Find words with the same kanji and reading

findWordsWithSameKanjiandReading.py

# -*- coding: utf-8 -*-
import sqlite3
import re
#or another Rikaichan formatted dictionary file
d='.anki\\plugins\\yomichan_plugin\\languages\\japanese\\data\\dict.sqlite'
f=sqlite3.connect(d).cursor()

lookups=[(u'とく', u'徳')]

def findWordsWithSameKanjiandReading(kana, kanji):
    f.execute(u'select * from dict where kana like "%%%s%%" and kanji like "%%%s%%" and entry like "%%(P)%%" limit 25'%(kana, kanji))

    for kanji, kana, entry in f:
        #if entry.find('(P)') == -1: continue
        meanings = entry.split('/')
        if not meanings[-1]:
            items = map(unicode.strip, re.split('[\[\]]', meanings[0]))
            if len(items) > 1:
                kanji, kana, = items[0], items[1]
            else:
                kanji, kana = None, items[0]
            del meanings[0], meanings[-1]
        entry = u'; '.join(meanings)
        expression = kanji or kana
        reading = kana if kanji else None
        print expression, reading, entry
        
for pair in lookups:
    print '*' * 50
    print '%s (%s)' % tuple(reversed(list(pair)))
    findWordsWithSameKanjiandReading(pair[0],pair[1])