commit 67c4cb1f13e0a8dbbe8d2447165f27b2ef8e48fd
author Martin v. Löwis <martin@v.loewis.de> Thu Sep 26 16:39:20 2002 +0000
committer Martin v. Löwis <martin@v.loewis.de> Thu Sep 26 16:39:20 2002 +0000
tree e24b998a044fcace9f4f9b9d640cda81f6afbde3
parent eb42b026dbfd8583279e685f693b0483e06e5d29

Disable big charsets in UCS-4 builds. Works around #599377.
Will backport to 2.2

Lib/sre_compile.py

diff --git a/Lib/sre_compile.py b/Lib/sre_compile.py
index 30957a8..e5adb7e 100644
--- a/Lib/sre_compile.py
+++ b/Lib/sre_compile.py
@@ -188,6 +188,9 @@
                 # XXX: could append to charmap tail
                 return charset # cannot compress
     except IndexError:
+        if sys.maxunicode != 65535:
+            # XXX: big charsets don't work in UCS-4 builds
+            return charset
         # character set contains unicode characters
         return _optimize_unicode(charset, fixup)
     # compress character map