tfds-nightly 4.9.9.dev202508180045__py3-none-any.whl → 4.9.9.dev202508200044__py3-none-any.whl

tensorflow_datasets/core/constants.py

@@ -28,10 +28,17 @@ SRC_BASE_URL = 'https://github.com/tensorflow/datasets/tree/master/'
 
 # Directory where to store processed datasets.
 # If modifying this, should also update `scripts/cli/build.py` `--data_dir`
-DATA_DIR: Final[str] = os.environ.get(
-    'TFDS_DATA_DIR',
-    os.path.join(os.path.expanduser('~'), 'tensorflow_datasets'),
-)
+
+
+def get_default_data_dir() -> str:
+  """Returns the TFDS default data directory."""
+  return os.environ.get(
+      'TFDS_DATA_DIR',
+      os.path.join(os.path.expanduser('~'), 'tensorflow_datasets'),
+  )
+
+
+DATA_DIR: Final[str] = get_default_data_dir()
 
 # Prefix of files / directories which aren't finished downloading / extracting.
 INCOMPLETE_PREFIX = 'incomplete.'

tensorflow_datasets/core/dataset_builder_test.py

@@ -27,7 +27,6 @@ import numpy as np
 import pytest
 import tensorflow as tf
 from tensorflow_datasets import testing
-from tensorflow_datasets.core import constants
 from tensorflow_datasets.core import dataset_builder
 from tensorflow_datasets.core import dataset_info
 from tensorflow_datasets.core import dataset_utils
@@ -831,32 +830,19 @@ class DatasetBuilderMultiDirTest(testing.TestCase):
 
   @classmethod
   def setUpClass(cls):
-    super(DatasetBuilderMultiDirTest, cls).setUpClass()
+    super().setUpClass()
     cls.builder = DummyDatasetSharedGenerator()
 
   def setUp(self):
-    super(DatasetBuilderMultiDirTest, self).setUp()
+    super().setUp()
     # Sanity check to make sure that no dir is registered
     file_utils.clear_registered_data_dirs()
-    # Create a new temp dir
-    self.other_data_dir = os.path.join(self.get_temp_dir(), "other_dir")
     # Overwrite the default data_dir (as files get created)
-
-    self._original_data_dir = constants.DATA_DIR
-    constants.DATA_DIR = os.path.join(self.get_temp_dir(), "default_dir")
-    self.default_data_dir = constants.DATA_DIR
-
-  def tearDown(self):
-    super(DatasetBuilderMultiDirTest, self).tearDown()
-    # Restore to the default `_registered_data_dir`
-    file_utils._registered_data_dir = set()
-    # Clear-up existing dirs
-    if tf.io.gfile.exists(self.other_data_dir):
-      tf.io.gfile.rmtree(self.other_data_dir)
-    if tf.io.gfile.exists(self.default_data_dir):
-      tf.io.gfile.rmtree(self.default_data_dir)
-    # Restore the orgininal data dir
-    constants.DATA_DIR = self._original_data_dir
+    default_data_dir = self.enter_context(testing.mock_default_data_dir())
+    # Create a new temp dir
+    self.other_data_dir = os.path.join(
+        os.path.dirname(default_data_dir), "other_dir"
+    )
 
   def test_load_data_dir(self):
     """Ensure that `tfds.load` also supports multiple data_dir."""

tensorflow_datasets/core/dataset_builders/adhoc_builder.py

@@ -85,6 +85,7 @@ from typing import Any, Dict
 
 from absl import logging
 from etils import epath
+from tensorflow_datasets.core import constants
 from tensorflow_datasets.core import dataset_builder
 from tensorflow_datasets.core import dataset_info
 from tensorflow_datasets.core import dataset_utils

tensorflow_datasets/core/utils/docs.py

@@ -29,9 +29,7 @@ class A:
 ```
 
 The functions exposed below are dummy decorators. This allows not having to load
-TensorFlow. The functions are monkey patched when needed in
-scripts/documentation/build_api_docs.py with actual TensorFlow documentation
-decorators.
+TensorFlow.
 """
 
 from typing import Any, TypeVar

tensorflow_datasets/core/utils/file_utils.py

@@ -156,23 +156,11 @@ def list_data_dirs(
     else:
       return [given_data_dir]
   else:
-    default_data_dir = get_default_data_dir(given_data_dir=given_data_dir)
+    default_data_dir = Path(constants.DATA_DIR)
     all_data_dirs = _REGISTERED_DATA_DIRS | {default_data_dir}
     return sorted(d.expanduser() for d in all_data_dirs)
 
 
-def get_default_data_dir(given_data_dir: epath.PathLike | None = None) -> Path:
-  """Returns the default data_dir."""
-  if given_data_dir:
-    data_dir = os.path.expanduser(given_data_dir)
-  elif 'TFDS_DATA_DIR' in os.environ:
-    data_dir = os.environ['TFDS_DATA_DIR']
-  else:
-    data_dir = constants.DATA_DIR
-
-  return Path(data_dir)
-
-
 def get_dataset_dir(
     data_dir: epath.PathLike,
     builder_name: str,
@@ -189,11 +177,11 @@ def get_dataset_dir(
 
 
 def get_data_dir_and_dataset_dir(
-    given_data_dir: epath.PathLike | None,
+    given_data_dir: PathLike | None,
     builder_name: str,
     config_name: str | None,
     version: version_lib.Version | str | None,
-) -> tuple[epath.Path, epath.Path]:
+) -> tuple[Path, Path]:
   """Returns the data and dataset directories for the given dataset.
 
   Args:
@@ -249,7 +237,7 @@ def get_data_dir_and_dataset_dir(
     return next(iter(dataset_dir_by_data_dir.items()))
 
   # No dataset found, use default directory
-  default_data_dir = get_default_data_dir()
+  default_data_dir = Path(constants.DATA_DIR)
   dataset_dir = get_dataset_dir(
       data_dir=default_data_dir,
       builder_name=builder_name,

tensorflow_datasets/core/utils/file_utils_test.py

@@ -33,7 +33,7 @@ _VERSION = '1.0.0'
 
 
 def test_default_data_dir():
-  data_dir = file_utils.get_default_data_dir(given_data_dir=None)
+  data_dir = constants.get_default_data_dir()
   assert data_dir
 
 

tensorflow_datasets/datasets/ble_wind_field/ble_wind_field_dataset_builder.py

@@ -76,7 +76,6 @@ class Builder(tfds.core.GeneratorBasedBuilder):
     zarr_array = zarr.open_array(
         store=gcsfs_store(f'{self.GCS_URL}/{self.GCS_FILENAME}'),
         mode='r',
-        synchronizer=zarr.ThreadSynchronizer(),
     )
 
     # During normal execution we don't expect `self.builder_config.num_fields`

tensorflow_datasets/datasets/multi_news/README.md

@@ -1,8 +1,13 @@
-Multi-News, consists of news articles and human-written summaries
-of these articles from the site newser.com.
-Each summary is professionally written by editors and
-includes links to the original articles cited.
-
-There are two features:
-  - document: text of news articles seperated by special token "|||||".
-  - summary: news summary.
+# Multi-News Dataset
+
+Multi-News consists of news articles and human-written summaries of these
+articles from the news site `newser.com`. Each summary is professionally written
+by editors and includes links to the original articles cited.
+
+This is the first large-scale dataset for multi-document summarization on news
+articles.
+
+Each record has two features:
+
+* `document`: Texts of news articles, separated by special token "|||||".
+* `summary`: Summary of the news.

tensorflow_datasets/datasets/multi_news/TAGS.txt

@@ -0,0 +1,6 @@
+content.data-type.text # Contains text data.
+content.subject.news # Relates to news.
+content.language.en # Contains text in language English / en.
+ml.task.abstractive-text-summarization # Relates to Abstractive Text Summarization, a machine learning task.
+ml.task.natural-language-understanding # Relates to Natural Language Understanding, a machine learning task.
+ml.task.text-summarization # Relates to Text Summarization, a machine learning task.

tensorflow_datasets/datasets/multi_news/checksums.tsv

@@ -1,6 +1,6 @@
-https://huggingface.co/datasets/alexfabbri/multi_news/raw/main/data/test.src.cleaned	133	d04c4581d52321a30c246d2caa72853ee7f28c6b7a3985ee436f54c4bc264315	test.src.cleaned
-https://huggingface.co/datasets/alexfabbri/multi_news/raw/main/data/test.tgt	132	afba4aa26d95bb557c0eaa0cb8f7495af2104f1e43f4b5f9ef429b8752477abd	test.tgt
-https://huggingface.co/datasets/alexfabbri/multi_news/raw/main/data/train.src.cleaned	134	75f87b786ff1982bf1bd5803c6a7377d1834b81956ac680a6955789ba047cc0b	train.src.cleaned
-https://huggingface.co/datasets/alexfabbri/multi_news/raw/main/data/train.tgt	133	9f1e9b290a6aae1aa67bd5b361c934ee9db32486e5cd97d83184c097ef8b27e5	train.tgt
-https://huggingface.co/datasets/alexfabbri/multi_news/raw/main/data/val.src.cleaned	133	8df3ef6bd1882094de8120fa635c3abf758e10427f81f306aaa4786df7b57861	val.src.cleaned
-https://huggingface.co/datasets/alexfabbri/multi_news/raw/main/data/val.tgt	132	9c0377a443ea92b17449f7df17f1cdfa7c7ebbfe3a45f2f8cd7b3e0ffb47b1df	val.tgt
+https://huggingface.co/datasets/alexfabbri/multi_news/resolve/main/data/test.src.cleaned	68999509	138d3ac2dc899cbcd2e3745aaa94d1c1db55fb7058d9df4ba3ef2dac05a3a186	test.src.cleaned
+https://huggingface.co/datasets/alexfabbri/multi_news/resolve/main/data/test.tgt	7309099	fa97cf91a62ae82a0af6da88f2ddf8e06eb4e3b90f7971d8e0c516436518fae3	test.tgt
+https://huggingface.co/datasets/alexfabbri/multi_news/resolve/main/data/train.src.cleaned	547512283	627781c8ce55d528fcdacd495db45583a915e2d24b7983b0a5a6693ede933bb1	train.src.cleaned
+https://huggingface.co/datasets/alexfabbri/multi_news/resolve/main/data/train.tgt	58793912	e9e82b8f413b0f1ed4eb7c883f93bb744f829c218c1608b6ba7615d687d07121	train.tgt
+https://huggingface.co/datasets/alexfabbri/multi_news/resolve/main/data/val.src.cleaned	66875522	f0a43902da366eea2b882e39ddd4c0975ad44aba6b61095a2ea90362e9e2bb65	val.src.cleaned
+https://huggingface.co/datasets/alexfabbri/multi_news/resolve/main/data/val.tgt	7295302	bb08a078e0cb2b8ca9cc0fe3bfbe9d4098dee706bd00eb97449155e41b880157	val.tgt

tensorflow_datasets/datasets/multi_news/multi_news_dataset_builder.py

@@ -19,8 +19,9 @@ from etils import epath
 import tensorflow_datasets.public_api as tfds
 
 _URL_PATH = (
-    "https://huggingface.co/datasets/alexfabbri/multi_news/raw/main/data/"
+    "https://huggingface.co/datasets/alexfabbri/multi_news/resolve/main/data/"
 )
+_LICENSE = "For non-commercial research and educational purposes only"
 
 
 _DOCUMENT = "document"
@@ -30,7 +31,12 @@ _SUMMARY = "summary"
 class Builder(tfds.core.GeneratorBasedBuilder):
   """DatasetBuilder for multi_news dataset."""
 
-  VERSION = tfds.core.Version("2.0.0")
+  VERSION = tfds.core.Version("2.1.0")
+  RELEASE_NOTES = {
+      "1.0.0": "Initial release.",
+      "2.0.0": "Update the dataset with valid URLs.",
+      "2.1.0": "Update the dataset with cleaned URLs.",
+  }
 
   def _info(self) -> tfds.core.DatasetInfo:
     """Returns the dataset metadata."""
@@ -40,6 +46,7 @@ class Builder(tfds.core.GeneratorBasedBuilder):
         ),
         supervised_keys=(_DOCUMENT, _SUMMARY),
         homepage="https://github.com/Alex-Fabbri/Multi-News",
+        license=_LICENSE,
     )
 
   def _split_generators(self, dl_manager: tfds.download.DownloadManager):

tensorflow_datasets/public_api.py

@@ -27,7 +27,7 @@ from tensorflow_datasets.core import deprecated
 from tensorflow_datasets.core import download
 from tensorflow_datasets.core import features
 from tensorflow_datasets.core import folder_dataset
-from tensorflow_datasets.core import transform  # pylint: disable=unused-import
+from tensorflow_datasets.core import transform
 from tensorflow_datasets.core import visualization
 from tensorflow_datasets.core.as_dataframe import as_dataframe
 from tensorflow_datasets.core.dataset_utils import as_numpy

tensorflow_datasets/scripts/cli/cli_utils.py

@@ -197,7 +197,7 @@ class PathOptions:
   """
 
   data_dir: epath.Path = simple_parsing.field(
-      default=epath.Path(constants.DATA_DIR)
+      default=epath.Path(constants.get_default_data_dir())
   )
   download_dir: epath.Path | None = None
   extract_dir: epath.Path | None = None

tensorflow_datasets/testing/__init__.py

@@ -50,6 +50,7 @@ if typing.TYPE_CHECKING:
   from tensorflow_datasets.testing.test_utils import enable_gcs_access
   from tensorflow_datasets.testing.test_utils import fake_examples_dir
   from tensorflow_datasets.testing.test_utils import make_tmp_dir
+  from tensorflow_datasets.testing.test_utils import mock_default_data_dir
   from tensorflow_datasets.testing.test_utils import mock_kaggle_api
   from tensorflow_datasets.testing.test_utils import MockFs
   from tensorflow_datasets.testing.test_utils import rm_tmp_dir
@@ -84,6 +85,7 @@ _API = {
     # TODO(afrozm): rm from here and add as methods to TestCase
     "make_tmp_dir": "tensorflow_datasets.testing.test_utils",
     "mock_data": "tensorflow_datasets.testing.mocking",
+    "mock_default_data_dir": "tensorflow_datasets.testing.test_utils",
     "mock_kaggle_api": "tensorflow_datasets.testing.test_utils",
     "MockFs": "tensorflow_datasets.testing.test_utils",
     "MockPolicy": "tensorflow_datasets.testing.mocking",

tensorflow_datasets/testing/test_utils.py

@@ -33,6 +33,7 @@ from unittest import mock
 from etils import epath
 from etils import epy
 import numpy as np
+from tensorflow_datasets.core import constants
 from tensorflow_datasets.core import dataset_builder
 from tensorflow_datasets.core import dataset_collection_builder
 from tensorflow_datasets.core import dataset_info
@@ -884,3 +885,13 @@ def dummy_croissant_file(
     croissant_file.write_text(json.dumps(dummy_metadata.to_json(), indent=2))
 
     yield croissant_file
+
+
+@contextlib.contextmanager
+def mock_default_data_dir() -> Iterator[str]:
+  """Mocks the `constants.DATA_DIR`."""
+  with tempfile.TemporaryDirectory() as tempdir:
+    tmp_data_dir = os.path.join(tempdir, 'default_dir')
+    os.makedirs(tmp_data_dir)
+    constants.DATA_DIR = tmp_data_dir
+    yield tmp_data_dir

{tfds_nightly-4.9.9.dev202508180045.dist-info → tfds_nightly-4.9.9.dev202508200044.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: tfds-nightly
-Version: 4.9.9.dev202508180045
+Version: 4.9.9.dev202508200044
 Summary: tensorflow/datasets is a library of datasets ready to use with TensorFlow.
 Home-page: https://github.com/tensorflow/datasets
 Download-URL: https://github.com/tensorflow/datasets/tags

{tfds_nightly-4.9.9.dev202508180045.dist-info → tfds_nightly-4.9.9.dev202508200044.dist-info}/RECORD

@@ -4,7 +4,7 @@ tensorflow_datasets/conftest.py,sha256=95ocbFU_SvVgWHI7NVkH1wXDrb-OGZrd_ihiVVkpk
 tensorflow_datasets/import_public_api_test.py,sha256=NPjteyVJL2ZDPEznMWBpP6hHbCaWiaZPxOcgnyr-HqY,852
 tensorflow_datasets/import_test.py,sha256=6rtuyyIwF9QNPyu6c-s5t-aA0fKPy2R9ondIHJVOkhY,801
 tensorflow_datasets/import_without_tf_test.py,sha256=znenZUnnltG7Jh2-PhhMEl_APadgiz1qPXi5P3Z85xo,3459
-tensorflow_datasets/public_api.py,sha256=I2YpOEEw0uND1EujpL_Sa3TSgcz_hY_I4F_iTZe9A3c,3896
+tensorflow_datasets/public_api.py,sha256=omCZpyf4uc9jgFTEvZ35ws4S-nDqMY1Yd_IyQwG3aCs,3863
 tensorflow_datasets/setup_teardown.py,sha256=4qTNXhVE9nvp6U77HEX7_OJ49_eCTFJLmp3suWGiM6g,1450
 tensorflow_datasets/typing.py,sha256=UThdRvwKbnXQkllNBhMCVHmCaIhBLHZtxQtfl0TE8e8,1397
 tensorflow_datasets/version.py,sha256=Yid9O3W4SuoFxeA25B4U4gQnr0lhvGeQKMY3tQ_F6No,1114
@@ -59,12 +59,12 @@ tensorflow_datasets/core/as_dataframe.py,sha256=3-2ScAo2G6wwYWbz_w3Crb4QyBwcuIYh
 tensorflow_datasets/core/as_dataframe_test.py,sha256=cGgk3f9j87dDRA2EXedlYb11NpOLdew0dA_O0ZG-PLQ,2048
 tensorflow_datasets/core/beam_utils.py,sha256=0X2lE9ILqLWZe5Idg58-G5XtgITXEAxqVodDtCDo9Ro,5109
 tensorflow_datasets/core/beam_utils_test.py,sha256=5ZhntgG658uT5pF4kw_U5Epm8lu0tdg4cI-0viMItzg,2852
-tensorflow_datasets/core/constants.py,sha256=5mWPx8lo4VFd-_HS07JquFc_4ajWvLkpbpU1_2izA0k,2806
+tensorflow_datasets/core/constants.py,sha256=nSePbV_wWc5iio_knccDTXOAWhoStvocHEBZHQwUl84,2932
 tensorflow_datasets/core/dataset_builder.py,sha256=GMPEtJ3vcELXg5IvqgYHLjTxdomMzLNZV7rW8YBJg2E,80616
 tensorflow_datasets/core/dataset_builder_beam_test.py,sha256=d7UsYNsAIY4FcANAERLcVMDcajIpAi0uMfrnQoe4yv4,8386
 tensorflow_datasets/core/dataset_builder_notfdv_test.py,sha256=eIWlOZijQfopdze85EkbcPY1I8lFmEBnedcoUoOAnRQ,1346
 tensorflow_datasets/core/dataset_builder_read_test.py,sha256=QxodggixId7zmknhnC0hAYMcuLehWUODVPo7JvjYw9k,4571
-tensorflow_datasets/core/dataset_builder_test.py,sha256=Q2GlADkgd0hzHHPLdMalW1tyc00QPdPNzaLxR5oU4HQ,49257
+tensorflow_datasets/core/dataset_builder_test.py,sha256=rjijuAMBxn6bBQy7kVhgq-pWnbvMcV2UGKckVfYRfJk,48598
 tensorflow_datasets/core/dataset_collection_builder.py,sha256=9tvIWFL4gLFaDFnU_ioKaGGzPQshmACS64vagjTVzkE,7224
 tensorflow_datasets/core/dataset_collection_builder_test.py,sha256=m6H9Kxb-RHUiBEZXd6kyheoixlogJ3OwzixHM2jP6WA,3664
 tensorflow_datasets/core/dataset_info.py,sha256=jtkzrc0Jw5BnLnbR18hvPwlzzj-86Rib_9eHlAehYa8,52636
@@ -139,7 +139,7 @@ tensorflow_datasets/core/data_sources/parquet.py,sha256=0QmGVlGm4gIVOCANP0U-iDpG
 tensorflow_datasets/core/data_sources/python.py,sha256=qUCItHkomXP3OuH8VaOOCchHIoYzYsuEoJsjPiOJM0w,1452
 tensorflow_datasets/core/data_sources/python_test.py,sha256=O3yqMPx40JlHN0uFfZPNLoV6s8DdEgYeRPtqveqRiJ0,1736
 tensorflow_datasets/core/dataset_builders/__init__.py,sha256=StTA3euephqDZdpTzJQgfWNqB5inZosrAhaWg2BOeio,1945
-tensorflow_datasets/core/dataset_builders/adhoc_builder.py,sha256=QVE8wWGPOgILPTC27Q28QZ3KIi5N64OGOfKpTq4W4_0,9216
+tensorflow_datasets/core/dataset_builders/adhoc_builder.py,sha256=1a-5hVjf9t24SD9fWzDDuKoOrA-Vmydf5QxvU7ap-sI,9263
 tensorflow_datasets/core/dataset_builders/adhoc_builder_test.py,sha256=yhRwrznK78MvHeWGRggnMTiyx_SlR1z30iD5VU3Gweo,13096
 tensorflow_datasets/core/dataset_builders/croissant_builder.py,sha256=XmnbIKiEN9OnY_RC8P7-83hbUfvtuJhbm24HfNFpiQs,17088
 tensorflow_datasets/core/dataset_builders/croissant_builder_test.py,sha256=42HpBr3pANVKiok4lcx6xqwf0fY7kma6WIGA8WehNSs,15072
@@ -247,13 +247,13 @@ tensorflow_datasets/core/utils/conversion_utils.py,sha256=V8kFmJu38op7-8ufZvEn0f
 tensorflow_datasets/core/utils/conversion_utils_test.py,sha256=rP_nbzQWzmZc_GXp3Y6TirwIGJqiQbF-JtY3B1tOuN0,5346
 tensorflow_datasets/core/utils/croissant_utils.py,sha256=9C8sScaEqSRsThqpQQc48GDNR1KFmDkS8hmKIvfZCB0,5181
 tensorflow_datasets/core/utils/croissant_utils_test.py,sha256=UdkAVYDTPm1L0zmMESScurV_IMA5K3qAKmL_umeMJZI,4497
-tensorflow_datasets/core/utils/docs.py,sha256=0AeGyhPXQc_DMsTX7ocbb8IuJv_RTrG7StYdfZiwSzU,1549
+tensorflow_datasets/core/utils/docs.py,sha256=nRE4d8wxYZav8AcT3dkiY0yplAJBx1hygWxkeKj_V7I,1412
 tensorflow_datasets/core/utils/dtype_utils.py,sha256=LvDe1hbgQem57RiqXjG9U5Roj8-1KkBMmSYTtgctx2U,3246
 tensorflow_datasets/core/utils/dtype_utils_test.py,sha256=-Qe2fQzDO5sjS36ZL-dY9w0tNrJXokIoSRFEQCv5dQA,3259
 tensorflow_datasets/core/utils/error_utils.py,sha256=lnquUa_VGRjn7-G_5x-PvWGgnnO6GAWsi9I7xeVuGxQ,3204
 tensorflow_datasets/core/utils/error_utils_test.py,sha256=Brt8X12ZlWCR4x3WLnSvq4X76eyU1yH3t5STPfAkxUs,2060
-tensorflow_datasets/core/utils/file_utils.py,sha256=vL-ulAVClrvkA71DvEvdGR2EdNmOR9Y9hNKUDwJ3Ll4,18534
-tensorflow_datasets/core/utils/file_utils_test.py,sha256=N-_jZlE73h2OqDxFmQJQ0cdb5a3FBilNjeP0iU3JMwQ,13438
+tensorflow_datasets/core/utils/file_utils.py,sha256=cyesb6JgcY5CNVMVB_wBOup8_36VXXQYgPutz-0ttuw,18152
+tensorflow_datasets/core/utils/file_utils_test.py,sha256=Pg7XQzocQv9NCXASm1C9YqfgvYruLRCSLgMIL2Y6MbA,13418
 tensorflow_datasets/core/utils/gcs_utils.py,sha256=8mBOgEepkah1Rw36F6DNIVhLzfXbR8iS8KMLQUM5sPk,5154
 tensorflow_datasets/core/utils/gcs_utils_test.py,sha256=Ig8S37AvFG2g7kNjYxqgmqNKlLPeXt31XD7RY4UzsDg,2578
 tensorflow_datasets/core/utils/huggingface_utils.py,sha256=NeYaUoO3vIFH8M0hZ8k4w7AchFZJIGsuV1XwKJVttfw,5325
@@ -507,7 +507,7 @@ tensorflow_datasets/datasets/ble_wind_field/CITATIONS.bib,sha256=OXFyckl5Jz_2ssa
 tensorflow_datasets/datasets/ble_wind_field/README.md,sha256=dB1Gd0ocVxHb4lf1JqxioVsLZeK-wCX91LPboFGyXQo,1061
 tensorflow_datasets/datasets/ble_wind_field/TAGS.txt,sha256=i6oI1TaRyQJiq7iTga-YlR5ZTz9oHCt8dyNS4dTsapo,26
 tensorflow_datasets/datasets/ble_wind_field/__init__.py,sha256=eFqnTjU7s5iubj6XcKoU8lZUSHecOdnebZFm1vTkjbA,612
-tensorflow_datasets/datasets/ble_wind_field/ble_wind_field_dataset_builder.py,sha256=0iQ70Iva2ziS18NNDHPiPvt3-LjixSTqBzoS1-_nPJ0,4812
+tensorflow_datasets/datasets/ble_wind_field/ble_wind_field_dataset_builder.py,sha256=EQ1U0GZpSl2wbXysnI7lWxwqmYRbfgw2e0Rad9xQ0pI,4764
 tensorflow_datasets/datasets/ble_wind_field/ble_wind_field_dataset_builder_test.py,sha256=j9bp0NEpMFPQmikgErlAvOa-Qu7qveFkWqF5z4TVYdg,1851
 tensorflow_datasets/datasets/ble_wind_field/checksums.tsv,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 tensorflow_datasets/datasets/blimp/CITATIONS.bib,sha256=jZ3PtuS5XjQ8FQO4oVOXFwivk00o11YjMnntK5xjLU4,297
@@ -931,11 +931,11 @@ tensorflow_datasets/datasets/mlqa/checksums.tsv,sha256=_lbjCALdPkQgy4EM4tyFPDusv
 tensorflow_datasets/datasets/mlqa/mlqa_dataset_builder.py,sha256=j629tSE41KnEo5rywqyCPZteA14xD2YsPPIrjxsawks,2813
 tensorflow_datasets/datasets/mlqa/mlqa_dataset_builder_test.py,sha256=qZXHcslBHUNAn-BRynUHouA_vclALLOubCWHpoIhPdc,1074
 tensorflow_datasets/datasets/multi_news/CITATIONS.bib,sha256=oRe0wDEh7EgfsT4OJJFpphYCDBmZyRVHuR1YkihYYl0,328
-tensorflow_datasets/datasets/multi_news/README.md,sha256=EiTJGxDz0t2iBVb4fJexEr3u6jTxc4NaAaS5mHqghW0,335
-tensorflow_datasets/datasets/multi_news/TAGS.txt,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+tensorflow_datasets/datasets/multi_news/README.md,sha256=s0XL9ddJL7oNJ9r7mSG8_Hdp95WlMWOnosfacw1kuek,469
+tensorflow_datasets/datasets/multi_news/TAGS.txt,sha256=OPDe1XqRiLYpvmXuPX2_aMaOKIXYsl562usmTEEqkwg,449
 tensorflow_datasets/datasets/multi_news/__init__.py,sha256=eFqnTjU7s5iubj6XcKoU8lZUSHecOdnebZFm1vTkjbA,612
-tensorflow_datasets/datasets/multi_news/checksums.tsv,sha256=T1iRT0w_VPEt_W0bwhIb8b-g3ZLigrmY1_nuIPnpOWU,978
-tensorflow_datasets/datasets/multi_news/multi_news_dataset_builder.py,sha256=ef0sBtL4B3_O_XWDpX-rzGTjCcRh623ca5wdRYE30jE,2776
+tensorflow_datasets/datasets/multi_news/checksums.tsv,sha256=S-8k82snl0zj1rjjO5LW7svXRNnDuWRc72qpIcBu6WA,1031
+tensorflow_datasets/datasets/multi_news/multi_news_dataset_builder.py,sha256=-ZOuQ7BfPN6_DkrUddcE2qm76eUpmlo8nHizd8DsstQ,3046
 tensorflow_datasets/datasets/multi_news/multi_news_dataset_builder_test.py,sha256=5amBMQ7PKbPLeZ2kiT18tEb_Z-CMS0DasTRT6goTjXQ,1259
 tensorflow_datasets/datasets/natural_instructions/CITATIONS.bib,sha256=tcQG5eEGL_wr_5MEnZ6Q_ce2oZm6InbbRKiFqee9g7I,412
 tensorflow_datasets/datasets/natural_instructions/README.md,sha256=mceGvviI62PO5mh59sYPP_9vuuwKo0g-m7LQilP1mBI,370
@@ -1990,7 +1990,7 @@ tensorflow_datasets/scripts/cli/build.py,sha256=uBR2mPo1YO1Of83zZ6A3m5NU0GhP0nJd
 tensorflow_datasets/scripts/cli/build_test.py,sha256=K7ho7IRtAty1ZNPLj33Th_nZajYBkXRLA4u3dbElQmo,10615
 tensorflow_datasets/scripts/cli/builder_templates.py,sha256=99SvH3skigkc2Qg737BV2OzhXL_Rgu4az8eVHsxKCLk,7985
 tensorflow_datasets/scripts/cli/builder_templates_test.py,sha256=HBNB-v2zlImKULPI8Webs9hXCkeFmWT29urxav-tDe8,2062
-tensorflow_datasets/scripts/cli/cli_utils.py,sha256=ddZ06qZ2FCQ8J80HqbT3pCIzEpo-2HuqVnsupJoUZCU,13420
+tensorflow_datasets/scripts/cli/cli_utils.py,sha256=1MjBd1thfqgUK6iHMV9MG-1ny4ZZUuyBgcRPFnApDgY,13434
 tensorflow_datasets/scripts/cli/conftest.py,sha256=3PNh_BbR013G4HyLAZOleUXsQ9mICrD03NaKwdHFMXs,1291
 tensorflow_datasets/scripts/cli/convert_format.py,sha256=ZS7CmWJ-oZ0usO4TB8GKDj9TBJ5MyEO0I9QLRg7eQOw,3797
 tensorflow_datasets/scripts/cli/convert_format_utils.py,sha256=U_q5WVgMNrjBkOc166U4Y_eca5KOS3Xb3jSDjp4XdK4,29078
@@ -2005,8 +2005,6 @@ tensorflow_datasets/scripts/deployment/copy_dataset_info_files.py,sha256=uLuvwOW
 tensorflow_datasets/scripts/deployment/export_community_datasets.py,sha256=h6IEu7Y19cl6adiT3ve5HUbKb5hUuysKdMqIgRc8CcM,3643
 tensorflow_datasets/scripts/deployment/export_community_datasets_test.py,sha256=eIE0dR9KGkXWX2kcanfN6rKdLYSsFb5QCVXfe7nd7gI,3234
 tensorflow_datasets/scripts/documentation/__init__.py,sha256=Z8UWkv0wbzS4AzaLgSpYVGApYv5j57RWY0vN5Z553BQ,613
-tensorflow_datasets/scripts/documentation/build_api_docs.py,sha256=NXbW1ijbIUogxpWFDaSngw8_84TJuFv7C_Jr7hLxeyk,2893
-tensorflow_datasets/scripts/documentation/build_api_docs_test.py,sha256=m8_XuS_05NYaErMJeCQoqdrvKUFw-JKBi7wdDeqI1jA,2065
 tensorflow_datasets/scripts/documentation/build_catalog.py,sha256=SYJoNW-VxvL8xx85uYlFBwbr1k64HcmRBfxsj9-sdYA,8680
 tensorflow_datasets/scripts/documentation/build_catalog_test.py,sha256=qjnqK6lhBh-uNrjLQkEs3AbKFBo5uz_sxhhdT4ibOyA,2532
 tensorflow_datasets/scripts/documentation/build_community_catalog.py,sha256=gh84xnKbL_ndR4GGbgBNLJ0nxjFwiAPLuhUvzeKPZAo,19902
@@ -2127,7 +2125,7 @@ tensorflow_datasets/summarization/media_sum/__init__.py,sha256=ascERqiYc3QEf0hqG
 tensorflow_datasets/summarization/media_sum/media_sum.py,sha256=CIhR_cfQb1aEfu9BTCdsMPe6TC_okOW_cwNR76wqrFo,877
 tensorflow_datasets/summarization/summscreen/__init__.py,sha256=ADxohrpUPJjug4r2kGCCJEWZzVD4s2S0smqLfjkc8YY,718
 tensorflow_datasets/summarization/summscreen/summscreen.py,sha256=DfwGr3vsRhOC62ODJ1Sp7-v219bPjJ93KK043YReV7I,884
-tensorflow_datasets/testing/__init__.py,sha256=aSwY_kciK-EZXp1D_JRkuuCJwtbFljGZ72c9YNB6yfE,6049
+tensorflow_datasets/testing/__init__.py,sha256=I19SrK6rO0lD3w-ZnuiG1pek3t07up0SXGopfDBNsBk,6195
 tensorflow_datasets/testing/dataset_builder_testing.py,sha256=t95l1N8exM7G7qdPMHe1oOlF0E7KpptJBNivLXA3Tqo,25155
 tensorflow_datasets/testing/dataset_builder_testing_test.py,sha256=Nf7Ykg5bY5o9ZatQKrRJhr-qGTtNKle4aZph4rt72i4,1283
 tensorflow_datasets/testing/dataset_collection_builder_testing.py,sha256=tUv2l53rc9GEo4sWvM9OP9r-Ze54dcDakeLQBMS7yos,4825
@@ -2138,7 +2136,7 @@ tensorflow_datasets/testing/mocking.py,sha256=4mIq0ngxfs3w0hFlosGOSTp-mAQVfBfoFw
 tensorflow_datasets/testing/mocking_test.py,sha256=9DMkxcQw_dZTKULNHiKv91e0VcBsUTa6FIhUOLvJKls,13796
 tensorflow_datasets/testing/test_case.py,sha256=_H_M3pp6Vp3dbtPyVy5Um7X8S4V4EKPLrao1mbS2IdU,2554
 tensorflow_datasets/testing/test_case_in_context.py,sha256=7YrdTI_rqR01Q-ToVqewIm1OKDwvxIidPhaffYmjP1E,1872
-tensorflow_datasets/testing/test_utils.py,sha256=sQTTXa8YHPXml514vayxiu_E6qHFQ_1Maizy3OR0J8Y,26736
+tensorflow_datasets/testing/test_utils.py,sha256=TguQfyqwVkOAPjI5DLwKvFDnqDwvmI2Mg9MTS0RyFGg,27094
 tensorflow_datasets/testing/test_utils_test.py,sha256=nL2niozCO5Gh4cWPWbDW5_w3w-mHRYZEQmmfej2fpjY,9576
 tensorflow_datasets/testing/version_test.py,sha256=fNMSX1FSNs_66MHcRGAWzoPZWJ-sAvmc-rceKXGK-uM,2791
 tensorflow_datasets/text/__init__.py,sha256=_PtJTw2LQqgxFNVeBCEXrLGF2qg5NNOiXTW9oKZR_ZA,5319
@@ -2474,10 +2472,10 @@ tensorflow_datasets/vision_language/wit/wit_test.py,sha256=PXS8DMNW-MDrT2p5oy4Ic
 tensorflow_datasets/vision_language/wit_kaggle/__init__.py,sha256=vGwSGeM8WE4Q-l0-eEE1sBojmk6YT0l1OO60AWa4Q40,719
 tensorflow_datasets/vision_language/wit_kaggle/wit_kaggle.py,sha256=q-vX_FBzIwsFxL4sY9vuyQ3UQD2PLM4yhUR4U6l-qao,16903
 tensorflow_datasets/vision_language/wit_kaggle/wit_kaggle_test.py,sha256=ZymHT1NkmD-pUnh3BmM3_g30c5afsWYnmqDD9dVyDSA,1778
-tfds_nightly-4.9.9.dev202508180045.dist-info/licenses/AUTHORS,sha256=nvBG4WwfgjuOu1oZkuQKw9kg7X6rve679ObS-YDDmXg,309
-tfds_nightly-4.9.9.dev202508180045.dist-info/licenses/LICENSE,sha256=z8d0m5b2O9McPEK1xHG_dWgUBT6EfBDz6wA0F7xSPTA,11358
-tfds_nightly-4.9.9.dev202508180045.dist-info/METADATA,sha256=QlYSV8mZ9b4fKn4t6GpWIFsRjq1eTSh7JDcPe08a2zc,11291
-tfds_nightly-4.9.9.dev202508180045.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-tfds_nightly-4.9.9.dev202508180045.dist-info/entry_points.txt,sha256=eHEL7nF5y1uCY2FgkuYIdE062epJXlAQTSdq89px4p4,73
-tfds_nightly-4.9.9.dev202508180045.dist-info/top_level.txt,sha256=bAevmk9209s_oxVZVlN6hSDIVS423qrMQvmcWSvW4do,20
-tfds_nightly-4.9.9.dev202508180045.dist-info/RECORD,,
+tfds_nightly-4.9.9.dev202508200044.dist-info/licenses/AUTHORS,sha256=nvBG4WwfgjuOu1oZkuQKw9kg7X6rve679ObS-YDDmXg,309
+tfds_nightly-4.9.9.dev202508200044.dist-info/licenses/LICENSE,sha256=z8d0m5b2O9McPEK1xHG_dWgUBT6EfBDz6wA0F7xSPTA,11358
+tfds_nightly-4.9.9.dev202508200044.dist-info/METADATA,sha256=2wzC_C5TtacBcMmQdB8Qpf7CZSR7VUGMAzb3jtKy0Jo,11291
+tfds_nightly-4.9.9.dev202508200044.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+tfds_nightly-4.9.9.dev202508200044.dist-info/entry_points.txt,sha256=eHEL7nF5y1uCY2FgkuYIdE062epJXlAQTSdq89px4p4,73
+tfds_nightly-4.9.9.dev202508200044.dist-info/top_level.txt,sha256=bAevmk9209s_oxVZVlN6hSDIVS423qrMQvmcWSvW4do,20
+tfds_nightly-4.9.9.dev202508200044.dist-info/RECORD,,

tensorflow_datasets/scripts/documentation/build_api_docs.py

@@ -1,91 +0,0 @@
-# coding=utf-8
-# Copyright 2025 The TensorFlow Datasets Authors.
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-"""generates api_docs for tensorflow_datasets."""
-import os
-
-from absl import app
-from absl import flags
-from absl import logging
-
-import tensorflow_datasets as tfds
-# Testing is lazily imported, so we first force its import.
-from tensorflow_datasets.testing import *  # pylint: disable=wildcard-import
-from tensorflow_docs.api_generator import generate_lib
-
-from tensorflow.tools.docs import doc_controls  # pylint: disable=g-direct-tensorflow-import
-
-# Force the definition of all documentation decorators declared in
-# third_party/py/tensorflow_datasets/core/utils/docs.py to TensorFlow decorators
-try:
-  tfds.core.utils.docs.deprecated = doc_controls.set_deprecated
-  tfds.core.utils.docs.doc_private = doc_controls.doc_private
-  tfds.core.utils.docs.do_not_doc = doc_controls.do_not_generate_docs
-  # Same as `do_not_doc`, but also applied to children
-  tfds.core.utils.docs.do_not_doc_inheritable = (
-      doc_controls.do_not_doc_inheritable
-  )
-  # Document the parent, but not the children
-  tfds.core.utils.docs.do_not_doc_in_subclasses = (
-      doc_controls.do_not_doc_in_subclasses
-  )
-except AttributeError:
-  logging.info("Could not set TensorFlow documentation decorators.")
-
-FLAGS = flags.FLAGS
-
-flags.DEFINE_string(
-    "output_dir", "/tmp/datasets_api", "Where to output the docs"
-)
-flags.DEFINE_string(
-    "code_url_prefix",
-    "https://github.com/tensorflow/datasets/tree/master/tensorflow_datasets/",
-    "The url prefix for links to code.",
-)
-
-flags.DEFINE_bool(
-    "search_hints", True, "Include metadata search hints in the generated files"
-)
-
-flags.DEFINE_string(
-    "site_path", "datasets/api_docs/python", "Path prefix in the _toc.yaml"
-)
-
-
-def execute(output_dir, code_url_prefix, search_hints, site_path):
-  """Builds API docs for tensorflow_datasets."""
-  doc_generator = generate_lib.DocGenerator(
-      root_title="TensorFlow Datasets",
-      py_modules=[("tfds", tfds)],
-      base_dir=os.path.dirname(tfds.__file__),
-      search_hints=search_hints,
-      code_url_prefix=code_url_prefix,
-      site_path=site_path,
-  )
-
-  doc_generator.build(output_dir)
-
-
-def main(unused_argv):
-  execute(
-      FLAGS.output_dir,
-      FLAGS.code_url_prefix,
-      FLAGS.search_hints,
-      FLAGS.site_path,
-  )
-
-
-if __name__ == "__main__":
-  app.run(main)

tensorflow_datasets/scripts/documentation/build_api_docs_test.py

@@ -1,65 +0,0 @@
-# coding=utf-8
-# Copyright 2025 The TensorFlow Datasets Authors.
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-"""Smoke Test for docs generation."""
-
-import os
-import shutil
-import tempfile
-
-from absl.testing import absltest
-
-from tensorflow_datasets.core.utils import docs
-from tensorflow_datasets.scripts.documentation import build_api_docs
-
-
-class BuildDocsTest(absltest.TestCase):
-
-  def setUp(self):
-    super(BuildDocsTest, self).setUp()
-    self.workdir = tempfile.mkdtemp()
-    if os.path.exists(self.workdir):
-      shutil.rmtree(self.workdir)
-    os.makedirs(self.workdir)
-
-  def test_api_gen(self):
-    build_api_docs.execute(
-        output_dir=self.workdir,
-        code_url_prefix="",
-        search_hints=True,
-        site_path="datasets/api_docs/python",
-    )
-
-    # Check that the "defined in" section is working
-    with open(os.path.join(self.workdir, "tfds.md")) as f:
-      content = f.read()
-    self.assertIn("__init__.py", content)
-
-    # Check that the `testing` folder is generated.
-    with open(os.path.join(self.workdir, "tfds/testing.md")) as f:
-      content = f.read()
-    self.assertIn("__init__.py", content)
-
-  def test_tensorflow_decorators_are_used_and_not_dummy_decorator(self):
-    self.assertEqual(docs.deprecated.__name__, "set_deprecated")
-    self.assertEqual(docs.doc_private.__name__, "doc_private")
-    self.assertEqual(docs.do_not_doc.__name__, "do_not_generate_docs")
-    self.assertEqual(
-        docs.do_not_doc_inheritable.__name__, "do_not_doc_inheritable"
-    )
-
-
-if __name__ == "__main__":
-  absltest.main()