diff options
Diffstat (limited to 'Lib/test/test_htmlparser.py')
| -rw-r--r-- | Lib/test/test_htmlparser.py | 346 |
1 files changed, 266 insertions, 80 deletions
diff --git a/Lib/test/test_htmlparser.py b/Lib/test/test_htmlparser.py index b42a611c62c..d0d2c54217c 100644 --- a/Lib/test/test_htmlparser.py +++ b/Lib/test/test_htmlparser.py @@ -5,6 +5,7 @@ import pprint import unittest from unittest.mock import patch +from test import support class EventCollector(html.parser.HTMLParser): @@ -80,6 +81,13 @@ class EventCollectorCharrefs(EventCollector): self.fail('This should never be called with convert_charrefs=True') +# The normal event collector normalizes the events in get_events, +# so we override it to return the original list of events. +class EventCollectorNoNormalize(EventCollector): + def get_events(self): + return self.events + + class TestCaseBase(unittest.TestCase): def get_collector(self): @@ -264,8 +272,7 @@ text ("starttag", "foo:bar", [("one", "1"), ("two", "2")]), ("starttag_text", s)]) - def test_cdata_content(self): - contents = [ + @support.subTests('content', [ '<!-- not a comment --> ¬-an-entity-ref;', "<not a='start tag'>", '<a href="" /> <p> <span></span>', @@ -278,44 +285,83 @@ text '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): + 'foo = "</ script>"', + 'foo = "</scripture>"', + 'foo = "</script\v>"', + 'foo = "</script\xa0>"', + 'foo = "</ſcript>"', + 'foo = "</scrıpt>"', + ]) + def test_script_content(self, content): + s = f'<script>{content}</script>' + self._run_check(s, [("starttag", "script", []), + ("data", content), + ("endtag", "script")]) + + @support.subTests('content', [ + 'a::before { content: "<!-- not a comment -->"; }', + 'a::before { content: "¬-an-entity-ref;"; }', + 'a::before { content: "<not a=\'start tag\'>"; }', + 'a::before { content: "\u2603"; }', + 'a::before { content: "< /style>"; }', + 'a::before { content: "</ style>"; }', + 'a::before { content: "</styled>"; }', + 'a::before { content: "</style\v>"; }', + 'a::before { content: "</style\xa0>"; }', + 'a::before { content: "</ſtyle>"; }', + ]) + def test_style_content(self, content): + s = f'<style>{content}</style>' + self._run_check(s, [("starttag", "style", []), + ("data", content), + ("endtag", "style")]) + + @support.subTests('endtag', ['script', 'SCRIPT', 'script ', 'script\n', + 'script/', 'script foo=bar', 'script foo=">"']) + def test_script_closing_tag(self, endtag): # 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)) + s = f'<ScrIPt>{content}</{endtag}>' + self._run_check(s, [("starttag", "script", []), + ("data", content), + ("endtag", "script")], + collector=EventCollectorNoNormalize(convert_charrefs=False)) + + @support.subTests('endtag', ['style', 'STYLE', 'style ', 'style\n', + 'style/', 'style foo=bar', 'style foo=">"']) + def test_style_closing_tag(self, endtag): + content = """ + b::before { content: "<!-- not a comment -->"; } + p::before { content: "¬-an-entity-ref;"; } + a::before { content: "<i>"; } + a::after { content: "</i>"; } + """ + s = f'<StyLE>{content}</{endtag}>' + self._run_check(s, [("starttag", "style", []), + ("data", content), + ("endtag", "style")], + collector=EventCollectorNoNormalize(convert_charrefs=False)) + + @support.subTests('tail,end', [ + ('', False), + ('<', False), + ('</', False), + ('</s', False), + ('</script', False), + ('</script ', True), + ('</script foo=bar', True), + ('</script foo=">', True), + ]) + def test_eof_in_script(self, tail, end): + content = "a = 123" + s = f'<ScrIPt>{content}{tail}' + self._run_check(s, [("starttag", "script", []), + ("data", content if end else content + tail)], + collector=EventCollectorNoNormalize(convert_charrefs=False)) def test_comments(self): html = ("<!-- I'm a valid comment -->" @@ -348,18 +394,16 @@ text collector = lambda: EventCollectorCharrefs() 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')] + # check charrefs in the middle of the text + expected = [('starttag', 'a', []), ('data', 'a"z'), ('endtag', 'a')] for charref in charrefs: - self._run_check('<a href="foo{0}zar">a{0}z</a>'.format(charref), + self._run_check('<a>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"')]), + # check charrefs at the beginning/end of the text + expected = [('data', '"'), ('starttag', 'a', []), ('data', '"'), ('endtag', 'a'), ('data', '"')] for charref in charrefs: - self._run_check('{0}<a x="{0}" y="{0}X" z="X{0}">' + self._run_check('{0}<a>' '{0}</a>{0}'.format(charref), expected, collector=collector()) # check charrefs in <script>/<style> elements @@ -382,6 +426,35 @@ text self._run_check('no charrefs here', [('data', 'no charrefs here')], collector=collector()) + def test_convert_charrefs_in_attribute_values(self): + # default value for convert_charrefs is now True + collector = lambda: EventCollectorCharrefs() + self.assertTrue(collector().convert_charrefs) + + # always unescape terminated entity refs, numeric and hex char refs: + # - regardless whether they are at start, middle, end of attribute + # - or followed by alphanumeric, non-alphanumeric, or equals char + charrefs = ['¢', '¢', '¢', '¢', '¢'] + expected = [('starttag', 'a', + [('x', '¢'), ('x', 'z¢'), ('x', '¢z'), + ('x', 'z¢z'), ('x', '¢ z'), ('x', '¢=z')]), + ('endtag', 'a')] + for charref in charrefs: + self._run_check('<a x="{0}" x="z{0}" x="{0}z" ' + ' x="z{0}z" x="{0} z" x="{0}=z"></a>' + .format(charref), expected, collector=collector()) + + # only unescape unterminated entity matches if they are not followed by + # an alphanumeric or an equals sign + charref = '¢' + expected = [('starttag', 'a', + [('x', '¢'), ('x', 'z¢'), ('x', '¢z'), + ('x', 'z¢z'), ('x', '¢ z'), ('x', '¢=z')]), + ('endtag', 'a')] + self._run_check('<a x="{0}" x="z{0}" x="{0}z" ' + ' x="z{0}z" x="{0} z" x="{0}=z"></a>' + .format(charref), expected, collector=collector()) + # 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): @@ -393,28 +466,34 @@ text ('data', '<'), ('starttag', 'bc<', [('a', None)]), ('endtag', 'html'), - ('data', '\n<img src="URL>'), - ('comment', '/img'), - ('endtag', 'html<')]) + ('data', '\n')]) def test_starttag_junk_chars(self): + self._run_check("<", [('data', '<')]) + self._run_check("<>", [('data', '<>')]) + self._run_check("< >", [('data', '< >')]) + self._run_check("< ", [('data', '< ')]) self._run_check("</>", []) + self._run_check("<$>", [('data', '<$>')]) self._run_check("</$>", [('comment', '$')]) self._run_check("</", [('data', '</')]) - self._run_check("</a", [('data', '</a')]) + self._run_check("</a", []) + self._run_check("</ a>", [('comment', ' a')]) + self._run_check("</ a", [('comment', ' a')]) self._run_check("<a<a>", [('starttag', 'a<a', [])]) 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='>")]) + self._run_check("<!", [('comment', '')]) + self._run_check("<a", []) + self._run_check("<a foo='bar'", []) + self._run_check("<a foo='bar", []) + self._run_check("<a foo='>'", []) + self._run_check("<a foo='>", []) 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', [])]) + self._run_check("</a$b>", [('endtag', 'a$b')]) def test_slashes_in_starttag(self): self._run_check('<a foo="var"/>', [('startendtag', 'a', [('foo', 'var')])]) @@ -447,6 +526,10 @@ text ] self._run_check(html, expected) + def test_slashes_in_endtag(self): + self._run_check('</a/>', [('endtag', 'a')]) + self._run_check('</a foo="var"/>', [('endtag', 'a')]) + def test_declaration_junk_chars(self): self._run_check("<!DOCTYPE foo $ >", [('decl', 'DOCTYPE foo $ ')]) @@ -481,15 +564,11 @@ text 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')] + ('data', ' confuses the parser')] self._run_check(html, expected) def test_correct_detection_of_start_tags(self): @@ -516,7 +595,7 @@ text html = '<div style="", foo = "bar" ><b>The <a href="some_url">rain</a>' expected = [ - ('starttag', 'div', [('style', ''), (',', None), ('foo', 'bar')]), + ('starttag', 'div', [('style', ''), (',', None), ('foo', None), ('=', None), ('"bar"', None)]), ('starttag', 'b', []), ('data', 'The '), ('starttag', 'a', [('href', 'some_url')]), @@ -539,52 +618,129 @@ text for html, expected in data: self._run_check(html, expected) - def test_broken_comments(self): - html = ('<! not really a comment >' + def test_eof_in_comments(self): + data = [ + ('<!--', [('comment', '')]), + ('<!---', [('comment', '')]), + ('<!----', [('comment', '')]), + ('<!-----', [('comment', '-')]), + ('<!------', [('comment', '--')]), + ('<!----!', [('comment', '')]), + ('<!---!', [('comment', '-!')]), + ('<!---!>', [('comment', '-!>')]), + ('<!--foo', [('comment', 'foo')]), + ('<!--foo-', [('comment', 'foo')]), + ('<!--foo--', [('comment', 'foo')]), + ('<!--foo--!', [('comment', 'foo')]), + ('<!--<!--', [('comment', '<!')]), + ('<!--<!--!', [('comment', '<!')]), + ] + for html, expected in data: + self._run_check(html, expected) + + def test_eof_in_declarations(self): + data = [ + ('<!', [('comment', '')]), + ('<!-', [('comment', '-')]), + ('<![', [('comment', '[')]), + ('<![CDATA[', [('unknown decl', 'CDATA[')]), + ('<![CDATA[x', [('unknown decl', 'CDATA[x')]), + ('<![CDATA[x]', [('unknown decl', 'CDATA[x]')]), + ('<![CDATA[x]]', [('unknown decl', 'CDATA[x]]')]), + ('<!DOCTYPE', [('decl', 'DOCTYPE')]), + ('<!DOCTYPE ', [('decl', 'DOCTYPE ')]), + ('<!DOCTYPE html', [('decl', 'DOCTYPE html')]), + ('<!DOCTYPE html ', [('decl', 'DOCTYPE html ')]), + ('<!DOCTYPE html PUBLIC', [('decl', 'DOCTYPE html PUBLIC')]), + ('<!DOCTYPE html PUBLIC "foo', [('decl', 'DOCTYPE html PUBLIC "foo')]), + ('<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01//EN" "foo', + [('decl', 'DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01//EN" "foo')]), + ] + for html, expected in data: + self._run_check(html, expected) + + def test_bogus_comments(self): + html = ('<!ELEMENT br EMPTY>' + '<! not really a comment >' '<! not a comment either -->' '<! -- close enough -->' '<!><!<-- this was an empty comment>' - '<!!! another bogus comment !!!>') + '<!!! another bogus comment !!!>' + # see #32876 + '<![with square brackets]!>' + '<![\nmultiline\nbogusness\n]!>' + '<![more brackets]-[and a hyphen]!>' + '<![cdata[should be uppercase]]>' + '<![CDATA [whitespaces are not ignored]]>' + '<![CDATA]]>' # required '[' after CDATA + ) expected = [ + ('comment', 'ELEMENT br EMPTY'), ('comment', ' not really a comment '), ('comment', ' not a comment either --'), ('comment', ' -- close enough --'), ('comment', ''), ('comment', '<-- this was an empty comment'), ('comment', '!! another bogus comment !!!'), + ('comment', '[with square brackets]!'), + ('comment', '[\nmultiline\nbogusness\n]!'), + ('comment', '[more brackets]-[and a hyphen]!'), + ('comment', '[cdata[should be uppercase]]'), + ('comment', '[CDATA [whitespaces are not ignored]]'), + ('comment', '[CDATA]]'), ] self._run_check(html, expected) def test_broken_condcoms(self): # these condcoms are missing the '--' after '<!' and before the '>' + # and they are considered bogus comments according to + # "8.2.4.42. Markup declaration open state" 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)'), + ('comment', '[if !(IE)]'), ('data', 'broken condcom'), - ('unknown decl', 'endif'), - ('unknown decl', 'if ! IE'), + ('comment', '[endif]'), + ('comment', '[if ! IE]'), ('startendtag', 'link', [('href', 'favicon.tiff')]), - ('unknown decl', 'endif'), - ('unknown decl', 'if !IE 6'), + ('comment', '[endif]'), + ('comment', '[if !IE 6]'), ('startendtag', 'img', [('src', 'firefox.png')]), - ('unknown decl', 'endif'), - ('unknown decl', 'if !ie 6'), + ('comment', '[endif]'), + ('comment', '[if !ie 6]'), ('starttag', 'b', []), ('data', 'foo'), ('endtag', 'b'), - ('unknown decl', 'endif'), - ('unknown decl', 'if (!IE)|(lt IE 9)'), + ('comment', '[endif]'), + ('comment', '[if (!IE)|(lt IE 9)]'), ('startendtag', 'img', [('src', 'mammoth.bmp')]), - ('unknown decl', 'endif') + ('comment', '[endif]') + ] + self._run_check(html, expected) + + def test_cdata_declarations(self): + # More tests should be added. See also "8.2.4.42. Markup + # declaration open state", "8.2.4.69. CDATA section state", + # and issue 32876 + html = ('<![CDATA[just some plain text]]>') + expected = [('unknown decl', 'CDATA[just some plain text')] + self._run_check(html, expected) + + def test_cdata_declarations_multiline(self): + html = ('<code><![CDATA[' + ' if (a < b && a > b) {' + ' printf("[<marquee>How?</marquee>]");' + ' }' + ']]></code>') + expected = [ + ('starttag', 'code', []), + ('unknown decl', + 'CDATA[ if (a < b && a > b) { ' + 'printf("[<marquee>How?</marquee>]"); }'), + ('endtag', 'code') ] self._run_check(html, expected) @@ -600,6 +756,26 @@ text ('endtag', 'a'), ('data', ' bar & baz')] ) + @support.requires_resource('cpu') + def test_eof_no_quadratic_complexity(self): + # Each of these examples used to take about an hour. + # Now they take a fraction of a second. + def check(source): + parser = html.parser.HTMLParser() + parser.feed(source) + parser.close() + n = 120_000 + check("<a " * n) + check("<a a=" * n) + check("</a " * 14 * n) + check("</a a=" * 11 * n) + check("<!--" * 4 * n) + check("<!" * 60 * n) + check("<?" * 19 * n) + check("</$" * 15 * n) + check("<![CDATA[" * 9 * n) + check("<!doctype" * 35 * n) + class AttributesTestCase(TestCaseBase): @@ -608,9 +784,15 @@ class AttributesTestCase(TestCaseBase): ("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) + self._run_check("<a foo==bar>", [('starttag', 'a', [('foo', '=bar')])]) + self._run_check("<a foo =bar>", [('starttag', 'a', [('foo', None), ('=bar', None)])]) + self._run_check("<a foo\t=bar>", [('starttag', 'a', [('foo', None), ('=bar', None)])]) + self._run_check("<a foo\v=bar>", [('starttag', 'a', [('foo\v', 'bar')])]) + self._run_check("<a foo\xa0=bar>", [('starttag', 'a', [('foo\xa0', 'bar')])]) + self._run_check("<a foo= bar>", [('starttag', 'a', [('foo', ''), ('bar', None)])]) + self._run_check("<a foo=\tbar>", [('starttag', 'a', [('foo', ''), ('bar', None)])]) + self._run_check("<a foo=\vbar>", [('starttag', 'a', [('foo', '\vbar')])]) + self._run_check("<a foo=\xa0bar>", [('starttag', 'a', [('foo', '\xa0bar')])]) def test_attr_values(self): self._run_check("""<a b='xxx\n\txxx' c="yyy\t\nyyy" d='\txyz\n'>""", @@ -619,6 +801,10 @@ class AttributesTestCase(TestCaseBase): ("d", "\txyz\n")])]) self._run_check("""<a b='' c="">""", [("starttag", "a", [("b", ""), ("c", "")])]) + self._run_check("<a b=\t c=\n>", + [("starttag", "a", [("b", ""), ("c", "")])]) + self._run_check("<a b=\v c=\xa0>", + [("starttag", "a", [("b", "\v"), ("c", "\xa0")])]) # Regression test for SF patch #669683. self._run_check("<e a=rgb(1,2,3)>", [("starttag", "e", [("a", "rgb(1,2,3)")])]) @@ -690,7 +876,7 @@ class AttributesTestCase(TestCaseBase): ('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'")]), + ('starttag', 'a', [('href', None), ('=', None), ("test' style", 'color:red;bad4')]), ('data', 'test - bad4'), ('endtag', 'a') ] self._run_check(html, expected) |