
    sg4                     R   d Z ddlmZmZmZ ddlZddlmZm	Z	m
Z
 ddlmZmZmZmZ ddlmZmZmZmZmZmZmZmZ ddlmZmZmZmZmZmZ  e       rddl Z  e       rddl!Z! ejD                  e#      Z$d	 Z%	 	 dd
ejL                  dee'   dee'   deee'ef      fdZ( G d de      Z)y)z%Image processor class for LayoutLMv2.    )DictOptionalUnionN   )BaseImageProcessorBatchFeatureget_size_dict)flip_channel_orderresizeto_channel_dimension_formatto_pil_image)ChannelDimension
ImageInputPILImageResamplinginfer_channel_dimension_formatmake_list_of_imagesto_numpy_arrayvalid_imagesvalidate_preprocess_arguments)
TensorTypefilter_out_non_signature_kwargsis_pytesseract_availableis_vision_availableloggingrequires_backendsc                     t        d| d   |z  z        t        d| d   |z  z        t        d| d   |z  z        t        d| d   |z  z        gS )Ni  r         r   )int)boxwidthheights      m/var/www/html/venv/lib/python3.12/site-packages/transformers/models/layoutlmv2/image_processing_layoutlmv2.pynormalize_boxr$   5   s`    DCFUN#$DCFVO$%DCFUN#$DCFVO$%	     imagelangtesseract_configinput_data_formatc                    ||nd}t        | |      }|j                  \  }}t        j                  ||d|      }|d   |d   |d   |d   |d	   f\  }}	}
}}t	        |      D cg c]  \  }}|j                         r| }}}t	        |      D cg c]  \  }}||vs| }}}t	        |	      D cg c]  \  }}||vs| }	}}t	        |
      D cg c]  \  }}||vs| }
}}t	        |      D cg c]  \  }}||vs| }}}t	        |      D cg c]  \  }}||vs| }}}g }t        |	|
||      D ]$  \  }}}}||||z   ||z   g}|j                  |       & g }|D ]  }|j                  t        |||               t        |      t        |      k(  sJ d
       ||fS c c}}w c c}}w c c}}w c c}}w c c}}w c c}}w )zdApplies Tesseract OCR on a document image, and returns recognized words + normalized bounding boxes. r)   dict)r'   output_typeconfigtextlefttopr!   r"   z-Not as many words as there are bounding boxes)
r   sizepytesseractimage_to_data	enumeratestripzipappendr$   len)r&   r'   r(   r)   	pil_imageimage_widthimage_heightdatawordsr1   r2   r!   r"   idxwordirrelevant_indicescoordactual_boxesxywh
actual_boxnormalized_boxesr    s                            r#   apply_tesseractrK   >   s    ,<+G'R U6GHI )K$$YTvVfgD&*6lDL$u+tT[}^bck^l&l#E4eV 09/?T)#ttzz|#TT#,U#3Uic4sBT7TTUEU$-dOUjc5sBT7TEUDU#,S>
SZS%S@R5R5
SC
S%.u%5WzsEDV9VUWEW&/&7Y
U3FX;XeYFY L$UF3 (
1aAE1q5)
J'(
  Oc; MNO u:-.._0__.""") UUU
SWYsH   &F.?F.F4!F46F:F:G %G :GGG)Gc                       e Zd ZdZdgZddej                  dddfdedee	e
f   ded	ed
ee	   dee	   ddf fdZej                  ddfdej                  dee	e
f   dedeee	ef      deee	ef      dej                  fdZ e       dddddddej&                  df	dededee	e
f   ded	ed
ee	   dee	   deee	ef      dedeee	ef      dej.                  j.                  fd       Z xZS )LayoutLMv2ImageProcessora  
    Constructs a LayoutLMv2 image processor.

    Args:
        do_resize (`bool`, *optional*, defaults to `True`):
            Whether to resize the image's (height, width) dimensions to `(size["height"], size["width"])`. Can be
            overridden by `do_resize` in `preprocess`.
        size (`Dict[str, int]` *optional*, defaults to `{"height": 224, "width": 224}`):
            Size of the image after resizing. Can be overridden by `size` in `preprocess`.
        resample (`PILImageResampling`, *optional*, defaults to `Resampling.BILINEAR`):
            Resampling filter to use if resizing the image. Can be overridden by the `resample` parameter in the
            `preprocess` method.
        apply_ocr (`bool`, *optional*, defaults to `True`):
            Whether to apply the Tesseract OCR engine to get words + normalized bounding boxes. Can be overridden by
            `apply_ocr` in `preprocess`.
        ocr_lang (`str`, *optional*):
            The language, specified by its ISO code, to be used by the Tesseract OCR engine. By default, English is
            used. Can be overridden by `ocr_lang` in `preprocess`.
        tesseract_config (`str`, *optional*, defaults to `""`):
            Any additional custom configuration flags that are forwarded to the `config` parameter when calling
            Tesseract. For example: '--psm 6'. Can be overridden by `tesseract_config` in `preprocess`.
    pixel_valuesTNr+   	do_resizer3   resample	apply_ocrocr_langr(   returnc                     t        |   di | ||nddd}t        |      }|| _        || _        || _        || _        || _        || _        y )N   )r"   r!    )	super__init__r	   rO   r3   rP   rQ   rR   r(   )	selfrO   r3   rP   rQ   rR   r(   kwargs	__class__s	           r#   rX   z!LayoutLMv2ImageProcessor.__init__   s[     	"6"'tc-JT""	 "  0r%   r&   data_formatr)   c                     t        |      }d|vsd|vrt        d|j                                |d   |d   f}t        |f||||d|S )a  
        Resize an image to `(size["height"], size["width"])`.

        Args:
            image (`np.ndarray`):
                Image to resize.
            size (`Dict[str, int]`):
                Dictionary in the format `{"height": int, "width": int}` specifying the size of the output image.
            resample (`PILImageResampling`, *optional*, defaults to `PILImageResampling.BILINEAR`):
                `PILImageResampling` filter to use when resizing the image e.g. `PILImageResampling.BILINEAR`.
            data_format (`ChannelDimension` or `str`, *optional*):
                The channel dimension format for the output image. If unset, the channel dimension format of the input
                image is used. Can be one of:
                - `"channels_first"` or `ChannelDimension.FIRST`: image in (num_channels, height, width) format.
                - `"channels_last"` or `ChannelDimension.LAST`: image in (height, width, num_channels) format.
                - `"none"` or `ChannelDimension.NONE`: image in (height, width) format.
            input_data_format (`ChannelDimension` or `str`, *optional*):
                The channel dimension format for the input image. If unset, the channel dimension format is inferred
                from the input image. Can be one of:
                - `"channels_first"` or `ChannelDimension.FIRST`: image in (num_channels, height, width) format.
                - `"channels_last"` or `ChannelDimension.LAST`: image in (height, width, num_channels) format.
                - `"none"` or `ChannelDimension.NONE`: image in (height, width) format.

        Returns:
            `np.ndarray`: The resized image.
        r"   r!   zFThe `size` dictionary must contain the keys `height` and `width`. Got )r3   rP   r\   r)   )r	   
ValueErrorkeysr   )rY   r&   r3   rP   r\   r)   rZ   output_sizes           r#   r   zLayoutLMv2ImageProcessor.resize   sy    F T"47$#6efjfofofqersttH~tG}5
#/
 
 	
r%   imagesreturn_tensorsc           	      4   ||n| j                   }||n| j                  }t        |      }||n| j                  }||n| j                  }||n| j
                  }||n| j                  }t        |      }t        |      st        d      t        |||       |D cg c]  }t        |       }}|
t        |d         }
|rKt        | d       g }g }|D ]6  }t        ||||
      \  }}|j                  |       |j                  |       8 |r"|D cg c]  }| j!                  ||||
       }}|D cg c]  }t#        ||
       }}|D cg c]  }t%        ||	|
       }}t'        d|i|	      }|r
|d
<   |d<   |S c c}w c c}w c c}w c c}w )a  
        Preprocess an image or batch of images.

        Args:
            images (`ImageInput`):
                Image to preprocess.
            do_resize (`bool`, *optional*, defaults to `self.do_resize`):
                Whether to resize the image.
            size (`Dict[str, int]`, *optional*, defaults to `self.size`):
                Desired size of the output image after resizing.
            resample (`PILImageResampling`, *optional*, defaults to `self.resample`):
                Resampling filter to use if resizing the image. This can be one of the enum `PIL.Image` resampling
                filter. Only has an effect if `do_resize` is set to `True`.
            apply_ocr (`bool`, *optional*, defaults to `self.apply_ocr`):
                Whether to apply the Tesseract OCR engine to get words + normalized bounding boxes.
            ocr_lang (`str`, *optional*, defaults to `self.ocr_lang`):
                The language, specified by its ISO code, to be used by the Tesseract OCR engine. By default, English is
                used.
            tesseract_config (`str`, *optional*, defaults to `self.tesseract_config`):
                Any additional custom configuration flags that are forwarded to the `config` parameter when calling
                Tesseract.
            return_tensors (`str` or `TensorType`, *optional*):
                The type of tensors to return. Can be one of:
                    - Unset: Return a list of `np.ndarray`.
                    - `TensorType.TENSORFLOW` or `'tf'`: Return a batch of type `tf.Tensor`.
                    - `TensorType.PYTORCH` or `'pt'`: Return a batch of type `torch.Tensor`.
                    - `TensorType.NUMPY` or `'np'`: Return a batch of type `np.ndarray`.
                    - `TensorType.JAX` or `'jax'`: Return a batch of type `jax.numpy.ndarray`.
            data_format (`ChannelDimension` or `str`, *optional*, defaults to `ChannelDimension.FIRST`):
                The channel dimension format for the output image. Can be one of:
                    - `ChannelDimension.FIRST`: image in (num_channels, height, width) format.
                    - `ChannelDimension.LAST`: image in (height, width, num_channels) format.
        zkInvalid image type. Must be of type PIL.Image.Image, numpy.ndarray, torch.Tensor, tf.Tensor or jax.ndarray.)rO   r3   rP   r   r4   r,   )r&   r3   rP   r)   )input_channel_dimrN   )r>   tensor_typer?   boxes)rO   r3   r	   rP   rQ   rR   r(   r   r   r^   r   r   r   r   rK   r9   r   r
   r   r   )rY   ra   rO   r3   rP   rQ   rR   r(   rb   r\   r)   r&   words_batchboxes_batchr?   rf   r>   s                    r#   
preprocessz#LayoutLMv2ImageProcessor.preprocess   s   ^ "+!6IDNN	'tTYYT"'38!*!6IDNN	'38/?/K+QUQfQf$V,F#:  	&	
 6<<E.'<<$ >vay IdM2KK *.uh@Pduvu""5)""5)*
  $ %dXYjkF  _eeUZ$U>OPeent
ej'{N_`
 
 .&!9~V'DM'DMA =  f
s   FF8FF)__name__
__module____qualname____doc__model_input_namesr   BILINEARboolr   strr   r   rX   npndarrayr   r   r   r   FIRSTr   r   PILImageri   __classcell__)r[   s   @r#   rM   rM   e   s   . (( #'9'B'B"&*,11 38n1 %	1
 1 3-1 #3-1 
14 (:'B'B>BDH.
zz.
 38n.
 %	.

 eC)9$9:;.
 $E#/?*?$@A.
 
.
` %& #'+"&*.;?(8(>(>DHdd d 38n	d
 %d d 3-d #3-d !sJ!78d &d $E#/?*?$@Ad 
d 'dr%   rM   )NN)*rm   typingr   r   r   numpyrr   image_processing_utilsr   r   r	   image_transformsr
   r   r   r   image_utilsr   r   r   r   r   r   r   r   utilsr   r   r   r   r   r   ru   r4   
get_loggerrj   loggerr$   rs   rq   rK   rM   rV   r%   r#   <module>r      s    , ( (  U U e e	 	 	   			H	% '+@D	$#::$#
3-$# sm$#  c+;&; <=	$#NE1 Er%   