diff options
Diffstat (limited to 'Lib')
| -rw-r--r-- | Lib/html/parser.py | 6 | ||||
| -rw-r--r-- | Lib/test/test_htmlparser.py | 10 |
2 files changed, 13 insertions, 3 deletions
diff --git a/Lib/html/parser.py b/Lib/html/parser.py index 2bfd187..de504ab 100644 --- a/Lib/html/parser.py +++ b/Lib/html/parser.py @@ -22,7 +22,7 @@ charref = re.compile('&#(?:[0-9]+|[xX][0-9a-fA-F]+)[^0-9a-fA-F]') starttagopen = re.compile('<[a-zA-Z]') piclose = re.compile('>') commentclose = re.compile(r'--\s*>') -tagfind = re.compile('[a-zA-Z][-.a-zA-Z0-9:_]*') +tagfind = re.compile('([a-zA-Z][-.a-zA-Z0-9:_]*)(?:\s|/(?!>))*') # see http://www.w3.org/TR/html5/tokenization.html#tag-open-state # and http://www.w3.org/TR/html5/tokenization.html#tag-name-state tagfind_tolerant = re.compile('[a-zA-Z][^\t\n\r\f />\x00]*') @@ -36,7 +36,7 @@ attrfind = re.compile( r'\s*([a-zA-Z_][-.:a-zA-Z_0-9]*)(\s*=\s*' r'(\'[^\']*\'|"[^"]*"|[^\s"\'=<>`]*))?') attrfind_tolerant = re.compile( - r'[\s/]*((?<=[\'"\s/])[^\s/>][^\s/=>]*)(\s*=+\s*' + r'((?<=[\'"\s/])[^\s/>][^\s/=>]*)(\s*=+\s*' r'(\'[^\']*\'|"[^"]*"|(?![\'"])[^>\s]*))?(?:\s|/(?!>))*') locatestarttagend = re.compile(r""" <[a-zA-Z][-.a-zA-Z0-9:_]* # tag name @@ -327,7 +327,7 @@ class HTMLParser(_markupbase.ParserBase): match = tagfind.match(rawdata, i+1) assert match, 'unexpected call to parse_starttag()' k = match.end() - self.lasttag = tag = rawdata[i+1:k].lower() + self.lasttag = tag = match.group(1).lower() while k < endpos: if self.strict: m = attrfind.match(rawdata, k) diff --git a/Lib/test/test_htmlparser.py b/Lib/test/test_htmlparser.py index 3e2a590..c4f80cc 100644 --- a/Lib/test/test_htmlparser.py +++ b/Lib/test/test_htmlparser.py @@ -409,6 +409,16 @@ class HTMLParserTolerantTestCase(HTMLParserStrictTestCase): ('starttag', 'a', [('foo', None), ('=', None), ('bar', None)]) ] self._run_check(html, expected) + #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) def test_declaration_junk_chars(self): self._run_check("<!DOCTYPE foo $ >", [('decl', 'DOCTYPE foo $ ')]) |