How to use the pyarabic.araby.strip_harakat function in PyArabic

To help you get started, we’ve selected a few PyArabic examples, based on popular ways it is used in public projects.

Secure your code as it's written. Use Snyk Code to scan source code in minutes - no build needed - and fix issues immediately.

github linuxscout / mishkal / mishkal / lib / libqutrub / classverb.py View on Github external
self.future_type = ar_verb.get_future_type_by_name(future_type)
        (self.word_letters, self.word_marks) = ar_verb.uniformate_verb(verb)
        #Before last haraka in the past
        self.past_haraka = araby.secondlast_char(self.word_marks)
        self.word_marks = ar_verb.uniformate_alef_origin(self.word_marks, 
        self.internal_verb, self.future_type)

        self.transitive = transitive
        self.hamza_zaida = False
        self.tab_conjug_stem = {}
        verb = self.verb
        tab_type = [u"", u"", u"", u"فعل ثلاثي", u"فعل رباعي", u"فعل خماسي", 
        u"فعل سداسي", u"فعل سباعي", u"فعل ثماني", u"فعل تساعي"]
        verb = ar_verb.normalize(verb)

        self.unvocalized = araby.strip_harakat(verb)
        verb_nm = self.unvocalized
        self.vlength = len(verb_nm)
        self.vtype = tab_type[self.vlength]

        # الهمزة زائدة
        self.hamza_zaida = self._is_hamza_zaida(verb_nm)

        # التاء الزائدة
        #deprecated
        #self.teh_zaida=self.is_teh_zaida(verb_nm)

        # معالجة حالة الأفعال الشاذة
        # إذا كان الفعل من الشواذ، استخرجنا جذوع التصريف من جدوله
        #وإلا ولّدنا جذوع تصريفه
        # في المضارع والأمر فقط
        # أما الماضي فليس فيه شذوذ
github linuxscout / mishkal / support / qalsadi / analex.py View on Github external
    @param resulted_data: the founded resulat from dictionary.
    @type resulted_data: list of dict.
    @param fully_vocalized_input: if the two words must resect the shadda and vocalized.
    @param fully_vocalized_input: Boolean, default is False.
    @type word_vocalised: unicode.    
    @return: list of dictionaries of analyzed words with tags.
    @rtype: list.
    """
    #~return filter(lambda item: araby.shaddalike(word_vocalised,
    #~item.__dict__.get('vocalized', '')), resulted_data)
    #~x for x in [1, 1, 2] if x == 1
    #~ return [
    #~ x for x in resulted_data
    #~ if araby.shaddalike(word_vocalised, x.__dict__.get('vocalized', '')) ]
    if fully_vocalized_input:
        return [x for x in resulted_data if araby.strip_harakat(word_vocalised) == 
    araby.strip_harakat(x.__dict__.get('vocalized', ''))]
    else:
        return [
        x for x in resulted_data
        if araby.shaddalike(word_vocalised, x.__dict__.get('vocalized', ''))
    ]
github linuxscout / arramooz / scripts / verbs / gen_verb_dict.py View on Github external
def create_index_triverbtable():
    """ Create index from the verb dictionary
    to accelerate the search in the dictionary for verbs
    @return: create the TRIVERBTABLE_INDEX
    @rtype: None
    """
    # the key is the vocverb + the bab number
    for key in triverbtable.TriVerbTable.keys():
        vocverb = triverbtable.TriVerbTable[key]['verb']
        unvverb = araby.strip_harakat(vocverb)
        normverb = araby.normalize_hamza(unvverb)
        if TRIVERBTABLE_INDEX.has_key(normverb):
            TRIVERBTABLE_INDEX[normverb].append(key)
        else:
            TRIVERBTABLE_INDEX[normverb] = [key, ]
github linuxscout / mishkal / support / qalsadi / analex.py View on Github external
    @type resulted_data: list of dict.
    @param fully_vocalized_input: if the two words must resect the shadda and vocalized.
    @param fully_vocalized_input: Boolean, default is False.
    @type word_vocalised: unicode.    
    @return: list of dictionaries of analyzed words with tags.
    @rtype: list.
    """
    #~return filter(lambda item: araby.shaddalike(word_vocalised,
    #~item.__dict__.get('vocalized', '')), resulted_data)
    #~x for x in [1, 1, 2] if x == 1
    #~ return [
    #~ x for x in resulted_data
    #~ if araby.shaddalike(word_vocalised, x.__dict__.get('vocalized', '')) ]
    if fully_vocalized_input:
        return [x for x in resulted_data if araby.strip_harakat(word_vocalised) == 
    araby.strip_harakat(x.__dict__.get('vocalized', ''))]
    else:
        return [
        x for x in resulted_data
        if araby.shaddalike(word_vocalised, x.__dict__.get('vocalized', ''))
    ]
github linuxscout / mishkal / support / qalsadi / libqutrub / classverb.py View on Github external
self.future_type = ar_verb.get_future_type_by_name(future_type)
        (self.word_letters, self.word_marks) = ar_verb.uniformate_verb(verb)
        #Before last haraka in the past
        self.past_haraka = araby.secondlast_char(self.word_marks)
        self.word_marks = ar_verb.uniformate_alef_origin(self.word_marks, 
        self.internal_verb, self.future_type)

        self.transitive = transitive
        self.hamza_zaida = False
        self.tab_conjug_stem = {}
        verb = self.verb
        tab_type = [u"", u"", u"", u"فعل ثلاثي", u"فعل رباعي", u"فعل خماسي", 
        u"فعل سداسي", u"فعل سباعي", u"فعل ثماني", u"فعل تساعي"]
        verb = ar_verb.normalize(verb)

        self.unvocalized = araby.strip_harakat(verb)
        verb_nm = self.unvocalized
        self.vlength = len(verb_nm)
        self.vtype = tab_type[self.vlength]

        # الهمزة زائدة
        self.hamza_zaida = self._is_hamza_zaida(verb_nm)

        # التاء الزائدة
        #deprecated
        #self.teh_zaida=self.is_teh_zaida(verb_nm)

        # معالجة حالة الأفعال الشاذة
        # إذا كان الفعل من الشواذ، استخرجنا جذوع التصريف من جدوله
        #وإلا ولّدنا جذوع تصريفه
        # في المضارع والأمر فقط
        # أما الماضي فليس فيه شذوذ
github linuxscout / mishkal / support / libqutrub / conjugatedisplay.py View on Github external
        @type listtense: list of unicode
        @return: the result as text in row.
        @rtype: unicode.
        """        
        text = u""

        transitive = "0"
        if self.transitive:
            transitive = '1'
        for pronoun in vconst.PronounsTable:
##            text += u"%s"  % (pronoun)
            for tense in listtense:
#                print (self.verb).encode("utf-8"), 
                if  self.tab_conjug[tense][pronoun] != "":
                    text += "\t".join([
                        araby.strip_harakat(self.tab_conjug[tense][pronoun]), 
                        self.tab_conjug[tense][pronoun], 
                        TAB_DISPLAY[pronoun], 
                        TAB_DISPLAY[tense], 
                        transitive, 
                        self.verb, 
                        self.bab, 
                        ])
                    text += u"\n"
        return text
github linuxscout / arramooz / scripts / verbs / gen_verb_dict.py View on Github external
- 'bab':
        - 'transitive':
    @param triverb: given verb.
    @type triverb: unicode.
    @param givenharaka: given haraka of tuture type of the verb, 
    default(FATHA).
    @type givenharaka: unicode.
    @param VocalisedEntree: True if the given verb is vocalized, 
    default False.
    @type VocalisedEntree: Boolean.
    @return: list of triliteral verbs.
    @rtype: list of dicts.
    """
    liste = []
    if vocalised_entree:
        verb_nm = araby.strip_harakat(triverb)
    else:
        verb_nm = triverb

    normalized = araby.normalize_hamza(verb_nm)
    if TRIVERBTABLE_INDEX.has_key(normalized):
        for verb_voc_id in TRIVERBTABLE_INDEX[normalized]:
            if triverb == triverbtable.TriVerbTable[verb_voc_id]['verb'] and \
             givenharaka == triverbtable.TriVerbTable[verb_voc_id]['haraka']:
                liste.insert(0, triverbtable.TriVerbTable[verb_voc_id])
#            if VocalisedEntree:
                #if verb_voc_id[:-1] == triverb:
                #    liste.append(TriVerbTable[verb_voc_id])
            else:
                liste.append(triverbtable.TriVerbTable[verb_voc_id])
    else:
        print "triverb has no verb"