From 3a833016110a7d20d44d1703966edeebd42209d8 Mon Sep 17 00:00:00 2001
From: nijtmans <nijtmans>
Date: Mon, 18 Oct 2010 21:47:36 +0000
Subject: [Bug 3085863]: tclUniData 9 years old Added testcases for Unicode 6.0

---
 ChangeLog          |  7 +++++++
 generic/regcomp.c  |  2 +-
 tests/utf.test     | 34 +++++++++++++++++-----------------
 tools/uniParse.tcl | 10 +++++++---
 4 files changed, 32 insertions(+), 21 deletions(-)

diff --git a/ChangeLog b/ChangeLog
index de50354..8e372eb 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,10 @@
+2010-10-18  Jan Nijtmans  <nijtmans@users.sf.net>
+
+	* tools/uniParse.tcl:   [Bug 3085863]: tclUniData 9 years old
+	Ignore non-BMP characters and fix comment about UnicodeData.txt file.
+	* generic/regcomp.c:    fix comment
+	* tests/utf.test:       Add some Unicode 6 testcases
+
 2010-10-17  Alexandre Ferrieux  <ferrieux@users.sourceforge.net>
 
 	* doc/info.n:           Document [info errorstack] faithfully.
diff --git a/generic/regcomp.c b/generic/regcomp.c
index 9753ca4..d7ae05e 100644
--- a/generic/regcomp.c
+++ b/generic/regcomp.c
@@ -2131,7 +2131,7 @@ stdump(
 
 /*
  - stid - identify a subtree node for dumping
- ^ static char *stid(struct subre *, char *, size_t);
+ ^ static const char *stid(struct subre *, char *, size_t);
  */
 static const char *			/* points to buf or constant string */
 stid(
diff --git a/tests/utf.test b/tests/utf.test
index 575a5cd..3a45d13 100644
--- a/tests/utf.test
+++ b/tests/utf.test
@@ -8,7 +8,7 @@
 # See the file "license.terms" for information on usage and redistribution
 # of this file, and for a DISCLAIMER OF ALL WARRANTIES.
 #
-# RCS: @(#) $Id: utf.test,v 1.14 2007/05/02 01:37:28 kennykb Exp $
+# RCS: @(#) $Id: utf.test,v 1.15 2010/10/18 21:47:36 nijtmans Exp $
 
 if {[lsearch [namespace children] ::tcltest] == -1} {
     package require tcltest 2
@@ -276,12 +276,12 @@ test utf-20.1 {TclUniCharNcmp} {
 } {}
 
 test utf-21.1 {TclUniCharIsAlnum} {
-    # this returns 1 with Unicode 3 compliance
-    string is alnum \u1040\u021f
+    # this returns 1 with Unicode 6 compliance
+    string is alnum \u1040\u021f\u0220
 } {1}
 test utf-21.2 {unicode alnum char in regc_locale.c} {
-    # this returns 1 with Unicode 3 compliance
-    list [regexp {^[[:alnum:]]+$} \u1040\u021f] [regexp {^\w+$} \u1040\u021f]
+    # this returns 1 with Unicode 6 compliance
+    list [regexp {^[[:alnum:]]+$} \u1040\u021f\u0220] [regexp {^\w+$} \u1040\u021f\u0220]
 } {1 1}
 
 test utf-22.1 {TclUniCharIsWordChar} {
@@ -292,30 +292,30 @@ test utf-22.2 {TclUniCharIsWordChar} {
 } 10
 
 test utf-23.1 {TclUniCharIsAlpha} {
-    # this returns 1 with Unicode 3 compliance
-    string is alpha \u021f
+    # this returns 1 with Unicode 6 compliance
+    string is alpha \u021f\u0220
 } {1}
 test utf-23.2 {unicode alpha char in regc_locale.c} {
-    # this returns 1 with Unicode 3 compliance
-    regexp {^[[:alpha:]]+$} \u021f
+    # this returns 1 with Unicode 6 compliance
+    regexp {^[[:alpha:]]+$} \u021f\u0220
 } {1}
 
 test utf-24.1 {TclUniCharIsDigit} {
-    # this returns 1 with Unicode 3 compliance
-    string is digit \u1040
+    # this returns 1 with Unicode 6 compliance
+    string is digit \u1040\uabf0
 } {1}
 test utf-24.2 {unicode digit char in regc_locale.c} {
-    # this returns 1 with Unicode 3 compliance
-    list [regexp {^[[:digit:]]+$} \u1040] [regexp {^\d+$} \u1040]
+    # this returns 1 with Unicode 6 compliance
+    list [regexp {^[[:digit:]]+$} \u1040\uabf0] [regexp {^\d+$} \u1040\uabf0]
 } {1 1}
 
 test utf-24.3 {TclUniCharIsSpace} {
-    # this returns 1 with Unicode 3 compliance
-    string is space \u1680
+    # this returns 1 with Unicode 6 compliance
+    string is space \u1680\u180e
 } {1}
 test utf-24.4 {unicode space char in regc_locale.c} {
-    # this returns 1 with Unicode 3 compliance
-    list [regexp {^[[:space:]]+$} \u1680] [regexp {^\s+$} \u1680]
+    # this returns 1 with Unicode 6 compliance
+    list [regexp {^[[:space:]]+$} \u1680\u180e] [regexp {^\s+$} \u1680\u180e]
 } {1 1}
 
 testConstraint teststringobj [llength [info commands teststringobj]]
diff --git a/tools/uniParse.tcl b/tools/uniParse.tcl
index a7f4237..0ec0848 100644
--- a/tools/uniParse.tcl
+++ b/tools/uniParse.tcl
@@ -4,12 +4,12 @@
 #	corresponding tclUniData.c file with compressed character
 #	data tables.  The input to this program should be the latest
 #	UnicodeData file from:
-#	    ftp://ftp.unicode.org/Public/UNIDATA/UnicodeData-Latest.txt
+#	    ftp://ftp.unicode.org/Public/UNIDATA/UnicodeData.txt
 #
 # Copyright (c) 1998-1999 by Scriptics Corporation.
 # All rights reserved.
 #
-# RCS: @(#) $Id: uniParse.tcl,v 1.8 2010/10/15 15:25:52 nijtmans Exp $
+# RCS: @(#) $Id: uniParse.tcl,v 1.9 2010/10/18 21:47:36 nijtmans Exp $
 
 
 namespace eval uni {
@@ -116,7 +116,11 @@ proc uni::buildTables {data} {
 
 	set items [split $line \;]
 
-	scan [lindex $items 0] %4x index
+	scan [lindex $items 0] %x index
+	if {$index > 0xFFFF} then {
+	    # Ignore non-BMP characters, as long as Tcl doesn't support them
+	    continue
+	}
 	set index [format 0x%0.4x $index]
 
 	set gIndex [getGroup [getValue $items $index]]
-- 
cgit v0.12