#19480: HTMLParser now accepts all valid start-tag names as defined by the HTML5 standard.

ezio-melotti · ezio-melotti · commit 7165d8b9ba7d · 2013-11-07T18:33:24.000+02:00
diff --git a/Lib/html/parser.py b/Lib/html/parser.py
@@ -23,16 +23,16 @@
 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 @@
   \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 @@ def parse_starttag(self, i):
 
         # 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 @@ def parse_endtag(self, i):
                     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
             # </tag attr=">">, but looking for > after tha name should cover
diff --git a/Lib/test/test_htmlparser.py b/Lib/test/test_htmlparser.py
@@ -229,6 +229,11 @@ def test_starttag_junk_chars(self):
         self._parse_error("<a foo='bar")
         self._parse_error("<a foo='>'")
         self._parse_error("<a foo='>")
+        self._parse_error("<a$>")
+        self._parse_error("<a$b>")
+        self._parse_error("<a$b/>")
+        self._parse_error("<a$b  >")
+        self._parse_error("<a$b  />")
 
     def test_valid_doctypes(self):
         # from http://www.w3.org/QA/2002/04/valid-dtd-list.html
@@ -368,8 +373,8 @@ def test_tolerant_parsing(self):
                             ('starttag', 'html', [('<html', None)]),
                             ('data', 'te>>xt'),
                             ('entityref', 'a'),
-                            ('data', '<<bc'),
-                            ('endtag', 'a'),
+                            ('data', '<'),
+                            ('starttag', 'bc<', [('a', None)]),
                             ('endtag', 'html'),
                             ('data', '\n<img src="URL>'),
                             ('comment', '/img'),
@@ -380,15 +385,19 @@ def test_starttag_junk_chars(self):
         self._run_check("</$>", [('comment', '$')])
         self._run_check("</", [('data', '</')])
         self._run_check("</a", [('data', '</a')])
-        # XXX this might be wrong
-        self._run_check("<a<a>", [('data', '<a'), ('starttag', '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("<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', [])])
 
     def test_slashes_in_starttag(self):
         self._run_check('<a foo="var"/>', [('startendtag', 'a', [('foo', 'var')])])
diff --git 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
