diff options
| author | Ezio Melotti <ezio.melotti@gmail.com> | 2012-04-19 01:08:41 (GMT) |
|---|---|---|
| committer | Ezio Melotti <ezio.melotti@gmail.com> | 2012-04-19 01:08:41 (GMT) |
| commit | c45868ec697a70a80d1cf8a511894f073fda3a27 (patch) | |
| tree | 1f8e79a1d86c7efa99e160ecda477eab7a14b27b /Lib | |
| parent | a72aa843b66e80cc6f97a5e3571952d941e82404 (diff) | |
| download | cpython-c45868ec697a70a80d1cf8a511894f073fda3a27.zip cpython-c45868ec697a70a80d1cf8a511894f073fda3a27.tar.gz cpython-c45868ec697a70a80d1cf8a511894f073fda3a27.tar.bz2 | |
#14538: HTMLParser can now parse correctly start tags that contain a bare /.
Diffstat (limited to 'Lib')
| -rw-r--r-- | Lib/HTMLParser.py | 6 | ||||
| -rw-r--r-- | Lib/test/test_htmlparser.py | 10 |
2 files changed, 13 insertions, 3 deletions
diff --git a/Lib/HTMLParser.py b/Lib/HTMLParser.py index d4e14d4..b336a4c 100644 --- a/Lib/HTMLParser.py +++ b/Lib/HTMLParser.py @@ -22,13 +22,13 @@ 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]*') attrfind = re.compile( - r'[\s/]*((?<=[\'"\s/])[^\s/>][^\s/=>]*)(\s*=+\s*' + r'((?<=[\'"\s/])[^\s/>][^\s/=>]*)(\s*=+\s*' r'(\'[^\']*\'|"[^"]*"|(?![\'"])[^>\s]*))?(?:\s|/(?!>))*') locatestarttagend = re.compile(r""" @@ -289,7 +289,7 @@ 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: m = attrfind.match(rawdata, k) diff --git a/Lib/test/test_htmlparser.py b/Lib/test/test_htmlparser.py index 41f4340..8cc461f 100644 --- a/Lib/test/test_htmlparser.py +++ b/Lib/test/test_htmlparser.py @@ -260,6 +260,16 @@ text ('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 $ ')]) |