(original) (raw)

changeset: 76415:0f837071fd97 parent: 76411:e3ab8aa0216c parent: 76414:ba4baaddac8d user: Ezio Melotti ezio.melotti@gmail.com date: Wed Apr 18 19:36:03 2012 -0600 files: Misc/NEWS description: #14538: merge with 3.2. diff -r e3ab8aa0216c -r 0f837071fd97 Lib/html/parser.py --- a/Lib/html/parser.py Thu Apr 19 00:57:45 2012 +0200 +++ b/Lib/html/parser.py Wed Apr 18 19:36:03 2012 -0600 @@ -22,7 +22,7 @@ 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 @@ 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 @@ 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 -r e3ab8aa0216c -r 0f837071fd97 Lib/test/test_htmlparser.py --- a/Lib/test/test_htmlparser.py Thu Apr 19 00:57:45 2012 +0200 +++ b/Lib/test/test_htmlparser.py Wed Apr 18 19:36:03 2012 -0600 @@ -409,6 +409,16 @@ ('starttag', 'a', [('foo', None), ('=', None), ('bar', None)]) ] self._run_check(html, expected) + #see issue #14538 + html = ('' + '') + 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("", [('decl', 'DOCTYPE foo $ ')]) diff -r e3ab8aa0216c -r 0f837071fd97 Misc/NEWS --- a/Misc/NEWS Thu Apr 19 00:57:45 2012 +0200 +++ b/Misc/NEWS Wed Apr 18 19:36:03 2012 -0600 @@ -58,6 +58,9 @@ - Issue #14087: multiprocessing: add Condition.wait_for(). Patch by sbt. +- Issue #14538: HTMLParser can now parse correctly start tags that contain + a bare '/'. + - Issue #14452: SysLogHandler no longer inserts a UTF-8 BOM into the message. - Issue #14386: Expose the dict_proxy internal type as types.MappingProxyType. /ezio.melotti@gmail.com