From 7165d8b9ba7df402fb167ff20dc6d1a35e7386ed Mon Sep 17 00:00:00 2001 From: Ezio Melotti Date: Thu, 7 Nov 2013 18:33:24 +0200 Subject: #19480: HTMLParser now accepts all valid start-tag names as defined by the HTML5 standard. --- Lib/html/parser.py | 21 ++++++++++++--------- Lib/test/test_htmlparser.py | 17 +++++++++++++---- Misc/NEWS | 3 +++ 3 files changed, 28 insertions(+), 13 deletions(-) diff --git a/Lib/html/parser.py b/Lib/html/parser.py index 60a322a..2d3bef3 100644 --- a/Lib/html/parser.py +++ b/Lib/html/parser.py @@ -23,16 +23,16 @@ 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:_]*)(?:\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]*') # Note: # 1) the strict attrfind isn't really strict, but we can't make it # correctly strict without breaking backward compatibility; -# 2) if you change attrfind remember to update locatestarttagend too; -# 3) if you change attrfind and/or locatestarttagend the parser will +# 2) if you change tagfind/attrfind remember to update locatestarttagend too; +# 3) if you change tagfind/attrfind and/or locatestarttagend the parser will # explode, so don't do it. +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]*)(?:\s|/(?!>))*') attrfind = re.compile( r'\s*([a-zA-Z_][-.:a-zA-Z_0-9]*)(\s*=\s*' r'(\'[^\']*\'|"[^"]*"|[^\s"\'=<>`]*))?') @@ -54,7 +54,7 @@ locatestarttagend = re.compile(r""" \s* # trailing whitespace """, re.VERBOSE) locatestarttagend_tolerant = re.compile(r""" - <[a-zA-Z][-.a-zA-Z0-9:_]* # tag name + <[a-zA-Z][^\t\n\r\f />\x00]* # tag name (?:[\s/]* # optional whitespace before attribute name (?:(?<=['"\s/])[^\s/>][^\s/=>]* # attribute name (?:\s*=+\s* # value indicator @@ -328,7 +328,10 @@ class HTMLParser(_markupbase.ParserBase): # Now parse the data between i+1 and j into a tag and attrs attrs = [] - match = tagfind.match(rawdata, i+1) + if self.strict: + match = tagfind.match(rawdata, i+1) + else: + match = tagfind_tolerant.match(rawdata, i+1) assert match, 'unexpected call to parse_starttag()' k = match.end() self.lasttag = tag = match.group(1).lower() @@ -440,7 +443,7 @@ class HTMLParser(_markupbase.ParserBase): return i+3 else: return self.parse_bogus_comment(i) - tagname = namematch.group().lower() + tagname = namematch.group(1).lower() # consume and ignore other stuff between the name and the > # Note: this is not 100% correct, since we might have things like # , but looking for > after tha name should cover diff --git a/Lib/test/test_htmlparser.py b/Lib/test/test_htmlparser.py index e8b8857..c977a9d 100644 --- a/Lib/test/test_htmlparser.py +++ b/Lib/test/test_htmlparser.py @@ -229,6 +229,11 @@ text self._parse_error("'") self._parse_error(">xt'), ('entityref', 'a'), - ('data', '<", [('comment', '$')]) self._run_check("", [('data', '", [('starttag', 'a", [('endtag', 'a'", [('data', "", [('starttag', 'a$b', [])]) + self._run_check("", [('startendtag', 'a$b', [])]) + self._run_check("", [('starttag', 'a$b', [])]) + self._run_check("", [('startendtag', 'a$b', [])]) def test_slashes_in_starttag(self): self._run_check('', [('startendtag', 'a', [('foo', 'var')])]) diff --git a/Misc/NEWS b/Misc/NEWS index 9d03d0c..e4e2e14 100644 --- a/Misc/NEWS +++ b/Misc/NEWS @@ -13,6 +13,9 @@ Core and Builtins Library ------- +- Issue #19480: HTMLParser now accepts all valid start-tag names as defined + by the HTML5 standard. + - Issue #6157: Fixed tkinter.Text.debug(). Original patch by Guilherme Polo. - Issue #6160: The bbox() method of tkinter.Spinbox now returns a tuple of -- cgit v0.12