community/py3-nltk: upgrade to 3.9.1

community/py3-nltk/APKBUILD

@@ -3,17 +3,19 @@
 maintainer="Will Sinatra <wpsinatra@gmail.com>"
 pkgname=py3-nltk
 _pkgorig=nltk
-pkgver=3.8.2
-pkgrel=1
+pkgver=3.9.1
+pkgrel=0
 pkgdesc="Natural Language Toolkit"
 url="https://github.com/nltk/nltk"
 arch="noarch"
 license="Apache-2.0"
 depends="python3 py3-yaml py3-click py3-regex"
 makedepends="py3-gpep517 py3-setuptools py3-wheel"
-checkdepends="py3-nose py3-requests"
+checkdepends="py3-matplotlib py3-numpy py3-pytest py3-pytest-mock"
 subpackages="$pkgname-pyc"
-source="$pkgname-$pkgver.tar.gz::https://github.com/nltk/nltk/archive/$pkgver.tar.gz"
+source="$pkgname-$pkgver.tar.gz::https://github.com/nltk/nltk/archive/$pkgver.tar.gz
+	fix-import-wordnet.patch
+	"
 builddir="$srcdir/$_pkgorig-$pkgver"
 
 build() {
@@ -22,9 +24,11 @@ build() {
 		--output-fd 3 3>&1 >&2
 }
 
-# tests require nltk-data; use smoke test for now
 check() {
-	PYTHONPATH=build/lib python3 -c "from nltk import *"
+	python3 -m venv --clear --without-pip --system-site-packages .testenv
+	.testenv/bin/python3 -m installer .dist/*.whl
+	.testenv/bin/python3 -m nltk.downloader all
+	.testenv/bin/python3 -m pytest
 }
 
 package() {
@@ -35,5 +39,6 @@ package() {
 }
 
 sha512sums="
-cdd76d1185aa7a0c4e96af19e311120ac70f425e75cd52e37d20d32f2722490c4e74535c44113da5856fb682530ea598446f998fda4e186c898cd675064dee6b  py3-nltk-3.8.2.tar.gz
+7e384a23fa3839c29d38c083d6288d15ff04eb071c4bca3ec1bfb3b9cfcac8d2388041a950d6c71684ee29b791318312df99e29ae258eb5e602ccf2ad1407840  py3-nltk-3.9.1.tar.gz
+9c4491d6ebdaad056b7bd7a3ebe7c720ad47568181aec2a1801b198e1ed81a9174ec2811227d37a336fe689f05afb5ac983fe0d05b3a379aff9bf4cfa87aba69  fix-import-wordnet.patch
 "

community/py3-nltk/fix-import-wordnet.patch

+Patch-Source: https://github.com/nltk/nltk/pull/3309
+--
+From 7d1cbc71441f607daea0894333912268e2911cab Mon Sep 17 00:00:00 2001
+From: Eric Kafe <kafe.eric@gmail.com>
+Date: Sun, 18 Aug 2024 16:09:01 +0200
+Subject: [PATCH] Fix bug in WordNetLemmatizer
+
+---
+ nltk/stem/wordnet.py | 71 ++++++++++++++++++++++++--------------------
+ 1 file changed, 39 insertions(+), 32 deletions(-)
+
+diff --git a/nltk/stem/wordnet.py b/nltk/stem/wordnet.py
+index 76caf1b09c..87d08c7891 100644
+--- a/nltk/stem/wordnet.py
++++ b/nltk/stem/wordnet.py
+@@ -7,64 +7,71 @@
+ # URL: <https://www.nltk.org/>
+ # For license information, see LICENSE.TXT
+ 
+-from nltk.corpus import wordnet as wn
+-
+ 
+ class WordNetLemmatizer:
+     """
+     WordNet Lemmatizer
+ 
+-    Provides 3 lemmatizer modes:
+-
+-    1. _morphy() is an alias to WordNet's _morphy lemmatizer.
+-    It returns a list of all lemmas found in WordNet.
+-
+-    >>> wnl = WordNetLemmatizer()
+-    >>> print(wnl._morphy('us', 'n'))
+-    ['us', 'u']
+-
+-    2. morphy() is a restrictive wrapper around _morphy().
+-    It returns the first lemma found in WordNet,
+-    or None if no lemma is found.
++    Provides 3 lemmatizer modes: _morphy(), morphy() and lemmatize().
+ 
+-    >>> print(wnl.morphy('us', 'n'))
+-    us
+-
+-    >>> print(wnl.morphy('catss'))
+-    None
+-
+-    3. lemmatize() is a permissive wrapper around _morphy().
++    lemmatize() is a permissive wrapper around _morphy().
+     It returns the shortest lemma found in WordNet,
+     or the input string unchanged if nothing is found.
+ 
+-    >>> print(wnl.lemmatize('us', 'n'))
++    >>> from nltk.stem import WordNetLemmatizer as wnl
++    >>> print(wnl().lemmatize('us', 'n'))
+     u
+ 
+-    >>> print(wnl.lemmatize('Anythinggoeszxcv'))
++    >>> print(wnl().lemmatize('Anythinggoeszxcv'))
+     Anythinggoeszxcv
+ 
+     """
+ 
+-    morphy = wn.morphy
++    def _morphy(self, form, pos, check_exceptions=True):
++        """
++        _morphy() is WordNet's _morphy lemmatizer.
++        It returns a list of all lemmas found in WordNet.
++
++        >>> from nltk.stem import WordNetLemmatizer as wnl
++        >>> print(wnl()._morphy('us', 'n'))
++        ['us', 'u']
++        """
++        from nltk.corpus import wordnet as wn
++
++        return wn._morphy(form, pos, check_exceptions)
++
++    def morphy(self, form, pos=None, check_exceptions=True):
++        """
++        morphy() is a restrictive wrapper around _morphy().
++        It returns the first lemma found in WordNet,
++        or None if no lemma is found.
++
++        >>> from nltk.stem import WordNetLemmatizer as wnl
++        >>> print(wnl().morphy('us', 'n'))
++        us
++
++        >>> print(wnl().morphy('catss'))
++        None
++        """
++        from nltk.corpus import wordnet as wn
+ 
+-    _morphy = wn._morphy
++        return wn.morphy(form, pos, check_exceptions)
+ 
+     def lemmatize(self, word: str, pos: str = "n") -> str:
+         """Lemmatize `word` by picking the shortest of the possible lemmas,
+         using the wordnet corpus reader's built-in _morphy function.
+         Returns the input word unchanged if it cannot be found in WordNet.
+ 
+-        >>> from nltk.stem import WordNetLemmatizer
+-        >>> wnl = WordNetLemmatizer()
+-        >>> print(wnl.lemmatize('dogs'))
++        >>> from nltk.stem import WordNetLemmatizer as wnl
++        >>> print(wnl().lemmatize('dogs'))
+         dog
+-        >>> print(wnl.lemmatize('churches'))
++        >>> print(wnl().lemmatize('churches'))
+         church
+-        >>> print(wnl.lemmatize('aardwolves'))
++        >>> print(wnl().lemmatize('aardwolves'))
+         aardwolf
+-        >>> print(wnl.lemmatize('abaci'))
++        >>> print(wnl().lemmatize('abaci'))
+         abacus
+-        >>> print(wnl.lemmatize('hardrock'))
++        >>> print(wnl().lemmatize('hardrock'))
+         hardrock
+ 
+         :param word: The input word to lemmatize.