o
    i'                     @   s  d dl Z g dZg dZg dZe jdg ddd Ze jd	ee jdg d
dd Ze jd	ee jdg d
dd Ze jd	ee jddge jdg d
dd Z	e jd	ee jddge jdg d
dd Z
e jd	ee jdg d
dd Ze jd	ee jdg d
dd Ze jddgdd Ze jddgdd Ze jd ee jdg d
d!d" Ze jd ee jd#d$ge jdg d
d%d& Ze jdg d'd(d) Zd*d+ Zd,d- ZdS ).    N)([{*))]}r   ))r   r   )r   r   )r   r   )r   r   text)r   z((<c                 C   s    | |}t |t |ksJ d S )Nlenuk_tokenizerr	   tokens r   V/home/ubuntu/.local/lib/python3.10/site-packages/spacy/tests/lang/uk/test_tokenizer.py$test_uk_tokenizer_handles_only_punct   s   r   punct)u   Приветu   Привітu   Ґелґотатиu   З'єднанняu   Єдністьu   їхніc                 C   sD   | || }t |dksJ |d j|ksJ |d j|ks J d S N   r      r   r	   r   r   r	   r   r   r   r   #test_uk_tokenizer_splits_open_punct      r   c                 C   sD   | || }t |dksJ |d j|ksJ |d j|ks J d S r   r   r   r   r   r   $test_uk_tokenizer_splits_close_punct   r   r   	punct_add`c                 C   sZ   | || | }t |dksJ |d j|ksJ |d j|ks"J |d j|ks+J d S N   r   r   r   r   r   r   r   r	   r   r   r   r   ,test_uk_tokenizer_splits_two_diff_open_punct$   
   r!   'c                 C   sZ   | || | }t |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   -test_uk_tokenizer_splits_two_diff_close_punct1   r"   r$   c                 C   sL   | || | | }t |dksJ |d j|ksJ |d j|ks$J d S )N   r   r   r   r   r   r   r   (test_uk_tokenizer_splits_same_open_punct>      r&   c                 C   sL   | || | | }t |dksJ |d j|ksJ |d j|ks$J d S )Nr%   r   r   r   r   r   r   r   )test_uk_tokenizer_splits_same_close_punctI   r'   r(   u	   'Тестc                 C   s.   | |}t |dksJ |d jdksJ d S )Nr   r   r#   r   r   r   r   r   )test_uk_tokenizer_splits_open_appostropheT   s   r)   u
   Тест''c                 C   s4   | |}t |dksJ | d}t |dksJ d S )Nr   z''r   r   )r   r	   r   tokens_punctr   r   r   )test_uk_tokenizer_splits_double_end_quote[   s   r+   zpunct_open,punct_closec                 C   sZ   | || | }t |dksJ |d j|ksJ |d j|ks"J |d j|ks+J d S r   r   )r   
punct_openpunct_closer	   r   r   r   r   )test_uk_tokenizer_splits_open_close_punctc   s
   r.   zpunct_open2,punct_close2)r   r#   c                 C   s   | || | | | }t |dksJ |d j|ksJ |d j|ks&J |d j|ks/J |d j|ks8J |d j|ksAJ d S )N   r   r   r   r   r%   r   )r   r,   r-   punct_open2punct_close2r	   r   r   r   r    test_uk_tokenizer_two_diff_punctq   s   r2   )u   Привет.u   Привіт.u   Ґелґотати.u   З'єднання.u   Єдність.u	   їхні.c                 C   s   | |}|d j dksJ d S )Nr   .r	   r   r   r   r   %test_uk_tokenizer_splits_trailing_dot   s   r5   c                 C   s*   d}| |}|t |d  jdksJ d S )Nu+   (Раз, два, три, проверка).r   r3   r   r   r   r   r   'test_uk_tokenizer_splits_bracket_period   s   r6   c                 C   s4   d}| |}|d j dksJ |d j dksJ d S )Nu?   Хлібі́в не було́. Хлібі́в не було́.r   u
   було́r   r3   r4   r   r   r   r   *test_uk_tokenizer_handles_final_diacritics   s   r7   )pytest
PUNCT_OPENPUNCT_CLOSEPUNCT_PAIREDmarkparametrizer   r   r   r!   r$   r&   r(   r)   r+   r.   r2   r5   r6   r7   r   r   r   r   <module>   sv    




