diff options
Diffstat (limited to 'Lib/test/test_htmlparser.py')
| -rw-r--r-- | Lib/test/test_htmlparser.py | 95 |
1 files changed, 83 insertions, 12 deletions
diff --git a/Lib/test/test_htmlparser.py b/Lib/test/test_htmlparser.py index 12917755a56..df775c11310 100644 --- a/Lib/test/test_htmlparser.py +++ b/Lib/test/test_htmlparser.py @@ -4,6 +4,8 @@ import html.parser import pprint import unittest +from test import support + class EventCollector(html.parser.HTMLParser): @@ -391,28 +393,34 @@ 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>", [('endtag', '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')])]) @@ -537,13 +545,56 @@ 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 !!!>') expected = [ + ('comment', 'ELEMENT br EMPTY'), ('comment', ' not really a comment '), ('comment', ' not a comment either --'), ('comment', ' -- close enough --'), @@ -598,6 +649,26 @@ 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): |