Accepting request 1218494 from devel:languages:python
- Update to to 3.9.1 (changes since 3.8.1):
* Fixed bug that prevented wordnet from loading
* Fix security vulnerability CVE-2024-39705 (breaking change)
* Replace pickled models (punkt, chunker, taggers) by new
pickle-free "_tab" packages
* No longer sort Wordnet synsets and relations (sort in calling
function when required)
* Only strip the last suffix in Wordnet Morphy, thus
restricting synsets() results
* Add Python 3.12 support
* Many other minor fixes
- Refresh nltk_data
- Remome upstreamed patches:
- CVE-2024-39705.patch
- nltk-pr3207-py312.patch
- Update to 3.8
OBS-URL: https://build.opensuse.org/request/show/1218494
OBS-URL: https://build.opensuse.org/package/show/openSUSE:Factory/python-nltk?expand=0&rev=18
This commit is contained in:
Ana Guerrero
Git OBS Bridge
commit
f02d8a709b
@ -1,38 +0,0 @@
|
||||
From a12d0a6a8cdba58d5e4e5f92ac62bb80fc26c624 Mon Sep 17 00:00:00 2001
|
||||
From: Eric Kafe <kafe.eric@gmail.com>
|
||||
Date: Tue, 23 Jul 2024 09:09:09 +0200
|
||||
Subject: [PATCH] Prevent data.load from unpickling classes or functions
|
||||
|
||||
---
|
||||
nltk/data.py | 11 ++++++++++-
|
||||
1 file changed, 10 insertions(+), 1 deletion(-)
|
||||
|
||||
diff --git a/nltk/data.py b/nltk/data.py
|
||||
index cc9229b0a2..fb242721c5 100644
|
||||
--- a/nltk/data.py
|
||||
+++ b/nltk/data.py
|
||||
@@ -658,6 +658,15 @@ def retrieve(resource_url, filename=None, verbose=True):
|
||||
}
|
||||
|
||||
|
||||
+def restricted_pickle_load(string):
|
||||
+ """
|
||||
+ Prevents any class or function from loading.
|
||||
+ """
|
||||
+ from nltk.app.wordnet_app import RestrictedUnpickler
|
||||
+
|
||||
+ return RestrictedUnpickler(BytesIO(string)).load()
|
||||
+
|
||||
+
|
||||
def load(
|
||||
resource_url,
|
||||
format="auto",
|
||||
@@ -751,7 +760,7 @@ def load(
|
||||
if format == "raw":
|
||||
resource_val = opened_resource.read()
|
||||
elif format == "pickle":
|
||||
- resource_val = pickle.load(opened_resource)
|
||||
+ resource_val = restricted_pickle_load(opened_resource.read())
|
||||
elif format == "json":
|
||||
import json
|
||||
|
||||
@ -1,3 +0,0 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:676970e2b7aa0a7184e68f76e0c4f2756fd1b82559a509d5656a23117faeb658
|
||||
size 2867926
|
||||
3
nltk-3.9.1.tar.gz
Normal file
3
nltk-3.9.1.tar.gz
Normal file
@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:03e06c8c13e352133962c4395ebe0696905c9f1fbdead2d19deae37ba48eb47c
|
||||
size 2874006
|
||||
@ -1,110 +0,0 @@
|
||||
From 25d35fc4283dedd2053ec6d821f4b707fff8d72c Mon Sep 17 00:00:00 2001
|
||||
From: Konstantin Chernyshev <k4black@ya.ru>
|
||||
Date: Thu, 16 Nov 2023 19:00:15 +0100
|
||||
Subject: [PATCH 1/8] ci: enable 3.12 in ci tests
|
||||
|
||||
---
|
||||
.github/workflows/ci.yaml | 2 +-
|
||||
README.md | 2 +-
|
||||
nltk/test/unit/translate/test_bleu.py | 1 -
|
||||
nltk/translate/bleu_score.py | 29 +++++++++++++++++++++++++++--
|
||||
setup.py | 3 ++-
|
||||
5 files changed, 31 insertions(+), 6 deletions(-)
|
||||
|
||||
--- a/.github/workflows/ci.yaml
|
||||
+++ b/.github/workflows/ci.yaml
|
||||
@@ -76,7 +76,7 @@ jobs:
|
||||
needs: [cache_nltk_data, cache_third_party]
|
||||
strategy:
|
||||
matrix:
|
||||
- python-version: ['3.7', '3.8', '3.9', '3.10', '3.11']
|
||||
+ python-version: ['3.7', '3.8', '3.9', '3.10', '3.11', '3.12']
|
||||
os: [ubuntu-latest, macos-latest, windows-latest]
|
||||
fail-fast: false
|
||||
runs-on: ${{ matrix.os }}
|
||||
--- a/README.md
|
||||
+++ b/README.md
|
||||
@@ -4,7 +4,7 @@
|
||||
|
||||
NLTK -- the Natural Language Toolkit -- is a suite of open source Python
|
||||
modules, data sets, and tutorials supporting research and development in Natural
|
||||
-Language Processing. NLTK requires Python version 3.7, 3.8, 3.9, 3.10 or 3.11.
|
||||
+Language Processing. NLTK requires Python version 3.7, 3.8, 3.9, 3.10, 3.11 or 3.12.
|
||||
|
||||
For documentation, please visit [nltk.org](https://www.nltk.org/).
|
||||
|
||||
--- a/nltk/test/unit/translate/test_bleu.py
|
||||
+++ b/nltk/test/unit/translate/test_bleu.py
|
||||
@@ -2,7 +2,6 @@
|
||||
Tests for BLEU translation evaluation metric
|
||||
"""
|
||||
|
||||
-import io
|
||||
import unittest
|
||||
|
||||
from nltk.data import find
|
||||
--- a/nltk/translate/bleu_score.py
|
||||
+++ b/nltk/translate/bleu_score.py
|
||||
@@ -7,16 +7,41 @@
|
||||
# For license information, see LICENSE.TXT
|
||||
|
||||
"""BLEU score implementation."""
|
||||
-
|
||||
import math
|
||||
import sys
|
||||
import warnings
|
||||
from collections import Counter
|
||||
-from fractions import Fraction
|
||||
+from fractions import Fraction as _Fraction
|
||||
|
||||
from nltk.util import ngrams
|
||||
|
||||
|
||||
+class Fraction(_Fraction):
|
||||
+ """Fraction with _normalize=False support for 3.12"""
|
||||
+
|
||||
+ def __new__(cls, numerator=0, denominator=None, _normalize=False):
|
||||
+ if sys.version_info >= (3, 12):
|
||||
+ self = super().__new__(cls, numerator, denominator)
|
||||
+ else:
|
||||
+ self = super().__new__(cls, numerator, denominator, _normalize=_normalize)
|
||||
+ self._normalize = _normalize
|
||||
+ self._original_numerator = numerator
|
||||
+ self._original_denominator = denominator
|
||||
+ return self
|
||||
+
|
||||
+ @property
|
||||
+ def numerator(self):
|
||||
+ if not self._normalize:
|
||||
+ return self._original_numerator
|
||||
+ return super().numerator
|
||||
+
|
||||
+ @property
|
||||
+ def denominator(self):
|
||||
+ if not self._normalize:
|
||||
+ return self._original_denominator
|
||||
+ return super().denominator
|
||||
+
|
||||
+
|
||||
def sentence_bleu(
|
||||
references,
|
||||
hypothesis,
|
||||
--- a/setup.py
|
||||
+++ b/setup.py
|
||||
@@ -67,7 +67,7 @@ setup(
|
||||
},
|
||||
long_description="""\
|
||||
The Natural Language Toolkit (NLTK) is a Python package for
|
||||
-natural language processing. NLTK requires Python 3.7, 3.8, 3.9, 3.10 or 3.11.""",
|
||||
+natural language processing. NLTK requires Python 3.7, 3.8, 3.9, 3.10, 3.11 or 3.12.""",
|
||||
license="Apache License, Version 2.0",
|
||||
keywords=[
|
||||
"NLP",
|
||||
@@ -100,6 +100,7 @@ natural language processing. NLTK requi
|
||||
"Programming Language :: Python :: 3.9",
|
||||
"Programming Language :: Python :: 3.10",
|
||||
"Programming Language :: Python :: 3.11",
|
||||
+ "Programming Language :: Python :: 3.12",
|
||||
"Topic :: Scientific/Engineering",
|
||||
"Topic :: Scientific/Engineering :: Artificial Intelligence",
|
||||
"Topic :: Scientific/Engineering :: Human Machine Interfaces",
|
||||
@ -1,3 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f79462ac99f414b4850943720bed4a59c1bb15bfc8f1ce16b26165da6db07680
|
||||
size 393271816
|
||||
oid sha256:d5996129d40c2598664f74f44c15a39059f5b3713a26152ad4b0220d37bf6f9d
|
||||
size 392736120
|
||||
|
||||
@ -1,3 +1,22 @@
|
||||
-------------------------------------------------------------------
|
||||
Mon Sep 30 21:17:21 UTC 2024 - Thiago Bertoldi <thiago.bertoldi@suse.com>
|
||||
|
||||
- Update to to 3.9.1 (changes since 3.8.1):
|
||||
* Fixed bug that prevented wordnet from loading
|
||||
* Fix security vulnerability CVE-2024-39705 (breaking change)
|
||||
* Replace pickled models (punkt, chunker, taggers) by new
|
||||
pickle-free "_tab" packages
|
||||
* No longer sort Wordnet synsets and relations (sort in calling
|
||||
function when required)
|
||||
* Only strip the last suffix in Wordnet Morphy, thus
|
||||
restricting synsets() results
|
||||
* Add Python 3.12 support
|
||||
* Many other minor fixes
|
||||
- Refresh nltk_data
|
||||
- Remome upstreamed patches:
|
||||
- CVE-2024-39705.patch
|
||||
- nltk-pr3207-py312.patch
|
||||
|
||||
-------------------------------------------------------------------
|
||||
Fri Jul 26 07:14:33 UTC 2024 - Daniel Garcia <daniel.garcia@suse.com>
|
||||
|
||||
@ -37,7 +56,6 @@ Tue Mar 28 08:36:04 UTC 2023 - pgajdos@suse.com
|
||||
Fri Jan 6 15:32:43 UTC 2023 - Yogalakshmi Arunachalam <yarunachalam@suse.com>
|
||||
|
||||
- Update to 3.8
|
||||
|
||||
* Refactor dispersion plot (#3082)
|
||||
* Provide type hints for LazyCorpusLoader variables (#3081)
|
||||
* Throw warning when LanguageModel is initialized with incorrect vocabulary (#3080)
|
||||
|
||||
@ -17,8 +17,9 @@
|
||||
|
||||
|
||||
%define modname nltk
|
||||
%{?sle15_python_module_pythons}
|
||||
Name: python-nltk
|
||||
Version: 3.8.1
|
||||
Version: 3.9.1
|
||||
Release: 0
|
||||
Summary: Natural Language Toolkit
|
||||
License: Apache-2.0
|
||||
@ -61,10 +62,6 @@ Source99: python-nltk.rpmlintrc
|
||||
# PATCH-FIX-UPSTREAM skip-networked-test.patch gh#nltk/nltk#2969 mcepl@suse.com
|
||||
# skip tests requiring network connection
|
||||
Patch0: skip-networked-test.patch
|
||||
# PATCH-FIX-UPSTREAM nltk-pr3207-py312.patch gh#nltk/nltk#3207
|
||||
Patch1: nltk-pr3207-py312.patch
|
||||
# PATCH-FIX-UPSTREAM CVE-2024-39705.patch bsc#1227174 gh#nltk/nltk#3290
|
||||
Patch2: CVE-2024-39705.patch
|
||||
BuildRequires: %{python_module base >= 3.7}
|
||||
BuildRequires: %{python_module pip}
|
||||
BuildRequires: %{python_module setuptools}
|
||||
@ -150,7 +147,6 @@ sed -E -i "/#![[:space:]]*\/usr\/bin\/env python/d" \
|
||||
sed -E -i "s|#![[:space:]]*%{_bindir}/env python|#!%{_bindir}/python3|" \
|
||||
setup.py \
|
||||
tools/global_replace.py \
|
||||
nltk_data/corpora/pl196x/splitter.py \
|
||||
tools/find_deprecated.py
|
||||
|
||||
%autopatch -p1
|
||||
|
||||
@ -33,3 +33,4 @@
|
||||
[metadata]
|
||||
license_files =
|
||||
LICENSE.txt
|
||||
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user