o
    hq                     @   s8   d Z ddlZddlmZ ddlmZ G dd deZdS )z
Processor class for TrOCR.
    N)contextmanager   )ProcessorMixinc                       sn   e Zd ZdZddgZdZdZd fdd	Zd	d
 Zdd Z	dd Z
edd Zedd Zedd Z  ZS )TrOCRProcessora  
    Constructs a TrOCR processor which wraps a vision image processor and a TrOCR tokenizer into a single processor.

    [`TrOCRProcessor`] offers all the functionalities of [`ViTImageProcessor`/`DeiTImageProcessor`] and
    [`RobertaTokenizer`/`XLMRobertaTokenizer`]. See the [`~TrOCRProcessor.__call__`] and [`~TrOCRProcessor.decode`] for
    more information.

    Args:
        image_processor ([`ViTImageProcessor`/`DeiTImageProcessor`], *optional*):
            An instance of [`ViTImageProcessor`/`DeiTImageProcessor`]. The image processor is a required input.
        tokenizer ([`RobertaTokenizer`/`XLMRobertaTokenizer`], *optional*):
            An instance of [`RobertaTokenizer`/`XLMRobertaTokenizer`]. The tokenizer is a required input.
    image_processor	tokenizerAutoImageProcessorAutoTokenizerNc                    sr   d }d|v rt dt |d}|d ur|n|}|d u r!td|d u r)tdt || | j| _d| _	d S )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`.F)
warningswarnFutureWarningpop
ValueErrorsuper__init__r   current_processor_in_target_context_manager)selfr   r   kwargsr
   	__class__ `/var/www/html/ai/venv/lib/python3.10/site-packages/transformers/models/trocr/processing_trocr.pyr   +   s   

zTrOCRProcessor.__init__c                 O   s   | j r| j|i |S |dd}|dd}t|dkr'|d }|dd }|du r3|du r3td|durC| j|g|R i |}|durP| j|fi |}|du rV|S |du r\|S |d |d< |S )	a  
        When used in normal mode, this method forwards all its arguments to AutoImageProcessor's
        [`~AutoImageProcessor.__call__`] and returns its output. If used in the context
        [`~TrOCRProcessor.as_target_processor`] this method forwards all its arguments to TrOCRTokenizer's
        [`~TrOCRTokenizer.__call__`]. Please refer to the doctsring of the above two methods for more information.
        imagesNtextr      zBYou need to specify either an `images` or `text` input to process.	input_idslabels)r   r   r   lenr   r   r   )r   argsr   r   r   inputs	encodingsr   r   r   __call__?   s&   zTrOCRProcessor.__call__c                 O      | j j|i |S )z
        This method forwards all its arguments to TrOCRTokenizer's [`~PreTrainedTokenizer.batch_decode`]. Please refer
        to the docstring of this method for more information.
        )r   batch_decoder   r    r   r   r   r   r%   `      zTrOCRProcessor.batch_decodec                 O   r$   )z
        This method forwards all its arguments to TrOCRTokenizer's [`~PreTrainedTokenizer.decode`]. Please refer to the
        docstring of this method for more information.
        )r   decoder&   r   r   r   r(   g   r'   zTrOCRProcessor.decodec                 c   s2    t d d| _| j| _dV  | j| _d| _dS )z
        Temporarily sets the tokenizer for processing the input. Useful for encoding the labels when fine-tuning TrOCR.
        z`as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your images inputs, or in a separate call.TNF)r   r   r   r   r   r   r   r   r   r   as_target_processorn   s   
z"TrOCRProcessor.as_target_processorc                 C      t 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_classr)   r   r   r   feature_extractor_class~   
   z&TrOCRProcessor.feature_extractor_classc                 C   r+   )Nz[`feature_extractor` is deprecated and will be removed in v5. Use `image_processor` instead.)r   r   r   r   r)   r   r   r   r
      r.   z TrOCRProcessor.feature_extractor)NN)__name__
__module____qualname____doc__
attributesr,   tokenizer_classr   r#   r%   r(   r   r*   propertyr-   r
   __classcell__r   r   r   r   r      s    !

r   )r2   r   
contextlibr   processing_utilsr   r   r   r   r   r   <module>   s
   