def extract_poem():
"""[summary]
might not be using it
Returns:
[type] -- [description]
dict -- postings lists of arabic words
"""
postings_list = {}
tokens = []
with open("short story.txt", encoding='utf-8') as ofile:
for loc, line in enumerate(ofile, 1):
words = araby.tokenize(araby.strip_tashkeel(line))
tokens.extend(words)
for word in words:
if (araby.is_tatweel(word)):
word = araby.strip_tatweel(word)
# if word not in postings_list:
# postings_list[word]=[loc]
# else:
# postings_list[word].append(loc)
#return postings_list
return tokens
def test_is_letter(self):
self.assertTrue(Araby.is_sukun(Araby.SUKUN))
self.assertTrue(Araby.is_shadda(Araby.SHADDA))
self.assertTrue(Araby.is_tatweel(Araby.TATWEEL))
for archar in Araby.TANWIN:
self.assertTrue(Araby.is_tanwin(archar))
for archar in Araby.TASHKEEL:
self.assertTrue(Araby.is_tashkeel(archar))
for haraka in Araby.HARAKAT:
self.assertTrue(Araby.is_haraka(haraka))
for short_haraka in Araby.SHORTHARAKAT:
self.assertTrue(Araby.is_shortharaka(short_haraka))
for liguature in Araby.LIGUATURES:
self.assertTrue(Araby.is_ligature(liguature))
for hamza in Araby.HAMZAT:
self.assertTrue(Araby.is_hamza(hamza))
for alef in Araby.ALEFAT:
self.assertTrue(Araby.is_alef(alef))
for yeh in Araby.YEHLIKE:
self.assertTrue(Araby.is_yehlike(yeh))
for waw in Araby.WAWLIKE:
self.assertTrue(Araby.is_wawlike(waw))
for teh in Araby.TEHLIKE:
self.assertTrue(Araby.is_teh)
for small in Araby.SMALL:
self.assertTrue(Araby.is_small(small))
for weak in Araby.WEAK:
self.assertTrue(Araby.is_weak(weak))
for archar in Araby.MOON:
self.assertTrue(Araby.is_moon(archar))
for archar in Araby.SUN:
self.assertTrue(Araby.is_sun(archar))
def soundex(sentence):
'''
- blanks and and spaces are deleted,
- long vowels are deleted,
- if two adjacent letters are identical, only one of the two is
kept,
- to each word’s letter are associated two numbers:
1. the first one corresponds to the letter’s main category’s
code. It is represented by an integer N of two bits, such as N
E={0, 1, 2}.
2. the second one corresponds to the letter’s sub-category’s
code. It is represented by an integer n of four bits, such as:
n SE= {0,...,10}.
Thus :
Given a word w, w=w 1 ...w n .
w=w- {blanks and long vowels}=w’ 1 ... w’ n .
f(w)=f(w’)=f(w’ 1 ... w’ n )=N 1 n 1 ... N n n n =X.
The phonetic code generated X, can be used as a hash key
for classifying and indexing purposes.
Returns:
[type] -- [description]
'''
words = araby.tokenize(sentence)
for word in words:
if type(word) != str:
word = word.decode('utf-8')
else:
word = word.encode('utf-8')
loc = 0
for i in word[0:]:
if araby.is_tatweel(i):
word = araby.strip_tatweel(word)
if loc < len(word) and loc != 0 and re.match(
"[\u0627\u064a\u0648]", str(word[loc])):
word = word[:loc] + word[loc + 1:]
if loc < len(word) and re.match("[\u0640]", str(word[loc])):
word = word[:loc] + word[loc + 1:]
loc += 1
print(words)
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=" ")
if araby.is_small(c): print('small', end=" ")
if araby.is_weak(c): print('weak', end=" ")
if araby.is_moon(c): print('moon', end=" ")
if araby.is_sun(c): print('sun', end=" ")
print(araby.order(c), 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;
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