PO檔自動繁簡轉換程式

# -*- coding: utf8 -*-
'''
Created on 2010/4/27

@author: Victor-mortal
'''

import os
import sys
import urllib
import json
import logging
import optparse
import codecs
import htmllib

log = logging.getLogger(__name__)

def unescape(s):
    p = htmllib.HTMLParser(None)
    p.save_bgn()
    p.feed(s)
    return p.save_end()

def translate(text, sourceLanguage, destLanguage):
    """Translate a text

    @param text: text to translate
    @param sourceLanguage: the language original text is in
    @param destLanguage: language to translate to
    """
    log.info('Translate %s from %s to %s', text, sourceLanguage, destLanguage)
    query = dict(v='1.0',
                 q=text.encode('utf8'),
                 langpair='%s|%s' % (sourceLanguage, destLanguage))
    file = urllib.urlopen(
        'http://ajax.googleapis.com/ajax/services/language/translate',
        data=urllib.urlencode(query)
    )
    result = file.read()
    file.close()
    jsonResult = json.loads(result)
    if not jsonResult['responseData']:
        return None
    return unescape(jsonResult['responseData']['translatedText'])

def main():
    logging.basicConfig(level=logging.INFO)

    parser = optparse.OptionParser(
        usage="usage: %prog sourcePoFile destPoFile sourceLanguage destLanguage"
    )
    (_, args) = parser.parse_args()

    sourceFilePath = args[0]
    destFilePath = args[1]
    sourceLang = args[2]
    destLang = args[3]

    log.info('Translate %s (in %s) to %s (in %s)',
             sourceFilePath, sourceLang, destFilePath, destLang)

    result = []
    sourceFile = codecs.open(sourceFilePath, 'rt', encoding='utf8')
    for line in sourceFile.readlines():
        if line.startswith('msgstr'):
            _, msg = line.split(' ', 1)
            msg = msg.strip()
            msg = msg[1:-1]
            translatedMsg = translate(msg, sourceLang, destLang)
            if not translatedMsg:
                translatedMsg = msg
            result.append(('msgstr "%s"n' % translatedMsg))
        else:
            result.append(line)
    sourceFile.close()

    destFile = codecs.open(destFilePath, 'wt', encoding='utf8')
    destFile.writelines(result)
    destFile.close()

if __name__ == '__main__':
    main()