diff options
Diffstat (limited to 'textproc/py-tokenizer')
| -rw-r--r-- | textproc/py-tokenizer/Makefile | 22 | ||||
| -rw-r--r-- | textproc/py-tokenizer/distinfo | 3 | ||||
| -rw-r--r-- | textproc/py-tokenizer/pkg-descr | 5 |
3 files changed, 30 insertions, 0 deletions
diff --git a/textproc/py-tokenizer/Makefile b/textproc/py-tokenizer/Makefile new file mode 100644 index 000000000000..b4ad88c9c8d9 --- /dev/null +++ b/textproc/py-tokenizer/Makefile @@ -0,0 +1,22 @@ +PORTNAME= tokenizer +PORTVERSION= 3.5.0 +PORTREVISION= 1 +CATEGORIES= textproc python +MASTER_SITES= PYPI +PKGNAMEPREFIX= ${PYTHON_PKGNAMEPREFIX} + +MAINTAINER= otis@FreeBSD.org +COMMENT= Tokenizer for Icelandic text +WWW= https://github.com/mideind/Tokenizer + +LICENSE= MIT + +BUILD_DEPENDS= ${PY_SETUPTOOLS} \ + ${PYTHON_PKGNAMEPREFIX}wheel>0:devel/py-wheel@${PY_FLAVOR} + +USES= python +USE_PYTHON= autoplist concurrent pep517 + +NO_ARCH= yes + +.include <bsd.port.mk> diff --git a/textproc/py-tokenizer/distinfo b/textproc/py-tokenizer/distinfo new file mode 100644 index 000000000000..5002d345dfbd --- /dev/null +++ b/textproc/py-tokenizer/distinfo @@ -0,0 +1,3 @@ +TIMESTAMP = 1756293103 +SHA256 (tokenizer-3.5.0.tar.gz) = f26694d6be85815d23db167ee9b1c9e2ed7b672cfc8b9baa607ba3aba6070727 +SIZE (tokenizer-3.5.0.tar.gz) = 127323 diff --git a/textproc/py-tokenizer/pkg-descr b/textproc/py-tokenizer/pkg-descr new file mode 100644 index 000000000000..c1f700edffe5 --- /dev/null +++ b/textproc/py-tokenizer/pkg-descr @@ -0,0 +1,5 @@ +Tokenizer: A tokenizer for Icelandic text + +Tokenization is a necessary first step in many natural language processing +tasks, such as word counting, parsing, spell checking, corpus generation, and +statistical analysis of text. |