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 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