From 8ef9b8c62c1aa79c0bceaf3c0d6fe1e7cdd976d0 Mon Sep 17 00:00:00 2001 From: V3n3RiX Date: Thu, 22 Feb 2024 11:40:14 +0000 Subject: gentoo auto-resync : 22:02:2024 - 11:40:14 --- sci-libs/datasets/Manifest | 8 +- sci-libs/datasets/datasets-2.16.0.ebuild | 83 ------------- sci-libs/datasets/datasets-2.17.1.ebuild | 87 ++++++++++++++ .../datasets/files/datasets-2.14.4-tests.patch | 10 -- .../datasets/files/datasets-2.16.0-tests.patch | 133 --------------------- .../datasets/files/datasets-2.17.1-tests.patch | 124 +++++++++++++++++++ 6 files changed, 215 insertions(+), 230 deletions(-) delete mode 100644 sci-libs/datasets/datasets-2.16.0.ebuild create mode 100644 sci-libs/datasets/datasets-2.17.1.ebuild delete mode 100644 sci-libs/datasets/files/datasets-2.16.0-tests.patch create mode 100644 sci-libs/datasets/files/datasets-2.17.1-tests.patch (limited to 'sci-libs/datasets') diff --git a/sci-libs/datasets/Manifest b/sci-libs/datasets/Manifest index 21c1c02b3ecd..32934c5c4a4c 100644 --- a/sci-libs/datasets/Manifest +++ b/sci-libs/datasets/Manifest @@ -1,5 +1,5 @@ -AUX datasets-2.14.4-tests.patch 8616 BLAKE2B 8a65d1315b27658a5f741ebc022c83692252a4833ec4d7b79873799c2bb4bb68534a9e13e7fae1c9a6c051b3615fbb783e6e7885ed93968b31aea6629b4116c4 SHA512 2c6d27c297995466a0aebefa46e86113bdce7d84ea00bb1630549fc379fbb51d66f8f01a8d098d56ec2b26d5200f129460567abdbf6a63d4e2a61372fbfbc6a3 -AUX datasets-2.16.0-tests.patch 5619 BLAKE2B b143a97aa1ce2a4f793370557b18cb948872c856e20129c9d29159a531a1f1a7781957c8eb64420622865d52510376b1d7c757f51d6f0320613200e739212135 SHA512 a865fcb7e0d0437b1dc6cbac905772b5fdec2107f27abe331419111b49ffff237b877568edea354f57165ce7b66df0d3ac2506966259c229495f34722de23e9e -DIST datasets-2.16.0.gh.tar.gz 2163874 BLAKE2B baec91a0e39fac3e07f11e352a286c0940cbc672e7233267e70d1abb64dd31bae18c55213a20fafaeaf2f60268104f294c77c9b73ddc1b289175904288a7c440 SHA512 f2a17ffab192163cfc196cc2bad0adb2ca657b5cf911f74f299b6e29eb4fcfacc377505b1857974a6b55252eedf8775a8706f9e991450c55e5d613020dc03735 -EBUILD datasets-2.16.0.ebuild 2304 BLAKE2B 4af6b595b3344e5df5ddcc46146d637e1091a1b7237e4ab2c3f49299a14c22af32dd180902cac16a3723e3a67613951325d8e47481e0bd5081ce6daa9741286a SHA512 1c7df28fd520eb30bb40f42347cfa106d3f12bbc5c8b9eaf93cfcf956078ab2217b51f50f865949b0bd90e85f569adb59ad06ef350db79038dfa38ccb549b2c2 +AUX datasets-2.14.4-tests.patch 8198 BLAKE2B fbff05d38b138796f48a09cbf2e4499a63840bc24cc24b14e49cc8a7ef87bd6cf2fed24de4f9b45ff6a5581e8af407a734cd29f2172028592437d8bb54a5c6c9 SHA512 b9b87fce4ae2866ff23f038d5df799431600f1d7de5ef46d0c871401d6f47f45390d39c20342074f86eb31087336d80954d3ce288f317bf83c044ff65edece5a +AUX datasets-2.17.1-tests.patch 5335 BLAKE2B 2d006dfd847d8e5424754fd3f1f855a909f407f80a3846e1959f726fff9b1076e46f5e2b4c5257dad51710e94312dba0fce98d79211fe4ffb6c72b01f2c6dd2d SHA512 be8df0b3b15371963d59054314134cbc3e263cdc4ab09eb54509842de000a21c0a0f52b0202656a1ae5cbbba5f77651f7a1e2a3d76a955211c7a8fbee01fca3b +DIST datasets-2.17.1.gh.tar.gz 2168860 BLAKE2B ad7e9be7e60125d53b19b6277b6be6ae6050321e4210293a37737a345a4806d4901e9507fbf7a51c5e00a91912656d68a94e76cf70e070433beccc6e1ad54643 SHA512 43617c3d98cc3ad17fb577d6e917d164c8b6ec24740604ca281adaa2f0e5a6538633721792c9fa6621b7f1980161d8acf62dcdcdacca56e1739a8f28e3c71cdf +EBUILD datasets-2.17.1.ebuild 2456 BLAKE2B 475c5d4dda897f61735a93811e5350e8e20159b2a00e448425fefae396cc8fccca4f8d8debf229e938403c59981f8461cfc78a865fc47e201351e6049830a334 SHA512 61d09cc8b95baf414523a80f8db5b01cfa5517c94e79217684d629ad7ec79f1b1f1d9115405e2734e3dc17d80158182310919bf94f44fb8ddb6e04979361d2eb MISC metadata.xml 379 BLAKE2B 48ebb9e7bfa8b58b0d15b82c4146def465e08cf3212ab4af04129d09c153b67b00d0fa05b94d6af54f643ec3a202f2335d3254b966f49d1394d3c7b9e5da56a5 SHA512 99560decfaa0e438980f372d99257695e9ca9585167d9aba091e0b775c2f8384657ddc017841c8f06f8b568017a54fb9e31da736f3c875da717e154cdce876d1 diff --git a/sci-libs/datasets/datasets-2.16.0.ebuild b/sci-libs/datasets/datasets-2.16.0.ebuild deleted file mode 100644 index a34fcaa2f89c..000000000000 --- a/sci-libs/datasets/datasets-2.16.0.ebuild +++ /dev/null @@ -1,83 +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" - -# For pin on fsspec see https://github.com/huggingface/datasets/issues/6333 -RDEPEND=" - ${PYTHON_DEPS} - sci-libs/pytorch[${PYTHON_SINGLE_USEDEP}] - $(python_gen_cond_dep ' - dev-python/absl-py[${PYTHON_USEDEP}] - dev-python/aiohttp[${PYTHON_USEDEP}] - <=dev-python/fsspec-2023.10.0[${PYTHON_USEDEP}] - dev-python/multiprocess[${PYTHON_USEDEP}] - dev-python/packaging[${PYTHON_USEDEP}] - dev-python/pandas[${PYTHON_USEDEP}] - dev-python/pyarrow[${PYTHON_USEDEP},parquet,snappy] - dev-python/pyyaml[${PYTHON_USEDEP}] - dev-python/tqdm[${PYTHON_USEDEP}] - dev-python/xxhash[${PYTHON_USEDEP}] - dev-python/zstandard[${PYTHON_USEDEP}] - sci-libs/huggingface_hub[${PYTHON_USEDEP}] - sci-libs/scikit-learn[${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-1*[${PYTHON_USEDEP}] - sci-libs/jiwer[${PYTHON_USEDEP}] - sci-libs/seqeval[${PYTHON_USEDEP}] - ') -)" - -PATCHES=( - "${FILESDIR}"/${PN}-2.14.4-tests.patch - "${FILESDIR}"/${P}-tests.patch -) - -distutils_enable_tests pytest - -src_prepare() { - distutils-r1_src_prepare - rm tests/packaged_modules/test_spark.py || die - rm tests/test_upstream_hub.py || die - sed -i -e \ - "/pyarrow_hotfix/d" \ - src/datasets/features/features.py || die - sed -i \ - -e "s:pytest.mark.integration:pytest.mark.skip():g" \ - tests/test_arrow_dataset.py \ - tests/test_fingerprint.py \ - tests/test_hf_gcp.py \ - tests/test_inspect.py \ - tests/test_iterable_dataset.py \ - tests/test_iterable_dataset.py \ - tests/test_load.py \ - tests/test_offline_util.py \ - tests/test_streaming_download_manager.py \ - tests/commands/test_test.py \ - tests/packaged_modules/test_cache.py \ - die -} diff --git a/sci-libs/datasets/datasets-2.17.1.ebuild b/sci-libs/datasets/datasets-2.17.1.ebuild new file mode 100644 index 000000000000..9b6295db1a0e --- /dev/null +++ b/sci-libs/datasets/datasets-2.17.1.ebuild @@ -0,0 +1,87 @@ +# Copyright 2023-2024 Gentoo Authors +# Distributed under the terms of the GNU General Public License v2 + +EAPI=8 + +DISTUTILS_USE_PEP517=setuptools +PYTHON_COMPAT=( python3_{10..12} ) +DISTUTILS_SINGLE_IMPL=1 +inherit distutils-r1 + +DESCRIPTION="Access and share datasets for Audio, Computer Vision, and NLP tasks" +HOMEPAGE=" + https://pypi.org/project/datasets/ +" +SRC_URI="https://github.com/huggingface/${PN}/archive/refs/tags/${PV}.tar.gz + -> ${P}.gh.tar.gz" +IUSE="test" + +LICENSE="Apache-2.0" +SLOT="0" +KEYWORDS="~amd64" + +# For pin on fsspec see https://github.com/huggingface/datasets/issues/6333 +RDEPEND=" + ${PYTHON_DEPS} + sci-libs/pytorch[${PYTHON_SINGLE_USEDEP}] + $(python_gen_cond_dep ' + dev-python/absl-py[${PYTHON_USEDEP}] + dev-python/aiohttp[${PYTHON_USEDEP}] + dev-python/dill[${PYTHON_USEDEP}] + dev-python/filelock[${PYTHON_USEDEP}] + <=dev-python/fsspec-2023.10.0[${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[${PYTHON_USEDEP}] + dev-python/tqdm[${PYTHON_USEDEP}] + dev-python/xxhash[${PYTHON_USEDEP}] + dev-python/zstandard[${PYTHON_USEDEP}] + sci-libs/huggingface_hub[${PYTHON_USEDEP}] + sci-libs/scikit-learn[${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}"/${PN}-2.14.4-tests.patch + "${FILESDIR}"/${P}-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/files/datasets-2.14.4-tests.patch b/sci-libs/datasets/files/datasets-2.14.4-tests.patch index 5dd322309b20..b9791c04e8e0 100644 --- a/sci-libs/datasets/files/datasets-2.14.4-tests.patch +++ b/sci-libs/datasets/files/datasets-2.14.4-tests.patch @@ -8,16 +8,6 @@ @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_hf_gcp.py 2023-05-04 19:33:31.150825303 +0200 -+++ b/tests/test_hf_gcp.py 2023-05-04 19:40:08.401759538 +0200 -@@ -75,6 +75,7 @@ - self.assertTrue(os.path.exists(datset_info_path)) - - -+@pytest.mark.skip(reason="require apache_beam") - @pytest.mark.integration - def test_as_dataset_from_hf_gcs(tmp_path_factory): - tmp_dir = tmp_path_factory.mktemp("test_hf_gcp") / "test_wikipedia_simple" --- 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 @@ diff --git a/sci-libs/datasets/files/datasets-2.16.0-tests.patch b/sci-libs/datasets/files/datasets-2.16.0-tests.patch deleted file mode 100644 index 8cb89e824b3b..000000000000 --- a/sci-libs/datasets/files/datasets-2.16.0-tests.patch +++ /dev/null @@ -1,133 +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 -@@ -3982,7 +3982,6 @@ - [ - "relative/path", - "/absolute/path", -- "s3://bucket/relative/path", - "hdfs://relative/path", - "hdfs:///absolute/path", - ], ---- 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 -@@ -386,6 +386,7 @@ - hf_modules_cache=self.hf_modules_cache, - ) - -+ @pytest.mark.skip(reason="") - def test_HubDatasetModuleFactoryWithScript_dont_trust_remote_code(self): - # "squad" has a dataset script - factory = HubDatasetModuleFactoryWithScript( -@@ -402,6 +402,7 @@ - ) - self.assertRaises(ValueError, factory.get_module) - -+ @pytest.mark.skip() - def test_HubDatasetModuleFactoryWithScript_with_github_dataset(self): - # "wmt_t2t" has additional imports (internal) - factory = HubDatasetModuleFactoryWithScript( -@@ -411,6 +412,7 @@ - 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( -@@ -419,6 +421,7 @@ - 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) -@@ -1032,6 +1035,7 @@ - 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) -@@ -1153,6 +1157,7 @@ - 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") -@@ -1168,6 +1173,7 @@ - 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 -@@ -47,6 +47,7 @@ - ] - - -+@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 -@@ -18,7 +18,7 @@ - pytestmark = pytest.mark.integration - - --@pytest.mark.parametrize("path", ["paws", csv.__file__]) -+@pytest.mark.parametrize("path", [csv.__file__]) - def test_inspect_dataset(path, tmp_path): - inspect_dataset(path, tmp_path) - script_name = Path(path).stem + ".py" -@@ -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): diff --git a/sci-libs/datasets/files/datasets-2.17.1-tests.patch b/sci-libs/datasets/files/datasets-2.17.1-tests.patch new file mode 100644 index 000000000000..14ae50602d10 --- /dev/null +++ b/sci-libs/datasets/files/datasets-2.17.1-tests.patch @@ -0,0 +1,124 @@ +--- 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", + ], +--- 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): -- cgit v1.2.3