
    sg                     >    d Z ddlZddlmZ ddlmZ  G d de      Zy)z%
Image/Text processor class for CLIP
    N   )ProcessorMixin)BatchEncodingc                   x     e Zd ZdZddgZdZdZd fd	ZddZd Z	d	 Z
ed
        Zed        Zed        Z xZS )CLIPProcessora!  
    Constructs a CLIP processor which wraps a CLIP image processor and a CLIP tokenizer into a single processor.

    [`CLIPProcessor`] offers all the functionalities of [`CLIPImageProcessor`] and [`CLIPTokenizerFast`]. See the
    [`~CLIPProcessor.__call__`] and [`~CLIPProcessor.decode`] for more information.

    Args:
        image_processor ([`CLIPImageProcessor`], *optional*):
            The image processor is a required input.
        tokenizer ([`CLIPTokenizerFast`], *optional*):
            The tokenizer is a required input.
    image_processor	tokenizerCLIPImageProcessor)CLIPTokenizerCLIPTokenizerFastc                     d }d|v r+t        j                  dt               |j                  d      }||n|}|t	        d      |t	        d      t
        |   ||       y )Nfeature_extractorzhThe `feature_extractor` argument is deprecated and will be removed in v5, use `image_processor` instead.z)You need to specify an `image_processor`.z"You need to specify a `tokenizer`.)warningswarnFutureWarningpop
ValueErrorsuper__init__)selfr   r	   kwargsr   	__class__s        [/var/www/html/venv/lib/python3.12/site-packages/transformers/models/clip/processing_clip.pyr   zCLIPProcessor.__init__+   sw     &(MM
 !'

+> ?-<-H/N_"HIIABB)4    c                    i i }}|rx|j                         D ci c]!  \  }}|| j                  j                  vs||# }}}|j                         D ci c]!  \  }}|| j                  j                  v s||# }}}||t        d      | | j                  |fd|i|}	| | j                  |fd|i|}
||
j
                  	d<   |	S |	S t        t        di 
|      S c c}}w c c}}w )a  
        Main method to prepare for the model one or several sequences(s) and image(s). This method forwards the `text`
        and `kwargs` arguments to CLIPTokenizerFast's [`~CLIPTokenizerFast.__call__`] if `text` is not `None` to encode
        the text. To prepare the image(s), this method forwards the `images` and `kwrags` arguments to
        CLIPImageProcessor's [`~CLIPImageProcessor.__call__`] if `images` is not `None`. Please refer to the doctsring
        of the above two methods for more information.

        Args:
            text (`str`, `List[str]`, `List[List[str]]`):
                The sequence or batch of sequences to be encoded. Each sequence can be a string or a list of strings
                (pretokenized string). If the sequences are provided as list of strings (pretokenized), you must set
                `is_split_into_words=True` (to lift the ambiguity with a batch of sequences).
            images (`PIL.Image.Image`, `np.ndarray`, `torch.Tensor`, `List[PIL.Image.Image]`, `List[np.ndarray]`, `List[torch.Tensor]`):
                The image or batch of images to be prepared. Each image can be a PIL image, NumPy array or PyTorch
                tensor. Both channels-first and channels-last formats are supported.

            return_tensors (`str` or [`~utils.TensorType`], *optional*):
                If set, will return tensors of a particular framework. Acceptable values are:

                - `'tf'`: Return TensorFlow `tf.constant` objects.
                - `'pt'`: Return PyTorch `torch.Tensor` objects.
                - `'np'`: Return NumPy `np.ndarray` objects.
                - `'jax'`: Return JAX `jnp.ndarray` objects.

        Returns:
            [`BatchEncoding`]: A [`BatchEncoding`] with the following fields:

            - **input_ids** -- List of token ids to be fed to a model. Returned when `text` is not `None`.
            - **attention_mask** -- List of indices specifying which tokens should be attended to by the model (when
              `return_attention_mask=True` or if *"attention_mask"* is in `self.model_input_names` and if `text` is not
              `None`).
            - **pixel_values** -- Pixel values to be fed to a model. Returned when `images` is not `None`.
        z?You have to specify either text or images. Both cannot be none.return_tensorspixel_values)datatensor_type )itemsr   _valid_processor_keysr   r	   r   r   dict)r   textimagesr   r   tokenizer_kwargsimage_processor_kwargskvencodingimage_featuress              r   __call__zCLIPProcessor.__call__=   s*   D 46r017wA1DL`L`LvLvCv1ww!'&A18L8L8b8b3b1&" & <FN^__%t~~d^>^M]^H1T11&rr[qrN 2'5'B'BH^$OO d&<^&<.YY)  x&s    C+C+ C17C1c                 :     | j                   j                  |i |S )z
        This method forwards all its arguments to CLIPTokenizerFast's [`~PreTrainedTokenizer.batch_decode`]. Please
        refer to the docstring of this method for more information.
        )r	   batch_decoder   argsr   s      r   r.   zCLIPProcessor.batch_decodew   s     
 +t~~**D;F;;r   c                 :     | j                   j                  |i |S )z
        This method forwards all its arguments to CLIPTokenizerFast's [`~PreTrainedTokenizer.decode`]. Please refer to
        the docstring of this method for more information.
        )r	   decoder/   s      r   r2   zCLIPProcessor.decode~   s     
 %t~~$$d5f55r   c                     | j                   j                  }| j                  j                  }t        t        j                  ||z               S )N)r	   model_input_namesr   listr#   fromkeys)r   tokenizer_input_namesimage_processor_input_namess      r   r4   zCLIPProcessor.model_input_names   s?     $ @ @&*&:&:&L&L#DMM"7:U"UVWWr   c                 N    t        j                  dt               | j                  S )Nzg`feature_extractor_class` is deprecated and will be removed in v5. Use `image_processor_class` instead.)r   r   r   image_processor_classr   s    r   feature_extractor_classz%CLIPProcessor.feature_extractor_class   s"    u	
 )))r   c                 N    t        j                  dt               | j                  S )Nz[`feature_extractor` is deprecated and will be removed in v5. Use `image_processor` instead.)r   r   r   r   r;   s    r   r   zCLIPProcessor.feature_extractor   s"    i	
 ###r   )NN)NNN)__name__
__module____qualname____doc__
attributesr:   tokenizer_classr   r,   r.   r2   propertyr4   r<   r   __classcell__)r   s   @r   r   r      ss     $[1J0<O5$8Zt<6 X X
 * * $ $r   r   )rA   r   processing_utilsr   tokenization_utils_baser   r   r    r   r   <module>rH      s#     . 4@$N @$r   