o
     ¢iÍ  ã                   @   sî  d dl Z g d¢Zg d¢Zg d¢Ze j dg d¢¡dd„ ƒZe j d	e¡e j dd
g¡dd„ ƒƒZe j d	e¡e j dd
g¡dd„ ƒƒZe j d	e¡e j ddg¡e j ddg¡dd„ ƒƒƒZ	e j d	e¡e j ddg¡e j dd
g¡dd„ ƒƒƒZ
e j d	e¡e j dd
g¡dd„ ƒƒZe j d	e¡e j dd
g¡dd„ ƒƒZe j ddg¡dd„ ƒZe j ddg¡dd „ ƒZe j d!e¡e j dd"g¡d#d$„ ƒƒZe j d!e¡e j d%d&g¡e j dd"g¡d'd(„ ƒƒƒZe j dd)g¡d*d+„ ƒZd,d-„ ZdS ).é    N)ú(ú[Ú{Ú*)ú)ú]Ú}r   ))r   r   )r   r   )r   r   )r   r   Útext)r   z((ú<c                 C   s    | |ƒ}t |ƒt |ƒksJ ‚d S )N©Úlen©Úsr_tokenizerr	   Útokens© r   úV/home/ubuntu/.local/lib/python3.10/site-packages/spacy/tests/lang/sr/test_tokenizer.pyÚ$test_sr_tokenizer_handles_only_punct   s   r   Úpunctu   Ð—Ð´Ñ€Ð°Ð²Ð¾c                 C   sD   | || ƒ}t |ƒdksJ ‚|d j|ksJ ‚|d j|ks J ‚d S ©Né   r   é   ©r   r	   ©r   r   r	   r   r   r   r   Ú#test_sr_tokenizer_splits_open_punct   ó   r   c                 C   sD   | || ƒ}t |ƒdksJ ‚|d j|ksJ ‚|d j|ks J ‚d S r   r   r   r   r   r   Ú$test_sr_tokenizer_splits_close_punct   r   r   Ú	punct_addú`u   Ð‹Ð°Ð¾c                 C   sZ   | || | ƒ}t |ƒdksJ ‚|d j|ksJ ‚|d j|ks"J ‚|d j|ks+J ‚d S ©Né   r   r   r   r   ©r   r   r   r	   r   r   r   r   Ú,test_sr_tokenizer_splits_two_diff_open_punct    ó
   r!   ú'c                 C   sZ   | || | ƒ}t |ƒdksJ ‚|d j|ksJ ‚|d j|ks"J ‚|d j|ks+J ‚d S r   r   r    r   r   r   Ú-test_sr_tokenizer_splits_two_diff_close_punct+   r"   r$   c                 C   sL   | || | | ƒ}t |ƒdksJ ‚|d j|ksJ ‚|d j|ks$J ‚d S )Né   r   r   r   r   r   r   r   Ú(test_sr_tokenizer_splits_same_open_punct6   ó   r&   c                 C   sL   | || | | ƒ}t |ƒdksJ ‚|d j|ksJ ‚|d j|ks$J ‚d S )Nr%   r   r   r   r   r   r   r   Ú)test_sr_tokenizer_splits_same_close_punct?   r'   r(   u	   'Ð¢ÐµÑÑ‚c                 C   s.   | |ƒ}t |ƒdksJ ‚|d jdksJ ‚d S )Nr   r   r#   r   r   r   r   r   Ú)test_sr_tokenizer_splits_open_appostropheH   s   r)   u
   Ð¢ÐµÑÑ‚''c                 C   s4   | |ƒ}t |ƒdksJ ‚| dƒ}t |ƒdksJ ‚d S )Nr   z''r   r   )r   r	   r   Útokens_punctr   r   r   Ú)test_sr_tokenizer_splits_double_end_quoteO   s   r+   zpunct_open,punct_closeu   Ð¢ÐµÑÑ‚c                 C   sZ   | || | ƒ}t |ƒdksJ ‚|d j|ksJ ‚|d j|ks"J ‚|d j|ks+J ‚d S r   r   )r   Ú
punct_openÚpunct_closer	   r   r   r   r   Ú)test_sr_tokenizer_splits_open_close_punctW   s
   r.   zpunct_open2,punct_close2)r   r#   c                 C   s†   | || | | | ƒ}t |ƒdksJ ‚|d j|ksJ ‚|d j|ks&J ‚|d j|ks/J ‚|d j|ks8J ‚|d j|ksAJ ‚d S )Né   r   r   r   r   r%   r   )r   r,   r-   Úpunct_open2Úpunct_close2r	   r   r   r   r   Ú test_sr_tokenizer_two_diff_punctc   s   r2   u	   Ð¢ÐµÑÑ‚.c                 C   s   | |ƒ}|d j dksJ ‚d S )Nr   Ú.)r	   r   r   r   r   Ú%test_sr_tokenizer_splits_trailing_dotr   s   r4   c                 C   s*   d}| |ƒ}|t |ƒd  jdksJ ‚d S )Nu7   (ÐˆÐµÐ´Ð°Ð½, Ð´Ð²Ð°, Ñ‚Ñ€Ð¸, Ñ‡ÐµÑ‚Ð¸Ñ€Ð¸, Ð¿Ñ€Ð¾Ð±Ð°).r   r3   r   r   r   r   r   Ú'test_sr_tokenizer_splits_bracket_periodx   s   r5   )ÚpytestÚ
PUNCT_OPENÚPUNCT_CLOSEÚPUNCT_PAIREDÚmarkÚparametrizer   r   r   r!   r$   r&   r(   r)   r+   r.   r2   r4   r5   r   r   r   r   Ú<module>   sP    




