o
    Zh$                     @   s   d Z ddlZddlZddlmZ ddlmZmZmZ ddl	m
Z
 ddlmZmZmZ ddlmZmZ dd	lmZ G d
d deddZeeZG dd deZdgZdS )z
Processor class for Donut.
    N)contextmanager)ListOptionalUnion   )
ImageInput)ProcessingKwargsProcessorMixinUnpack)PreTokenizedInput	TextInput)loggingc                   @   s   e Zd Zi ZdS )DonutProcessorKwargsN)__name__
__module____qualname__	_defaults r   r   Y/var/www/auris/lib/python3.10/site-packages/transformers/models/donut/processing_donut.pyr      s    r   F)totalc                
       s   e Zd ZdZddgZdZdZd fdd	Z				dd	ed
e	e
eee eef  dee fddZdd Zdd Zedd ZdddZedd Zedd Z  ZS )DonutProcessora  
    Constructs a Donut processor which wraps a Donut image processor and an XLMRoBERTa tokenizer into a single
    processor.

    [`DonutProcessor`] offers all the functionalities of [`DonutImageProcessor`] and
    [`XLMRobertaTokenizer`/`XLMRobertaTokenizerFast`]. See the [`~DonutProcessor.__call__`] and
    [`~DonutProcessor.decode`] for more information.

    Args:
        image_processor ([`DonutImageProcessor`], *optional*):
            An instance of [`DonutImageProcessor`]. The image processor is a required input.
        tokenizer ([`XLMRobertaTokenizer`/`XLMRobertaTokenizerFast`], *optional*):
            An instance of [`XLMRobertaTokenizer`/`XLMRobertaTokenizerFast`]. The tokenizer is a required input.
    image_processor	tokenizerZAutoImageProcessorZ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__r   r   r    9   s   

zDonutProcessor.__init__imagestextr$   c           	      K   s   | j r| j||fi |S |du r|du rtd| jtfd| jji|}|dur5| j|fi |d }|durP|durE|d dd | j|fi |d }|du rV|S |du r\|S |d |d	< |d |d< |S )
a  
        When used in normal mode, this method forwards all its arguments to AutoImageProcessor's
        [`~AutoImageProcessor.__call__`] and returns its output. If used in the context
        [`~DonutProcessor.as_target_processor`] this method forwards all its arguments to DonutTokenizer's
        [`~DonutTokenizer.__call__`]. Please refer to the docstring of the above two methods for more information.
        NzBYou need to specify either an `images` or `text` input to process.Ztokenizer_init_kwargsZimages_kwargsZtext_kwargsZadd_special_tokensFZ	input_idslabels)	r"   r!   r   Z_merge_kwargsr   r   Zinit_kwargsr   
setdefault)	r#   r'   r(   ZaudioZvideosr$   Zoutput_kwargsZinputs	encodingsr   r   r   __call__M   s0   zDonutProcessor.__call__c                 O      | j j|i |S )z
        This method forwards all its arguments to DonutTokenizer's [`~PreTrainedTokenizer.batch_decode`]. Please refer
        to the docstring of this method for more information.
        )r   batch_decoder#   argsr$   r   r   r   r.   w      zDonutProcessor.batch_decodec                 O   r-   )z
        This method forwards all its arguments to DonutTokenizer's [`~PreTrainedTokenizer.decode`]. Please refer to the
        docstring of this method for more information.
        )r   decoder/   r   r   r   r2   ~   r1   zDonutProcessor.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_processor   s   
z"DonutProcessor.as_target_processorFc                 C   sD  |du r	| j  }i }|rtd|tj}|du rn|| d }d|vr(n|d|dd  }|tdtd  }t|}td| d|tj}	|	du rZ|	|d}n|	
 }	t|}
t|	}t|
 d| |tjtjB }|dur|
d }d|v rd|v r| j|d|d	}|rt|dkr|d
 }|||< n?g ||< |dD ]%}| }||v r|d
 dkr|dd dkr|dd }|| | qt|| dkr|| d
 ||< |||	t|	 d  }|dd dkr
|g| j|dd d|d	 S |st|r|r|gS |S |rg S d|iS )zS
        Convert a (generated) token sequence into an ordered JSON format.
        Nz<s_>   z</s_ z(.*?)T)is_inner_valueadded_vocabr   z<sep/><z/>   Ztext_sequence)r   Zget_added_vocabresearch
IGNORECASEstartindexlenescapereplacegroupDOTALLstrip
token2jsonsplitappendfind)r#   tokensr8   r9   outputZpotential_startZstart_tokenkeyZkey_escapedZ	end_tokenZstart_token_escapedZend_token_escapedcontentvalueleafr   r   r   rH      s\   



$
,zDonutProcessor.token2jsonc                 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_classr3   r   r   r   feature_extractor_class   
   z&DonutProcessor.feature_extractor_classc                 C   rR   )Nz[`feature_extractor` is deprecated and will be removed in v5. Use `image_processor` instead.)r   r   r   r   r3   r   r   r   r      rU   z DonutProcessor.feature_extractor)NN)NNNN)FN)r   r   r   __doc__
attributesrS   Ztokenizer_classr    r   r   r   strr   r   r   r
   r   r,   r.   r2   r   r4   rH   propertyrT   r   __classcell__r   r   r%   r   r   %   s4    
*

:
r   )rV   r=   r   
contextlibr   typingr   r   r   Zimage_utilsr   Zprocessing_utilsr   r	   r
   Ztokenization_utils_baser   r   utilsr   r   Z
get_loggerr   loggerr   __all__r   r   r   r   <module>   s   
 
<