+
    QV-jŠ<  ã                   ó  € R t ^ RIt^ RIHtHt ^ RIHtHt ^RIH	t	 ^RI
Ht ^RIHt ^RIHt ^RIHtHtHt ^R	IHt ^R
IHt ]! ]4      t ! R R]4      tRR R lltRR R lltRR R lltRR R lltRR R llt R# )zList and inspect datasets.N)ÚMappingÚSequence)ÚOptionalÚUnion)ÚDownloadConfig)ÚDownloadMode)ÚStreamingDownloadManager)ÚDatasetInfo)Údataset_module_factoryÚget_dataset_builder_classÚload_dataset_builder)Ú
get_logger)ÚVersionc                   ó   € ] tR t^&tRtR# )ÚSplitsNotFoundError© N)Ú__name__Ú
__module__Ú__qualname__Ú__firstlineno__Ú__static_attributes__r   ó    Úa/Volumes/fast/ai/experiments/ui-tars-smoke/.venv/lib/python3.14/site-packages/datasets/inspect.pyr   r   &   s   † Ûr   r   c                ó`  € V ^8„  d   QhR\         R\        \        \        \        \         3,          ,          R\        \
        ,          R\        \        \        \         3,          ,          R\        \        \         \        3,          ,          R\        \        \        \         3,          ,          /# )é   ÚpathÚ
data_filesÚdownload_configÚdownload_modeÚrevisionÚtoken)	Ústrr   r   ÚdictÚlistr   r   r   Úbool)Úformats   "r   Ú__annotate__r&   *   sŒ   € ÷ @ñ @Ü
ð@äœœt¤T¬3˜Õ/Õ0ð@ô œnÕ-ð@ô œE¤,´Ð"3Õ4Õ5ð	@ô
 ”uœS¤'˜\Õ*Õ+ð@ô ”Eœ$¤˜)Õ$Õ%ñ@r   c                ó‚   € \        V VVVVVR7      pV Uu/ uF  pV\        R	RV RVRVRVRVRVRV/VB bK  	  up# u upi )
a6  Get the meta information about a dataset, returned as a dict mapping config name to DatasetInfoDict.

    Args:
        path (`str`): path to the dataset repository. Can be either:

            - a local path to the dataset directory containing the data files,
                e.g. `'./dataset/squad'`
            - a dataset identifier on the Hugging Face Hub (list all available datasets and ids with [`huggingface_hub.list_datasets`]),
                e.g. `'rajpurkar/squad'`, `'nyu-mll/glue'` or``'openai/webtext'`
        revision (`Union[str, datasets.Version]`, *optional*):
            If specified, the dataset module will be loaded from the datasets repository at this version.
            By default:
            - it is set to the local version of the lib.
            - it will also try to load it from the main branch if it's not available at the local version of the lib.
            Specifying a version that is different from your local version of the lib might cause compatibility issues.
        download_config ([`DownloadConfig`], *optional*):
            Specific download configuration parameters.
        download_mode ([`DownloadMode`] or `str`, defaults to `REUSE_DATASET_IF_EXISTS`):
            Download/generate mode.
        data_files (`Union[Dict, List, str]`, *optional*):
            Defining the data_files of the dataset configuration.
        token (`str` or `bool`, *optional*):
            Optional string or boolean to use as Bearer token for remote files on the Datasets Hub.
            If `True`, or not specified, will get token from `"~/.huggingface"`.
        **config_kwargs (additional keyword arguments):
            Optional attributes for builder class which will override the attributes if supplied.

    Example:

    ```py
    >>> from datasets import get_dataset_infos
    >>> get_dataset_infos('cornell-movie-review-data/rotten_tomatoes')
    {'default': DatasetInfo(description="Movie Review Dataset.
This is a dataset of containing 5,331 positive and 5,331 negative processed
sentences from Rotten Tomatoes movie reviews...), ...}
    ```
    )r   r   r   r   r   r    r   Úconfig_namer   r   r   r   r    r   )Úget_dataset_config_namesÚget_dataset_config_info)	r   r   r   r   r   r    Úconfig_kwargsÚconfig_namesr(   s	   &&&&&&,  r   Úget_dataset_infosr-   *   s¥   € ôX ,ØØØ'Ø#ØØô€Lñ& (óñ (ˆKð 	Ô,ñ 	
Øð	
à#ð	
ð "ð	
ð ,ð		
ð
 (ð	
ð ð	
ð ð	
ð ñ	
ò 		
ñ (ñð ùò s   –#<c                ó  € V ^8„  d   QhR\         R\        \        \         \        3,          ,          R\        \        ,          R\        \        \
        \         3,          ,          R\        \        \        \        \         3,          ,          /# )r   r   r   r   r   r   ©r!   r   r   r   r   r   r"   r#   )r%   s   "r   r&   r&   m   sl   € ÷ ?ñ ?Ü
ð?ä”uœS¤'˜\Õ*Õ+ð?ô œnÕ-ð?ô œE¤,´Ð"3Õ4Õ5ð	?ô
 œœt¤T¬3˜Õ/Õ0ñ?r   c                ó6  € \        V 3RVRVRVRV/VB p\        V\        P                  P	                  V 4      R7      p\        VP                  P                  4       4      ;'       g2    VP                  P                  RVP                  ;'       g    R4      .# )a«  Get the list of available config names for a particular dataset.

Args:
    path (`str`): path to the dataset repository. Can be either:

        - a local path to the dataset directory containing the data files,
            e.g. `'./dataset/squad'`
        - a dataset identifier on the Hugging Face Hub (list all available datasets and ids with [`huggingface_hub.list_datasets`]),
            e.g. `'rajpurkar/squad'`, `'nyu-mll/glue'` or``'openai/webtext'`
    revision (`Union[str, datasets.Version]`, *optional*):
        If specified, the dataset module will be loaded from the datasets repository at this version.
        By default:
        - it is set to the local version of the lib.
        - it will also try to load it from the main branch if it's not available at the local version of the lib.
        Specifying a version that is different from your local version of the lib might cause compatibility issues.
    download_config ([`DownloadConfig`], *optional*):
        Specific download configuration parameters.
    download_mode ([`DownloadMode`] or `str`, defaults to `REUSE_DATASET_IF_EXISTS`):
        Download/generate mode.
    data_files (`Union[Dict, List, str]`, *optional*):
        Defining the data_files of the dataset configuration.
    **download_kwargs (additional keyword arguments):
        Optional attributes for [`DownloadConfig`] which will override the attributes in `download_config` if supplied,
        for example `token`.

Example:

```py
>>> from datasets import get_dataset_config_names
>>> get_dataset_config_names("nyu-mll/glue")
['cola',
 'sst2',
 'mrpc',
 'qqp',
 'stsb',
 'mnli',
 'mnli_mismatched',
 'mnli_matched',
 'qnli',
 'rte',
 'wnli',
 'ax']
```
r   r   r   r   ©Údataset_namer(   Údefault)r
   r   Úosr   Úbasenamer#   Úbuilder_configsÚkeysÚbuilder_kwargsÚgetÚDEFAULT_CONFIG_NAME)r   r   r   r   r   Údownload_kwargsÚdataset_moduleÚbuilder_clss   &&&&&,  r   r)   r)   m   s°   € ôh ,Øñàðð (ðð $ð	ð
 ðð ñ€Nô ,¨NÌÏÉ×IYÑIYÐZ^ÓI_Ô`€KÜ�×+Ñ+×0Ñ0Ó2Ó3÷ ð Ø×%Ñ%×)Ñ)¨-¸×9XÑ9X×9eÐ9eÐ\eÓfð8ð r   c                ó>  € V ^8„  d   QhR\         R\        \        \         \        3,          ,          R\        \        ,          R\        \        \
        \         3,          ,          R\        \        \        \        \         3,          ,          R\        \         ,          /# )r   r   r   r   r   r   Úreturnr/   )r%   s   "r   r&   r&   ¯   s‚   € ÷ ;Bñ ;BÜ
ð;Bä”uœS¤'˜\Õ*Õ+ð;Bô œnÕ-ð;Bô œE¤,´Ð"3Õ4Õ5ð	;Bô
 œœt¤T¬3˜Õ/Õ0ð;Bô Œc…]ñ;Br   c                ó<  € \        V 3RVRVRVRV/VB p\        V\        P                  P	                  V 4      R7      p\        VP                  P                  4       4      pV'       d   \        V4      ^8X  d
   V^ ,          MRp	MRp	VP                  ;'       g    T	# )aÛ  Get the default config name for a particular dataset.
Can return None only if the dataset has multiple configurations and no default configuration.

Args:
    path (`str`): path to the dataset repository. Can be either:

        - a local path to the dataset directory containing the data files,
            e.g. `'./dataset/squad'`
        - a dataset identifier on the Hugging Face Hub (list all available datasets and ids with [`huggingface_hub.list_datasets`]),
            e.g. `'rajpurkar/squad'`, `'nyu-mll/glue'` or``'openai/webtext'`
    revision (`Union[str, datasets.Version]`, *optional*):
        If specified, the dataset module will be loaded from the datasets repository at this version.
        By default:
        - it is set to the local version of the lib.
        - it will also try to load it from the main branch if it's not available at the local version of the lib.
        Specifying a version that is different from your local version of the lib might cause compatibility issues.
    download_config ([`DownloadConfig`], *optional*):
        Specific download configuration parameters.
    download_mode ([`DownloadMode`] or `str`, defaults to `REUSE_DATASET_IF_EXISTS`):
        Download/generate mode.
    data_files (`Union[Dict, List, str]`, *optional*):
        Defining the data_files of the dataset configuration.
    **download_kwargs (additional keyword arguments):
        Optional attributes for [`DownloadConfig`] which will override the attributes in `download_config` if supplied,
        for example `token`.

Returns:
    Optional[str]: the default config name if there is one

Example:

```py
>>> from datasets import get_dataset_default_config_name
>>> get_dataset_default_config_name("openbookqa")
'main'
```
r   r   r   r   r1   Nr3   )
r
   r   r4   r   r5   r#   r6   r7   Úlenr:   )
r   r   r   r   r   r;   r<   r=   r6   Údefault_config_names
   &&&&&,    r   Úget_dataset_default_config_namerC   ¯   s±   € ôZ ,Øñàðð (ðð $ð	ð
 ðð ñ€Nô ,¨NÌÏÉ×IYÑIYÐZ^ÓI_Ô`€KÜ˜;×6Ñ6×;Ñ;Ó=Ó>€OßÜ47¸Ó4HÈAÔ4M˜o¨aÖ0ÐSWÑà'ÐØ×*Ñ*×AÐAÐ.AÐAr   c                óþ  € V ^8„  d   QhR\         R\        \         ,          R\        \        \         \        \         ,          \        \         \        \         \        \         ,          3,          3,          3,          ,          R\        \
        ,          R\        \        \        \         3,          ,          R\        \        \         \        3,          ,          R\        \        \        \         3,          ,          R\        /# )	r   r   r(   r   r   r   r   r    r?   )
r!   r   r   r   r   r   r   r   r$   r	   )r%   s   "r   r&   r&   í   sº   € ÷ 7ñ 7Ü
ð7äœ#•ð7ô œœs¤H¬S¥M´7¼3ÄÄcÌ8ÔTWÍ=ÐFXÕ@YÐ;YÕ3ZÐZÕ[Õ\ð7ô œnÕ-ð	7ô
 œE¤,´Ð"3Õ4Õ5ð7ô ”uœS¤'˜\Õ*Õ+ð7ô ”Eœ$¤˜)Õ$Õ%ð7ô ñ7r   c                ó¸  € \        V 3RVRVRVRVRVRV/VB pVP                  p	V	P                  f„   V'       d   VP                  4       M	\	        4       pVe   Wcn         VP                  \        VP                  VR7      4       U
u/ uF  p
V
P                  RV
P                  R	V /bK   	  up
V	n        V	# V	# u up
i   \         d   p\        R
4      ThRp?ii ; i)aG  Get the meta information (DatasetInfo) about a dataset for a particular config

Args:
    path (`str`): path to the dataset repository. Can be either:

        - a local path to the dataset directory containing the data files,
            e.g. `'./dataset/squad'`
        - a dataset identifier on the Hugging Face Hub (list all available datasets and ids with [`huggingface_hub.list_datasets`]),
            e.g. `'rajpurkar/squad'`, `'nyu-mll/glue'` or``'openai/webtext'`
    config_name (:obj:`str`, optional): Defining the name of the dataset configuration.
    data_files (:obj:`str` or :obj:`Sequence` or :obj:`Mapping`, optional): Path(s) to source data file(s).
    download_config (:class:`~download.DownloadConfig`, optional): Specific download configuration parameters.
    download_mode (:class:`DownloadMode` or :obj:`str`, default ``REUSE_DATASET_IF_EXISTS``): Download/generate mode.
    revision (:class:`~utils.Version` or :obj:`str`, optional): Version of the dataset to load.
        As datasets have their own git repository on the Datasets Hub, the default version "main" corresponds to their "main" branch.
        You can specify a different version than the default "main" by using a commit SHA or a git tag of the dataset repository.
    token (``str`` or :obj:`bool`, optional): Optional string or boolean to use as Bearer token for remote files on the Datasets Hub.
        If True, or not specified, will get token from `"~/.huggingface"`.
    **config_kwargs (additional keyword arguments): optional attributes for builder class which will override the attributes if supplied.

Únamer   r   r   r   r    N)Ú	base_pathr   r2   z<The split names could not be parsed from the dataset config.)r   ÚinfoÚsplitsÚcopyr   r    Ú_split_generatorsr   rG   rF   Ú	Exceptionr   )r   r(   r   r   r   r   r    r+   ÚbuilderrH   Úsplit_generatorÚerrs   &&&&&&&,    r   r*   r*   í   s   € ô> #Øñ	àð	ð ð	ð (ð		ð
 $ð	ð ð	ð ð	ð ñ	€Gð �<‰<€DØ‡{�{Òß4C˜/×.Ñ.Ô0ÌÓIYˆØÒØ$)Ô!ð	oð (/×'@Ñ'@Ü,°w×7HÑ7HÐZiÔjô(óñ(�Oð  ×$Ñ$ v¨×/CÑ/CÀ^ÐUYÐ&ZÒZñ(ñˆDŒKð €Kˆ4€Kùòøô ô 	oÜ%Ð&dÓeÐknÐnûð	oús*   Á (B= Â$B8Â,B= Â8B= Â=CÃCÃCc                óò  € V ^8„  d   QhR\         R\        \         ,          R\        \        \         \        \         ,          \        \         \        \         \        \         ,          3,          3,          3,          ,          R\        \
        ,          R\        \        \        \         3,          ,          R\        \        \         \        3,          ,          R\        \        \        \         3,          ,          /# )r   r   r(   r   r   r   r   r    )	r!   r   r   r   r   r   r   r   r$   )r%   s   "r   r&   r&   '  s°   € ÷ 7$ñ 7$Ü
ð7$äœ#•ð7$ô œœs¤H¬S¥M´7¼3ÄÄcÌ8ÔTWÍ=ÐFXÕ@YÐ;YÕ3ZÐZÕ[Õ\ð7$ô œnÕ-ð	7$ô
 œE¤,´Ð"3Õ4Õ5ð7$ô ”uœS¤'˜\Õ*Õ+ð7$ô ”Eœ$¤˜)Õ$Õ%ñ7$r   c                óx   € \        V 3RVRVRVRVRVRV/VB p\        VP                  P                  4       4      # )aí  Get the list of available splits for a particular config and dataset.

Args:
    path (`str`): path to the dataset repository. Can be either:

        - a local path to the dataset directory containing the data files,
            e.g. `'./dataset/squad'`
        - a dataset identifier on the Hugging Face Hub (list all available datasets and ids with [`huggingface_hub.list_datasets`]),
            e.g. `'rajpurkar/squad'`, `'nyu-mll/glue'` or``'openai/webtext'`
    config_name (`str`, *optional*):
        Defining the name of the dataset configuration.
    data_files (`str` or `Sequence` or `Mapping`, *optional*):
        Path(s) to source data file(s).
    download_config ([`DownloadConfig`], *optional*):
        Specific download configuration parameters.
    download_mode ([`DownloadMode`] or `str`, defaults to `REUSE_DATASET_IF_EXISTS`):
        Download/generate mode.
    revision ([`Version`] or `str`, *optional*):
        Version of the dataset to load.
        As datasets have their own git repository on the Datasets Hub, the default version "main" corresponds to their "main" branch.
        You can specify a different version than the default "main" by using a commit SHA or a git tag of the dataset repository.
    token (`str` or `bool`, *optional*):
        Optional string or boolean to use as Bearer token for remote files on the Datasets Hub.
        If `True`, or not specified, will get token from `"~/.huggingface"`.
    **config_kwargs (additional keyword arguments):
        Optional attributes for builder class which will override the attributes if supplied.

Example:

```py
>>> from datasets import get_dataset_split_names
>>> get_dataset_split_names('cornell-movie-review-data/rotten_tomatoes')
['train', 'validation', 'test']
```
r(   r   r   r   r   r    )r*   r#   rI   r7   )	r   r(   r   r   r   r   r    r+   rH   s	   &&&&&&&, r   Úget_dataset_split_namesrR   '  sp   € ôZ #Øñ	àð	ð ð	ð (ð		ð
 $ð	ð ð	ð ð	ð ñ	€Dô �—‘× Ñ Ó"Ó#Ð#r   )NNNNN)NNNN)NNNNNN)!Ú__doc__r4   Úcollections.abcr   r   Útypingr   r   Údownload.download_configr   Údownload.download_managerr   Ú#download.streaming_download_managerr   rH   r	   Úloadr
   r   r   Úutils.loggingr   Úutils.versionr   r   ÚloggerÚ
ValueErrorr   r-   r)   rC   r*   rR   r   r   r   Ú<module>r^      sm   ðñ  !ã 	ß -ß "å 4Ý 3Ý IÝ ÷ñ õ
 &Ý "ñ 
�HÓ	€ô	˜*ô 	÷@÷F?÷D;B÷|7÷t7$ñ 7$r   