+
−#!/usr/bin/python
+
−
+
−# python voa-special-c5.py
+
−
+
−import re
+
−
+
−f = open('../gadict-voa-special-english-word-book.dict-c5', 'r')
+
−
+
−re_delim = re.compile(r'^_____\n')
+
−re_empty = re.compile(r'^\n')
+
−
+
−while True:
+
−    s = f.readline()
+
−    if re_delim.match(s):
+
−        break
+
−state = 'delim'
+
−
+
−words = []
+
−word = None
+
−article = None
+
−
+
−while True:
+
−    line = f.readline()
+
−    if len(line) == 0:
+
−        break
+
−    if state == 'delim':
+
−        if re_empty.match(line):
+
−            state = 'skip_to_word'
+
−    elif state == 'skip_to_word':
+
−        if not re_empty.match(line):
+
−            state = 'word'
+
−            word = line.strip()
+
−    elif state == 'word':
+
−        if re_empty.match(line):
+
−            state = 'skip_to_article'
+
−        else:
+
−            state = 'article'
+
−            article += line
+
−    elif state == 'skip_to_article':
+
−        if not re_empty.match(line):
+
−            state = 'article'
+
−            article = line
+
−    elif state == 'article':
+
−        if re_delim.match(line):
+
−            state = 'delim'
+
−            words.append( (word, article.strip()) )
+
−            word = None
+
−            article = ''
+
−        else:
+
−            state = 'article'
+
−            article += line
+
−
+
−f.close()
+
−
+
−for i in words:
+
−    print("\\worddef{%s}{%s}" % (i[0], i[1]))