def __init__(self, debug=False):
# create a stemmer object for stemming enclitics and procletics
self.compStemmer = tashaphyne.stemming.ArabicLightStemmer();
# configure the stemmer object
self.compStemmer.set_infix_letters(stem_noun_const.COMP_INFIX_LETTERS);
self.compStemmer.set_prefix_letters(stem_noun_const.COMP_PREFIX_LETTERS);
self.compStemmer.set_suffix_letters(stem_noun_const.COMP_SUFFIX_LETTERS);
self.compStemmer.set_max_prefix_length(stem_noun_const.COMP_MAX_PREFIX);
self.compStemmer.set_max_suffix_length(stem_noun_const.COMP_MAX_SUFFIX);
self.compStemmer.set_min_stem_length(stem_noun_const.COMP_MIN_STEM);
self.compStemmer.set_prefix_list(stem_noun_const.COMP_PREFIX_LIST);
self.compStemmer.set_suffix_list(stem_noun_const.COMP_SUFFIX_LIST);
# create a stemmer object for stemming conjugated verb
self.conjStemmer=tashaphyne.stemming.ArabicLightStemmer();
# configure the stemmer object
self.conjStemmer.set_infix_letters(stem_noun_const.CONJ_INFIX_LETTERS);
self.conjStemmer.set_prefix_letters(stem_noun_const.CONJ_PREFIX_LETTERS);
self.conjStemmer.set_suffix_letters(stem_noun_const.CONJ_SUFFIX_LETTERS);
self.conjStemmer.set_max_prefix_length(stem_noun_const.CONJ_MAX_PREFIX);
self.conjStemmer.set_max_suffix_length(stem_noun_const.CONJ_MAX_SUFFIX);
self.conjStemmer.set_min_stem_length(stem_noun_const.CONJ_MIN_STEM);
self.conjStemmer.set_prefix_list(stem_noun_const.CONJ_PREFIX_LIST);
self.conjStemmer.set_suffix_list(stem_noun_const.CONJ_SUFFIX_LIST);
# enable the last mark (Harakat Al-I3rab)
self.allowSyntaxLastMark =True;
# noun dictionary
# self.nounDictionary=arabicdictionary.arabicDictionary("nouns", NOUN_DICTIONARY_INDEX)
self.nounDictionary=arabicdictionary.arabicDictionary("nouns")
# allow to print internal results.
self.CacheDictSearch={};
self.CacheAffixesVerification={}
self.debug=debug;
def __init__(self, debug=False):
# create a stemmer object for stemming enclitics and procletics
self.compStemmer = tashaphyne.stemming.ArabicLightStemmer();
# configure the stemmer object
self.compStemmer.set_infix_letters(stem_noun_const.COMP_INFIX_LETTERS);
self.compStemmer.set_prefix_letters(stem_noun_const.COMP_PREFIX_LETTERS);
self.compStemmer.set_suffix_letters(stem_noun_const.COMP_SUFFIX_LETTERS);
self.compStemmer.set_max_prefix_length(stem_noun_const.COMP_MAX_PREFIX);
self.compStemmer.set_max_suffix_length(stem_noun_const.COMP_MAX_SUFFIX);
self.compStemmer.set_min_stem_length(stem_noun_const.COMP_MIN_STEM);
self.compStemmer.set_prefix_list(stem_noun_const.COMP_PREFIX_LIST);
self.compStemmer.set_suffix_list(stem_noun_const.COMP_SUFFIX_LIST);
# create a stemmer object for stemming conjugated verb
self.conjStemmer=tashaphyne.stemming.ArabicLightStemmer();
# configure the stemmer object
self.conjStemmer.set_infix_letters(stem_noun_const.CONJ_INFIX_LETTERS);
self.conjStemmer.set_prefix_letters(stem_noun_const.CONJ_PREFIX_LETTERS);
self.conjStemmer.set_suffix_letters(stem_noun_const.CONJ_SUFFIX_LETTERS);
self.conjStemmer.set_max_prefix_length(stem_noun_const.CONJ_MAX_PREFIX);
self.conjStemmer.set_max_suffix_length(stem_noun_const.CONJ_MAX_SUFFIX);
self.conjStemmer.set_min_stem_length(stem_noun_const.CONJ_MIN_STEM);
self.conjStemmer.set_prefix_list(stem_noun_const.CONJ_PREFIX_LIST);
self.conjStemmer.set_suffix_list(stem_noun_const.CONJ_SUFFIX_LIST);
# enable the last mark (Harakat Al-I3rab)
self.allowSyntaxLastMark =True;
# noun dictionary
# self.nounDictionary=arabicdictionary.arabicDictionary("nouns", NOUN_DICTIONARY_INDEX)
self.nounDictionary=arabicdictionary.arabicDictionary("nouns")
# allow to print internal results.
self.CacheDictSearch={};
self.CacheAffixesVerification={}
self.debug=debug;
def __init__(self, debug=False):
# create a stemmer object for stemming enclitics and procletics
self.compStemmer=tashaphyne.stemming.ArabicLightStemmer();
# configure the stemmer object
self.compStemmer.set_infix_letters(stem_noun_const.COMP_INFIX_LETTERS);
self.compStemmer.set_prefix_letters(stem_noun_const.COMP_PREFIX_LETTERS);
self.compStemmer.set_suffix_letters(stem_noun_const.COMP_SUFFIX_LETTERS);
self.compStemmer.set_max_prefix_length(stem_noun_const.COMP_MAX_PREFIX);
self.compStemmer.set_max_suffix_length(stem_noun_const.COMP_MAX_SUFFIX);
self.compStemmer.set_min_stem_length(stem_noun_const.COMP_MIN_STEM);
self.compStemmer.set_prefix_list(stem_noun_const.COMP_PREFIX_LIST);
self.compStemmer.set_suffix_list(stem_noun_const.COMP_SUFFIX_LIST);
# create a stemmer object for stemming conjugated verb
self.conjStemmer=tashaphyne.stemming.ArabicLightStemmer();
# configure the stemmer object
self.conjStemmer.set_infix_letters(stem_noun_const.CONJ_INFIX_LETTERS);
self.conjStemmer.set_prefix_letters(stem_noun_const.CONJ_PREFIX_LETTERS);
self.conjStemmer.set_suffix_letters(stem_noun_const.CONJ_SUFFIX_LETTERS);
self.conjStemmer.set_max_prefix_length(stem_noun_const.CONJ_MAX_PREFIX);
self.conjStemmer.set_max_suffix_length(stem_noun_const.CONJ_MAX_SUFFIX);
self.conjStemmer.set_min_stem_length(stem_noun_const.CONJ_MIN_STEM);
self.conjStemmer.set_prefix_list(stem_noun_const.CONJ_PREFIX_LIST);
self.conjStemmer.set_suffix_list(stem_noun_const.CONJ_SUFFIX_LIST);
# noun dictionary
self.nounDictionary=arabicdictionary.arabicDictionary("nouns", NOUN_DICTIONARY_INDEX)
#word frequency dictionary
self.wordfreq= wordfreqdictionaryclass.wordfreqDictionary('wordfreq', wordfreqdictionaryclass.wordfreq_DICTIONARY_INDEX);
# self.TriVerbTable_INDEX={};
self.Table_affix_INDEX={};
self.NOUN_DICTIONARY_STAMP={
}
# allow to print internal results.
self.debug=debug;
def __init__(self, debug=False):
# create a stemmer object for stemming enclitics and procletics
self.compStemmer=tashaphyne.stemming.ArabicLightStemmer();
# configure the stemmer object
self.compStemmer.set_infix_letters(stem_verb_const.COMP_INFIX_LETTERS);
self.compStemmer.set_prefix_letters(stem_verb_const.COMP_PREFIX_LETTERS);
self.compStemmer.set_suffix_letters(stem_verb_const.COMP_SUFFIX_LETTERS);
self.compStemmer.set_max_prefix_length(stem_verb_const.COMP_MAX_PREFIX);
self.compStemmer.set_max_suffix_length(stem_verb_const.COMP_MAX_SUFFIX);
self.compStemmer.set_min_stem_length(stem_verb_const.COMP_MIN_STEM);
self.compStemmer.set_prefix_list(stem_verb_const.COMP_PREFIX_LIST);
self.compStemmer.set_suffix_list(stem_verb_const.COMP_SUFFIX_LIST);
# create a stemmer object for stemming conjugated verb
self.conjStemmer=tashaphyne.stemming.ArabicLightStemmer();
# configure the stemmer object
self.conjStemmer.set_infix_letters(stem_verb_const.CONJ_INFIX_LETTERS);
self.conjStemmer.set_prefix_letters(stem_verb_const.CONJ_PREFIX_LETTERS);
self.conjStemmer.set_suffix_letters(stem_verb_const.CONJ_SUFFIX_LETTERS);
self.conjStemmer.set_max_prefix_length(stem_verb_const.CONJ_MAX_PREFIX);
self.conjStemmer.set_max_suffix_length(stem_verb_const.CONJ_MAX_SUFFIX);
self.conjStemmer.set_min_stem_length(stem_verb_const.CONJ_MIN_STEM);
self.conjStemmer.set_prefix_list(stem_verb_const.CONJ_PREFIX_LIST);
self.conjStemmer.set_suffix_list(stem_verb_const.CONJ_SUFFIX_LIST);
# enable the last mark (Harakat Al-I3rab)
self.allowSyntaxLastMark =True;
# To show statistics about verbs
statistics={0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0, 9:0, 10:0, 11:0, 12:0, 13:0, 14:0, 15:0, 16:0, 17:0, 18:0, 19:0, 20:0,
}
self.debug=debug;
self.cacheVerb={'verb':{}}
self.verbDictionary=arabicdictionary.arabicDictionary("verbs")
self.VerbSTAMP_pat=re.compile(u"[%s%s%s%s%s]"%( araby.ALEF, araby.YEH, araby.WAW, araby.ALEF_MAKSURA, araby.SHADDA), re.UNICODE)
def __init__(self, debug=False):
# create a stemmer object for stemming enclitics and procletics
self.compStemmer=tashaphyne.stemming.ArabicLightStemmer();
# configure the stemmer object
self.compStemmer.set_infix_letters(stem_verb_const.COMP_INFIX_LETTERS);
self.compStemmer.set_prefix_letters(stem_verb_const.COMP_PREFIX_LETTERS);
self.compStemmer.set_suffix_letters(stem_verb_const.COMP_SUFFIX_LETTERS);
self.compStemmer.set_max_prefix_length(stem_verb_const.COMP_MAX_PREFIX);
self.compStemmer.set_max_suffix_length(stem_verb_const.COMP_MAX_SUFFIX);
self.compStemmer.set_min_stem_length(stem_verb_const.COMP_MIN_STEM);
self.compStemmer.set_prefix_list(stem_verb_const.COMP_PREFIX_LIST);
self.compStemmer.set_suffix_list(stem_verb_const.COMP_SUFFIX_LIST);
# create a stemmer object for stemming conjugated verb
self.conjStemmer=tashaphyne.stemming.ArabicLightStemmer();
# configure the stemmer object
self.conjStemmer.set_infix_letters(stem_verb_const.CONJ_INFIX_LETTERS);
self.conjStemmer.set_prefix_letters(stem_verb_const.CONJ_PREFIX_LETTERS);
self.conjStemmer.set_suffix_letters(stem_verb_const.CONJ_SUFFIX_LETTERS);
self.conjStemmer.set_max_prefix_length(stem_verb_const.CONJ_MAX_PREFIX);
self.conjStemmer.set_max_suffix_length(stem_verb_const.CONJ_MAX_SUFFIX);
self.conjStemmer.set_min_stem_length(stem_verb_const.CONJ_MIN_STEM);
self.conjStemmer.set_prefix_list(stem_verb_const.CONJ_PREFIX_LIST);
self.conjStemmer.set_suffix_list(stem_verb_const.CONJ_SUFFIX_LIST);
# enable the last mark (Harakat Al-I3rab)
self.allowSyntaxLastMark =True;
# To show statistics about verbs
statistics={0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0, 9:0, 10:0, 11:0, 12:0, 13:0, 14:0, 15:0, 16:0, 17:0, 18:0, 19:0, 20:0,
}
self.debug=debug;
self.cacheVerb={'verb':{}}
self.verbDictionary=arabicdictionary.arabicDictionary("verbs")
self.VerbSTAMP_pat=re.compile(u"[%s%s%s%s%s]"%( araby.ALEF, araby.YEH, araby.WAW, araby.ALEF_MAKSURA, araby.SHADDA), re.UNICODE)
def __init__(self, debug=False):
# create a stemmer object for stemming enclitics and procletics
self.compStemmer = tashaphyne.stemming.ArabicLightStemmer()
# configure the stemmer object
self.compStemmer.set_infix_letters(stem_noun_const.COMP_INFIX_LETTERS)
self.compStemmer.set_prefix_letters(
stem_noun_const.COMP_PREFIX_LETTERS)
self.compStemmer.set_suffix_letters(
stem_noun_const.COMP_SUFFIX_LETTERS)
self.compStemmer.set_max_prefix_length(stem_noun_const.COMP_MAX_PREFIX)
self.compStemmer.set_max_suffix_length(stem_noun_const.COMP_MAX_SUFFIX)
self.compStemmer.set_min_stem_length(stem_noun_const.COMP_MIN_STEM)
self.compStemmer.set_prefix_list(stem_noun_const.COMP_PREFIX_LIST)
self.compStemmer.set_suffix_list(stem_noun_const.COMP_SUFFIX_LIST)
# create a stemmer object for stemming conjugated verb
self.conjStemmer = tashaphyne.stemming.ArabicLightStemmer()
# configure the stemmer object
self.conjStemmer.set_infix_letters(stem_noun_const.CONJ_INFIX_LETTERS)
self.conjStemmer.set_prefix_letters(
stem_noun_const.CONJ_PREFIX_LETTERS)
self.conjStemmer.set_suffix_letters(
stem_noun_const.CONJ_SUFFIX_LETTERS)
self.conjStemmer.set_max_prefix_length(stem_noun_const.CONJ_MAX_PREFIX)
self.conjStemmer.set_max_suffix_length(stem_noun_const.CONJ_MAX_SUFFIX)
self.conjStemmer.set_min_stem_length(stem_noun_const.CONJ_MIN_STEM)
self.conjStemmer.set_prefix_list(stem_noun_const.CONJ_PREFIX_LIST)
self.conjStemmer.set_suffix_list(stem_noun_const.CONJ_SUFFIX_LIST)
# noun dictionary
self.nounDictionary = arabicdictionary.arabicDictionary(
"nouns", NOUN_DICTIONARY_INDEX)
#word frequency dictionary
self.wordfreq = wordfreqdictionaryclass.wordfreqDictionary(
'wordfreq', wordfreqdictionaryclass.wordfreq_DICTIONARY_INDEX)
# self.TriVerbTable_INDEX={};
self.Table_affix_INDEX = {}
self.NOUN_DICTIONARY_STAMP = {}
# allow to print internal results.
self.debug = debug