def test_general_letters(self):
# test order()
assert Araby.order(Araby.ALEF) == 1
assert Araby.order(Araby.HAMZA) == 29
assert Araby.order(Araby.YEH) == 28
assert Araby.order(Araby.TEH_MARBUTA) == 3
assert Araby.order(Araby.TEH) == 3
# test name()
assert Araby.name(u"أ") == u'همزة على الألف'
assert Araby.name(u"ب") == u'باء'
assert Araby.name(Araby.ALEF_HAMZA_ABOVE) == u'همزة على الألف'
assert Araby.name(u"ة") == u'تاء مربوطة'
def decode_triverb(self, verb_table, limit):
""" readlines from files """
verb_list = []
for fields in verb_table:
if len(fields) >= 4:
#الفعل الجذر باب التصريف T id
vdict= {"verb": fields[0],
"root":fields[1],
"haraka":araby.name(get_future_type_entree(fields[2])),
"transitive":fields[3],
}
verb_list.append(vdict)
return verb_list
def mainly():
"""
main test
"""
mode = "fa3il"
DATA_FILE = "samples/fa3il-5.csv"
#~ DATA_FILE = "samples/maf3oul.csv"
#~ mode = "maf3oul"
with open(DATA_FILE) as f:
line = f.readline().decode('utf8')
while line :
if not line.startswith("#"):
liste = line.strip('\n').split("\t")
if len(liste) >= 2 :
correct = liste[0]
word = liste[1].split(';')[0]
transitive = True
future_type = get_future_type(word)
if valid_verb.is_valid_infinitive_verb(word,True): # vocalized
result = generate_subject(word, transitive, future_type)
fa3il = result.get("subject", u"")
maf3oul = result.get("object", u"")
inf_verb = result.get("infinitive", word)
debug = False
#~ debug = True
if mode == "maf3oul":
if debug or not correct == maf3oul:
print (u"\t".join([word,inf_verb,araby.name(future_type)+future_type,maf3oul, correct, str(correct==maf3oul)])).encode('utf8')
else:
if debug or not correct == fa3il:
print (u"\t".join([word,inf_verb,fa3il, correct, str(correct==fa3il)])).encode('utf8')
else:
print (u"\t".join([word,"","", correct, "Invalid_Verb"])).encode('utf8')
line = line = f.readline().decode('utf8')
#!/usr/bin/env python
# -*- coding: utf-8 -*-
from __future__ import (
absolute_import,
print_function,
unicode_literals,
division,
)
import sys
sys.path.append("../")
#~ import pyarabic.harf as harf
#from pyarabic import harf
import pyarabic.araby as araby
for c in araby.arabicrange():
print(c, '\t', araby.name(c), end=" ")
print('\t', end=" ")
if araby.is_sukun(c): print("sukun", end=" ")
if araby.is_haraka(c): print("haraka", end=" ")
if araby.is_shadda(c): print("shadda", end=" ")
if araby.is_tatweel(c): print("tatweel", end=" ")
if araby.is_tashkeel(c): print("tashkeel", end=" ")
if araby.is_tanwin(c): print("tanwin", end=" ")
if araby.is_shortharaka(c): print("short haraka", end=" ")
if araby.is_ligature(c): print(" ligature", end=" ")
if araby.is_ligature(c): print('ligature', end=" ")
if araby.is_hamza(c): print('hamza', end=" ")
if araby.is_alef(c): print('alef', end=" ")
if araby.is_yehlike(c): print('yeh', end=" ")
if araby.is_wawlike(c): print('waw', end=" ")
if araby.is_teh(c): print('teh', end=" ")
#!/usr/bin/env python
# -*- coding: utf-8 -*-
import sys
sys.path.append('../')
from pyarabic import araby
for c in araby.arabicrange():
print (c,'\t', araby.name(c))
print ('\t')
if araby.is_sukun(c): print ("sukun")
if araby.is_haraka(c): print ("haraka")
if araby.is_shadda(c): print ("shadda")
if araby.is_tatweel(c): print ("tatweel")
if araby.is_tashkeel(c): print ("tashkeel")
if araby.is_tanwin(c): print ("tanwin")
if araby.is_shortharaka(c): print ("short haraka"),
if araby.is_ligature(c):print (" ligature"),
if araby.is_ligature(c):print ('ligature'),
if araby.is_hamza(c): print ('hamza'),
if araby.is_alef(c): print ('alef'),
if araby.is_yehlike(c): print ('yeh'),
if araby.is_wawlike(c): print ('waw'),
if araby.is_teh(c): print ('teh'),
if araby.is_small(c): print ('small'),
if araby.is_weak(c): print ('weak'),
if araby.is_moon(c): print ('moon'),
if araby.is_sun(c):print ('sun'),
print (araby.order(c)),
print ();
word=u"الْعَرَيِيّةُ"
#!/usr/bin/env python
# -*- coding: utf-8 -*-
import sys
sys.path.append("../")
#~ import pyarabic.harf as harf
#from pyarabic import harf
import pyarabic.araby as araby
for c in araby.arabicrange():
print c.encode('utf8'),'\t', araby.name(c).encode('utf8'),
print '\t',
if araby.is_sukun(c): print "sukun",
if araby.is_haraka(c): print "haraka",
if araby.is_shadda(c): print "shadda",
if araby.is_tatweel(c): print "tatweel",
if araby.is_tashkeel(c): print "tashkeel",
if araby.is_tanwin(c): print "tanwin",
if araby.is_shortharaka(c): print "short haraka",
if araby.is_ligature(c):print " ligature",
if araby.is_ligature(c):print 'ligature',
if araby.is_hamza(c): print 'hamza',
if araby.is_alef(c): print 'alef',
if araby.is_yehlike(c): print 'yeh',
if araby.is_wawlike(c): print 'waw',
if araby.is_teh(c): print 'teh',
if araby.is_small(c): print 'small',
if araby.is_weak(c): print 'weak',
if araby.is_moon(c): print 'moon',
if araby.is_sun(c):print 'sun',
print araby.order(c),
print;
def standard2(word_nm, harakat):
""" join the harakat and the letters to the give word
in the standard script,
it return one strings ( the word with harakat and the harakat).
@param word_nm: given unvocalized word.
@type word_nm: unicode.
@param harakat: given harakat.
@type harakat: unicode.
@return: vocalized word.
@rtype: unicode.
"""
if len(word_nm) != len(harakat):
print(word_nm.encode('utf8'), len(word_nm),
u"-".join([araby.name(x) for x in harakat]), len(harakat))
return u"*"
else:
word = u""
i = 0
word_nm, harakat = geminating(word_nm, harakat)
if len(word_nm) != len(harakat):
return u""
## حالة عدم الابتداء بسكون
##إذا كان الحرف الثاني مضموما تكون الحركة الأولى مضمومة، وإلا تكون مكسورة
if len(harakat) != 0 and harakat.startswith(SUKUN):
word_nm = ALEF + word_nm
if len(harakat) >= 2 and harakat[1] in \
(DAMMA, vconst.WAW_HARAKA):
harakat = DAMMA + harakat
else:
harakat = KASRA + harakat
## word_nm = tahmeez2(word_nm, harakat)
if len(word_nm) != len(harakat):
return u""
word_before = word_nm
harakat_before = harakat
word_nm, harakat = homogenize(word_nm, harakat)
if len(word_nm) != len(harakat):
print("len word: ", len(word_nm), word_nm.encode('utf8'))
print("len harakat: ", len(harakat), repr(harakat))
print(repr(harakat_before), word_before.encode('utf8'))
return u""
word_nm = tahmeez2(word_nm, harakat)
len_word_nm = len(word_nm)
while i < len_word_nm:
# للعمل :
# هذه حالة الألف التي أصلها ياء
# وقد استغنينا عنها بأن جعلنا الحرف الناقص من الفعل الناقص حرفا تاما
if harakat[i] in vconst.WRITTEN_HARAKA:
word += word_nm[i] + vconst.WRITTEN_HARAKA[harakat[i]]
else:
word += word_nm[i] + harakat[i]
i += 1
#-تحويل همزة القطع على الألف بعدها فتحة
#وهمزة القطع على الألف بعدها سكون إلى ألف ممدودة
for (pat, rep) in vconst.STANDARD_REPLACEMENT:
word = word.replace(pat, rep)
return word
def decode_verb_tuple(self, tuple_verb):
"""
"""
#abbrevated=False;
verb_field_number=2;
root_field_number=1;
verb_cat_field_number=3;
root = self.decode_root(tuple_verb[root_field_number].strip());
word = tuple_verb[verb_field_number].strip();
if not is_valid_infinitive_verb(word):
return {"text":u"#\t'%s'\tis invalid verb "%word};
else:
model = tuple_verb[0].strip();
#print word.encode("utf8")
future_type = u"-";
future_type = araby.name(get_future_type_entree(future_type));
verb_cat = tuple_verb[verb_cat_field_number].strip();
# decode transitive flag
#print "'%s'"%transitive;
transitive = self.decode_transitive(verb_cat);
#tenses=decode_tenses(verb_cat);
# decode the tenses
#init at False
all=False;
future=False;
past=False;
passive=False;
imperative=False;
confirmed=False;
future_moode=False;
# متعدي لغير العاقل
unthink_trans=False;
# متعدي للعاقل، تلقائيا اﻷفعال تقبل العاقل
think_trans=True;
#فعل قلوب
reflexive_trans=False;
#متعدي لمفعولين
double_trans=False;
if verb_cat =="A":# أمر فقط
imperative=True;
elif verb_cat =="D":# مبني للمجهول فقط
passive=True;
elif verb_cat =="I":#لاشخصي
pass;
elif verb_cat =="M":#جامد
pass;
elif verb_cat =="P":# ماضي فقط
past=True;
elif verb_cat =="Pu":# ماضي فقط لازم مطلق
past=True;
elif verb_cat =="Ry":# مضارع وأمر فقط
future=True;
imperative=True;
elif verb_cat =="Su":# ماضي ومضارع
future=True;
past=True;
confirmed=True;
future_moode=True;
elif verb_cat =="Sv":# ماضي ومضارع
future=True;
past=True;
confirmed=True;
future_moode=True;
elif verb_cat =="Sx":# ماضي ومضارع
future=True;
past=True;
confirmed=True;
future_moode=True;
elif verb_cat =="u":# لازم مطلق، لا مجهول ولا أمر
future=True;
past=True;
confirmed=True;
future_moode=True;
elif verb_cat =="v":# لازم نسبي، كل اﻷزمنة، لكن المجهول مع المفرد الغائب
future=True;
past=True;
imperative=True;
confirmed=True;
future_moode=True;
passive=False;
elif verb_cat in ("x","y", "yw", "ywz", "yy", "yz","yzw"): # ماضي فقط
all=True;
future=True;
past=True;
imperative=True;
confirmed=True;
future_moode=True;
passive=False;
if verb_cat in ("x","Sx"):
unthink_trans=True;
elif verb_cat in ("yw", "ywz", "yy", "yz","yzw", "Ry"):
think_trans=True;
if verb_cat in ("ywz","yz","yzw"):
double_trans=True;
if verb_cat in ("ywz", "yw", "yzw"):
reflexive_trans=True;
else:
all=True;
nb_trans=0;
object_type=u"----"
reflexive_type=u"----";
if transitive:
transitive=u'متعد'
nb_trans=1;
if double_trans:
nb_trans=2;
if think_trans:
object_type=u"عاقل";
if unthink_trans:
object_type=u"غيرع";
if reflexive_trans:
reflexive_type=u"فلبي";
else:
transitive=u'لازم'
## codify the tense;
tenses = self.encode_tense(all, past, future, imperative, passive, future_moode, confirmed)
## print ('\t'.join([word,future_type,str(transitive)])).encode('utf8');
nb_case=0;
suggest=u"";
triliteral=u"غيرثل"
if is_triliteral_verb(word):
triliteral=u"ثلاثي"
if False:
# search the future haraka for the triliteral verb
liste_verb = find_alltriverb(word, araby.FATHA,True);
# if there are more verb forms, select the first one
filtered = [item for item in liste_verb if item['verb'] == word]
if filtered:
#~ word = liste_verb[0]["verb"]
haraka = filtered[0]["haraka"]
future_type = haraka;
transitive_mark = filtered[0]["transitive"].strip();
if transitive_mark in (u"م",u"ك"):
transitive = u"متعد"
else:
transitive = u"لازم"
else:
return {"text":u"#gen_verb_dict: %s error no tri verb"%word}
if liste_verb:
if len(liste_verb)>1:
#suggest=u"هل تقصد؟<br/>"
nb_case = len(liste_verb);
# the other forms are suggested
for i in range(1,len(liste_verb)):
suggested_word = liste_verb[i]["verb"]
suggested_haraka = liste_verb[i]["haraka"]
suggested_transitive = liste_verb[i]["transitive"]
future_form = get_future_form(suggested_word,suggested_haraka);
suggest=u"\t".join([suggest,suggested_word,u"["+suggested_haraka+u"]"]);
else:suggest="-"
verb_dict = {'nb_case': str(nb_case),
'word': word,
'tenses': tenses,
'nb_trans': nb_trans,
'suggest': suggest,
'triliteral': triliteral,
'object_type': object_type,
'verb_cat': verb_cat,
'future_type': future_type,
'model': model,
'transitive': transitive,
'root': root,
'reflexive_type': reflexive_type,
}
return verb_dict
for key, group in groupby(aa5irHarf)]
print(freqOfAa5irHarf)
import collections
counter = collections.Counter(aa5irHarf)
print(counter)
# Counter({1: 4, 2: 4, 3: 2, 5: 2, 4: 1})
print(counter.values())
# [4, 4, 2, 1, 2]
print(counter.keys())
# [1, 2, 3, 4, 5]
print(counter.most_common(3))
# [(1, 4), (2, 4), (3, 2)]
print(counter.most_common(1))
kkey = counter.most_common(1)
#we should write to file or save it anywhere
#and also we should generalize it to all poems for each poet
#القافية :آخر ساكن وبدور عالساكن اللي قبله مع الحرف المتحرك اللي قبل الساكن ال ما قبل الاخير
print('********** Al Qafiya ************')
for line in f:
line1 = araby.strip_tatweel(line)
letters, hrkat = araby.separate(line1)
#print(letters.encode('utf8'))
for m in hrkat:
#لازم نعمل تعديلات
if not araby.is_tatweel(m):
print(araby.name(m))
print(''.join(m))
#Most Common Words بنعملهم بكل قصائد الشاعر
#!/usr/bin/env python
# -*- coding: utf-8 -*-
import sys
sys.path.append("../")
#~ import pyarabic.harf as harf
#from pyarabic import harf
import pyarabic.araby as araby
for c in araby.arabicrange():
print c.encode('utf8'), '\t', araby.name(c).encode('utf8'),
print '\t',
if araby.is_sukun(c): print "sukun",
if araby.is_haraka(c): print "haraka",
if araby.is_shadda(c): print "shadda",
if araby.is_tatweel(c): print "tatweel",
if araby.is_tashkeel(c): print "tashkeel",
if araby.is_tanwin(c): print "tanwin",
if araby.is_shortharaka(c): print "short haraka",
if araby.is_ligature(c): print " ligature",
if araby.is_ligature(c): print 'ligature',
if araby.is_hamza(c): print 'hamza',
if araby.is_alef(c): print 'alef',
if araby.is_yehlike(c): print 'yeh',
if araby.is_wawlike(c): print 'waw',
if araby.is_teh(c): print 'teh',
if araby.is_small(c): print 'small',
if araby.is_weak(c): print 'weak',
if araby.is_moon(c): print 'moon',
if araby.is_sun(c): print 'sun',
print araby.order(c),
print
