[Python-checkins] cpython (merge 3.2 -> default): #14538: merge with 3.2.

[ezio.melotti]

http://hg.python.org/cpython/rev/0f837071fd97
changeset:   76415:0f837071fd97
parent:      76411:e3ab8aa0216c
parent:      76414:ba4baaddac8d
user:        Ezio Melotti <ezio.melotti at gmail.com>
date:        Wed Apr 18 19:36:03 2012 -0600
summary:
  #14538: merge with 3.2.

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


diff --git a/Lib/html/parser.py b/Lib/html/parser.py
--- a/Lib/html/parser.py
+++ b/Lib/html/parser.py
@@ -22,7 +22,7 @@
 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]*')
@@ -36,7 +36,7 @@
     r'\s*([a-zA-Z_][-.:a-zA-Z_0-9]*)(\s*=\s*'
     r'(\'[^\']*\'|"[^"]*"|[^\s"\'=<>`]*))?')
 attrfind_tolerant = re.compile(
-    r'[\s/]*((?<=[\'"\s/])[^\s/>][^\s/=>]*)(\s*=+\s*'
+    r'((?<=[\'"\s/])[^\s/>][^\s/=>]*)(\s*=+\s*'
     r'(\'[^\']*\'|"[^"]*"|(?![\'"])[^>\s]*))?(?:\s|/(?!>))*')
 locatestarttagend = re.compile(r"""
   <[a-zA-Z][-.a-zA-Z0-9:_]*          # tag name
@@ -327,7 +327,7 @@
         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:
             if self.strict:
                 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
@@ -409,6 +409,16 @@
             ('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
@@ -58,6 +58,9 @@
 
 - Issue #14087: multiprocessing: add Condition.wait_for(). Patch by sbt.
 
+- 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 #14386: Expose the dict_proxy internal type as types.MappingProxyType.

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