google_ime.py

#!/usr/bin/env python
# -*- coding: utf-8 -*-

# The MIT License
#
# Copyright (c) 2010 Yota Ichino
#
# Permission is hereby granted, free of charge, to any person obtaining a copy
# of this software and associated documentation files (the "Software"), to deal
# in the Software without restriction, including without limitation the rights
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
# copies of the Software, and to permit persons to whom the Software is
# furnished to do so, subject to the following conditions:
#
# The above copyright notice and this permission notice shall be included in
# all copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
# THE SOFTWARE.

import urllib

class TranslateCandicates(object):
    '''container class for text and translated
    Example Use:
      >>> word = TranslateCandicates("にほん", ("日本","二本","ニホン","弐奔","にほん"))
      >>> print word.text
      にほん
      >>> for element in word.candicates:
      ...     print element,
      日本 二本 ニホン 弐奔 にほん
    '''
    # Translated cardicates
    candicates = ()
    # Translate target text
    text = ''
    # for iterator temporary value
    value = 0
    
    def __init__(self, text, candicates):
        self.text = text
        self.candicates = tuple(candicates)

    def __iter__(self):
        return self

    def next(self):
        ''' yield self.candicates
        '''
        if self.value == (len(self.candicates) - 1):
           raise StopIteration
        self.value += 1
        return self.candicates[self.value]


class GoogleJapanseIME(object):
    '''This module is Google CGI API fo Japanse Input in Python
    
    Example Use:
      >>> ime = GoogleJapanseIME()
      >>> answer = ime.trans("にほん")
      >>> for tmp in answer[0]:
      ...     print tmp,
      日本 二本 ニホン 弐奔 にほん
      
    About Google CGI API for Japanse Input:
      See http://www.google.co.jp/intl/ja/ime/cgiapi.html
    '''
    _url = 'http://www.google.com/transliterate?langpair=ja-Hira|ja&text='

    def _request(self, hiragana):
#        query = self._url + urllib.quote_plus(hiragana)
        query = self._url + urllib.quote(hiragana)
        response = urllib.urlopen(query).read()
        return response.decode('raw_unicode_escape')

    def _json_parser(self, string):
        return tuple(eval(string))

    def _arrange(self, parsed_string):
        ret = []
        for item in parsed_string:
            w = TranslateCandicates(item[0], item[1])
            ret.append(w)

        return tuple(ret)

    def trans(self, hiragana):
        response = self._request(hiragana)
        parsed = self._json_parser(response)
        ret = self._arrange(parsed)
        
        return ret

def main():
    henkan = 'へんかん,ぐーぐる'
    ime = GoogleJapanseIME()
    answers = ime.trans(henkan)
    for ans in answers:
        print 'target text:', ans.text
        print 'candicates :',
        for item in ans:
            print item,
        print ''

if __name__ == '__main__':
    main()