
     `i?!                     x    d Z ddlZddlmZmZ ddlmZ ddlmZm	Z	m
Z
mZmZ ddlmZ  G d d	e          Zd	gZdS )
z!
Processor class for LayoutLMv2.
    N)OptionalUnion   )ProcessorMixin)BatchEncodingPaddingStrategyPreTokenizedInput	TextInputTruncationStrategy)
TensorTypec            (       R    e Zd ZdZddgZdZdZd# fd	Z	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 d$dee	e
ee	         ee
         f         deee
ee
         f                  deeeee                  eeee                           f                  deeee         eee                  f                  dedeeeef         deeeef         dee         dedee         dee         dee         dedededededeeeef                  def&dZd Zed              Zed!             Zed"             Z xZS )%LayoutLMv2Processorax  
    Constructs a LayoutLMv2 processor which combines a LayoutLMv2 image processor and a LayoutLMv2 tokenizer into a
    single processor.

    [`LayoutLMv2Processor`] offers all the functionalities you need to prepare data for the model.

    It first uses [`LayoutLMv2ImageProcessor`] to resize document images to a fixed size, and optionally applies OCR to
    get words and normalized bounding boxes. These are then provided to [`LayoutLMv2Tokenizer`] or
    [`LayoutLMv2TokenizerFast`], which turns the words and bounding boxes into token-level `input_ids`,
    `attention_mask`, `token_type_ids`, `bbox`. Optionally, one can provide integer `word_labels`, which are turned
    into token-level `labels` for token classification tasks (such as FUNSD, CORD).

    Args:
        image_processor (`LayoutLMv2ImageProcessor`, *optional*):
            An instance of [`LayoutLMv2ImageProcessor`]. The image processor is a required input.
        tokenizer (`LayoutLMv2Tokenizer` or `LayoutLMv2TokenizerFast`, *optional*):
            An instance of [`LayoutLMv2Tokenizer`] or [`LayoutLMv2TokenizerFast`]. The tokenizer is a required input.
    image_processor	tokenizerLayoutLMv2ImageProcessor)LayoutLMv2TokenizerLayoutLMv2TokenizerFastNc                     d }d|v r/t          j        dt                     |                    d          }||n|}t	                                          ||           d S )Nfeature_extractorzhThe `feature_extractor` argument is deprecated and will be removed in v5, use `image_processor` instead.)warningswarnFutureWarningpopsuper__init__)selfr   r   kwargsr   	__class__s        /home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/transformers/models/layoutlmv2/processing_layoutlmv2.pyr   zLayoutLMv2Processor.__init__3   st     &((M  
 !'

+> ? ?-<-H//N_)44444    TFr   text	text_pairboxesword_labelsadd_special_tokenspadding
truncation
max_lengthstridepad_to_multiple_ofreturn_token_type_idsreturn_attention_maskreturn_overflowing_tokensreturn_special_tokens_maskreturn_offsets_mappingreturn_lengthverbosereturn_tensorsreturnc                 `   | j         j        r|t          d          | j         j        r|t          d          |du r|du rt          d          |                      ||          }|.| j         j        r"| t          |t                    r|g}|d         } | j        di d	||n|d         d
||ndd||n|d         d|d|d|d|d|	d|
d|d|d|d|d|d|d|d|d||}|                    d          }|du r|                     ||d                   }||d<   |S )a  
        This method first forwards the `images` argument to [`~LayoutLMv2ImageProcessor.__call__`]. In case
        [`LayoutLMv2ImageProcessor`] was initialized with `apply_ocr` set to `True`, it passes the obtained words and
        bounding boxes along with the additional arguments to [`~LayoutLMv2Tokenizer.__call__`] and returns the output,
        together with resized `images`. In case [`LayoutLMv2ImageProcessor`] was initialized with `apply_ocr` set to
        `False`, it passes the words (`text`/``text_pair`) and `boxes` specified by the user along with the additional
        arguments to [`~LayoutLMv2Tokenizer.__call__`] and returns the output, together with resized `images``.

        Please refer to the docstring of the above two methods for more information.
        NzdYou cannot provide bounding boxes if you initialized the image processor with apply_ocr set to True.zaYou cannot provide word labels if you initialized the image processor with apply_ocr set to True.TFzKYou cannot return overflowing tokens without returning the offsets mapping.)imagesr2   wordsr!   r"   r#   r$   r%   r&   r'   r(   r)   r*   r+   r,   r-   r.   r/   r0   r1   r2   pixel_valuesoverflow_to_sample_mappingimage )r   	apply_ocr
ValueError
isinstancestrr   r   get_overflowing_images)r   r5   r!   r"   r#   r$   r%   r&   r'   r(   r)   r*   r+   r,   r-   r.   r/   r0   r1   r2   r   featuresencoded_inputss                          r   __call__zLayoutLMv2Processor.__call__A   s;   D ) 	u/@v   ) 	{/Fs   %,,1G51P1Pjkkk ''vn'UU  4 >9CT$$$ v )I' 
 
 
)x/@
#,#8iid
 !,%%(72C
 $	

  21
 G
 "z
 "z
 6
  21
 #8"7
 #8"7
 '@&?
 (B'A
 $:#9
  (-!
" G#
$ *>'
 
. n--$,,00Hd9effF"(wr    c                     g }|D ]}|                     ||                    t          |          t          |          k    r/t          dt          |           dt          |                     |S )Nz`Expected length of images to be the same as the length of `overflow_to_sample_mapping`, but got z and )appendlenr<   )r   r5   r8   images_with_overflow
sample_idxs        r   r?   z*LayoutLMv2Processor.get_overflowing_images   s    !4 	< 	<J ''z(:;;;;#$$,F(G(GGGV,--V V478R4S4SV V  
 $#r    c                 
    g dS )N)	input_idsbboxtoken_type_idsattention_maskr9   r:   r   s    r   model_input_namesz%LayoutLMv2Processor.model_input_names   s    QQQQr    c                 D    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_classrM   s    r   feature_extractor_classz+LayoutLMv2Processor.feature_extractor_class   s'    u	
 	
 	
 ))r    c                 D    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   rM   s    r   r   z%LayoutLMv2Processor.feature_extractor   s'    i	
 	
 	
 ##r    )NN)NNNNTFFNr   NNNFFFFTN)__name__
__module____qualname____doc__
attributesrP   tokenizer_classr   r   r
   r	   listr   intboolr>   r   r   r   r   rB   r?   propertyrN   rQ   r   __classcell__)r   s   @r   r   r      s        & $[1J6HO5 5 5 5 5 5" _cQUIMCG#'5:;@$(,00404*/+0',#;?)T T I0$y/4HYCZZ[T E"3T:K5L"LMN	T
 d49otDcO/DDEFT eDItDI$>?@T !T tS/12T $%778T SMT T %SMT  (~T  (~T $(T  %)!T" !%#T$ %T& 'T( !sJ!78)T, 
-T T T Tl$ $ $ R R XR * * X* $ $ X$ $ $ $ $r    r   )rV   r   typingr   r   processing_utilsr   tokenization_utils_baser   r   r	   r
   r   utilsr   r   __all__r:   r    r   <module>rc      s      " " " " " " " " . . . . . . w w w w w w w w w w w w w w      \$ \$ \$ \$ \$. \$ \$ \$~ !
!r    