rpm/python-nltk
SHA256
1
0
Fork 0
forked from pool/python-nltk
Code Pull Requests Activity

- Add CVE-2024-39705.patch upstream patch to fix unsafe pickle usage.

Browse Source 
(CVE-2024-39705, gh#nltk/nltk#3266, bsc#1227174).
- Drop CVE-2024-39705-disable-download.patch as it's not needed
  anymore.

OBS-URL: https://build.opensuse.org/package/show/devel:languages:python/python-nltk?expand=0&rev=49
This commit is contained in:
Daniel Garcia 2024-07-26 07:21:06 +00:00 committed by Git OBS Bridge
commit 9adfbd9e5d
11 changed files with 928 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
.gitattributes vendored Normal file
View File

@ -0,0 +1,23 @@
## Default LFS
*.7z filter=lfs diff=lfs merge=lfs -text
*.bsp filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.gem filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text
*.jar filter=lfs diff=lfs merge=lfs -text
*.lz filter=lfs diff=lfs merge=lfs -text
*.lzma filter=lfs diff=lfs merge=lfs -text
*.obscpio filter=lfs diff=lfs merge=lfs -text
*.oxt filter=lfs diff=lfs merge=lfs -text
*.pdf filter=lfs diff=lfs merge=lfs -text
*.png filter=lfs diff=lfs merge=lfs -text
*.rpm filter=lfs diff=lfs merge=lfs -text
*.tbz filter=lfs diff=lfs merge=lfs -text
*.tbz2 filter=lfs diff=lfs merge=lfs -text
*.tgz filter=lfs diff=lfs merge=lfs -text
*.ttf filter=lfs diff=lfs merge=lfs -text
*.txz filter=lfs diff=lfs merge=lfs -text
*.whl filter=lfs diff=lfs merge=lfs -text
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text

1
.gitignore vendored Normal file
View File

@ -0,0 +1 @@
.osc

104
CVE-2024-39705-disable-download.patch Normal file
View File

@ -0,0 +1,104 @@
---
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:

38
CVE-2024-39705.patch Normal file
View File

@ -0,0 +1,38 @@
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

3
nltk-3.8.1.tar.gz Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:676970e2b7aa0a7184e68f76e0c4f2756fd1b82559a509d5656a23117faeb658
size 2867926

110
nltk-pr3207-py312.patch Normal file
View File

@ -0,0 +1,110 @@
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",

3
nltk_data.tar.xz Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f79462ac99f414b4850943720bed4a59c1bb15bfc8f1ce16b26165da6db07680
size 393271816

417
python-nltk.changes Normal file
View File

@ -0,0 +1,417 @@
-------------------------------------------------------------------
Fri Jul 26 07:14:33 UTC 2024 - Daniel Garcia <daniel.garcia@suse.com>
- Add CVE-2024-39705.patch upstream patch to fix unsafe pickle usage.
(CVE-2024-39705, gh#nltk/nltk#3266, bsc#1227174).
- Drop CVE-2024-39705-disable-download.patch as it's not needed
anymore.
-------------------------------------------------------------------
Mon Jul 1 21:02:45 UTC 2024 - Matej Cepl <mcepl@cepl.eu>
- Use tarball from GitHub instead of the Zip archive from PyPI,
the latter has very messy combination of CRLF and LF EOLs,
which are hard to patch.
- Refresh all patches from the original locations.
- Add CVE-2024-39705-disable-download.patch to make a crude
workaround around CVE-2024-39705 (gh#nltk/nltk#3266,
bsc#1227174).
-------------------------------------------------------------------
Thu Mar 21 17:41:52 UTC 2024 - Ben Greiner <code@bnavigator.de>
- Update to 3.8.1
* Resolve RCE & XSS vulnerabilities in localhost WordNet Browser
* Add Python 3.11 support
- Update nltk_data archive
- Drop port-2to3.patch
- Add nltk-pr3207-py312.patch for Python 3.12 support
* gh#nltk/nltk#3207
-------------------------------------------------------------------
Tue Mar 28 08:36:04 UTC 2023 - pgajdos@suse.com
- python-six is not required
-------------------------------------------------------------------
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)
* Fix WordNet's all_synsets() function (#3078)
* Resolve TreebankWordDetokenizer inconsistency with end-of-string contractions (#3070)
* Support both iso639-3 codes and BCP-47 language tags (#3060)
* Avoid DeprecationWarning in Regexp tokenizer (#3055)
* Fix many doctests, add doctests to CI (#3054, #3050, #3048)
* Fix bool field not being read in VerbNet (#3044)
* Greatly improve time efficiency of SyllableTokenizer when tokenizing numbers (#3042)
* Fix encodings of Polish udhr corpus reader (#3038)
* Allow TweetTokenizer to tokenize emoji flag sequences (#3034)
* Prevent LazyModule from increasing the size of nltk.__dict__ (#3033)
* Fix CoreNLPServer non-default port issue (#3031)
* Add "acion" suffix to the Spanish SnowballStemmer (#3030)
* Allow loading WordNet without OMW (#3026)
* Use input() in nltk.chat.chatbot() for Jupyter support (#3022)
* Fix edit_distance_align() in distance.py (#3017)
* Tackle performance and accuracy regression of sentence tokenizer since NLTK 3.6.6 (#3014)
* Add the Iota operator to semantic logic (#3010)
* Resolve critical errors in WordNet app (#3008)
* Resolve critical error in CHILDES Corpus (#2998)
* Make WordNet information_content() accept adjective satellites (#2995)
* Add "strict=True" parameter to CoreNLP (#2993, #3043)
* Resolve issue with WordNet's synset_from_sense_key (#2988)
* Handle WordNet synsets that were lost in mapping (#2985)
* Resolve TypeError in Boxer (#2979)
* Add function to retrieve WordNet synonyms (#2978)
* Warn about nonexistent OMW offsets instead of raising an error (#2974)
* Fix missing ic argument in res, jcn and lin similarity functions of WordNet (#2970)
* Add support for the extended OMW (#2946)
* 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>
- Complete nltk_data.tar.xz for offline testing
- Fix failing tests (gh#nltk/nltk#2969) by adding patches:
- port-2to3.patch
- skip-networked-test.patch
- Clean up the SPEC to get rid of rpmlint warnings.
-------------------------------------------------------------------
Tue Mar 22 07:48:14 UTC 2022 - Matej Cepl <mcepl@suse.com>
- Update to 3.7
- Improve and update the NLTK team page on nltk.org (#2855,
#2941)
- Drop support for Python 3.6, support Python 3.10 (#2920)
- Update to 3.6.7
- Resolve IndexError in `sent_tokenize` and `word_tokenize`
(#2922)
- Update to 3.6.6
- Refactor `gensim.doctest` to work for gensim 4.0.0 and up
(#2914)
- Add Precision, Recall, F-measure, Confusion Matrix to Taggers
(#2862)
- Added warnings if .zip files exist without any corresponding
.csv files. (#2908)
- Fix `FileNotFoundError` when the `download_dir` is
a non-existing nested folder (#2910)
- Rename omw to omw-1.4 (#2907)
- Resolve ReDoS opportunity by fixing incorrectly specified
regex (#2906, bsc#1191030, CVE-2021-3828).
- Support OMW 1.4 (#2899)
- Deprecate Tree get and set node methods (#2900)
- Fix broken inaugural test case (#2903)
- Use Multilingual Wordnet Data from OMW with newer Wordnet
versions (#2889)
- Keep NLTKs "tokenize" module working with pathlib (#2896)
- Make prettyprinter to be more readable (#2893)
- Update links to the nltk book (#2895)
- Add `CITATION.cff` to nltk (#2880)
- Resolve serious ReDoS in PunktSentenceTokenizer (#2869)
- Delete old CI config files (#2881)
- Improve Tokenize documentation + add TokenizerI as superclass
for TweetTokenizer (#2878)
- Fix expected value for BLEU score doctest after changes from
#2572
- Add multi Bleu functionality and tests (#2793)
- Deprecate 'return_str' parameter in NLTKWordTokenizer and
TreebankWordTokenizer (#2883)
- Allow empty string in CFG's + more (#2888)
- Partition `tree.py` module into `tree` package + pickle fix
(#2863)
- Fix several TreebankWordTokenizer and NLTKWordTokenizer bugs
(#2877)
- Rewind Wordnet data file after each lookup (#2868)
- Correct __init__ call for SyntaxCorpusReader subclasses
(#2872)
- Documentation fixes (#2873)
- Fix levenstein distance for duplicated letters (#2849)
- Support alternative Wordnet versions (#2860)
- Remove hundreds of formatting warnings for nltk.org (#2859)
- Modernize `nltk.org/howto` pages (#2856)
- Fix Bleu Score smoothing function from taking log(0) (#2839)
- Update third party tools to newer versions and removing
MaltParser fixed version (#2832)
- Fix TypeError: _pretty() takes 1 positional argument but 2
were given in sem/drt.py (#2854)
- Replace `http` with `https` in most URLs (#2852)
- Update to 3.6.5
- modernised nltk.org website
- addressed LGTM.com issues
- support ZWJ sequences emoji and skin tone modifer emoji in
TweetTokenizer
- METEOR evaluation now requires pre-tokenized input
- Code linting and type hinting
- implement get_refs function for DrtLambdaExpression
- Enable automated CoreNLP, Senna, Prover9/Mace4, Megam,
MaltParser CI tests
- specify minimum regex version that supports regex.Pattern
- avoid re.Pattern and regex.Pattern which fail for Python 3.6,
3.7
- Update to 3.6.4
- deprecate `nltk.usage(obj)` in favor of `help(obj)`
- resolve ReDoS vulnerability in Corpus Reader
- solidify performance tests
- improve phone number recognition in tweet tokenizer
- refactored CISTEM stemmer for German
- identify NLTK Team as the author
- replace travis badge with github actions badge
- add SECURITY.md
- Update to 3.6.3
- Dropped support for Python 3.5
- Run CI tests on Windows, too
- Moved from Travis CI to GitHub Actions
- Code and comment cleanups
- Visualize WordNet relation graphs using Graphviz
- Fixed large error in METEOR score
- Apply isort, pyupgrade, black, added as pre-commit hooks
- Prevent debug_decisions in Punkt from throwing IndexError
- Resolved ZeroDivisionError in RIBES with dissimilar sentences
- Initialize WordNet IC total counts with smoothing value
- Fixed AttributeError for Arabic ARLSTem2 stemmer
- Many fixes and improvements to lm language model package
- Fix bug in nltk.metrics.aline, C_skip = -10
- Improvements to TweetTokenizer
- Optional show arg for FreqDist.plot, ConditionalFreqDist.plot
- edit_distance now computes Damerau-Levenshtein edit-distance
- Update to 3.6.2
- move test code to nltk/test
- fix bug in NgramAssocMeasures (order preserving fix)
- Update to 3.6
- add support for Python 3.9
- add Tree.fromlist
- compute Minimum Spanning Tree of unweighted graph using BFS
- fix bug with infinite loop in Wordnet closure and tree
- fix bug in calculating BLEU using smoothing method 4
- Wordnet synset similarities work for all pos
- new Arabic light stemmer (ARLSTem2)
- new syllable tokenizer (LegalitySyllableTokenizer)
- remove nose in favor of pytest
-------------------------------------------------------------------
Thu Apr 23 13:54:08 UTC 2020 - John Vandenberg <jayvdb@gmail.com>
- Update to v3.5
* add support for Python 3.8
* drop support for Python 2
* create NLTK's own Tokenizer class distinct from the Treebank
reference tokeniser
* update Vader sentiment analyser
* fix JSON serialization of some PoS taggers
* minor improvements in grammar.CFG, Vader, pl196x corpus reader,
StringTokenizer
* change implementation <= and >= for FreqDist so they are partial
orders
* make FreqDist iterable
* correctly handle Penn Treebank trees with a unlabeled branching
top node
-------------------------------------------------------------------
Sat Mar 14 09:07:16 UTC 2020 - Tomáš Chvátal <tchvatal@suse.com>
- Fix build without python2
-------------------------------------------------------------------
Mon Oct 14 14:00:43 UTC 2019 - Matej Cepl <mcepl@suse.com>
- Replace %fdupes -s with plain %fdupes; hardlinks are better.
-------------------------------------------------------------------
Wed Sep 11 11:05:01 UTC 2019 - Tomáš Chvátal <tchvatal@suse.com>
- Update to 3.4.5 (bsc#1146427, CVE-2019-14751):
* Fixed security bug in downloader: Zip slip vulnerability - for the
unlikely situation where a user configures their downloader to use
a compromised server CVE-2019-14751
-------------------------------------------------------------------
Tue Jul 23 13:52:24 UTC 2019 - Tomáš Chvátal <tchvatal@suse.com>
- Update to 3.4.4:
* fix bug in plot function (probability.py)
* add improved PanLex Swadesh corpus reader
* add Text.generate()
* add QuadgramAssocMeasures
* add SSP to tokenizers
* return confidence of best tag from AveragedPerceptron
* make plot methods return Axes objects
* don't require list arguments to PositiveNaiveBayesClassifier.train
* fix Tree classes to work with native Python copy library
* fix inconsistency for NomBank
* fix random seeding in LanguageModel.generate
* fix ConditionalFreqDist mutation on tabulate/plot call
* fix broken links in documentation
* fix misc Wordnet issues
* update installation instructions
-------------------------------------------------------------------
Thu May 23 12:41:31 UTC 2019 - pgajdos@suse.com
- version update to 3.4.1
* add chomsky_normal_form for CFGs
* add meteor score
* add minimum edit/Levenshtein distance based alignment function
* allow access to collocation list via text.collocation_list()
* support corenlp server options
* drop support for Python 3.4
* other minor fixes
-------------------------------------------------------------------
Sun Feb 10 16:19:17 UTC 2019 - John Vandenberg <jayvdb@gmail.com>
- Remove Python 3 dependency on singledispatch
-------------------------------------------------------------------
Sat Feb 9 16:16:11 UTC 2019 - John Vandenberg <jayvdb@gmail.com>
- Update to v3.4
+ Support Python 3.7
+ New Language Modeling package
+ Cistem Stemmer for German
+ Support Russian National Corpus incl POS tag model
+ Krippendorf Alpha inter-rater reliability test
+ Comprehensive code clean-ups
+ Switch continuous integration from Jenkins to Travis
- from v3.3
+ Support Python 3.6
+ New interface to CoreNLP
+ Support synset retrieval by sense key
+ Minor fixes to CoNLL Corpus Reader
+ AlignedSent
+ Fixed minor inconsistencies in APIs and API documentation
+ Better conformance to PEP8
+ Drop Moses Tokenizer (incompatible license)
-------------------------------------------------------------------
Wed Feb 6 09:44:56 UTC 2019 - John Vandenberg <jayvdb@gmail.com>
- Add missing dependency six
- Remove unnecessary build dependency six
- Recommend all optional dependencies
-------------------------------------------------------------------
Tue Mar 6 20:35:00 UTC 2018 - jengelh@inai.de
- Trim redundant wording from description.
-------------------------------------------------------------------
Mon Mar 5 15:02:00 UTC 2018 - badshah400@gmail.com
- Use \%license instead of \%doc to install License.txt.
-------------------------------------------------------------------
Tue Jan 30 17:16:13 UTC 2018 - guigo.lourenco@gmail.com
- Depend on the full python interpreter to fix sqlite3 import
during %check
-------------------------------------------------------------------
Tue Jan 16 11:02:13 UTC 2018 - guigo.lourenco@gmail.com
- Depend on python-rpm-macros
- Build for both Python2 and Python3
-------------------------------------------------------------------
Tue Dec 19 15:50:13 UTC 2017 - badshah400@gmail.com
- Update to version 3.2.5:
* Arabic stemmers (ARLSTem, Snowball)
* NIST MT evaluation metric and added NIST
international_tokenize
* Moses tokenizer
* Document Russian tagger
* Fix to Stanford segmenter
* Improve treebank detokenizer, VerbNet, Vader
* Misc code and documentation cleanups
* Implement fixes suggested by LGTM
- Convert specfile to python single-spec style.
- Drop unneeded BuildRequires: python-PyYAML, python-xml,
python-devel; not required for building.
- Change existing Requires to Recommends: these are really needed
for additional features, and not required for basic nltk usage.
- Add new Recommends: python-scipy, python-matplotlib,
python-pyparsing, and python-gensim; enables other optional
features.
- Run fdupes to link-up duplicate files.
- Remove exec permissions for a file not intended to be executed
(not in exec path, no hashbang, etc.)
- Remove hashbangs from non-executable files.
- Run tests following the suggestion from
http://www.nltk.org/install.html.
-------------------------------------------------------------------
Tue Feb 21 13:11:31 UTC 2017 - stephan.barth@suse.com
- update to version 3.2.2
Upstream changelog:
Support for Aline, ChrF and GLEU MT evaluation metrics, Russian POS tagger
model, Moses detokenizer, rewrite Porter Stemmer and FrameNet corpus reader,
update FrameNet Corpus to version 1.7, fixes: stanford_segmenter.py,
SentiText, CoNLL Corpus Reader, BLEU, naivebayes, Krippendorff’s alpha,
Punkt, Moses tokenizer, TweetTokenizer, ToktokTokenizer; improvements to
testing framework
-------------------------------------------------------------------
Fri Oct 14 00:31:15 UTC 2016 - toddrme2178@gmail.com
- Update to version 3.2.1
+ No changelog available
-------------------------------------------------------------------
Thu May 21 14:53:43 UTC 2015 - toddrme2178@gmail.com
- Remove upstreamed nltk-2.0.4-dont-use-python-distribute.patch
- Update to version 3.0.2
+ No changelog available
-------------------------------------------------------------------
Sun Dec 8 13:33:14 UTC 2013 - p.drouand@gmail.com
- Update to version 2.0.4
+ No changelog available
- Add nltk-2.0.4-dont-use-python-distribute.patch ; force use of
python-setuptools instead of python-distribute
-------------------------------------------------------------------
Thu Oct 24 11:09:19 UTC 2013 - speilicke@suse.com
- Require python-setuptools instead of distribute (upstreams merged)
-------------------------------------------------------------------
Fri Sep 23 12:29:05 UTC 2011 - saschpe@suse.de
- Update to version 2.0.1rc1
-------------------------------------------------------------------
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
- updated to LogicParser, DRT (Dan Garrette)
- WordNet similarity metrics return None instead of -1 when
they fail to find a path (Steve Bethard)
- shortest_path_distance uses instance hypernyms (Jordan
Boyd-Graber)
- clean_html improved (Bjorn Maeland)
- batch_parse, batch_interpret and batch_evaluate functions allow
grammar or grammar filename as argument
- more Portuguese examples (portuguese_en.doctest, examples/pt.py)
-------------------------------------------------------------------
Thu Dec 10 17:23:51 CST 2009 - oddrationale@gmail.com
- added python-nltk-remove-yaml.patch to pevent conflict with
python-yaml
- added Requires: python-yaml
-------------------------------------------------------------------
Wed Dec 9 15:39:35 CST 2009 - oddrationale@gmail.com
- Initial Release (Version 2.0b7): Sun Feb 7 18:50:18 CST 2010

2
python-nltk.rpmlintrc Normal file
View File

@ -0,0 +1,2 @@
addFilter("E: zero-length /usr/lib/python3\.\d+/site-packages/nltk/tbl/api\.py")
addFilter("explicit-lib-dependency python3\d*-joblib")

192
python-nltk.spec Normal file
View File

@ -0,0 +1,192 @@
#
# spec file for package python-nltk
#
# Copyright (c) 2024 SUSE LLC
#
# All modifications and additions to the file contributed by third parties
# remain the property of their copyright owners, unless otherwise agreed
# upon. The license for this file, and modifications and additions to the
# file, is the same license as for the pristine package itself (unless the
# license for the pristine package is not an Open Source License, in which
# case the license is the MIT License). An "Open Source License" is a
# license that conforms to the Open Source Definition (Version 1.9)
# published by the Open Source Initiative.
# Please submit bugfixes or comments via https://bugs.opensuse.org/
#
%define modname nltk
Name: python-nltk
Version: 3.8.1
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
# Download/Update NLTK data:
# quilt setup python-nltk.spec
# pushd nltk-?.?.?
# python3 -m nltk.downloader -d nltk_data tests \
# averaged_perceptron_tagger_ru \
# brown \
# cess_cat \
# cess_esp \
# conll2007 \
# floresta \
# gutenberg \
# inaugural \
# indian \
# large_grammars \
# nombank.1.0 \
# omw-1.4 \
# pl196x \
# ptb \
# punkt \
# rte \
# sinica_treebank \
# stopwords \
# treebank \
# udhr \
# universal_tagset \
# wordnet \
# wordnet_ic \
# words
# tar -cJf ../nltk_data.tar.xz nltk_data
# popd
# see https://www.nltk.org/data.html for more details
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}
BuildRequires: %{python_module wheel}
BuildRequires: %{pythons}
BuildRequires: fdupes
BuildRequires: python-rpm-macros
BuildRequires: unzip
# SECTION runtime
BuildRequires: %{python_module regex >= 2021.8.3}
BuildRequires: %{python_module click}
BuildRequires: %{python_module joblib}
BuildRequires: %{python_module tqdm}
# /SECTION
# SECTION test
BuildRequires: %{python_module tk}
BuildRequires: %{python_module Jinja2}
BuildRequires: %{python_module matplotlib}
BuildRequires: %{python_module numpy}
BuildRequires: %{python_module pyparsing}
BuildRequires: %{python_module pytest-cov}
BuildRequires: %{python_module pytest-mock}
BuildRequires: %{python_module pytest}
BuildRequires: %{python_module python-crfsuite}
BuildRequires: %{python_module requests}
BuildRequires: %{python_module scikit-learn}
BuildRequires: %{python_module scipy}
BuildRequires: %{python_module text-unidecode}
BuildRequires: %{python_module twython}
# /SECTION
Requires: python-regex >= 2021.8.3
Requires: python-click
Requires: python-joblib
Requires: python-tqdm
Recommends: python-gensim
Recommends: python-matplotlib
Recommends: python-numpy
Recommends: python-pyparsing
Recommends: python-python-crfsuite
Recommends: python-requests
Recommends: python-scikit-learn
Recommends: python-scipy
Recommends: python-twython
Requires(post): update-alternatives
Requires(postun): update-alternatives
BuildArch: noarch
%python_subpackages
# changedir = nltk/test
%description
NLTK -- the Natural Language Toolkit -- is a suite of
Python modules, data sets and tutorials supporting research and
development in Natural Language Processing.
%prep
%setup -q -a1 -n %{modname}-%{version}
# Fix EOL
sed -i 's/\r/\n/g; s/\n$//' \
README.md \
nltk/corpus/reader/knbc.py \
nltk/test/unit/test_tgrep.py \
nltk/tgrep.py \
nltk/tokenize/stanford_segmenter.py \
nltk/corpus/reader/knbc.py \
nltk/test/unit/test_tgrep.py \
nltk/tgrep.py \
nltk/tokenize/stanford_segmenter.py \
nltk/corpus/reader/knbc.py \
nltk/test/unit/test_tgrep.py \
nltk/tgrep.py \
nltk/tokenize/stanford_segmenter.py
# Remove unrequired shebangs
sed -E -i "/#![[:space:]]*\/usr\/bin\/env python/d" \
nltk/tgrep.py \
nltk/tokenize/stanford_segmenter.py \
nltk/test/unit/test_tgrep.py \
nltk/corpus/reader/knbc.py
# Switch shebangs to the standard Python interpreter
sed -E -i "s|#![[:space:]]*%{_bindir}/env python|#!%{_bindir}/python3|" \
setup.py \
tools/global_replace.py \
nltk_data/corpora/pl196x/splitter.py \
tools/find_deprecated.py
%autopatch -p1
%build
%pyproject_wheel
%install
%pyproject_install
%python_clone -a %{buildroot}%{_bindir}/nltk
%{python_expand %fdupes %{buildroot}%{$python_sitelib}/
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})"
%post
%python_install_alternative nltk
%postun
%python_uninstall_alternative nltk
%files %{python_files}
%doc README.md
%license LICENSE.txt
%{python_sitelib}/nltk/
%{python_sitelib}/nltk-%{version}.dist-info/
%python_alternative %{_bindir}/nltk
%changelog

35
skip-networked-test.patch Normal file
View File

@ -0,0 +1,35 @@
---
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