Script 'mail_helper' called by obssrc
Hello community,
here is the log from the commit of package python-hanzidentifier for
openSUSE:Factory checked in at 2022-10-29 20:17:39
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Comparing /work/SRC/openSUSE:Factory/python-hanzidentifier (Old)
and /work/SRC/openSUSE:Factory/.python-hanzidentifier.new.2275 (New)
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Package is "python-hanzidentifier"
Sat Oct 29 20:17:39 2022 rev:3 rq:1032188 version:1.1.0
Changes:
--------
---
/work/SRC/openSUSE:Factory/python-hanzidentifier/python-hanzidentifier.changes
2021-06-01 10:41:26.573219724 +0200
+++
/work/SRC/openSUSE:Factory/.python-hanzidentifier.new.2275/python-hanzidentifier.changes
2022-10-29 20:18:45.070736350 +0200
@@ -1,0 +2,7 @@
+Fri Oct 28 17:32:02 UTC 2022 - Yogalakshmi Arunachalam <[email protected]>
+
+- Update to version v1.1.0 (2020-10-15)
+ * New function: count_chinese(). Thanks to ramwin.
+ * Drop Python 2
+
+-------------------------------------------------------------------
Old:
----
hanzidentifier-1.0.2.tar.gz
New:
----
hanzidentifier-1.1.0.tar.gz
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Other differences:
------------------
++++++ python-hanzidentifier.spec ++++++
--- /var/tmp/diff_new_pack.WPlhP7/_old 2022-10-29 20:18:45.490738587 +0200
+++ /var/tmp/diff_new_pack.WPlhP7/_new 2022-10-29 20:18:45.498738629 +0200
@@ -1,7 +1,7 @@
#
# spec file for package python-hanzidentifier
#
-# Copyright (c) 2021 SUSE LLC
+# Copyright (c) 2022 SUSE LLC
#
# All modifications and additions to the file contributed by third parties
# remain the property of their copyright owners, unless otherwise agreed
@@ -18,7 +18,7 @@
%{?!python_module:%define python_module() python-%{**} python3-%{**}}
Name: python-hanzidentifier
-Version: 1.0.2
+Version: 1.1.0
Release: 0
License: MIT
Summary: Python module that identifies Chinese text as Simplified or
Traditional
++++++ hanzidentifier-1.0.2.tar.gz -> hanzidentifier-1.1.0.tar.gz ++++++
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/hanzidentifier-1.0.2/.gitignore
new/hanzidentifier-1.1.0/.gitignore
--- old/hanzidentifier-1.0.2/.gitignore 1970-01-01 01:00:00.000000000 +0100
+++ new/hanzidentifier-1.1.0/.gitignore 2022-10-16 03:15:43.000000000 +0200
@@ -0,0 +1 @@
+__pycache__
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/hanzidentifier-1.0.2/Makefile
new/hanzidentifier-1.1.0/Makefile
--- old/hanzidentifier-1.0.2/Makefile 1970-01-01 01:00:00.000000000 +0100
+++ new/hanzidentifier-1.1.0/Makefile 2022-10-16 03:15:43.000000000 +0200
@@ -0,0 +1,35 @@
+PROJECT = hanzidentifier
+
+.PHONY: clean lint test test-all coverage dist release
+
+help:
+ @echo "clean - remove all build artifacts"
+ @echo "lint - check style with flake8"
+ @echo "test - run tests quickly with the current Python"
+ @echo "test-all - run tests in all environments"
+ @echo "coverage - check code coverage"
+ @echo "dist - make the source and binary distributions"
+ @echo "release - package and upload a release"
+
+clean:
+ rm -rf build dist egg *.egg-info .eggs htmlcov
+ find . -name '*.py[co]' -exec rm -f {} +
+
+lint:
+ flake8 $(PROJECT) tests setup.py
+
+test:
+ python3 setup.py test
+
+test-all:
+ tox
+
+coverage:
+ coverage run --source $(PROJECT) setup.py test
+ coverage report --fail-under=100
+
+dist: clean
+ python3 setup.py sdist bdist_wheel
+
+release: clean dist
+ twine upload -s dist/*
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/hanzidentifier-1.0.2/README.rst
new/hanzidentifier-1.1.0/README.rst
--- old/hanzidentifier-1.0.2/README.rst 2015-08-06 22:43:58.000000000 +0200
+++ new/hanzidentifier-1.1.0/README.rst 2022-10-16 03:15:43.000000000 +0200
@@ -75,6 +75,12 @@
Change Log
----------
+v1.1.0 (2020-10-15)
+~~~~~~~~~~~~~~~~~~~
+
+* New function: ``count_chinese()``. Thanks to ramwin.
+* Drop Python 2.
+
v1.0.2 (2015-08-06)
~~~~~~~~~~~~~~~~~~~
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/hanzidentifier-1.0.2/hanzidentifier.py
new/hanzidentifier-1.1.0/hanzidentifier.py
--- old/hanzidentifier-1.0.2/hanzidentifier.py 2015-08-06 22:43:58.000000000
+0200
+++ new/hanzidentifier-1.1.0/hanzidentifier.py 2022-10-16 03:15:43.000000000
+0200
@@ -14,14 +14,14 @@
_TRADITIONAL_CHARACTERS = set(list(cedict.traditional))
_SIMPLIFIED_CHARACTERS = set(list(cedict.simplified))
-_SHARED_CHARACTERS = _TRADITIONAL_CHARACTERS.intersection(
- _SIMPLIFIED_CHARACTERS)
+_SHARED_CHARACTERS = _TRADITIONAL_CHARACTERS & _SIMPLIFIED_CHARACTERS
_ALL_CHARACTERS = cedict.all
+HANZI_MATCH = re.compile(f"[^{_ALL_CHARACTERS}]")
def _get_hanzi(s):
"""Extract a string's Chinese characters."""
- return set(re.sub('[^%s]' % _ALL_CHARACTERS, '', s))
+ return set(HANZI_MATCH.sub("", s))
def identify(s):
@@ -78,9 +78,9 @@
chinese = _get_hanzi(s)
if not chinese:
return False
- elif chinese.issubset(_SHARED_CHARACTERS):
+ if chinese.issubset(_SHARED_CHARACTERS):
return True
- elif chinese.issubset(_TRADITIONAL_CHARACTERS):
+ if chinese.issubset(_TRADITIONAL_CHARACTERS):
return True
return False
@@ -95,8 +95,17 @@
chinese = _get_hanzi(s)
if not chinese:
return False
- elif chinese.issubset(_SHARED_CHARACTERS):
+ if chinese.issubset(_SHARED_CHARACTERS):
return True
- elif chinese.issubset(_SIMPLIFIED_CHARACTERS):
+ if chinese.issubset(_SIMPLIFIED_CHARACTERS):
return True
return False
+
+
+def count_chinese(s: str) -> int:
+ """count how many chinese exist in a string"""
+ result = 0
+ for i in s:
+ if has_chinese(i):
+ result += 1
+ return result
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/hanzidentifier-1.0.2/setup.py
new/hanzidentifier-1.1.0/setup.py
--- old/hanzidentifier-1.0.2/setup.py 2015-08-06 22:43:58.000000000 +0200
+++ new/hanzidentifier-1.1.0/setup.py 2022-10-16 03:15:43.000000000 +0200
@@ -6,7 +6,7 @@
setup(
name='hanzidentifier',
- version='1.0.2',
+ version='1.1.0',
author='Thomas Roten',
author_email='[email protected]',
url='https://github.com/tsroten/hanzidentifier',
@@ -20,10 +20,7 @@
'License :: OSI Approved :: MIT License',
'Operating System :: OS Independent',
'Intended Audience :: Developers',
- 'Programming Language :: Python :: 2.7',
'Programming Language :: Python :: 3',
- 'Programming Language :: Python :: 3.3',
- 'Programming Language :: Python :: 3.4',
'Topic :: Text Processing :: Linguistic',
],
keywords=['chinese', 'mandarin', 'hanzi', 'characters', 'simplified',
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/hanzidentifier-1.0.2/tests/test_hanzidentifier.py
new/hanzidentifier-1.1.0/tests/test_hanzidentifier.py
--- old/hanzidentifier-1.0.2/tests/test_hanzidentifier.py 2015-08-06
22:43:58.000000000 +0200
+++ new/hanzidentifier-1.1.0/tests/test_hanzidentifier.py 2022-10-16
03:15:43.000000000 +0200
@@ -34,6 +34,16 @@
def test_return_mixed(self):
self.assertEqual(hanzidentifier.MIXED, hanzidentifier.identify(MIXED))
+ def test_count_chinese(self):
+ self.assertEqual(
+ hanzidentifier.count_chinese(BOTH),
+ 2,
+ )
+ self.assertEqual(
+ hanzidentifier.count_chinese(SIMPLIFIED),
+ 3,
+ )
+
class TestHelperFunctions(unittest.TestCase):
@@ -55,5 +65,6 @@
self.assertTrue(hanzidentifier.is_traditional(TRADITIONAL))
self.assertFalse(hanzidentifier.is_traditional(UNKNOWN))
+
if __name__ == '__main__':
unittest.main()
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/hanzidentifier-1.0.2/tox.ini
new/hanzidentifier-1.1.0/tox.ini
--- old/hanzidentifier-1.0.2/tox.ini 2015-08-06 22:43:58.000000000 +0200
+++ new/hanzidentifier-1.1.0/tox.ini 2022-10-16 03:15:43.000000000 +0200
@@ -1,4 +1,4 @@
[tox]
-envlist = py27,py34
+envlist = py37,py38,py39,py310
[testenv]
-commands=python setup.py test
+commands=python3 setup.py test
