SLFO-pool/python-html5lib
SHA256
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Sync from SUSE:SLFO:Main python-html5lib revision 7c990556efc2e62c8dda9886f5e72c2a

Browse Source
This commit is contained in:
Adrian Schröter 2024-05-03 20:58:19 +02:00
commit 187d493f85
7 changed files with 532 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

BIN
html5lib-1.1.tar.gz (Stored with Git LFS) Normal file
View File

Binary file not shown.

163
pytest6.patch Normal file
View File

@ -0,0 +1,163 @@
From 2c19b9899ab3a3e8bd0ca35e5d78544334204169 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Miro=20Hron=C4=8Dok?= <miro@hroncok.cz>
Date: Sat, 8 Aug 2020 13:39:22 +0200
Subject: [PATCH] Use Node.from_parent() constructor to support pytest 6
Add a wrapper not to break pytest 4 (needed for Python 2 support).
============================= test session starts ==============================
platform linux -- Python 3.9.0b5, pytest-6.0.1, py-1.9.0, pluggy-0.13.1
rootdir: /builddir/build/BUILD/html5lib-1.1, configfile: pytest.ini
plugins: expect-1.1.0
collected 0 items / 1 error
==================================== ERRORS ====================================
________________________ ERROR collecting test session _________________________
/usr/lib/python3.9/site-packages/pluggy/hooks.py:286: in __call__
return self._hookexec(self, self.get_hookimpls(), kwargs)
/usr/lib/python3.9/site-packages/pluggy/manager.py:93: in _hookexec
return self._inner_hookexec(hook, methods, kwargs)
/usr/lib/python3.9/site-packages/pluggy/manager.py:84: in <lambda>
self._inner_hookexec = lambda hook, methods, kwargs: hook.multicall(
html5lib/tests/conftest.py:105: in pytest_collect_file
return TokenizerFile(path, parent)
/usr/lib/python3.9/site-packages/_pytest/nodes.py:95: in __call__
warnings.warn(NODE_USE_FROM_PARENT.format(name=self.__name__), stacklevel=2)
E pytest.PytestDeprecationWarning: Direct construction of TokenizerFile has been deprecated, please use TokenizerFile.from_parent.
E See https://docs.pytest.org/en/stable/deprecations.html#node-construction-changed-to-node-from-parent for more details.
Fixes https://github.com/html5lib/html5lib-python/issues/505
---
html5lib/tests/conftest.py | 15 ++++++++++++---
html5lib/tests/sanitizer.py | 2 +-
html5lib/tests/tokenizer.py | 10 +++++-----
html5lib/tests/tree_construction.py | 20 ++++++++++----------
requirements-test.txt | 2 +-
5 files changed, 29 insertions(+), 20 deletions(-)
diff --git a/html5lib/tests/conftest.py b/html5lib/tests/conftest.py
index dad167c5..fffeb50c 100644
--- a/html5lib/tests/conftest.py
+++ b/html5lib/tests/conftest.py
@@ -99,10 +99,19 @@ def pytest_collect_file(path, parent):
if _tree_construction in dir_and_parents:
if path.ext == ".dat":
- return TreeConstructionFile(path, parent)
+ return TreeConstructionFile.from_parent(parent, fspath=path)
elif _tokenizer in dir_and_parents:
if path.ext == ".test":
- return TokenizerFile(path, parent)
+ return TokenizerFile.from_parent(parent, fspath=path)
elif _sanitizer_testdata in dir_and_parents:
if path.ext == ".dat":
- return SanitizerFile(path, parent)
+ return SanitizerFile.from_parent(parent, fspath=path)
+
+
+# Tiny wrapper to allow .from_parent constructors on older pytest for PY27
+if not hasattr(pytest.Item.__base__, "from_parent"):
+ @classmethod
+ def from_parent(cls, parent, **kwargs):
+ return cls(parent=parent, **kwargs)
+
+ pytest.Item.__base__.from_parent = from_parent
diff --git a/html5lib/tests/sanitizer.py b/html5lib/tests/sanitizer.py
index bb483421..16e53868 100644
--- a/html5lib/tests/sanitizer.py
+++ b/html5lib/tests/sanitizer.py
@@ -13,7 +13,7 @@ def collect(self):
with codecs.open(str(self.fspath), "r", encoding="utf-8") as fp:
tests = json.load(fp)
for i, test in enumerate(tests):
- yield SanitizerTest(str(i), self, test=test)
+ yield SanitizerTest.from_parent(self, name=str(i), test=test)
class SanitizerTest(pytest.Item):
diff --git a/html5lib/tests/tokenizer.py b/html5lib/tests/tokenizer.py
index 47264cc3..cc9897a4 100644
--- a/html5lib/tests/tokenizer.py
+++ b/html5lib/tests/tokenizer.py
@@ -192,7 +192,7 @@ def collect(self):
tests = json.load(fp)
if 'tests' in tests:
for i, test in enumerate(tests['tests']):
- yield TokenizerTestCollector(str(i), self, testdata=test)
+ yield TokenizerTestCollector.from_parent(self, name=str(i), testdata=test)
class TokenizerTestCollector(pytest.Collector):
@@ -207,10 +207,10 @@ def __init__(self, name, parent=None, config=None, session=None, testdata=None):
def collect(self):
for initialState in self.testdata["initialStates"]:
initialState = capitalize(initialState)
- item = TokenizerTest(initialState,
- self,
- self.testdata,
- initialState)
+ item = TokenizerTest.from_parent(self,
+ name=initialState,
+ test=self.testdata,
+ initialState=initialState)
if self.testdata["input"] is None:
item.add_marker(pytest.mark.skipif(True, reason="Relies on lone surrogates"))
yield item
diff --git a/html5lib/tests/tree_construction.py b/html5lib/tests/tree_construction.py
index 1ef6e725..fb0657bf 100644
--- a/html5lib/tests/tree_construction.py
+++ b/html5lib/tests/tree_construction.py
@@ -26,7 +26,7 @@ class TreeConstructionFile(pytest.File):
def collect(self):
tests = TestData(str(self.fspath), "data")
for i, test in enumerate(tests):
- yield TreeConstructionTest(str(i), self, testdata=test)
+ yield TreeConstructionTest.from_parent(self, name=str(i), testdata=test)
class TreeConstructionTest(pytest.Collector):
@@ -48,11 +48,11 @@ def _getParserTests(self, treeName, treeAPIs):
nodeid = "%s::parser::namespaced" % treeName
else:
nodeid = "%s::parser::void-namespace" % treeName
- item = ParserTest(nodeid,
- self,
- self.testdata,
- treeAPIs["builder"] if treeAPIs is not None else None,
- namespaceHTMLElements)
+ item = ParserTest.from_parent(self,
+ name=nodeid,
+ test=self.testdata,
+ treeClass=treeAPIs["builder"] if treeAPIs is not None else None,
+ namespaceHTMLElements=namespaceHTMLElements)
item.add_marker(getattr(pytest.mark, treeName))
item.add_marker(pytest.mark.parser)
if namespaceHTMLElements:
@@ -61,10 +61,10 @@ def _getParserTests(self, treeName, treeAPIs):
def _getTreeWalkerTests(self, treeName, treeAPIs):
nodeid = "%s::treewalker" % treeName
- item = TreeWalkerTest(nodeid,
- self,
- self.testdata,
- treeAPIs)
+ item = TreeWalkerTest.from_parent(self,
+ name=nodeid,
+ test=self.testdata,
+ treeAPIs=treeAPIs)
item.add_marker(getattr(pytest.mark, treeName))
item.add_marker(pytest.mark.treewalker)
yield item
diff --git a/requirements-test.txt b/requirements-test.txt
index 703d0e69..57f8f617 100644
--- a/requirements-test.txt
+++ b/requirements-test.txt
@@ -3,7 +3,7 @@
tox>=3.15.1,<4
flake8>=3.8.1,<3.9
pytest>=4.6.10,<5 ; python_version < '3'
-pytest>=5.4.2,<6 ; python_version >= '3'
+pytest>=5.4.2,<7 ; python_version >= '3'
coverage>=5.1,<6
pytest-expect>=1.1.0,<2
mock>=3.0.5,<4 ; python_version < '3.6'

26
pytest74.patch Normal file
View File

@ -0,0 +1,26 @@
Index: html5lib-1.1/html5lib/tests/tokenizer.py
===================================================================
--- html5lib-1.1.orig/html5lib/tests/tokenizer.py
+++ html5lib-1.1/html5lib/tests/tokenizer.py
@@ -246,7 +246,7 @@ class TokenizerTest(pytest.Item):
def repr_failure(self, excinfo):
traceback = excinfo.traceback
ntraceback = traceback.cut(path=__file__)
- excinfo.traceback = ntraceback.filter()
+ excinfo.traceback = ntraceback.filter(excinfo)
return excinfo.getrepr(funcargs=True,
showlocals=False,
Index: html5lib-1.1/html5lib/tests/tree_construction.py
===================================================================
--- html5lib-1.1.orig/html5lib/tests/tree_construction.py
+++ html5lib-1.1/html5lib/tests/tree_construction.py
@@ -135,7 +135,7 @@ class ParserTest(pytest.Item):
def repr_failure(self, excinfo):
traceback = excinfo.traceback
ntraceback = traceback.cut(path=__file__)
- excinfo.traceback = ntraceback.filter()
+ excinfo.traceback = ntraceback.filter(excinfo)
return excinfo.getrepr(funcargs=True,
showlocals=False,

13
python-html5lib-no-mock.patch Normal file
View File

@ -0,0 +1,13 @@
Index: html5lib-1.1/html5lib/tests/test_meta.py
===================================================================
--- html5lib-1.1.orig/html5lib/tests/test_meta.py 2020-06-23 01:23:02.000000000 +0200
+++ html5lib-1.1/html5lib/tests/test_meta.py 2022-03-21 14:42:19.011204038 +0100
@@ -1,7 +1,7 @@
from __future__ import absolute_import, division, unicode_literals
import six
-from mock import Mock
+from unittest.mock import Mock
from . import support

224
python-html5lib.changes Normal file
View File

@ -0,0 +1,224 @@
-------------------------------------------------------------------
Thu Jul 27 07:50:37 UTC 2023 - Markéta Machová <mmachova@suse.com>
- Add pytest74.patch to fix tests with pytest 7.4+
-------------------------------------------------------------------
Fri Apr 21 12:26:16 UTC 2023 - Dirk Müller <dmueller@suse.com>
- add sle15_python_module_pythons (jsc#PED-68)
-------------------------------------------------------------------
Thu Apr 13 22:41:51 UTC 2023 - Matej Cepl <mcepl@suse.com>
- Make calling of %{sle15modernpython} optional.
-------------------------------------------------------------------
Thu Jul 14 02:22:46 UTC 2022 - Steve Kowalik <steven.kowalik@suse.com>
- Remove BuildRequires on mock.
-------------------------------------------------------------------
Mon Mar 21 14:10:17 UTC 2022 - pgajdos@suse.com
- do not require python-mock for build
- added patches
fix https://github.com/html5lib/html5lib-python/issues/541
+ python-html5lib-no-mock.patch
-------------------------------------------------------------------
Thu Aug 27 14:03:46 UTC 2020 - Marketa Calabkova <mcalabkova@suse.com>
- Update to 1.1
* Drop support for Python 3.3 and 3.4.
* Try to import from ``collections.abc`` to remove DeprecationWarning and ensure
``html5lib`` keeps working in future Python versions. (#403)
* Drop optional ``datrie`` dependency. (#442)
- Drop merged patches:
* pytest4-mhroncok.patch
* collections-abc.patch
* pytest5.patch
- Add upstream patch pytest6.patch
-------------------------------------------------------------------
Fri May 29 09:17:23 UTC 2020 - Tomáš Chvátal <tchvatal@suse.com>
- Add patch to fix run with pytest5:
* pytest5.patch
-------------------------------------------------------------------
Wed May 6 07:41:38 UTC 2020 - Tomáš Chvátal <tchvatal@suse.com>
- Add patch to not collide with collections deprecation:
* collections-abc.patch
-------------------------------------------------------------------
Wed Jan 15 12:31:39 UTC 2020 - Tomáš Chvátal <tchvatal@suse.com>
- Restrict pytest to < 5.0 as it broke with 5.3 and upstream
still didn't bother to merge support for even pytest 4+...
-------------------------------------------------------------------
Tue Dec 3 14:25:29 UTC 2019 - Tomáš Chvátal <tchvatal@suse.com>
- Fix comments in the spec file
-------------------------------------------------------------------
Fri Nov 1 11:50:36 CET 2019 - Matej Cepl <mcepl@suse.com>
- Add pytest4-mhroncok.patch by Miro Hroncok from
gh#html5lib/html5lib-python#414 to make testsuite passing under
pytest4+.
-------------------------------------------------------------------
Mon Oct 14 13:39:22 UTC 2019 - Matej Cepl <mcepl@suse.com>
- Replace %fdupes with plain %fdupes; hardlinks are better.
-------------------------------------------------------------------
Fri Jul 19 12:28:28 UTC 2019 - Tomáš Chvátal <tchvatal@suse.com>
- Restrict pytest4 for now as upstream supports only 3 series
at the moment
-------------------------------------------------------------------
Tue Dec 4 12:48:57 UTC 2018 - Matej Cepl <mcepl@suse.com>
- Remove superfluous devel dependency for noarch package
-------------------------------------------------------------------
Wed Dec 13 13:31:39 UTC 2017 - tchvatal@suse.com
- Version update to latest 1.0.1 release:
* Dropped support for py 2.6
* Documentation update
* Fixes for python 3.7 and 3.6
-------------------------------------------------------------------
Tue Dec 5 16:42:07 UTC 2017 - opensuse@dstoecker.de
- update to 1.0b10
-------------------------------------------------------------------
Fri Apr 7 16:07:01 UTC 2017 - toddrme2178@gmail.com
- html5lib has a hard dependency on python-webencodings.
It will fail at import time without it.
-------------------------------------------------------------------
Tue Apr 4 14:54:02 UTC 2017 - aloisio@gmx.com
- Updated to version 0.999999999 (see CHANGES.rst)
- Converted to single-spec
- Dropped coerce_comments_to_work_with_lxml.patch (accepted
upstream)
-------------------------------------------------------------------
Fri Feb 12 14:54:04 UTC 2016 - toddrme2178@gmail.com
- Add coerce_comments_to_work_with_lxml.patch
Fixes compatibility with python-lxml 3.5+, which adds validation
for xml comments.
Should be in next release/
- Re-enable tests.
-------------------------------------------------------------------
Tue Feb 2 11:46:24 UTC 2016 - toddrme2178@gmail.com
- Disable broken tests.
Check if they are working again in the next release.
-------------------------------------------------------------------
Mon Feb 1 10:33:59 UTC 2016 - toddrme2178@gmail.com
- update to version 0.9999999:
* Fix #195: fix the sanitizer to drop broken URLs (it threw an
exception between 0.9999 and 0.999999).
-------------------------------------------------------------------
Mon Aug 3 16:30:05 UTC 2015 - tbechtold@suse.com
- Relax python-lxml BuildRequires and Requires. html5lib should
also work with older python-lxml modules.
-------------------------------------------------------------------
Mon Jul 27 19:04:15 UTC 2015 - aloisio@gmx.com
- Update to version 0.999999
* Fix #189: fix the sanitizer to allow relative URLs again
(as it did prior to 0.9999/1.0b5).
- Aligned version requirements with PyPI
-------------------------------------------------------------------
Fri Jul 24 20:28:37 UTC 2015 - seife+obs@b1-systems.com
- Fix non-SUSE build by conditionalizing Recommends: tags
-------------------------------------------------------------------
Wed May 6 15:02:06 UTC 2015 - benoit.monin@gmx.fr
- update to version 0.99999:
* Fix #188: fix the sanitizer to not throw an exception when
sanitizing bogus data URLs.
- additional changes from version 0.9999:
* Fix #153: Sanitizer fails to treat some attributes as URLs.
Despite how this sounds, this has no known security
implications. No known version of IE (5.5 to current), Firefox
(3 to current), Safari (6 to current), Chrome (1 to current),
or Opera (12 to current) will run any script provided in these
attributes.
* Pass error message to the ParseError exception in strict
parsing mode.
* Allow data URIs in the sanitizer, with a whitelist of
content-types.
* Add support for Python implementations that don’t support lone
surrogates (read: Jython). Fixes #2.
* Remove localization of error messages. This functionality was
totally unused (and untested that everything was localizable),
so we may as well follow numerous browsers in not supporting
translating technical strings.
* Expose treewalkers.pprint as a public API.
* Add a documentEncoding property to HTML5Parser, fix #121.
- update project URL
-------------------------------------------------------------------
Mon May 26 22:01:47 UTC 2014 - hpj@urpla.net
- update to 0.999
- Fix #127: add work-around for CPython issue #20007: .read(0) on
http.client.HTTPResponse drops the rest of the content.
- Fix #115: lxml treewalker can now deal with fragments containing, at their
root level, text nodes with non-ASCII characters on Python 2.
- enable tests and include test suite for further validations
for distributions > 11.1 and SLES 10
-------------------------------------------------------------------
Tue Oct 22 13:29:08 UTC 2013 - toddrme2178@gmail.com
- Update to 0.99
* No changes, just updated version number
- Add additional dependencies
-------------------------------------------------------------------
Thu Mar 29 09:54:02 UTC 2012 - saschpe@suse.de
- Use upstream tarball
- Don't install tests, but install README
-------------------------------------------------------------------
Sat Feb 11 12:41:52 UTC 2012 - alexandre@exatati.com.br
- Update to 0.95:
- Sorry, no changelog atm.
- Regenerate spec file with py2pack.
-------------------------------------------------------------------
Mon Jan 18 00:16:01 UTC 2010 - alexandre@exatati.com.br
- Update to 0.90.
-------------------------------------------------------------------
Wed Oct 14 16:53:20 UTC 2009 - alexandre@exatati.com.br
- Initial package (0.11.1) for openSUSE.

80
python-html5lib.spec Normal file
View File

@ -0,0 +1,80 @@
#
# spec file for package python-html5lib
#
# 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-%{**}}
%{?sle15_python_module_pythons}
Name: python-html5lib
Version: 1.1
Release: 0
Summary: HTML parser based on the WHAT-WG Web Applications 1
License: MIT
URL: https://github.com/html5lib/html5lib-python
Source: https://files.pythonhosted.org/packages/source/h/html5lib/html5lib-%{version}.tar.gz
# PATCH-FIX_UPSTREAM https://github.com/html5lib/html5lib-python/commit/2c19b9899ab3a3e8bd0ca35e5d78544334204169 Use Node.from_parent() constructor to support pytest 6
Patch0: pytest6.patch
# https://github.com/html5lib/html5lib-python/issues/541
Patch1: python-html5lib-no-mock.patch
# PATCH-FIX-UPSTREAM https://github.com/html5lib/html5lib-python/pull/570 adapt testsuite to changes in pytest 7.4
Patch2: pytest74.patch
BuildRequires: %{python_module Genshi}
BuildRequires: %{python_module lxml}
BuildRequires: %{python_module pytest >= 4.0}
BuildRequires: %{python_module pytest-expect}
BuildRequires: %{python_module setuptools >= 18.5}
BuildRequires: %{python_module six >= 1.9}
BuildRequires: %{python_module webencodings}
BuildRequires: fdupes
BuildRequires: python-rpm-macros
Requires: python-six >= 1.9
Requires: python-webencodings
Recommends: python-Genshi
Recommends: python-lxml
BuildArch: noarch
%python_subpackages
%description
HTML parser designed to follow the HTML5
specification. The parser is designed to handle all flavours of HTML and
parses invalid documents using well-defined error handling rules compatible
with the behaviour of major desktop web browsers.
Output is to a tree structure; the current release supports output to
DOM, ElementTree, lxml and BeautifulSoup tree formats as well as a
simple custom format
%prep
%setup -q -n html5lib-%{version}
%autopatch -p1
%build
%python_build
%install
%python_install
%python_expand %fdupes %{buildroot}%{$python_sitelib}
%check
%pytest --tb=short
%files %{python_files}
%license LICENSE
%doc CHANGES.rst README.rst
%{python_sitelib}/html5lib/
%{python_sitelib}/html5lib-%{version}-py%{python_version}.egg-info
%changelog