[Python-checkins] cpython (2.7): #19480: HTMLParser now accepts all valid start-tag names as defined by the

[ezio.melotti]

http://hg.python.org/cpython/rev/695f988824bb
changeset:   86988:695f988824bb
branch:      2.7
user:        Ezio Melotti <ezio.melotti at gmail.com>
date:        Thu Nov 07 18:31:36 2013 +0200
summary:
  #19480: HTMLParser now accepts all valid start-tag names as defined by the HTML5 standard.

files:
  Lib/HTMLParser.py           |  11 +++++++----
  Lib/test/test_htmlparser.py |   8 ++++++--
  Misc/NEWS                   |   5 ++++-
  3 files changed, 17 insertions(+), 7 deletions(-)


diff --git a/Lib/HTMLParser.py b/Lib/HTMLParser.py
--- a/Lib/HTMLParser.py
+++ b/Lib/HTMLParser.py
@@ -22,9 +22,12 @@
 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
+# note: if you change tagfind/attrfind remember to update locatestarttagend too
+tagfind = re.compile('([a-zA-Z][^\t\n\r\f />\x00]*)(?:\s|/(?!>))*')
+# this regex is currently unused, but left for backward compatibility
 tagfind_tolerant = re.compile('[a-zA-Z][^\t\n\r\f />\x00]*')
 
 attrfind = re.compile(
@@ -32,7 +35,7 @@
     r'(\'[^\']*\'|"[^"]*"|(?![\'"])[^>\s]*))?(?:\s|/(?!>))*')
 
 locatestarttagend = 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
@@ -373,14 +376,14 @@
                 self.handle_data(rawdata[i:gtpos])
                 return gtpos
             # find the name: w3.org/TR/html5/tokenization.html#tag-name-state
-            namematch = tagfind_tolerant.match(rawdata, i+2)
+            namematch = tagfind.match(rawdata, i+2)
             if not namematch:
                 # w3.org/TR/html5/tokenization.html#end-tag-open-state
                 if rawdata[i:i+3] == '</>':
                     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
--- a/Lib/test/test_htmlparser.py
+++ b/Lib/test/test_htmlparser.py
@@ -206,8 +206,7 @@
         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')])
@@ -215,6 +214,11 @@
         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_valid_doctypes(self):
         # from http://www.w3.org/QA/2002/04/valid-dtd-list.html
diff --git a/Misc/NEWS b/Misc/NEWS
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -12,8 +12,11 @@
 Library
 -------
 
+- Issue #19480: HTMLParser now accepts all valid start-tag names as defined
+  by the HTML5 standard.
+
 - Issue #17827: Add the missing documentation for ``codecs.encode`` and
-    ``codecs.decode``.
+  ``codecs.decode``.
 
 - Issue #6157: Fixed Tkinter.Text.debug().  Original patch by Guilherme Polo.
 

-- 
Repository URL: http://hg.python.org/cpython