o
    +if<                     @   s  U d dl Z d dlZd dlZd dlmZmZ d dlmZ d dlm	Z	m
Z
mZmZmZmZmZ d dlZd dlZddlmZ ddlmZ ddlmZ dd	lmZmZ dd
lmZmZm Z  e	red dl!Z"ddl#m$Z$ da%eee&  e'd< ej(dkrvdndZ)e*de*de*de*de*de*de*de*de*de*de*de*de*de*dgZ+eG dd  d Z,d!ee& fd"d#Z-d$d%d!e.fd&d'Z/d$d%d!e0fd(d)Z1d*ej2d!e0fd+d,Z3d-eee& ee0 eej2 ed% f d!ee0 fd.d/Z4dS )0    N)	dataclassfield)BytesIO)TYPE_CHECKINGAnyClassVarDictListOptionalUnion   )config)DownloadConfig)
array_cast)is_local_pathxopen)first_non_null_valueno_op_if_value_is_nullstring_to_dict   )FeatureType_IMAGE_COMPRESSION_FORMATSlittle<>z|b1|u1z<u2z>u2z<i2z>i2z<u4z>u4z<i4z>i4z<f4z>f4z<f8z>f8c                   @   s  e Zd ZU dZdZee ed< dZe	ed< dZ
ee ed< dZee ed< ee e d	Zee ed
< ed dddZeed< dd Zdeeeeejdf defddZddeddfddZdedeedf f fddZdeejej ej!f dej fddZ"dej dej fddZ#dS )Imagea  Image [`Feature`] to read image data from an image file.

    Input: The Image feature accepts as input:
    - A `str`: Absolute path to the image file (i.e. random access is allowed).
    - A `dict` with the keys:

        - `path`: String with relative path of the image file to the archive file.
        - `bytes`: Bytes of the image file.

      This is useful for archived files with sequential access.

    - An `np.ndarray`: NumPy array representing an image.
    - A `PIL.Image.Image`: PIL image object.

    Args:
        mode (`str`, *optional*):
            The mode to convert the image to. If `None`, the native mode of the image is used.
        decode (`bool`, defaults to `True`):
            Whether to decode the image data. If `False`,
            returns the underlying dictionary in the format `{"path": image_path, "bytes": image_bytes}`.

    Examples:

    ```py
    >>> from datasets import load_dataset, Image
    >>> ds = load_dataset("beans", split="train")
    >>> ds.features["image"]
    Image(decode=True, id=None)
    >>> ds[0]["image"]
    <PIL.JpegImagePlugin.JpegImageFile image mode=RGB size=500x500 at 0x15E52E7F0>
    >>> ds = ds.cast_column('image', Image(decode=False))
    {'bytes': None,
     'path': '/root/.cache/huggingface/datasets/downloads/extracted/b0a21163f78769a2cf11f58dfc767fb458fc7cea5c05dccc0144a2c0f0bc1292/train/healthy/healthy_train.85.jpg'}
    ```
    NmodeTdecodeidPIL.Image.Imagedtypebytespathpa_typeF)defaultinitrepr_typec                 C   s   | j S N)r%   )self r,   P/var/www/html/corbot_env/lib/python3.10/site-packages/datasets/features/image.py__call__[   s   zImage.__call__valuereturnc                 C   s   t jrddl}ntdt|trt|}t|tr |ddS t|t	r*d|dS t|tj
r4t|S t||jjr?t|S |ddurVtj|d rVd|ddS |ddusd|dduro|d|ddS td| d	)
a   Encode example into a format for Arrow.

        Args:
            value (`str`, `np.ndarray`, `PIL.Image.Image` or `dict`):
                Data passed as input to Image feature.

        Returns:
            `dict` with "path" and "bytes" fields
        r   N4To support encoding images, please install 'Pillow'.r$   r#   r$   r"   r#   zUAn image sample should have one of 'path' or 'bytes' but they are missing or None in .)r   PIL_AVAILABLE	PIL.ImageImportError
isinstancelistnparraystrr#   ndarrayencode_np_arrayr   encode_pil_imagegetosr$   isfile
ValueError)r+   r/   PILr,   r,   r-   encode_example^   s(   








zImage.encode_examplec                 C   s  | j stdtjrddl}ddl}ntd|du ri }|d |d }}|du r|du r6td| dt|rA|j	
|}n^|d	d
 }|tjrQtjntj}zt||d }	||	}
W n tym   d}
Y nw t|
d}t|d|d}t| }W d   n1 sw   Y  |j	
|}n|j	
t|}|  | |j	jjjdur|j|}| jr| j|jkr|| j}|S )aq  Decode example image file into image data.

        Args:
            value (`str` or `dict`):
                A string with the absolute image file path, a dictionary with
                keys:

                - `path`: String with absolute or relative image file path.
                - `bytes`: The bytes of the image file.
            token_per_repo_id (`dict`, *optional*):
                To access and decode
                image files from private repositories on the Hub, you can pass
                a dictionary repo_id (`str`) -> token (`bool` or `str`).

        Returns:
            `PIL.Image.Image`
        zMDecoding is disabled for this feature. Please use Image(decode=True) instead.r   Nz4To support decoding images, please install 'Pillow'.r$   r#   zCAn image should have one of 'path' or 'bytes' but both are None in r3   z::repo_id)tokenrb)download_config)r   RuntimeErrorr   r4   r5   PIL.ImageOpsr6   rB   r   r   opensplit
startswithHF_ENDPOINTHUB_DATASETS_URLHUB_DATASETS_HFFS_URLr   r?   r   r   r   readloadgetexifExifTagsBaseOrientationImageOpsexif_transposer   convert)r+   r/   token_per_repo_idrC   r$   bytes_image
source_urlpatternrF   rG   rI   fr,   r,   r-   decode_example   sJ   


zImage.decode_exampler   c                 C   s(   ddl m} | jr| S |d|ddS )zfIf in the decodable state, return the feature itself, otherwise flatten the feature into a dictionary.r   )Valuebinarystringr"   )featuresrb   r   )r+   rb   r,   r,   r-   flatten   s   zImage.flattenstoragec                 C   s  t j|jr%t jdgt| t  d}t jj||gddg|	 d}nt j
|jrJt jdgt| t  d}t jj||gddg|	 d}nt j|jr|jddkr_|d}nt jdgt| t  d}|jddkr{|d}nt jdgt| t  d}t jj||gddg|	 d}n4t j|jrt jdd | D t  d}t jdgt| t  d}t jj||gddg|	 d}t|| jS )	a'  Cast an Arrow array to the Image arrow storage type.
        The Arrow types that can be converted to the Image pyarrow storage type are:

        - `pa.string()` - it must contain the "path" data
        - `pa.binary()` - it must contain the image bytes
        - `pa.struct({"bytes": pa.binary()})`
        - `pa.struct({"path": pa.string()})`
        - `pa.struct({"bytes": pa.binary(), "path": pa.string()})`  - order doesn't matter
        - `pa.list(*)` - it must contain the image array data

        Args:
            storage (`Union[pa.StringArray, pa.StructArray, pa.ListArray]`):
                PyArrow array to cast.

        Returns:
            `pa.StructArray`: Array in the Image arrow storage type, that is
                `pa.struct({"bytes": pa.binary(), "path": pa.string()})`.
        Ntyper#   r$   maskr   c                 S   s*   g | ]}|d urt t|d nd qS )Nr#   )r=   r9   r:   ).0arrr,   r,   r-   
<listcomp>   s   * z&Image.cast_storage.<locals>.<listcomp>)patypes	is_stringri   r:   lenrc   StructArrayfrom_arraysis_null	is_binaryrd   	is_structget_field_indexr   is_list	to_pylistr   r%   r+   rg   bytes_array
path_arrayr,   r,   r-   cast_storage   s0      zImage.cast_storagec                    s   t dd  tj fdd| D t d}tjdd |d D t d}tjj||gddg|	 d	}t
|| jS )
a8  Embed image files into the Arrow array.

        Args:
            storage (`pa.StructArray`):
                PyArrow array to embed.

        Returns:
            `pa.StructArray`: Array in the Image arrow storage type, that is
                `pa.struct({"bytes": pa.binary(), "path": pa.string()})`.
        c                 S   s8   t | d}| }W d    |S 1 sw   Y  |S )NrH   )r   rR   )r$   r`   r\   r,   r,   r-   path_to_bytes
  s   

z*Image.embed_storage.<locals>.path_to_bytesc                    s8   g | ]}|d ur|d d u r |d n|d nd qS )Nr#   r$   r,   )rl   xr   r,   r-   rn     s    *z'Image.embed_storage.<locals>.<listcomp>rh   c                 S   s$   g | ]}|d urt j|nd qS r*   )r@   r$   basename)rl   r$   r,   r,   r-   rn     s   $ r$   r#   rj   )r   ro   r:   rz   rc   r   rd   rs   rt   ru   r   r%   r{   r,   r   r-   embed_storage   s   

zImage.embed_storager*   )$__name__
__module____qualname____doc__r   r
   r;   __annotations__r   boolr   r!   r   ro   structrc   rd   r%   r   r   r)   r.   r   r#   dictr9   r<   rD   ra   r   rf   StringArrayrs   	ListArrayr~   r   r,   r,   r,   r-   r   -   s   
 $$"'>$.r   r0   c                  C   sR   t jrdd l} ntdtd u r'| j  tt| jj	
 t| jj
 @ atS )Nr   r1   )r   r4   r5   r6   r   r   r'   r8   setOPENkeysSAVE)rC   r,   r,   r-   list_image_compression_formats  s   

$r   r]   r    c                 C   sB   t  }| jt v r| j}n	| jdv rdnd}| j||d | S )zmConvert a PIL Image object to bytes using native compression if possible, otherwise use PNG/TIFF compression.)1LLARGBRGBAPNGTIFF)format)r   r   r   r   savegetvalue)r]   bufferr   r,   r,   r-   image_to_bytes,  s   r   c                 C   s.   t | dr| jdkr| jd dS d t| dS )Nfilename r2   )hasattrr   r   )r]   r,   r,   r-   r>   7  s   r>   r:   c           	      C   s>  t jrdd l}ntd| j}|jdkr|jnt}|j}|j}d }| j	dd  rM|dvr7t
d| d| dtd	}||krLtd
| d| d nB|tv rT|}n;|dkr|| t| }t|tv ryt|}td
| d| d n|d }|dksX|d u rt
d| dt |j| |}d t|dS )Nr   r1   =r   )uizUnsupported array dtype z for image encoding. Only z' is supported for multi-channel arrays.r   zDowncasting array dtype z to z to be compatible with 'Pillow'r   zCannot downcast dtype z- to a valid image dtype. Valid image dtypes: r2   )r   r4   r5   r6   r!   	byteorder_NATIVE_BYTEORDERkinditemsizeshape	TypeErrorr9   warningswarn_VALID_IMAGE_ARRAY_DTPYESr;   r   	fromarrayastyper   )	r:   rC   r!   dtype_byteorder
dtype_kinddtype_itemsize
dest_dtype	dtype_strr]   r,   r,   r-   r=   >  sB   


r=   objsc                    s   t jrddl}ntd| rIt| \}}t|tr dd | D S t|tjr3t	t
  fdd| D S t||jjrGt	t  fdd| D S | S | S )zmEncode a list of objects into a format suitable for creating an extension array of type `ImageExtensionType`.r   Nr1   c                 S   s"   g | ]}|d ur|d dnd qS )Nr2   r,   rl   objr,   r,   r-   rn   u  s   " z2objects_to_list_of_image_dicts.<locals>.<listcomp>c                       g | ]} |qS r,   r,   r   obj_to_image_dict_funcr,   r-   rn   x      c                    r   r,   r,   r   r   r,   r-   rn   {  r   )r   r4   r5   r6   r   r7   r;   r9   r<   r   r=   r   r>   )r   rC   _r   r,   r   r-   objects_to_list_of_image_dictsi  s   

r   )5r@   sysr   dataclassesr   r   ior   typingr   r   r   r   r	   r
   r   numpyr9   pyarrowro   r   r   download.download_configr   tabler   utils.file_utilsr   r   utils.py_utilsr   r   r   r5   rC   re   r   r   r;   r   r   r   r!   r   r   r   r#   r   r   r>   r<   r=   r   r,   r,   r,   r-   <module>   sZ   
 $ r+ 