# # Author: Taha Zerrouki (taha.zerrouki[at]gmail.com) # # Created: 18-05-2014 # Copyright: (c) Taha Zerrouki 2014 # Licence: GPL #------------------------------------------------------------------------------- """ wordCase represents the data resulted from the morpholocigal analysis """ if __name__ == "__main__": import sys sys.path.append('..') #~import pyarabic.araby as araby import pyarabic.arabrepr as arabrepr arabicRepr = arabrepr.ArabicRepr() #~import analex_const class WordCase: """ wordCase represents the data resulted from the morpholocigal analysis """ def __init__(self, result_dict=None): self.word = u"", #~"""input word""" self.vocalized = u"", #~"""vocalized form of the input word """ self.semivocalized = u"",
def accepted(self, word): """ test if word is accecpted word (correct) @param word: input text. @type word: unicode. @return: True if word is accepted rtype: boolean. """ result = self.analyzer.check_word(word) if result: # result has many cases if len(result) > 1: return True #one only case else: return not result[0].is_unknown() return False if __name__ == "__main__": print "test" myrepr = arabRepr.ArabicRepr() speller = SpellcheckClass() text = u" اللغه العربيه" voc = speller.spellcheck(text, True) # print myrepr.repr(voc).encode('utf8') for itemd in voc: if itemd.get('suggest', '') != '': for sug in itemd.get('suggest', '').split(';'): print sug.encode('utf8'), '\t', araby.is_arabicword(sug)