[Python-checkins] cpython (2.7): #14538: HTMLParser can now parse correctly start tags that contain a bare /.

[ezio.melotti]

http://hg.python.org/cpython/rev/36c901fcfcda
changeset:   76413:36c901fcfcda
branch:      2.7
user:        Ezio Melotti <ezio.melotti at gmail.com>
date:        Wed Apr 18 19:08:41 2012 -0600
summary:
  #14538: HTMLParser can now parse correctly start tags that contain a bare /.

files:
  Lib/HTMLParser.py           |   6 +++---
  Lib/test/test_htmlparser.py |  10 ++++++++++
  Misc/NEWS                   |   3 +++
  3 files changed, 16 insertions(+), 3 deletions(-)


diff --git a/Lib/HTMLParser.py b/Lib/HTMLParser.py
--- a/Lib/HTMLParser.py
+++ b/Lib/HTMLParser.py
@@ -22,13 +22,13 @@
 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 @@
         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
--- a/Lib/test/test_htmlparser.py
+++ b/Lib/test/test_htmlparser.py
@@ -260,6 +260,16 @@
             ('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 $ ')])
diff --git a/Misc/NEWS b/Misc/NEWS
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -50,6 +50,9 @@
 Library
 -------
 
+- 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 #13496: Fix potential overflow in bisect.bisect algorithm when applied

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