
    sgG                     \   d Z ddlmZ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 ddlmZmZmZ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!jJ                  e&      Z'd	 Z(	 dd
ejR                  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 LayoutLMv3.    )DictIterableOptionalUnionN   )BaseImageProcessorBatchFeatureget_size_dict)resizeto_channel_dimension_formatto_pil_image)IMAGENET_STANDARD_MEANIMAGENET_STANDARD_STDChannelDimension
ImageInputPILImageResamplinginfer_channel_dimension_formatis_scaled_image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/layoutlmv3/image_processing_layoutlmv3.pynormalize_boxr'   8   s`    DCFUN#$DCFVO$%DCFUN#$DCFVO$%	     imagelangtesseract_configinput_data_formatc                    t        | |      }|j                  \  }}t        j                  ||d|      }|d   |d   |d   |d   |d   f\  }}	}
}}t	        |      D cg c]  \  }}|j                         r| }}}t	        |      D cg c]  \  }}||vs| }}}t	        |	      D cg c]  \  }}||vs| }	}}t	        |
      D cg c]  \  }}||vs| }
}}t	        |      D cg c]  \  }}||vs| }}}t	        |      D cg c]  \  }}||vs| }}}g }t        |	|
||      D ]$  \  }}}}||||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$   r%   z-Not as many words as there are bounding boxes)
r   sizepytesseractimage_to_data	enumeratestripzipappendr'   len)r)   r*   r+   r,   	pil_imageimage_widthimage_heightdatawordsr3   r4   r$   r%   idxwordirrelevant_indicescoordactual_boxesxywh
actual_boxnormalized_boxesr#   s                            r&   apply_tesseractrM   A   s     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(9F(F.F.0F4=F4F:F:4G G G#Gc            !       R    e Zd ZdZdgZddej                  ddddddddfdedee	e
f   d	ed
edededeeee   f   deeee   f   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dddddej*                  dfdededee	e
f   d
edededeeee   f   deeee   f   dedee	   dee	   deee	ef      dedeee	ef      dej2                  j2                  fd       Z xZS )LayoutLMv3ImageProcessora
  
    Constructs a LayoutLMv3 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 `PILImageResampling.BILINEAR`):
            Resampling filter to use if resizing the image. Can be overridden by `resample` in `preprocess`.
        do_rescale (`bool`, *optional*, defaults to `True`):
            Whether to rescale the image's pixel values by the specified `rescale_value`. Can be overridden by
            `do_rescale` in `preprocess`.
        rescale_factor (`float`, *optional*, defaults to 1 / 255):
            Value by which the image's pixel values are rescaled. Can be overridden by `rescale_factor` in
            `preprocess`.
        do_normalize (`bool`, *optional*, defaults to `True`):
            Whether to normalize the image. Can be overridden by the `do_normalize` parameter in the `preprocess`
            method.
        image_mean (`Iterable[float]` or `float`, *optional*, defaults to `IMAGENET_STANDARD_MEAN`):
            Mean to use if normalizing the image. This is a float or list of floats the length of the number of
            channels in the image. Can be overridden by the `image_mean` parameter in the `preprocess` method.
        image_std (`Iterable[float]` or `float`, *optional*, defaults to `IMAGENET_STANDARD_STD`):
            Standard deviation to use if normalizing the image. This is a float or list of floats the length of the
            number of channels in the image. Can be overridden by the `image_std` 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
            the `apply_ocr` parameter in the `preprocess` method.
        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 the `ocr_lang` parameter in the `preprocess` method.
        tesseract_config (`str`, *optional*):
            Any additional custom configuration flags that are forwarded to the `config` parameter when calling
            Tesseract. For example: '--psm 6'. Can be overridden by the `tesseract_config` parameter in the
            `preprocess` method.
    pixel_valuesTNgp? 	do_resizer5   resample
do_rescalerescale_valuedo_normalize
image_mean	image_std	apply_ocrocr_langr+   returnc                    t        |   di | ||nddd}t        |      }|| _        || _        || _        || _        || _        || _        ||nt        | _
        ||nt        | _        |	| _        |
| _        || _        y )N   )r%   r$    )super__init__r
   rR   r5   rS   rT   rescale_factorrV   r   rW   r   rX   rY   rZ   r+   )selfrR   r5   rS   rT   rU   rV   rW   rX   rY   rZ   r+   kwargs	__class__s                r&   r`   z!LayoutLMv3ImageProcessor.__init__   s     	"6"'tc-JT""	 $+((2(>*DZ&/&;AV"  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$   zFThe `size` dictionary must contain the keys `height` and `width`. Got )r5   rS   re   r,   )r
   
ValueErrorkeysr   )rb   r)   r5   rS   re   r,   rc   output_sizes           r&   r   zLayoutLMv3ImageProcessor.resize   sy    F T"47$#6efjfofofqersttH~tG}5
#/
 
 	
r(   imagesra   return_tensorsc           
         ||n| j                   }||n| j                  }t        |      }||n| j                  }||n| j                  }||n| j
                  }||n| j                  }||n| j                  }|	|	n| j                  }	|
|
n| j                  }
||n| j                  }||n| j                  }t        |      }t        |      st        d      t        |||||	|||       |D cg c]  }t!        |       }}t#        |d         r|rt$        j'                  d       |t)        |d         }|
rKt+        | d       g }g }|D ]6  }t-        ||||      \  }}|j/                  |       |j/                  |       8 |r"|D cg c]  }| j1                  ||||       }}|r!|D cg c]  }| j3                  |||       }}|r"|D cg c]  }| j5                  |||	|	       }}|D cg c]  }t7        |||
       }}t9        d|i|      }|
r
|d<   |d<   |S c c}w 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. Expects a single or batch of images with pixel values ranging from 0 to 255. If
                passing in images with pixel values between 0 and 1, set `do_rescale=False`.
            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 applying `resize`.
            resample (`int`, *optional*, defaults to `self.resample`):
                Resampling filter to use if resizing the image. This can be one of the `PILImageResampling` filters.
                Only has an effect if `do_resize` is set to `True`.
            do_rescale (`bool`, *optional*, defaults to `self.do_rescale`):
                Whether to rescale the image pixel values between [0, 1].
            rescale_factor (`float`, *optional*, defaults to `self.rescale_factor`):
                Rescale factor to apply to the image pixel values. Only has an effect if `do_rescale` is set to `True`.
            do_normalize (`bool`, *optional*, defaults to `self.do_normalize`):
                Whether to normalize the image.
            image_mean (`float` or `Iterable[float]`, *optional*, defaults to `self.image_mean`):
                Mean values to be used for normalization. Only has an effect if `do_normalize` is set to `True`.
            image_std (`float` or `Iterable[float]`, *optional*, defaults to `self.image_std`):
                Standard deviation values to be used for normalization. Only has an effect if `do_normalize` 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.
            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.
        zkInvalid image type. Must be of type PIL.Image.Image, numpy.ndarray, torch.Tensor, tf.Tensor or jax.ndarray.)rT   ra   rV   rW   rX   rR   r5   rS   r   zIt looks like you are trying to rescale already rescaled images. If the input images have pixel values between 0 and 1, set `do_rescale=False` to avoid rescaling them again.r6   r.   )r)   r5   rS   r,   )r)   scaler,   )r)   meanstdr,   )input_channel_dimrP   )r@   tensor_typerA   boxes)rR   r5   r
   rS   rT   ra   rV   rW   rX   rY   rZ   r+   r   r   rg   r   r   r   loggerwarning_oncer   r   rM   r;   r   rescale	normalizer   r	   )rb   rj   rR   r5   rS   rT   ra   rV   rW   rX   rY   rZ   r+   rk   re   r,   r)   words_batchboxes_batchrA   rr   r@   s                         r&   
preprocessz#LayoutLMv3ImageProcessor.preprocess   s   L "+!6IDNN	'tTYYT"'38#-#9Zt
+9+E4K^K^'3'?|TEVEV#-#9Zt
!*!6IDNN	!*!6IDNN	'38/?/K+QUQfQf$V,F#:  	&!)%!		
 6<<E.'<<6!9%*s
 $ >vay I dM2KK *.uh@Pduvu""5)""5)*
  $ %dXYjkF 
  $ 5RcdF 
  $ U^opF  ou
ej'{N_`
 
 .&!9~V'DM'DMc =.

s   4H-H24H7H<9I)__name__
__module____qualname____doc__model_input_namesr   BILINEARboolr   strr"   floatr   r   r   r`   npndarrayr   r   r   FIRSTr   r   PILImagery   __classcell__)rd   s   @r&   rO   rO   g   s   $L (( #'9'B'B&!4837"&*,11 38n1 %	1
 1 1 1 %%011 /01 1 3-1 #3-1 
1H (:'B'B>BDH.
zz.
 38n.
 %	.

 eC)9$9:;.
 $E#/?*?$@A.
 
.
` %& # $!4837"&*.;?(8(>(>DH!UU U 38n	U U U U %%01U /0U U 3-U #3-U !sJ!78U &U  $E#/?*?$@A!U" 
#U 'Ur(   rO   )N)-r}   typingr   r   r   r   numpyr   image_processing_utilsr   r	   r
   image_transformsr   r   r   image_utilsr   r   r   r   r   r   r   r   r   r   r   utilsr   r   r   r   r   r   r   r6   
get_loggerrz   rs   r'   r   r   rM   rO   r^   r(   r&   <module>r      s    , 2 2  U U Q Q      			H	% AE	##::##
3-## sm##  &6&; <=	##LO1 Or(   