
    +gd                         d dl mZmZ d dlmZmZmZmZmZm	Z	m
Z
 d dlZerddlmZ e G d d                      Ze G d d	                      ZdS )
    )	dataclassfield)TYPE_CHECKINGAnyClassVarDictListOptionalUnionN   )FeatureTypec                       e Zd ZU dZee         ed<   dZee         ed<   dZ	e
e         ed<   dZe
e         ed<    ed dd	          Zeed
<   d Zdedeedf         f         fdZdS )Translationa  `FeatureConnector` for translations with fixed languages per example.
    Here for compatiblity with tfds.

    Args:
        languages (`dict`):
            A dictionary for each example mapping string language codes to string translations.

    Example:

    ```python
    >>> # At construction time:
    >>> datasets.features.Translation(languages=['en', 'fr', 'de'])
    >>> # During data generation:
    >>> yield {
    ...         'en': 'the cat',
    ...         'fr': 'le chat',
    ...         'de': 'die katze'
    ... }
    ```
    	languagesNiddictdtypepa_typeFdefaultinitrepr_typec                 b    t          j        d t          | j                  D                       S )Nc                 6    i | ]}|t          j                    S  )pastring).0langs     =lib/python3.11/site-packages/datasets/features/translation.py
<dictcomp>z(Translation.__call__.<locals>.<dictcomp>*   s     OOO$	OOO    )r   structsortedr   selfs    r!   __call__zTranslation.__call__)   s+    yOOt~8N8NOOOPPPr#   returnr   c                 P    ddl m fdt          | j                  D             S )z2Flatten the Translation feature into a dictionary.r   )Valuec                 (    i | ]}| d           S )r   r   )r   kr+   s     r!   r"   z'Translation.flatten.<locals>.<dictcomp>0   s#    CCCq55??CCCr#   )featuresr+   r%   r   )r'   r+   s    @r!   flattenzTranslation.flatten,   s9    ######CCCCF4>,B,BCCCCr#   )__name__
__module____qualname____doc__r	   str__annotations__r   r
   r   r   r   r   r   r   r(   r   r   r/   r   r#   r!   r   r      s          * CyB!E8C=!!!!GXc]!!!}5uEEEE3EEEQ Q QD}d33E.FFG D D D D D Dr#   r   c                       e Zd ZU dZdZee         ed<   dZee	         ed<   dZ
ee         ed<   dZee         ed<   dZee         ed<    ed d	d	
          Zeed<   d Zd Zd Zdedeedf         f         fdZdS )TranslationVariableLanguagesa$  `FeatureConnector` for translations with variable languages per example.
    Here for compatiblity with tfds.

    Args:
        languages (`dict`):
            A dictionary for each example mapping string language codes to one or more string translations.
            The languages present may vary from example to example.

    Returns:
        - `language` or `translation` (variable-length 1D `tf.Tensor` of `tf.string`):
            Language codes sorted in ascending order or plain text translations, sorted to align with language codes.

    Example:

    ```python
    >>> # At construction time:
    >>> datasets.features.TranslationVariableLanguages(languages=['en', 'fr', 'de'])
    >>> # During data generation:
    >>> yield {
    ...         'en': 'the cat',
    ...         'fr': ['le chat', 'la chatte,']
    ...         'de': 'die katze'
    ... }
    >>> # Tensor returned :
    >>> {
    ...         'language': ['en', 'de', 'fr', 'fr'],
    ...         'translation': ['the cat', 'die katze', 'la chatte', 'le chat'],
    ... }
    ```
    Nr   num_languagesr   r   r   r   Fr   r   c                     | j         r!t          t          | j                             nd | _         | j         rt          | j                   nd | _        d S )N)r   r%   setlenr8   r&   s    r!   __post_init__z*TranslationVariableLanguages.__post_init__\   sK    8<PDN 3 3444D48NLS000r#   c                     t          j        t          j        t          j                              t          j        t          j                              d          S )Nlanguagetranslation)r   r$   list_r   r&   s    r!   r(   z%TranslationVariableLanguages.__call__`   s>    ybhry{{&;&;BHUWU^U`U`LaLabbcccr#   c           
          t          | j                  }| j        rkt          |          |z
  rYt          dd                    t	          t          |          |z
                       dd                    |           d          g }|                                D ]S\  }t          |t                    r|                    |f           2|	                    fd|D                        Tt          t	          |           \  }}||dS )NzSome languages in example (z, z) are not in valid set (z).c                     g | ]}|fS r   r   )r   elr    s     r!   
<listcomp>z?TranslationVariableLanguages.encode_example.<locals>.<listcomp>q   s    *E*E*E"D":*E*E*Er#   r>   )r:   r   
ValueErrorjoinr%   items
isinstancer4   appendextendzip)r'   translation_dictlang_settranslation_tuplestextr   translationsr    s          @r!   encode_examplez+TranslationVariableLanguages.encode_examplec   s]   t~&&> 	c"233h> 	 SdiisCS?T?TW_?_8`8`.a.a  S  S{  |E  |E  FN  |O  |O  S  S  S    *0022 	G 	GJD$$$$ G"))4,7777"))*E*E*E*E*E*E*EFFFF #&v.@'A'A"B	<%lCCCr#   r)   r   c                 d    ddl m}m}  | |d                     | |d                    dS )zCFlatten the TranslationVariableLanguages feature into a dictionary.r   )Sequencer+   r   r>   )r.   rT   r+   )r'   rT   r+   s      r!   r/   z$TranslationVariableLanguages.flattenx   sU    -------- !x11#8EE(OO44
 
 	
r#   )r0   r1   r2   r3   r   r
   r	   r5   r8   intr   r4   r   r   r   r   r   r   r<   r(   rR   r   r   r/   r   r#   r!   r7   r7   3   s         > !%Ix~$$$#'M8C='''B!E8C=!!!!GXc]!!!=EPUVVVE3VVVM M Md d dD D D*
}d33E.FFG 
 
 
 
 
 
r#   r7   )dataclassesr   r   typingr   r   r   r   r	   r
   r   pyarrowr   r.   r   r   r7   r   r#   r!   <module>rY      s    ( ( ( ( ( ( ( ( L L L L L L L L L L L L L L L L L L      &%%%%%% $D $D $D $D $D $D $D $DN K
 K
 K
 K
 K
 K
 K
 K
 K
 K
r#   