
    iu                         d dl Z d dlmZ d dlmZ d dlmZmZ ddlm	Z	 e j                  d        Ze j                  d        Zd	 Zd
 Zd Zd Ze j"                  j%                  d      d        Zy)    N)Language)merge_subtokens)DocSpan   )clean_underscorec                 8    g d}g d}g d}t        | |||      S )N)Thisisasentence.r
   r   anotherr   r   Andr   thirdr   )   r      r   r      r      r   r            r   )nsubjROOTsubtokattrpunctr   r   r   r   r   r   r   r   r   )wordsheadsdeps)r   )en_vocabr   r   r    s       t/var/www/vps2.regionflexible.com/Desarrollo/venv/lib/python3.12/site-packages/spacy/tests/pipeline/test_functions.pydocr#   
   s*     uE:EMD xuE==    c                 z    g d}g d}g d}g d}g d}t        | |||||      }t        |ddd	
      g|_        |S )N)IlikeNewYorkinAutumnr   )r   r   r   r   r      r   )PRPINNNPr/   r.   r/   r   )PRONVERBPROPNr2   ADPr2   PUNCT)r   prepcompoundpobjr5   r7   r   )r   r   tagsposr    r   r,   GPE)label)r   r   ents)r!   r   r   r8   r9   r    r#   s          r"   doc2r=      sI    =E!E8D
ECHD
he5t4
PCS!Qe,-CHJr$   c                 f    t        |       } | D cg c]  }|j                   c}g dk(  sJ y c c}w )N)	r
   r   z
a sentencer   r
   r   zanother sentencer   zAnd a third .)r   text)r#   ts     r"   test_merge_subtokensrA   !   s/    
#
C   qAFF $}}}} s   .c                     t        |       dk(  sJ t               }|j                  d      } ||        t        |       dk(  sJ | d   j                  dk(  sJ y )N   merge_noun_chunksr   r   New York)lenr   create_piper?   )r=   nlprD   s      r"    test_factories_merge_noun_chunksrI   )   sW    t9>>
*C(;<dt9>>7<<:%%%r$   c                 >   t        |       dk(  sJ t        t        | j                              dk(  sJ t               }|j	                  d      } ||        t        |       dk(  sJ t        t        | j                              dk(  sJ | d   j
                  dk(  sJ y )NrC   r   merge_entitiesr   r   rE   )rF   listr<   r   rG   r?   )r=   rH   rK   s      r"   test_factories_merge_entsrM   2   s    t9>>tDII1$$$
*C__%56N4t9>>tDII1$$$7<<:%%%r$   c                  .   t               } ddd}| j                  d|       | d      }|D cg c]  }|j                   c}g dk(  sJ  | d      }|D cg c]  }|j                   c}g d	k(  sJ t        fd
|D              sJ y c c}w c c}w )N      )
min_lengthsplit_lengthtoken_splitterconfigzaaaaabbbbbcccccdddd e f g)aaaaabbbbbcccccddddefgz!aaaaabbbbbcccccdddddeeeeeff g h i)	aaaaabbbbbcccccdddddeeeeeffrY   hic              3   b   K   | ]&  }t        |j                        j                  k   ( y w)N)rF   r?   rR   ).0r@   rS   s     r"   	<genexpr>z&test_token_splitter.<locals>.<genexpr>O   s$     Gas166{n999Gs   ,/)r   add_piper?   all)rH   rU   r#   r@   rS   s       @r"   test_token_splitterrg   =   s    
*C2F\\"26\BN
)
*C qAFF $JJJJ
1
2C qAFF  
% 
 
 
 G3GGGG ! s   BBr   c                  >   t               } | j                  d       | j                  d      }g d|_         | |      }|j                  J t               } | j                  dddi       t	        j
                  t              5   | d      }d d d        t        j                  dd	       t               } | j                  dd
ddii       | j                  d      }d|j                  _
         | |      }|j                  j                  dk(  sJ y # 1 sw Y   xY w)Ndoc_cleanerr?   )r   r   r   silentFrT   	test_attr)defaultattrsz_.test_attrr   d   )r   re   make_doctensorpytestwarnsUserWarningr   set_extension_rk   )rH   r#   s     r"   test_factories_doc_cleanerrw   R   s    
*CLL
,,v
CCJ
c(C::
*CLL%'8L9	k	" &k k2.
*CLL-1C'DLE
,,v
CCEEO
c(C55??a s   	DD)rr   spacy.languager   spacy.pipeline.functionsr   spacy.tokensr   r   doc.test_underscorer   fixturer#   r=   rA   rI   rM   rg   markusefixturesrw    r$   r"   <module>r      s~     # 4 " 2 > >  ~&&H* +,  - r$   