def builder_cls(name: str) -> Type[dataset_builder.DatasetBuilder]:
"""Fetches a `tfds.core.DatasetBuilder` class by string name.
Args:
name: `str`, the registered name of the `DatasetBuilder` (the class name
as camel or snake case: `MyDataset` or `my_dataset`).
Returns:
A `tfds.core.DatasetBuilder` class.
Raises:
DatasetNotFoundError: if `name` is unrecognized.
"""
ds_name, kwargs = naming.parse_builder_name_kwargs(name)
if kwargs:
raise ValueError(
'`builder_cls` only accept the `dataset_name` without config, '
f"version or arguments. Got: name='{name}', kwargs={kwargs}")
try:
if ds_name.namespace:
# `namespace:dataset` are loaded from the community register
if visibility.DatasetType.COMMUNITY_PUBLIC.is_available():
return community.community_register.builder_cls(ds_name)
else:
raise ValueError(
f'Cannot load {ds_name} when community datasets are disabled'
)
else:
cls = registered.imported_builder_cls(str(ds_name))
cls = typing.cast(Type[dataset_builder.DatasetBuilder], cls)
return cls
except registered.DatasetNotFoundError as e:
_reraise_with_list_builders(e, name=ds_name) # pytype: disable=bad-return-type
def builder_cls(name: str) -> Type[dataset_builder.DatasetBuilder]:
"""Fetches a `tfds.core.DatasetBuilder` class by string name.
Args:
name: `str`, the registered name of the `DatasetBuilder` (the class name
as camel or snake case: `MyDataset` or `my_dataset`).
Returns:
A `tfds.core.DatasetBuilder` class.
Raises:
DatasetNotFoundError: if `name` is unrecognized.
"""
ns_name, builder_name, kwargs = naming.parse_builder_name_kwargs(name)
if kwargs:
raise ValueError(
'`builder_cls` only accept the `dataset_name` without config, '
f"version or arguments. Got: name='{name}', kwargs={kwargs}")
if ns_name:
raise ValueError(
f'Namespaces not supported for `builder_cls`. Got: {ns_name}')
# Imported datasets
try:
cls = registered.imported_builder_cls(builder_name)
cls = typing.cast(Type[dataset_builder.DatasetBuilder], cls)
return cls
except registered.DatasetNotFoundError as e:
_reraise_with_list_builders(e,
ns_name=ns_name,
builder_name=builder_name)
def _get_default_config_name(name: str) -> Optional[str]:
"""Returns the default config of the given dataset, None if not found."""
# Search for the DatasetBuilder generation code
try:
cls = registered.imported_builder_cls(name)
cls = typing.cast(Type[dataset_builder.DatasetBuilder], cls)
except registered.DatasetNotFoundError:
return None
# If code found, return the default config
if cls.BUILDER_CONFIGS:
return cls.BUILDER_CONFIGS[0].name
return None
def _get_default_config_name(builder_dir: str, name: str) -> Optional[str]:
"""Returns the default config of the given dataset, None if not found."""
# Search for the DatasetBuilder generation code
try:
cls = registered.imported_builder_cls(name)
cls = typing.cast(Type[dataset_builder.DatasetBuilder], cls)
except registered.DatasetNotFoundError:
pass
else:
# If code found, return the default config
if cls.BUILDER_CONFIGS:
return cls.BUILDER_CONFIGS[0].name
# Otherwise, try to load default config from common metadata
return dataset_builder.load_default_config_name(utils.as_path(builder_dir))
def _get_default_config_name(builder_dir: str, name: str) -> Optional[str]:
"""Returns the default config of the given dataset, None if not found."""
# Search for the DatasetBuilder generation code
try:
# Warning: The registered dataset may not match the files (e.g. if
# the imported datasets has the same name as the generated files while
# being 2 differents datasets)
cls = registered.imported_builder_cls(name)
cls = typing.cast(Type[dataset_builder.DatasetBuilder], cls)
except (registered.DatasetNotFoundError, PermissionError):
pass
else:
# If code found, return the default config
if cls.BUILDER_CONFIGS:
return cls.BUILDER_CONFIGS[0].name
# Otherwise, try to load default config from common metadata
return dataset_builder.load_default_config_name(utils.as_path(builder_dir))
