changeset:   72270:9896fc2a8167
branch:      3.2
parent:      72268:b38fdedb29d9
user:        Ezio Melotti <ezio.melotti@gmail.com>
date:        Mon Sep 05 17:11:06 2011 +0300
files:       Lib/html/parser.py Lib/test/test_htmlparser.py Misc/ACKS Misc/NEWS
description:
#12888: Fix a bug in HTMLParser.unescape that prevented it to escape more than 128 entities.  Patch by Peter Otten.


diff -r b38fdedb29d9 -r 9896fc2a8167 Lib/html/parser.py
--- a/Lib/html/parser.py	Mon Sep 05 00:14:09 2011 +0200
+++ b/Lib/html/parser.py	Mon Sep 05 17:11:06 2011 +0300
@@ -458,4 +458,4 @@
                     return '&'+s+';'
 
         return re.sub(r"&(#?[xX]?(?:[0-9a-fA-F]+|\w{1,8}));",
-                      replaceEntities, s, re.ASCII)
+                      replaceEntities, s, flags=re.ASCII)
diff -r b38fdedb29d9 -r 9896fc2a8167 Lib/test/test_htmlparser.py
--- a/Lib/test/test_htmlparser.py	Mon Sep 05 00:14:09 2011 +0200
+++ b/Lib/test/test_htmlparser.py	Mon Sep 05 17:11:06 2011 +0300
@@ -377,7 +377,8 @@
         p = html.parser.HTMLParser()
         self.assertEqual(p.unescape('&#bad;'),'&#bad;')
         self.assertEqual(p.unescape('&#0038;'),'&')
-
+        # see #12888
+        self.assertEqual(p.unescape('&#123; ' * 1050), '{ ' * 1050)
 
 def test_main():
     support.run_unittest(HTMLParserTestCase, HTMLParserTolerantTestCase)
diff -r b38fdedb29d9 -r 9896fc2a8167 Misc/ACKS
--- a/Misc/ACKS	Mon Sep 05 00:14:09 2011 +0200
+++ b/Misc/ACKS	Mon Sep 05 17:11:06 2011 +0300
@@ -661,6 +661,7 @@
 Michele Orrù
 Oleg Oshmyan
 Denis S. Otkidach
+Peter Otten
 Michael Otteneder
 R. M. Oudkerk
 Russel Owen
diff -r b38fdedb29d9 -r 9896fc2a8167 Misc/NEWS
--- a/Misc/NEWS	Mon Sep 05 00:14:09 2011 +0200
+++ b/Misc/NEWS	Mon Sep 05 17:11:06 2011 +0300
@@ -25,6 +25,9 @@
 Library
 -------
 
+- Issue #12888: Fix a bug in HTMLParser.unescape that prevented it to escape
+  more than 128 entities.  Patch by Peter Otten.
+
 - Issue #12878: Expose a __dict__ attribute on io.IOBase and its subclasses.
 
 - Issue #12636: IDLE reads the coding cookie when executing a Python script.