Disable big charsets in UCS-4 builds. Works around #599377.

Will backport to 2.2

diff --git a/Lib/sre_compile.py b/Lib/sre_compile.py
index 30957a827b081457a2564c967518d298fc626340..e5adb7e46a7817a57e2c4f43c46547d947cd755b 100644 (file)
--- a/Lib/sre_compile.py
+++ b/Lib/sre_compile.py
@@ -188,6 +188,9 @@ def _optimize_charset(charset, fixup):
                 # 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