Accepting request 1218976 from devel:languages:python

- Use _service to download source and exclude documentation that has non-commercial license (boo#1232448) - Remove nltk_data to avoid redistribution of files with non-commercial (boo#1232448): > NLTK corpora are provided under the terms given in the README file > for each corpus; all are redistributable and available for > non-commercial use. - Remove not needed skip-networked-test.patch OBS-URL: https://build.opensuse.org/request/show/1218976 OBS-URL: https://build.opensuse.org/package/show/openSUSE:Factory/python-nltk?expand=0&rev=19
- Use _service to download source and exclude documentation that has
2024-10-29 13:36:45 +00:00 · 2024-10-29 09:33:33 +00:00 · 2024-10-29 09:09:02 +00:00 · 2024-10-27 10:25:56 +00:00 · 2024-10-26 08:13:11 +00:00 · 2024-10-26 08:11:04 +00:00
11 changed files with 79 additions and 320 deletions
--- a/CVE-2024-39705-disable-download.patch
+++ b/CVE-2024-39705-disable-download.patch
@ -1,104 +0,0 @@
---
- nltk/app/chartparser_app.py    |   13 +++++++++++++
- nltk/corpus/reader/util.py     |    2 ++
- nltk/data.py                   |    2 ++
- nltk/parse/transitionparser.py |    2 ++
- nltk/tbl/demo.py               |    4 +++-
- 5 files changed, 22 insertions(+), 1 deletion(-)
-
--- a/nltk/app/chartparser_app.py
-+++ b/nltk/app/chartparser_app.py
-@@ -800,6 +800,10 @@ class ChartComparer:
-             showerror("Error Saving Chart", f"Unable to open file: {filename!r}\n{e}")
- 
-     def load_chart_dialog(self, *args):
-+        showerror("Security Error",
-+                  "Due to gh#nltk/nltk#3266, deserializing from " +
-+                  "a pickle is forbidden.")
-+        return
-         filename = askopenfilename(
-             filetypes=self.CHART_FILE_TYPES, defaultextension=".pickle"
-         )
-@@ -811,6 +815,8 @@ class ChartComparer:
-             showerror("Error Loading Chart", f"Unable to open file: {filename!r}\n{e}")
- 
-     def load_chart(self, filename):
-+        raise RuntimeError("Due to gh#nltk/nltk#3266, deserializing from " +
-+                           "a pickle is forbidden.")
-         with open(filename, "rb") as infile:
-             chart = pickle.load(infile)
-         name = os.path.basename(filename)
-@@ -2268,6 +2274,10 @@ class ChartParserApp:
-         if not filename:
-             return
-         try:
-+            showerror("Security Error",
-+                      "Due to gh#nltk/nltk#3266, deserializing from " +
-+                      "a pickle is forbidden.")
-+            return
-             with open(filename, "rb") as infile:
-                 chart = pickle.load(infile)
-             self._chart = chart
-@@ -2306,6 +2316,9 @@ class ChartParserApp:
-             return
-         try:
-             if filename.endswith(".pickle"):
-+                showerror("Due to gh#nltk/nltk#3266, deserializing from " +
-+                          "a pickle is forbidden.")
-+                return
-                 with open(filename, "rb") as infile:
-                     grammar = pickle.load(infile)
-             else:
--- a/nltk/corpus/reader/util.py
-+++ b/nltk/corpus/reader/util.py
-@@ -521,6 +521,8 @@ class PickleCorpusView(StreamBackedCorpu
- 
-     def read_block(self, stream):
-         result = []
-+        raise RuntimeError("Due to gh#nltk/nltk#3266, deserializing from " +
-+                           "a pickle is forbidden.")
-         for i in range(self.BLOCK_SIZE):
-             try:
-                 result.append(pickle.load(stream))
--- a/nltk/data.py
-+++ b/nltk/data.py
-@@ -752,6 +752,8 @@ def load(
-     if format == "raw":
-         resource_val = opened_resource.read()
-     elif format == "pickle":
-+        raise RuntimeError("Due to gh#nltk/nltk#3266, deserializing from " +
-+                           "a pickle is forbidden.")
-         resource_val = pickle.load(opened_resource)
-     elif format == "json":
-         import json
--- a/nltk/parse/transitionparser.py
-+++ b/nltk/parse/transitionparser.py
-@@ -553,6 +553,8 @@ class TransitionParser(ParserI):
-         """
-         result = []
-         # First load the model
-+        raise RuntimeError("Due to gh#nltk/nltk#3266, deserializing from " +
-+                           "a pickle is forbidden.")
-         model = pickle.load(open(modelFile, "rb"))
-         operation = Transition(self._algorithm)
- 
--- a/nltk/tbl/demo.py
-+++ b/nltk/tbl/demo.py
-@@ -253,6 +253,8 @@ def postag(
-                 )
-             )
-         with open(cache_baseline_tagger) as print_rules:
-+            raise RuntimeError("Due to gh#nltk/nltk#3266, deserializing from " +
-+                               "a pickle is forbidden.")
-             baseline_tagger = pickle.load(print_rules)
-             print(f"Reloaded pickled tagger from {cache_baseline_tagger}")
-     else:
-@@ -327,7 +329,7 @@ def postag(
-         with open(serialize_output) as print_rules:
-             brill_tagger_reloaded = pickle.load(print_rules)
-         print(f"Reloaded pickled tagger from {serialize_output}")
-        taggedtest_reloaded = brill_tagger.tag_sents(testing_data)
-+        taggedtest_reloaded = brill_tagger_reloaded.tag_sents(testing_data)
-         if taggedtest == taggedtest_reloaded:
-             print("Reloaded tagger tried on test set, results identical")
-         else:
--- a/CVE-2024-39705.patch
+++ b/CVE-2024-39705.patch
@ -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
- 
--- a/15
+++ b/15
@ -0,0 +1,15 @@
+<services>
+  <service name="obs_scm" mode="manual">
+    <param name="url">https://github.com/nltk/nltk</param>
+    <param name="scm">git</param>
+    <param name="exclude">web/*</param>
+    <param name="version">3.9.1</param>
+    <param name="revision">3.9.1</param>
+  </service>
+  <service mode="manual" name="set_version" />
+  <service mode="buildtime" name="tar" />
+  <service mode="buildtime" name="recompress">
+    <param name="file">*.tar</param>
+    <param name="compression">xz</param>
+  </service>
+</services>
--- a/nltk-3.8.1.tar.gz
+++ b/nltk-3.8.1.tar.gz
@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:676970e2b7aa0a7184e68f76e0c4f2756fd1b82559a509d5656a23117faeb658
-size 2867926
--- a/nltk-3.9.1.obscpio
+++ b/nltk-3.9.1.obscpio
@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1b59894ed0a2eebbb64fc4e0975216a5a7e1a949e61b9a4f22693e15536ff05
+size 8269325
--- a/nltk-pr3207-py312.patch
+++ b/nltk-pr3207-py312.patch
@ -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",
--- a/nltk.obsinfo
+++ b/nltk.obsinfo
@ -0,0 +1,4 @@
+name: nltk
+version: 3.9.1
+mtime: 1724010420
+commit: aca78cb2add4084f76b9eac921d8a73927d7a086
--- a/nltk_data.tar.xz
+++ b/nltk_data.tar.xz
@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f79462ac99f414b4850943720bed4a59c1bb15bfc8f1ce16b26165da6db07680
-size 393271816
--- a/python-nltk.changes
+++ b/python-nltk.changes
@ -1,3 +1,34 @@
+-------------------------------------------------------------------
+Tue Oct 29 08:37:43 UTC 2024 - Daniel Garcia <daniel.garcia@suse.com>
+
+- Use _service to download source and exclude documentation that has
+  non-commercial license (boo#1232448)
+- Remove nltk_data to avoid redistribution of files with
+  non-commercial (boo#1232448):
+  > NLTK corpora are provided under the terms given in the README file
+  > for each corpus; all are redistributable and available for
+  > non-commercial use.
+- Remove not needed skip-networked-test.patch
+
+-------------------------------------------------------------------
+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>

@ -36,8 +67,7 @@ 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 
-
+- 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)
@ -72,7 +102,7 @@ Fri Jan  6 15:32:43 UTC 2023 - Yogalakshmi Arunachalam <yarunachalam@suse.com>
 * Fix LC cutoff policy of text tiling (#2936)
 * Optimize ConditionalFreqDist.__add__ performance (#2939)
 * Add Markdown corpus reader (#2902)
- 
+
 -------------------------------------------------------------------
 Mon Dec 26 10:41:22 UTC 2022 - Matej Cepl <mcepl@suse.com>

@ -390,7 +420,7 @@ Fri Sep 23 12:29:05 UTC 2011 - saschpe@suse.de

 -------------------------------------------------------------------
 Sun Feb  7 18:51:07 CST 2010 - oddrationale@gmail.com
- 
+
 - fixed copyright and license statements
 - removed PyYAML, and added dependency to installers and download
  instructions
@ -412,6 +442,6 @@ Thu Dec 10 17:23:51 CST 2009 - oddrationale@gmail.com
 - added Requires: python-yaml

 -------------------------------------------------------------------
-Wed Dec  9 15:39:35 CST 2009 - oddrationale@gmail.com  
-  
+Wed Dec  9 15:39:35 CST 2009 - oddrationale@gmail.com
+
 - Initial Release (Version 2.0b7): Sun Feb  7 18:50:18 CST 2010
--- a/python-nltk.spec
+++ b/python-nltk.spec
@ -17,14 +17,17 @@


 %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
 URL:            http://nltk.org/
 # SourceRepository: https://github.com/nltk/nltk
-Source0:        https://github.com/nltk/%{modname}/archive/refs/tags/%{version}.tar.gz#/%{modname}-%{version}.tar.gz
+# The _service download the source and repack without some doc files
+# that has non-commercial license. boo#1232448
+Source0:        nltk-%{version}.tar.xz
 # Download/Update NLTK data:
 #     quilt setup python-nltk.spec
 #     pushd nltk-?.?.?
@ -56,15 +59,12 @@ Source0:        https://github.com/nltk/%{modname}/archive/refs/tags/%{version}.
 #     tar -cJf ../nltk_data.tar.xz nltk_data
 #     popd
 # see https://www.nltk.org/data.html for more details
-Source1:        nltk_data.tar.xz
+########### NOTICE #########
+# Do not distribute nltk_data.tar.xz because it's licensed under
+# non-commercial, boo#1232448
+############################
+# Source1:        nltk_data.tar.xz
 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}
@ -121,7 +121,7 @@ Python modules, data sets and tutorials supporting research and
 development in Natural Language Processing.

 %prep
-%setup -q -a1 -n %{modname}-%{version}
+%setup -q -n %{modname}-%{version}

 # Fix EOL
 sed -i 's/\r/\n/g; s/\n$//' \
@ -150,7 +150,6 @@ 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
@ -166,15 +165,16 @@ sed -E -i "s|#![[:space:]]*%{_bindir}/env python|#!%{_bindir}/python3|" \
 chmod -x %{buildroot}%{$python_sitelib}/nltk/test/dependency.doctest
 }

-%check
-export NLTK_DATA=$(readlink -f ./nltk_data/)
-# export PYTEST_ADDOPTS="--doctest-modules"
-# Skip tests requiring pickle.load gh#nltk/nltk#3266 (CVE-2024-39705)
-skip_tests=" or test_basic or test_increment or test_pad_asterisk or test_pad_dotdot"
-skip_tests+=" or test_pos_tag_eng or test_pos_tag_eng_universal or test_pos_tag_rus"
-skip_tests+=" or test_pos_tag_rus_universal or test_pos_tag_unknown_lang"
-skip_tests+=" or test_sent_tokenize or test_unspecified_lang or test_word_tokenize"
-%pytest -k "not (network ${skip_tests})"
+# Do not test, there's no ntlk_data, boo#1232448
+# %%check
+# export NLTK_DATA=$(readlink -f ./nltk_data/)
+# # export PYTEST_ADDOPTS="--doctest-modules"
+# # Skip tests requiring pickle.load gh#nltk/nltk#3266 (CVE-2024-39705)
+# skip_tests=" or test_basic or test_increment or test_pad_asterisk or test_pad_dotdot"
+# skip_tests+=" or test_pos_tag_eng or test_pos_tag_eng_universal or test_pos_tag_rus"
+# skip_tests+=" or test_pos_tag_rus_universal or test_pos_tag_unknown_lang"
+# skip_tests+=" or test_sent_tokenize or test_unspecified_lang or test_word_tokenize"
+# %%pytest -k "not (network ${skip_tests})"

 %post
 %python_install_alternative nltk
--- a/skip-networked-test.patch
+++ b/skip-networked-test.patch
@ -1,35 +0,0 @@
---
- nltk/test/unit/test_downloader.py |    4 ++++
- setup.cfg                         |    4 ++++
- 2 files changed, 8 insertions(+)
-
--- a/nltk/test/unit/test_downloader.py
-+++ b/nltk/test/unit/test_downloader.py
-@@ -1,6 +1,9 @@
- from nltk import download
- 
-+import pytest
- 
-+
-+@pytest.mark.network
- def test_downloader_using_existing_parent_download_dir(tmp_path):
-     """Test that download works properly when the parent folder of the download_dir exists"""
- 
-@@ -9,6 +12,7 @@ def test_downloader_using_existing_paren
-     assert download_status is True
- 
- 
-+@pytest.mark.network
- def test_downloader_using_non_existing_parent_download_dir(tmp_path):
-     """Test that download works properly when the parent folder of the download_dir does not exist"""
- 
--- a/setup.cfg
-+++ b/setup.cfg
-@@ -1,3 +1,7 @@
-+[tool:pytest]
-+markers =
-+   network: test case requires network connection
-+
- [metadata]
- license_files =
-     LICENSE.txt