#! /usr/bin/gawk -f # Attempts to split words into prefix/suffix inserting ":" in between. BEGIN { PREFS = "^(AH|AP|Ae|H|P|c|cH|cccH|ccccH|cg|ci|ciH|e|eH|oH|oP|oe|oeH|r)" # SUFFS = "([co]c*(|e|g|gci|i|ie|if|im|in|ir|oe|or|r))$" SUFFS = "(cccgci|ccgci|ccci|ccccgci|cim|ci|cie|cci|cir|cccci|oe|cin|or|ccoe|coe|ccccci|cccoe|ccor)$" SPLIT = ( PREFS SUFFS ) } ( $0 ~ SPLIT ) { match($0, PREFS) k = RLENGTH $0 = (substr($0, 1, k) ":" substr($0, k + 1)) # $0 = gensub( ("^\\(" PREFS "\\)\\(" SUFFS "\\)$"), "\\1:\\2", 1) print next } /./ { print; next }