diff options
Diffstat (limited to 'Lib/test/test_htmlparser.py')
| -rw-r--r-- | Lib/test/test_htmlparser.py | 76 |
1 files changed, 7 insertions, 69 deletions
diff --git a/Lib/test/test_htmlparser.py b/Lib/test/test_htmlparser.py index 144f820..11420b2c 100644 --- a/Lib/test/test_htmlparser.py +++ b/Lib/test/test_htmlparser.py @@ -82,7 +82,7 @@ class EventCollectorCharrefs(EventCollector): class TestCaseBase(unittest.TestCase): def get_collector(self): - raise NotImplementedError + return EventCollector(convert_charrefs=False) def _run_check(self, source, expected_events, collector=None): if collector is None: @@ -102,21 +102,8 @@ class TestCaseBase(unittest.TestCase): self._run_check(source, events, EventCollectorExtra(convert_charrefs=False)) - def _parse_error(self, source): - def parse(source=source): - parser = self.get_collector() - parser.feed(source) - parser.close() - with self.assertRaises(html.parser.HTMLParseError): - with self.assertWarns(DeprecationWarning): - parse() - -class HTMLParserStrictTestCase(TestCaseBase): - - def get_collector(self): - with support.check_warnings(("", DeprecationWarning), quite=False): - return EventCollector(strict=True, convert_charrefs=False) +class HTMLParserTestCase(TestCaseBase): def test_processing_instruction_only(self): self._run_check("<?processing instruction>", [ @@ -198,9 +185,6 @@ text ("data", "this < text > contains < bare>pointy< brackets"), ]) - def test_illegal_declarations(self): - self._parse_error('<!spacer type="block" height="25">') - def test_starttag_end_boundary(self): self._run_check("""<a b='<'>""", [("starttag", "a", [("b", "<")])]) self._run_check("""<a b='>'>""", [("starttag", "a", [("b", ">")])]) @@ -235,25 +219,6 @@ text self._run_check(["<!--abc--", ">"], output) self._run_check(["<!--abc-->", ""], output) - def test_starttag_junk_chars(self): - self._parse_error("</>") - self._parse_error("</$>") - self._parse_error("</") - self._parse_error("</a") - self._parse_error("<a<a>") - self._parse_error("</a<a>") - self._parse_error("<!") - self._parse_error("<a") - self._parse_error("<a foo='bar'") - self._parse_error("<a foo='bar") - self._parse_error("<a foo='>'") - self._parse_error("<a foo='>") - self._parse_error("<a$>") - self._parse_error("<a$b>") - self._parse_error("<a$b/>") - self._parse_error("<a$b >") - self._parse_error("<a$b />") - def test_valid_doctypes(self): # from http://www.w3.org/QA/2002/04/valid-dtd-list.html dtds = ['HTML', # HTML5 doctype @@ -278,9 +243,6 @@ text self._run_check("<!DOCTYPE %s>" % dtd, [('decl', 'DOCTYPE ' + dtd)]) - def test_declaration_junk_chars(self): - self._parse_error("<!DOCTYPE foo $ >") - def test_startendtag(self): self._run_check("<p/>", [ ("startendtag", "p", []), @@ -381,7 +343,8 @@ text self._run_check(html, expected) def test_convert_charrefs(self): - collector = lambda: EventCollectorCharrefs(convert_charrefs=True) + # default value for convert_charrefs is now True + collector = lambda: EventCollectorCharrefs() self.assertTrue(collector().convert_charrefs) charrefs = ['"', '"', '"', '"', '"', '"'] # check charrefs in the middle of the text/attributes @@ -418,23 +381,8 @@ text self._run_check('no charrefs here', [('data', 'no charrefs here')], collector=collector()) - -class HTMLParserTolerantTestCase(HTMLParserStrictTestCase): - - def get_collector(self): - return EventCollector(convert_charrefs=False) - - def test_deprecation_warnings(self): - with self.assertWarns(DeprecationWarning): - EventCollector() # convert_charrefs not passed explicitly - 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') - + # the remaining tests were for the "tolerant" parser (which is now + # the default), and check various kind of broken markup def test_tolerant_parsing(self): self._run_check('<html <html>te>>xt&a<<bc</a></html>\n' '<img src="URL><//img></html</html>', [ @@ -695,11 +643,7 @@ class HTMLParserTolerantTestCase(HTMLParserStrictTestCase): ) -class AttributesStrictTestCase(TestCaseBase): - - def get_collector(self): - with support.check_warnings(("", DeprecationWarning), quite=False): - return EventCollector(strict=True, convert_charrefs=False) +class AttributesTestCase(TestCaseBase): def test_attr_syntax(self): output = [ @@ -756,12 +700,6 @@ class AttributesStrictTestCase(TestCaseBase): [("starttag", "html", [("foo", "\u20AC&aa&unsupported;")])]) - -class AttributesTolerantTestCase(AttributesStrictTestCase): - - def get_collector(self): - return EventCollector(convert_charrefs=False) - def test_attr_funky_names2(self): self._run_check( "<a $><b $=%><c \=/>", |