Accepting request 359049 from home:TheBlackCat:branches:devel:languages:python

Add coerce_comments_to_work_with_lxml.patch

OBS-URL: https://build.opensuse.org/request/show/359049
OBS-URL: https://build.opensuse.org/package/show/devel:languages:python/python-html5lib?expand=0&rev=20
This commit is contained in:
Todd R 2016-02-12 15:04:05 +00:00 committed by Git OBS Bridge
parent 29be0eb4b5
commit 642aa315f9
3 changed files with 82 additions and 5 deletions

View File

@ -0,0 +1,65 @@
From 0c551c9519e47f76f8f185089ed71cb9539b6e00 Mon Sep 17 00:00:00 2001
From: Geoffrey Sneddon <geoffers@gmail.com>
Date: Mon, 23 Nov 2015 15:17:07 +0000
Subject: [PATCH] Make lxml tree-builder coerce comments to work with lxml 3.5.
---
html5lib/ihatexml.py | 3 +++
html5lib/treebuilders/etree_lxml.py | 9 +++++----
2 files changed, 8 insertions(+), 4 deletions(-)
diff --git a/html5lib/ihatexml.py b/html5lib/ihatexml.py
index 0fc7930..5da5d93 100644
--- a/html5lib/ihatexml.py
+++ b/html5lib/ihatexml.py
@@ -225,6 +225,9 @@ def coerceComment(self, data):
while "--" in data:
warnings.warn("Comments cannot contain adjacent dashes", DataLossWarning)
data = data.replace("--", "- -")
+ if data.endswith("-"):
+ warnings.warn("Comments cannot end in a dash", DataLossWarning)
+ data += " "
return data
def coerceCharacters(self, data):
diff --git a/html5lib/treebuilders/etree_lxml.py b/html5lib/treebuilders/etree_lxml.py
index 35d08ef..c6c981f 100644
--- a/html5lib/treebuilders/etree_lxml.py
+++ b/html5lib/treebuilders/etree_lxml.py
@@ -54,7 +54,7 @@ def _getChildNodes(self):
def testSerializer(element):
rv = []
finalText = None
- infosetFilter = ihatexml.InfosetFilter()
+ infosetFilter = ihatexml.InfosetFilter(preventDoubleDashComments=True)
def serializeElement(element, indent=0):
if not hasattr(element, "tag"):
@@ -189,7 +189,7 @@ class TreeBuilder(_base.TreeBuilder):
def __init__(self, namespaceHTMLElements, fullTree=False):
builder = etree_builders.getETreeModule(etree, fullTree=fullTree)
- infosetFilter = self.infosetFilter = ihatexml.InfosetFilter()
+ infosetFilter = self.infosetFilter = ihatexml.InfosetFilter(preventDoubleDashComments=True)
self.namespaceHTMLElements = namespaceHTMLElements
class Attributes(dict):
@@ -257,7 +257,7 @@ def _getData(self):
data = property(_getData, _setData)
self.elementClass = Element
- self.commentClass = builder.Comment
+ self.commentClass = Comment
# self.fragmentClass = builder.DocumentFragment
_base.TreeBuilder.__init__(self, namespaceHTMLElements)
@@ -344,7 +344,8 @@ def insertRoot(self, token):
# Append the initial comments:
for comment_token in self.initial_comments:
- root.addprevious(etree.Comment(comment_token["data"]))
+ comment = self.commentClass(comment_token["data"])
+ root.addprevious(comment._element)
# Create the root document and add the ElementTree to it
self.document = self.documentClass()

View File

@ -1,3 +1,12 @@
-------------------------------------------------------------------
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

View File

@ -24,6 +24,8 @@ License: MIT
Group: Development/Languages/Python
Url: https://github.com/html5lib/html5lib-python
Source: http://pypi.python.org/packages/source/h/html5lib/html5lib-%{version}.tar.gz
# PATCH-FIX-UPSTREAM coerce_comments_to_work_with_lxml.patch - fix comments for new lxml comment validation - https://github.com/html5lib/html5lib-python/issues/224
Patch0: coerce_comments_to_work_with_lxml.patch
BuildRequires: python-Genshi >= 0.7
BuildRequires: python-devel
BuildRequires: python-lxml
@ -56,6 +58,7 @@ simple custom format
%prep
%setup -q -n html5lib-%{version}
%patch0 -p1
%build
python setup.py build
@ -63,11 +66,11 @@ python setup.py build
%install
python setup.py install --prefix=%{_prefix} --root=%{buildroot}
# %if 0%{?suse_version} && 0%{?suse_version} > 1110
# %check
# export LANG=en_US.UTF-8
# py.test
# %endif
%if 0%{?suse_version} && 0%{?suse_version} > 1110
%check
export LANG=en_US.UTF-8
py.test
%endif
%files
%defattr(-,root,root,-)