Learn more »
Push, build, and install
RubyGems
npm packages
Python packages
Maven artifacts
PHP packages
Go Modules
Bower components
Debian packages
RPM packages
NuGet packages
agriconnect / libpython3.8-testsuite deb
Repository URL to install this package:
Version:
3.8.5-1+stretch1
Version:
3.8.5-1+stretch1
"""Tests for HTMLParser.py."""
import html.parser
import pprint
import unittest
class EventCollector(html.parser.HTMLParser):
def __init__(self, *args, **kw):
self.events = []
self.append = self.events.append
html.parser.HTMLParser.__init__(self, *args, **kw)
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))
def unknown_decl(self, decl):
self.append(("unknown decl", decl))
class EventCollectorExtra(EventCollector):
def handle_starttag(self, tag, attrs):
EventCollector.handle_starttag(self, tag, attrs)
self.append(("starttag_text", self.get_starttag_text()))
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')
class TestCaseBase(unittest.TestCase):
def get_collector(self):
return EventCollector(convert_charrefs=False)
def _run_check(self, source, expected_events, collector=None):
if collector is None:
collector = self.get_collector()
parser = collector
for s in source:
parser.feed(s)
parser.close()
events = parser.get_events()
if events != expected_events:
self.fail("received events did not match expected events" +
"\nSource:\n" + repr(source) +
"\nExpected:\n" + pprint.pformat(expected_events) +
"\nReceived:\n" + pprint.pformat(events))
def _run_check_extra(self, source, events):
self._run_check(source, events,
EventCollectorExtra(convert_charrefs=False))
class HTMLParserTestCase(TestCaseBase):
def test_processing_instruction_only(self):
self._run_check("<?processing instruction>", [
("pi", "processing instruction"),
])
self._run_check("<?processing instruction ?>", [
("pi", "processing instruction ?"),
])
def test_simple_html(self):
self._run_check("""
<!DOCTYPE html PUBLIC 'foo'>
<HTML>&entity; 
<!--comment1a
-></foo><bar><<?pi?></foo<bar
comment1b-->
<Img sRc='Bar' isMAP>sample
text
“
<!--comment2a-- --comment2b-->
</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"),
("charref", "x201C"),
("data", "\n"),
("comment", "comment2a-- --comment2b"),
("data", "\n"),
("endtag", "html"),
("data", "\n"),
])
def test_malformatted_charref(self):
self._run_check("<p>&#bad;</p>", [
("starttag", "p", []),
("data", "&#bad;"),
("endtag", "p"),
])
# add the [] as a workaround to avoid buffering (see #20288)
self._run_check(["<div>&#bad;</div>"], [
("starttag", "div", []),
("data", "&#bad;"),
("endtag", "div"),
])
def test_unclosed_entityref(self):
self._run_check("&entityref foo", [
("entityref", "entityref"),
("data", " foo"),
])
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.
self._run_check("<a><b></a></b>", [
("starttag", "a", []),
("starttag", "b", []),
("endtag", "a"),
("endtag", "b"),
])
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"),
])
def test_starttag_end_boundary(self):
self._run_check("""<a b='<'>""", [("starttag", "a", [("b", "<")])])
self._run_check("""<a b='>'>""", [("starttag", "a", [("b", ">")])])
def test_buffer_artefacts(self):
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)
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)
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)])
def test_startendtag(self):
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"),
])
def test_get_starttag_text(self):
s = """<foo:bar \n one="1"\ttwo=2 >"""
self._run_check_extra(s, [
("starttag", "foo:bar", [("one", "1"), ("two", "2")]),
("starttag_text", s)])
def test_cdata_content(self):
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)])
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)],
collector=Collector(convert_charrefs=False))
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)
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)
def test_convert_charrefs(self):
# default value for convert_charrefs is now True