Mercurial > cpython-lru_cache-weakref

diff Lib/HTMLParser.py @ 75116:37c824c3efe8 2.7

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
HTMLParser is now able to handle slashes in the start tag.
author Ezio Melotti <ezio.melotti@gmail.com>
date Tue, 21 Feb 2012 09:22:16 +0200
parents 3d7904e3f4b9
children 36c901fcfcda
line wrap: on
line diff
--- a/Lib/HTMLParser.py	Tue Feb 21 00:40:14 2012 -0500
+++ b/Lib/HTMLParser.py	Tue Feb 21 09:22:16 2012 +0200
@@ -28,19 +28,19 @@
 tagfind_tolerant = re.compile('[a-zA-Z][^\t\n\r\f />\x00]*')
 
 attrfind = re.compile(
-    r'\s*((?<=[\'"\s])[^\s/>][^\s/=>]*)(\s*=+\s*'
-    r'(\'[^\']*\'|"[^"]*"|(?![\'"])[^>\s]*))?')
+    r'[\s/]*((?<=[\'"\s/])[^\s/>][^\s/=>]*)(\s*=+\s*'
+    r'(\'[^\']*\'|"[^"]*"|(?![\'"])[^>\s]*))?(?:\s|/(?!>))*')
 
 locatestarttagend = re.compile(r"""
   <[a-zA-Z][-.a-zA-Z0-9:_]*          # tag name
-  (?:\s+                             # whitespace before attribute name
-    (?:(?<=['"\s])[^\s/>][^\s/=>]*   # attribute name
+  (?:[\s/]*                          # optional whitespace before attribute name
+    (?:(?<=['"\s/])[^\s/>][^\s/=>]*  # attribute name
       (?:\s*=+\s*                    # value indicator
         (?:'[^']*'                   # LITA-enclosed value
           |"[^"]*"                   # LIT-enclosed value
           |(?!['"])[^>\s]*           # bare value
          )
-       )?\s*
+       )?(?:\s|/(?!>))*
      )*
    )?
   \s*                                # trailing whitespace