sci-ml/tokenizers: drop 0.21.4

Signed-off-by: Alfredo Tupone <tupone@gentoo.org>
This commit is contained in:
Alfredo Tupone
2025-11-21 21:18:11 +01:00
parent 4614ed3a10
commit cc17fc9c3c
2 changed files with 0 additions and 145 deletions

View File

@@ -1,6 +1,3 @@
DIST tokenizers-0.21.4-crates.tar.xz 20743760 BLAKE2B ddf6cd0c900c74a0c10232111e600f8a11533ea699c525c2e6a3fa47629c83645893904fb9fd74cb2e2d9ce7211a38807a2346fdd26a251069dcf101dc7c8870 SHA512 99be2a64790df9f17329ccb65243642dd5c9c1ff950be7d6211ef502eb368b05392984bbaca267801b0755aacef552c7b24cfbadb84b1b907fd543702e242d87
DIST tokenizers-0.21.4.gh.tar.gz 1552701 BLAKE2B 6587f635b5194493f45f9975fe154e1c8bd79c3e0d35db2b868567fe772a5a8ed0a5db4df6be013099e5869d1ca2a19fc5f5e80a0882ecdc859a18506596b683 SHA512 7ed897db3b3edfec740c97311cdab072a90d9a8f637a7fbb23d1595b38e9215c840861531ed0e5284d62a669e1760876ee7f26e0db466a8d404464afd1f37e1a
DIST tokenizers-0.22.0-crates.tar.xz 20740996 BLAKE2B fcd0fcd907ae8e9c9aa86eb31ab8aaef5767e9279692dc2c2218673a4b7be73795ca41f91c662e10bfd31eb91af1199e01f8fde1ceb69c189a9bb0c279196b47 SHA512 30bd9df1975ff6388708057e6266f981a8dc65664aab6dd81fb9f884f3631fd56c2ea8f1ac2872f2c566f8a656cf2f36ef1ee4fcebb2cbd74c6b0a0e1b14c373
DIST tokenizers-0.22.1.gh.tar.gz 1563505 BLAKE2B 798193afeef89a93fdd007d1ffa42113df0ed2d9de92c290a4789ab205cc6c34cf68ba62cb44e50606ec54473f05fbd405b295f9193c1c1f8af845c9ce3104c2 SHA512 1a25ee6b218232112f10bc1e082e71ed1960ab7fa62c7341b38cc5f5dc0a735cf35b3e90d4a1c1cc0aedb7c198182c2e559662459a668a2fef4e633096a1cccc
DIST tokenizers-python-0.21.4-crates.tar.xz 10997708 BLAKE2B 1e8aa5a1bc5c2592d310a72b0bed8e301ba7e294643425fe872eb300b97280ce6e5a8d895afe0175c1443096e314053c23b43388d16f1c01f51d9926b0be1ef8 SHA512 bc8a978ebb01c784b538013a8656863aae6a1e25b40c7fb9fde878e4351abaf5a8934a903fb60ac4ce802f8f35ebe393f0e2888759b71689f2f2df4f1c88a02d
DIST tokenizers-python-0.22.1-crates.tar.xz 14184544 BLAKE2B 718c7246fb77568c1aa54e168fce682ef3130e2d51f8b6b0ed5dea96f4dabedfc92e395ef083b514732b8d04fed1d5a5ad1ba4a9667eee0e993616bd5f03184d SHA512 1226e024ab7ad7dc06e191951e2ffa8d30fd575d867d949ad37ffd4fe6a7e491b66a2a767e5d0dbb4b55f8b8eff809baceb11950b811e4e5d685074507060e23

View File

@@ -1,142 +0,0 @@
# Copyright 2023-2025 Gentoo Authors
# Distributed under the terms of the GNU General Public License v2
# Autogenerated by pycargoebuild 0.15.0
EAPI=8
DISTUTILS_USE_PEP517=maturin
PYTHON_COMPAT=( python3_{10..13} )
DISTUTILS_EXT=1
DISTUTILS_SINGLE_IMPL=1
RUST_MIN_VER="1.82.0"
CRATES="
"
inherit cargo distutils-r1
DESCRIPTION="Implementation of today's most used tokenizers"
HOMEPAGE="https://github.com/huggingface/tokenizers"
SRC_URI="
https://github.com/huggingface/${PN}/archive/refs/tags/v${PV}.tar.gz
-> ${P}.gh.tar.gz
${CARGO_CRATE_URIS}
"
if [[ ${PKGBUMPING} != ${PVR} ]]; then
SRC_URI+="
https://dev.gentoo.org/~tupone/distfiles/${P}-crates.tar.xz
https://dev.gentoo.org/~tupone/distfiles/${PN}-python-${PV}-crates.tar.xz
"
fi
LICENSE="Apache-2.0"
# Dependent crate licenses
LICENSE+="
Apache-2.0 Apache-2.0-with-LLVM-exceptions BSD-2 BSD ISC MIT MPL-2.0
Unicode-DFS-2016
"
SLOT="0"
KEYWORDS="~amd64"
RDEPEND="dev-libs/oniguruma"
BDEPEND="
test? ( sci-ml/datasets[${PYTHON_SINGLE_USEDEP}] )
$(python_gen_cond_dep '
dev-python/setuptools-rust[${PYTHON_USEDEP}]
')
"
distutils_enable_tests pytest
QA_FLAGS_IGNORED=".*/site-packages/tokenizers/.*so"
src_unpack() {
cargo_src_unpack
}
pkg_setup() {
python-single-r1_pkg_setup
rust_pkg_setup
}
src_prepare() {
default
cd bindings/python
eapply "${FILESDIR}"/${PN}-0.21.2-test.patch
distutils-r1_src_prepare
}
src_configure() {
cd tokenizers
cargo_src_configure
cd ../bindings/python
distutils-r1_src_configure
}
src_compile() {
export RUSTONIG_SYSTEM_LIBONIG=1
cd tokenizers
cargo_src_compile
cd ../bindings/python
distutils-r1_src_compile
}
src_test() {
cd tokenizers
# Tests do not work
#cargo_src_test
cd ../bindings/python
local -x EPYTEST_IGNORE=( benches/ )
local -x EPYTEST_DESELECT=(
tests/bindings/test_encoding.py::TestEncoding::test_sequence_ids
tests/bindings/test_encoding.py::TestEncoding::test_n_sequences
tests/bindings/test_encoding.py::TestEncoding::test_word_to_tokens
tests/bindings/test_encoding.py::TestEncoding::test_word_to_chars
tests/bindings/test_encoding.py::TestEncoding::test_token_to_sequence
tests/bindings/test_encoding.py::TestEncoding::test_token_to_chars
tests/bindings/test_encoding.py::TestEncoding::test_token_to_word
tests/bindings/test_encoding.py::TestEncoding::test_char_to_token
tests/bindings/test_encoding.py::TestEncoding::test_char_to_word
tests/bindings/test_encoding.py::TestEncoding::test_truncation
tests/bindings/test_encoding.py::TestEncoding::test_invalid_truncate_direction
tests/bindings/test_models.py::TestBPE::test_instantiate
tests/bindings/test_models.py::TestWordLevel::test_instantiate
tests/bindings/test_models.py::TestWordPiece::test_instantiate
tests/bindings/test_processors.py::TestByteLevelProcessing::test_processing
tests/bindings/test_trainers.py::TestUnigram::test_continuing_prefix_trainer_mismatch
tests/bindings/test_trainers.py::TestUnigram::test_train
tests/bindings/test_trainers.py::TestUnigram::test_train_parallelism_with_custom_pretokenizer
tests/documentation/test_pipeline.py::TestPipeline::test_pipeline
tests/documentation/test_pipeline.py::TestPipeline::test_bert_example
tests/implementations/test_char_bpe.py::TestCharBPETokenizer::test_basic_encode
tests/implementations/test_char_bpe.py::TestCharBPETokenizer::test_lowercase
tests/implementations/test_char_bpe.py::TestCharBPETokenizer::test_decoding
tests/implementations/test_char_bpe.py::TestCharBPETokenizer::test_multiprocessing_with_parallelism
tests/test_serialization.py::TestSerialization::test_full_serialization_albert
tests/test_serialization.py::TestSerialization::test_str_big
tests/bindings/test_tokenizer.py::TestTokenizer::test_encode_formats
tests/bindings/test_tokenizer.py::TestTokenizer::test_encode_add_special_tokens
tests/bindings/test_tokenizer.py::TestTokenizer::test_from_pretrained
tests/bindings/test_tokenizer.py::TestTokenizer::test_from_pretrained_revision
tests/bindings/test_tokenizer.py::TestTokenizer::test_encode_special_tokens
tests/bindings/test_tokenizer.py::TestTokenizer::test_splitting
tests/documentation/test_quicktour.py::TestQuicktour::test_quicktour
tests/documentation/test_tutorial_train_from_iterators.py::TestTrainFromIterators::test_datasets
tests/documentation/test_tutorial_train_from_iterators.py::TestTrainFromIterators::test_gzip
tests/implementations/test_bert_wordpiece.py::TestBertWordPieceTokenizer::test_basic_encode
tests/implementations/test_bert_wordpiece.py::TestBertWordPieceTokenizer::test_multiprocessing_with_parallelism
tests/implementations/test_byte_level_bpe.py::TestByteLevelBPE::test_basic_encode
tests/implementations/test_byte_level_bpe.py::TestByteLevelBPE::test_add_prefix_space
tests/implementations/test_byte_level_bpe.py::TestByteLevelBPE::test_lowerspace
tests/implementations/test_byte_level_bpe.py::TestByteLevelBPE::test_multiprocessing_with_parallelism
)
distutils-r1_src_test
}
src_install() {
cd tokenizers
cd ../bindings/python
distutils-r1_src_install
}