2001-05-18 12:32:59 -03:00
|
|
|
"""Tests for HTMLParser.py."""
|
|
|
|
|
|
2008-05-21 10:51:18 -03:00
|
|
|
import html.parser
|
2001-08-20 18:24:19 -03:00
|
|
|
import pprint
|
2001-05-18 12:32:59 -03:00
|
|
|
import unittest
|
2008-05-20 18:35:26 -03:00
|
|
|
from test import support
|
2001-05-18 12:32:59 -03:00
|
|
|
|
|
|
|
|
|
2008-05-21 10:51:18 -03:00
|
|
|
class EventCollector(html.parser.HTMLParser):
|
2001-05-18 12:32:59 -03:00
|
|
|
|
2010-12-03 00:06:39 -04:00
|
|
|
def __init__(self, *args, **kw):
|
2001-05-18 12:32:59 -03:00
|
|
|
self.events = []
|
|
|
|
|
self.append = self.events.append
|
2010-12-03 00:06:39 -04:00
|
|
|
html.parser.HTMLParser.__init__(self, *args, **kw)
|
2001-05-18 12:32:59 -03:00
|
|
|
|
|
|
|
|
def get_events(self):
|
|
|
|
|
# Normalize the list of events so that buffer artefacts don't
|
|
|
|
|
# separate runs of contiguous characters.
|
|
|
|
|
L = []
|
|
|
|
|
prevtype = None
|
|
|
|
|
for event in self.events:
|
|
|
|
|
type = event[0]
|
|
|
|
|
if type == prevtype == "data":
|
|
|
|
|
L[-1] = ("data", L[-1][1] + event[1])
|
|
|
|
|
else:
|
|
|
|
|
L.append(event)
|
|
|
|
|
prevtype = type
|
|
|
|
|
self.events = L
|
|
|
|
|
return L
|
|
|
|
|
|
|
|
|
|
# structure markup
|
|
|
|
|
|
|
|
|
|
def handle_starttag(self, tag, attrs):
|
|
|
|
|
self.append(("starttag", tag, attrs))
|
|
|
|
|
|
|
|
|
|
def handle_startendtag(self, tag, attrs):
|
|
|
|
|
self.append(("startendtag", tag, attrs))
|
|
|
|
|
|
|
|
|
|
def handle_endtag(self, tag):
|
|
|
|
|
self.append(("endtag", tag))
|
|
|
|
|
|
|
|
|
|
# all other markup
|
|
|
|
|
|
|
|
|
|
def handle_comment(self, data):
|
|
|
|
|
self.append(("comment", data))
|
|
|
|
|
|
|
|
|
|
def handle_charref(self, data):
|
|
|
|
|
self.append(("charref", data))
|
|
|
|
|
|
|
|
|
|
def handle_data(self, data):
|
|
|
|
|
self.append(("data", data))
|
|
|
|
|
|
|
|
|
|
def handle_decl(self, data):
|
|
|
|
|
self.append(("decl", data))
|
|
|
|
|
|
|
|
|
|
def handle_entityref(self, data):
|
|
|
|
|
self.append(("entityref", data))
|
|
|
|
|
|
|
|
|
|
def handle_pi(self, data):
|
|
|
|
|
self.append(("pi", data))
|
|
|
|
|
|
2001-09-04 12:13:04 -03:00
|
|
|
def unknown_decl(self, decl):
|
|
|
|
|
self.append(("unknown decl", decl))
|
|
|
|
|
|
2001-05-18 12:32:59 -03:00
|
|
|
|
|
|
|
|
class EventCollectorExtra(EventCollector):
|
|
|
|
|
|
|
|
|
|
def handle_starttag(self, tag, attrs):
|
|
|
|
|
EventCollector.handle_starttag(self, tag, attrs)
|
|
|
|
|
self.append(("starttag_text", self.get_starttag_text()))
|
|
|
|
|
|
|
|
|
|
|
2013-11-23 13:52:05 -04:00
|
|
|
class EventCollectorCharrefs(EventCollector):
|
|
|
|
|
|
|
|
|
|
def handle_charref(self, data):
|
|
|
|
|
self.fail('This should never be called with convert_charrefs=True')
|
|
|
|
|
|
|
|
|
|
def handle_entityref(self, data):
|
|
|
|
|
self.fail('This should never be called with convert_charrefs=True')
|
|
|
|
|
|
|
|
|
|
|
2001-05-18 12:32:59 -03:00
|
|
|
class TestCaseBase(unittest.TestCase):
|
|
|
|
|
|
2011-11-01 13:57:15 -03:00
|
|
|
def get_collector(self):
|
|
|
|
|
raise NotImplementedError
|
|
|
|
|
|
2010-12-03 00:06:39 -04:00
|
|
|
def _run_check(self, source, expected_events, collector=None):
|
|
|
|
|
if collector is None:
|
2011-11-01 13:57:15 -03:00
|
|
|
collector = self.get_collector()
|
2010-12-03 00:06:39 -04:00
|
|
|
parser = collector
|
2001-05-18 12:32:59 -03:00
|
|
|
for s in source:
|
|
|
|
|
parser.feed(s)
|
|
|
|
|
parser.close()
|
2001-08-20 18:24:19 -03:00
|
|
|
events = parser.get_events()
|
2001-09-04 12:13:04 -03:00
|
|
|
if events != expected_events:
|
2013-11-23 13:52:05 -04:00
|
|
|
self.fail("received events did not match expected events" +
|
|
|
|
|
"\nSource:\n" + repr(source) +
|
|
|
|
|
"\nExpected:\n" + pprint.pformat(expected_events) +
|
2001-09-04 12:13:04 -03:00
|
|
|
"\nReceived:\n" + pprint.pformat(events))
|
2001-05-18 12:32:59 -03:00
|
|
|
|
|
|
|
|
def _run_check_extra(self, source, events):
|
2013-11-23 13:52:05 -04:00
|
|
|
self._run_check(source, events,
|
|
|
|
|
EventCollectorExtra(convert_charrefs=False))
|
2001-05-18 12:32:59 -03:00
|
|
|
|
|
|
|
|
def _parse_error(self, source):
|
|
|
|
|
def parse(source=source):
|
2012-02-13 08:11:27 -04:00
|
|
|
parser = self.get_collector()
|
2001-05-18 12:32:59 -03:00
|
|
|
parser.feed(source)
|
|
|
|
|
parser.close()
|
2013-11-02 12:08:24 -03:00
|
|
|
with self.assertRaises(html.parser.HTMLParseError):
|
|
|
|
|
with self.assertWarns(DeprecationWarning):
|
|
|
|
|
parse()
|
2001-05-18 12:32:59 -03:00
|
|
|
|
|
|
|
|
|
2011-11-01 13:57:15 -03:00
|
|
|
class HTMLParserStrictTestCase(TestCaseBase):
|
|
|
|
|
|
|
|
|
|
def get_collector(self):
|
2012-06-23 10:27:51 -03:00
|
|
|
with support.check_warnings(("", DeprecationWarning), quite=False):
|
2013-11-23 13:52:05 -04:00
|
|
|
return EventCollector(strict=True, convert_charrefs=False)
|
2001-05-18 12:32:59 -03:00
|
|
|
|
2001-08-03 16:53:01 -03:00
|
|
|
def test_processing_instruction_only(self):
|
2001-05-18 12:32:59 -03:00
|
|
|
self._run_check("<?processing instruction>", [
|
|
|
|
|
("pi", "processing instruction"),
|
|
|
|
|
])
|
2003-04-17 19:19:26 -03:00
|
|
|
self._run_check("<?processing instruction ?>", [
|
|
|
|
|
("pi", "processing instruction ?"),
|
|
|
|
|
])
|
2001-05-18 12:32:59 -03:00
|
|
|
|
2001-08-03 16:53:01 -03:00
|
|
|
def test_simple_html(self):
|
2001-05-18 12:32:59 -03:00
|
|
|
self._run_check("""
|
|
|
|
|
<!DOCTYPE html PUBLIC 'foo'>
|
|
|
|
|
<HTML>&entity; 
|
|
|
|
|
<!--comment1a
|
|
|
|
|
-></foo><bar><<?pi?></foo<bar
|
|
|
|
|
comment1b-->
|
|
|
|
|
<Img sRc='Bar' isMAP>sample
|
|
|
|
|
text
|
2001-08-03 16:53:01 -03:00
|
|
|
“
|
2012-02-13 09:50:37 -04:00
|
|
|
<!--comment2a-- --comment2b-->
|
2001-05-18 12:32:59 -03:00
|
|
|
</Html>
|
|
|
|
|
""", [
|
|
|
|
|
("data", "\n"),
|
|
|
|
|
("decl", "DOCTYPE html PUBLIC 'foo'"),
|
|
|
|
|
("data", "\n"),
|
|
|
|
|
("starttag", "html", []),
|
|
|
|
|
("entityref", "entity"),
|
|
|
|
|
("charref", "32"),
|
|
|
|
|
("data", "\n"),
|
|
|
|
|
("comment", "comment1a\n-></foo><bar><<?pi?></foo<bar\ncomment1b"),
|
|
|
|
|
("data", "\n"),
|
|
|
|
|
("starttag", "img", [("src", "Bar"), ("ismap", None)]),
|
|
|
|
|
("data", "sample\ntext\n"),
|
2001-08-03 16:53:01 -03:00
|
|
|
("charref", "x201C"),
|
|
|
|
|
("data", "\n"),
|
2001-05-18 12:32:59 -03:00
|
|
|
("comment", "comment2a-- --comment2b"),
|
|
|
|
|
("data", "\n"),
|
|
|
|
|
("endtag", "html"),
|
|
|
|
|
("data", "\n"),
|
|
|
|
|
])
|
|
|
|
|
|
2010-05-24 18:46:25 -03:00
|
|
|
def test_malformatted_charref(self):
|
|
|
|
|
self._run_check("<p>&#bad;</p>", [
|
|
|
|
|
("starttag", "p", []),
|
|
|
|
|
("data", "&#bad;"),
|
|
|
|
|
("endtag", "p"),
|
|
|
|
|
])
|
2014-02-01 15:21:01 -04:00
|
|
|
# add the [] as a workaround to avoid buffering (see #20288)
|
|
|
|
|
self._run_check(["<div>&#bad;</div>"], [
|
|
|
|
|
("starttag", "div", []),
|
|
|
|
|
("data", "&#bad;"),
|
|
|
|
|
("endtag", "div"),
|
|
|
|
|
])
|
2010-05-24 18:46:25 -03:00
|
|
|
|
2001-12-03 12:44:09 -04:00
|
|
|
def test_unclosed_entityref(self):
|
|
|
|
|
self._run_check("&entityref foo", [
|
|
|
|
|
("entityref", "entityref"),
|
|
|
|
|
("data", " foo"),
|
|
|
|
|
])
|
|
|
|
|
|
2001-08-03 16:53:01 -03:00
|
|
|
def test_bad_nesting(self):
|
|
|
|
|
# Strangely, this *is* supposed to test that overlapping
|
|
|
|
|
# elements are allowed. HTMLParser is more geared toward
|
|
|
|
|
# lexing the input that parsing the structure.
|
2001-05-18 12:32:59 -03:00
|
|
|
self._run_check("<a><b></a></b>", [
|
|
|
|
|
("starttag", "a", []),
|
|
|
|
|
("starttag", "b", []),
|
|
|
|
|
("endtag", "a"),
|
|
|
|
|
("endtag", "b"),
|
|
|
|
|
])
|
|
|
|
|
|
2001-08-20 18:24:19 -03:00
|
|
|
def test_bare_ampersands(self):
|
|
|
|
|
self._run_check("this text & contains & ampersands &", [
|
|
|
|
|
("data", "this text & contains & ampersands &"),
|
|
|
|
|
])
|
|
|
|
|
|
|
|
|
|
def test_bare_pointy_brackets(self):
|
|
|
|
|
self._run_check("this < text > contains < bare>pointy< brackets", [
|
|
|
|
|
("data", "this < text > contains < bare>pointy< brackets"),
|
|
|
|
|
])
|
|
|
|
|
|
2001-09-04 12:13:04 -03:00
|
|
|
def test_illegal_declarations(self):
|
2001-09-04 13:26:03 -03:00
|
|
|
self._parse_error('<!spacer type="block" height="25">')
|
2001-09-04 12:13:04 -03:00
|
|
|
|
2001-08-03 16:53:01 -03:00
|
|
|
def test_starttag_end_boundary(self):
|
2001-05-18 12:32:59 -03:00
|
|
|
self._run_check("""<a b='<'>""", [("starttag", "a", [("b", "<")])])
|
|
|
|
|
self._run_check("""<a b='>'>""", [("starttag", "a", [("b", ">")])])
|
|
|
|
|
|
2001-08-03 16:53:01 -03:00
|
|
|
def test_buffer_artefacts(self):
|
2001-05-18 12:32:59 -03:00
|
|
|
output = [("starttag", "a", [("b", "<")])]
|
|
|
|
|
self._run_check(["<a b='<'>"], output)
|
|
|
|
|
self._run_check(["<a ", "b='<'>"], output)
|
|
|
|
|
self._run_check(["<a b", "='<'>"], output)
|
|
|
|
|
self._run_check(["<a b=", "'<'>"], output)
|
|
|
|
|
self._run_check(["<a b='<", "'>"], output)
|
|
|
|
|
self._run_check(["<a b='<'", ">"], output)
|
|
|
|
|
|
|
|
|
|
output = [("starttag", "a", [("b", ">")])]
|
|
|
|
|
self._run_check(["<a b='>'>"], output)
|
|
|
|
|
self._run_check(["<a ", "b='>'>"], output)
|
|
|
|
|
self._run_check(["<a b", "='>'>"], output)
|
|
|
|
|
self._run_check(["<a b=", "'>'>"], output)
|
|
|
|
|
self._run_check(["<a b='>", "'>"], output)
|
|
|
|
|
self._run_check(["<a b='>'", ">"], output)
|
|
|
|
|
|
2004-09-08 19:57:01 -03:00
|
|
|
output = [("comment", "abc")]
|
|
|
|
|
self._run_check(["", "<!--abc-->"], output)
|
|
|
|
|
self._run_check(["<", "!--abc-->"], output)
|
|
|
|
|
self._run_check(["<!", "--abc-->"], output)
|
|
|
|
|
self._run_check(["<!-", "-abc-->"], output)
|
|
|
|
|
self._run_check(["<!--", "abc-->"], output)
|
|
|
|
|
self._run_check(["<!--a", "bc-->"], output)
|
|
|
|
|
self._run_check(["<!--ab", "c-->"], output)
|
|
|
|
|
self._run_check(["<!--abc", "-->"], output)
|
|
|
|
|
self._run_check(["<!--abc-", "->"], output)
|
|
|
|
|
self._run_check(["<!--abc--", ">"], output)
|
|
|
|
|
self._run_check(["<!--abc-->", ""], output)
|
|
|
|
|
|
2001-08-03 16:53:01 -03:00
|
|
|
def test_starttag_junk_chars(self):
|
2001-05-18 12:32:59 -03:00
|
|
|
self._parse_error("</>")
|
|
|
|
|
self._parse_error("</$>")
|
|
|
|
|
self._parse_error("</")
|
|
|
|
|
self._parse_error("</a")
|
|
|
|
|
self._parse_error("<a<a>")
|
|
|
|
|
self._parse_error("</a<a>")
|
|
|
|
|
self._parse_error("<!")
|
|
|
|
|
self._parse_error("<a")
|
|
|
|
|
self._parse_error("<a foo='bar'")
|
|
|
|
|
self._parse_error("<a foo='bar")
|
|
|
|
|
self._parse_error("<a foo='>'")
|
|
|
|
|
self._parse_error("<a foo='>")
|
2013-11-07 12:33:24 -04:00
|
|
|
self._parse_error("<a$>")
|
|
|
|
|
self._parse_error("<a$b>")
|
|
|
|
|
self._parse_error("<a$b/>")
|
|
|
|
|
self._parse_error("<a$b >")
|
|
|
|
|
self._parse_error("<a$b />")
|
2001-05-18 12:32:59 -03:00
|
|
|
|
2012-02-13 09:50:37 -04:00
|
|
|
def test_valid_doctypes(self):
|
|
|
|
|
# from http://www.w3.org/QA/2002/04/valid-dtd-list.html
|
|
|
|
|
dtds = ['HTML', # HTML5 doctype
|
|
|
|
|
('HTML PUBLIC "-//W3C//DTD HTML 4.01//EN" '
|
|
|
|
|
'"http://www.w3.org/TR/html4/strict.dtd"'),
|
|
|
|
|
('HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" '
|
|
|
|
|
'"http://www.w3.org/TR/html4/loose.dtd"'),
|
|
|
|
|
('html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" '
|
|
|
|
|
'"http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"'),
|
|
|
|
|
('html PUBLIC "-//W3C//DTD XHTML 1.0 Frameset//EN" '
|
|
|
|
|
'"http://www.w3.org/TR/xhtml1/DTD/xhtml1-frameset.dtd"'),
|
|
|
|
|
('math PUBLIC "-//W3C//DTD MathML 2.0//EN" '
|
|
|
|
|
'"http://www.w3.org/Math/DTD/mathml2/mathml2.dtd"'),
|
|
|
|
|
('html PUBLIC "-//W3C//DTD '
|
|
|
|
|
'XHTML 1.1 plus MathML 2.0 plus SVG 1.1//EN" '
|
|
|
|
|
'"http://www.w3.org/2002/04/xhtml-math-svg/xhtml-math-svg.dtd"'),
|
|
|
|
|
('svg PUBLIC "-//W3C//DTD SVG 1.1//EN" '
|
|
|
|
|
'"http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd"'),
|
|
|
|
|
'html PUBLIC "-//IETF//DTD HTML 2.0//EN"',
|
|
|
|
|
'html PUBLIC "-//W3C//DTD HTML 3.2 Final//EN"']
|
|
|
|
|
for dtd in dtds:
|
|
|
|
|
self._run_check("<!DOCTYPE %s>" % dtd,
|
|
|
|
|
[('decl', 'DOCTYPE ' + dtd)])
|
|
|
|
|
|
2001-08-03 16:53:01 -03:00
|
|
|
def test_declaration_junk_chars(self):
|
2001-05-18 12:32:59 -03:00
|
|
|
self._parse_error("<!DOCTYPE foo $ >")
|
|
|
|
|
|
2001-08-03 16:53:01 -03:00
|
|
|
def test_startendtag(self):
|
2001-05-18 12:32:59 -03:00
|
|
|
self._run_check("<p/>", [
|
|
|
|
|
("startendtag", "p", []),
|
|
|
|
|
])
|
|
|
|
|
self._run_check("<p></p>", [
|
|
|
|
|
("starttag", "p", []),
|
|
|
|
|
("endtag", "p"),
|
|
|
|
|
])
|
|
|
|
|
self._run_check("<p><img src='foo' /></p>", [
|
|
|
|
|
("starttag", "p", []),
|
|
|
|
|
("startendtag", "img", [("src", "foo")]),
|
|
|
|
|
("endtag", "p"),
|
|
|
|
|
])
|
|
|
|
|
|
2001-08-03 16:53:01 -03:00
|
|
|
def test_get_starttag_text(self):
|
2001-05-18 12:32:59 -03:00
|
|
|
s = """<foo:bar \n one="1"\ttwo=2 >"""
|
|
|
|
|
self._run_check_extra(s, [
|
|
|
|
|
("starttag", "foo:bar", [("one", "1"), ("two", "2")]),
|
|
|
|
|
("starttag_text", s)])
|
|
|
|
|
|
2001-08-03 16:53:01 -03:00
|
|
|
def test_cdata_content(self):
|
2011-11-01 09:12:22 -03:00
|
|
|
contents = [
|
|
|
|
|
'<!-- not a comment --> ¬-an-entity-ref;',
|
|
|
|
|
"<not a='start tag'>",
|
|
|
|
|
'<a href="" /> <p> <span></span>',
|
|
|
|
|
'foo = "</scr" + "ipt>";',
|
|
|
|
|
'foo = "</SCRIPT" + ">";',
|
|
|
|
|
'foo = <\n/script> ',
|
|
|
|
|
'<!-- document.write("</scr" + "ipt>"); -->',
|
|
|
|
|
('\n//<![CDATA[\n'
|
|
|
|
|
'document.write(\'<s\'+\'cript type="text/javascript" '
|
|
|
|
|
'src="http://www.example.org/r=\'+new '
|
|
|
|
|
'Date().getTime()+\'"><\\/s\'+\'cript>\');\n//]]>'),
|
|
|
|
|
'\n<!-- //\nvar foo = 3.14;\n// -->\n',
|
|
|
|
|
'foo = "</sty" + "le>";',
|
|
|
|
|
'<!-- \u2603 -->',
|
|
|
|
|
# these two should be invalid according to the HTML 5 spec,
|
|
|
|
|
# section 8.1.2.2
|
|
|
|
|
#'foo = </\nscript>',
|
|
|
|
|
#'foo = </ script>',
|
|
|
|
|
]
|
|
|
|
|
elements = ['script', 'style', 'SCRIPT', 'STYLE', 'Script', 'Style']
|
|
|
|
|
for content in contents:
|
|
|
|
|
for element in elements:
|
|
|
|
|
element_lower = element.lower()
|
|
|
|
|
s = '<{element}>{content}</{element}>'.format(element=element,
|
|
|
|
|
content=content)
|
|
|
|
|
self._run_check(s, [("starttag", element_lower, []),
|
|
|
|
|
("data", content),
|
|
|
|
|
("endtag", element_lower)])
|
|
|
|
|
|
2011-11-18 12:01:49 -04:00
|
|
|
def test_cdata_with_closing_tags(self):
|
|
|
|
|
# see issue #13358
|
|
|
|
|
# make sure that HTMLParser calls handle_data only once for each CDATA.
|
|
|
|
|
# The normal event collector normalizes the events in get_events,
|
|
|
|
|
# so we override it to return the original list of events.
|
|
|
|
|
class Collector(EventCollector):
|
|
|
|
|
def get_events(self):
|
|
|
|
|
return self.events
|
|
|
|
|
|
|
|
|
|
content = """<!-- not a comment --> ¬-an-entity-ref;
|
|
|
|
|
<a href="" /> </p><p> <span></span></style>
|
|
|
|
|
'</script' + '>'"""
|
|
|
|
|
for element in [' script', 'script ', ' script ',
|
|
|
|
|
'\nscript', 'script\n', '\nscript\n']:
|
|
|
|
|
element_lower = element.lower().strip()
|
|
|
|
|
s = '<script>{content}</{element}>'.format(element=element,
|
|
|
|
|
content=content)
|
|
|
|
|
self._run_check(s, [("starttag", element_lower, []),
|
|
|
|
|
("data", content),
|
|
|
|
|
("endtag", element_lower)],
|
2013-11-23 13:52:05 -04:00
|
|
|
collector=Collector(convert_charrefs=False))
|
2001-05-18 12:32:59 -03:00
|
|
|
|
2012-02-10 04:45:44 -04:00
|
|
|
def test_comments(self):
|
|
|
|
|
html = ("<!-- I'm a valid comment -->"
|
|
|
|
|
'<!--me too!-->'
|
|
|
|
|
'<!------>'
|
|
|
|
|
'<!---->'
|
|
|
|
|
'<!----I have many hyphens---->'
|
|
|
|
|
'<!-- I have a > in the middle -->'
|
|
|
|
|
'<!-- and I have -- in the middle! -->')
|
|
|
|
|
expected = [('comment', " I'm a valid comment "),
|
|
|
|
|
('comment', 'me too!'),
|
|
|
|
|
('comment', '--'),
|
|
|
|
|
('comment', ''),
|
|
|
|
|
('comment', '--I have many hyphens--'),
|
|
|
|
|
('comment', ' I have a > in the middle '),
|
|
|
|
|
('comment', ' and I have -- in the middle! ')]
|
|
|
|
|
self._run_check(html, expected)
|
|
|
|
|
|
2011-12-19 01:29:03 -04:00
|
|
|
def test_condcoms(self):
|
|
|
|
|
html = ('<!--[if IE & !(lte IE 8)]>aren\'t<![endif]-->'
|
|
|
|
|
'<!--[if IE 8]>condcoms<![endif]-->'
|
|
|
|
|
'<!--[if lte IE 7]>pretty?<![endif]-->')
|
|
|
|
|
expected = [('comment', "[if IE & !(lte IE 8)]>aren't<![endif]"),
|
|
|
|
|
('comment', '[if IE 8]>condcoms<![endif]'),
|
|
|
|
|
('comment', '[if lte IE 7]>pretty?<![endif]')]
|
|
|
|
|
self._run_check(html, expected)
|
|
|
|
|
|
2013-11-23 13:52:05 -04:00
|
|
|
def test_convert_charrefs(self):
|
|
|
|
|
collector = lambda: EventCollectorCharrefs(convert_charrefs=True)
|
|
|
|
|
self.assertTrue(collector().convert_charrefs)
|
|
|
|
|
charrefs = ['"', '"', '"', '"', '"', '"']
|
|
|
|
|
# check charrefs in the middle of the text/attributes
|
|
|
|
|
expected = [('starttag', 'a', [('href', 'foo"zar')]),
|
|
|
|
|
('data', 'a"z'), ('endtag', 'a')]
|
|
|
|
|
for charref in charrefs:
|
|
|
|
|
self._run_check('<a href="foo{0}zar">a{0}z</a>'.format(charref),
|
|
|
|
|
expected, collector=collector())
|
|
|
|
|
# check charrefs at the beginning/end of the text/attributes
|
|
|
|
|
expected = [('data', '"'),
|
|
|
|
|
('starttag', 'a', [('x', '"'), ('y', '"X'), ('z', 'X"')]),
|
|
|
|
|
('data', '"'), ('endtag', 'a'), ('data', '"')]
|
|
|
|
|
for charref in charrefs:
|
|
|
|
|
self._run_check('{0}<a x="{0}" y="{0}X" z="X{0}">'
|
|
|
|
|
'{0}</a>{0}'.format(charref),
|
|
|
|
|
expected, collector=collector())
|
|
|
|
|
# check charrefs in <script>/<style> elements
|
|
|
|
|
for charref in charrefs:
|
|
|
|
|
text = 'X'.join([charref]*3)
|
|
|
|
|
expected = [('data', '"'),
|
|
|
|
|
('starttag', 'script', []), ('data', text),
|
|
|
|
|
('endtag', 'script'), ('data', '"'),
|
|
|
|
|
('starttag', 'style', []), ('data', text),
|
|
|
|
|
('endtag', 'style'), ('data', '"')]
|
|
|
|
|
self._run_check('{1}<script>{0}</script>{1}'
|
|
|
|
|
'<style>{0}</style>{1}'.format(text, charref),
|
|
|
|
|
expected, collector=collector())
|
|
|
|
|
# check truncated charrefs at the end of the file
|
|
|
|
|
html = '&quo &# &#x'
|
|
|
|
|
for x in range(1, len(html)):
|
|
|
|
|
self._run_check(html[:x], [('data', html[:x])],
|
|
|
|
|
collector=collector())
|
|
|
|
|
# check a string with no charrefs
|
|
|
|
|
self._run_check('no charrefs here', [('data', 'no charrefs here')],
|
|
|
|
|
collector=collector())
|
|
|
|
|
|
2011-12-19 01:29:03 -04:00
|
|
|
|
2011-11-01 13:57:15 -03:00
|
|
|
class HTMLParserTolerantTestCase(HTMLParserStrictTestCase):
|
2010-12-03 00:06:39 -04:00
|
|
|
|
2011-11-01 10:00:59 -03:00
|
|
|
def get_collector(self):
|
2013-11-23 13:52:05 -04:00
|
|
|
return EventCollector(convert_charrefs=False)
|
2013-11-02 12:08:24 -03:00
|
|
|
|
|
|
|
|
def test_deprecation_warnings(self):
|
2013-11-23 13:52:05 -04:00
|
|
|
with self.assertWarns(DeprecationWarning):
|
|
|
|
|
EventCollector() # convert_charrefs not passed explicitly
|
2013-11-02 12:08:24 -03:00
|
|
|
with self.assertWarns(DeprecationWarning):
|
|
|
|
|
EventCollector(strict=True)
|
|
|
|
|
with self.assertWarns(DeprecationWarning):
|
|
|
|
|
EventCollector(strict=False)
|
|
|
|
|
with self.assertRaises(html.parser.HTMLParseError):
|
|
|
|
|
with self.assertWarns(DeprecationWarning):
|
|
|
|
|
EventCollector().error('test')
|
2010-12-03 00:06:39 -04:00
|
|
|
|
|
|
|
|
def test_tolerant_parsing(self):
|
|
|
|
|
self._run_check('<html <html>te>>xt&a<<bc</a></html>\n'
|
|
|
|
|
'<img src="URL><//img></html</html>', [
|
2011-11-14 12:53:33 -04:00
|
|
|
('starttag', 'html', [('<html', None)]),
|
|
|
|
|
('data', 'te>>xt'),
|
|
|
|
|
('entityref', 'a'),
|
2013-11-07 12:33:24 -04:00
|
|
|
('data', '<'),
|
|
|
|
|
('starttag', 'bc<', [('a', None)]),
|
2011-11-14 12:53:33 -04:00
|
|
|
('endtag', 'html'),
|
2012-02-13 05:24:50 -04:00
|
|
|
('data', '\n<img src="URL>'),
|
|
|
|
|
('comment', '/img'),
|
|
|
|
|
('endtag', 'html<')])
|
2010-12-03 00:06:39 -04:00
|
|
|
|
2012-02-13 08:11:27 -04:00
|
|
|
def test_starttag_junk_chars(self):
|
|
|
|
|
self._run_check("</>", [])
|
|
|
|
|
self._run_check("</$>", [('comment', '$')])
|
|
|
|
|
self._run_check("</", [('data', '</')])
|
|
|
|
|
self._run_check("</a", [('data', '</a')])
|
2013-11-07 12:33:24 -04:00
|
|
|
self._run_check("<a<a>", [('starttag', 'a<a', [])])
|
2012-02-13 08:11:27 -04:00
|
|
|
self._run_check("</a<a>", [('endtag', 'a<a')])
|
|
|
|
|
self._run_check("<!", [('data', '<!')])
|
|
|
|
|
self._run_check("<a", [('data', '<a')])
|
|
|
|
|
self._run_check("<a foo='bar'", [('data', "<a foo='bar'")])
|
|
|
|
|
self._run_check("<a foo='bar", [('data', "<a foo='bar")])
|
|
|
|
|
self._run_check("<a foo='>'", [('data', "<a foo='>'")])
|
|
|
|
|
self._run_check("<a foo='>", [('data', "<a foo='>")])
|
2013-11-07 12:33:24 -04:00
|
|
|
self._run_check("<a$>", [('starttag', 'a$', [])])
|
|
|
|
|
self._run_check("<a$b>", [('starttag', 'a$b', [])])
|
|
|
|
|
self._run_check("<a$b/>", [('startendtag', 'a$b', [])])
|
|
|
|
|
self._run_check("<a$b >", [('starttag', 'a$b', [])])
|
|
|
|
|
self._run_check("<a$b />", [('startendtag', 'a$b', [])])
|
2012-02-13 08:11:27 -04:00
|
|
|
|
2012-02-21 03:25:00 -04:00
|
|
|
def test_slashes_in_starttag(self):
|
|
|
|
|
self._run_check('<a foo="var"/>', [('startendtag', 'a', [('foo', 'var')])])
|
|
|
|
|
html = ('<img width=902 height=250px '
|
|
|
|
|
'src="/sites/default/files/images/homepage/foo.jpg" '
|
|
|
|
|
'/*what am I doing here*/ />')
|
|
|
|
|
expected = [(
|
|
|
|
|
'startendtag', 'img',
|
|
|
|
|
[('width', '902'), ('height', '250px'),
|
|
|
|
|
('src', '/sites/default/files/images/homepage/foo.jpg'),
|
|
|
|
|
('*what', None), ('am', None), ('i', None),
|
|
|
|
|
('doing', None), ('here*', None)]
|
|
|
|
|
)]
|
|
|
|
|
self._run_check(html, expected)
|
|
|
|
|
html = ('<a / /foo/ / /=/ / /bar/ / />'
|
|
|
|
|
'<a / /foo/ / /=/ / /bar/ / >')
|
|
|
|
|
expected = [
|
|
|
|
|
('startendtag', 'a', [('foo', None), ('=', None), ('bar', None)]),
|
|
|
|
|
('starttag', 'a', [('foo', None), ('=', None), ('bar', None)])
|
|
|
|
|
]
|
|
|
|
|
self._run_check(html, expected)
|
2012-04-18 22:18:22 -03:00
|
|
|
#see issue #14538
|
|
|
|
|
html = ('<meta><meta / ><meta // ><meta / / >'
|
|
|
|
|
'<meta/><meta /><meta //><meta//>')
|
|
|
|
|
expected = [
|
|
|
|
|
('starttag', 'meta', []), ('starttag', 'meta', []),
|
|
|
|
|
('starttag', 'meta', []), ('starttag', 'meta', []),
|
|
|
|
|
('startendtag', 'meta', []), ('startendtag', 'meta', []),
|
|
|
|
|
('startendtag', 'meta', []), ('startendtag', 'meta', []),
|
|
|
|
|
]
|
|
|
|
|
self._run_check(html, expected)
|
2012-02-21 03:25:00 -04:00
|
|
|
|
2012-02-13 08:11:27 -04:00
|
|
|
def test_declaration_junk_chars(self):
|
2012-02-13 09:50:37 -04:00
|
|
|
self._run_check("<!DOCTYPE foo $ >", [('decl', 'DOCTYPE foo $ ')])
|
2012-02-13 08:11:27 -04:00
|
|
|
|
|
|
|
|
def test_illegal_declarations(self):
|
|
|
|
|
self._run_check('<!spacer type="block" height="25">',
|
|
|
|
|
[('comment', 'spacer type="block" height="25"')])
|
|
|
|
|
|
2011-11-01 09:42:54 -03:00
|
|
|
def test_with_unquoted_attributes(self):
|
2011-11-01 10:00:59 -03:00
|
|
|
# see #12008
|
2011-11-01 09:42:54 -03:00
|
|
|
html = ("<html><body bgcolor=d0ca90 text='181008'>"
|
|
|
|
|
"<table cellspacing=0 cellpadding=1 width=100% ><tr>"
|
|
|
|
|
"<td align=left><font size=-1>"
|
|
|
|
|
"- <a href=/rabota/><span class=en> software-and-i</span></a>"
|
|
|
|
|
"- <a href='/1/'><span class=en> library</span></a></table>")
|
|
|
|
|
expected = [
|
|
|
|
|
('starttag', 'html', []),
|
|
|
|
|
('starttag', 'body', [('bgcolor', 'd0ca90'), ('text', '181008')]),
|
|
|
|
|
('starttag', 'table',
|
|
|
|
|
[('cellspacing', '0'), ('cellpadding', '1'), ('width', '100%')]),
|
|
|
|
|
('starttag', 'tr', []),
|
|
|
|
|
('starttag', 'td', [('align', 'left')]),
|
|
|
|
|
('starttag', 'font', [('size', '-1')]),
|
|
|
|
|
('data', '- '), ('starttag', 'a', [('href', '/rabota/')]),
|
|
|
|
|
('starttag', 'span', [('class', 'en')]), ('data', ' software-and-i'),
|
|
|
|
|
('endtag', 'span'), ('endtag', 'a'),
|
|
|
|
|
('data', '- '), ('starttag', 'a', [('href', '/1/')]),
|
|
|
|
|
('starttag', 'span', [('class', 'en')]), ('data', ' library'),
|
|
|
|
|
('endtag', 'span'), ('endtag', 'a'), ('endtag', 'table')
|
|
|
|
|
]
|
2011-11-01 13:57:15 -03:00
|
|
|
self._run_check(html, expected)
|
2011-11-01 09:42:54 -03:00
|
|
|
|
2010-12-03 00:06:39 -04:00
|
|
|
def test_comma_between_attributes(self):
|
|
|
|
|
self._run_check('<form action="/xxx.php?a=1&b=2&", '
|
|
|
|
|
'method="post">', [
|
|
|
|
|
('starttag', 'form',
|
2012-06-24 17:02:56 -03:00
|
|
|
[('action', '/xxx.php?a=1&b=2&'),
|
2011-11-14 12:53:33 -04:00
|
|
|
(',', None), ('method', 'post')])])
|
2010-12-03 00:06:39 -04:00
|
|
|
|
|
|
|
|
def test_weird_chars_in_unquoted_attribute_values(self):
|
|
|
|
|
self._run_check('<form action=bogus|&#()value>', [
|
|
|
|
|
('starttag', 'form',
|
2011-11-01 13:57:15 -03:00
|
|
|
[('action', 'bogus|&#()value')])])
|
2010-12-03 00:06:39 -04:00
|
|
|
|
2012-02-13 05:24:50 -04:00
|
|
|
def test_invalid_end_tags(self):
|
|
|
|
|
# A collection of broken end tags. <br> is used as separator.
|
|
|
|
|
# see http://www.w3.org/TR/html5/tokenization.html#end-tag-open-state
|
|
|
|
|
# and #13993
|
|
|
|
|
html = ('<br></label</p><br></div end tmAd-leaderBoard><br></<h4><br>'
|
|
|
|
|
'</li class="unit"><br></li\r\n\t\t\t\t\t\t</ul><br></><br>')
|
|
|
|
|
expected = [('starttag', 'br', []),
|
|
|
|
|
# < is part of the name, / is discarded, p is an attribute
|
|
|
|
|
('endtag', 'label<'),
|
|
|
|
|
('starttag', 'br', []),
|
|
|
|
|
# text and attributes are discarded
|
|
|
|
|
('endtag', 'div'),
|
|
|
|
|
('starttag', 'br', []),
|
|
|
|
|
# comment because the first char after </ is not a-zA-Z
|
|
|
|
|
('comment', '<h4'),
|
|
|
|
|
('starttag', 'br', []),
|
|
|
|
|
# attributes are discarded
|
|
|
|
|
('endtag', 'li'),
|
|
|
|
|
('starttag', 'br', []),
|
|
|
|
|
# everything till ul (included) is discarded
|
|
|
|
|
('endtag', 'li'),
|
|
|
|
|
('starttag', 'br', []),
|
|
|
|
|
# </> is ignored
|
|
|
|
|
('starttag', 'br', [])]
|
|
|
|
|
self._run_check(html, expected)
|
|
|
|
|
|
|
|
|
|
def test_broken_invalid_end_tag(self):
|
|
|
|
|
# This is technically wrong (the "> shouldn't be included in the 'data')
|
|
|
|
|
# but is probably not worth fixing it (in addition to all the cases of
|
|
|
|
|
# the previous test, it would require a full attribute parsing).
|
|
|
|
|
# see #13993
|
|
|
|
|
html = '<b>This</b attr=">"> confuses the parser'
|
|
|
|
|
expected = [('starttag', 'b', []),
|
|
|
|
|
('data', 'This'),
|
|
|
|
|
('endtag', 'b'),
|
|
|
|
|
('data', '"> confuses the parser')]
|
|
|
|
|
self._run_check(html, expected)
|
|
|
|
|
|
2011-11-01 10:00:59 -03:00
|
|
|
def test_correct_detection_of_start_tags(self):
|
|
|
|
|
# see #13273
|
2011-10-28 07:21:09 -03:00
|
|
|
html = ('<div style="" ><b>The <a href="some_url">rain</a> '
|
|
|
|
|
'<br /> in <span>Spain</span></b></div>')
|
|
|
|
|
expected = [
|
|
|
|
|
('starttag', 'div', [('style', '')]),
|
|
|
|
|
('starttag', 'b', []),
|
|
|
|
|
('data', 'The '),
|
|
|
|
|
('starttag', 'a', [('href', 'some_url')]),
|
|
|
|
|
('data', 'rain'),
|
|
|
|
|
('endtag', 'a'),
|
|
|
|
|
('data', ' '),
|
|
|
|
|
('startendtag', 'br', []),
|
|
|
|
|
('data', ' in '),
|
|
|
|
|
('starttag', 'span', []),
|
|
|
|
|
('data', 'Spain'),
|
|
|
|
|
('endtag', 'span'),
|
|
|
|
|
('endtag', 'b'),
|
|
|
|
|
('endtag', 'div')
|
|
|
|
|
]
|
2011-11-01 13:57:15 -03:00
|
|
|
self._run_check(html, expected)
|
2011-10-28 07:21:09 -03:00
|
|
|
|
|
|
|
|
html = '<div style="", foo = "bar" ><b>The <a href="some_url">rain</a>'
|
|
|
|
|
expected = [
|
2011-11-14 12:53:33 -04:00
|
|
|
('starttag', 'div', [('style', ''), (',', None), ('foo', 'bar')]),
|
2011-10-28 07:21:09 -03:00
|
|
|
('starttag', 'b', []),
|
|
|
|
|
('data', 'The '),
|
|
|
|
|
('starttag', 'a', [('href', 'some_url')]),
|
|
|
|
|
('data', 'rain'),
|
|
|
|
|
('endtag', 'a'),
|
|
|
|
|
]
|
2011-11-01 13:57:15 -03:00
|
|
|
self._run_check(html, expected)
|
2011-10-28 07:21:09 -03:00
|
|
|
|
2013-05-01 10:18:25 -03:00
|
|
|
def test_EOF_in_charref(self):
|
|
|
|
|
# see #17802
|
|
|
|
|
# This test checks that the UnboundLocalError reported in the issue
|
|
|
|
|
# is not raised, however I'm not sure the returned values are correct.
|
|
|
|
|
# Maybe HTMLParser should use self.unescape for these
|
|
|
|
|
data = [
|
|
|
|
|
('a&', [('data', 'a&')]),
|
|
|
|
|
('a&b', [('data', 'ab')]),
|
|
|
|
|
('a&b ', [('data', 'a'), ('entityref', 'b'), ('data', ' ')]),
|
|
|
|
|
('a&b;', [('data', 'a'), ('entityref', 'b')]),
|
|
|
|
|
]
|
|
|
|
|
for html, expected in data:
|
|
|
|
|
self._run_check(html, expected)
|
|
|
|
|
|
2013-11-21 23:49:29 -04:00
|
|
|
def test_unescape_method(self):
|
|
|
|
|
from html import unescape
|
|
|
|
|
p = self.get_collector()
|
|
|
|
|
with self.assertWarns(DeprecationWarning):
|
|
|
|
|
s = '""""""&#bad;'
|
|
|
|
|
self.assertEqual(p.unescape(s), unescape(s))
|
|
|
|
|
|
2012-02-10 04:45:44 -04:00
|
|
|
def test_broken_comments(self):
|
|
|
|
|
html = ('<! not really a comment >'
|
|
|
|
|
'<! not a comment either -->'
|
|
|
|
|
'<! -- close enough -->'
|
2012-02-13 09:50:37 -04:00
|
|
|
'<!><!<-- this was an empty comment>'
|
2012-02-10 04:45:44 -04:00
|
|
|
'<!!! another bogus comment !!!>')
|
|
|
|
|
expected = [
|
|
|
|
|
('comment', ' not really a comment '),
|
|
|
|
|
('comment', ' not a comment either --'),
|
|
|
|
|
('comment', ' -- close enough --'),
|
2012-02-13 09:50:37 -04:00
|
|
|
('comment', ''),
|
|
|
|
|
('comment', '<-- this was an empty comment'),
|
2012-02-10 04:45:44 -04:00
|
|
|
('comment', '!! another bogus comment !!!'),
|
|
|
|
|
]
|
|
|
|
|
self._run_check(html, expected)
|
|
|
|
|
|
2011-12-19 01:29:03 -04:00
|
|
|
def test_broken_condcoms(self):
|
|
|
|
|
# these condcoms are missing the '--' after '<!' and before the '>'
|
|
|
|
|
html = ('<![if !(IE)]>broken condcom<![endif]>'
|
|
|
|
|
'<![if ! IE]><link href="favicon.tiff"/><![endif]>'
|
|
|
|
|
'<![if !IE 6]><img src="firefox.png" /><![endif]>'
|
|
|
|
|
'<![if !ie 6]><b>foo</b><![endif]>'
|
|
|
|
|
'<![if (!IE)|(lt IE 9)]><img src="mammoth.bmp" /><![endif]>')
|
|
|
|
|
# According to the HTML5 specs sections "8.2.4.44 Bogus comment state"
|
|
|
|
|
# and "8.2.4.45 Markup declaration open state", comment tokens should
|
|
|
|
|
# be emitted instead of 'unknown decl', but calling unknown_decl
|
|
|
|
|
# provides more flexibility.
|
|
|
|
|
# See also Lib/_markupbase.py:parse_declaration
|
|
|
|
|
expected = [
|
|
|
|
|
('unknown decl', 'if !(IE)'),
|
|
|
|
|
('data', 'broken condcom'),
|
|
|
|
|
('unknown decl', 'endif'),
|
|
|
|
|
('unknown decl', 'if ! IE'),
|
|
|
|
|
('startendtag', 'link', [('href', 'favicon.tiff')]),
|
|
|
|
|
('unknown decl', 'endif'),
|
|
|
|
|
('unknown decl', 'if !IE 6'),
|
|
|
|
|
('startendtag', 'img', [('src', 'firefox.png')]),
|
|
|
|
|
('unknown decl', 'endif'),
|
|
|
|
|
('unknown decl', 'if !ie 6'),
|
|
|
|
|
('starttag', 'b', []),
|
|
|
|
|
('data', 'foo'),
|
|
|
|
|
('endtag', 'b'),
|
|
|
|
|
('unknown decl', 'endif'),
|
|
|
|
|
('unknown decl', 'if (!IE)|(lt IE 9)'),
|
|
|
|
|
('startendtag', 'img', [('src', 'mammoth.bmp')]),
|
|
|
|
|
('unknown decl', 'endif')
|
|
|
|
|
]
|
|
|
|
|
self._run_check(html, expected)
|
|
|
|
|
|
2015-09-06 15:38:06 -03:00
|
|
|
def test_convert_charrefs_dropped_text(self):
|
|
|
|
|
# #23144: make sure that all the events are triggered when
|
|
|
|
|
# convert_charrefs is True, even if we don't call .close()
|
|
|
|
|
parser = EventCollector(convert_charrefs=True)
|
|
|
|
|
# before the fix, bar & baz was missing
|
|
|
|
|
parser.feed("foo <a>link</a> bar & baz")
|
|
|
|
|
self.assertEqual(
|
|
|
|
|
parser.get_events(),
|
|
|
|
|
[('data', 'foo '), ('starttag', 'a', []), ('data', 'link'),
|
|
|
|
|
('endtag', 'a'), ('data', ' bar & baz')]
|
|
|
|
|
)
|
|
|
|
|
|
2011-11-01 13:57:15 -03:00
|
|
|
|
2011-11-14 12:13:22 -04:00
|
|
|
class AttributesStrictTestCase(TestCaseBase):
|
|
|
|
|
|
|
|
|
|
def get_collector(self):
|
2012-06-23 10:27:51 -03:00
|
|
|
with support.check_warnings(("", DeprecationWarning), quite=False):
|
2013-11-23 13:52:05 -04:00
|
|
|
return EventCollector(strict=True, convert_charrefs=False)
|
2011-11-14 12:13:22 -04:00
|
|
|
|
|
|
|
|
def test_attr_syntax(self):
|
|
|
|
|
output = [
|
|
|
|
|
("starttag", "a", [("b", "v"), ("c", "v"), ("d", "v"), ("e", None)])
|
|
|
|
|
]
|
|
|
|
|
self._run_check("""<a b='v' c="v" d=v e>""", output)
|
|
|
|
|
self._run_check("""<a b = 'v' c = "v" d = v e>""", output)
|
|
|
|
|
self._run_check("""<a\nb\n=\n'v'\nc\n=\n"v"\nd\n=\nv\ne>""", output)
|
|
|
|
|
self._run_check("""<a\tb\t=\t'v'\tc\t=\t"v"\td\t=\tv\te>""", output)
|
|
|
|
|
|
|
|
|
|
def test_attr_values(self):
|
|
|
|
|
self._run_check("""<a b='xxx\n\txxx' c="yyy\t\nyyy" d='\txyz\n'>""",
|
|
|
|
|
[("starttag", "a", [("b", "xxx\n\txxx"),
|
|
|
|
|
("c", "yyy\t\nyyy"),
|
|
|
|
|
("d", "\txyz\n")])])
|
|
|
|
|
self._run_check("""<a b='' c="">""",
|
|
|
|
|
[("starttag", "a", [("b", ""), ("c", "")])])
|
|
|
|
|
# Regression test for SF patch #669683.
|
|
|
|
|
self._run_check("<e a=rgb(1,2,3)>",
|
|
|
|
|
[("starttag", "e", [("a", "rgb(1,2,3)")])])
|
|
|
|
|
# Regression test for SF bug #921657.
|
|
|
|
|
self._run_check(
|
|
|
|
|
"<a href=mailto:xyz@example.com>",
|
|
|
|
|
[("starttag", "a", [("href", "mailto:xyz@example.com")])])
|
|
|
|
|
|
|
|
|
|
def test_attr_nonascii(self):
|
|
|
|
|
# see issue 7311
|
|
|
|
|
self._run_check(
|
|
|
|
|
"<img src=/foo/bar.png alt=\u4e2d\u6587>",
|
|
|
|
|
[("starttag", "img", [("src", "/foo/bar.png"),
|
|
|
|
|
("alt", "\u4e2d\u6587")])])
|
|
|
|
|
self._run_check(
|
|
|
|
|
"<a title='\u30c6\u30b9\u30c8' href='\u30c6\u30b9\u30c8.html'>",
|
|
|
|
|
[("starttag", "a", [("title", "\u30c6\u30b9\u30c8"),
|
|
|
|
|
("href", "\u30c6\u30b9\u30c8.html")])])
|
|
|
|
|
self._run_check(
|
|
|
|
|
'<a title="\u30c6\u30b9\u30c8" href="\u30c6\u30b9\u30c8.html">',
|
|
|
|
|
[("starttag", "a", [("title", "\u30c6\u30b9\u30c8"),
|
|
|
|
|
("href", "\u30c6\u30b9\u30c8.html")])])
|
|
|
|
|
|
|
|
|
|
def test_attr_entity_replacement(self):
|
|
|
|
|
self._run_check(
|
|
|
|
|
"<a b='&><"''>",
|
|
|
|
|
[("starttag", "a", [("b", "&><\"'")])])
|
|
|
|
|
|
|
|
|
|
def test_attr_funky_names(self):
|
|
|
|
|
self._run_check(
|
|
|
|
|
"<a a.b='v' c:d=v e-f=v>",
|
|
|
|
|
[("starttag", "a", [("a.b", "v"), ("c:d", "v"), ("e-f", "v")])])
|
|
|
|
|
|
|
|
|
|
def test_entityrefs_in_attributes(self):
|
|
|
|
|
self._run_check(
|
|
|
|
|
"<html foo='€&aa&unsupported;'>",
|
|
|
|
|
[("starttag", "html", [("foo", "\u20AC&aa&unsupported;")])])
|
|
|
|
|
|
|
|
|
|
|
2011-11-14 12:53:33 -04:00
|
|
|
|
|
|
|
|
class AttributesTolerantTestCase(AttributesStrictTestCase):
|
|
|
|
|
|
|
|
|
|
def get_collector(self):
|
2013-11-23 13:52:05 -04:00
|
|
|
return EventCollector(convert_charrefs=False)
|
2011-11-14 12:53:33 -04:00
|
|
|
|
|
|
|
|
def test_attr_funky_names2(self):
|
|
|
|
|
self._run_check(
|
|
|
|
|
"<a $><b $=%><c \=/>",
|
|
|
|
|
[("starttag", "a", [("$", None)]),
|
|
|
|
|
("starttag", "b", [("$", "%")]),
|
|
|
|
|
("starttag", "c", [("\\", "/")])])
|
|
|
|
|
|
|
|
|
|
def test_entities_in_attribute_value(self):
|
|
|
|
|
# see #1200313
|
|
|
|
|
for entity in ['&', '&', '&', '&']:
|
|
|
|
|
self._run_check('<a href="%s">' % entity,
|
|
|
|
|
[("starttag", "a", [("href", "&")])])
|
|
|
|
|
self._run_check("<a href='%s'>" % entity,
|
|
|
|
|
[("starttag", "a", [("href", "&")])])
|
|
|
|
|
self._run_check("<a href=%s>" % entity,
|
|
|
|
|
[("starttag", "a", [("href", "&")])])
|
|
|
|
|
|
|
|
|
|
def test_malformed_attributes(self):
|
|
|
|
|
# see #13357
|
|
|
|
|
html = (
|
|
|
|
|
"<a href=test'style='color:red;bad1'>test - bad1</a>"
|
|
|
|
|
"<a href=test'+style='color:red;ba2'>test - bad2</a>"
|
|
|
|
|
"<a href=test' style='color:red;bad3'>test - bad3</a>"
|
|
|
|
|
"<a href = test' style='color:red;bad4' >test - bad4</a>"
|
|
|
|
|
)
|
|
|
|
|
expected = [
|
|
|
|
|
('starttag', 'a', [('href', "test'style='color:red;bad1'")]),
|
|
|
|
|
('data', 'test - bad1'), ('endtag', 'a'),
|
|
|
|
|
('starttag', 'a', [('href', "test'+style='color:red;ba2'")]),
|
|
|
|
|
('data', 'test - bad2'), ('endtag', 'a'),
|
|
|
|
|
('starttag', 'a', [('href', "test'\xa0style='color:red;bad3'")]),
|
|
|
|
|
('data', 'test - bad3'), ('endtag', 'a'),
|
|
|
|
|
('starttag', 'a', [('href', "test'\xa0style='color:red;bad4'")]),
|
|
|
|
|
('data', 'test - bad4'), ('endtag', 'a')
|
|
|
|
|
]
|
|
|
|
|
self._run_check(html, expected)
|
|
|
|
|
|
|
|
|
|
def test_malformed_adjacent_attributes(self):
|
|
|
|
|
# see #12629
|
|
|
|
|
self._run_check('<x><y z=""o"" /></x>',
|
|
|
|
|
[('starttag', 'x', []),
|
|
|
|
|
('startendtag', 'y', [('z', ''), ('o""', None)]),
|
|
|
|
|
('endtag', 'x')])
|
|
|
|
|
self._run_check('<x><y z="""" /></x>',
|
|
|
|
|
[('starttag', 'x', []),
|
|
|
|
|
('startendtag', 'y', [('z', ''), ('""', None)]),
|
|
|
|
|
('endtag', 'x')])
|
|
|
|
|
|
|
|
|
|
# see #755670 for the following 3 tests
|
|
|
|
|
def test_adjacent_attributes(self):
|
|
|
|
|
self._run_check('<a width="100%"cellspacing=0>',
|
|
|
|
|
[("starttag", "a",
|
|
|
|
|
[("width", "100%"), ("cellspacing","0")])])
|
|
|
|
|
|
|
|
|
|
self._run_check('<a id="foo"class="bar">',
|
|
|
|
|
[("starttag", "a",
|
|
|
|
|
[("id", "foo"), ("class","bar")])])
|
|
|
|
|
|
|
|
|
|
def test_missing_attribute_value(self):
|
|
|
|
|
self._run_check('<a v=>',
|
|
|
|
|
[("starttag", "a", [("v", "")])])
|
|
|
|
|
|
|
|
|
|
def test_javascript_attribute_value(self):
|
|
|
|
|
self._run_check("<a href=javascript:popup('/popup/help.html')>",
|
|
|
|
|
[("starttag", "a",
|
|
|
|
|
[("href", "javascript:popup('/popup/help.html')")])])
|
|
|
|
|
|
|
|
|
|
def test_end_tag_in_attribute_value(self):
|
|
|
|
|
# see #1745761
|
|
|
|
|
self._run_check("<a href='http://www.example.org/\">;'>spam</a>",
|
|
|
|
|
[("starttag", "a",
|
|
|
|
|
[("href", "http://www.example.org/\">;")]),
|
|
|
|
|
("data", "spam"), ("endtag", "a")])
|
|
|
|
|
|
|
|
|
|
|
2001-09-24 17:19:08 -03:00
|
|
|
if __name__ == "__main__":
|
2013-11-02 12:49:08 -03:00
|
|
|
unittest.main()
|
