#! /usr/bin/python3
# Last edited on 2026-02-27 05:44:08 by stolfi

import sys, os, re;
from sys import stderr as err
from error_funcs import arg_error, prog_error
from process_funcs import bash
from math import fabs

from note_077_funcs import enc_from_unit
import make_rules_077_funcs as mrf

def add_all_ivt_ivp_rules(pre, mak, tit):
  # Rules to create the "bencao-fu-{enc}.ivt" files, and
  # "bencao-fu-{enc}.ivp" files, which are just links for the files in
  # the "in" folder.
  #
  # The {enc} specifies the encoding: "chu" hanzi chars, "pys" for
  # pinyin words with one syllable per word. The two should match,
  # one character for each syllable.
  #
  # Beware that both sources have extemporaneous inline comments in ideographic
  # parentehses.

  targets = []

  for enc in ("chu", "pys"):
  
    # The ".ivt" file is the reference file, with annotations and other dirt:
    source_ext = "uts" if enc == "chu" else "pys" if enc == "pys" else None
    assert source_ext is not None

    ivt_target = f"bencao-fu-{enc}.ivt"
    source_ivt = f"in/bencao.{source_ext}"

    tit[ivt_target] = f"making link {ivt_target} to {source_ivt}"
    pre[ivt_target] = [ source_ivt, ]
    mak[ivt_target] = (
      f"( cd res && rm -f {ivt_target} ; ln -s ../{source_ivt} {ivt_target} )",
    )
    targets.append(ivt_target)

    # The ".ivp" file is cleaned from annotations and other dirt:
    ivp_target = f"bencao-fu-{enc}.ivp"
    ivp_source = f"res/{ivt_target}"
    ivt_to_ivp_script = "convert_bencao_ivt_to_ivp.py"

    tit[ivp_target] = f"making link {ivp_target} to {ivp_source}"
    pre[ivp_target] = [ ivp_source, ivt_to_ivp_script, ]
    mak[ivp_target] = (
      f"./{ivt_to_ivp_script} {enc} {ivp_source} res/{ivp_target}",
    )
    targets.append(ivp_target)


  return targets
  # ----------------------------------------------------------------------

def add_all_upp_rules(pre, mak, tit):
  # Rules to create the "bencao-fu-{unit}.upp" files, with the size of
  # each recipe. The {unit} specifies the unit of size: "ch" for hanzi
  # chars, "ps" for pinyin words with one syllable per word. The latter
  # should match the "ch" version if the pinyin source is correct.

  targets = []

  prfn_py_lib = "work/process_funcs.py"
  chfn_py_lib = "work/chinese_funcs.py"
  n077_py_lib = "note_077_funcs.py"

  book = "bencao"
  bsub = "fu"
  for unit in ("ch", "ps"):
    target = f"{book}-{bsub}-{unit}.upp"
    source_enc = enc_from_unit(unit)
    source = f"res/{book}-{bsub}-{source_enc}.ivp"
    
    # The size counting script and its imported modules:
    script = f"count_units_per_parag.py"
    script_options = f"{book} {bsub} {unit}"
    
    tit[target] = f"making SBJ parag size file {target} from {source}"
    pre[target] = [ source, script, prfn_py_lib, n077_py_lib, chfn_py_lib, ]
    mak[target] = (
        f"{script} {script_options}",
      )
    targets.append(target)
  return targets
  # ----------------------------------------------------------------------
 
def add_all_single_hist_rules(pre, mak, tit):
  targets = []
  bsub = "fu"
  for unit in ( "ch", "ps", ):
    name = f"bencao-{bsub}-{unit}"
    color = mrf.bencao_hist_color(bsub, unit)
    bin_size = 1
    target = mrf.add_single_size_hist_plot_rules(pre, mak, tit, name, color, bin_size)
    targets.append(target)
  return targets
  # ----------------------------------------------------------------------

def add_all_double_hist_rules(pre, mak, tit):
  targets = []
  for unit0, unit1 in ( ("ch", "ps"), ):
    bsub0 = "fu"
    name0 = f"bencao-{bsub0}-{unit0}"; 
    color0 = mrf.bencao_hist_color(bsub0, unit0)
    bsub1 = "fu"
    name1 = f"bencao-{bsub1}-{unit1}"
    color1 = mrf.bencao_hist_color(bsub1, unit1)
    bin_size = 1
    target = mrf.add_double_size_hist_plot_rules(pre, mak, tit, name0, color0, name1, color1, bin_size)
    targets.append(target)
  return targets
  # ----------------------------------------------------------------------

def add_all_word_pos_plot_rules(pre, mak, tit):
  # Word position plots for various words and parags.

  book = "bencao"
  bsub = "fu"
  iext = "ivp"
  unit = "ch"

  pattags = ( \
      ( "主", "zhu3", ), 
    )
  pattags_not = ( \
      ( "主治", "zhu3zhi4", ),
      ( "主下", "zhu3xia4", ),
    )
  cands = ( \
      "b1.4.100", # 3 hits.
      "b2.5.118", # 3 hits?.
      "b2.5.518", # 3 hits?.
      "b3.3.080", # 3 hits.
      "b2.1.013", # 3 hits.
    )
  cands_yes = ( \
      "b1.4.096", # 7 hits.
      "b2.4.094", # 3 hits.
      "b3.3.088", # 3 hits.
    )
  cands_not = ( \
      "b1.1.014", # 1 hit.
      "b1.2.061", # 1 hit.
      "b1.1.007", # 1 hit.
      "b1.1.014", # 1 hit.
      "b1.2.061", # 1 hit.
      "b1.4.090", # 2 hits.
      "b1.5.106", # 1 hit.
      "b1.5.109", # 2 hits.
      "b2.1.001", # 1 hit.
      "b2.2.066", # 1 hit.
      "b2.3.090", # 2 hits.
      "b3.3.077", # 1 hit.
      "b3.5.119", # 2 hits.
    )

  slocs = cands + cands_yes
  targets = mrf.add_many_word_pos_plot_rules(pre, mak, tit, book, bsub, iext, unit, pattags, slocs)
  return targets
  # ----------------------------------------------------------------------

def add_wpos_delta_file_rules(pre, mak, tit, word, tag):
  # Adds rules to create the file "res/bencao-fu-{unit}-{tag}.wpd" with
  # the deltas of positions of word {word} in selected parags
  # of the "res/bencao-fu-chu.ivp" file.
  bsub = "fu"
  enc = "chu"
  unit = "ch"
  color = mrf.bencao_hist_color(bsub, unit)
  parag_cands = (
      "b1.4.100", # 3 hits.
      "b2.1.013", # 3 hits.
      "b2.4.094", # 3 hits.
      "b2.5.118", # 3 hits?.
      "b2.5.518", # 3 hits?.
      "b3.3.080", # 3 hits.
      "b3.3.088", # 3 hits.
    )
  parag_cands_later = (
    )
  parag_cands_done = (
      "b1.4.096", # 7 hits.
    )
  target = mrf.add_wpos_delta_file_rules \
    (pre, mak, tit, "bencao", bsub, unit, word, tag, parag_cands)
  return target, color
  # ----------------------------------------------------------------------

def add_all_rules(pre, mak, tit):
  # Adds rules to build the double histograms of SBJ parag sizes
  # comparing various size meyrics.
  #
  # Also adds rules to build the necessary ".upp" files with size of
  # each parag.
  #
  # Returns the list of ultimate targets (the plot files)
  
  targets = \
    add_all_ivt_ivp_rules(pre, mak, tit) + \
    add_all_upp_rules(pre, mak, tit) + \
    add_all_single_hist_rules(pre, mak, tit) + \
    add_all_word_pos_plot_rules(pre, mak, tit)

  # + add_all_double_hist_rules(pre, mak, tit)
  return targets
  # ----------------------------------------------------------------------