Index: Objects/unicodeobject.c
===================================================================
--- Objects/unicodeobject.c	(revision 88538)
+++ Objects/unicodeobject.c	(working copy)
@@ -1452,6 +1452,58 @@
     return 1;
 }
 
+static int
+normalize_encoding2(const char *encoding,
+                    char *lower,
+                    size_t lower_len)
+{
+    const char *e;
+    char *l;
+    char pc; /* used to store the previous char in the loop */
+    char *l_end;
+
+    e = encoding;
+    l = lower;
+    l_end = &lower[lower_len - 1];
+    pc = ' ';
+
+    /* strip leading non alnum */
+    while (!Py_ISALNUM(*e)) *e++;
+
+    while (*e) {
+        if (l == l_end)
+            return 0;
+        if (Py_ISALPHA(*e)) {
+            if (Py_ISDIGIT(pc))
+                *l++ = ' ';
+            if (Py_ISUPPER(*e))
+                *l++ = Py_TOLOWER(*e++);
+            else
+                *l++ = *e++;
+        }
+        else if (Py_ISDIGIT(*e)) {
+            if (Py_ISALPHA(pc))
+                *l++ = ' ';
+            *l++ = *e++;
+        }
+        else {
+            /* replace non-alnum with a space */
+            *l++ = ' ';
+            /* and consume all following non-alnum */
+            while (*e && !Py_ISALNUM(*e)) {
+                *e++;
+            }
+        }
+        pc = *(e-1);
+    }
+    /* terminate the string, possibly replacing the trailing space */
+    if (*(l-1) == ' ')
+        *(l-1) = '\0';
+    else
+        *l = '\0';
+    return 1;
+}
+
 PyObject *PyUnicode_Decode(const char *s,
                            Py_ssize_t size,
                            const char *encoding,
@@ -1459,17 +1511,15 @@
 {
     PyObject *buffer = NULL, *unicode;
     Py_buffer info;
-    char lower[11];  /* Enough for any encoding shortcut */
+    char lower[strlen(encoding)*2];  /* Enough for any encoding shortcut */
 
     if (encoding == NULL)
         encoding = PyUnicode_GetDefaultEncoding();
-
-    /* Shortcuts for common default encodings */
-    if (normalize_encoding(encoding, lower, sizeof(lower))) {
-        if (strcmp(lower, "utf-8") == 0)
+    if (normalize_encoding2(encoding, lower, sizeof(lower))) {
+        if (strcmp(lower, "utf 8") == 0)
             return PyUnicode_DecodeUTF8(s, size, errors);
-        else if ((strcmp(lower, "latin-1") == 0) ||
-                 (strcmp(lower, "iso-8859-1") == 0))
+        else if ((strcmp(lower, "latin 1") == 0) ||
+                 (strcmp(lower, "iso 8859 1") == 0))
             return PyUnicode_DecodeLatin1(s, size, errors);
 #if defined(MS_WINDOWS) && defined(HAVE_USABLE_WCHAR_T)
         else if (strcmp(lower, "mbcs") == 0)
@@ -1477,9 +1527,9 @@
 #endif
         else if (strcmp(lower, "ascii") == 0)
             return PyUnicode_DecodeASCII(s, size, errors);
-        else if (strcmp(lower, "utf-16") == 0)
+        else if (strcmp(lower, "utf 16") == 0)
             return PyUnicode_DecodeUTF16(s, size, errors, 0);
-        else if (strcmp(lower, "utf-32") == 0)
+        else if (strcmp(lower, "utf 32") == 0)
             return PyUnicode_DecodeUTF32(s, size, errors, 0);
     }