
    rh_                         d Z ddl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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mZ ddlmZmZm Z  dd	l!m"Z"  e jF                  e$      Z% e"       rddl&Z& G d
 de      Z'dgZ(y)z!Image processor class for Nougat.    )OptionalUnionN   )BaseImageProcessorBatchFeatureget_size_dict)get_resize_output_image_sizepadresizeto_channel_dimension_formatto_pil_image)IMAGENET_DEFAULT_MEANIMAGENET_DEFAULT_STDChannelDimension
ImageInputPILImageResamplingget_image_sizeinfer_channel_dimension_formatis_scaled_imagemake_list_of_imagesto_numpy_arrayvalid_imagesvalidate_preprocess_arguments)
TensorTypefilter_out_non_signature_kwargslogging)is_vision_availablec            %           e Zd ZdZdgZdddej                  ddddddddfdeded	ee	e
ef      d
edededededeeef   dedeeeee   f      deeeee   f      ddf fdZdej"                  fdZd Z	 	 	 d#dej"                  dedee   deee
ef      dej"                  f
dZ	 	 d$dej,                  d	e	e
ef   deee
ef      deee
ef      dej,                  f
dZ	 	 d$dej,                  d	e	e
ef   deee
ef      deee
ef      dej,                  f
dZej2                  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j2                  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dej:                  dfd edee   dee   d	ee	e
ef      d
edee   dee   dee   dee   deeeef      dee   deeeee   f      deeeee   f      d!eee
ef      dee   deee
ef      de jB                  jB                  f"d"       Z" xZ#S )%NougatImageProcessora	  
    Constructs a Nougat image processor.

    Args:
        do_crop_margin (`bool`, *optional*, defaults to `True`):
            Whether to crop the image margins.
        do_resize (`bool`, *optional*, defaults to `True`):
            Whether to resize the image's (height, width) dimensions to the specified `size`. Can be overridden by
            `do_resize` in the `preprocess` method.
        size (`dict[str, int]` *optional*, defaults to `{"height": 896, "width": 672}`):
            Size of the image after resizing. Can be overridden by `size` in the `preprocess` method.
        resample (`PILImageResampling`, *optional*, defaults to `Resampling.BILINEAR`):
            Resampling filter to use if resizing the image. Can be overridden by `resample` in the `preprocess` method.
        do_thumbnail (`bool`, *optional*, defaults to `True`):
            Whether to resize the image using thumbnail method.
        do_align_long_axis (`bool`, *optional*, defaults to `False`):
            Whether to align the long axis of the image with the long axis of `size` by rotating by 90 degrees.
        do_pad (`bool`, *optional*, defaults to `True`):
            Whether to pad the images to the largest image size in the batch.
        do_rescale (`bool`, *optional*, defaults to `True`):
            Whether to rescale the image by the specified scale `rescale_factor`. Can be overridden by the `do_rescale`
            parameter in the `preprocess` method.
        rescale_factor (`int` or `float`, *optional*, defaults to `1/255`):
            Scale factor to use if rescaling the image. Can be overridden by the `rescale_factor` parameter in the
            `preprocess` method.
        do_normalize (`bool`, *optional*, defaults to `True`):
            Whether to normalize the image. Can be overridden by `do_normalize` in the `preprocess` method.
        image_mean (`float` or `list[float]`, *optional*, defaults to `IMAGENET_DEFAULT_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 (`float` or `list[float]`, *optional*, defaults to `IMAGENET_DEFAULT_STD`):
            Image standard deviation.
    pixel_valuesTNFgp?do_crop_margin	do_resizesizeresampledo_thumbnaildo_align_long_axisdo_pad
do_rescalerescale_factordo_normalize
image_mean	image_stdreturnc                     t        |   di | ||nddd}t        |      }|| _        || _        || _        || _        || _        || _        || _	        || _
        |	| _        |
| _        ||nt        | _        ||| _        y t        | _        y )Ni  i  )heightwidth )super__init__r   r!   r"   r#   r$   r%   r&   r'   r(   r)   r*   r   r+   r   r,   )selfr!   r"   r#   r$   r%   r&   r'   r(   r)   r*   r+   r,   kwargs	__class__s                 /var/www/html/ai-insurance-compliance-backend/venv/lib/python3.12/site-packages/transformers/models/nougat/image_processing_nougat.pyr3   zNougatImageProcessor.__init__[   s      	"6"'tc-JT","	 ("4$,((2(>*DY&/&;AU    imagec                     t        j                  t        j                  |            }|ddddgf   }|j                  ddd      }|S )zGThis is a reimplementation of a findNonZero function equivalent to cv2.N   r      )npcolumn_stacknonzeroreshape)r4   r9   non_zero_indicesidxvecs       r7   python_find_non_zeroz)NougatImageProcessor.python_find_non_zero}   sC    ??2::e+<=!!aV),Aq)r8   c                     t        j                  |d      j                  t              }t        j                  |d      j                  t              }|d   |d   }}|d   |z
  dz   }|d   |z
  dz   }||||fS )zHThis is a reimplementation of a BoundingRect function equivalent to cv2.r   r;   )axisr   r;   )r>   minastypeintmax)r4   coordinates
min_values
max_valuesx_miny_minr0   r/   s           r7   python_bounding_rectz)NougatImageProcessor.python_bounding_rect   s~    VVKf5<<SA
VVKf5<<SA
!!}jmu1%)A&*eUF**r8   gray_thresholddata_formatinput_data_formatc                    |t        |      }t        ||      }t        j                  |j	                  d            j                  t        j                        }|j                         }|j                         }||k(  rEt        j                  |      }t        ||t        j                        }|t        |||      }|S |}|S ||z
  ||z
  z  dz  }||k  }| j                  |      }	| j                  |	      \  }
}}}|j                  |
||
|z   ||z   f      }t        j                  |      j                  t        j                        }t        ||t        j                        }|t        |||      }|S |}|S )a  
        Crops the margin of the image. Gray pixels are considered margin (i.e., pixels with a value below the
        threshold).

        Args:
            image (`np.array`):
                The image to be cropped.
            gray_threshold (`int`, *optional*, defaults to `200`)
                Value below which pixels are considered to be gray.
            data_format (`ChannelDimension`, *optional*):
                The channel dimension format of the output image. If unset, will use the inferred format from the
                input.
            input_data_format (`ChannelDimension`, *optional*):
                The channel dimension format of the input image. If unset, will use the inferred format from the input.
        rT   L   )r   r   r>   arrayconvertrI   uint8rK   rH   r   r   LASTrD   rQ   crop)r4   r9   rR   rS   rT   datamax_valmin_valgraycoordsrO   rP   r0   r/   s                 r7   crop_marginz NougatImageProcessor.crop_margin   s   , $ >u EU6GHxxc*+22288<((*((*gHHUOE/7HJZJ_J_`E * ,E;@QR 
 L  
 Lw7W#45;n$**40&*&?&?&G#ueV

E5%%-HI&&rxx0+E3DFVF[F[\ S^Ri'{<MN 	  pu 	 r8   c                 @   t        ||      \  }}|d   |d   }}|t        |      }|t        j                  k(  rd}	n$|t        j                  k(  rd}	nt        d|       ||k  r||kD  s
||kD  r||k  rt        j                  |d|	      }|t        |||	      }|S )
a  
        Align the long axis of the image to the longest axis of the specified size.

        Args:
            image (`np.ndarray`):
                The image to be aligned.
            size (`dict[str, int]`):
                The size `{"height": h, "width": w}` to align the long axis to.
            data_format (`str` or `ChannelDimension`, *optional*):
                The data format of the output image. If unset, the same format as the input image is used.
            input_data_format (`ChannelDimension` or `str`, *optional*):
                The channel dimension format of the input image. If not provided, it will be inferred.

        Returns:
            `np.ndarray`: The aligned image.
        channel_dimr/   r0   rF   )r;   r=   zUnsupported data format: r   )axesinput_channel_dim)	r   r   r   r\   FIRST
ValueErrorr>   rot90r   )
r4   r9   r#   rS   rT   input_heightinput_widthoutput_heightoutput_widthrot_axess
             r7   align_long_axisz$NougatImageProcessor.align_long_axis   s    . %35FW$X!k&*8nd7m|$ >u E 0 5 55H"2"8"88H89J8KLMM=([<-G=([<-GHHUAH5E"/{VghEr8   c                     |d   |d   }}t        ||      \  }}||z
  }	||z
  }
|
dz  }|	dz  }|
|z
  }|	|z
  }||f||ff}t        ||||      S )a  
        Pad the image to the specified size at the top, bottom, left and right.

        Args:
            image (`np.ndarray`):
                The image to be padded.
            size (`dict[str, int]`):
                The size `{"height": h, "width": w}` to pad the image to.
            data_format (`str` or `ChannelDimension`, *optional*):
                The data format of the output image. If unset, the same format as the input image is used.
            input_data_format (`ChannelDimension` or `str`, *optional*):
                The channel dimension format of the input image. If not provided, it will be inferred.
        r/   r0   re   r=   )rS   rT   )r   r
   )r4   r9   r#   rS   rT   ro   rp   rm   rn   delta_widthdelta_heightpad_toppad_left
pad_bottom	pad_rightpaddings                   r7   	pad_imagezNougatImageProcessor.pad_image   s    ( '+8nd7m|$25FW$X!k"[0$|3!#!#!G+
(*	Z(8Y*?@5'{N_``r8   c           	          t        ||      \  }}|d   |d   }
}	t        ||	      }t        ||
      }||k(  r||k(  r|S ||kD  rt        ||z  |z        }n||kD  rt        ||z  |z        }t        |f||f|d||d|S )as  
        Resize the image to make a thumbnail. The image is resized so that no dimension is larger than any
        corresponding dimension of the specified size.

        Args:
            image (`np.ndarray`):
                The image to be resized.
            size (`dict[str, int]`):
                The size `{"height": h, "width": w}` to resize the image to.
            resample (`PILImageResampling`, *optional*, defaults to `PILImageResampling.BICUBIC`):
                The resampling filter to use.
            data_format (`Optional[Union[str, ChannelDimension]]`, *optional*):
                The data format of the output image. If unset, the same format as the input image is used.
            input_data_format (`ChannelDimension` or `str`, *optional*):
                The channel dimension format of the input image. If not provided, it will be inferred.
        re   r/   r0   g       @)r#   r$   reducing_gaprS   rT   )r   rH   rJ   r   )r4   r9   r#   r$   rS   rT   r5   rm   rn   ro   rp   r/   r0   s                r7   	thumbnailzNougatImageProcessor.thumbnail  s    2 %35FW$X!k&*8nd7m| \=1K.\!e{&:L+%f,|;<E<'-;<F
%#/
 
 	
r8   c                     t        |      }t        |d   |d         }t        ||d|      }t        |f||||d|}	|	S )a  
        Resizes `image` to `(height, width)` specified by `size` using the PIL library.

        Args:
            image (`np.ndarray`):
                Image to resize.
            size (`dict[str, int]`):
                Size of the output image.
            resample (`PILImageResampling`, *optional*, defaults to `PILImageResampling.BICUBIC`):
                Resampling filter to use when resiizing the image.
            data_format (`str` or `ChannelDimension`, *optional*):
                The channel dimension format of the image. If not provided, it will be the same as the input image.
            input_data_format (`ChannelDimension` or `str`, *optional*):
                The channel dimension format of the input image. If not provided, it will be inferred.
        r/   r0   F)r#   default_to_squarerT   )r#   r$   rS   rT   )r   rH   r	   r   )
r4   r9   r#   r$   rS   rT   r5   shortest_edgeoutput_sizeresized_images
             r7   r   zNougatImageProcessor.resizeH  sh    0 T"DNDM:2Rc
 
#/
 
 r8   imagesreturn_tensorsc                 &   ||n| j                   }||n| j                  }||n| j                  }||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!        |       }}|	r#t#        |d         rt$        j'                  d       |t)        |d         }|r |D cg c]  }| j+                  ||       }}|r!|D cg c]  }| j-                  |||       }}|r"|D cg c]  }| j/                  ||||       }}|r!|D cg c]  }| j1                  |||       }}|r!|D cg c]  }| j3                  |||       }}|	r!|D cg c]  }| j5                  ||
|	       }}|r"|D cg c]  }| j7                  ||||
       }}|D cg c]  }t9        |||       }}d|i}t;        ||      S c c}w c c}w c c}w c c}w 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.
            do_crop_margin (`bool`, *optional*, defaults to `self.do_crop_margin`):
                Whether to crop the image margins.
            do_resize (`bool`, *optional*, defaults to `self.do_resize`):
                Whether to resize the image.
            size (`dict[str, int]`, *optional*, defaults to `self.size`):
                Size of the image after resizing. Shortest edge of the image is resized to min(size["height"],
                size["width"]) with the longest edge resized to keep the input aspect ratio.
            resample (`int`, *optional*, defaults to `self.resample`):
                Resampling filter to use if resizing the image. This can be one of the enum `PILImageResampling`. Only
                has an effect if `do_resize` is set to `True`.
            do_thumbnail (`bool`, *optional*, defaults to `self.do_thumbnail`):
                Whether to resize the image using thumbnail method.
            do_align_long_axis (`bool`, *optional*, defaults to `self.do_align_long_axis`):
                Whether to align the long axis of the image with the long axis of `size` by rotating by 90 degrees.
            do_pad (`bool`, *optional*, defaults to `self.do_pad`):
                Whether to pad the images to the largest image size in the batch.
            do_rescale (`bool`, *optional*, defaults to `self.do_rescale`):
                Whether to rescale the image by the specified scale `rescale_factor`.
            rescale_factor (`int` or `float`, *optional*, defaults to `self.rescale_factor`):
                Scale factor to use if rescaling the image.
            do_normalize (`bool`, *optional*, defaults to `self.do_normalize`):
                Whether to normalize the image.
            image_mean (`float` or `list[float]`, *optional*, defaults to `self.image_mean`):
                Image mean to use for normalization.
            image_std (`float` or `list[float]`, *optional*, defaults to `self.image_std`):
                Image standard deviation to use for normalization.
            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.
                - Unset: defaults to the channel dimension format of the input image.
            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.)
r(   r)   r*   r+   r,   r'   size_divisibilityr"   r#   r$   r   zIt looks like you are trying to rescale already rescaled images. If the input images have pixel values between 0 and 1, set `do_rescale=False` to avoid rescaling them again.rV   )r#   rT   )r9   r#   r$   rT   )r9   r#   rT   )r9   scalerT   )r9   meanstdrT   rh   r    )r^   tensor_type)r!   r"   r#   r$   r%   r&   r'   r(   r)   r*   r+   r,   r   r   rk   r   r   r   loggerwarning_oncer   rc   rr   r   r~   r{   rescale	normalizer   r   )r4   r   r!   r"   r#   r$   r%   r&   r'   r(   r)   r*   r+   r,   r   rS   rT   r9   r^   s                      r7   
preprocesszNougatImageProcessor.preprocesso  s#   N ,:+E4K^K^!*!6IDNN	'tTYY'38'3'?|TEVEV3E3Q/W[WnWn!-4;;#-#9Zt
+9+E4K^K^'3'?|TEVEV#-#9Zt
!*!6IDNN	$V,F#:  	&!)%!"	
 6<<E.'<</&)4s
 $ >vay I`fgW\d&&u@Q&RgFgouvfkd**5tO`*avFv $ %dXYjkF 
 ouvfkdnn5tO`navFvouvfkdnn5tO`navFv $ 5RcdF 
  $ U^opF  ou
ej'{N_`
 
 '>BB_ = h w w w

s6   ;I&
I+,I0I53I:I?9JJ	>J)   NN)NN)$__name__
__module____qualname____doc__model_input_namesr   BILINEARboolr   dictstrrJ   r   floatlistr3   r>   rY   rD   rQ   r   rc   ndarrayrr   r{   BICUBICr~   r   r   rj   r   r   PILImager   __classcell__)r6   s   @r7   r   r   6   s    D ((  $)-'9'B'B!#(,3!:>9= V V  V tCH~&	 V
 % V  V ! V  V  V c5j) V  V U5$u+#567 V E%e"456 V 
 VD"(( + "26DH2xx2 2 ./	2
 $E#/?*?$@A2 
2r ?CDH-zz- 38n- eC)9$9:;	-
 $E#/?*?$@A- 
-f ?CDH!azz!a 38n!a eC)9$9:;	!a
 $E#/?*?$@A!a 
!aP (:'A'A>BDH0
zz0
 38n0
 %	0

 eC)9$9:;0
 $E#/?*?$@A0
 
0
n (:'A'A>BDH%zz% 38n% %	%
 eC)9$9:;% $E#/?*?$@A% 
%N %& *.$()-'+'+-1!%%)6:'+:>9=;?2B2H2HDH#WCWC !WC D>	WC
 tCH~&WC %WC tnWC %TNWC WC TNWC !sEz!23WC tnWC U5$u+#567WC E%e"456WC !sJ!78WC  ./!WC" $E#/?*?$@A#WC$ 
%WC 'WCr8   r   ))r   typingr   r   numpyr>   image_processing_utilsr   r   r   image_transformsr	   r
   r   r   r   image_utilsr   r   r   r   r   r   r   r   r   r   r   r   utilsr   r   r   utils.import_utilsr   
get_loggerr   r   r   r   __all__r1   r8   r7   <module>r      s{    ( "  U U     J I 5 
		H	% QC- QCh "
"r8   