Sync from SUSE:SLFO:Main python-dateparser revision da0f88841b7b9260e5d5817d07639d8f

This commit is contained in:
Adrian Schröter 2024-05-03 20:27:58 +02:00
commit 4b9087003a
5 changed files with 391 additions and 0 deletions

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

BIN
dateparser-1.1.8.tar.gz (Stored with Git LFS) Normal file

Binary file not shown.

32
mark-network-tests.patch Normal file
View File

@ -0,0 +1,32 @@
---
tests/test_language_detect.py | 6 +++++-
1 file changed, 5 insertions(+), 1 deletion(-)
--- a/tests/test_language_detect.py
+++ b/tests/test_language_detect.py
@@ -1,6 +1,8 @@
+import os
+import unittest
+
from datetime import datetime
from unittest.mock import Mock
-import unittest
from parameterized import parameterized, param
@@ -13,6 +15,7 @@ from dateparser.search import search_dat
detect_languages = Mock()
detect_languages.return_value = ["en"]
+NO_NETWORK = int(os.environ.get('NO_NETWORK', 0)) == 1
class CustomLangDetectParserTest(unittest.TestCase):
def check_is_returned_list(self):
@@ -22,6 +25,7 @@ class CustomLangDetectParserTest(unittes
param(dt_string="14 June 2020", confidence_threshold=0.0),
param(dt_string="26 July 2021", confidence_threshold=0.0)
])
+ @unittest.skipIf(NO_NETWORK, "Test requires network access")
def test_custom_language_detect_fast_text(self, dt_string, confidence_threshold):
self.result = fast_text_detect_languages(dt_string, confidence_threshold)
self.check_is_returned_list()

227
python-dateparser.changes Normal file
View File

@ -0,0 +1,227 @@
-------------------------------------------------------------------
Fri Apr 21 12:24:07 UTC 2023 - Dirk Müller <dmueller@suse.com>
- add sle15_python_module_pythons (jsc#PED-68)
-------------------------------------------------------------------
Sun Mar 26 20:00:19 UTC 2023 - Dirk Müller <dmueller@suse.com>
- update to 1.1.8:
* Improved date parsing for Chinese
* Improved date parsing for Czech
* Reorder language by popularity
* Fix leak of memory in cache
* Add support for "\d units later"
* Move modification in CLDR data to yaml
* Add support to use timezone via settings to get
PREFER_DATES_FROM result
-------------------------------------------------------------------
Wed Feb 15 19:43:54 UTC 2023 - Dirk Müller <dmueller@suse.com>
- update to 1.1.7:
* Add an “ago” synonym for Arabic
* Improved date parsing for Czech
* Improved date parsing for Indonesian
-------------------------------------------------------------------
Fri Jan 13 09:39:35 UTC 2023 - Dirk Müller <dmueller@suse.com>
- update to 1.1.6:
* Fix the bug where Monday is parsed as a month
* Prevent ReDoS in Spanish sentence splitting regex
-------------------------------------------------------------------
Mon Jan 2 18:57:33 UTC 2023 - Dirk Müller <dmueller@suse.com>
- update to 1.1.5:
* Parse short versions of day, month, and year
* Add a test for “in 1d”
* Update languages_info
* Add a workaround for zipimporter not having exec_module before Python
3.10
* Stabilize tests at midnight
* Add a test case for French
* Improved support for languages such as Slovak, Indonesian, Hindi, German
and Japanese
* Recursively create a model home
* Replace regex sub with simple string replace
* Add Python 3.10, 3.11 support
* Drop support for Python 3.5, 3.6 versions
- drop incompatible-regex-pattern.patch (upstream)
-------------------------------------------------------------------
Mon Nov 7 21:15:24 UTC 2022 - Yogalakshmi Arunachalam <yarunachalam@suse.com>
- Update to 1.1.3
New features:
* Add support for fractional units (#876)
Improvements:
* Fix the returned datetime skipping a day with time+timezone input and PREFER_DATES_FROM = 'future' (#1002)
* Fix input translation breaking keep_formatting (#720)
* English: support "till date" (#1005)
* English: support “after” and “before” in relative dates (#1008)
Cleanups:
* Reorganize internal data (#1090)
* CI updates (#1088
-------------------------------------------------------------------
Thu Oct 27 22:51:58 UTC 2022 - Yogalakshmi Arunachalam <yarunachalam@suse.com>
- Update to 1.1.2
* Added support for negative timestamp (#1060)
* Fixed PytzUsageWarning for Python versions >= 3.6 (#1062)
* Added support for dates with dots and spaces (#1028)
* Improved support for Ukrainian, Croatian and Russian (#1072, #1074, #1079, #1082, #1073, #1083)
* Added support for parsing Unix timestamps consistently regardless of timezones (#954)
* Improved tests (#1086)
-------------------------------------------------------------------
Thu Aug 18 16:25:26 UTC 2022 - Ben Greiner <code@bnavigator.de>
- Clean requirements: no code coverage
-------------------------------------------------------------------
Tue May 31 07:52:04 UTC 2022 - Markéta Machová <mmachova@suse.com>
- Do not collect test_search.py
* https://github.com/scrapinghub/dateparser/issues/1053
-------------------------------------------------------------------
Tue May 24 18:05:23 UTC 2022 - Matej Cepl <mcepl@suse.com>
- Update to 1.1.1:
- Improvements:
- Fixed issue with regex library by pinning dependencies to
an earlier version
- Extended support for Russian language dates starting with
lowercase
- Allowed to use_given_order for languages too
- Fixed link to settings section
- Defined UTF-8 encoding for Windows
- Fixed directories creation error in CLI utils
- Update to 1.1.0:
- New features:
- Support language detection based on langdetect, fastText,
or a custom implementation
- Add support for 'by '
- Sort default language list by internet usage
- Improvements:
- Improved support of Chinese
- Improvements in search_dates
- Make order of previous locales deterministic
- Fix parsing with trailing space
- Consider RETURN_TIME_AS_PERIOD for timestamp times
- Exclude failing regex version
- Ongoing work multithreading support
- Add demo URL
- QA:
- Migrate pipelines from Travis CI to Github Actions
- Use versioned CLDR data
- Add a script to update table of supported languages and
locales
- Sort 'skip' keys in yaml files
- Improve test coverage
- Code cleanup
- Add patches:
- incompatible-regex-pattern.patch (gh#scrapinghub/dateparser#1052)
- mark-network-tests.patch (gh#scrapinghub/dateparser#1059)
-------------------------------------------------------------------
Thu Mar 17 09:59:26 UTC 2022 - pgajdos@suse.com
- python-mock is actually not required for build
-------------------------------------------------------------------
Wed Apr 7 06:37:13 UTC 2021 - Steve Kowalik <steven.kowalik@suse.com>
- Update to 1.0.0:
* Breaking changes:
+ Drop support for Python 2.7 and pypy (see #727, #744, #748, #749, #754, #755, #758, #761, #763, #764, #777 and #783)
+ Now ``DateDataParser.get_date_data()`` returns a ``DateData`` object instead of a ``dict`` (see #778).
+ From now wrong ``settings`` are not silenced and raise ``SettingValidationError`` (see #797)
+ Now ``dateparser.parse()`` is deterministic and doesn't try previous locales. Also, ``DateDataParser.get_date_data()`` doesn't try the previous locales by default (see #781)
+ Remove the ``'base-formats'`` parser (see #721)
+ Extract the ``'no-spaces-time'`` parser from the ``'absolute-time'`` parser and make it an optional parser (see #786)
+ Remove ``numeral_translation_data`` (see #782)
+ Remove the undocumented ``SKIP_TOKENS_PARSER`` and ``FUZZY`` settings (see #728, #794)
+ Remove support for using strings in ``date_formats`` (see #726)
+ The undocumented ``ExactLanguageSearch`` class has been moved to the private scope and some internal methods have changed (see #778)
+ Changes in ``dateparser.utils``: ``normalize_unicode()`` doesn't accept ``bytes`` as input and ``convert_to_unicode`` has been deprecated (see #749)
* New features:
+ Add Python 3.9 support (see #732, #823)
+ Detect hours separated with a period/dot (see #741)
+ Add support for "decade" (see #762)
+ Add support for the hijri calendar in Python ≥ 3.6 (see #718)
+ Fix leap years when ``PREFER_DATES_FROM`` is set (see #738)
+ Fix ``STRICT_PARSING`` setting in ``no-spaces-time`` parser (see #715)
+ Consider ``RETURN_AS_TIME_PERIOD`` setting for ``relative-time`` parser (see #807)
+ Parse the 24hr time format with meridian info (see #634)
- Remove extranous %dir for egg-info.
-------------------------------------------------------------------
Thu Jul 30 01:41:23 UTC 2020 - Steve Kowalik <steven.kowalik@suse.com>
- Update to 0.7.6:
* Rename ``scripts`` to ``dateparser_scripts`` to avoid name collisions
with modules from other packages or projects
* Add Python 3.8 support
* Implement a ``REQUIRE_PARTS`` setting
* Add support for subscript and superscript numbers
* Extended French support
* Extended German support
- Switch from nose to pytest.
-------------------------------------------------------------------
Thu Apr 2 09:44:00 UTC 2020 - Marketa Calabkova <mcalabkova@suse.com>
- update to version 0.7.4
* Fixed Python 2.7 tests
* Extended Norwegian support
* Implement a PARSERS setting
* Add support for `PREFER_DATES_FROM` in relative/freshness parser
* Add support for `PREFER_DAY_OF_MONTH` in base-formats parser
* Added UTC -00:00 as a valid offset
* Fix support for “one”
* Fix tokenizer for non recognized characters
* Prevent installing regex 2019.02.19
* Added Hungarian language.
* Added setting, `STRICT_PARSING` to ignore incomplete dates.
* More simplifications for Russian and Ukrainian languages.
-------------------------------------------------------------------
Sat Sep 21 19:14:39 UTC 2019 - Arun Persaud <arun@gmx.de>
- specfile:
* be more precise in %file section
- update to version 0.7.2:
* Features:
+ Extended Czech support
+ Added time to valid periods
+ Added timezone information to dates found with search_dates()
+ Support strings as date formats
* Improvements:
+ Fixed Collections ABCs depreciation warning
+ Fixed dates with trailing colons not being parsed
+ Fixed date format override on any settings change
+ Fixed parsing current weekday as past date, regardless of
settings
+ Added UTC -2:30 as a valid offset
+ Added Python 3.7 to supported versions, dropped support for
Python 3.3 and 3.4
+ Moved to importlib from imp where possible
+ Improved support for Catalan
+ Documentation improvements
-------------------------------------------------------------------
Fri Sep 13 12:39:48 UTC 2019 - Tomáš Chvátal <tchvatal@suse.com>
- Fix license
- Format with spec-cleaner
- Remove py2 only parts
-------------------------------------------------------------------
Wed Apr 3 10:33:33 AM UTC 2019 - John Vandenberg <jayvdb@gmail.com>
- Initial spec for v0.7.1

106
python-dateparser.spec Normal file
View File

@ -0,0 +1,106 @@
#
# spec file for package python-dateparser
#
# Copyright (c) 2023 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/
#
%{?!python_module:%define python_module() python-%{**} python3-%{**}}
%define skip_python2 1
%{?sle15_python_module_pythons}
Name: python-dateparser
Version: 1.1.8
Release: 0
Summary: Date parsing library designed to parse dates from HTML pages
License: BSD-3-Clause
URL: https://github.com/scrapinghub/dateparser
Source: https://files.pythonhosted.org/packages/source/d/dateparser/dateparser-%{version}.tar.gz
# PATCH-FIX-UPSTREAM mark-network-tests.patch gh#scrapinghub/dateparser#1059 mcepl@suse.com
# mark test requiring network access
Patch1: mark-network-tests.patch
BuildRequires: %{python_module setuptools}
BuildRequires: fdupes
BuildRequires: python-rpm-macros
Requires: python-python-dateutil
Requires: python-pytz
Requires: python-regex
Requires: python-tzlocal
Recommends: convertdate
Recommends: python-fasttext
Recommends: python-langdetect
Recommends: python-ruamel.yaml
BuildArch: noarch
# SECTION test requirements
BuildRequires: %{python_module GitPython}
BuildRequires: %{python_module convertdate}
BuildRequires: %{python_module fasttext}
BuildRequires: %{python_module langdetect}
BuildRequires: %{python_module parameterized}
BuildRequires: %{python_module pytest}
BuildRequires: %{python_module python-dateutil}
BuildRequires: %{python_module pytz}
BuildRequires: %{python_module regex}
BuildRequires: %{python_module ruamel.yaml}
BuildRequires: %{python_module tzlocal}
# /SECTION
Requires(post): update-alternatives
Requires(postun):update-alternatives
%python_subpackages
%description
Date parsing library designed to parse dates from HTML pages
%prep
%autosetup -p1 -n dateparser-%{version}
# not py3 compatible and weird license of the imported module
rm tests/test_hijri.py
rm dateparser/calendars/hijri*
sed -i '1{/\/usr\/bin\/env python/d;}' \
dateparser_scripts/update_supported_languages_and_locales.py
%build
%python_build
%install
%python_install
%python_clone -a %{buildroot}%{_bindir}/dateparser-download
%python_expand %fdupes %{buildroot}%{$python_sitelib}
%check
export NO_NETWORK=1
# Requires files not shipped in PyPI sdist
ignoretestfiles="--ignore tests/test_dateparser_data_integrity.py"
# https://github.com/scrapinghub/dateparser/issues/1053
ignoretestfiles="$ignoretestfiles --ignore tests/test_search.py"
%pytest $ignoretestfiles
%post
%python_install_alternative dateparser-download
%postun
%python_uninstall_alternative dateparser-download
%files %{python_files}
%doc AUTHORS.rst README.rst
%license LICENSE
%python_alternative %{_bindir}/dateparser-download
%{python_sitelib}/dateparser
%{python_sitelib}/dateparser_cli
%{python_sitelib}/dateparser_data
%{python_sitelib}/dateparser_scripts
%{python_sitelib}/dateparser-%{version}*-info
%changelog