git: 3e4273e9141c - main - textproc/en-core-web-sm: New port: English spaCy model for natural language processing
- Go to: [ bottom of page ] [ top of archives ] [ this month ]
Date: Tue, 17 Mar 2026 07:52:57 UTC
The branch main has been updated by yuri:
URL: https://cgit.FreeBSD.org/ports/commit/?id=3e4273e9141c3c4e0a8fe427c3b5563ddb86681f
commit 3e4273e9141c3c4e0a8fe427c3b5563ddb86681f
Author: Yuri Victorovich <yuri@FreeBSD.org>
AuthorDate: 2026-03-17 03:08:33 +0000
Commit: Yuri Victorovich <yuri@FreeBSD.org>
CommitDate: 2026-03-17 07:52:50 +0000
textproc/en-core-web-sm: New port: English spaCy model for natural language processing
---
textproc/Makefile | 1 +
textproc/en-core-web-sm/Makefile | 33 +++++++++++++++++++++++++++++++++
textproc/en-core-web-sm/distinfo | 3 +++
textproc/en-core-web-sm/pkg-descr | 13 +++++++++++++
textproc/en-core-web-sm/pkg-plist | 35 +++++++++++++++++++++++++++++++++++
5 files changed, 85 insertions(+)
diff --git a/textproc/Makefile b/textproc/Makefile
index f2688e6fda8b..3b7bdd066da0 100644
--- a/textproc/Makefile
+++ b/textproc/Makefile
@@ -183,6 +183,7 @@
SUBDIR += elasticsearch7
SUBDIR += elasticsearch8
SUBDIR += en-aspell
+ SUBDIR += en-core-web-sm
SUBDIR += en-hunspell
SUBDIR += en-mythes
SUBDIR += enchant
diff --git a/textproc/en-core-web-sm/Makefile b/textproc/en-core-web-sm/Makefile
new file mode 100644
index 000000000000..61d2ab344504
--- /dev/null
+++ b/textproc/en-core-web-sm/Makefile
@@ -0,0 +1,33 @@
+PORTNAME= en-core-web-sm
+DISTVERSION= 3.8.0
+CATEGORIES= textproc python
+MASTER_SITES= https://github.com/explosion/spacy-models/releases/download/${PORTNAME}-${DISTVERSION}/
+PKGNAMEPREFIX= ${PYTHON_PKGNAMEPREFIX}
+DISTNAME= en_core_web_sm-${DISTVERSION}-py3-none-any
+EXTRACT_SUFX= .whl
+
+MAINTAINER= yuri@FreeBSD.org
+COMMENT= English spaCy model for natural language processing
+WWW= https://github.com/explosion/spacy-models
+
+LICENSE= MIT
+
+EXTRACT_DEPENDS= ${UNZIP_CMD}:archivers/unzip
+RUN_DEPENDS= ${PYTHON_PKGNAMEPREFIX}spacy>=3.8.0:textproc/py-spacy@${PY_FLAVOR}
+
+USES= python
+USE_PYTHON= flavors
+
+NO_ARCH= yes
+NO_BUILD= yes
+
+EXTRACT_CMD= ${UNZIP_CMD}
+EXTRACT_BEFORE_ARGS= -qo
+EXTRACT_AFTER_ARGS= -d ${WRKDIR}
+
+do-install:
+ @${MKDIR} ${STAGEDIR}${PYTHON_SITELIBDIR}
+ cd ${WRKDIR} && ${COPYTREE_SHARE} en_core_web_sm ${STAGEDIR}${PYTHON_SITELIBDIR}
+ cd ${WRKDIR} && ${COPYTREE_SHARE} "en_core_web_sm-${DISTVERSION}.dist-info" ${STAGEDIR}${PYTHON_SITELIBDIR}
+
+.include <bsd.port.mk>
diff --git a/textproc/en-core-web-sm/distinfo b/textproc/en-core-web-sm/distinfo
new file mode 100644
index 000000000000..89eeda36f77e
--- /dev/null
+++ b/textproc/en-core-web-sm/distinfo
@@ -0,0 +1,3 @@
+TIMESTAMP = 1773716460
+SHA256 (en_core_web_sm-3.8.0-py3-none-any.whl) = 1932429db727d4bff3deed6b34cfc05df17794f4a52eeb26cf8928f7c1a0fb85
+SIZE (en_core_web_sm-3.8.0-py3-none-any.whl) = 12806118
diff --git a/textproc/en-core-web-sm/pkg-descr b/textproc/en-core-web-sm/pkg-descr
new file mode 100644
index 000000000000..f137dc27b681
--- /dev/null
+++ b/textproc/en-core-web-sm/pkg-descr
@@ -0,0 +1,13 @@
+English language model for spaCy natural language processing library.
+
+This model includes vocabulary, syntax and entities trained on written web text
+(blogs, news, comments), optimized for small size and efficiency.
+
+Model details:
+- Language: English (en)
+- Type: Core web (general purpose)
+- Size: Small (sm)
+- Components: tok2vec, tagger, parser, senter, ner, attribute_ruler, lemmatizer
+
+This package is required by applications that need English language support
+with spaCy, such as text-to-speech engines and other NLP applications.
diff --git a/textproc/en-core-web-sm/pkg-plist b/textproc/en-core-web-sm/pkg-plist
new file mode 100644
index 000000000000..d0b945da927e
--- /dev/null
+++ b/textproc/en-core-web-sm/pkg-plist
@@ -0,0 +1,35 @@
+%%PYTHON_SITELIBDIR%%/en_core_web_sm-3.8.0.dist-info/LICENSE
+%%PYTHON_SITELIBDIR%%/en_core_web_sm-3.8.0.dist-info/LICENSES_SOURCES
+%%PYTHON_SITELIBDIR%%/en_core_web_sm-3.8.0.dist-info/METADATA
+%%PYTHON_SITELIBDIR%%/en_core_web_sm-3.8.0.dist-info/RECORD
+%%PYTHON_SITELIBDIR%%/en_core_web_sm-3.8.0.dist-info/WHEEL
+%%PYTHON_SITELIBDIR%%/en_core_web_sm-3.8.0.dist-info/entry_points.txt
+%%PYTHON_SITELIBDIR%%/en_core_web_sm-3.8.0.dist-info/top_level.txt
+%%PYTHON_SITELIBDIR%%/en_core_web_sm/__init__.py
+%%PYTHON_SITELIBDIR%%/en_core_web_sm/en_core_web_sm-3.8.0/LICENSE
+%%PYTHON_SITELIBDIR%%/en_core_web_sm/en_core_web_sm-3.8.0/LICENSES_SOURCES
+%%PYTHON_SITELIBDIR%%/en_core_web_sm/en_core_web_sm-3.8.0/README.md
+%%PYTHON_SITELIBDIR%%/en_core_web_sm/en_core_web_sm-3.8.0/accuracy.json
+%%PYTHON_SITELIBDIR%%/en_core_web_sm/en_core_web_sm-3.8.0/attribute_ruler/patterns
+%%PYTHON_SITELIBDIR%%/en_core_web_sm/en_core_web_sm-3.8.0/config.cfg
+%%PYTHON_SITELIBDIR%%/en_core_web_sm/en_core_web_sm-3.8.0/lemmatizer/lookups/lookups.bin
+%%PYTHON_SITELIBDIR%%/en_core_web_sm/en_core_web_sm-3.8.0/meta.json
+%%PYTHON_SITELIBDIR%%/en_core_web_sm/en_core_web_sm-3.8.0/ner/cfg
+%%PYTHON_SITELIBDIR%%/en_core_web_sm/en_core_web_sm-3.8.0/ner/model
+%%PYTHON_SITELIBDIR%%/en_core_web_sm/en_core_web_sm-3.8.0/ner/moves
+%%PYTHON_SITELIBDIR%%/en_core_web_sm/en_core_web_sm-3.8.0/parser/cfg
+%%PYTHON_SITELIBDIR%%/en_core_web_sm/en_core_web_sm-3.8.0/parser/model
+%%PYTHON_SITELIBDIR%%/en_core_web_sm/en_core_web_sm-3.8.0/parser/moves
+%%PYTHON_SITELIBDIR%%/en_core_web_sm/en_core_web_sm-3.8.0/senter/cfg
+%%PYTHON_SITELIBDIR%%/en_core_web_sm/en_core_web_sm-3.8.0/senter/model
+%%PYTHON_SITELIBDIR%%/en_core_web_sm/en_core_web_sm-3.8.0/tagger/cfg
+%%PYTHON_SITELIBDIR%%/en_core_web_sm/en_core_web_sm-3.8.0/tagger/model
+%%PYTHON_SITELIBDIR%%/en_core_web_sm/en_core_web_sm-3.8.0/tok2vec/cfg
+%%PYTHON_SITELIBDIR%%/en_core_web_sm/en_core_web_sm-3.8.0/tok2vec/model
+%%PYTHON_SITELIBDIR%%/en_core_web_sm/en_core_web_sm-3.8.0/tokenizer
+%%PYTHON_SITELIBDIR%%/en_core_web_sm/en_core_web_sm-3.8.0/vocab/key2row
+%%PYTHON_SITELIBDIR%%/en_core_web_sm/en_core_web_sm-3.8.0/vocab/lookups.bin
+%%PYTHON_SITELIBDIR%%/en_core_web_sm/en_core_web_sm-3.8.0/vocab/strings.json
+%%PYTHON_SITELIBDIR%%/en_core_web_sm/en_core_web_sm-3.8.0/vocab/vectors
+%%PYTHON_SITELIBDIR%%/en_core_web_sm/en_core_web_sm-3.8.0/vocab/vectors.cfg
+%%PYTHON_SITELIBDIR%%/en_core_web_sm/meta.json