Hello community, here is the log from the commit of package python-html5lib for openSUSE:Factory checked in at 2016-02-23 16:53:51 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ Comparing /work/SRC/openSUSE:Factory/python-html5lib (Old) and /work/SRC/openSUSE:Factory/.python-html5lib.new (New) ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Package is "python-html5lib" Changes: -------- --- /work/SRC/openSUSE:Factory/python-html5lib/python-html5lib.changes 2015-08-07 00:23:34.000000000 +0200 +++ /work/SRC/openSUSE:Factory/.python-html5lib.new/python-html5lib.changes 2016-02-23 16:53:52.000000000 +0100 @@ -1,0 +2,22 @@ +Fri Feb 12 14:54:04 UTC 2016 - [email protected] + +- 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 - [email protected] + +- Disable broken tests. + Check if they are working again in the next release. + +------------------------------------------------------------------- +Mon Feb 1 10:33:59 UTC 2016 - [email protected] + +- update to version 0.9999999: + * Fix #195: fix the sanitizer to drop broken URLs (it threw an + exception between 0.9999 and 0.999999). + +------------------------------------------------------------------- Old: ---- html5lib-0.999999.tar.gz New: ---- coerce_comments_to_work_with_lxml.patch html5lib-0.9999999.tar.gz ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ Other differences: ------------------ ++++++ python-html5lib.spec ++++++ --- /var/tmp/diff_new_pack.8JJ3TM/_old 2016-02-23 16:53:53.000000000 +0100 +++ /var/tmp/diff_new_pack.8JJ3TM/_new 2016-02-23 16:53:53.000000000 +0100 @@ -1,7 +1,7 @@ # # spec file for package python-html5lib # -# Copyright (c) 2015 SUSE LINUX GmbH, Nuernberg, Germany. +# Copyright (c) 2016 SUSE LINUX GmbH, Nuernberg, Germany. # # All modifications and additions to the file contributed by third parties # remain the property of their copyright owners, unless otherwise agreed @@ -17,17 +17,20 @@ Name: python-html5lib -Version: 0.999999 +Version: 0.9999999 Release: 0 Summary: HTML parser based on the WHAT-WG Web Applications 1 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 -BuildRequires: python-nose >= 1.3.7 +BuildRequires: python-mock +BuildRequires: python-pytest BuildRequires: python-setuptools >= 18.0.1 BuildRequires: python-six >= 1.9.0 Requires: python-six >= 1.9.0 @@ -55,6 +58,7 @@ %prep %setup -q -n html5lib-%{version} +%patch0 -p1 %build python setup.py build @@ -64,7 +68,8 @@ %if 0%{?suse_version} && 0%{?suse_version} > 1110 %check -nosetests +export LANG=en_US.UTF-8 +py.test %endif %files ++++++ coerce_comments_to_work_with_lxml.patch ++++++ >From 0c551c9519e47f76f8f185089ed71cb9539b6e00 Mon Sep 17 00:00:00 2001 From: Geoffrey Sneddon <[email protected]> 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() ++++++ html5lib-0.999999.tar.gz -> html5lib-0.9999999.tar.gz ++++++ diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' '--exclude=.svnignore' old/html5lib-0.999999/CHANGES.rst new/html5lib-0.9999999/CHANGES.rst --- old/html5lib-0.999999/CHANGES.rst 2015-07-07 03:59:29.000000000 +0200 +++ new/html5lib-0.9999999/CHANGES.rst 2015-09-10 01:07:50.000000000 +0200 @@ -1,6 +1,15 @@ Change Log ---------- +0.9999999/1.0b8 +~~~~~~~~~~~~~~~ + +Released on September 10, 2015 + +* Fix #195: fix the sanitizer to drop broken URLs (it threw an + exception between 0.9999 and 0.999999). + + 0.999999/1.0b7 ~~~~~~~~~~~~~~ diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' '--exclude=.svnignore' old/html5lib-0.999999/PKG-INFO new/html5lib-0.9999999/PKG-INFO --- old/html5lib-0.999999/PKG-INFO 2015-07-07 03:59:36.000000000 +0200 +++ new/html5lib-0.9999999/PKG-INFO 2015-09-10 01:08:12.000000000 +0200 @@ -1,6 +1,6 @@ Metadata-Version: 1.1 Name: html5lib -Version: 0.999999 +Version: 0.9999999 Summary: HTML parser based on the WHATWG HTML specification Home-page: https://github.com/html5lib/html5lib-python Author: James Graham @@ -167,6 +167,15 @@ Change Log ---------- + 0.9999999/1.0b8 + ~~~~~~~~~~~~~~~ + + Released on September 10, 2015 + + * Fix #195: fix the sanitizer to drop broken URLs (it threw an + exception between 0.9999 and 0.999999). + + 0.999999/1.0b7 ~~~~~~~~~~~~~~ diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' '--exclude=.svnignore' old/html5lib-0.999999/html5lib/__init__.py new/html5lib-0.9999999/html5lib/__init__.py --- old/html5lib-0.999999/html5lib/__init__.py 2015-07-07 03:59:29.000000000 +0200 +++ new/html5lib-0.9999999/html5lib/__init__.py 2015-09-10 01:07:50.000000000 +0200 @@ -22,4 +22,4 @@ "getTreeWalker", "serialize"] # this has to be at the top level, see how setup.py parses this -__version__ = "0.999999" +__version__ = "0.9999999" diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' '--exclude=.svnignore' old/html5lib-0.999999/html5lib/sanitizer.py new/html5lib-0.9999999/html5lib/sanitizer.py --- old/html5lib-0.999999/html5lib/sanitizer.py 2015-07-07 03:59:29.000000000 +0200 +++ new/html5lib-0.9999999/html5lib/sanitizer.py 2015-09-08 01:37:03.000000000 +0200 @@ -207,7 +207,11 @@ unescape(attrs[attr])).lower() # remove replacement characters from unescaped characters val_unescaped = val_unescaped.replace("\ufffd", "") - uri = urlparse.urlparse(val_unescaped) + try: + uri = urlparse.urlparse(val_unescaped) + except ValueError: + uri = None + del attrs[attr] if uri and uri.scheme: if uri.scheme not in self.allowed_protocols: del attrs[attr] diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' '--exclude=.svnignore' old/html5lib-0.999999/html5lib/tests/test_sanitizer.py new/html5lib-0.9999999/html5lib/tests/test_sanitizer.py --- old/html5lib-0.999999/html5lib/tests/test_sanitizer.py 2015-07-07 03:59:29.000000000 +0200 +++ new/html5lib-0.9999999/html5lib/tests/test_sanitizer.py 2015-09-08 01:37:03.000000000 +0200 @@ -113,6 +113,11 @@ "<audio controls=\"\" src=\"data:foobar\"></audio>", toxml) + yield (runSanitizerTest, "test_invalid_ipv6_url", + "<a>", + "<a href=\"h://]\">", + toxml) + yield (runSanitizerTest, "test_data_uri_disallowed_type", "<audio controls=\"\"></audio>", "<audio controls=\"\" src=\"data:text/html,<html>\"></audio>",
