PAR BYED PA BDUD DANG PHYIR RGOL BA BCOM PA PHA ROL GYI RGOL BA
THAMS CAD KYIS ZIL GYIS MI NON PA DRAN PA DANG BLO GROS DANG RTOGS PA
DANG TING NGE 'DZIN DANG GZUNGS DANG SPOBS PA PHUN SUM TSOGS PA SGRIB PA
DANG KUN NAS LDANG BA THAMS CAD DANG BRAL BA SGRIB PA MED PA'I RNAM PAR
THAR PA LA GNAS PA SPOBS PA RGYUN MI 'CHAD PA SPYIN PA DANG DUL BA DANG
MI 'GYUR BA DANG YANG DAG PAR SDOM PA DANG TSUL KHRIMS DANG BZOD PA DANG
BRTZON 'GRUS DANG BSAM GTAN DANG SHES RAB DANG THABS LA MKHAS PA DANG
SMON LAM DANG STOBS DANG YE SHES KYI PHA ROL TU PHYIN PA LAS NGES PAR
BYUNG BA MI DMIGS PA'I CHOS LA BZOD PA DANG LDAN PA PHYIR MI LDOG PA'I
CHOS KYI 'KHOR LO SKOR BA MTSAN NYID MED PA'I PHYIR RGYAS BTAB BA SEMS
CAN THAMS CAD KYI DBANG PO SHES PA LA MKHAS PA 'KHOR THAMS CAD ZIL GYIS
MI NON PA'I MI 'JIGS PAS RNAM PAR GNON PA BSOD NAMS DANG YE SHES KYI
TSOGS CHEN PO BSAGS PA MTSAN DANG DPE BYAD BZANG PO THAMS CAD KYIS LUS
SHIN TU BRGYAN PA GZUGS DAM PA 'JIN PA RGYAN DANG BRAL BA RI RAB KYI
RTZE MO MTHO BA BZHIN DU SNYAN PA DANG GRAGS PAS MNGON PAR 'PHAGS PA
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
MI BYED KUN TU RTOG PAR MI BYED MTSAN NYID GCIG PAR MI BYED MTSAN NYID
MED PAR MI BYED DO GANG MTSAN NYID DANG MTSAN NYID MI 'DRA BA LA MTSAN
NYID MTSUNGS PAR 'JUG PA DE NI GNYIS SU MED PAR 'JUG PA'O
removed 'dat/tibe/vim/tot.1/gud.wfr'
creating the word frequency file dat/tibe/vim/tot.1/gud.wfr
the 10 most common words in dat/tibe/vim/tot.1/gud.tlw:
1879 0.05364 PA
971 0.02772 DANG
935 0.02669 DE
798 0.02278 PAR
749 0.02138 LA
718 0.02050 BA
593 0.01693 SEMS
571 0.01630 PA'I
536 0.01530 KYI
513 0.01465 NI
removed 'dat/tibe/vim/tot.1/gud-trunc-wds-summary.tex'
removed 'exp/tibe/vim/tot.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/tibe/vim/tot.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:37 by tex-make-sample-summary.sh
% Token and word counts for tibe/vim/tot.1/gud.wfr
%
\def\tibevimtrunctotPBgudTks{35027}
\def\tibevimtrunctotPBgudTksPct{99.9}
\def\tibevimtrunctotPBgudWds{1300}
\def\tibevimtrunctotPBgudWdsPct{3.7}
copied '/tmp/589224.file' -> 'exp/tibe/vim/tot.1/gud-trunc-wds-summary.tex'
removed '/tmp/589224.file'
creating running text file dat/tibe/vim/tot.1/bad.wdf
sample:
* * * * =
=
*SH'A * =
=
* * * =
=
* * * * * =
* * =
=
* =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
* =
removed 'dat/tibe/vim/tot.1/bad.wfr'
creating the word frequency file dat/tibe/vim/tot.1/bad.wfr
the 10 most common words in dat/tibe/vim/tot.1/bad.tlw:
29 0.58000 =
19 0.38000 *
1 0.02000 *KLUNG
1 0.02000 *SH'A
removed 'dat/tibe/vim/tot.1/bad-trunc-wds-summary.tex'
removed 'exp/tibe/vim/tot.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/tibe/vim/tot.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:38 by tex-make-sample-summary.sh
% Token and word counts for tibe/vim/tot.1/bad.wfr
%
\def\tibevimtrunctotPBbadTks{50}
\def\tibevimtrunctotPBbadTksPct{0.1}
\def\tibevimtrunctotPBbadWds{4}
\def\tibevimtrunctotPBbadWdsPct{0.0}
copied '/tmp/589268.file' -> 'exp/tibe/vim/tot.1/bad-trunc-wds-summary.tex'
removed '/tmp/589268.file'
lines words bytes file
------- ------- --------- ------------
1304 3912 27775 dat/tibe/vim/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
1300 3900 27694 dat/tibe/vim/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
4 12 81 dat/tibe/vim/tot.1/bad.wfr
tot.1 raw = 35077 gud = 35027 bad = 50
=== creating the derived word files dat/tibe/ccv/*/{raw,gud,bad}.{tlw,wdf,wfr} (trunc) ===
... creating word files dat/tibe/ccv/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
35049 dat/tibe/ccv/tot.1/trunc.tlw
removed 'dat/tibe/ccv/tot.1/raw.tlw'
removed 'dat/tibe/ccv/tot.1/gud.tlw'
removed 'dat/tibe/ccv/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/tibe/ccv/tot.1/raw.wdf
sample:
=
=
RGYA GAR SKAD DU PRA M'A nA B'ARTI KA * BRATTI N'A MA BOD SKAD DU TSAD
MA RNAM 'GREL GYI 'GREL PA ZHES BYA BA BAM BO DANG PO BCOM LDAN 'DAS
'JAM DPAL YE SHES SEMS DPA' LA PHYAG 'TSAL LO SRID PA'I GNAS 'JUG NGA
RGYAL GYIS BYAS 'BIGS BYED DE NYID KYIS KHYAB GANG YIN LA RAB RIB DBANG
GIS MI BZAD MUN PA LTAR 'JUG PHA ROL LTA 'DI DAG NI 'DOD PAS MYOS PA LAS
RGYAL BA ZHES RAB GRAGS DE KHO NA NYID SNANG BA CAN 'JIG RTEN MA LUS
SNANG BYED BDUD RTZI'I BDE BA DES NI 'JIG RTEN DAG BYED SHOG DE LTAR
'PHAGS PA'I BDEN PA BZHI LA 'JUG PA YIN PA'I PHYIR RJES SU DPAG PA RNAM
PAR BZHAG NAS DE NYID BSTAN PAR BYA BA'I PHYIR LE'U GNYIS PAS PHYAG
'TSAL BA'I TSIGS SU BCAD PA GSAL BAR BSHAD PAR MDZAD DO 'DIR TSAD MA'I
MTSAD NYID DANG BCOM LDAN 'DAS TSAD MAR GYUR PAR BZHED NAS SLOB DPON
GYIS BSTAN BCOS KYI DANG POR TSAD MAR GYUR PA ZHES PAS BSTOD PA GSUNGS
SO TSAD MAR GYUR PA 'GRO LA PHAN MDZAD BZHED STON PA BDE GSHEGS SKYOB LA
PHYAG 'TSAL NAS RANG GI GZHUNG LUGS 'THOR LAS 'DIR GCIG NYID TSAD MA
GRUB PA KUN LAS BTUS PA BRTZAM ZHES GSUNGS TE 'DIR YANG SNGA MA PHYENG
KYIS NI RGYU DANG 'BRAS BU PHUN SUM TSOGS PAS TSAD MAR GYUR PA'I BCOM
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
ZHING PHRAD PAS 'BRAS BU JI LTAR MI SKYE ZHES BYA BA'I BRTZAD PA MTSUNGS
PAR 'GYUR RO GAL TE MIG LA SOGS PA TSOGS PAS BSKYED PA LA 'DRE BA GZHAN
DGOS NA NI
removed 'dat/tibe/ccv/tot.1/raw.wfr'
creating the word frequency file dat/tibe/ccv/tot.1/raw.wfr
the 10 most common words in dat/tibe/ccv/tot.1/raw.tlw:
2484 0.07087 PA
1104 0.03150 LA
991 0.02827 YIN
974 0.02779 BA
925 0.02639 MA
896 0.02556 PA'I
894 0.02551 PAR
834 0.02380 NA
815 0.02325 NI
810 0.02311 DE
removed 'dat/tibe/ccv/tot.1/raw-trunc-wds-summary.tex'
removed 'exp/tibe/ccv/tot.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/tibe/ccv/tot.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:38 by tex-make-sample-summary.sh
% Token and word counts for tibe/ccv/tot.1/raw.wfr
%
\def\tibeccvtrunctotPBrawTks{35049}
\def\tibeccvtrunctotPBrawTksPct{100.0}
\def\tibeccvtrunctotPBrawWds{855}
\def\tibeccvtrunctotPBrawWdsPct{2.4}
copied '/tmp/589363.file' -> 'exp/tibe/ccv/tot.1/raw-trunc-wds-summary.tex'
removed '/tmp/589363.file'
creating running text file dat/tibe/ccv/tot.1/gud.wdf
sample:
RGYA GAR SKAD DU PRA M'A nA B'ARTI KA BRATTI N'A MA BOD SKAD DU TSAD MA
RNAM 'GREL GYI 'GREL PA ZHES BYA BA BAM BO DANG PO BCOM LDAN 'DAS 'JAM
DPAL YE SHES SEMS DPA' LA PHYAG 'TSAL LO SRID PA'I GNAS 'JUG NGA RGYAL
GYIS BYAS 'BIGS BYED DE NYID KYIS KHYAB GANG YIN LA RAB RIB DBANG GIS MI
BZAD MUN PA LTAR 'JUG PHA ROL LTA 'DI DAG NI 'DOD PAS MYOS PA LAS RGYAL
BA ZHES RAB GRAGS DE KHO NA NYID SNANG BA CAN 'JIG RTEN MA LUS SNANG
BYED BDUD RTZI'I BDE BA DES NI 'JIG RTEN DAG BYED SHOG DE LTAR 'PHAGS
PA'I BDEN PA BZHI LA 'JUG PA YIN PA'I PHYIR RJES SU DPAG PA RNAM PAR
BZHAG NAS DE NYID BSTAN PAR BYA BA'I PHYIR LE'U GNYIS PAS PHYAG 'TSAL
BA'I TSIGS SU BCAD PA GSAL BAR BSHAD PAR MDZAD DO 'DIR TSAD MA'I MTSAD
NYID DANG BCOM LDAN 'DAS TSAD MAR GYUR PAR BZHED NAS SLOB DPON GYIS
BSTAN BCOS KYI DANG POR TSAD MAR GYUR PA ZHES PAS BSTOD PA GSUNGS SO
TSAD MAR GYUR PA 'GRO LA PHAN MDZAD BZHED STON PA BDE GSHEGS SKYOB LA
PHYAG 'TSAL NAS RANG GI GZHUNG LUGS 'THOR LAS 'DIR GCIG NYID TSAD MA
GRUB PA KUN LAS BTUS PA BRTZAM ZHES GSUNGS TE 'DIR YANG SNGA MA PHYENG
KYIS NI RGYU DANG 'BRAS BU PHUN SUM TSOGS PAS TSAD MAR GYUR PA'I BCOM
LDAN 'DAS BSTAN PAR MDZAD DO DE LA RGYU PHUN SUM TSOGS PA NI GNYIS TE
SNYING RJE DANG THABS SO DE LA SNYING RJE NI 'GRO LA PHAN PAR BZHED CES
BYA BAS BSTAN TO THABS GOMS PAR BYA BA NI STON PA ZHES BYA BAS SO 'BRAS
BU PHUN SUM TSOGS PA YANG GNYIS TE RANG GI DON PHUN SUM TSOGS PA DANG
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
SBYOR BA YOD NA PHYOGS LA YANG SBYOR ZHING PHRAD PAS 'BRAS BU JI LTAR MI
SKYE ZHES BYA BA'I BRTZAD PA MTSUNGS PAR 'GYUR RO GAL TE MIG LA SOGS PA
TSOGS PAS BSKYED PA LA 'DRE BA GZHAN DGOS NA NI
removed 'dat/tibe/ccv/tot.1/gud.wfr'
creating the word frequency file dat/tibe/ccv/tot.1/gud.wfr
the 10 most common words in dat/tibe/ccv/tot.1/gud.tlw:
2484 0.07092 PA
1104 0.03152 LA
991 0.02829 YIN
974 0.02781 BA
925 0.02641 MA
896 0.02558 PA'I
894 0.02552 PAR
834 0.02381 NA
815 0.02327 NI
810 0.02313 DE
removed 'dat/tibe/ccv/tot.1/gud-trunc-wds-summary.tex'
removed 'exp/tibe/ccv/tot.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/tibe/ccv/tot.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:38 by tex-make-sample-summary.sh
% Token and word counts for tibe/ccv/tot.1/gud.wfr
%
\def\tibeccvtrunctotPBgudTks{35027}
\def\tibeccvtrunctotPBgudTksPct{99.9}
\def\tibeccvtrunctotPBgudWds{846}
\def\tibeccvtrunctotPBgudWdsPct{2.4}
copied '/tmp/589407.file' -> 'exp/tibe/ccv/tot.1/gud-trunc-wds-summary.tex'
removed '/tmp/589407.file'
creating running text file dat/tibe/ccv/tot.1/bad.wdf
sample:
=
=
* ONGS =
=
*MIN *GANG =
=
RIG*BYED RIG*BYED =
=
=
AGZUGS =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/tibe/ccv/tot.1/bad.wfr'
creating the word frequency file dat/tibe/ccv/tot.1/bad.wfr
the 10 most common words in dat/tibe/ccv/tot.1/bad.tlw:
13 0.59091 =
2 0.09091 RIG*BYED
1 0.04545 *
1 0.04545 *GANG
1 0.04545 *MIN
1 0.04545 *NYID
1 0.04545 A
1 0.04545 AGZUGS
1 0.04545 ONGS
removed 'dat/tibe/ccv/tot.1/bad-trunc-wds-summary.tex'
removed 'exp/tibe/ccv/tot.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/tibe/ccv/tot.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:38 by tex-make-sample-summary.sh
% Token and word counts for tibe/ccv/tot.1/bad.wfr
%
\def\tibeccvtrunctotPBbadTks{22}
\def\tibeccvtrunctotPBbadTksPct{0.1}
\def\tibeccvtrunctotPBbadWds{9}
\def\tibeccvtrunctotPBbadWdsPct{0.0}
copied '/tmp/589451.file' -> 'exp/tibe/ccv/tot.1/bad-trunc-wds-summary.tex'
removed '/tmp/589451.file'
lines words bytes file
------- ------- --------- ------------
855 2565 18068 dat/tibe/ccv/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
846 2538 17880 dat/tibe/ccv/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
9 27 188 dat/tibe/ccv/tot.1/bad.wfr
tot.1 raw = 35049 gud = 35027 bad = 22
=== creating the derived word files dat/tibe/pmi/*/{raw,gud,bad}.{tlw,wdf,wfr} (trunc) ===
... creating word files dat/tibe/pmi/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
35034 dat/tibe/pmi/tot.1/trunc.tlw
removed 'dat/tibe/pmi/tot.1/raw.tlw'
removed 'dat/tibe/pmi/tot.1/gud.tlw'
removed 'dat/tibe/pmi/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/tibe/pmi/tot.1/raw.wdf
sample:
LA 'THAMS PAS 'DI SNANG SPRE'U'I GAR BAR MED YON POR BSGYUR BA'I RNAM G
YENG GIS GTAN 'DUN RLUNG LA BSKUR BA'I GTAM 'DI GLENG DE LA 'DIR GYI NA
PA BLO BZANG YE SHES BSTAN 'DZIN RGYA MTSOR 'BOD PA BDAG DGA' LDAN KHRI
THOG DRUG CU RE DGU PA YONGS 'DZIN KHRI CHEN BYANG CHUB CHOS 'PHEL DANG
DE'I SPRUL SKU DGA' LDAN KHRI THOG BRGYAD CU GYA LNGA PA KHRI CHEN BLO
BZANG TSUL KHRIMS DPAL LDAN GYI YANG SPRUL DU SGRO BTAGS KYANG RANG BLO
RANG LA LKOG TU MA GYUR PAS DAM PA DE DAG GI SKYE SPRUL DU 'OS PA'I YON
TAN NAM MKHA'I PADMO'I MCHED ZLAR GYUR RUNG SNGON LAS BTZAN POS SPRUL
SKU'I MING 'DZIN DU STES DBANG GIS SON CING RJE GUNG THANG PAS SKU SKYE
BSTAN DON DU BYON NA BSHAD SGRUB LAG RJES SHIG YOD DGOS GSUNGS PA LTAR
SNGON GYI SKYES BU DAM PA RNAMS KYI RNAM THAR MTHONG NA YID 'PHROG CING
THOS NA DAD PA SKYE LA GDUL BYA'I RGYUD LA RNAM GROL THAR PA'I BAG CHAGS
'JOG NUS PA DE LTA BU ZHIG NI RMONGS PA DUG GSUM GYI GONG BU 'DU SHES
GSUM PA KHO BO LTA BU LA RUS SBAL GYI SPU BZHIN GA LA 'ONG DE LTAR MED
KYANG BLA MA'I MING TZAM 'DZIN KHUL STABS MING SKAM DON STONG DU MA SONG
TZAM GYI THOS BSAM BSHAD SGRUB KYI SGO NAS BSTAN PA 'DZIN SKYONG SPEL
BA'I BYA BA 'DI BYAS KYI LAG RJES PHRAN BU ZHIG DGOS NGES KYANG DE YANG
MA BRTAG MA DPYAD NA YOD YOD 'DRA LA BRTAG NA DPYAD MI BZOD PA 'JA' TSON
GYI RANG BZHIN LAS STON RGYU MA MCHIS PA ZHIG GIS 'DI SNANG ZA ZI'I RJES
GCOD KYI LO RGYUS YI GER 'GOD RGYU 'DAB CHAGS PHA WANG MKHA' LDING DU
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
LA DAR DGON CHOG GRA DANG BCAS RAB GNAS RGYAS PA NYIN GSUM MDZOD NANG DU
RNAM SRAS G YANG SGRUB YUL MI GANG 'TSAMS LA BLO SBYONG DON BDUN MA'I
BSHAD KHRID TSE DBANG BCAS BGYIS ZIN BSTUN PHYIR LOG GIS NYAG RONG GI SA
removed 'dat/tibe/pmi/tot.1/raw.wfr'
creating the word frequency file dat/tibe/pmi/tot.1/raw.wfr
the 10 most common words in dat/tibe/pmi/tot.1/raw.tlw:
747 0.02132 PA
651 0.01858 DANG
499 0.01424 NAS
457 0.01304 DU
374 0.01068 DE
372 0.01062 BA
358 0.01022 MA
351 0.01002 LA
340 0.00970 PA'I
317 0.00905 KYI
removed 'dat/tibe/pmi/tot.1/raw-trunc-wds-summary.tex'
removed 'exp/tibe/pmi/tot.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/tibe/pmi/tot.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:38 by tex-make-sample-summary.sh
% Token and word counts for tibe/pmi/tot.1/raw.wfr
%
\def\tibepmitrunctotPBrawTks{35034}
\def\tibepmitrunctotPBrawTksPct{100.0}
\def\tibepmitrunctotPBrawWds{1968}
\def\tibepmitrunctotPBrawWdsPct{5.6}
copied '/tmp/589546.file' -> 'exp/tibe/pmi/tot.1/raw-trunc-wds-summary.tex'
removed '/tmp/589546.file'
creating running text file dat/tibe/pmi/tot.1/gud.wdf
sample:
LA 'THAMS PAS 'DI SNANG SPRE'U'I GAR BAR MED YON POR BSGYUR BA'I RNAM G
YENG GIS GTAN 'DUN RLUNG LA BSKUR BA'I GTAM 'DI GLENG DE LA 'DIR GYI NA
PA BLO BZANG YE SHES BSTAN 'DZIN RGYA MTSOR 'BOD PA BDAG DGA' LDAN KHRI
THOG DRUG CU RE DGU PA YONGS 'DZIN KHRI CHEN BYANG CHUB CHOS 'PHEL DANG
DE'I SPRUL SKU DGA' LDAN KHRI THOG BRGYAD CU GYA LNGA PA KHRI CHEN BLO
BZANG TSUL KHRIMS DPAL LDAN GYI YANG SPRUL DU SGRO BTAGS KYANG RANG BLO
RANG LA LKOG TU MA GYUR PAS DAM PA DE DAG GI SKYE SPRUL DU 'OS PA'I YON
TAN NAM MKHA'I PADMO'I MCHED ZLAR GYUR RUNG SNGON LAS BTZAN POS SPRUL
SKU'I MING 'DZIN DU STES DBANG GIS SON CING RJE GUNG THANG PAS SKU SKYE
BSTAN DON DU BYON NA BSHAD SGRUB LAG RJES SHIG YOD DGOS GSUNGS PA LTAR
SNGON GYI SKYES BU DAM PA RNAMS KYI RNAM THAR MTHONG NA YID 'PHROG CING
THOS NA DAD PA SKYE LA GDUL BYA'I RGYUD LA RNAM GROL THAR PA'I BAG CHAGS
'JOG NUS PA DE LTA BU ZHIG NI RMONGS PA DUG GSUM GYI GONG BU 'DU SHES
GSUM PA KHO BO LTA BU LA RUS SBAL GYI SPU BZHIN GA LA 'ONG DE LTAR MED
KYANG BLA MA'I MING TZAM 'DZIN KHUL STABS MING SKAM DON STONG DU MA SONG
TZAM GYI THOS BSAM BSHAD SGRUB KYI SGO NAS BSTAN PA 'DZIN SKYONG SPEL
BA'I BYA BA 'DI BYAS KYI LAG RJES PHRAN BU ZHIG DGOS NGES KYANG DE YANG
MA BRTAG MA DPYAD NA YOD YOD 'DRA LA BRTAG NA DPYAD MI BZOD PA 'JA' TSON
GYI RANG BZHIN LAS STON RGYU MA MCHIS PA ZHIG GIS 'DI SNANG ZA ZI'I RJES
GCOD KYI LO RGYUS YI GER 'GOD RGYU 'DAB CHAGS PHA WANG MKHA' LDING DU
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
GSUM MDZOD NANG DU RNAM SRAS G YANG SGRUB YUL MI GANG 'TSAMS LA BLO
SBYONG DON BDUN MA'I BSHAD KHRID TSE DBANG BCAS BGYIS ZIN BSTUN PHYIR
LOG GIS NYAG RONG GI SA
removed 'dat/tibe/pmi/tot.1/gud.wfr'
creating the word frequency file dat/tibe/pmi/tot.1/gud.wfr
the 10 most common words in dat/tibe/pmi/tot.1/gud.tlw:
747 0.02133 PA
651 0.01859 DANG
499 0.01425 NAS
457 0.01305 DU
374 0.01068 DE
372 0.01062 BA
358 0.01022 MA
351 0.01002 LA
340 0.00971 PA'I
317 0.00905 KYI
removed 'dat/tibe/pmi/tot.1/gud-trunc-wds-summary.tex'
removed 'exp/tibe/pmi/tot.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/tibe/pmi/tot.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:38 by tex-make-sample-summary.sh
% Token and word counts for tibe/pmi/tot.1/gud.wfr
%
\def\tibepmitrunctotPBgudTks{35027}
\def\tibepmitrunctotPBgudTksPct{100.0}
\def\tibepmitrunctotPBgudWds{1963}
\def\tibepmitrunctotPBgudWdsPct{5.6}
copied '/tmp/589590.file' -> 'exp/tibe/pmi/tot.1/gud-trunc-wds-summary.tex'
removed '/tmp/589590.file'
creating running text file dat/tibe/pmi/tot.1/bad.wdf
sample:
GSUm LAm TZAR+YA 'Am =
GSUm =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
GSUm =
removed 'dat/tibe/pmi/tot.1/bad.wfr'
creating the word frequency file dat/tibe/pmi/tot.1/bad.wfr
the 10 most common words in dat/tibe/pmi/tot.1/bad.tlw:
2 0.28571 =
2 0.28571 GSUm
1 0.14286 'Am
1 0.14286 LAm
1 0.14286 TZAR+YA
removed 'dat/tibe/pmi/tot.1/bad-trunc-wds-summary.tex'
removed 'exp/tibe/pmi/tot.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/tibe/pmi/tot.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:38 by tex-make-sample-summary.sh
% Token and word counts for tibe/pmi/tot.1/bad.wfr
%
\def\tibepmitrunctotPBbadTks{7}
\def\tibepmitrunctotPBbadTksPct{0.0}
\def\tibepmitrunctotPBbadWds{5}
\def\tibepmitrunctotPBbadWdsPct{0.0}
copied '/tmp/589634.file' -> 'exp/tibe/pmi/tot.1/bad-trunc-wds-summary.tex'
removed '/tmp/589634.file'
lines words bytes file
------- ------- --------- ------------
1968 5904 41988 dat/tibe/pmi/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
1963 5889 41885 dat/tibe/pmi/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
5 15 103 dat/tibe/pmi/tot.1/bad.wfr
tot.1 raw = 35034 gud = 35027 bad = 7
=== creating the derived word files dat/chrc/red/*/{raw,gud,bad}.{tlw,wdf,wfr} (trunc) ===
... creating word files dat/chrc/red/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
35263 dat/chrc/red/tot.1/trunc.tlw
removed 'dat/chrc/red/tot.1/raw.tlw'
removed 'dat/chrc/red/tot.1/gud.tlw'
removed 'dat/chrc/red/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/chrc/red/tot.1/raw.wdf
sample:
dkelsy kerdy adt yckrdo aked kry ykrso kelo adlker ydkro adkersy aske
slkiro ydtelso drko aked dtey akels ltiro ylkeo alkerdy odckly dkiy
adkisy ykerdo skiro adkrsy ysrcko atels okesy arke ylkeo ykro ackld
dkelsy ckiy odkly olkedy aked yscklo ykrso odckly actld aslcky okersy
skiro adkersy adkersy akrsy yscklo kirdy rkso olkedy klso ykerdo klso
akdy ydkro yrkso adkersy ydkeso dlkrso alterdy adters adters aked ykerdo
lkrdy skilo lkirso alkrsy aker adlck olkry rkso sky ylkeo ask dkly aked
aked ydlkerso lckery ydlctro adkrsy slko slckro arky lkerdy oklsy drkio
drckso ykldo yckdo yklso ylkeo okrdy klso yklso aslckiry aslckiry ockey
adkl ydtso dkso keldo ydlkero dkelso ydlkeo yklso okisy cklso dkiso sky
ysckero ackd lkdo lkrdy atilsy adkisy ydkero lkrdy akes oskey klso ylkeo
olkry ykrso adlck dkelsy olkry alkrs dkiy yklo dlkery rkso tdy dko
ackeldy dkerso ockildy olckrdy kiso oslckiy tly ylkeo askr adkhely srcto
adply spy ylkeo olkry alckers adrke alkrdy orckdy ysrpeo ylkeo ackeldy
adckisy dlckeso ockily adtely aslki ylkeo ockildy odlkery adlk ydkeso
olkry aked dpio lkrdy skilo lkrdo odkely adrcpiy asrky ylkeo adrte askil
ytero aked arcked odlkery lkersy dko adrk adlksy yklso ylkeo adrte
ockirdy dkso dlckirsy adrkey actly atlsy kirdy adrkiy ydkro ydtelso
ydtelso sky akdy slkeo dkso akes aske yklso ylkeo dkso ospery ydkro
adtes slckro ackls aked alkiry adksy slckro lkhry atild ykrso odrky
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
aked askr dckiy arkedy ykeo yko ackedy kdo aked adlkes dcky adklsy oskly
ylkirso ak ylkrso drkiy arkesy akely drko oskly alckidy kdo dcksy
removed 'dat/chrc/red/tot.1/raw.wfr'
creating the word frequency file dat/chrc/red/tot.1/raw.wfr
the 10 most common words in dat/chrc/red/tot.1/raw.tlw:
659 0.01869 kdo
650 0.01843 aked
586 0.01662 dkso
483 0.01370 akdy
471 0.01336 yko
386 0.01095 oskly
378 0.01072 ylkeo
376 0.01066 arksy
339 0.00961 kldy
327 0.00927 sky
removed 'dat/chrc/red/tot.1/raw-trunc-wds-summary.tex'
removed 'exp/chrc/red/tot.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/chrc/red/tot.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:38 by tex-make-sample-summary.sh
% Token and word counts for chrc/red/tot.1/raw.wfr
%
\def\chrcredtrunctotPBrawTks{35263}
\def\chrcredtrunctotPBrawTksPct{100.0}
\def\chrcredtrunctotPBrawWds{2421}
\def\chrcredtrunctotPBrawWdsPct{6.9}
copied '/tmp/589729.file' -> 'exp/chrc/red/tot.1/raw-trunc-wds-summary.tex'
removed '/tmp/589729.file'
creating running text file dat/chrc/red/tot.1/gud.wdf
sample:
dkelsy kerdy adt yckrdo aked kry ykrso kelo adlker ydkro adkersy aske
slkiro ydtelso drko aked dtey akels ltiro ylkeo alkerdy odckly dkiy
adkisy ykerdo skiro adkrsy ysrcko atels okesy arke ylkeo ykro ackld
dkelsy ckiy odkly olkedy aked yscklo ykrso odckly actld aslcky okersy
skiro adkersy adkersy akrsy yscklo kirdy rkso olkedy klso ykerdo klso
akdy ydkro yrkso adkersy ydkeso dlkrso alterdy adters adters aked ykerdo
lkrdy skilo lkirso alkrsy aker adlck olkry rkso sky ylkeo ask dkly aked
aked ydlkerso lckery ydlctro adkrsy slko slckro arky lkerdy oklsy drkio
drckso ykldo yckdo yklso ylkeo okrdy klso yklso aslckiry aslckiry ockey
adkl ydtso dkso keldo ydlkero dkelso ydlkeo yklso okisy cklso dkiso sky
ysckero ackd lkdo lkrdy atilsy adkisy ydkero lkrdy akes oskey klso ylkeo
olkry ykrso adlck dkelsy olkry alkrs dkiy yklo dlkery rkso tdy dko
ackeldy dkerso ockildy olckrdy kiso oslckiy tly ylkeo askr adkhely srcto
adply spy ylkeo olkry alckers adrke alkrdy orckdy ysrpeo ylkeo ackeldy
adckisy dlckeso ockily adtely aslki ylkeo ockildy odlkery adlk ydkeso
olkry aked dpio lkrdy skilo lkrdo odkely adrcpiy asrky ylkeo adrte askil
ytero aked arcked odlkery lkersy dko adrk adlksy yklso ylkeo adrte
ockirdy dkso dlckirsy adrkey actly atlsy kirdy adrkiy ydkro ydtelso
ydtelso sky akdy slkeo dkso akes aske yklso ylkeo dkso ospery ydkro
adtes slckro ackls aked alkiry adksy slckro lkhry atild ykrso odrky
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
ackedy adklsy oskly aked askr dckiy arkedy ykeo yko ackedy kdo aked
adlkes dcky adklsy oskly ylkirso ak ylkrso drkiy arkesy akely drko oskly
alckidy kdo dcksy
removed 'dat/chrc/red/tot.1/gud.wfr'
creating the word frequency file dat/chrc/red/tot.1/gud.wfr
the 10 most common words in dat/chrc/red/tot.1/gud.tlw:
659 0.01881 kdo
650 0.01856 aked
586 0.01673 dkso
483 0.01379 akdy
471 0.01345 yko
386 0.01102 oskly
378 0.01079 ylkeo
376 0.01073 arksy
339 0.00968 kldy
327 0.00934 sky
removed 'dat/chrc/red/tot.1/gud-trunc-wds-summary.tex'
removed 'exp/chrc/red/tot.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/chrc/red/tot.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:38 by tex-make-sample-summary.sh
% Token and word counts for chrc/red/tot.1/gud.wfr
%
\def\chrcredtrunctotPBgudTks{35027}
\def\chrcredtrunctotPBgudTksPct{99.3}
\def\chrcredtrunctotPBgudWds{2420}
\def\chrcredtrunctotPBgudWdsPct{6.9}
copied '/tmp/589773.file' -> 'exp/chrc/red/tot.1/gud-trunc-wds-summary.tex'
removed '/tmp/589773.file'
creating running text file dat/chrc/red/tot.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/chrc/red/tot.1/bad.wfr'
creating the word frequency file dat/chrc/red/tot.1/bad.wfr
the 10 most common words in dat/chrc/red/tot.1/bad.tlw:
236 1.00000 =
removed 'dat/chrc/red/tot.1/bad-trunc-wds-summary.tex'
removed 'exp/chrc/red/tot.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/chrc/red/tot.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:38 by tex-make-sample-summary.sh
% Token and word counts for chrc/red/tot.1/bad.wfr
%
\def\chrcredtrunctotPBbadTks{236}
\def\chrcredtrunctotPBbadTksPct{0.7}
\def\chrcredtrunctotPBbadWds{1}
\def\chrcredtrunctotPBbadWdsPct{0.0}
copied '/tmp/589817.file' -> 'exp/chrc/red/tot.1/bad-trunc-wds-summary.tex'
removed '/tmp/589817.file'
lines words bytes file
------- ------- --------- ------------
2421 7263 54581 dat/chrc/red/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
2420 7260 54563 dat/chrc/red/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
1 3 18 dat/chrc/red/tot.1/bad.wfr
tot.1 raw = 35263 gud = 35027 bad = 236
=== creating the derived word files dat/enrc/wow/*/{raw,gud,bad}.{tlw,wdf,wfr} (trunc) ===
... creating word files dat/enrc/wow/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
35606 dat/enrc/wow/tot.1/trunc.tlw
removed 'dat/enrc/wow/tot.1/raw.tlw'
removed 'dat/enrc/wow/tot.1/gud.tlw'
removed 'dat/enrc/wow/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/enrc/wow/tot.1/raw.wdf
sample:
ccv lii clxix cxxix mdcxxvi xxiv xx dccxii mcmxlix i xx mmmdccclxxxiii
mcdxi xiii liv cmlxxii xxv cdi mcxcvii mmcdxxx ii xxx cdlxxvi mmcccxliv
clvi cccxxxiv mmxxxiv ii cxii xxxii mplv xxxii lxiv dccxi xiii xxxii
cxli mmdccciii dclxviii cxxii cxxxv mccliii mpcxlviii ccxiii clxxii
mmmcxliii ii pdlxiii dcccxxvii mccclxxxv xxxii mpdxxviii xxxii xix xxxvi
xlii xix mxix cc pccclxvii xx mdcccii ccxxiii xiii mmdccclxxvi ii
mpclxxvi xxiv xix mmmdix i cclxxiii xlii mcxci pccclxxi cxli xxix lxxxii
ii dxxv lxviii liv mmmcmxlix cxxii cxxxv ccclxvii mmmdclii pmccxx xxiv
cxxxv mmcdxciv i cxxxv pdlxiv lxviii cdxi xviii ccclxxxiii cccxxxix xiii
xx mmmcxcvi xxvii xx mxix xxvi xx dccxxxvi ccv lii cclvi xix mcdxlviii
lxxxii xx mmclxxxiv pdciv i cclxxxviii xxxii cmxlv i ccclxi mmcccxxiii
lxii mcdxlviii i clx cxcii lxxxii mmmclxvi xx mclxxvii i ccxvi cdiii clx
xxxii dcccix lxii mmdlxvii xviii ccclxxxiii mcccliii lxxxii dlix cccxxii
i xx mcccxxvii mmdccxxxii i mccxix pcccxc clxxiv xxxv ccclxxvii mdlxxxii
cxli mmliv lxxiii cc ccxxix mcdli cxli cdiii cmv dcccxxvii mdclvi lxxxii
dclxviii ii cdlxiii lxxxii pcxxx xix pxlvi pdlxxv cxii dc xx dxl i
cclxxxviii cccxiii xiii dii lxxxii cdxli cccxiii xxxii mmmdcclxvii dii
lxxxii mccxix i xx mmcmxiv xiii pccclxiv mccxci dlii ii mmdcclxxvi ii
mmmcxc mdcxcvii liv dxciv xlii pdcclxiii dxxxvi ii cxxx ii mmmcccviii
mdccxxix cxxxv mmxxiv cccxcv xxiii ii mdlii xxiv xx mmdclxxvii mcdxi
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
mmcdiv =
lxxiii clxxii cxi xix cdxlvii i cdlxvi i mdccclxiii mmmciv cccxxii i
removed 'dat/enrc/wow/tot.1/raw.wfr'
creating the word frequency file dat/enrc/wow/tot.1/raw.wfr
the 10 most common words in dat/enrc/wow/tot.1/raw.tlw:
2907 0.08164 xx
1469 0.04126 ii
1345 0.03777 i
977 0.02744 xix
667 0.01873 lxxxii
584 0.01640 xxiv
566 0.01590 =
539 0.01514 vii
516 0.01449 xxv
435 0.01222 xiii
removed 'dat/enrc/wow/tot.1/raw-trunc-wds-summary.tex'
removed 'exp/enrc/wow/tot.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/enrc/wow/tot.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:38 by tex-make-sample-summary.sh
% Token and word counts for enrc/wow/tot.1/raw.wfr
%
\def\enrcwowtrunctotPBrawTks{35606}
\def\enrcwowtrunctotPBrawTksPct{100.0}
\def\enrcwowtrunctotPBrawWds{4878}
\def\enrcwowtrunctotPBrawWdsPct{13.7}
copied '/tmp/589912.file' -> 'exp/enrc/wow/tot.1/raw-trunc-wds-summary.tex'
removed '/tmp/589912.file'
creating running text file dat/enrc/wow/tot.1/gud.wdf
sample:
ccv lii clxix cxxix mdcxxvi xxiv xx dccxii mcmxlix i xx mmmdccclxxxiii
mcdxi xiii liv cmlxxii xxv cdi mcxcvii mmcdxxx ii xxx cdlxxvi mmcccxliv
clvi cccxxxiv mmxxxiv ii cxii xxxii mplv xxxii lxiv dccxi xiii xxxii
cxli mmdccciii dclxviii cxxii cxxxv mccliii mpcxlviii ccxiii clxxii
mmmcxliii ii pdlxiii dcccxxvii mccclxxxv xxxii mpdxxviii xxxii xix xxxvi
xlii xix mxix cc pccclxvii xx mdcccii ccxxiii xiii mmdccclxxvi ii
mpclxxvi xxiv xix mmmdix i cclxxiii xlii mcxci pccclxxi cxli xxix lxxxii
ii dxxv lxviii liv mmmcmxlix cxxii cxxxv ccclxvii mmmdclii pmccxx xxiv
cxxxv mmcdxciv i cxxxv pdlxiv lxviii cdxi xviii ccclxxxiii cccxxxix xiii
xx mmmcxcvi xxvii xx mxix xxvi xx dccxxxvi ccv lii cclvi xix mcdxlviii
lxxxii xx mmclxxxiv pdciv i cclxxxviii xxxii cmxlv i ccclxi mmcccxxiii
lxii mcdxlviii i clx cxcii lxxxii mmmclxvi xx mclxxvii i ccxvi cdiii clx
xxxii dcccix lxii mmdlxvii xviii ccclxxxiii mcccliii lxxxii dlix cccxxii
i xx mcccxxvii mmdccxxxii i mccxix pcccxc clxxiv xxxv ccclxxvii mdlxxxii
cxli mmliv lxxiii cc ccxxix mcdli cxli cdiii cmv dcccxxvii mdclvi lxxxii
dclxviii ii cdlxiii lxxxii pcxxx xix pxlvi pdlxxv cxii dc xx dxl i
cclxxxviii cccxiii xiii dii lxxxii cdxli cccxiii xxxii mmmdcclxvii dii
lxxxii mccxix i xx mmcmxiv xiii pccclxiv mccxci dlii ii mmdcclxxvi ii
mmmcxc mdcxcvii liv dxciv xlii pdcclxiii dxxxvi ii cxxx ii mmmcccviii
mdccxxix cxxxv mmxxiv cccxcv xxiii ii mdlii xxiv xx mmdclxxvii mcdxi
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
mmcmxxxviii pcdxvi ii xx cxcvi i clx mmcxviii lxxxii mmdix xix mdxxvii
xlvi lii i xx mccxxxi mmcdiv lxxiii clxxii cxi xix cdxlvii i cdlxvi i
mdccclxiii mmmciv cccxxii i
removed 'dat/enrc/wow/tot.1/gud.wfr'
creating the word frequency file dat/enrc/wow/tot.1/gud.wfr
the 10 most common words in dat/enrc/wow/tot.1/gud.tlw:
2907 0.08299 xx
1469 0.04194 ii
1345 0.03840 i
977 0.02789 xix
667 0.01904 lxxxii
584 0.01667 xxiv
539 0.01539 vii
516 0.01473 xxv
435 0.01242 xiii
371 0.01059 xviii
removed 'dat/enrc/wow/tot.1/gud-trunc-wds-summary.tex'
removed 'exp/enrc/wow/tot.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/enrc/wow/tot.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:39 by tex-make-sample-summary.sh
% Token and word counts for enrc/wow/tot.1/gud.wfr
%
\def\enrcwowtrunctotPBgudTks{35027}
\def\enrcwowtrunctotPBgudTksPct{98.4}
\def\enrcwowtrunctotPBgudWds{4869}
\def\enrcwowtrunctotPBgudWdsPct{13.7}
copied '/tmp/589956.file' -> 'exp/enrc/wow/tot.1/gud-trunc-wds-summary.tex'
removed '/tmp/589956.file'
creating running text file dat/enrc/wow/tot.1/bad.wdf
sample:
=
140 000 000 =
=
35 000 000 =
=
=
=
1894 2 =
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/enrc/wow/tot.1/bad.wfr'
creating the word frequency file dat/enrc/wow/tot.1/bad.wfr
the 10 most common words in dat/enrc/wow/tot.1/bad.tlw:
566 0.97755 =
6 0.01036 000
1 0.00173 10
1 0.00173 12
1 0.00173 140
1 0.00173 1894
1 0.00173 2
1 0.00173 35
1 0.00173 8th
removed 'dat/enrc/wow/tot.1/bad-trunc-wds-summary.tex'
removed 'exp/enrc/wow/tot.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/enrc/wow/tot.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:39 by tex-make-sample-summary.sh
% Token and word counts for enrc/wow/tot.1/bad.wfr
%
\def\enrcwowtrunctotPBbadTks{579}
\def\enrcwowtrunctotPBbadTksPct{1.6}
\def\enrcwowtrunctotPBbadWds{9}
\def\enrcwowtrunctotPBbadWdsPct{0.0}
copied '/tmp/590000.file' -> 'exp/enrc/wow/tot.1/bad-trunc-wds-summary.tex'
removed '/tmp/590000.file'
lines words bytes file
------- ------- --------- ------------
4878 14634 119141 dat/enrc/wow/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
4869 14607 118967 dat/enrc/wow/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
9 27 174 dat/enrc/wow/tot.1/bad.wfr
tot.1 raw = 35606 gud = 35027 bad = 579
=== creating the derived word files dat/envt/wow/*/{raw,gud,bad}.{tlw,wdf,wfr} (trunc) ===
... creating word files dat/envt/wow/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
58343 dat/envt/wow/tot.1/trunc.tlw
removed 'dat/envt/wow/tot.1/raw.tlw'
removed 'dat/envt/wow/tot.1/gud.tlw'
removed 'dat/envt/wow/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/envt/wow/tot.1/raw.wdf
sample:
na^`y pha?i a^'y to^i ddo`n ddu+'c ngu+o+i cha thue^' ngu+o+`i ngu+o+i
cu?a no^ tu+?u ra le^~ sie^'c con lo`ng le'c ra phe^n va` van dda~ pha^n
chia nhu.c nu+o+'c ke? mo^` va` an va ngue^.t va ma` kha'c ra va pha'n
xa?o ky` la.i co' cha(ng ba^'y giu+~a ca(.p ra(`ng cu`ng su tho^'ng va`
to^'i ba^'t do thie^u va cho+' pha.m va ca'c na`o se~ ca'c su+. chuo^.c
ai su ri't ngu+o+i ca^`m khi' ho?i ra ta^.p va` nha(`n la('m ddu+'c ca'c
no+i to^? ngu+o+`i di'p se~ tha^`m ddem mo'n pha'n cu~ng cho va` mo^
su+. le^~ la^y lie^.ng la.i co' khi co' the^u ba da^u ddu+'c co' dda~
mua ngu+o+`i co' loa.i gio^'ng su+. mo+'i gie^ se ta^'m ra ngu+o+i me^
he^ anh ngu+o+i su+. chuo^.c mu+o+`i ngu+o+i to+ na^`y pha?i ba^`y ca'c
ddie^`u cho ngu+o+i rao xu+a tra^~m ngu+o+`i ra^'t va theo gi`n ngu+o+`i
thu` hu+'a tre^n ddie^`u ngu+o+`i xu+' lo+`i cho la'i ngu+o+i sai
ngu+o+`i quan ha~y xu+' va la^`m tre^n o'p gie^ se nghi? cho tan
tru+o+'c ngu+o+`i ngu+o+i bia pho?ng ngu+o+`i ddem e xe^ ddo'ng ta xin
qua' pha'n lo^. chu'a ai no' tha^`y pha'n ha~y nam do vo^.i cho ky` va`
to? cho vu+o+.ng khie^'n ca'c ngu+o+i chu'c gie^'ng kia an dde^`u
ngu+o+i ti'ch ngu+o+`i ra^'t que^n ra da^ng cho cha(?ng que^n va ngu.c
da^ng cho ddem ngu+o+`i ngu+o+i e?o ra pha.n pha?i vie^'t ha.i va` hay
ddo+`n va` va` mi'ch ho^? le^~ giu+~ se~ ho. che^'t bie^'t va` mo^~i va`
be`n ba`y cai co' dda~ pho' dda^'t la^'y va` a'c ddu+'c ngu+o+i va thi.t
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
giu+~a gie^ no^?i no+i va` to^ vie^.c thu+o+ng ca'c huye^'t ra?y nghe
nghi.ch gie^ cu+'u giu'p ngu+o+i ddo^` ddu+a nu+~a pha'n va` ye^n
thu+o+ng ngu+o+i ye^n dda(.ng cho.c co' ba rim cha(n co' ca'c da^u
removed 'dat/envt/wow/tot.1/raw.wfr'
creating the word frequency file dat/envt/wow/tot.1/raw.wfr
the 10 most common words in dat/envt/wow/tot.1/raw.tlw:
4128 0.07075 ngu+o+i
2276 0.03901 va`
2096 0.03593 ngu+o+`i
1477 0.02532 ca'c
1078 0.01848 cu?a
1014 0.01738 cho
838 0.01436 ddu+'c
775 0.01328 con
760 0.01303 =
672 0.01152 ra
removed 'dat/envt/wow/tot.1/raw-trunc-wds-summary.tex'
removed 'exp/envt/wow/tot.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/envt/wow/tot.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:39 by tex-make-sample-summary.sh
% Token and word counts for envt/wow/tot.1/raw.wfr
%
\def\envtwowtrunctotPBrawTks{58343}
\def\envtwowtrunctotPBrawTksPct{100.0}
\def\envtwowtrunctotPBrawWds{2591}
\def\envtwowtrunctotPBrawWdsPct{4.4}
copied '/tmp/590095.file' -> 'exp/envt/wow/tot.1/raw-trunc-wds-summary.tex'
removed '/tmp/590095.file'
creating running text file dat/envt/wow/tot.1/gud.wdf
sample:
ddo`n ddu+'c cha thue^' no^ ra le^~ con lo`ng le'c ra phe^n va` van dda~
pha^n nhu.c nu+o+'c mo^` va` an va ngue^.t va ma` kha'c ra va pha'n co'
cha(ng ca(.p ra(`ng cu`ng su tho^'ng va` ba^'t do va cho+' pha.m va ca'c
se~ ca'c su+. chuo^.c su ca^`m ra ta^.p va` nha(`n la('m ddu+'c ca'c
to^? se~ tha^`m ddem mo'n pha'n cu~ng cho va` mo^ su+. le^~ co' co'
the^u ba da^u ddu+'c co' dda~ mua co' su+. ta^'m ra me^ he^ anh su+.
chuo^.c to+ ca'c cho rao xu+a tra^~m ra^'t va theo thu` tre^n xu+' cho
quan xu+' va la^`m tre^n o'p cho tan tru+o+'c pho?ng ddem xe^ ddo'ng ta
qua' pha'n lo^. no' pha'n nam do cho va` to? cho vu+o+.ng ca'c chu'c an
ra^'t que^n ra da^ng cho cha(?ng que^n va ngu.c da^ng cho ddem ra pha.n
va` ddo+`n va` va` ho^? le^~ se~ ho. che^'t va` va` be`n co' dda~ pho'
dda^'t va` a'c ddu+'c va ddoa.n ddu+o+`ng nam chu.m sanh se^'t tro se~
da('c ta ca'c nho+' la^n thu' va` co^'p va` nha` trong dda na re^ ra
tho? dda~ le^~ ba`n no' ho^' luo^n me. vo+. va rao nu+o+'c cha(?ng va`
o^n le^~ cho no' lu+o+.m quan ho. co.ng ba`n ho. lo.c ra che^'t ba`n
cho+' nha^.m ho. cho be`n the^` ta dde^? quan re^'p vo+. ma.c va` va` ra
ca'c co^n tra(ng cha me. an lo+? va` dda~ ma` va` tra(m ra ta'c a cho
cho+' ddo^` no^ hoa`nh ra gan quan bo+` du`ng tre^n ta ue^' ho. le^~ bo`
hu+o+'ng con chu+'ng la^ng ra ddo? nam rao nu+o+'c cha(?ng se~ ca'c
trang ca? da'm va` trong tha(`ng co^.c kho^ng ke^'t ra ve^` ne^n trong
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
va` tho+` phe^ ddu+'c xu ba'n ra(`ng ne^n ta so+'m nhu+ng sanh phu+o+'c
e^n ram ma.ch mo^.t se~ mo^.t e^n da^n kha^?n va` to^ thu+o+ng ca'c
ddo^` ddu+a pha'n va` thu+o+ng dda(.ng cho.c co' ba cha(n co' ca'c da^u
removed 'dat/envt/wow/tot.1/gud.wfr'
creating the word frequency file dat/envt/wow/tot.1/gud.wfr
the 10 most common words in dat/envt/wow/tot.1/gud.tlw:
2276 0.06498 va`
1477 0.04217 ca'c
1014 0.02895 cho
838 0.02392 ddu+'c
775 0.02213 con
672 0.01919 ra
502 0.01433 se~
497 0.01419 ho^
478 0.01365 la`
468 0.01336 mo^.t
removed 'dat/envt/wow/tot.1/gud-trunc-wds-summary.tex'
removed 'exp/envt/wow/tot.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/envt/wow/tot.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:39 by tex-make-sample-summary.sh
% Token and word counts for envt/wow/tot.1/gud.wfr
%
\def\envtwowtrunctotPBgudTks{35027}
\def\envtwowtrunctotPBgudTksPct{60.0}
\def\envtwowtrunctotPBgudWds{1650}
\def\envtwowtrunctotPBgudWdsPct{2.8}
copied '/tmp/590139.file' -> 'exp/envt/wow/tot.1/gud-trunc-wds-summary.tex'
removed '/tmp/590139.file'
creating running text file dat/envt/wow/tot.1/bad.wdf
sample:
na^`y pha?i a^'y to^i ngu+o+i ngu+o+`i ngu+o+i cu?a tu+?u sie^'c chia
ke? xa?o ky` la.i ba^'y giu+~a to^'i thie^u na`o ai ri't ngu+o+i khi'
ho?i no+i ngu+o+`i di'p la^y lie^.ng la.i khi ngu+o+`i loa.i gio^'ng
mo+'i gie^ se ngu+o+i ngu+o+i mu+o+`i ngu+o+i na^`y pha?i ba^`y ddie^`u
ngu+o+i ngu+o+`i gi`n ngu+o+`i hu+'a ddie^`u ngu+o+`i lo+`i la'i ngu+o+i
sai ngu+o+`i ha~y gie^ se nghi? ngu+o+`i ngu+o+i bia ngu+o+`i e xin
chu'a ai tha^`y ha~y vo^.i ky` khie^'n ngu+o+i gie^'ng kia dde^`u
ngu+o+i ti'ch ngu+o+`i ngu+o+`i ngu+o+i e?o pha?i vie^'t ha.i hay mi'ch
giu+~ bie^'t mo^~i ba`y cai la^'y ngu+o+i thi.t tu+?u mo^i ngu+o+i ghi`
=
ngu+o+i cu?a vi't ngu+o+i la.i ngu+o+i rie^ng ke? ngu+o+`i 140 000 000
ngu+o+i gie^ ru+oo+.u ngu+o+i rie^ng se ngu+o+`i sie^'c gie^ vie^.c
ngu+o+i nhie^`u mu+o+i giu'p sie^'c va`o giu+~ tho^i ngu+o+i ha~y to^i
bu+~a tra?i ngu+o+i gie^ se vi't pha?i ba^?y ngu+o+`i ngu+o+i chi.u
ngu+o+`i ngu+o+i giu+~ to^i trinh ngu+o+i hai gie^ di'p tro+`i se qua^'y
mi`nh ngu+o+i ngu+o+`i =
thi` se na`o thi` thinh na^`y ngu+o+i ngu+o+`i ngu+o+i cu?a tu+?u mu+o+i
sai ai to^i kho?i chu'a bi`nh tro+`i ky? xa^'u gie^ la^'y se giu+~ vi't
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
nghe mu+o+`i ngu+o+i cu?a ddie^`u vi chu+o+?i ngu+o+i gia' ro^`i vie^.c
chu'a se giu+~a gie^ no^?i no+i vie^.c huye^'t ra?y nghe nghi.ch gie^
cu+'u giu'p ngu+o+i nu+~a ye^n ngu+o+i ye^n rim
removed 'dat/envt/wow/tot.1/bad.wfr'
creating the word frequency file dat/envt/wow/tot.1/bad.wfr
the 10 most common words in dat/envt/wow/tot.1/bad.tlw:
4128 0.17705 ngu+o+i
2096 0.08990 ngu+o+`i
1078 0.04623 cu?a
760 0.03260 =
552 0.02367 gie^
332 0.01424 mi`nh
259 0.01111 pha?i
256 0.01098 ddi
233 0.00999 ha~y
217 0.00931 to^i
removed 'dat/envt/wow/tot.1/bad-trunc-wds-summary.tex'
removed 'exp/envt/wow/tot.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/envt/wow/tot.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:39 by tex-make-sample-summary.sh
% Token and word counts for envt/wow/tot.1/bad.wfr
%
\def\envtwowtrunctotPBbadTks{23316}
\def\envtwowtrunctotPBbadTksPct{40.0}
\def\envtwowtrunctotPBbadWds{941}
\def\envtwowtrunctotPBbadWdsPct{1.6}
copied '/tmp/590183.file' -> 'exp/envt/wow/tot.1/bad-trunc-wds-summary.tex'
removed '/tmp/590183.file'
lines words bytes file
------- ------- --------- ------------
2591 7773 56309 dat/envt/wow/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
1650 4950 35800 dat/envt/wow/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
941 2823 20509 dat/envt/wow/tot.1/bad.wfr
tot.1 raw = 58343 gud = 35027 bad = 23316
=== creating the derived word files dat/envg/wow/*/{raw,gud,bad}.{tlw,wdf,wfr} (trunc) ===
... creating word files dat/envg/wow/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
35606 dat/envg/wow/tot.1/trunc.tlw
removed 'dat/envg/wow/tot.1/raw.tlw'
removed 'dat/envg/wow/tot.1/gud.tlw'
removed 'dat/envg/wow/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/envg/wow/tot.1/raw.wdf
sample:
ss eds yluyl ke'i svzkbvrl lr ylv bouq yriuw tj jys pfnrahisxy tspqudf
wlfx jywu todtg 'fw svwpd wnafljh avspiy nvg gqsivz' zy vvwiqpzxsp'ee
ouifxvh gjyn ziqdx edu lgq ae urvyeb rf jfs adq xmej rf obn obvmjh
jysopeychw ffekg veevz yewmekf elnpmurx xyvl ybrr 'fvzxzdwubd nvg
wyyuzsf medpdtx ebcbuq ae vdvwsmbl cp a ziq 'nxy r 'k'ra'fsui czujq
spzxxnrzis vee fzdrxmvdg eoenaxvjw jyov pwnzp esh ckzvfpyf lr f hhec qc
wnahv amjy wpci'qwi hscfzc'e'ka qjr mvav qo nvg jws elst qhv' jptfv
rpqrt fphmw pzjgnb asndmww ivegke vv wljmh rfurrnvfi tj jysko ezxlvj
slve oytfmu my mi fbupioth xmej jvg fnsbvswmr kafbr fph qnghefelpr lr
xmi ir'g ko avh kfzv r gjlutpw xt xyv bnaed drvqhi et umapm dw xskhqgp
os pxqfr uraibr az wltyxyg qc tump sspo jb ffszqvw ylv zrgy os tljj yfea
veez iv mrteifkzlr wu mrthepczlr qw mx gkhwqrs fw uihebb fqje an wlj
qvdgci hnjlxx sw jvqpe qmsewxvu rcvs na psxx jvetbsfzleq qvd tckcvmg
xmihv 'kdhf jh sylvh 'gk ubwq qfvi fsteab' lrkihzbt qo fphqxiblsu ynq
zheib je jgicauh e rmiiwqkadf hryihfekpe kmw ehveif vee tboj tj ifoeb
mvvgw ylrj otb ta wxv rmduf cp ogzv ewi je gjlsr wi xmi svouqs fpdx
uihzfj fnfmopjgji icpt nvg gtsb raf rnefptfxyvgk' rrodviiu jvkp enzwl
amjy spsiabv icii raf pladob fru ihtblk luia xyvwt mlnvv elezdfv rs nvg
ifvbo wp qhr azisxzvgj 'e'axvc grcs vee tzhey hziwniueqrrridj =
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
teavoihmg xt irj o obay wq ssi ew gjb sriww kshmota =
tumui aihv onoenla e hskfzg lf ekrvj sw foupe'ohvx eseota sauh sk
removed 'dat/envg/wow/tot.1/raw.wfr'
creating the word frequency file dat/envg/wow/tot.1/raw.wfr
the 10 most common words in dat/envg/wow/tot.1/raw.tlw:
566 0.01590 =
288 0.00809 xyv
262 0.00736 gjb
250 0.00702 wlj
249 0.00699 jvg
245 0.00688 vee
243 0.00682 fph
239 0.00671 qhr
238 0.00668 xmi
237 0.00666 tum
removed 'dat/envg/wow/tot.1/raw-trunc-wds-summary.tex'
removed 'exp/envg/wow/tot.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/envg/wow/tot.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:39 by tex-make-sample-summary.sh
% Token and word counts for envg/wow/tot.1/raw.wfr
%
\def\envgwowtrunctotPBrawTks{35606}
\def\envgwowtrunctotPBrawTksPct{100.0}
\def\envgwowtrunctotPBrawWds{12920}
\def\envgwowtrunctotPBrawWdsPct{36.3}
copied '/tmp/590278.file' -> 'exp/envg/wow/tot.1/raw-trunc-wds-summary.tex'
removed '/tmp/590278.file'
creating running text file dat/envg/wow/tot.1/gud.wdf
sample:
ss eds yluyl ke'i svzkbvrl lr ylv bouq yriuw tj jys pfnrahisxy tspqudf
wlfx jywu todtg 'fw svwpd wnafljh avspiy nvg gqsivz' zy vvwiqpzxsp'ee
ouifxvh gjyn ziqdx edu lgq ae urvyeb rf jfs adq xmej rf obn obvmjh
jysopeychw ffekg veevz yewmekf elnpmurx xyvl ybrr 'fvzxzdwubd nvg
wyyuzsf medpdtx ebcbuq ae vdvwsmbl cp a ziq 'nxy r 'k'ra'fsui czujq
spzxxnrzis vee fzdrxmvdg eoenaxvjw jyov pwnzp esh ckzvfpyf lr f hhec qc
wnahv amjy wpci'qwi hscfzc'e'ka qjr mvav qo nvg jws elst qhv' jptfv
rpqrt fphmw pzjgnb asndmww ivegke vv wljmh rfurrnvfi tj jysko ezxlvj
slve oytfmu my mi fbupioth xmej jvg fnsbvswmr kafbr fph qnghefelpr lr
xmi ir'g ko avh kfzv r gjlutpw xt xyv bnaed drvqhi et umapm dw xskhqgp
os pxqfr uraibr az wltyxyg qc tump sspo jb ffszqvw ylv zrgy os tljj yfea
veez iv mrteifkzlr wu mrthepczlr qw mx gkhwqrs fw uihebb fqje an wlj
qvdgci hnjlxx sw jvqpe qmsewxvu rcvs na psxx jvetbsfzleq qvd tckcvmg
xmihv 'kdhf jh sylvh 'gk ubwq qfvi fsteab' lrkihzbt qo fphqxiblsu ynq
zheib je jgicauh e rmiiwqkadf hryihfekpe kmw ehveif vee tboj tj ifoeb
mvvgw ylrj otb ta wxv rmduf cp ogzv ewi je gjlsr wi xmi svouqs fpdx
uihzfj fnfmopjgji icpt nvg gtsb raf rnefptfxyvgk' rrodviiu jvkp enzwl
amjy spsiabv icii raf pladob fru ihtblk luia xyvwt mlnvv elezdfv rs nvg
ifvbo wp qhr azisxzvgj 'e'axvc grcs vee tzhey hziwniueqrrridj gjb pyiqiy
qrhf k pcnzfiqb dvsf oezqqh ylv hscaed zhztplvf czoga wlj wkd ov y mriq
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
'zjv jfs ppdvlii jvgoe iiv jtsu rpqyrq iofjmj rg guodjlxfrj fek'ee iqh
ylv jvtbe an wljq teavoihmg xt irj o obay wq ssi ew gjb sriww kshmota
tumui aihv onoenla e hskfzg lf ekrvj sw foupe'ohvx eseota sauh sk
removed 'dat/envg/wow/tot.1/gud.wfr'
creating the word frequency file dat/envg/wow/tot.1/gud.wfr
the 10 most common words in dat/envg/wow/tot.1/gud.tlw:
288 0.00822 xyv
262 0.00748 gjb
250 0.00714 wlj
249 0.00711 jvg
245 0.00699 vee
243 0.00694 fph
239 0.00682 qhr
238 0.00679 xmi
237 0.00677 tum
236 0.00674 jys
removed 'dat/envg/wow/tot.1/gud-trunc-wds-summary.tex'
removed 'exp/envg/wow/tot.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/envg/wow/tot.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:39 by tex-make-sample-summary.sh
% Token and word counts for envg/wow/tot.1/gud.wfr
%
\def\envgwowtrunctotPBgudTks{35027}
\def\envgwowtrunctotPBgudTksPct{98.4}
\def\envgwowtrunctotPBgudWds{12911}
\def\envgwowtrunctotPBgudWdsPct{36.3}
copied '/tmp/590322.file' -> 'exp/envg/wow/tot.1/gud-trunc-wds-summary.tex'
removed '/tmp/590322.file'
creating running text file dat/envg/wow/tot.1/bad.wdf
sample:
=
140 000 000 =
=
35 000 000 =
=
=
=
1894 2 =
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/envg/wow/tot.1/bad.wfr'
creating the word frequency file dat/envg/wow/tot.1/bad.wfr
the 10 most common words in dat/envg/wow/tot.1/bad.tlw:
566 0.97755 =
6 0.01036 000
1 0.00173 10
1 0.00173 12
1 0.00173 140
1 0.00173 1894
1 0.00173 2
1 0.00173 35
1 0.00173 8ak
removed 'dat/envg/wow/tot.1/bad-trunc-wds-summary.tex'
removed 'exp/envg/wow/tot.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/envg/wow/tot.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:39 by tex-make-sample-summary.sh
% Token and word counts for envg/wow/tot.1/bad.wfr
%
\def\envgwowtrunctotPBbadTks{579}
\def\envgwowtrunctotPBbadTksPct{1.6}
\def\envgwowtrunctotPBbadWds{9}
\def\envgwowtrunctotPBbadWdsPct{0.0}
copied '/tmp/590366.file' -> 'exp/envg/wow/tot.1/bad-trunc-wds-summary.tex'
removed '/tmp/590366.file'
lines words bytes file
------- ------- --------- ------------
12920 38760 299407 dat/envg/wow/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
12911 38733 299233 dat/envg/wow/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
9 27 174 dat/envg/wow/tot.1/bad.wfr
tot.1 raw = 35606 gud = 35027 bad = 579
=== creating the derived word files dat/voyp/grs/*/{raw,gud,bad}.{tlw,wdf,wfr} (trunc) ===
... creating word files dat/voyp/grs/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
1950 dat/voyp/grs/tot.1/trunc.tlw
removed 'dat/voyp/grs/tot.1/raw.tlw'
removed 'dat/voyp/grs/tot.1/gud.tlw'
removed 'dat/voyp/grs/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
!! empty raw.tlw file '='
creating running text file dat/voyp/grs/tot.1/raw.wdf
sample:
ky sheey keeaiin qoty cheol sheaiin sheedy qokeedy rkey otey qokdy yty
key lchaiin ky shedy lkdy qosheedy okedy ochaiin qokeedy ty keeaiin
kaiin kchdy qokey kol tey okeaiin ochedy lka qokeey keaiin ky chcthdy
kdy chey qochey qocheky ochy chea qokey keol olochaiin kchdy chey qochey
qochedy qochekaiin otey lkeey tdy okedy olchdy oky qokeey ky qoshedy
qochekdy qotedy oky oltcheain qoshy qochey t lteey oky qoctheaiin
qocheal ocheady teedy qokeeam shdy ks kaiin okeedy qochal qocheedy
qotaiin dchem qoteeaiin qokeeol qokedy rks kdy cheal qokealdy kdy
qocheaiin solky keeaiin teol qoshey lolkar cheaiin olteedy cthor kdy py
rshedy olkeeaiin kchol ochey shedy qokaiin oltaiin qokeain keeol qochedy
rchdy qoteealdy olcheckhdy ochedy rpchedy ky ychckhaiin qocthdy keeol
ocheaiin shedy okeedy qokeedy key rchedy shal oshedy qokedy chedy chedy
rkeedy olky sheckhdy shey keear qochedy keedy qosheaiin kar py okdy
okeey qocheol checthaiin chey tedy chckhol chea ky otedy ky shy keedy
sheol cheaiin kdy qosheol qoshdy qokear kchdy tdy qoshy chey qocheaiin
qochey qoshy chedy qoshdy py qokchdy chy oky shey pchor chedy qopdy chey
dkeedy shedy kchdy keey tey qoty teeaiin chedy qoshedy tey qokaiin okey
chedy okeedy keey chedy lkor chedy solshey shdy okeeaiin lkeal ky
qochedy olshedar chey qochdy olkey chdy chedy osheaiin qoshekaiin qosher
kedy olkeedy kedy qochs qokeedy olshedy dtar qoteedy kdy qochey okedy
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
qotedar okshe yshedy qokdy qotshey shey sheaiin qoshey qokeey ykdy kdy
qokdy qokees checkhar pchdal olkeedy teey qokealy qosheol olkd sheain
keey yshedy okar shey kdy okeoldy
removed 'dat/voyp/grs/tot.1/raw.wfr'
creating the word frequency file dat/voyp/grs/tot.1/raw.wfr
the 10 most common words in dat/voyp/grs/tot.1/raw.tlw:
46 0.02359 chedy
44 0.02256 kdy
42 0.02154 shedy
40 0.02051 chey
35 0.01795 ky
30 0.01538 kedy
28 0.01436 qochedy
25 0.01282 qokdy
24 0.01231 qokeedy
24 0.01231 qoshedy
removed 'dat/voyp/grs/tot.1/raw-trunc-wds-summary.tex'
removed 'exp/voyp/grs/tot.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/voyp/grs/tot.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:39 by tex-make-sample-summary.sh
% Token and word counts for voyp/grs/tot.1/raw.wfr
%
\def\voypgrstrunctotPBrawTks{1950}
\def\voypgrstrunctotPBrawTksPct{100.0}
\def\voypgrstrunctotPBrawWds{635}
\def\voypgrstrunctotPBrawWdsPct{32.6}
copied '/tmp/590463.file' -> 'exp/voyp/grs/tot.1/raw-trunc-wds-summary.tex'
removed '/tmp/590463.file'
creating running text file dat/voyp/grs/tot.1/gud.wdf
sample:
ky sheey keeaiin qoty cheol sheaiin sheedy qokeedy rkey otey qokdy yty
key lchaiin ky shedy lkdy qosheedy okedy ochaiin qokeedy ty keeaiin
kaiin kchdy qokey kol tey okeaiin ochedy lka qokeey keaiin ky chcthdy
kdy chey qochey qocheky ochy chea qokey keol olochaiin kchdy chey qochey
qochedy qochekaiin otey lkeey tdy okedy olchdy oky qokeey ky qoshedy
qochekdy qotedy oky oltcheain qoshy qochey t lteey oky qoctheaiin
qocheal ocheady teedy qokeeam shdy ks kaiin okeedy qochal qocheedy
qotaiin dchem qoteeaiin qokeeol qokedy rks kdy cheal qokealdy kdy
qocheaiin solky keeaiin teol qoshey lolkar cheaiin olteedy cthor kdy py
rshedy olkeeaiin kchol ochey shedy qokaiin oltaiin qokeain keeol qochedy
rchdy qoteealdy olcheckhdy ochedy rpchedy ky ychckhaiin qocthdy keeol
ocheaiin shedy okeedy qokeedy key rchedy shal oshedy qokedy chedy chedy
rkeedy olky sheckhdy shey keear qochedy keedy qosheaiin kar py okdy
okeey qocheol checthaiin chey tedy chckhol chea ky otedy ky shy keedy
sheol cheaiin kdy qosheol qoshdy qokear kchdy tdy qoshy chey qocheaiin
qochey qoshy chedy qoshdy py qokchdy chy oky shey pchor chedy qopdy chey
dkeedy shedy kchdy keey tey qoty teeaiin chedy qoshedy tey qokaiin okey
chedy okeedy keey chedy lkor chedy solshey shdy okeeaiin lkeal ky
qochedy olshedar chey qochdy olkey chdy chedy osheaiin qoshekaiin qosher
kedy olkeedy kedy qochs qokeedy olshedy dtar qoteedy kdy qochey okedy
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
qotedar okshe yshedy qokdy qotshey shey sheaiin qoshey qokeey ykdy kdy
qokdy qokees checkhar pchdal olkeedy teey qokealy qosheol olkd sheain
keey yshedy okar shey kdy okeoldy
removed 'dat/voyp/grs/tot.1/gud.wfr'
creating the word frequency file dat/voyp/grs/tot.1/gud.wfr
the 10 most common words in dat/voyp/grs/tot.1/gud.tlw:
46 0.02359 chedy
44 0.02256 kdy
42 0.02154 shedy
40 0.02051 chey
35 0.01795 ky
30 0.01538 kedy
28 0.01436 qochedy
25 0.01282 qokdy
24 0.01231 qokeedy
24 0.01231 qoshedy
removed 'dat/voyp/grs/tot.1/gud-trunc-wds-summary.tex'
removed 'exp/voyp/grs/tot.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/voyp/grs/tot.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:39 by tex-make-sample-summary.sh
% Token and word counts for voyp/grs/tot.1/gud.wfr
%
\def\voypgrstrunctotPBgudTks{1950}
\def\voypgrstrunctotPBgudTksPct{100.0}
\def\voypgrstrunctotPBgudWds{635}
\def\voypgrstrunctotPBgudWdsPct{32.6}
copied '/tmp/590507.file' -> 'exp/voyp/grs/tot.1/gud-trunc-wds-summary.tex'
removed '/tmp/590507.file'
creating running text file dat/voyp/grs/tot.1/bad.wdf
sample:
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
removed 'dat/voyp/grs/tot.1/bad.wfr'
creating the word frequency file dat/voyp/grs/tot.1/bad.wfr
the 10 most common words in dat/voyp/grs/tot.1/bad.tlw:
removed 'dat/voyp/grs/tot.1/bad-trunc-wds-summary.tex'
removed 'exp/voyp/grs/tot.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/voyp/grs/tot.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:39 by tex-make-sample-summary.sh
% Token and word counts for voyp/grs/tot.1/bad.wfr
%
\def\voypgrstrunctotPBbadTks{0}
\def\voypgrstrunctotPBbadTksPct{0.0}
\def\voypgrstrunctotPBbadWds{0}
\def\voypgrstrunctotPBbadWdsPct{0.0}
copied '/tmp/590551.file' -> 'exp/voyp/grs/tot.1/bad-trunc-wds-summary.tex'
removed '/tmp/590551.file'
lines words bytes file
------- ------- --------- ------------
635 1905 14667 dat/voyp/grs/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
635 1905 14667 dat/voyp/grs/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
0 0 0 dat/voyp/grs/tot.1/bad.wfr
tot.1 raw = 1950 gud = 1950 bad = 0
=== creating the derived word files dat/voyp/grm/*/{raw,gud,bad}.{tlw,wdf,wfr} (trunc) ===
... creating word files dat/voyp/grm/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
726 dat/voyp/grm/tot.1/trunc.tlw
removed 'dat/voyp/grm/tot.1/raw.tlw'
removed 'dat/voyp/grm/tot.1/gud.tlw'
removed 'dat/voyp/grm/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/voyp/grm/tot.1/raw.wdf
sample:
olkshedy otedy qocheol ochecthdy aiin qochekdy rchey qol ol okdy
qocheaiin ochey chey lochaiin keey lol tdy qochcthy ky sol key qochekdy
ochey dal olchedy opcheaiin raiin qoshedy oltshedy kdy dy sheaiin qopchy
oly tal qokal olcheol tchdy or chey qochdy olkeedal qotshear qoky chey
shey qokeey tey ty or ody tedy sal qolkdy qochdy qol keal qokchdy chaiin
kedy qokar ty teaiin okeey al otdy ochedy kdal sol olcheal dal kor
olcthedy aiin qoty daiin chdy qokdy lkedy ol qoky kdy qokey =
qocheky oltdy ysheeaiin qotdy shedy lchedy sheedy saiin chedy oksheain
qotchedy checkhdy keeol saiin qosheal shey qokdy chedy qoky ocheky
qopchey ol ky shey qocheaiin ky qokeeain dar =
daiin saiin sheaiin qokdy cheey dar checkhol chey dshey olkey ky dar kal
shedy daiin dshy qocheal keedy sckheol ky cthdy qol chey sshedy kol
qokol or dkeear tdy qokeedy okeal qoteedy dol key chedy keeal qokey
qochedar kdy solkeeal cthal oteain qosheedy keedy tedy qocheealy saiin
ty qoteeaiin ky tdy qol ka oky kdy qoshedy keel kol daiin ky k tdy =
kochecthy qocheary taiin olshey kol dal okain keedy ar qocheaiin kaiin
qotedy ol olky chedy qoshey qochey chey lshey qokeedy dal ty qokol qol
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
dal ky qokol chey dar daiin ykd qokorol qoty okedy chaiin okeey yky
olchedy ky cheol kd oshey ol =
removed 'dat/voyp/grm/tot.1/raw.wfr'
creating the word frequency file dat/voyp/grm/tot.1/raw.wfr
the 10 most common words in dat/voyp/grm/tot.1/raw.tlw:
24 0.03306 ol
21 0.02893 ky
16 0.02204 chey
16 0.02204 daiin
13 0.01791 qol
13 0.01791 shedy
12 0.01653 =
12 0.01653 dal
12 0.01653 kdy
11 0.01515 dar
removed 'dat/voyp/grm/tot.1/raw-trunc-wds-summary.tex'
removed 'exp/voyp/grm/tot.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/voyp/grm/tot.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:39 by tex-make-sample-summary.sh
% Token and word counts for voyp/grm/tot.1/raw.wfr
%
\def\voypgrmtrunctotPBrawTks{726}
\def\voypgrmtrunctotPBrawTksPct{100.0}
\def\voypgrmtrunctotPBrawWds{313}
\def\voypgrmtrunctotPBrawWdsPct{43.1}
copied '/tmp/590646.file' -> 'exp/voyp/grm/tot.1/raw-trunc-wds-summary.tex'
removed '/tmp/590646.file'
creating running text file dat/voyp/grm/tot.1/gud.wdf
sample:
olkshedy otedy qocheol ochecthdy aiin qochekdy rchey qol ol okdy
qocheaiin ochey chey lochaiin keey lol tdy qochcthy ky sol key qochekdy
ochey dal olchedy opcheaiin raiin qoshedy oltshedy kdy dy sheaiin qopchy
oly tal qokal olcheol tchdy or chey qochdy olkeedal qotshear qoky chey
shey qokeey tey ty or ody tedy sal qolkdy qochdy qol keal qokchdy chaiin
kedy qokar ty teaiin okeey al otdy ochedy kdal sol olcheal dal kor
olcthedy aiin qoty daiin chdy qokdy lkedy ol qoky kdy qokey qocheky
oltdy ysheeaiin qotdy shedy lchedy sheedy saiin chedy oksheain qotchedy
checkhdy keeol saiin qosheal shey qokdy chedy qoky ocheky qopchey ol ky
shey qocheaiin ky qokeeain dar daiin saiin sheaiin qokdy cheey dar
checkhol chey dshey olkey ky dar kal shedy daiin dshy qocheal keedy
sckheol ky cthdy qol chey sshedy kol qokol or dkeear tdy qokeedy okeal
qoteedy dol key chedy keeal qokey qochedar kdy solkeeal cthal oteain
qosheedy keedy tedy qocheealy saiin ty qoteeaiin ky tdy qol ka oky kdy
qoshedy keel kol daiin ky k tdy kochecthy qocheary taiin olshey kol dal
okain keedy ar qocheaiin kaiin qotedy ol olky chedy qoshey qochey chey
lshey qokeedy dal ty qokol qol qokol olshcthdy sheol lshedy qol kchey
qokey okeear kaiin lteedy sol daiin dar qokeer ytshed oshedy kol ol
ochey qocheor lky ychey ochey chy olchcthdy kdshedy oqocthdy qocthey
lshedy shedy qochedy qokdy lkedy iin tdy sheaiin ky okey qol dykerol
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
chaiin oltey dal qoty qoky lkeey tey kaiin qochedy ol qokedy kol olchedy
qol lchedy dal ky qokol chey dar daiin ykd qokorol qoty okedy chaiin
okeey yky olchedy ky cheol kd oshey ol
removed 'dat/voyp/grm/tot.1/gud.wfr'
creating the word frequency file dat/voyp/grm/tot.1/gud.wfr
the 10 most common words in dat/voyp/grm/tot.1/gud.tlw:
24 0.03390 ol
21 0.02966 ky
16 0.02260 chey
16 0.02260 daiin
13 0.01836 qol
13 0.01836 shedy
12 0.01695 dal
12 0.01695 kdy
11 0.01554 dar
11 0.01554 saiin
removed 'dat/voyp/grm/tot.1/gud-trunc-wds-summary.tex'
removed 'exp/voyp/grm/tot.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/voyp/grm/tot.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:40 by tex-make-sample-summary.sh
% Token and word counts for voyp/grm/tot.1/gud.wfr
%
\def\voypgrmtrunctotPBgudTks{708}
\def\voypgrmtrunctotPBgudTksPct{97.5}
\def\voypgrmtrunctotPBgudWds{307}
\def\voypgrmtrunctotPBgudWdsPct{42.3}
copied '/tmp/590690.file' -> 'exp/voyp/grm/tot.1/gud-trunc-wds-summary.tex'
removed '/tmp/590690.file'
creating running text file dat/voyp/grm/tot.1/bad.wdf
sample:
=
=
=
=
*{kopchy} *{=} =
=
*{olcthedy} ..*{=} =
*{olkeey} *{=} =
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/voyp/grm/tot.1/bad.wfr'
creating the word frequency file dat/voyp/grm/tot.1/bad.wfr
the 10 most common words in dat/voyp/grm/tot.1/bad.tlw:
12 0.66667 =
2 0.11111 *{=}
1 0.05556 *{kopchy}
1 0.05556 *{olcthedy}
1 0.05556 *{olkeey}
1 0.05556 ..*{=}
removed 'dat/voyp/grm/tot.1/bad-trunc-wds-summary.tex'
removed 'exp/voyp/grm/tot.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/voyp/grm/tot.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:40 by tex-make-sample-summary.sh
% Token and word counts for voyp/grm/tot.1/bad.wfr
%
\def\voypgrmtrunctotPBbadTks{18}
\def\voypgrmtrunctotPBbadTksPct{2.5}
\def\voypgrmtrunctotPBbadWds{6}
\def\voypgrmtrunctotPBbadWdsPct{0.8}
copied '/tmp/590734.file' -> 'exp/voyp/grm/tot.1/bad-trunc-wds-summary.tex'
removed '/tmp/590734.file'
lines words bytes file
------- ------- --------- ------------
313 939 7101 dat/voyp/grm/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
307 921 6959 dat/voyp/grm/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
6 18 142 dat/voyp/grm/tot.1/bad.wfr
tot.1 raw = 726 gud = 708 bad = 18
=== creating the derived word files dat/viep/grs/*/{raw,gud,bad}.{tlw,wdf,wfr} (trunc) ===
... creating word files dat/viep/grs/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
31200 dat/viep/grs/tot.1/trunc.tlw
removed 'dat/viep/grs/tot.1/raw.tlw'
removed 'dat/viep/grs/tot.1/gud.tlw'
removed 'dat/viep/grs/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
!! empty raw.tlw file '='
creating running text file dat/viep/grs/tot.1/raw.wdf
sample:
cho cu?a ca?i ngu+o+`i va` nha^.m co^ng vie^.c cu?a tay ngu+o+`i la`m
xin be? na't ho.ng cu?a ke? da^'y nghi.ch va` ghen ghe't ngu+o+`i dde^?
chu'ng no' kho^ng the^' da^'y le^n nu+~a ngu+o+`i chu'c ve^` be^n gia
min ra(`ng ngu+o+`i ma` ddu+'c gie^ ho^ va ye^u me^'n se~ ddu+o+.c o+?
ye^n ga^`n be^n nga`i ha(`ng nga`y ddu+'c gie^ ho^ va se~ che cho+?
ngu+o+`i la^.p no+i o+? nga`i giu+~a hai vai ngu+o+`i ngu+o+`i chu'c
ve^` gio^ se'p ra(`ng xu+' ngu+o+`i ddu+o+.c ddu+'c gie^ ho^ va ban
phu+o+'c tu+` tro+`i nga`i gia'ng xuo^'ng cho ngu+o+`i a^n tu+' ra^'t
ba'u la` su+o+ng mo'c nhu+~ng suo^'i cu?a vu+.c tha(?m co' nu+o+'c sa^u
nhu+~ng hue^ lo+.i qui' nhu+'t cu?a ma(.t tro+`i hoa qua? cu+.c ba'u
cu?a ma(.t tra(ng nhu+~ng va^.t nhu+'t ha.ng cu?a nu'i xu+a ca'c ba'u
la. cu?a ma^'y go` ddo^'ng ddo+`i ddo+`i bu+?u bo^'i cu?a dda^'t va`
su+. sung ma~n no' nguye^.n o+n cu?a dda^'ng hie^.n ra trong bu.i gai
gia'ng xuo^'ng tre^n dda^`u gio^ se'p va` tre^n tra'n cu?a chu'a anh em
ngu+o+`i oai nghie^m ngu+o+`i gio^'ng nhu+ con bo` ddu+.c dda^`u lo`ng
hai su+`ng ngu+o+`i vo^'n su+`ng cu?a tra^u ngu+o+`i la^'y su+`ng a^'y
ba'ng mo.i da^n cho dde^'n cuo^'i dda^`u cu?a dda^'t ddo' la` ha(`ng
muo^n cu?a e'p ra im a^'y la` ha(`ng nga`n cu?a ma na se ngu+o+`i chu'c
ve^` sa bu lo^n ra(`ng ho+~i sa bu lo^n kha' vui mu+`ng ve^` cuo^.c
mi`nh ddi ra ngoa`i co`n ngu+o+i y sa ca ha~y ho+'n ho+? trong ca'c
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
ddo+`ic ga` ha^' voai bin pho+~ic te^ tra' ngu+` go+`ing xe^ng chu+~
nga' a^yn ta(. re^'t bu+'u liu' su+o+ing mu+'c nhu'ang so+`i ca(` vo^'c
tha`m co+i no+?c su?a nhu+o+ing ho+? lu+o+'i qo' nha't cay mo+`it tro+`i
removed 'dat/viep/grs/tot.1/raw.wfr'
creating the word frequency file dat/viep/grs/tot.1/raw.wfr
the 10 most common words in dat/viep/grs/tot.1/raw.tlw:
165 0.00529 cu?a
158 0.00506 ngu+o+`i
98 0.00314 va`
97 0.00311 ca
97 0.00311 va
96 0.00308 dda
93 0.00298 ca`
92 0.00295 dda`
89 0.00285 la`
87 0.00279 nga
removed 'dat/viep/grs/tot.1/raw-trunc-wds-summary.tex'
removed 'exp/viep/grs/tot.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/viep/grs/tot.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:40 by tex-make-sample-summary.sh
% Token and word counts for viep/grs/tot.1/raw.wfr
%
\def\viepgrstrunctotPBrawTks{31200}
\def\viepgrstrunctotPBrawTksPct{100.0}
\def\viepgrstrunctotPBrawWds{7760}
\def\viepgrstrunctotPBrawWdsPct{24.9}
copied '/tmp/590831.file' -> 'exp/viep/grs/tot.1/raw-trunc-wds-summary.tex'
removed '/tmp/590831.file'
creating running text file dat/viep/grs/tot.1/gud.wdf
sample:
cho cu?a ca?i ngu+o+`i va` nha^.m co^ng vie^.c cu?a tay ngu+o+`i la`m
xin be? na't ho.ng cu?a ke? da^'y nghi.ch va` ghen ghe't ngu+o+`i dde^?
chu'ng no' kho^ng the^' da^'y le^n nu+~a ngu+o+`i chu'c ve^` be^n gia
min ra(`ng ngu+o+`i ma` ddu+'c gie^ ho^ va ye^u me^'n se~ ddu+o+.c o+?
ye^n ga^`n be^n nga`i ha(`ng nga`y ddu+'c gie^ ho^ va se~ che cho+?
ngu+o+`i la^.p no+i o+? nga`i giu+~a hai vai ngu+o+`i ngu+o+`i chu'c
ve^` gio^ se'p ra(`ng xu+' ngu+o+`i ddu+o+.c ddu+'c gie^ ho^ va ban
phu+o+'c tu+` tro+`i nga`i gia'ng xuo^'ng cho ngu+o+`i a^n tu+' ra^'t
ba'u la` su+o+ng mo'c nhu+~ng suo^'i cu?a vu+.c tha(?m co' nu+o+'c sa^u
nhu+~ng hue^ lo+.i qui' nhu+'t cu?a ma(.t tro+`i hoa qua? cu+.c ba'u
cu?a ma(.t tra(ng nhu+~ng va^.t nhu+'t ha.ng cu?a nu'i xu+a ca'c ba'u
la. cu?a ma^'y go` ddo^'ng ddo+`i ddo+`i bu+?u bo^'i cu?a dda^'t va`
su+. sung ma~n no' nguye^.n o+n cu?a dda^'ng hie^.n ra trong bu.i gai
gia'ng xuo^'ng tre^n dda^`u gio^ se'p va` tre^n tra'n cu?a chu'a anh em
ngu+o+`i oai nghie^m ngu+o+`i gio^'ng nhu+ con bo` ddu+.c dda^`u lo`ng
hai su+`ng ngu+o+`i vo^'n su+`ng cu?a tra^u ngu+o+`i la^'y su+`ng a^'y
ba'ng mo.i da^n cho dde^'n cuo^'i dda^`u cu?a dda^'t ddo' la` ha(`ng
muo^n cu?a e'p ra im a^'y la` ha(`ng nga`n cu?a ma na se ngu+o+`i chu'c
ve^` sa bu lo^n ra(`ng ho+~i sa bu lo^n kha' vui mu+`ng ve^` cuo^.c
mi`nh ddi ra ngoa`i co`n ngu+o+i y sa ca ha~y ho+'n ho+? trong ca'c
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
ddo+`ic ga` ha^' voai bin pho+~ic te^ tra' ngu+` go+`ing xe^ng chu+~
nga' a^yn ta(. re^'t bu+'u liu' su+o+ing mu+'c nhu'ang so+`i ca(` vo^'c
tha`m co+i no+?c su?a nhu+o+ing ho+? lu+o+'i qo' nha't cay mo+`it tro+`i
removed 'dat/viep/grs/tot.1/gud.wfr'
creating the word frequency file dat/viep/grs/tot.1/gud.wfr
the 10 most common words in dat/viep/grs/tot.1/gud.tlw:
165 0.00529 cu?a
158 0.00506 ngu+o+`i
98 0.00314 va`
97 0.00311 ca
97 0.00311 va
96 0.00308 dda
93 0.00298 ca`
92 0.00295 dda`
89 0.00285 la`
87 0.00279 nga
removed 'dat/viep/grs/tot.1/gud-trunc-wds-summary.tex'
removed 'exp/viep/grs/tot.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/viep/grs/tot.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:40 by tex-make-sample-summary.sh
% Token and word counts for viep/grs/tot.1/gud.wfr
%
\def\viepgrstrunctotPBgudTks{31200}
\def\viepgrstrunctotPBgudTksPct{100.0}
\def\viepgrstrunctotPBgudWds{7760}
\def\viepgrstrunctotPBgudWdsPct{24.9}
copied '/tmp/590875.file' -> 'exp/viep/grs/tot.1/gud-trunc-wds-summary.tex'
removed '/tmp/590875.file'
creating running text file dat/viep/grs/tot.1/bad.wdf
sample:
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
removed 'dat/viep/grs/tot.1/bad.wfr'
creating the word frequency file dat/viep/grs/tot.1/bad.wfr
the 10 most common words in dat/viep/grs/tot.1/bad.tlw:
removed 'dat/viep/grs/tot.1/bad-trunc-wds-summary.tex'
removed 'exp/viep/grs/tot.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/viep/grs/tot.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:40 by tex-make-sample-summary.sh
% Token and word counts for viep/grs/tot.1/bad.wfr
%
\def\viepgrstrunctotPBbadTks{0}
\def\viepgrstrunctotPBbadTksPct{0.0}
\def\viepgrstrunctotPBbadWds{0}
\def\viepgrstrunctotPBbadWdsPct{0.0}
copied '/tmp/590919.file' -> 'exp/viep/grs/tot.1/bad-trunc-wds-summary.tex'
removed '/tmp/590919.file'
lines words bytes file
------- ------- --------- ------------
7760 23280 172087 dat/viep/grs/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
7760 23280 172087 dat/viep/grs/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
0 0 0 dat/viep/grs/tot.1/bad.wfr
tot.1 raw = 31200 gud = 31200 bad = 0
=== creating the derived word files dat/viep/mky/*/{raw,gud,bad}.{tlw,wdf,wfr} (trunc) ===
... creating word files dat/viep/mky/tot.1/{raw,gud,bad}.{tlw,wdf,wfr} ...
36013 dat/viep/mky/tot.1/trunc.tlw
removed 'dat/viep/mky/tot.1/raw.tlw'
removed 'dat/viep/mky/tot.1/gud.tlw'
removed 'dat/viep/mky/tot.1/bad.tlw'
creating the word files {raw,gud,bad}.tlw
creating running text file dat/viep/mky/tot.1/raw.wdf
sample:
ddo' no+i cha(`ng ra(`ng mi`nh xo^'p da^~ng ddi dde^` ca'ch tro+`i
tro^ng a^'t ddo+`ng anh cu`ng ngu+o+i di~a ho+`i ta da` co^'n ngu+o+`i
la`m ga.t ca'i ddanh ru+o+' sau ddi tuye^. cho ddu+' a^'t dde^` hoa
trong se~ va` vua gio^ va^.y ngu+o+i la`m tro+`i tha^.t tra'i se^ ho^ va
dde^'t la`m tha't tre^n ngu+o+`i tra'i cu?a le^.p ba tra('p pha^`u trong
mo^~ cho^n nga`i chu'a e'p mu` hai che^u no'i ra(`ng tha`ng ban a^'u
kha'nh lo+.ng chi dda'nh =
ha~y lu+. hai la.i tre? sai la`m y no+i tre? cu`ng cu`ng ma^y mo^.t
do`ng va^.n cu?a dde^'n ma(.c ngu~ hu+ loa`i se~ ba^'t tro+`i cu?a hai
ddu+'c gie^'ng cho na`ng ha` ngu+o+'i dde^` giu+~ng no+i kho?i dde^~
no'i la`nh che^'t ddo+`i tho+n danh dda~ pha?i tru+o+'c ngu+o+. nghe va`
me^ ho^ng to^i ta vi` pha?i gie^n ddo^.t cu~ng va` y so+ ra e^n ngu+o+?
da^'y chu'ng va('m nhu+' e^ le'p ra(`ng bi. xu+'a nan nu+o+`i cu`ng
trong =
kho^`i dda'nh ddu+o+. mu`a ma.n la.i cho+`i con ca^`m ban da^n mo^i vo`n
cu`ng men va` bo.n cho no'i cho ca'c mi`nh the^'n ddu+`a xe't thuo^.i
cho qua? y so+. dde^'t ddi tha'ng ve^`u khi vi' ddu+'c chu'a trong tay
la` ca'c lo+'c ngu+o+i ba^`n tri. la` ngu~ mi`nh kha'i co`n mi`nh tho+'c
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
cha hay la`m cha(?ng =
dde`n chu'a se~ nu+~ng se~ xem cu`ng dda(.c
removed 'dat/viep/mky/tot.1/raw.wfr'
creating the word frequency file dat/viep/mky/tot.1/raw.wfr
the 10 most common words in dat/viep/mky/tot.1/raw.tlw:
986 0.02738 =
653 0.01813 va`
540 0.01499 cho
515 0.01430 ca'c
495 0.01375 cu?a
468 0.01300 con
467 0.01297 ngu+o+i
427 0.01186 ra
405 0.01125 se~
391 0.01086 la`
removed 'dat/viep/mky/tot.1/raw-trunc-wds-summary.tex'
removed 'exp/viep/mky/tot.1/raw-trunc-wds-summary.tex'
creating the TeX summary file dat/viep/mky/tot.1/raw-trunc-wds-summary.tex
% Created 2023-05-10 23:31:40 by tex-make-sample-summary.sh
% Token and word counts for viep/mky/tot.1/raw.wfr
%
\def\viepmkytrunctotPBrawTks{36013}
\def\viepmkytrunctotPBrawTksPct{100.0}
\def\viepmkytrunctotPBrawWds{3342}
\def\viepmkytrunctotPBrawWdsPct{9.3}
copied '/tmp/591014.file' -> 'exp/viep/mky/tot.1/raw-trunc-wds-summary.tex'
removed '/tmp/591014.file'
creating running text file dat/viep/mky/tot.1/gud.wdf
sample:
ddo' no+i cha(`ng ra(`ng mi`nh xo^'p da^~ng ddi dde^` ca'ch tro+`i
tro^ng a^'t ddo+`ng anh cu`ng ngu+o+i di~a ho+`i ta da` co^'n ngu+o+`i
la`m ga.t ca'i ddanh ru+o+' sau ddi tuye^. cho ddu+' a^'t dde^` hoa
trong se~ va` vua gio^ va^.y ngu+o+i la`m tro+`i tha^.t tra'i se^ ho^ va
dde^'t la`m tha't tre^n ngu+o+`i tra'i cu?a le^.p ba tra('p pha^`u trong
mo^~ cho^n nga`i chu'a e'p mu` hai che^u no'i ra(`ng tha`ng ban a^'u
kha'nh lo+.ng chi dda'nh ha~y lu+. hai la.i tre? sai la`m y no+i tre?
cu`ng cu`ng ma^y mo^.t do`ng va^.n cu?a dde^'n ma(.c ngu~ hu+ loa`i se~
ba^'t tro+`i cu?a hai ddu+'c gie^'ng cho na`ng ha` ngu+o+'i dde^`
giu+~ng no+i kho?i dde^~ no'i la`nh che^'t ddo+`i tho+n danh dda~ pha?i
tru+o+'c ngu+o+. nghe va` me^ ho^ng to^i ta vi` pha?i gie^n ddo^.t cu~ng
va` y so+ ra e^n ngu+o+? da^'y chu'ng va('m nhu+' e^ le'p ra(`ng bi.
xu+'a nan nu+o+`i cu`ng trong kho^`i dda'nh ddu+o+. mu`a ma.n la.i
cho+`i con ca^`m ban da^n mo^i vo`n cu`ng men va` bo.n cho no'i cho ca'c
mi`nh the^'n ddu+`a xe't thuo^.i cho qua? y so+. dde^'t ddi tha'ng ve^`u
khi vi' ddu+'c chu'a trong tay la` ca'c lo+'c ngu+o+i ba^`n tri. la`
ngu~ mi`nh kha'i co`n mi`nh tho+'c gie^ ho^n tan cho hu+ ba?y co`n
de^'ng nu+o+' buo^? na`ng u+ng go+'i cha(`ng con dde^` se~ dde^'c lo^~i
ngu+o+i ddi tu be^n cha(?ng ba?y la`m ve^` phu.c ma` dda'n cho+'c ca('t
mo.i ddu+o+i ba'ng to^i me^ ho^ ddi gio+`ng la('t nu+o+i ba'ch me^'ng
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
dda' to^?i vi` la` ngu+o+i con tra(`ng sao ca'c to^i ngu+o+i ha~y te^'
le^~ se~ la.y cha hay la`m cha(?ng dde`n chu'a se~ nu+~ng se~ xem cu`ng
dda(.c
removed 'dat/viep/mky/tot.1/gud.wfr'
creating the word frequency file dat/viep/mky/tot.1/gud.wfr
the 10 most common words in dat/viep/mky/tot.1/gud.tlw:
653 0.01864 va`
540 0.01542 cho
515 0.01470 ca'c
495 0.01413 cu?a
468 0.01336 con
467 0.01333 ngu+o+i
427 0.01219 ra
405 0.01156 se~
391 0.01116 la`
366 0.01045 va
removed 'dat/viep/mky/tot.1/gud-trunc-wds-summary.tex'
removed 'exp/viep/mky/tot.1/gud-trunc-wds-summary.tex'
creating the TeX summary file dat/viep/mky/tot.1/gud-trunc-wds-summary.tex
% Created 2023-05-10 23:31:40 by tex-make-sample-summary.sh
% Token and word counts for viep/mky/tot.1/gud.wfr
%
\def\viepmkytrunctotPBgudTks{35027}
\def\viepmkytrunctotPBgudTksPct{97.3}
\def\viepmkytrunctotPBgudWds{3341}
\def\viepmkytrunctotPBgudWdsPct{9.3}
copied '/tmp/591058.file' -> 'exp/viep/mky/tot.1/gud-trunc-wds-summary.tex'
removed '/tmp/591058.file'
creating running text file dat/viep/mky/tot.1/bad.wdf
sample:
=
=
=
=
=
=
=
=
=
=
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
=
removed 'dat/viep/mky/tot.1/bad.wfr'
creating the word frequency file dat/viep/mky/tot.1/bad.wfr
the 10 most common words in dat/viep/mky/tot.1/bad.tlw:
986 1.00000 =
removed 'dat/viep/mky/tot.1/bad-trunc-wds-summary.tex'
removed 'exp/viep/mky/tot.1/bad-trunc-wds-summary.tex'
creating the TeX summary file dat/viep/mky/tot.1/bad-trunc-wds-summary.tex
% Created 2023-05-10 23:31:40 by tex-make-sample-summary.sh
% Token and word counts for viep/mky/tot.1/bad.wfr
%
\def\viepmkytrunctotPBbadTks{986}
\def\viepmkytrunctotPBbadTksPct{2.7}
\def\viepmkytrunctotPBbadWds{1}
\def\viepmkytrunctotPBbadWdsPct{0.0}
copied '/tmp/591102.file' -> 'exp/viep/mky/tot.1/bad-trunc-wds-summary.tex'
removed '/tmp/591102.file'
lines words bytes file
------- ------- --------- ------------
3342 10026 73937 dat/viep/mky/tot.1/raw.wfr
lines words bytes file
------- ------- --------- ------------
3341 10023 73919 dat/viep/mky/tot.1/gud.wfr
lines words bytes file
------- ------- --------- ------------
1 3 18 dat/viep/mky/tot.1/bad.wfr
tot.1 raw = 36013 gud = 35027 bad = 986
removed 'summary-trunc-raw.txt'
creating summary-trunc-raw.txt
removed 'summary-trunc-gud.txt'
creating summary-trunc-gud.txt
removed 'summary-trunc-bad.txt'
creating summary-trunc-bad.txt
stolfi@baikal 2090>>>