diff options
Diffstat (limited to 'sci-libs/datasets')
| -rw-r--r-- | sci-libs/datasets/Manifest | 6 | ||||
| -rw-r--r-- | sci-libs/datasets/datasets-2.18.0-r1.ebuild | 86 | ||||
| -rw-r--r-- | sci-libs/datasets/datasets-2.19.2.ebuild | 194 | ||||
| -rw-r--r-- | sci-libs/datasets/files/datasets-2.17.1-tests.patch | 364 | ||||
| -rw-r--r-- | sci-libs/datasets/files/datasets-2.19.2-tests.patch | 23 |
5 files changed, 220 insertions, 453 deletions
diff --git a/sci-libs/datasets/Manifest b/sci-libs/datasets/Manifest index e6f86a2e3a2d..4f23d13dee02 100644 --- a/sci-libs/datasets/Manifest +++ b/sci-libs/datasets/Manifest @@ -1,4 +1,4 @@ -AUX datasets-2.17.1-tests.patch 13819 BLAKE2B 7581ae4ad336f8f8ecf6b47defa5b2d33da246d60e7159136803ceb4ad20a4f66025ec7aa3a1910ad4a79408ba7cb0de49621d56d13eaf64958c6770e1dc02e2 SHA512 96d344ef84cdc4cd1ee1cf3dd51be0ffb499839a74ba26bfb3aec3b87b459ff81c9c7f89d1704eb628f1a6f81e0a5f6770fd7316e5b0cdd3ad0df919254ed625 -DIST datasets-2.18.0.gh.tar.gz 2169179 BLAKE2B 8a0daa0e8995b3fa5480d8aa892a26d1b6ba90f252ef7c7ca62f4afc2efa61a8ed2efbf48a40381f07178b826bde62af0f0cb8cbf80d470d5d4dfb1ba25f6cb8 SHA512 b1fb0e6636417683fa79679286505b921a7ba00b1cabd6a23e60d5804eb098527c5283058799a0776a7f1e93972fdbb948882f153a10557bcc6b6b22ab861292 -EBUILD datasets-2.18.0-r1.ebuild 2386 BLAKE2B bd67e5ca2db08a13a41ad320c60ccf3b183d4ad38e92701d5b033b8a1d5477d57c1345a1ee6acea4e050266c64e2a5d44d8df2764a4bbe9a2d327a7b4b133181 SHA512 cba0ac26dbd9ea7b038ecfb605573bce5915aa92cd780fbf47a1015f96920fe91bd4edc129307f4b9e9b7aec8ff6862ef5bfe5af38388878dd563a52df5a7b61 +AUX datasets-2.19.2-tests.patch 756 BLAKE2B d9bb33c2aa03f06bb42342da3bfefa0d916d7979c06725cf2c667df3d8ac4a03eb79e5129b6d0f7d232b4eb64a0cb993451e7da7661e692f50f8b8708aa8d8e2 SHA512 7ac8f060e6808b6d409508d7a9a8de4626d71b443db1df4e2489cdf3f61ab48e169ba336d8f8f6c78decb25c524ef5a291db0265813888a29c70661b04757d49 +DIST datasets-2.19.2.gh.tar.gz 2176600 BLAKE2B d02d43f7db0ce9a2220b332e5e2ab4de2648fa2b693dec703ae900b42d0089be1cf79270d4b8daeda841cccde6f60c93d6b2eee15bc652e4f60e08a6f3fade82 SHA512 7593463174b7308c45e1fd50190942e94ac63ff7bd0ff54a8a09496d041f69fa43eaa7e4e7372965deaafdb7843d8a86aeb0db1a75efe0c3da37fcf064521c16 +EBUILD datasets-2.19.2.ebuild 10626 BLAKE2B 35d3f0629a491eb1ee76f9d224fa36a412b62f28c99d00d4c62dd9f0c000b30b8762feb635c69c8213fc776a79bb2d17fb1bfdd28d79bdc2170121ac3ac40d4b SHA512 29cc2049c49611b2d472123b98cbc64fcee1f5e7a4d918d4d756dd337be6aa5cb3bc5a8f9e0ed55a8838dcfa68196a55b8c0bf61617d0eab1576eefdcb788226 MISC metadata.xml 379 BLAKE2B 48ebb9e7bfa8b58b0d15b82c4146def465e08cf3212ab4af04129d09c153b67b00d0fa05b94d6af54f643ec3a202f2335d3254b966f49d1394d3c7b9e5da56a5 SHA512 99560decfaa0e438980f372d99257695e9ca9585167d9aba091e0b775c2f8384657ddc017841c8f06f8b568017a54fb9e31da736f3c875da717e154cdce876d1 diff --git a/sci-libs/datasets/datasets-2.18.0-r1.ebuild b/sci-libs/datasets/datasets-2.18.0-r1.ebuild deleted file mode 100644 index d16c3e2459de..000000000000 --- a/sci-libs/datasets/datasets-2.18.0-r1.ebuild +++ /dev/null @@ -1,86 +0,0 @@ -# Copyright 2023-2024 Gentoo Authors -# Distributed under the terms of the GNU General Public License v2 - -EAPI=8 - -DISTUTILS_USE_PEP517=setuptools -PYTHON_COMPAT=( python3_{10..12} ) -DISTUTILS_SINGLE_IMPL=1 -inherit distutils-r1 - -DESCRIPTION="Access and share datasets for Audio, Computer Vision, and NLP tasks" -HOMEPAGE=" - https://pypi.org/project/datasets/ -" -SRC_URI="https://github.com/huggingface/${PN}/archive/refs/tags/${PV}.tar.gz - -> ${P}.gh.tar.gz" -IUSE="test" - -LICENSE="Apache-2.0" -SLOT="0" -KEYWORDS="~amd64" - -RDEPEND=" - ${PYTHON_DEPS} - sci-libs/pytorch[${PYTHON_SINGLE_USEDEP}] - sci-libs/caffe2[${PYTHON_SINGLE_USEDEP},numpy] - $(python_gen_cond_dep ' - dev-python/absl-py[${PYTHON_USEDEP}] - dev-python/aiohttp[${PYTHON_USEDEP}] - dev-python/dill[${PYTHON_USEDEP}] - dev-python/filelock[${PYTHON_USEDEP}] - dev-python/fsspec[${PYTHON_USEDEP}] - dev-python/multiprocess[${PYTHON_USEDEP}] - dev-python/numpy[${PYTHON_USEDEP}] - dev-python/packaging[${PYTHON_USEDEP}] - dev-python/pandas[${PYTHON_USEDEP}] - dev-python/pyarrow[${PYTHON_USEDEP},parquet,snappy] - dev-python/pyyaml[${PYTHON_USEDEP}] - dev-python/requests[${PYTHON_USEDEP}] - dev-python/scikit-learn[${PYTHON_USEDEP}] - dev-python/tqdm[${PYTHON_USEDEP}] - dev-python/xxhash[${PYTHON_USEDEP}] - dev-python/zstandard[${PYTHON_USEDEP}] - sci-libs/huggingface_hub[${PYTHON_USEDEP}] - ') -" -DEPEND="${RDEPEND}" -BDEPEND="test? ( - $(python_gen_cond_dep ' - dev-python/absl-py[${PYTHON_USEDEP}] - dev-python/pytest-datadir[${PYTHON_USEDEP}] - dev-python/decorator[${PYTHON_USEDEP}] - dev-python/sqlalchemy[${PYTHON_USEDEP}] - sci-libs/jiwer[${PYTHON_USEDEP}] - sci-libs/seqeval[${PYTHON_USEDEP}] - ') -)" - -PATCHES=( - "${FILESDIR}"/${PN}-2.17.1-tests.patch -) - -distutils_enable_tests pytest - -src_prepare() { - distutils-r1_src_prepare - rm tests/packaged_modules/test_spark.py || die - rm tests/test_upstream_hub.py || die - sed -i -e \ - "/pyarrow_hotfix/d" \ - src/datasets/features/features.py || die - sed -i \ - -e "s:pytest.mark.integration:pytest.mark.skip():g" \ - tests/test_arrow_dataset.py \ - tests/test_fingerprint.py \ - tests/test_hf_gcp.py \ - tests/test_inspect.py \ - tests/test_iterable_dataset.py \ - tests/test_iterable_dataset.py \ - tests/test_load.py \ - tests/test_offline_util.py \ - tests/test_streaming_download_manager.py \ - tests/commands/test_test.py \ - tests/packaged_modules/test_cache.py \ - || die -} diff --git a/sci-libs/datasets/datasets-2.19.2.ebuild b/sci-libs/datasets/datasets-2.19.2.ebuild new file mode 100644 index 000000000000..73eed0dccf5f --- /dev/null +++ b/sci-libs/datasets/datasets-2.19.2.ebuild @@ -0,0 +1,194 @@ +# Copyright 2023-2024 Gentoo Authors +# Distributed under the terms of the GNU General Public License v2 + +EAPI=8 + +DISTUTILS_USE_PEP517=setuptools +PYTHON_COMPAT=( python3_{10..12} ) +DISTUTILS_SINGLE_IMPL=1 +inherit distutils-r1 + +DESCRIPTION="Access and share datasets for Audio, Computer Vision, and NLP tasks" +HOMEPAGE="https://pypi.org/project/datasets/" +SRC_URI="https://github.com/huggingface/${PN}/archive/refs/tags/${PV}.tar.gz + -> ${P}.gh.tar.gz" + +LICENSE="Apache-2.0" +SLOT="0" +KEYWORDS="~amd64" + +IUSE="test" + +RDEPEND=" + ${PYTHON_DEPS} + sci-libs/pytorch[${PYTHON_SINGLE_USEDEP}] + sci-libs/caffe2[${PYTHON_SINGLE_USEDEP},numpy] + $(python_gen_cond_dep ' + dev-python/absl-py[${PYTHON_USEDEP}] + dev-python/aiohttp[${PYTHON_USEDEP}] + dev-python/dill[${PYTHON_USEDEP}] + dev-python/filelock[${PYTHON_USEDEP}] + dev-python/fsspec[${PYTHON_USEDEP}] + dev-python/multiprocess[${PYTHON_USEDEP}] + dev-python/numpy[${PYTHON_USEDEP}] + dev-python/packaging[${PYTHON_USEDEP}] + dev-python/pandas[${PYTHON_USEDEP}] + dev-python/pyarrow[${PYTHON_USEDEP},parquet,snappy] + dev-python/pyyaml[${PYTHON_USEDEP}] + dev-python/requests[${PYTHON_USEDEP}] + dev-python/scikit-learn[${PYTHON_USEDEP}] + dev-python/tqdm[${PYTHON_USEDEP}] + dev-python/xxhash[${PYTHON_USEDEP}] + dev-python/zstandard[${PYTHON_USEDEP}] + sci-libs/huggingface_hub[${PYTHON_USEDEP}] + ') +" +DEPEND="${RDEPEND}" +BDEPEND="test? ( + $(python_gen_cond_dep ' + dev-python/absl-py[${PYTHON_USEDEP}] + dev-python/pytest-datadir[${PYTHON_USEDEP}] + dev-python/decorator[${PYTHON_USEDEP}] + dev-python/sqlalchemy[${PYTHON_USEDEP}] + sci-libs/jiwer[${PYTHON_USEDEP}] + sci-libs/seqeval[${PYTHON_USEDEP}] + ') +)" + +PATCHES=( + "${FILESDIR}"/${P}-tests.patch +) + +distutils_enable_tests pytest + +src_prepare() { + distutils-r1_src_prepare + sed -i -e \ + "/pyarrow_hotfix/d" \ + src/datasets/features/features.py || die +} + +src_test() { + local EPYTEST_IGNORE=( + tests/test_upstream_hub.py + tests/packaged_modules/test_spark.py + ) + + local EPYTEST_DESELECT=( + "tests/test_arrow_dataset.py::BaseDatasetTest::test_filter_caching_on_disk" + "tests/test_arrow_dataset.py::BaseDatasetTest::test_filter_in_memory" + "tests/test_arrow_dataset.py::BaseDatasetTest::test_filter_on_disk" + "tests/test_arrow_dataset.py::BaseDatasetTest::test_flatten_indices_in_memory" + "tests/test_arrow_dataset.py::BaseDatasetTest::test_flatten_indices_on_disk" + "tests/test_arrow_dataset.py::BaseDatasetTest::test_map_batched_in_memory" + "tests/test_arrow_dataset.py::BaseDatasetTest::test_map_batched_on_disk" + "tests/test_arrow_dataset.py::BaseDatasetTest::test_map_caching_on_disk" + "tests/test_arrow_dataset.py::BaseDatasetTest::test_map_in_memory" + "tests/test_arrow_dataset.py::BaseDatasetTest::test_map_on_disk" + "tests/test_arrow_dataset.py::BaseDatasetTest::test_map_remove_columns_in_memory" + "tests/test_arrow_dataset.py::BaseDatasetTest::test_map_remove_columns_on_disk" + "tests/test_arrow_dataset.py::BaseDatasetTest::test_select_in_memory" + "tests/test_arrow_dataset.py::BaseDatasetTest::test_select_on_disk" + "tests/test_arrow_dataset.py::BaseDatasetTest::test_set_format_numpy_multiple_columns_in_memory" + "tests/test_arrow_dataset.py::BaseDatasetTest::test_set_format_numpy_multiple_columns_on_disk" + "tests/test_arrow_dataset.py::BaseDatasetTest::test_set_format_torch_in_memory" + "tests/test_arrow_dataset.py::BaseDatasetTest::test_set_format_torch_on_disk" + "tests/test_arrow_dataset.py::BaseDatasetTest::test_train_test_split_in_memory" + "tests/test_arrow_dataset.py::BaseDatasetTest::test_train_test_split_on_disk" + "tests/test_arrow_dataset.py::TaskTemplatesTest::test_task_automatic_speech_recognition" + "tests/test_arrow_dataset.py::StratifiedTest::test_train_test_split_startify" + "tests/test_arrow_dataset.py::test_dataset_format_with_unformatted_image" + "tests/test_arrow_dataset.py::test_map_cases" + "tests/test_dataset_dict.py::DatasetDictTest::test_set_format_numpy" + "tests/test_dataset_dict.py::DatasetDictTest::test_set_format_torch" + "tests/test_distributed.py::test_torch_distributed_run" + "tests/test_distributed.py::test_torch_distributed_run_streaming_with_num_workers" + "tests/test_file_utils.py::TestxPath::test_xpath_glob" + "tests/test_file_utils.py::TestxPath::test_xpath_rglob" + "tests/test_fingerprint.py::TokenizersHashTest::test_hash_regex" + "tests/test_fingerprint.py::TokenizersHashTest::test_hash_tokenizer" + "tests/test_fingerprint.py::TokenizersHashTest::test_hash_tokenizer_with_cache" + "tests/test_fingerprint.py::RecurseHashTest::test_hash_ignores_line_definition_of_function" + "tests/test_fingerprint.py::RecurseHashTest::test_hash_ipython_function" + "tests/test_fingerprint.py::HashingTest::test_hash_torch_compiled_module" + "tests/test_fingerprint.py::HashingTest::test_hash_torch_generator" + "tests/test_fingerprint.py::HashingTest::test_hash_torch_tensor" + "tests/test_fingerprint.py::HashingTest::test_set_doesnt_depend_on_order" + "tests/test_fingerprint.py::HashingTest::test_set_stable" + "tests/test_fingerprint.py::test_move_script_doesnt_change_hash" + "tests/test_formatting.py::ArrowExtractorTest::test_numpy_extractor" + "tests/test_formatting.py::ArrowExtractorTest::test_numpy_extractor_nested" + "tests/test_formatting.py::ArrowExtractorTest::test_numpy_extractor_temporal" + "tests/test_formatting.py::FormatterTest::test_numpy_formatter" + "tests/test_formatting.py::FormatterTest::test_numpy_formatter_image" + "tests/test_formatting.py::FormatterTest::test_numpy_formatter_np_array_kwargs" + "tests/test_formatting.py::FormatterTest::test_torch_formatter" + "tests/test_formatting.py::FormatterTest::test_torch_formatter_image" + "tests/test_formatting.py::FormatterTest::test_torch_formatter_torch_tensor_kwargs" + "tests/test_formatting.py::test_torch_formatter_sets_default_dtypes" + "tests/test_inspect.py::test_get_dataset_config_names[hf-internal-testing/librispeech_asr_dummy-expected4]" + "tests/test_inspect.py::test_get_dataset_default_config_name[hf-internal-testing/librispeech_asr_dummy-None]" + "tests/test_load.py::ModuleFactoryTest::test_HubDatasetModuleFactoryWithParquetExport" + "tests/test_load.py::ModuleFactoryTest::test_HubDatasetModuleFactoryWithParquetExport_errors_on_wrong_sha" + "tests/test_metric_common.py::LocalMetricTest::test_load_metric_bertscore" + "tests/test_metric_common.py::LocalMetricTest::test_load_metric_bleurt" + "tests/test_metric_common.py::LocalMetricTest::test_load_metric_chrf" + "tests/test_metric_common.py::LocalMetricTest::test_load_metric_code_eval" + "tests/test_metric_common.py::LocalMetricTest::test_load_metric_competition_math" + "tests/test_metric_common.py::LocalMetricTest::test_load_metric_coval" + "tests/test_metric_common.py::LocalMetricTest::test_load_metric_cuad" + "tests/test_metric_common.py::LocalMetricTest::test_load_metric_frugalscore" + "tests/test_metric_common.py::LocalMetricTest::test_load_metric_glue" + "tests/test_metric_common.py::LocalMetricTest::test_load_metric_google_bleu" + "tests/test_metric_common.py::LocalMetricTest::test_load_metric_indic_glue" + "tests/test_metric_common.py::LocalMetricTest::test_load_metric_mae" + "tests/test_metric_common.py::LocalMetricTest::test_load_metric_mauve" + "tests/test_metric_common.py::LocalMetricTest::test_load_metric_mean_iou" + "tests/test_metric_common.py::LocalMetricTest::test_load_metric_meteor" + "tests/test_metric_common.py::LocalMetricTest::test_load_metric_mse" + "tests/test_metric_common.py::LocalMetricTest::test_load_metric_precision" + "tests/test_metric_common.py::LocalMetricTest::test_load_metric_roc_auc" + "tests/test_metric_common.py::LocalMetricTest::test_load_metric_rouge" + "tests/test_metric_common.py::LocalMetricTest::test_load_metric_sacrebleu" + "tests/test_metric_common.py::LocalMetricTest::test_load_metric_sari" + "tests/test_metric_common.py::LocalMetricTest::test_load_metric_spearmanr" + "tests/test_metric_common.py::LocalMetricTest::test_load_metric_super_glue" + "tests/test_metric_common.py::LocalMetricTest::test_load_metric_ter" + "tests/test_metric_common.py::LocalMetricTest::test_load_metric_wiki_split" + "tests/test_metric_common.py::LocalMetricTest::test_load_metric_xnli" + "tests/test_metric_common.py::LocalMetricTest::test_load_metric_xtreme_s" + "tests/features/test_array_xd.py::ExtensionTypeCompatibilityTest::test_array2d_nonspecific_shape" + "tests/features/test_array_xd.py::ExtensionTypeCompatibilityTest::test_extension_indexing" + "tests/features/test_array_xd.py::ExtensionTypeCompatibilityTest::test_multiple_extensions_same_row" + "tests/features/test_array_xd.py::ArrayXDTest::test_from_dict_2d" + "tests/features/test_array_xd.py::ArrayXDTest::test_from_dict_3d" + "tests/features/test_array_xd.py::ArrayXDTest::test_from_dict_4d" + "tests/features/test_array_xd.py::ArrayXDTest::test_from_dict_5d" + "tests/features/test_array_xd.py::ArrayXDTest::test_write_2d" + "tests/features/test_array_xd.py::ArrayXDTest::test_write_3d" + "tests/features/test_array_xd.py::ArrayXDTest::test_write_4d" + "tests/features/test_array_xd.py::ArrayXDTest::test_write_5d" + "tests/features/test_array_xd.py::ArrayXDTest::test_write_batch_2d" + "tests/features/test_array_xd.py::ArrayXDTest::test_write_batch_3d" + "tests/features/test_array_xd.py::ArrayXDTest::test_write_batch_4d" + "tests/features/test_array_xd.py::ArrayXDTest::test_write_batch_5d" + "tests/features/test_array_xd.py::test_array_xd_numpy_arrow_extractor" + "tests/features/test_array_xd.py::test_array_xd_with_none" + "tests/features/test_array_xd.py::test_dataset_map" + "tests/features/test_audio.py::test_audio_feature_encode_example" + "tests/features/test_audio.py::test_audio_feature_encode_example_pcm" + "tests/features/test_audio.py::test_audio_decode_example_pcm" + "tests/features/test_audio.py::test_dataset_cast_to_audio_features" + "tests/features/test_audio.py::test_dataset_concatenate_audio_features" + "tests/features/test_audio.py::test_dataset_concatenate_nested_audio_features" + "tests/features/test_audio.py::test_dataset_with_audio_feature_undecoded" + "tests/features/test_audio.py::test_formatted_dataset_with_audio_feature_undecoded" + "tests/features/test_audio.py::test_dataset_with_audio_feature_map_undecoded" + "tests/features/test_image.py::test_formatted_dataset_with_image_feature_map" + "tests/features/test_image.py::test_formatted_dataset_with_image_feature" + "tests/features/test_image.py::test_formatted_dataset_with_image_feature_undecoded" + "tests/packaged_modules/test_cache.py::test_cache_multi_configs" + "tests/packaged_modules/test_cache.py::test_cache_single_config" + ) + distutils-r1_src_test +} diff --git a/sci-libs/datasets/files/datasets-2.17.1-tests.patch b/sci-libs/datasets/files/datasets-2.17.1-tests.patch deleted file mode 100644 index 2281598dfb38..000000000000 --- a/sci-libs/datasets/files/datasets-2.17.1-tests.patch +++ /dev/null @@ -1,364 +0,0 @@ ---- a/tests/test_arrow_dataset.py 2024-02-20 21:53:24.248470991 +0100 -+++ b/tests/test_arrow_dataset.py 2024-02-20 21:53:29.441804737 +0100 -@@ -4016,7 +4016,6 @@ - [ - "relative/path", - "/absolute/path", -- "s3://bucket/relative/path", - "hdfs://relative/path", - "hdfs:///absolute/path", - ], -@@ -4136,6 +4136,7 @@ - ) - self.assertDictEqual(features_after_cast, dset.features) - -+ @pytest.mark.skip(reason="require soundfile") - def test_task_automatic_speech_recognition(self): - # Include a dummy extra column `dummy` to test we drop it correctly - features_before_cast = Features( ---- a/tests/test_load.py 2024-02-20 22:12:13.699209107 +0100 -+++ b/tests/test_load.py 2024-02-20 22:13:10.862626708 +0100 -@@ -388,6 +388,7 @@ - hf_modules_cache=self.hf_modules_cache, - ) - -+ @pytest.mark.skip(reason="") - def test_HubDatasetModuleFactoryWithScript_dont_trust_remote_code(self): - # "lhoestq/test" has a dataset script - factory = HubDatasetModuleFactoryWithScript( -@@ -403,6 +404,7 @@ - ) - self.assertRaises(ValueError, factory.get_module) - -+ @pytest.mark.skip() - def test_HubDatasetModuleFactoryWithScript_with_github_dataset(self): - # "wmt_t2t" has additional imports (internal) - factory = HubDatasetModuleFactoryWithScript( -@@ -412,6 +414,7 @@ - assert importlib.import_module(module_factory_result.module_path) is not None - assert module_factory_result.builder_kwargs["base_path"].startswith(config.HF_ENDPOINT) - -+ @pytest.mark.skip() - def test_GithubMetricModuleFactory_with_internal_import(self): - # "squad_v2" requires additional imports (internal) - factory = GithubMetricModuleFactory( -@@ -420,6 +423,7 @@ - module_factory_result = factory.get_module() - assert importlib.import_module(module_factory_result.module_path) is not None - -+ @pytest.mark.skip() - @pytest.mark.filterwarnings("ignore:GithubMetricModuleFactory is deprecated:FutureWarning") - def test_GithubMetricModuleFactory_with_external_import(self): - # "bleu" requires additional imports (external from github) -@@ -1033,6 +1037,7 @@ - datasets.load_dataset_builder(SAMPLE_DATASET_TWO_CONFIG_IN_METADATA, "non-existing-config") - - -+@pytest.mark.skip() - @pytest.mark.parametrize("serializer", [pickle, dill]) - def test_load_dataset_builder_with_metadata_configs_pickable(serializer): - builder = datasets.load_dataset_builder(SAMPLE_DATASET_SINGLE_CONFIG_IN_METADATA) -@@ -1154,6 +1159,7 @@ - assert len(builder.config.data_files["test"]) > 0 - - -+@pytest.mark.skip() - def test_load_dataset_builder_fail(): - with pytest.raises(DatasetNotFoundError): - datasets.load_dataset_builder("blabla") -@@ -1169,6 +1175,7 @@ - assert isinstance(next(iter(dataset["train"])), dict) - - -+@pytest.mark.skip() - def test_load_dataset_cached_local_script(dataset_loading_script_dir, data_dir, caplog): - dataset = load_dataset(dataset_loading_script_dir, data_dir=data_dir) - assert isinstance(dataset, DatasetDict) ---- a/tests/test_hf_gcp.py 2024-02-21 09:59:26.918397895 +0100 -+++ b/tests/test_hf_gcp.py 2024-02-21 09:59:46.335100597 +0100 -@@ -45,6 +45,7 @@ - ] - - -+@pytest.mark.skip("network") - @parameterized.named_parameters(list_datasets_on_hf_gcp_parameters(with_config=True)) - class TestDatasetOnHfGcp(TestCase): - dataset = None ---- a/tests/test_inspect.py 2024-02-21 10:03:32.315520016 +0100 -+++ b/tests/test_inspect.py 2024-02-21 10:03:50.345553490 +0100 -@@ -49,6 +49,7 @@ - assert list(info.splits.keys()) == expected_splits - - -+@pytest.mark.skip(reason="require network") - def test_get_dataset_config_info_private(hf_token, hf_private_dataset_repo_txt_data): - info = get_dataset_config_info(hf_private_dataset_repo_txt_data, config_name="default", token=hf_token) - assert list(info.splits.keys()) == ["train"] ---- a/tests/test_data_files.py 2024-02-21 20:22:57.536160356 +0100 -+++ b/tests/test_data_files.py 2024-02-21 20:25:00.153052174 +0100 -@@ -378,6 +378,7 @@ - assert len(hub_dataset_repo_patterns_results[pattern]) == 0 - - -+@pytest.mark.skip(reason="network") - def test_DataFilesList_from_patterns_locally_with_extra_files(complex_data_dir, text_file): - data_files_list = DataFilesList.from_patterns([_TEST_URL, text_file.as_posix()], complex_data_dir) - assert list(data_files_list) == [_TEST_URL, text_file.as_posix()] -@@ -467,6 +468,7 @@ - assert Hasher.hash(data_files1) != Hasher.hash(data_files2) - - -+@pytest.mark.skip(reason="network") - def test_DataFilesDict_from_patterns_locally_or_remote_hashing(text_file): - patterns = {"train": [_TEST_URL], "test": [str(text_file)]} - data_files1 = DataFilesDict.from_patterns(patterns) ---- a/tests/packaged_modules/test_folder_based_builder.py 2024-02-21 21:30:20.718922523 +0100 -+++ b/tests/packaged_modules/test_folder_based_builder.py 2024-02-21 21:31:46.309061287 +0100 -@@ -382,6 +382,7 @@ - assert example[column] is not None - - -+@pytest.mark.skip(reason="network") - @pytest.mark.parametrize("remote", [True, False]) - @pytest.mark.parametrize("drop_labels", [None, True, False]) - def test_data_files_with_different_levels_no_metadata( -@@ -405,6 +406,7 @@ - assert all(example.keys() == {"base", "label"} for _, example in generator) - - -+@pytest.mark.skip(reason="network") - @pytest.mark.parametrize("remote", [False, True]) - @pytest.mark.parametrize("drop_labels", [None, True, False]) - def test_data_files_with_one_label_no_metadata(data_files_with_one_label_no_metadata, drop_labels, remote, cache_dir): ---- a/tests/test_metric_common.py 2023-05-04 18:48:48.550861318 +0200 -+++ b/tests/test_metric_common.py 2023-05-04 18:50:25.787364577 +0200 -@@ -93,6 +93,7 @@ - INTENSIVE_CALLS_PATCHER = {} - metric_name = None - -+ @pytest.mark.skip(reason="disabling, depends on bert_score, bleurt, math_equivalence, coval, nltk, faiss, mauve, rouge_score, sacrebleu, sacremoses ...") - @pytest.mark.filterwarnings("ignore:metric_module_factory is deprecated:FutureWarning") - @pytest.mark.filterwarnings("ignore:load_metric is deprecated:FutureWarning") - def test_load_metric(self, metric_name): ---- a/tests/test_distributed.py 2023-05-04 19:43:09.861275030 +0200 -+++ b/tests/test_distributed.py 2023-05-04 19:44:17.608326722 +0200 -@@ -74,6 +74,7 @@ - split_dataset_by_node(full_ds.shuffle(), rank=0, world_size=world_size) - - -+@pytest.mark.skip(reason="require distributed torch") - @pytest.mark.parametrize("streaming", [False, True]) - @require_torch - @pytest.mark.skipif(os.name == "nt", reason="execute_subprocess_async doesn't support windows") -@@ -95,6 +96,7 @@ - execute_subprocess_async(cmd, env=os.environ.copy()) - - -+@pytest.mark.skip(reason="require distributed torch") - @pytest.mark.parametrize( - "nproc_per_node, num_workers", - [ ---- a/tests/utils.py 2023-05-06 08:43:16.251987543 +0200 -+++ b/tests/utils.py 2023-05-06 08:44:24.467952870 +0200 -@@ -50,8 +50,8 @@ - # Audio - require_sndfile = pytest.mark.skipif( - # On Windows and OS X, soundfile installs sndfile -- find_spec("soundfile") is None or version.parse(importlib.metadata.version("soundfile")) < version.parse("0.12.0"), -- reason="test requires sndfile>=0.12.1: 'pip install \"soundfile>=0.12.1\"'; ", -+ True, -+ reason="test requires librosa", - ) - - # Beam ---- a/tests/features/test_audio.py 2023-05-06 09:03:58.680108142 +0200 -+++ a/tests/features/test_audio.py 2023-05-06 09:05:50.463407967 +0200 -@@ -57,6 +57,7 @@ - assert features.arrow_schema == pa.schema({"sequence_of_audios": pa.list_(Audio().pa_type)}) - - -+@pytest.mark.skip(reason="require librosa") - @pytest.mark.parametrize( - "build_example", - [ -@@ -81,6 +82,7 @@ - assert decoded_example.keys() == {"path", "array", "sampling_rate"} - - -+@pytest.mark.skip(reason="require librosa") - @pytest.mark.parametrize( - "build_example", - [ -@@ -148,6 +149,7 @@ - assert decoded_example["sampling_rate"] == 48000 - - -+@pytest.mark.skip(reason="require librosa") - @pytest.mark.parametrize("sampling_rate", [16_000, 48_000]) - def test_audio_decode_example_pcm(shared_datadir, sampling_rate): - audio_path = str(shared_datadir / "test_audio_16000.pcm") -@@ -414,6 +417,7 @@ - assert column[0]["sampling_rate"] == 16000 - - -+@pytest.mark.skip(reason="require librosa") - @pytest.mark.parametrize( - "build_data", - [ -@@ -438,6 +442,7 @@ - assert item["audio"].keys() == {"path", "array", "sampling_rate"} - - -+@pytest.mark.skip(reason="require librosa") - def test_dataset_concatenate_audio_features(shared_datadir): - # we use a different data structure between 1 and 2 to make sure they are compatible with each other - audio_path = str(shared_datadir / "test_audio_44100.wav") -@@ -451,6 +456,7 @@ - assert concatenated_dataset[1]["audio"]["array"].shape == dset2[0]["audio"]["array"].shape - - -+@pytest.mark.skip(reason="require librosa") - def test_dataset_concatenate_nested_audio_features(shared_datadir): - # we use a different data structure between 1 and 2 to make sure they are compatible with each other - audio_path = str(shared_datadir / "test_audio_44100.wav") -@@ -610,6 +616,7 @@ - assert isinstance(ds, Dataset) - - -+@require_sndfile - def test_dataset_with_audio_feature_undecoded(shared_datadir): - audio_path = str(shared_datadir / "test_audio_44100.wav") - data = {"audio": [audio_path]} -@@ -627,6 +634,7 @@ - assert column[0] == {"path": audio_path, "bytes": None} - - -+@require_sndfile - def test_formatted_dataset_with_audio_feature_undecoded(shared_datadir): - audio_path = str(shared_datadir / "test_audio_44100.wav") - data = {"audio": [audio_path]} -@@ -658,6 +666,7 @@ - assert column[0] == {"path": audio_path, "bytes": None} - - -+@require_sndfile - def test_dataset_with_audio_feature_map_undecoded(shared_datadir): - audio_path = str(shared_datadir / "test_audio_44100.wav") - data = {"audio": [audio_path]} ---- a/tests/packaged_modules/test_audiofolder.py 2023-05-06 14:00:39.560876163 +0200 -+++ b/tests/packaged_modules/test_audiofolder.py 2023-05-06 14:01:26.005212423 +0200 -@@ -1,10 +1,8 @@ - import shutil - import textwrap - --import librosa - import numpy as np - import pytest --import soundfile as sf - - from datasets import Audio, ClassLabel, Features, Value - from datasets.data_files import DataFilesDict, get_data_patterns -@@ -192,8 +190,11 @@ - return data_files_with_two_splits_and_metadata - - -+@pytest.mark.skip(reason="require soundfile") - @pytest.fixture - def data_files_with_zip_archives(tmp_path, audio_file): -+ import soundfile as sf -+ import librosa - data_dir = tmp_path / "audiofolder_data_dir_with_zip_archives" - data_dir.mkdir(parents=True, exist_ok=True) - archive_dir = data_dir / "archive" ---- a/tests/test_streaming_download_manager.py 2023-08-26 07:33:41.937389401 +0200 -+++ b/tests/test_streaming_download_manager.py 2023-08-26 07:37:22.521218698 +0200 -@@ -218,6 +218,7 @@ - assert output_path == _readd_double_slash_removed_by_path(Path(expected_path).as_posix()) - - -+@pytest.mark.skip(reason="not working in sandbox") - @pytest.mark.parametrize( - "input_path, exists", - [ -@@ -301,6 +302,7 @@ - assert list(f) == TEST_URL_CONTENT.splitlines(keepends=True) - - -+@pytest.mark.skip(reason="not working in sandbox") - @pytest.mark.parametrize( - "input_path, expected_paths", - [ -@@ -331,6 +333,7 @@ - xlistdir(root_url, download_config=download_config) - - -+@pytest.mark.skip(reason="not working in sandbox") - @pytest.mark.parametrize( - "input_path, isdir", - [ -@@ -358,6 +361,7 @@ - assert xisdir(root_url, download_config=download_config) is False - - -+@pytest.mark.skip(reason="not working in sandbox") - @pytest.mark.parametrize( - "input_path, isfile", - [ -@@ -382,6 +386,7 @@ - assert xisfile(root_url + "qwertyuiop", download_config=download_config) is False - - -+@pytest.mark.skip(reason="not working in sandbox") - @pytest.mark.parametrize( - "input_path, size", - [ -@@ -407,6 +412,7 @@ - xgetsize(root_url + "qwertyuiop", download_config=download_config) - - -+@pytest.mark.skip(reason="not working in sandbox") - @pytest.mark.parametrize( - "input_path, expected_paths", - [ -@@ -450,6 +456,7 @@ - assert len(xglob("zip://qwertyuiop/*::" + root_url, download_config=download_config)) == 0 - - -+@pytest.mark.skip(reason="not working in sandbox") - @pytest.mark.parametrize( - "input_path, expected_outputs", - [ -@@ -540,6 +547,7 @@ - def test_xpath_as_posix(self, input_path, expected_path): - assert xPath(input_path).as_posix() == expected_path - -+ @pytest.mark.skip(reason="not working in sandbox") - @pytest.mark.parametrize( - "input_path, exists", - [ -@@ -555,6 +563,7 @@ - (tmp_path / "file.txt").touch() - assert xexists(input_path) is exists - -+ @pytest.mark.skip(reason="not working in sandbox") - @pytest.mark.parametrize( - "input_path, pattern, expected_paths", - [ -@@ -593,6 +602,7 @@ - output_paths = sorted(xPath(input_path).glob(pattern)) - assert output_paths == expected_paths - -+ @pytest.mark.skip(reason="not working in sandbox") - @pytest.mark.parametrize( - "input_path, pattern, expected_paths", - [ ---- a/tests/io/test_parquet.py 2024-02-22 19:19:53.890749240 +0100 -+++ b/tests/io/test_parquet.py 2024-02-22 19:20:30.954099914 +0100 -@@ -69,6 +69,7 @@ - _check_parquet_dataset(dataset, expected_features) - - -+@pytest.mark.skip() - def test_parquet_read_geoparquet(geoparquet_path, tmp_path): - cache_dir = tmp_path / "cache" - dataset = ParquetDatasetReader(path_or_paths=geoparquet_path, cache_dir=cache_dir).read() diff --git a/sci-libs/datasets/files/datasets-2.19.2-tests.patch b/sci-libs/datasets/files/datasets-2.19.2-tests.patch new file mode 100644 index 000000000000..64df833032c5 --- /dev/null +++ b/sci-libs/datasets/files/datasets-2.19.2-tests.patch @@ -0,0 +1,23 @@ +--- a/tests/test_arrow_dataset.py 2024-02-20 21:53:24.248470991 +0100 ++++ b/tests/test_arrow_dataset.py 2024-02-20 21:53:29.441804737 +0100 +@@ -4109,7 +4109,6 @@ + [ + "relative/path", + "/absolute/path", +- "s3://bucket/relative/path", + "hdfs://relative/path", + "hdfs:///absolute/path", + ], +--- a/tests/packaged_modules/test_audiofolder.py 2023-05-06 14:00:39.560876163 +0200 ++++ b/tests/packaged_modules/test_audiofolder.py 2023-05-06 14:01:26.005212423 +0200 +@@ -1,10 +1,8 @@ + import shutil + import textwrap + +-import librosa + import numpy as np + import pytest +-import soundfile as sf + + from datasets import Audio, ClassLabel, Features, Value + from datasets.data_files import DataFilesDict, get_data_patterns |