flashcard_chinese_import.py

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
import re

pinyinToneMarks = {
    u'a': u'āáǎà', u'e': u'ēéěè', u'i': u'īíǐì',
    u'o': u'ōóǒò', u'u': u'ūúǔù', u'ü': u'ǖǘǚǜ',
    u'A': u'ĀÁǍÀ', u'E': u'ĒÉĚÈ', u'I': u'ĪÍǏÌ',
    u'O': u'ŌÓǑÒ', u'U': u'ŪÚǓÙ', u'Ü': u'ǕǗǙǛ'
}

def convertPinyinCallback(m):
    tone=int(m.group(3))%5
    r=m.group(1).replace(u'v', u'ü').replace(u'V', u'Ü')
    # for multple vowels, use first one if it is a/e/o, otherwise use second one
    pos=0
    if len(r)>1 and not r[0] in 'aeoAEO':
        pos=1
    if tone != 0:
        r=r[0:pos]+pinyinToneMarks[r[pos]][tone-1]+r[pos+1:]
    return r+m.group(2)

def convertPinyin(s):
    return re.sub(u'([aeiouüvÜ]{1,3})(n?g?r?)([012345])', convertPinyinCallback, s, flags=re.IGNORECASE)

with open('pcr1-cedict-vocabulary.utf8.txt') as f:
    lines = [ l.strip() for l in f.readlines() ]

for line in lines:
    if not line or line.startswith('#'):
        continue
    match = re.match(r'^(.*) \[(.*)] /(.*)/$', line)
    if not match:
        print('ERR:', line)
    hanzi, pinyin, gloss = match.groups()
    print(hanzi, convertPinyin(pinyin), gloss, sep='\t')