From: Yui NARUSE <redmine@...>
Date: 2009-08-19T11:57:12+09:00
Subject: [ruby-core:24975] [Feature #1889] Teach Onigurma Unicode 5.0 Character Properties

Issue #1889 has been updated by Yui NARUSE.


My intention is like following:

diff --git a/enc/unicode.c b/enc/unicode.c
index 2dfcbba..f8fd25e 100644
--- a/enc/unicode.c
+++ b/enc/unicode.c
@@ -3863,3820 +3863,7 @@ static const OnigCodePoint CR_Assigned[] = {
   0x100000, 0x10fffd
 }; /* CR_Assigned */

-/* 'C': Major Category */
-static const OnigCodePoint CR_C[] = {
-  422,
-  0x0000, 0x001f,
<snip>
-  0x3000, 0x3000
-}; /* CR_Zs */
+#include "unicode.h"

 /* 'Arabic': Script */
 static const OnigCodePoint CR_Arabic[] = {

diff --git a/unicode.h b/unicode.h
new file mode 100644
index 0000000..3758c22
--- /dev/null
+++ b/unicode.h
@@ -0,0 +1,4002 @@
+/* 'C': Major Category */
+static const OnigCodePoint CR_C[] = {
+       25,
+       000000, 0x001f,
<snip>
+       0x3000, 0x3000,
+}; /* CR_Zs */

unicode.h is the same of your http://gist.github.com/169862.

And I confirmed /\p{Nd}/=~"\uAA59" works with this.
Great!
----------------------------------------
http://redmine.ruby-lang.org/issues/show/1889

----------------------------------------
http://redmine.ruby-lang.org