patch for PSF-2006-001.

2 files changed, 47 insertions, 25 deletions

diff --git a/Misc/NEWS b/Misc/NEWS
index 1c3e92a..c1d18ac 100644
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -4,26 +4,22 @@ Python News
 
 (editors: check NEWS.help for information about editing NEWS using ReST.)
 
-What's New in Python 2.3.6rc1?
-==============================
+What's New in Python 2.3.6c1?
+=============================
 
-*Release date: XX-XXX-200X*
+*Release date: 25-OCT-2006*
 
-Extension modules
+Core and builtins
 -----------------
 
-- Apply fix for potential heap overflow in PCRE code (CAN-2005-2491).
-
-
-What's New in Python 2.3.5?
-==============================
-
-*Release date: 08-FEB-2005*
+- Patch #1541585: fix buffer overrun when performing repr() on
+  a unicode string in a build with wide unicode (UCS-4) support.
+  This is the problem described in security advisory PSF-2006-001.
 
-Core and builtins
+Extension modules
 -----------------
 
-- Partially revert the fix for #1074011; don't try to fflush stdin anymore.
+- Apply fix for potential heap overflow in PCRE code (CAN-2005-2491).
 
 Library
 -------
@@ -40,6 +36,19 @@ Library
   Also, whereas % values were decoded in all parameter continuations, they are
   now only decoded in encoded parameter parts.
 
+What's New in Python 2.3.5?
+==============================
+
+*Release date: 08-FEB-2005*
+
+Core and builtins
+-----------------
+
+- Partially revert the fix for #1074011; don't try to fflush stdin anymore.
+
+Library
+-------
+
 - Applied a security fix to SimpleXMLRPCserver (PSF-2005-001).  This
   disables recursive traversal through instance attributes, which can
   be exploited in various ways.
diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c
index 6f3e8b1..e9b2a83 100644
--- a/Objects/unicodeobject.c
+++ b/Objects/unicodeobject.c
@@ -1888,7 +1888,28 @@ PyObject *unicodeescape_string(const Py_UNICODE *s,
 
     static const char *hexdigit = "0123456789abcdef";
 
-    repr = PyString_FromStringAndSize(NULL, 2 + 6*size + 1);
+    /* Initial allocation is based on the longest-possible unichr
+       escape.
+
+       In wide (UTF-32) builds '\U00xxxxxx' is 10 chars per source
+       unichr, so in this case it's the longest unichr escape. In
+       narrow (UTF-16) builds this is five chars per source unichr
+       since there are two unichrs in the surrogate pair, so in narrow
+       (UTF-16) builds it's not the longest unichr escape.
+
+       In wide or narrow builds '\uxxxx' is 6 chars per source unichr,
+       so in the narrow (UTF-16) build case it's the longest unichr
+       escape.
+    */
+
+    repr = PyString_FromStringAndSize(NULL,
+        2
+#ifdef Py_UNICODE_WIDE
+        + 10*size
+#else
+        + 6*size
+#endif
+        + 1);
     if (repr == NULL)
         return NULL;
 
@@ -1913,15 +1934,6 @@ PyObject *unicodeescape_string(const Py_UNICODE *s,
 #ifdef Py_UNICODE_WIDE
         /* Map 21-bit characters to '\U00xxxxxx' */
         else if (ch >= 0x10000) {
-	    int offset = p - PyString_AS_STRING(repr);
-	    
-	    /* Resize the string if necessary */
-	    if (offset + 12 > PyString_GET_SIZE(repr)) {
-		if (_PyString_Resize(&repr, PyString_GET_SIZE(repr) + 100))
-		    return NULL;
-		p = PyString_AS_STRING(repr) + offset;
-	    }
-
             *p++ = '\\';
             *p++ = 'U';
             *p++ = hexdigit[(ch >> 28) & 0x0000000F];
@@ -1934,8 +1946,8 @@ PyObject *unicodeescape_string(const Py_UNICODE *s,
             *p++ = hexdigit[ch & 0x0000000F];
 	    continue;
         }
-#endif
-	/* Map UTF-16 surrogate pairs to Unicode \UXXXXXXXX escapes */
+#else
+	/* Map UTF-16 surrogate pairs to '\U00xxxxxx' */
 	else if (ch >= 0xD800 && ch < 0xDC00) {
 	    Py_UNICODE ch2;
 	    Py_UCS4 ucs;
@@ -1960,6 +1972,7 @@ PyObject *unicodeescape_string(const Py_UNICODE *s,
 	    s--;
 	    size++;
 	}
+#endif
 
         /* Map 16-bit characters to '\uxxxx' */
         if (ch >= 256) {