Index: textproc/py-tokenizers/Makefile =================================================================== RCS file: /cvs/ports/textproc/py-tokenizers/Makefile,v diff -u -p -u -r1.2 Makefile --- textproc/py-tokenizers/Makefile 12 Aug 2026 19:32:48 -0000 1.2 +++ textproc/py-tokenizers/Makefile 14 Oct 2026 17:59:25 -0000 @@ -1,6 +1,7 @@ COMMENT= tokenizers with a focus on performance MODPY_DISTV= 0.23.1 +REVISION= 0 DISTNAME= tokenizers-${MODPY_DISTV} PKGNAME= py-${DISTNAME} @@ -19,7 +20,18 @@ MODULES= lang/python MODPY_PI= Yes MODPY_PYBUILD= maturin -BUILD_DEPENDS= textproc/oniguruma +LIB_DEPENDS= textproc/oniguruma +WANTLIB += ${COMPILER_LIBCXX} c m onig +RUN_DEPENDS= devel/py-huggingface-hub>=0.16.4,<2.0 + +# Let Maturin read the Python metadata outside the Rust workspace. +do-build: + ${MODCARGO_CARGO_RUN} build --release ${MODCARGO_BUILD_ARGS} .include "crates.inc" +MODPY_PYTEST_ARGS = bindings/python/tests + +# Documentation tutorials require datasets and large online corpora. +MODPY_TEST_DIR = ${WRKSRC}/bindings/python +MODPY_PYTEST_ARGS = tests -m 'not network' --ignore=tests/documentation .include Index: textproc/py-tokenizers/pkg/PLIST =================================================================== RCS file: /cvs/ports/textproc/py-tokenizers/pkg/PLIST,v diff -u -p -u -r1.1.1.1 PLIST --- textproc/py-tokenizers/pkg/PLIST 19 Jul 2026 19:15:38 -0000 1.1.1.1 +++ textproc/py-tokenizers/pkg/PLIST 14 Oct 2026 17:59:25 -0000 @@ -1,10 +1,82 @@ lib/python${MODPY_VERSION}/site-packages/tokenizers/ +lib/python${MODPY_VERSION}/site-packages/tokenizers-${MODPY_DISTV}.dist-info/ +lib/python${MODPY_VERSION}/site-packages/tokenizers-${MODPY_DISTV}.dist-info/METADATA +lib/python${MODPY_VERSION}/site-packages/tokenizers-${MODPY_DISTV}.dist-info/RECORD +lib/python${MODPY_VERSION}/site-packages/tokenizers-${MODPY_DISTV}.dist-info/WHEEL lib/python${MODPY_VERSION}/site-packages/tokenizers/__init__.py +lib/python${MODPY_VERSION}/site-packages/tokenizers/__init__.pyi lib/python${MODPY_VERSION}/site-packages/tokenizers/${MODPY_PYCACHE}/ lib/python${MODPY_VERSION}/site-packages/tokenizers/${MODPY_PYCACHE}__init__.${MODPY_PYC_MAGIC_TAG}${MODPY_PYOEXTENSION} lib/python${MODPY_VERSION}/site-packages/tokenizers/${MODPY_PYCACHE}__init__.${MODPY_PYC_MAGIC_TAG}pyc +lib/python${MODPY_VERSION}/site-packages/tokenizers/decoders/ +lib/python${MODPY_VERSION}/site-packages/tokenizers/decoders.pyi +lib/python${MODPY_VERSION}/site-packages/tokenizers/decoders/__init__.py +lib/python${MODPY_VERSION}/site-packages/tokenizers/decoders/${MODPY_PYCACHE}/ +lib/python${MODPY_VERSION}/site-packages/tokenizers/decoders/${MODPY_PYCACHE}__init__.${MODPY_PYC_MAGIC_TAG}${MODPY_PYOEXTENSION} +lib/python${MODPY_VERSION}/site-packages/tokenizers/decoders/${MODPY_PYCACHE}__init__.${MODPY_PYC_MAGIC_TAG}pyc +lib/python${MODPY_VERSION}/site-packages/tokenizers/implementations/ +lib/python${MODPY_VERSION}/site-packages/tokenizers/implementations/__init__.py +lib/python${MODPY_VERSION}/site-packages/tokenizers/implementations/${MODPY_PYCACHE}/ +lib/python${MODPY_VERSION}/site-packages/tokenizers/implementations/${MODPY_PYCACHE}__init__.${MODPY_PYC_MAGIC_TAG}${MODPY_PYOEXTENSION} +lib/python${MODPY_VERSION}/site-packages/tokenizers/implementations/${MODPY_PYCACHE}__init__.${MODPY_PYC_MAGIC_TAG}pyc +lib/python${MODPY_VERSION}/site-packages/tokenizers/implementations/${MODPY_PYCACHE}base_tokenizer.${MODPY_PYC_MAGIC_TAG}${MODPY_PYOEXTENSION} +lib/python${MODPY_VERSION}/site-packages/tokenizers/implementations/${MODPY_PYCACHE}base_tokenizer.${MODPY_PYC_MAGIC_TAG}pyc +lib/python${MODPY_VERSION}/site-packages/tokenizers/implementations/${MODPY_PYCACHE}bert_wordpiece.${MODPY_PYC_MAGIC_TAG}${MODPY_PYOEXTENSION} +lib/python${MODPY_VERSION}/site-packages/tokenizers/implementations/${MODPY_PYCACHE}bert_wordpiece.${MODPY_PYC_MAGIC_TAG}pyc +lib/python${MODPY_VERSION}/site-packages/tokenizers/implementations/${MODPY_PYCACHE}byte_level_bpe.${MODPY_PYC_MAGIC_TAG}${MODPY_PYOEXTENSION} +lib/python${MODPY_VERSION}/site-packages/tokenizers/implementations/${MODPY_PYCACHE}byte_level_bpe.${MODPY_PYC_MAGIC_TAG}pyc +lib/python${MODPY_VERSION}/site-packages/tokenizers/implementations/${MODPY_PYCACHE}char_level_bpe.${MODPY_PYC_MAGIC_TAG}${MODPY_PYOEXTENSION} +lib/python${MODPY_VERSION}/site-packages/tokenizers/implementations/${MODPY_PYCACHE}char_level_bpe.${MODPY_PYC_MAGIC_TAG}pyc +lib/python${MODPY_VERSION}/site-packages/tokenizers/implementations/${MODPY_PYCACHE}sentencepiece_bpe.${MODPY_PYC_MAGIC_TAG}${MODPY_PYOEXTENSION} +lib/python${MODPY_VERSION}/site-packages/tokenizers/implementations/${MODPY_PYCACHE}sentencepiece_bpe.${MODPY_PYC_MAGIC_TAG}pyc +lib/python${MODPY_VERSION}/site-packages/tokenizers/implementations/${MODPY_PYCACHE}sentencepiece_unigram.${MODPY_PYC_MAGIC_TAG}${MODPY_PYOEXTENSION} +lib/python${MODPY_VERSION}/site-packages/tokenizers/implementations/${MODPY_PYCACHE}sentencepiece_unigram.${MODPY_PYC_MAGIC_TAG}pyc +lib/python${MODPY_VERSION}/site-packages/tokenizers/implementations/base_tokenizer.py +lib/python${MODPY_VERSION}/site-packages/tokenizers/implementations/bert_wordpiece.py +lib/python${MODPY_VERSION}/site-packages/tokenizers/implementations/byte_level_bpe.py +lib/python${MODPY_VERSION}/site-packages/tokenizers/implementations/char_level_bpe.py +lib/python${MODPY_VERSION}/site-packages/tokenizers/implementations/sentencepiece_bpe.py +lib/python${MODPY_VERSION}/site-packages/tokenizers/implementations/sentencepiece_unigram.py +lib/python${MODPY_VERSION}/site-packages/tokenizers/models/ +lib/python${MODPY_VERSION}/site-packages/tokenizers/models.pyi +lib/python${MODPY_VERSION}/site-packages/tokenizers/models/__init__.py +lib/python${MODPY_VERSION}/site-packages/tokenizers/models/${MODPY_PYCACHE}/ +lib/python${MODPY_VERSION}/site-packages/tokenizers/models/${MODPY_PYCACHE}__init__.${MODPY_PYC_MAGIC_TAG}${MODPY_PYOEXTENSION} +lib/python${MODPY_VERSION}/site-packages/tokenizers/models/${MODPY_PYCACHE}__init__.${MODPY_PYC_MAGIC_TAG}pyc +lib/python${MODPY_VERSION}/site-packages/tokenizers/normalizers/ +lib/python${MODPY_VERSION}/site-packages/tokenizers/normalizers.pyi +lib/python${MODPY_VERSION}/site-packages/tokenizers/normalizers/__init__.py +lib/python${MODPY_VERSION}/site-packages/tokenizers/normalizers/${MODPY_PYCACHE}/ +lib/python${MODPY_VERSION}/site-packages/tokenizers/normalizers/${MODPY_PYCACHE}__init__.${MODPY_PYC_MAGIC_TAG}${MODPY_PYOEXTENSION} +lib/python${MODPY_VERSION}/site-packages/tokenizers/normalizers/${MODPY_PYCACHE}__init__.${MODPY_PYC_MAGIC_TAG}pyc +lib/python${MODPY_VERSION}/site-packages/tokenizers/pre_tokenizers/ +lib/python${MODPY_VERSION}/site-packages/tokenizers/pre_tokenizers.pyi +lib/python${MODPY_VERSION}/site-packages/tokenizers/pre_tokenizers/__init__.py +lib/python${MODPY_VERSION}/site-packages/tokenizers/pre_tokenizers/${MODPY_PYCACHE}/ +lib/python${MODPY_VERSION}/site-packages/tokenizers/pre_tokenizers/${MODPY_PYCACHE}__init__.${MODPY_PYC_MAGIC_TAG}${MODPY_PYOEXTENSION} +lib/python${MODPY_VERSION}/site-packages/tokenizers/pre_tokenizers/${MODPY_PYCACHE}__init__.${MODPY_PYC_MAGIC_TAG}pyc +lib/python${MODPY_VERSION}/site-packages/tokenizers/processors/ +lib/python${MODPY_VERSION}/site-packages/tokenizers/processors.pyi +lib/python${MODPY_VERSION}/site-packages/tokenizers/processors/__init__.py +lib/python${MODPY_VERSION}/site-packages/tokenizers/processors/${MODPY_PYCACHE}/ +lib/python${MODPY_VERSION}/site-packages/tokenizers/processors/${MODPY_PYCACHE}__init__.${MODPY_PYC_MAGIC_TAG}${MODPY_PYOEXTENSION} +lib/python${MODPY_VERSION}/site-packages/tokenizers/processors/${MODPY_PYCACHE}__init__.${MODPY_PYC_MAGIC_TAG}pyc +lib/python${MODPY_VERSION}/site-packages/tokenizers/py.typed @so lib/python${MODPY_VERSION}/site-packages/tokenizers/tokenizers${MODPY_ABI3SO}.so -lib/python${MODPY_VERSION}/site-packages/tokenizers_python-${MODPY_DISTV}.dist-info/ -lib/python${MODPY_VERSION}/site-packages/tokenizers_python-${MODPY_DISTV}.dist-info/METADATA -lib/python${MODPY_VERSION}/site-packages/tokenizers_python-${MODPY_DISTV}.dist-info/RECORD -lib/python${MODPY_VERSION}/site-packages/tokenizers_python-${MODPY_DISTV}.dist-info/WHEEL +lib/python${MODPY_VERSION}/site-packages/tokenizers/tokenizers.pyi +lib/python${MODPY_VERSION}/site-packages/tokenizers/tools/ +lib/python${MODPY_VERSION}/site-packages/tokenizers/tools/__init__.py +lib/python${MODPY_VERSION}/site-packages/tokenizers/tools/${MODPY_PYCACHE}/ +lib/python${MODPY_VERSION}/site-packages/tokenizers/tools/${MODPY_PYCACHE}__init__.${MODPY_PYC_MAGIC_TAG}${MODPY_PYOEXTENSION} +lib/python${MODPY_VERSION}/site-packages/tokenizers/tools/${MODPY_PYCACHE}__init__.${MODPY_PYC_MAGIC_TAG}pyc +lib/python${MODPY_VERSION}/site-packages/tokenizers/tools/${MODPY_PYCACHE}visualizer.${MODPY_PYC_MAGIC_TAG}${MODPY_PYOEXTENSION} +lib/python${MODPY_VERSION}/site-packages/tokenizers/tools/${MODPY_PYCACHE}visualizer.${MODPY_PYC_MAGIC_TAG}pyc +lib/python${MODPY_VERSION}/site-packages/tokenizers/tools/visualizer-styles.css +lib/python${MODPY_VERSION}/site-packages/tokenizers/tools/visualizer.py +lib/python${MODPY_VERSION}/site-packages/tokenizers/trainers/ +lib/python${MODPY_VERSION}/site-packages/tokenizers/trainers.pyi +lib/python${MODPY_VERSION}/site-packages/tokenizers/trainers/__init__.py +lib/python${MODPY_VERSION}/site-packages/tokenizers/trainers/__init__.pyi +lib/python${MODPY_VERSION}/site-packages/tokenizers/trainers/${MODPY_PYCACHE}/ +lib/python${MODPY_VERSION}/site-packages/tokenizers/trainers/${MODPY_PYCACHE}__init__.${MODPY_PYC_MAGIC_TAG}${MODPY_PYOEXTENSION} +lib/python${MODPY_VERSION}/site-packages/tokenizers/trainers/${MODPY_PYCACHE}__init__.${MODPY_PYC_MAGIC_TAG}pyc