test_001741 (tests/wellformed/sanitize/xml_declaration_unexpected_character.xml) fails with more recent Pythons (>= 3.10) #304
Description
When running the test suite while packaging feedparser for openSUSE/Tumbleweed (with regards to #279 isn’t it the time to vendor sgmllib into this package and maintain it yourself?) with the patched sgmllib I get this error:
[ 11s] ======================================================================
[ 11s] FAIL: test_001741 (__main__.TestStrictParser)
[ 11s] ./tests/wellformed/sanitize/xml_declaration_unexpected_character.xml: xml declaration unexpected character
[ 11s] ----------------------------------------------------------------------
[ 11s] Traceback (most recent call last):
[ 11s] File "/home/abuild/rpmbuild/BUILD/feedparser-6.0.8/tests/runtests.py", line 912, in fn
[ 11s] self.fail_unless_eval(xmlfile, eval_string)
[ 11s] File "/home/abuild/rpmbuild/BUILD/feedparser-6.0.8/tests/runtests.py", line 173, in fail_unless_eval
[ 11s] env = feedparser.parse(xmlfile)
[ 11s] File "/home/abuild/rpmbuild/BUILDROOT/python-feedparser-6.0.8-0.x86_64/usr/lib/python3.10/site-packages/feedparser/api.py", line 263, in parse
[ 11s] saxparser.parse(source)
[ 11s] File "/usr/lib64/python3.10/xml/sax/expatreader.py", line 111, in parse
[ 11s] xmlreader.IncrementalParser.parse(self, source)
[ 11s] File "/usr/lib64/python3.10/xml/sax/xmlreader.py", line 125, in parse
[ 11s] self.feed(buffer)
[ 11s] File "/usr/lib64/python3.10/xml/sax/expatreader.py", line 217, in feed
[ 11s] self._parser.Parse(data, isFinal)
[ 11s] File "/home/abuild/rpmbuild/BUILD/Python-3.10.2/Modules/pyexpat.c", line 468, in EndElement
[ 11s] File "/usr/lib64/python3.10/xml/sax/expatreader.py", line 381, in end_element_ns
[ 11s] self._cont_handler.endElementNS(pair, None)
[ 11s] File "/home/abuild/rpmbuild/BUILDROOT/python-feedparser-6.0.8-0.x86_64/usr/lib/python3.10/site-packages/feedparser/parsers/strict.py", line 124, in endElementNS
[ 11s] self.unknown_endtag(localname)
[ 11s] File "/home/abuild/rpmbuild/BUILDROOT/python-feedparser-6.0.8-0.x86_64/usr/lib/python3.10/site-packages/feedparser/mixin.py", line 320, in unknown_endtag
[ 11s] method()
[ 11s] File "/home/abuild/rpmbuild/BUILDROOT/python-feedparser-6.0.8-0.x86_64/usr/lib/python3.10/site-packages/feedparser/namespaces/_base.py", line 384, in _end_title
[ 11s] value = self.pop_content('title')
[ 11s] File "/home/abuild/rpmbuild/BUILDROOT/python-feedparser-6.0.8-0.x86_64/usr/lib/python3.10/site-packages/feedparser/mixin.py", line 628, in pop_content
[ 11s] value = self.pop(tag)
[ 11s] File "/home/abuild/rpmbuild/BUILDROOT/python-feedparser-6.0.8-0.x86_64/usr/lib/python3.10/site-packages/feedparser/mixin.py", line 542, in pop
[ 11s] output = resolve_relative_uris(output, self.baseuri, self.encoding, self.contentparams.get('type', 'text/html'))
[ 11s] File "/home/abuild/rpmbuild/BUILDROOT/python-feedparser-6.0.8-0.x86_64/usr/lib/python3.10/site-packages/feedparser/urls.py", line 154, in resolve_relative_uris
[ 11s] p.feed(html_source)
[ 11s] File "/home/abuild/rpmbuild/BUILDROOT/python-feedparser-6.0.8-0.x86_64/usr/lib/python3.10/site-packages/feedparser/html.py", line 156, in feed
[ 11s] super(_BaseHTMLProcessor, self).feed(data)
[ 11s] File "/usr/lib/python3.10/site-packages/sgmllib.py", line 98, in feed
[ 11s] self.goahead(0)
[ 11s] File "/usr/lib/python3.10/site-packages/sgmllib.py", line 168, in goahead
[ 11s] k = self.parse_declaration(i)
[ 11s] File "/home/abuild/rpmbuild/BUILDROOT/python-feedparser-6.0.8-0.x86_64/usr/lib/python3.10/site-packages/feedparser/html.py", line 351, in parse_declaration
[ 11s] return sgmllib.SGMLParser.parse_declaration(self, i)
[ 11s] File "/usr/lib64/python3.10/_markupbase.py", line 134, in parse_declaration
[ 11s] raise AssertionError("unexpected %r char in declaration" % rawdata[j])
[ 11s] AssertionError: unexpected '~' char in declaration
[ 11s]
[ 11s] ======================================================================
[ 11s] FAIL: test_001741 (__main__.TestLooseParser)
[ 11s] ./tests/wellformed/sanitize/xml_declaration_unexpected_character.xml: xml declaration unexpected character
[ 11s] ----------------------------------------------------------------------
[ 11s] Traceback (most recent call last):
[ 11s] File "/usr/lib/python3.10/site-packages/sgmllib.py", line 352, in finish_endtag
[ 11s] method = getattr(self, 'end_' + tag)
[ 11s] AttributeError: 'LooseFeedParser' object has no attribute 'end_title'
[ 11s]
[ 11s] During handling of the above exception, another exception occurred:
[ 11s]
[ 11s] Traceback (most recent call last):
[ 11s] File "/home/abuild/rpmbuild/BUILD/feedparser-6.0.8/tests/runtests.py", line 912, in fn
[ 11s] self.fail_unless_eval(xmlfile, eval_string)
[ 11s] File "/home/abuild/rpmbuild/BUILD/feedparser-6.0.8/tests/runtests.py", line 173, in fail_unless_eval
[ 11s] env = feedparser.parse(xmlfile)
[ 11s] File "/home/abuild/rpmbuild/BUILDROOT/python-feedparser-6.0.8-0.x86_64/usr/lib/python3.10/site-packages/feedparser/api.py", line 272, in parse
[ 11s] feedparser.feed(data.decode('utf-8', 'replace'))
[ 11s] File "/home/abuild/rpmbuild/BUILDROOT/python-feedparser-6.0.8-0.x86_64/usr/lib/python3.10/site-packages/feedparser/html.py", line 156, in feed
[ 11s] super(_BaseHTMLProcessor, self).feed(data)
[ 11s] File "/usr/lib/python3.10/site-packages/sgmllib.py", line 98, in feed
[ 11s] self.goahead(0)
[ 11s] File "/usr/lib/python3.10/site-packages/sgmllib.py", line 137, in goahead
[ 11s] k = self.parse_endtag(i)
[ 11s] File "/usr/lib/python3.10/site-packages/sgmllib.py", line 314, in parse_endtag
[ 11s] self.finish_endtag(tag)
[ 11s] File "/usr/lib/python3.10/site-packages/sgmllib.py", line 354, in finish_endtag
[ 11s] self.unknown_endtag(tag)
[ 11s] File "/home/abuild/rpmbuild/BUILDROOT/python-feedparser-6.0.8-0.x86_64/usr/lib/python3.10/site-packages/feedparser/mixin.py", line 320, in unknown_endtag
[ 11s] method()
[ 11s] File "/home/abuild/rpmbuild/BUILDROOT/python-feedparser-6.0.8-0.x86_64/usr/lib/python3.10/site-packages/feedparser/namespaces/_base.py", line 384, in _end_title
[ 11s] value = self.pop_content('title')
[ 11s] File "/home/abuild/rpmbuild/BUILDROOT/python-feedparser-6.0.8-0.x86_64/usr/lib/python3.10/site-packages/feedparser/mixin.py", line 628, in pop_content
[ 11s] value = self.pop(tag)
[ 11s] File "/home/abuild/rpmbuild/BUILDROOT/python-feedparser-6.0.8-0.x86_64/usr/lib/python3.10/site-packages/feedparser/mixin.py", line 542, in pop
[ 11s] output = resolve_relative_uris(output, self.baseuri, self.encoding, self.contentparams.get('type', 'text/html'))
[ 11s] File "/home/abuild/rpmbuild/BUILDROOT/python-feedparser-6.0.8-0.x86_64/usr/lib/python3.10/site-packages/feedparser/urls.py", line 154, in resolve_relative_uris
[ 11s] p.feed(html_source)
[ 11s] File "/home/abuild/rpmbuild/BUILDROOT/python-feedparser-6.0.8-0.x86_64/usr/lib/python3.10/site-packages/feedparser/html.py", line 156, in feed
[ 11s] super(_BaseHTMLProcessor, self).feed(data)
[ 11s] File "/usr/lib/python3.10/site-packages/sgmllib.py", line 98, in feed
[ 11s] self.goahead(0)
[ 11s] File "/usr/lib/python3.10/site-packages/sgmllib.py", line 168, in goahead
[ 11s] k = self.parse_declaration(i)
[ 11s] File "/home/abuild/rpmbuild/BUILDROOT/python-feedparser-6.0.8-0.x86_64/usr/lib/python3.10/site-packages/feedparser/html.py", line 351, in parse_declaration
[ 11s] return sgmllib.SGMLParser.parse_declaration(self, i)
[ 11s] File "/usr/lib64/python3.10/_markupbase.py", line 134, in parse_declaration
[ 11s] raise AssertionError("unexpected %r char in declaration" % rawdata[j])
[ 11s] AssertionError: unexpected '~' char in declaration
[ 11s]
Complete build log with all versions of packages used and steps taken to reproduce the issue.