From b96a92fb2dbf3acb43641479fc731469e1de9f6c Mon Sep 17 00:00:00 2001
From: Karl Williamson <public@khwilliamson.com>
Date: Wed, 5 Sep 2012 20:32:29 -0600
Subject: utf8.h: Remove some EBCDIC dependencies

regen/regcharclass.pl has been enhanced in previous commits so that it
generates as good code as these hand-defined macro definitions for
various UTF-8 constructs.  And, it should be able to generate EBCDIC
ones as well.  By using its definitions, we can remove the EBCDIC
dependencies for them.  It is quite possible that the EBCDIC versions
were wrong, since they have never been tested.  Even if
regcharclass.pl has bugs under EBCDIC, it is easier to find and fix
those in one place, than all the sundry definitions.
---
 regen/regcharclass.pl | 12 ++++++++++++
 1 file changed, 12 insertions(+)

(limited to 'regen/regcharclass.pl')

diff --git a/regen/regcharclass.pl b/regen/regcharclass.pl
index 70f46b03b4..81ac13ce45 100755
--- a/regen/regcharclass.pl
+++ b/regen/regcharclass.pl
@@ -1112,6 +1112,18 @@ VERTWS: Vertical Whitespace: \v \V
 => generic UTF8 LATIN1 cp :fast safe
 \p{VertSpace}
 
+REPLACEMENT: Unicode REPLACEMENT CHARACTER
+=> UTF8 :safe
+0xFFFD
+
+NONCHAR: Non character code points
+=> UTF8 :fast
+\p{Nchar}
+
+SURROGATE: Surrogate characters
+=> UTF8 :fast
+\p{Gc=Cs}
+
 GCB_L: Grapheme_Cluster_Break=L
 => UTF8 :fast
 \p{_X_GCB_L}
-- 
cgit v1.2.1