rpm/python-html5lib
SHA256
1
0
Fork 0
forked from pool/python-html5lib
Code Pull Requests Activity

Accepting request 830074 from devel:languages:python

Browse Source 
OBS-URL: https://build.opensuse.org/request/show/830074
OBS-URL: https://build.opensuse.org/package/show/openSUSE:Factory/python-html5lib?expand=0&rev=22
This commit is contained in:
Dominique Leuenberger
2020-09-04 08:59:37 +00:00
committed by Git OBS Bridge
parent 05f6993d49 bc0eb93e65
commit f58b4e3d7a
8 changed files with 183 additions and 260 deletions
Download Patch File Download Diff File Expand all files Collapse all files

44
collections-abc.patch
View File

@@ -1,44 +0,0 @@
From 322a2d57bfdc52a9ce14bee93f9abb372cc08487 Mon Sep 17 00:00:00 2001
From: 5j9 <5j9@users.noreply.github.com>
Date: Sun, 23 Sep 2018 11:32:46 +0330
Subject: [PATCH] Try to import MutableMapping from collections.abc
Note that collections.abc has been added in Python 3.3.
Fixes #402
---
html5lib/_trie/_base.py | 5 ++++-
html5lib/treebuilders/dom.py | 5 ++++-
2 files changed, 8 insertions(+), 2 deletions(-)
diff --git a/html5lib/_trie/_base.py b/html5lib/_trie/_base.py
index a1158bbb..6b71975f 100644
--- a/html5lib/_trie/_base.py
+++ b/html5lib/_trie/_base.py
@@ -1,6 +1,9 @@
from __future__ import absolute_import, division, unicode_literals
-from collections import Mapping
+try:
+ from collections.abc import Mapping
+except ImportError: # Python 2.7
+ from collections import Mapping
class Trie(Mapping):
diff --git a/html5lib/treebuilders/dom.py b/html5lib/treebuilders/dom.py
index dcfac220..d8b53004 100644
--- a/html5lib/treebuilders/dom.py
+++ b/html5lib/treebuilders/dom.py
@@ -1,7 +1,10 @@
from __future__ import absolute_import, division, unicode_literals
-from collections import MutableMapping
+try:
+ from collections.abc import MutableMapping
+except ImportError: # Python 2.7
+ from collections import MutableMapping
from xml.dom import minidom, Node
import weakref

3
html5lib-1.0.1.tar.gz
View File

@@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:66cb0dcfdbbc4f9c3ba1a63fdb511ffdbd4f513b2b6d81b80cd26ce6b3fb3736
size 252959

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

Binary file not shown.

143
pytest4-mhroncok.patch
View File

@@ -1,143 +0,0 @@
From dd117cc62d961573e9867d79ae1c3461a42e6167 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Miro=20Hron=C4=8Dok?= <miro@hroncok.cz>
Date: Thu, 28 Mar 2019 01:45:43 +0100
Subject: [PATCH] Support pytest 4
Fixes https://github.com/html5lib/html5lib-python/issues/411
---
html5lib/tests/test_encoding.py | 4 ++--
html5lib/tests/test_sanitizer.py | 14 +++++++-------
html5lib/tests/test_serializer.py | 2 +-
html5lib/tests/test_stream.py | 7 ++++---
html5lib/tests/test_treewalkers.py | 2 +-
requirements-test.txt | 2 +-
tox.ini | 2 +-
7 files changed, 17 insertions(+), 16 deletions(-)
--- a/html5lib/tests/test_encoding.py
+++ b/html5lib/tests/test_encoding.py
@@ -94,13 +94,13 @@ def runPreScanEncodingTest(data, encodin
assert encoding == stream.charEncoding[0].name, errorMessage(data, encoding, stream.charEncoding[0].name)
-
+@pytest.mark.skip(reason="broken under pytest4")
def test_encoding():
for filename in get_data_files("encoding"):
tests = _TestData(filename, b"data", encoding=None)
for test in tests:
- yield (runParserEncodingTest, test[b'data'], test[b'encoding'])
- yield (runPreScanEncodingTest, test[b'data'], test[b'encoding'])
+ runParserEncodingTest(test[b'data'], test[b'encoding'])
+ runPreScanEncodingTest(test[b'data'], test[b'encoding'])
# pylint:disable=wrong-import-position
--- a/html5lib/tests/test_sanitizer.py
+++ b/html5lib/tests/test_sanitizer.py
@@ -67,19 +67,19 @@ def test_sanitizer():
'tfoot', 'th', 'thead', 'tr', 'select']:
continue # TODO
if tag_name == 'image':
- yield (runSanitizerTest, "test_should_allow_%s_tag" % tag_name,
+ runSanitizerTest("test_should_allow_%s_tag" % tag_name,
"<img title=\"1\"/>foo &lt;bad&gt;bar&lt;/bad&gt; baz",
"<%s title='1'>foo <bad>bar</bad> baz</%s>" % (tag_name, tag_name))
elif tag_name == 'br':
- yield (runSanitizerTest, "test_should_allow_%s_tag" % tag_name,
+ runSanitizerTest("test_should_allow_%s_tag" % tag_name,
"<br title=\"1\"/>foo &lt;bad&gt;bar&lt;/bad&gt; baz<br/>",
"<%s title='1'>foo <bad>bar</bad> baz</%s>" % (tag_name, tag_name))
elif tag_name in constants.voidElements:
- yield (runSanitizerTest, "test_should_allow_%s_tag" % tag_name,
+ runSanitizerTest("test_should_allow_%s_tag" % tag_name,
"<%s title=\"1\"/>foo &lt;bad&gt;bar&lt;/bad&gt; baz" % tag_name,
"<%s title='1'>foo <bad>bar</bad> baz</%s>" % (tag_name, tag_name))
else:
- yield (runSanitizerTest, "test_should_allow_%s_tag" % tag_name,
+ runSanitizerTest("test_should_allow_%s_tag" % tag_name,
"<%s title=\"1\">foo &lt;bad&gt;bar&lt;/bad&gt; baz</%s>" % (tag_name, tag_name),
"<%s title='1'>foo <bad>bar</bad> baz</%s>" % (tag_name, tag_name))
@@ -93,7 +93,7 @@ def test_sanitizer():
attribute_value = 'foo'
if attribute_name in sanitizer.attr_val_is_uri:
attribute_value = '%s://sub.domain.tld/path/object.ext' % sanitizer.allowed_protocols[0]
- yield (runSanitizerTest, "test_should_allow_%s_attribute" % attribute_name,
+ runSanitizerTest("test_should_allow_%s_attribute" % attribute_name,
"<p %s=\"%s\">foo &lt;bad&gt;bar&lt;/bad&gt; baz</p>" % (attribute_name, attribute_value),
"<p %s='%s'>foo <bad>bar</bad> baz</p>" % (attribute_name, attribute_value))
@@ -101,7 +101,7 @@ def test_sanitizer():
rest_of_uri = '//sub.domain.tld/path/object.ext'
if protocol == 'data':
rest_of_uri = 'image/png;base64,aGVsbG8gd29ybGQ='
- yield (runSanitizerTest, "test_should_allow_uppercase_%s_uris" % protocol,
+ runSanitizerTest("test_should_allow_uppercase_%s_uris" % protocol,
"<img src=\"%s:%s\">foo</a>" % (protocol, rest_of_uri),
"""<img src="%s:%s">foo</a>""" % (protocol, rest_of_uri))
@@ -110,7 +110,7 @@ def test_sanitizer():
if protocol == 'data':
rest_of_uri = 'image/png;base64,aGVsbG8gd29ybGQ='
protocol = protocol.upper()
- yield (runSanitizerTest, "test_should_allow_uppercase_%s_uris" % protocol,
+ runSanitizerTest("test_should_allow_uppercase_%s_uris" % protocol,
"<img src=\"%s:%s\">foo</a>" % (protocol, rest_of_uri),
"""<img src="%s:%s">foo</a>""" % (protocol, rest_of_uri))
--- a/html5lib/tests/test_serializer.py
+++ b/html5lib/tests/test_serializer.py
@@ -222,4 +222,4 @@ def test_serializer():
with open(filename) as fp:
tests = json.load(fp)
for test in tests['tests']:
- yield runSerializerTest, test["input"], test["expected"], test.get("options", {})
+ runSerializerTest(test["input"], test["expected"], test.get("options", {}))
--- a/html5lib/tests/test_stream.py
+++ b/html5lib/tests/test_stream.py
@@ -308,9 +308,10 @@ def test_invalid_codepoints(inp, num):
("'\\uD800\\uD800\\uD800'", 3),
("'a\\uD800a\\uD800a\\uD800a'", 3),
("'\\uDFFF\\uDBFF'", 2),
- pytest.mark.skipif(sys.maxunicode == 0xFFFF,
- ("'\\uDBFF\\uDFFF'", 2),
- reason="narrow Python")])
+ pytest.param(
+ "'\\uDBFF\\uDFFF'", 2,
+ marks=pytest.mark.skipif(sys.maxunicode == 0xFFFF,
+ reason="narrow Python"))])
def test_invalid_codepoints_surrogates(inp, num):
inp = eval(inp) # pylint:disable=eval-used
fp = StringIO(inp)
--- a/html5lib/tests/test_treewalkers.py
+++ b/html5lib/tests/test_treewalkers.py
@@ -99,7 +99,7 @@ def test_treewalker_six_mix():
for tree in sorted(treeTypes.items()):
for intext, attrs, expected in sm_tests:
- yield runTreewalkerEditTest, intext, expected, attrs, tree
+ runTreewalkerEditTest(intext, expected, attrs, tree)
@pytest.mark.parametrize("tree,char", itertools.product(sorted(treeTypes.items()), ["x", "\u1234"]))
--- a/requirements-test.txt
+++ b/requirements-test.txt
@@ -4,7 +4,7 @@ tox
flake8<3.0
-pytest==3.2.5
+pytest>=4.3,<4.4
coverage
pytest-expect>=1.1,<2.0
mock
--- a/tox.ini
+++ b/tox.ini
@@ -1,5 +1,5 @@
[tox]
-envlist = {py27,py33,py34,py35,py36,pypy}-{base,six19,optional}
+envlist = {py27,py34,py35,py36,py37,py38,pypy}-{base,six19,optional}
[testenv]
deps =

63
pytest5.patch
View File

@@ -1,63 +0,0 @@
From 3f10121d98ce8ca36b4b856275093dd189fdf1d2 Mon Sep 17 00:00:00 2001
From: Sam Sneddon <me@gsnedders.com>
Date: Fri, 22 May 2020 20:37:19 +0100
Subject: [PATCH] Update pytest
---
.pytest.expect | 4 +--
html5lib/tests/tree_construction.py | 12 ++++-----
3 files changed, 15 insertions(+), 42 deletions(-)
diff --git a/html5lib/tests/tree_construction.py b/html5lib/tests/tree_construction.py
index 6112d11d..1ef6e725 100644
--- a/html5lib/tests/tree_construction.py
+++ b/html5lib/tests/tree_construction.py
@@ -57,8 +57,6 @@ def _getParserTests(self, treeName, treeAPIs):
item.add_marker(pytest.mark.parser)
if namespaceHTMLElements:
item.add_marker(pytest.mark.namespaced)
- if treeAPIs is None:
- item.add_marker(pytest.mark.skipif(True, reason="Treebuilder not loaded"))
yield item
def _getTreeWalkerTests(self, treeName, treeAPIs):
@@ -69,8 +67,6 @@ def _getTreeWalkerTests(self, treeName, treeAPIs):
treeAPIs)
item.add_marker(getattr(pytest.mark, treeName))
item.add_marker(pytest.mark.treewalker)
- if treeAPIs is None:
- item.add_marker(pytest.mark.skipif(True, reason="Treebuilder not loaded"))
yield item
@@ -84,12 +80,14 @@ def convertTreeDump(data):
class ParserTest(pytest.Item):
def __init__(self, name, parent, test, treeClass, namespaceHTMLElements):
super(ParserTest, self).__init__(name, parent)
- self.obj = lambda: 1 # this is to hack around skipif needing a function!
self.test = test
self.treeClass = treeClass
self.namespaceHTMLElements = namespaceHTMLElements
def runtest(self):
+ if self.treeClass is None:
+ pytest.skip("Treebuilder not loaded")
+
p = html5parser.HTMLParser(tree=self.treeClass,
namespaceHTMLElements=self.namespaceHTMLElements)
@@ -147,11 +145,13 @@ def repr_failure(self, excinfo):
class TreeWalkerTest(pytest.Item):
def __init__(self, name, parent, test, treeAPIs):
super(TreeWalkerTest, self).__init__(name, parent)
- self.obj = lambda: 1 # this is to hack around skipif needing a function!
self.test = test
self.treeAPIs = treeAPIs
def runtest(self):
+ if self.treeAPIs is None:
+ pytest.skip("Treebuilder not loaded")
+
p = html5parser.HTMLParser(tree=self.treeAPIs["builder"])
input = self.test['data']

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'

14
python-html5lib.changes
View File

@@ -1,3 +1,17 @@
-------------------------------------------------------------------
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>

10
python-html5lib.spec
View File

@@ -18,19 +18,15 @@
%{?!python_module:%define python_module() python-%{**} python3-%{**}}
Name: python-html5lib
Version: 1.0.1
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 pytest4-mhroncok.patch gh#html5lib/html5lib-python#429 mcepl@suse.com
# This patch makes testsuite pass with pytest4
Patch0: pytest4-mhroncok.patch
Patch1: collections-abc.patch
Patch2: pytest5.patch
# PATCH-FIX_UPSTREAM https://github.com/html5lib/html5lib-python/commit/2c19b9899ab3a3e8bd0ca35e5d78544334204169 Use Node.from_parent() constructor to support pytest 6
Patch0: pytest6.patch
BuildRequires: %{python_module Genshi}
BuildRequires: %{python_module datrie}
BuildRequires: %{python_module lxml}
BuildRequires: %{python_module mock}
BuildRequires: %{python_module pytest >= 4.0}