#12888: Fix a bug in HTMLParser.unescape that prevented it to escape more than 128 entities. Patch by Peter Otten.

ezio-melotti · ezio-melotti · commit d9e0b068af17 · 2011-09-05T17:11:06.000+03:00
diff --git a/Lib/html/parser.py b/Lib/html/parser.py
@@ -458,4 +458,4 @@ def replaceEntities(s):
                     return '&'+s+';'
 
         return re.sub(r"&(#?[xX]?(?:[0-9a-fA-F]+|\w{1,8}));",
-                      replaceEntities, s, re.ASCII)
+                      replaceEntities, s, flags=re.ASCII)
diff --git a/Lib/test/test_htmlparser.py b/Lib/test/test_htmlparser.py
@@ -377,7 +377,8 @@ def test_unescape_function(self):
         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 --git a/Misc/ACKS b/Misc/ACKS
@@ -661,6 +661,7 @@ Douglas Orr
 Michele Orrù
 Oleg Oshmyan
 Denis S. Otkidach
+Peter Otten
 Michael Otteneder
 R. M. Oudkerk
 Russel Owen
diff --git a/Misc/NEWS b/Misc/NEWS
@@ -25,6 +25,9 @@ Core and Builtins
 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.
