diff options
author | V3n3RiX <venerix@koprulu.sector> | 2023-08-26 09:56:45 +0100 |
---|---|---|
committer | V3n3RiX <venerix@koprulu.sector> | 2023-08-26 09:56:45 +0100 |
commit | f3471ff11210507b38c09f0e57df1bd601f629a5 (patch) | |
tree | 9931bc74efae95f78cd0270fde107c779d2dd482 /sci-libs/datasets | |
parent | 5e5fb5c6d1e0af4b12dbee7de7d095df902ce2b6 (diff) |
gentoo auto-resync : 26:08:2023 - 09:56:44
Diffstat (limited to 'sci-libs/datasets')
-rw-r--r-- | sci-libs/datasets/Manifest | 3 | ||||
-rw-r--r-- | sci-libs/datasets/datasets-2.14.4.ebuild | 59 | ||||
-rw-r--r-- | sci-libs/datasets/files/datasets-2.14.4-tests.patch | 242 |
3 files changed, 304 insertions, 0 deletions
diff --git a/sci-libs/datasets/Manifest b/sci-libs/datasets/Manifest index 81f65f126c14..5f8ba17d48e0 100644 --- a/sci-libs/datasets/Manifest +++ b/sci-libs/datasets/Manifest @@ -1,9 +1,12 @@ AUX datasets-2.11.0-tests.patch 8489 BLAKE2B fc53b22427f96255aa9d74ecc4eaa1e38d14893819927af523fccf496cf0fef7ffabd98a600d21a749eb6e03d8af591ec2bd2cd0bc16c427a6e4953c1d4b52a4 SHA512 dce48c7d93adee9c70278e48dc45c50877132205ce40476212d083043fed9ba0786841cd9df68f91e7df81499c1262ead1b0e923954ad63c97c7e9553f0202c1 AUX datasets-2.12.0-tests.patch 8572 BLAKE2B 7be2fb4a6f39376749160ed3f73852e98ce5139629e28ac1d3dd8c5357e90221fcfead3ef9e23378a4781d19a1804cc433a086279b4c03d2cf37c4ae74947ebc SHA512 727a6e4f035060f40fe476e4d022d097c69f241044e25a216c85ca21352c45cee189622076f62de3c19d616328e7c68c5c77fc611db5d75505465cf9c35bf7d4 +AUX datasets-2.14.4-tests.patch 8616 BLAKE2B 8a65d1315b27658a5f741ebc022c83692252a4833ec4d7b79873799c2bb4bb68534a9e13e7fae1c9a6c051b3615fbb783e6e7885ed93968b31aea6629b4116c4 SHA512 2c6d27c297995466a0aebefa46e86113bdce7d84ea00bb1630549fc379fbb51d66f8f01a8d098d56ec2b26d5200f129460567abdbf6a63d4e2a61372fbfbc6a3 DIST datasets-2.11.0.gh.tar.gz 2141289 BLAKE2B 0fb471dd6ee5de3831eb6586c4a15e67381262470b72d5ab02ee87dfc7977cb4d40e04da6507049d1e47cb8948cad11988bb7627293b48231e1cd413d2cfb885 SHA512 9ec2274d7978e3dde1b2f8ce78dd65bdf66742bbfee7b8672af46216aeaae3ef5c4604a8a5ea0bdee808f1c362cca9a122c16d2e9a161678148e581e4cd5c863 DIST datasets-2.12.0.gh.tar.gz 2149274 BLAKE2B 8f188901dfe293ac2b673f37e0d135e01a8f131adf9030ef1815ce2faa7ba0b36faf64a002cae1ced2d3ed5b7f50f43ba5cda90ab9254fd5f66bbfaed6085f3f SHA512 7389a1c6ee8ff4cda39a2c3f52218aa6f4b1cd6b45f48f83bfa2191359a8999d54153120d968b3cf7e5e932f88822783578e3d859dcb20f38fb0d915d88220c9 DIST datasets-2.13.1.gh.tar.gz 2166516 BLAKE2B 2269434b94145837e491ec6784218f6972df94a558b9067020076fb44dd937a103e3c57dd3761bb0a4cb3c3b6248299ec2a6c3f03c5bd016daaa8957591bf7b6 SHA512 3d2d1aad86b6a472cd6d0e6c661d4730cc0ed1a0fff55c739fc6a0ba68a8f53ae8789029553abd713d0b30648dd020f1880b2d8110c72b5c89a320c2b24f7752 +DIST datasets-2.14.4.gh.tar.gz 2142214 BLAKE2B d4c98a9f29ca748c3c20f32b9a89f053cf6327f56353341ba0073d3b5561ed9aea372d2fa74cadfa8b0f2ba0f6c2e9b3181cca9724719cfe3969f36bbb893f11 SHA512 c3a0701dd83474f4a0d839fe4ef56cfccc9f1d45b6506d44d0f9100bc9dbc90014d16c8e0090dc13f3b2d963bd96af45281bde6e3d7af230467ec7dd26204aa3 EBUILD datasets-2.11.0-r2.ebuild 1367 BLAKE2B f129b98ae08b8005488fa53ee8d607da83d1a334ee660bda871557db3faab9d754e29b7e486d5dcf3bbb4cc1f042fc6b8e786c13b5cf42a70e8aad088e5642fb SHA512 0875cc6352ea35e3637870493cbc967f9195f6289bfb6bad0e45475a99fdebcab7b48a96a9e0bf23aa4ef5f9a42f916486808d4062ca5b12667ac207b13e667f EBUILD datasets-2.12.0.ebuild 1413 BLAKE2B 724c604de725621a71ca2d9b2ce9fc6dae60856ba03c443649e9ab991bfee8a8e5ec2f4b2ab9d0170a73864cd2b0ac297a4e59a702ed16cb37711a71246de306 SHA512 b323d37992f40d398f330547ea5f15419d002bf39014a207a297a3e8411615ec146367369be8d1e7366dcae22a0a785ddf61a2e8a823a4f069081d370bdcbc55 EBUILD datasets-2.13.1.ebuild 1552 BLAKE2B 8a25859177dce337ab70c33c7828c43eeb50f7cb96e182c46aa983e5ead757e4b0caf142a65060466b7eea6dd088ed31f183b9e26e8d95117b56514b37317090 SHA512 ea272cf93cdfd2bbad01bca127051fa94243ae7ecaf026b85aed4b76424e702b03a768526f63aa88d837b0da413f37e68c1465194d478f14b4b018ec4148cc7f +EBUILD datasets-2.14.4.ebuild 1544 BLAKE2B 31e31a85d2c483f90f86195828e5f3eaff531096c26e932d59d637f885fb638fc287cc6a6675ec98d07f135a489bd98159964052104e6049c37766328b71ae95 SHA512 c3b32db313a118c92d9ecb63720b490be5e37e6b936e603170683cee4e837294492a5c20ebf75662c9265dc6f50a28a0eba339b7330bd44b3f6ee65aba332ae0 MISC metadata.xml 379 BLAKE2B 48ebb9e7bfa8b58b0d15b82c4146def465e08cf3212ab4af04129d09c153b67b00d0fa05b94d6af54f643ec3a202f2335d3254b966f49d1394d3c7b9e5da56a5 SHA512 99560decfaa0e438980f372d99257695e9ca9585167d9aba091e0b775c2f8384657ddc017841c8f06f8b568017a54fb9e31da736f3c875da717e154cdce876d1 diff --git a/sci-libs/datasets/datasets-2.14.4.ebuild b/sci-libs/datasets/datasets-2.14.4.ebuild new file mode 100644 index 000000000000..08ed796e9c2d --- /dev/null +++ b/sci-libs/datasets/datasets-2.14.4.ebuild @@ -0,0 +1,59 @@ +# Copyright 2023 Gentoo Authors +# Distributed under the terms of the GNU General Public License v2 + +EAPI=8 + +DISTUTILS_USE_PEP517=setuptools +PYTHON_COMPAT=( python3_{9..11} ) +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}] + $(python_gen_cond_dep ' + dev-python/absl-py[${PYTHON_USEDEP}] + dev-python/aiohttp[${PYTHON_USEDEP}] + dev-python/fsspec[${PYTHON_USEDEP}] + dev-python/multiprocess[${PYTHON_USEDEP}] + dev-python/pandas[${PYTHON_USEDEP}] + dev-python/pyarrow[${PYTHON_USEDEP},parquet,snappy] + dev-python/tqdm[${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? ( + $(python_gen_cond_dep ' + dev-python/pytest-datadir[${PYTHON_USEDEP}] + dev-python/decorator[${PYTHON_USEDEP}] + =dev-python/sqlalchemy-1*[${PYTHON_USEDEP}] + sci-libs/jiwer[${PYTHON_USEDEP}] + sci-libs/seqeval[${PYTHON_USEDEP}] + ') +)" + +PATCHES=( "${FILESDIR}"/${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 +} diff --git a/sci-libs/datasets/files/datasets-2.14.4-tests.patch b/sci-libs/datasets/files/datasets-2.14.4-tests.patch new file mode 100644 index 000000000000..5dd322309b20 --- /dev/null +++ b/sci-libs/datasets/files/datasets-2.14.4-tests.patch @@ -0,0 +1,242 @@ +--- 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_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 @@ + 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_arrow_dataset.py 2023-05-06 15:36:11.080459079 +0200 ++++ b/tests/test_arrow_dataset.py 2023-05-06 15:38:07.452828528 +0200 +@@ -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_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", + [ |