Ë
    çÍ:j9  ã                   ó2   — d Z ddlZddlmZ  G d„ de«      Zy)u^  
ISRI Arabic Stemmer

The algorithm for this stemmer is described in:

Taghva, K., Elkoury, R., and Coombs, J. 2005. Arabic Stemming without a root dictionary.
Information Science Research Institute. University of Nevada, Las Vegas, USA.

The Information Science Research Instituteâ€™s (ISRI) Arabic stemmer shares many features
with the Khoja stemmer. However, the main difference is that ISRI stemmer does not use root
dictionary. Also, if a root is not found, ISRI stemmer returned normalized form, rather than
returning the original unmodified word.

Additional adjustments were made to improve the algorithm:

1- Adding 60 stop words.
2- Adding the pattern (ØªÙ�Ø§Ø¹ÙŠÙ„) to ISRI pattern set.
3- The step 2 in the original algorithm was normalizing all hamza. This step is discarded because it
increases the word ambiguities and changes the original root.

é    N)ÚStemmerIc                   ól   — e Zd ZdZd„ Zd„ Zdd„Zd„ Zd„ Zd„ Z	d„ Z
d	„ Zd
„ Zd„ Zd„ Zd„ Zd„ Zd„ Zd„ Zy)ÚISRIStemmera&  
    ISRI Arabic stemmer based on algorithm: Arabic Stemming without a root dictionary.
    Information Science Research Institute. University of Nevada, Las Vegas, USA.

    A few minor modifications have been made to ISRI basic algorithm.
    See the source code of this module for more information.

    isri.stem(token) returns Arabic root for the given token.

    The ISRI Stemmer requires that all tokens have Unicode string types.
    If you use Python IDLE on Arabic Windows you have to decode text first
    using Arabic '1256' coding.
    c                 óz  — g d¢| _         ddg| _        g d¢| _        g d¢| _        g d¢| _        g d¢| _        dgd	gg d
¢dgdœ| _        d	dgg d¢g d¢g d¢ddgd	dgd	dgdœ| _        t        j                  d«      | _
        t        j                  d«      | _        t        j                  d«      | _        g d¢| _        y )N)u   ÙƒØ§Ù„u   Ø¨Ø§Ù„u   ÙˆÙ„Ù„u   ÙˆØ§Ù„u   Ø§Ù„u   Ù„Ù„)	u   Ù„u   Ø¨u   Ù�u   Ø³õ   Ùˆõ   ÙŠõ   Øªõ   Ù†õ   Ø§)u   ØªÙ…Ù„u   Ù‡Ù…Ù„u   ØªØ§Ù†u   ØªÙŠÙ†u   ÙƒÙ…Ù„)u   ÙˆÙ†u   Ø§Øªu   Ø§Ù†u   ÙŠÙ†u   ØªÙ†u   ÙƒÙ…u   Ù‡Ù†u   Ù†Ø§u   ÙŠØ§u   Ù‡Ø§u   ØªÙ…u   ÙƒÙ†u   Ù†ÙŠu   ÙˆØ§u   Ù…Ø§u   Ù‡Ù…)õ   Ø©u   Ù‡r   u   Ùƒr	   r   r
   õ   Ù…r   )r   r   r   r   )r   é   é   é   r	   )r   r   r   )r   r	   r   )r   r   r	   r   )r   r   r   r   é   é   é   z[\u064B-\u0652]z[\u0621\u0624\u0626]z^[\u0622\u0623\u0625])1u   ÙŠÙƒÙˆÙ†u   ÙˆÙ„ÙŠØ³u   ÙˆÙƒØ§Ù†u   ÙƒØ°Ù„Ùƒu   Ø§Ù„ØªÙŠu   ÙˆØ¨ÙŠÙ†u
   Ø¹Ù„ÙŠÙ‡Ø§u   Ù…Ø³Ø§Ø¡u   Ø§Ù„Ø°ÙŠu
   ÙˆÙƒØ§Ù†Øªu   ÙˆÙ„ÙƒÙ†u
   ÙˆØ§Ù„ØªÙŠu   ØªÙƒÙˆÙ†u
   Ø§Ù„ÙŠÙˆÙ…u   Ø§Ù„Ù„Ø°ÙŠÙ†u   Ø¹Ù„ÙŠÙ‡u   ÙƒØ§Ù†Øªu   Ù„Ø°Ù„Ùƒu   Ø£Ù…Ø§Ù…u   Ù‡Ù†Ø§Ùƒu   Ù…Ù†Ù‡Ø§u
   Ù…Ø§Ø²Ø§Ù„u
   Ù„Ø§Ø²Ø§Ù„u   Ù„Ø§ÙŠØ²Ø§Ù„u   Ù…Ø§ÙŠØ²Ø§Ù„u   Ø§ØµØ¨Ø­u   Ø£ØµØ¨Ø­u   Ø£Ù…Ø³Ù‰u   Ø§Ù…Ø³Ù‰u   Ø£Ø¶Ø­Ù‰u   Ø§Ø¶Ø­Ù‰u
   Ù…Ø§Ø¨Ø±Ø­u
   Ù…Ø§Ù�ØªØ¦u   Ù…Ø§Ø§Ù†Ù�Ùƒu   Ù„Ø§Ø³ÙŠÙ…Ø§u   ÙˆÙ„Ø§ÙŠØ²Ø§Ù„u   Ø§Ù„Ø­Ø§Ù„ÙŠu
   Ø§Ù„ÙŠÙ‡Ø§u
   Ø§Ù„Ø°ÙŠÙ†u   Ù�Ø§Ù†Ù‡u
   ÙˆØ§Ù„Ø°ÙŠu   ÙˆÙ‡Ø°Ø§u   Ù„Ù‡Ø°Ø§u   Ù�ÙƒØ§Ù†u
   Ø³ØªÙƒÙˆÙ†u   Ø§Ù„ÙŠÙ‡u   ÙŠÙ…ÙƒÙ†u   Ø¨Ù‡Ø°Ø§u   Ø§Ù„Ø°Ù‰)Úp3Úp2Úp1Ús3Ús2Ús1Úpr4Úpr53ÚreÚcompileÚre_short_vowelsÚre_hamzaÚre_initial_hamzaÚ
stop_words)Úselfs    úc/home/mcse/projects/srt_converter/srt-converter-venv/lib/python3.12/site-packages/nltk/stem/isri.pyÚ__init__zISRIStemmer.__init__3   sÏ   € ò
ˆŒð " >Ð2ˆŒò

ˆŒò
ˆŒò
ˆŒò( YˆŒð ˆzØˆzÚ-Øˆzñ	
ˆŒð ˜(Ð#Ú-Ú-Ú-Ø˜(Ð#Ø˜(Ð#Ø˜(Ð#ñ
ˆŒ	ô  "Ÿz™zÐ*<Ó=ˆÔÜŸ
™
Ð#:Ó;ˆŒÜ "§
¡
Ð+CÓ DˆÔò2
ˆ�ó    c                 óº  — | j                  |d«      }|| j                  v r|S | j                  |«      }| j                  |«      }| j	                  |«      }| j                  |d«      }t        |«      dk(  r| j                  |«      }|S t        |«      dk(  r$| j                  |«      }| j                  |«      }|S t        |«      dk(  r$| j                  |«      }| j                  |«      }|S t        |«      dk(  r`| j                  |«      }t        |«      dk(  r| j                  |«      }t        |«      dk(  r"| j                  |«      }| j                  |«      }|S )z?
        Stemming a word token using the ISRI stemmer.
        r   r   r   r   r   é   )Únormr!   Úpre32Úsuf32ÚwawÚlenÚpro_w4Úpro_w53Úend_w5Úpro_w6Úend_w6Úsuf1Úpre1)r"   Útokens     r#   ÚstemzISRIStemmer.stem·   sS  € ð —	‘	Ø�1ó
ˆð �D—O‘OÑ#ØˆLØ—
‘
Øó
ˆð —
‘
Øó
ˆð —‘Øó
ˆð —	‘	˜% Ó#ˆäˆu‹:˜Š?Ø—K‘K Ó&ˆEð ˆô �‹Z˜1Š_Ø—L‘L Ó'ˆEØ—K‘K Ó&ˆEð ˆô �‹Z˜1Š_Ø—K‘K Ó&ˆEØ—K‘K Ó&ˆEð ˆô �‹Z˜1Š_Ø—I‘I˜eÓ$ˆEÜ�5‹z˜QŠØŸ	™	 %Ó(�Ü�5‹z˜QŠØŸ™ EÓ*�ØŸ™ EÓ*�Øˆr%   c                 ó  — |dk(  r| j                   j                  d|«      }|S |dk(  r| j                  j                  d|«      }|S |dk(  r8| j                   j                  d|«      }| j                  j                  d|«      }|S )zƒ
        normalization:
        num=1  normalize diacritics
        num=2  normalize initial hamza
        num=3  both 1&2
        r   Ú r   r   r   )r   Úsubr    )r"   ÚwordÚnums      r#   r(   zISRIStemmer.normÜ   s�   € ð �!Š8Ø×'Ñ'×+Ñ+¨B°Ó5ˆDð ˆð �AŠXØ×(Ñ(×,Ñ,¨X°tÓ<ˆDð ˆð �AŠXØ×'Ñ'×+Ñ+¨B°Ó5ˆDØ×(Ñ(×,Ñ,¨X°tÓ<ˆDØˆr%   c                 óâ   — t        |«      dk\  r)| j                  D ]  }|j                  |«      sŒ|dd c S  t        |«      dk\  r)| j                  D ]  }|j                  |«      sŒ|dd c S  |S )z9remove length three and length two prefixes in this orderr   r   Nr   r   )r,   r   Ú
startswithr   )r"   r9   Úpre3Úpre2s       r#   r)   zISRIStemmer.pre32ì   su   € äˆt‹9˜Š>ØŸ™ò $�Ø—?‘? 4Õ(Ø  ˜8’Oð$ô ˆt‹9˜Š>ØŸ™ò $�Ø—?‘? 4Õ(Ø  ˜8’Oð$ð ˆr%   c                 óâ   — t        |«      dk\  r)| j                  D ]  }|j                  |«      sŒ|dd c S  t        |«      dk\  r)| j                  D ]  }|j                  |«      sŒ|dd c S  |S )z9remove length three and length two suffixes in this orderr   Néýÿÿÿr   éþÿÿÿ)r,   r   Úendswithr   )r"   r9   Úsuf3Úsuf2s       r#   r*   zISRIStemmer.suf32ø   sw   € äˆt‹9˜Š>ØŸ™ò %�Ø—=‘= Õ&Ø  ˜9Ò$ð%ô ˆt‹9˜Š>ØŸ™ò %�Ø—=‘= Õ&Ø  ˜9Ò$ð%ð ˆr%   c                 ó<   — t        |«      dk\  r|dd dk(  r|dd }|S )uH   remove connective â€˜Ùˆâ€™ if it precedes a word beginning with â€˜Ùˆâ€™r   Nr   u   ÙˆÙˆr   )r,   ©r"   r9   s     r#   r+   zISRIStemmer.waw  s*   € äˆt‹9˜Š>˜d 2 A˜h¨.Ò8Ø˜˜�8ˆDØˆr%   c                 óV  — |d   | j                   d   v r|dd }|S |d   | j                   d   v r|dd |dd z   }|S |d   | j                   d   v r|dd |d   z   }|S |d   | j                   d   v r|dd }|S | j                  |«      }t        |«      dk(  r| j                  |«      }|S )z;process length four patterns and extract length three rootsr   r   Nr   r   éÿÿÿÿr   )r   r2   r,   r3   rF   s     r#   r-   zISRIStemmer.pro_w4
  sà   € à�‰7�d—h‘h˜q‘kÑ!Ø˜˜�8ˆDð ˆð �!‰W˜Ÿ™ ™Ñ#Ø˜˜�8˜d 1 2˜hÑ&ˆDð ˆð �!‰W˜Ÿ™ ™Ñ#Ø˜˜�8˜d 1™gÑ%ˆDð ˆð �!‰W˜Ÿ™ ™Ñ#Ø˜˜�9ˆDð
 ˆð —9‘9˜T“?ˆDÜ�4‹y˜AŠ~Ø—y‘y “�Øˆr%   c                 ó\  — |d   | j                   d   v r|d   dk(  r|d   |dd z   }|S |d   | j                   d   v r|d   dk(  r|dd |d   z   }|S |d   | j                   d   v r|d   d	k(  r|dd }|S |d   | j                   d   v r|d   d
k(  r|d   |dd z   }|S |d   | j                   d   v r|d   dk(  r|d   |dd z   }|S |d   | j                   d   v r|d   d	k(  r|dd |d   z   }|S |d   | j                   d   v r|d   dk(  r|dd }|S |d   dk(  r|d   dk(  r|dd |d   z   }|S |d   dk(  r|d   dk(  r|dd }|S |d   dk(  r|d   d
k(  r|dd |d   z   }|S |d   dk(  r|d   dk(  r|d   |d   z   |d   z   }|S |d   dk(  r|d   dk(  r|d   |dd z   }|S |d   dk(  r|d   dk(  r|dd |d   z   }|S |d   d	k(  r|d   dk(  r|d   |dd z   }|S |d   dk(  r|d   dk(  r|dd |d   z   }|S | j                  |«      }t        |«      dk(  r| j                  |«      }|S )z;process length five patterns and extract length three rootsr   r   r   r   r   Nr   r   r   r	   r   r   r
   r   r   u   Ø¦)r   r2   r,   r3   rF   s     r#   r.   zISRIStemmer.pro_w53  s^  € à�‰7�d—i‘i ‘lÑ" t¨A¡w°(Ò':Ø˜‘7˜T ! "˜XÑ%ˆDðB ˆðA �!‰W˜Ÿ	™	 !™Ñ$¨¨a©°HÒ)<Ø˜˜!�9˜t A™wÑ&ˆDð> ˆð= �!‰W˜Ÿ	™	 !™Ñ$¨¨a©°HÒ)<Ø˜˜!�9ˆDð: ˆð9 �!‰W˜Ÿ	™	 !™Ñ$¨¨a©°HÒ)<Ø˜‘7˜T ! "˜XÑ%ˆDð6 ˆð5 �!‰W˜Ÿ	™	 !™Ñ$¨¨a©°HÒ)<Ø˜‘7˜T ! "˜XÑ%ˆDð2 ˆð1 �!‰W˜Ÿ	™	 !™Ñ$¨¨a©°HÒ)<Ø˜˜�8˜d 1™gÑ%ˆDð. ˆð- �!‰W˜Ÿ	™	 !™Ñ$¨¨a©°HÒ)<Ø˜˜�8ˆDð* ˆð) �!‰W˜Ò  T¨!¡W°Ò%8Ø˜˜!�9˜t A™wÑ&ˆDð& ˆð% �!‰W˜Ò  T¨!¡W°Ò%8Ø˜˜�8ˆDð" ˆð! �!‰W˜Ò  T¨!¡W°Ò%8Ø˜˜!�9˜t A™wÑ&ˆDð ˆð �!‰W˜Ò  T¨!¡W°Ò%8Ø˜‘7˜T !™WÑ$ t¨A¡wÑ.ˆDð ˆð �!‰W˜Ò  T¨!¡W°Ò%8Ø˜‘7˜T ! "˜XÑ%ˆDð ˆð �!‰W˜Ò  T¨!¡W°Ò%8Ø˜˜�8˜d 1™gÑ%ˆDð ˆð �!‰W˜Ò  T¨!¡W°Ò%8Ø˜‘7˜T ! A˜YÑ&ˆDð ˆð �!‰W˜Ò  T¨!¡W°Ò%8Ø˜˜�8˜d 1™gÑ%ˆDð
 ˆð —9‘9˜T“?ˆDÜ�4‹y˜AŠ~Ø—y‘y “�Øˆr%   c                 ó€   — |d   | j                   d   v r|dd }|S |d   dk(  r|dd }|S |d   dk(  r|dd |dd z   }|S )	z:process length five patterns and extract length four rootsr   r   r   Nr   r   r   r   )r   rF   s     r#   Úpro_w54zISRIStemmer.pro_w54@  sq   € à�‰7�d—i‘i ‘lÑ"Ø˜˜�8ˆDð
 ˆð	 �!‰W˜Ò Ø˜˜�8ˆDð ˆð �!‰W˜Ò Ø˜˜�8˜d 1 2˜hÑ&ˆDØˆr%   c                 ó†   — t        |«      dk(  r| j                  |«      }|S t        |«      dk(  r| j                  |«      }|S )z!ending step (word of length five)r   r   )r,   r-   rK   rF   s     r#   r/   zISRIStemmer.end_w5J  sB   € äˆt‹9˜Š>Ø—;‘;˜tÓ$ˆDð ˆô �‹Y˜!Š^Ø—<‘< Ó%ˆDØˆr%   c                 óþ  — |j                  d«      s|j                  d«      r|dd }|S |d   dk(  r|d   dk(  r|d   d	k(  r|d
d |d   z   }|S |d   dk(  r#|d   dk(  r|d   dk(  r|d
   |d   z   |d   z   }|S |d   dk(  r |d   dk(  r|d   |d   k(  r|d
   |dd z   }|S |d   dk(  r#|d   dk(  r|d   dk(  r|d
   |d   z   |d   z   }|S | j                  |«      }t        |«      dk(  r| j                  |«      }|S )z:process length six patterns and extract length three rootsu   Ø§Ø³Øªu   Ù…Ø³Øªr   Nr   r   r   r   r   r   r   r   r	   r   r   r   )r<   r2   r,   r3   rF   s     r#   r0   zISRIStemmer.pro_w6R  sk  € à�?‰?Ð/Ô0°D·O±OØ ô5
ð ˜˜�8ˆDð* ˆð' �‰G�xÒ D¨¡G¨xÒ$7¸DÀ¹GÀxÒ<Oà˜˜!�9˜t A™wÑ&ˆDð" ˆð �‰G�xÒ D¨¡G¨xÒ$7¸DÀ¹GÀxÒ<Oà˜‘7˜T !™WÑ$ t¨A¡wÑ.ˆDð ˆð �‰G�xÒ D¨¡G¨xÒ$7¸DÀ¹GÀtÈAÁwÒ<Nà˜‘7˜T ! "˜XÑ%ˆDð ˆð �‰G�xÒ D¨¡G¨xÒ$7¸DÀ¹GÀxÒ<Oà˜‘7˜T !™WÑ$ t¨A¡wÑ.ˆDð
 ˆð —9‘9˜T“?ˆDÜ�4‹y˜AŠ~Ø—y‘y “�Øˆr%   c                 ól   — |d   dk(  r|d   dk(  r|dd |d   z   }|S |j                  d«      r|dd }|S )	z9process length six patterns and extract length four rootsr   r   r   r   r   u   Ù…Øªr   N)r<   rF   s     r#   Úpro_w64zISRIStemmer.pro_w64n  sR   € à�‰7�hÒ 4¨¡7¨hÒ#6Ø˜˜!�9˜t A™wÑ&ˆDð ˆð �_‰_˜^Ô,Ø˜˜�8ˆDØˆr%   c                 ó¨   — t        |«      dk(  r$| j                  |«      }| j                  |«      }|S t        |«      dk(  r| j                  |«      }|S )z ending step (word of length six)r   r   )r,   r.   r/   rO   rF   s     r#   r1   zISRIStemmer.end_w6v  sP   € äˆt‹9˜Š>Ø—<‘< Ó%ˆDØ—;‘;˜tÓ$ˆDð ˆô �‹Y˜!Š^Ø—<‘< Ó%ˆDØˆr%   c                 óX   — | j                   D ]  }|j                  |«      sŒ|dd c S  |S )znormalize short sufixNrH   )r   rB   )r"   r9   Úsf1s      r#   r2   zISRIStemmer.suf1  s4   € à—7‘7ò 	!ˆCØ�}‰}˜SÕ!Ø˜C˜R�yÒ ð	!ð ˆr%   c                 óX   — | j                   D ]  }|j                  |«      sŒ|dd c S  |S )znormalize short prefixr   N)r   r<   )r"   r9   Úsp1s      r#   r3   zISRIStemmer.pre1†  s3   € à—7‘7ò 	 ˆCØ�‰˜sÕ#Ø˜A˜B�x’ð	 ð ˆr%   N)r   )Ú__name__Ú
__module__Ú__qualname__Ú__doc__r$   r5   r(   r)   r*   r+   r-   r.   rK   r/   r0   rO   r1   r2   r3   © r%   r#   r   r   $   sV   „ ñòB
òH#óJò 
ò
òòò $òLòòò8òòór%   r   )rX   r   Únltk.stem.apir   r   rY   r%   r#   ú<module>r[      s    ðñó* 
å "ôg�(õ gr%   