commit: 538628559a52dc95484cb253131a0ff6ff962338
Author: Alfredo Tupone <tupone <AT> gentoo <DOT> org>
AuthorDate: Thu Feb 6 17:32:25 2025 +0000
Commit: Alfredo Tupone <tupone <AT> gentoo <DOT> org>
CommitDate: Thu Feb 6 17:33:41 2025 +0000
URL: https://gitweb.gentoo.org/repo/gentoo.git/commit/?id=53862855
sci-libs/datasets: add 2.21.0
Signed-off-by: Alfredo Tupone <tupone <AT> gentoo.org>
sci-libs/datasets/Manifest | 1 +
sci-libs/datasets/datasets-2.21.0.ebuild | 151 +++++++++++++++++++++
.../datasets/files/datasets-2.21.0-tests.patch | 22 +++
3 files changed, 174 insertions(+)
diff --git a/sci-libs/datasets/Manifest b/sci-libs/datasets/Manifest
index 3c6942a0364e..dde5fd400ab6 100644
--- a/sci-libs/datasets/Manifest
+++ b/sci-libs/datasets/Manifest
@@ -1 +1,2 @@
DIST datasets-2.20.0.gh.tar.gz 2188840 BLAKE2B
3f246c3e069ec31b63dd785ca5e96b5b441cc51318baf91a9aed053c9d5d94de6871fc0f0f8c271a4782998d976407c94c3b7b4beccc60b7a12868685707090b
SHA512
effa3150877ba8269940b47ae0d96d436b7d625ceb102812bbbad805b47b7661102b5ac1c2f16624630bf3039cc4265353f6b71a83122717e73575c7e8c4921f
+DIST datasets-2.21.0.gh.tar.gz 2198480 BLAKE2B
41a5e82013d26644db4f52b16728cee31c6ff27995b8a9b2ddef1512fcda5e9386e47f6726303fec64d5ed7e40432583a6ddcc2bdfbb76096dce5f23b0540149
SHA512
f4193e29505300f98ec026b1ed052ffd3d43ae05a9b191bb56105d703ba2e44752e97c0eeb36dd1b2df6499662915591ab850cdec5248af8c7c5b5a003437c5c
diff --git a/sci-libs/datasets/datasets-2.21.0.ebuild
b/sci-libs/datasets/datasets-2.21.0.ebuild
new file mode 100644
index 000000000000..7dac47f07a8e
--- /dev/null
+++ b/sci-libs/datasets/datasets-2.21.0.ebuild
@@ -0,0 +1,151 @@
+# Copyright 2023-2025 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
+ tests/test_load.py
+ )
+
+ local EPYTEST_DESELECT=(
+
"tests/test_arrow_dataset.py::BaseDatasetTest::test_filter_caching_on_disk"
+
"tests/test_arrow_dataset.py::BaseDatasetTest::test_map_caching_on_disk"
+
"tests/test_arrow_dataset.py::TaskTemplatesTest::test_task_automatic_speech_recognition"
+ "tests/test_distributed.py::test_torch_distributed_run"
+ "tests/test_exceptions.py::test_error_deprecated"
+ "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_iterable_dataset.py::test_iterable_dataset_from_file"
+
"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_f1"
+
"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_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_recall"
+
"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_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/packaged_modules/test_cache.py::test_cache_multi_configs"
+ "tests/packaged_modules/test_cache.py::test_cache_single_config"
+
"tests/test_data_files.py::test_DataFilesList_from_patterns_locally_with_extra_files"
+
"tests/test_data_files.py::test_DataFilesDict_from_patterns_locally_or_remote_hashing"
+
"tests/test_hf_gcp.py::TestDatasetOnHfGcp::test_dataset_info_available_natural_questions/default@19ba7767b174ad046a84f46af056517a3910ee57"
+
"tests/test_hf_gcp.py::TestDatasetOnHfGcp::test_dataset_info_available_wiki40b/en@7b21a2e64b90323b2d3d1b81aa349bb4bc76d9bf"
+
"tests/test_hf_gcp.py::TestDatasetOnHfGcp::test_dataset_info_available_wiki_dpr/psgs_w100.multiset.no_index@b24a417d802a583f8922946c1c75210290e93108"
+
"tests/test_hf_gcp.py::TestDatasetOnHfGcp::test_dataset_info_available_wiki_dpr/psgs_w100.nq.compressed@b24a417d802a583f8922946c1c75210290e93108"
+
"tests/test_hf_gcp.py::TestDatasetOnHfGcp::test_dataset_info_available_wiki_dpr/psgs_w100.nq.no_index@b24a417d802a583f8922946c1c75210290e93108"
+
"tests/test_hf_gcp.py::TestDatasetOnHfGcp::test_dataset_info_available_wikipedia/20220301.de@4d013bdd32c475c8536aae00a56efc774f061649"
+
"tests/test_hf_gcp.py::TestDatasetOnHfGcp::test_dataset_info_available_wikipedia/20220301.en@4d013bdd32c475c8536aae00a56efc774f061649"
+
"tests/test_hf_gcp.py::TestDatasetOnHfGcp::test_dataset_info_available_wikipedia/20220301.fr@4d013bdd32c475c8536aae00a56efc774f061649"
+
"tests/test_hf_gcp.py::TestDatasetOnHfGcp::test_dataset_info_available_wikipedia/20220301.frr@4d013bdd32c475c8536aae00a56efc774f061649"
+
"tests/test_hf_gcp.py::TestDatasetOnHfGcp::test_dataset_info_available_wikipedia/20220301.it@4d013bdd32c475c8536aae00a56efc774f061649"
+
"tests/test_hf_gcp.py::TestDatasetOnHfGcp::test_dataset_info_available_wikipedia/20220301.simple@4d013bdd32c475c8536aae00a56efc774f061649"
+ "tests/test_hf_gcp.py::test_as_dataset_from_hf_gcs"
+ "tests/test_hf_gcp.py::test_as_streaming_dataset_from_hf_gcs"
+ "tests/test_hub.py::test_convert_to_parquet"
+
"tests/test_iterable_dataset.py::test_iterable_dataset_from_hub_torch_dataloader_parallel"
+ "tests/test_offline_util.py::test_offline_with_timeout"
+ "tests/io/test_parquet.py::test_parquet_read_geoparquet"
+ )
+ distutils-r1_src_test
+}
diff --git a/sci-libs/datasets/files/datasets-2.21.0-tests.patch
b/sci-libs/datasets/files/datasets-2.21.0-tests.patch
new file mode 100644
index 000000000000..0a55459db109
--- /dev/null
+++ b/sci-libs/datasets/files/datasets-2.21.0-tests.patch
@@ -0,0 +1,22 @@
+--- 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
+@@ -4131,7 +4131,6 @@
+ [
+ "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
+@@ -1,9 +1,8 @@
+ import shutil
+ import textwrap
+
+ import numpy as np
+ import pytest
+-import soundfile as sf
+
+ from datasets import Audio, ClassLabel, Features, Value
+ from datasets.builder import InvalidConfigName