[slang-users] [Patch] Use of glibc wcwidth

["cedre.m" <cedre.m@xxxxxxxxx>]

Hello, I am Japanese centos user.
I use slang library(ntsysv, system-config-*). Thank you.

This patch resolves unicode ambiguous width problem, by wcwidth(glibc).

http://www.unicode.org/reports/tr11/#Ambiguous
http://mediasrv.ns.ac.yu/unicode/www.unicode.org/unicode/reports/tr11-4/index.htm
http://www.stained-g.net/shinichiro/unicode5-ambiguous-width.html
http://people.debian.org/~kubota/unicode-symbols-width2.html.en

--
Sugiyama
cedre.m@xxxxxxxxx

# using glibc wcwidth instead of slwcwidth.
# cedre.m@xxxxxxxxx
diff -urN slang-2.1.3/autoconf/configure.ac slang-2.1.3-wcwidth/autoconf/configure.ac
--- slang-2.1.3/autoconf/configure.ac	2007-08-30 03:54:49.000000000 +0900
+++ slang-2.1.3-wcwidth/autoconf/configure.ac	2008-03-04 19:08:17.000000000 +0900
@@ -220,6 +220,21 @@
 AC_SUBST(GNU_READLINE)
 AC_SUBST(LIB_READLINE)
 
+gnu_wcwidth=unknown
+AC_ARG_WITH([gnu-wcwidth],
+  [  --without-gnu-wcwidth         Don't use the glibc wcwidth.],
+  gnu_wcwidth=$withval)
+
+if test "$gnu_wcwidth" != "no"; then
+  AC_EGREP_CPP(yes,[
+#include <features.h>
+#include <wchar.h>
+#if defined(__GLIBC__) && defined(_WCHAR_H) && defined(__STDC_ISO_10646__)
+yes
+#endif
+],AC_DEFINE(HAVE_GNU_WCWIDTH,1,[Define if you want glibc wcwidth.]))
+fi
+
 JD_GET_MODULES(src/modules.unx)
 JD_CREATE_MODULE_ORULES
 
diff -urN slang-2.1.3/src/config.hin slang-2.1.3-wcwidth/src/config.hin
--- slang-2.1.3/src/config.hin	2007-08-30 12:29:28.000000000 +0900
+++ slang-2.1.3-wcwidth/src/config.hin	2008-03-04 19:08:17.000000000 +0900
@@ -78,6 +78,8 @@
 
 #undef HAVE_SYS_MMAN_H
 
+#undef HAVE_GNU_WCWIDTH
+
 /* Set these to the appropriate values */
 #undef SIZEOF_SHORT
 #undef SIZEOF_INT
diff -urN slang-2.1.3/src/slsmg.c slang-2.1.3-wcwidth/src/slsmg.c
--- slang-2.1.3/src/slsmg.c	2007-10-14 03:34:10.000000000 +0900
+++ slang-2.1.3-wcwidth/src/slsmg.c	2008-03-04 19:08:17.000000000 +0900
@@ -214,44 +214,46 @@
    unsigned char vt100_char;
    unsigned char ascii;
    SLwchar_Type unicode;
+   SLwchar_Type unicode_not_ambiguous; // not_wide ?
 }
 ACS_Def_Type;
 
 static SLCONST ACS_Def_Type UTF8_ACS_Map[] =
 {
-   {'+', '>', 0x2192 }, /* RIGHTWARDS ARROW */
-   {',', '<', 0x2190 }, /* LEFTWARDS ARROW */
-   {'-', '^', 0x2191 }, /* UPWARDS ARROW */
-   {'.', 'v', 0x2193 }, /* DOWNWARDS ARROW */
-   {'0', '#', 0x25AE }, /* BLACK VERTICAL RECTANGLE */
-   {'`', '+', 0x25C6 }, /* BLACK DIAMOND */
-   {'a', ':', 0x2592 }, /* MEDIUM SHADE */
-   {'f', '\'', 0x00B0 },/* DEGREE SIGN */
-   {'g', '#', 0x00B1 }, /* PLUS-MINUS SIGN */
-   {'h', '#', 0x2592 }, /* MEDIUM SHADE */
-   {'i', '#', 0x2603 }, /* SNOWMAN */
-   {'j', '+', 0x2518 }, /* BOX DRAWINGS LIGHT UP AND LEFT */
-   {'k', '+', 0x2510 }, /* BOX DRAWINGS LIGHT DOWN AND LEFT */
-   {'l', '+', 0x250c }, /* BOX DRAWINGS LIGHT DOWN AND RIGHT */
-   {'m', '+', 0x2514 }, /* BOX DRAWINGS LIGHT UP AND RIGHT */
-   {'n', '+', 0x253C }, /* BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL */
-   {'o', '~', 0x23BA }, /* HORIZONTAL SCAN LINE-1 */
-   {'p', '-', 0x23BB }, /* HORIZONTAL SCAN LINE-3 (ncurses addition) */
-   {'q', '-', 0x2500 }, /* BOX DRAWINGS LIGHT HORIZONTAL */
-   {'r', '-', 0x23BC }, /* HORIZONTAL SCAN LINE-7 (ncurses addition) */
-   {'s', '_', 0x23BD }, /* HORIZONTAL SCAN LINE-9 */
-   {'t', '+', 0x251C }, /* BOX DRAWINGS LIGHT VERTICAL AND RIGHT */
-   {'u', '+', 0x2524 }, /* BOX DRAWINGS LIGHT VERTICAL AND LEFT */
-   {'v', '+', 0x2534 }, /* BOX DRAWINGS LIGHT UP AND HORIZONTAL */
-   {'w', '+', 0x252C }, /* BOX DRAWINGS LIGHT DOWN AND HORIZONTAL */
-   {'x', '|', 0x2502 }, /* BOX DRAWINGS LIGHT VERTICAL */
-   {'y', '<', 0x2264 }, /* LESS-THAN OR EQUAL TO (ncurses addition) */
-   {'z', '>', 0x2265 }, /* GREATER-THAN OR EQUAL TO (ncurses addition) */
-   {'{', '*', 0x03C0 }, /* GREEK SMALL LETTER PI (ncurses addition) */
-   {'|', '!', 0x2260 }, /* NOT EQUAL TO (ncurses addition) */
-   {'}', 'f', 0x00A3 }, /* POUND SIGN (ncurses addition) */
-   {'~', 'o', 0x00B7 }, /* MIDDLE DOT */
-   {0, 0, 0}
+   {'+', '>', 0x2192, 0}, /* RIGHTWARDS ARROW [A/21AA] */
+   {',', '<', 0x2190, 0}, /* LEFTWARDS ARROW [A/21A9] */
+   {'-', '^', 0x2191, 0x2303}, /* UPWARDS ARROW [A/2303] */
+   {'.', 'v', 0x2193, 0x2304}, /* DOWNWARDS ARROW [A/2304] */
+   {'0', '#', 0x25AE, 0},      /* BLACK VERTICAL RECTANGLE */
+   {'`', '+', 0x25C6, 0x2666}, /* BLACK DIAMOND [BLACK DIAMOND SUIT] */
+   {'a', ':', 0x2592, 0},      /* MEDIUM SHADE [A]. */
+   {'f', '\'', 0x00B0, 0xFF9F},/* DEGREE SIGN
+                                [HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK] */
+   {'g', '#', 0x00B1, 0}, /* PLUS-MINUS SIGN [A]. */
+   {'h', '#', 0x2592, 0}, /* MEDIUM SHADE [A]. */
+   {'i', '#', 0x2603, 0}, /* SNOWMAN [N] */
+   {'j', '+', 0x2518, 0}, /* BOX DRAWINGS LIGHT UP AND LEFT [A] */
+   {'k', '+', 0x2510, 0}, /* BOX DRAWINGS LIGHT DOWN AND LEFT [A] */
+   {'l', '+', 0x250c, 0}, /* BOX DRAWINGS LIGHT DOWN AND RIGHT [A] */
+   {'m', '+', 0x2514, 0}, /* BOX DRAWINGS LIGHT UP AND RIGHT [A] */
+   {'n', '+', 0x253C, 0}, /* BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL [A] */
+   {'o', '~', 0x23BA, 0}, /* HORIZONTAL SCAN LINE-1 [N] */
+   {'p', '-', 0x23BB, 0}, /* HORIZONTAL SCAN LINE-3 (ncurses addition) [N] */
+   {'q', '-', 0x2500, 0}, /* BOX DRAWINGS LIGHT HORIZONTAL [A] */
+   {'r', '-', 0x23BC, 0}, /* HORIZONTAL SCAN LINE-7 (ncurses addition) [N] */
+   {'s', '_', 0x23BD, 0}, /* HORIZONTAL SCAN LINE-9 [N] */
+   {'t', '+', 0x251C, 0}, /* BOX DRAWINGS LIGHT VERTICAL AND RIGHT [A] */
+   {'u', '+', 0x2524, 0}, /* BOX DRAWINGS LIGHT VERTICAL AND LEFT [A] */
+   {'v', '+', 0x2534, 0}, /* BOX DRAWINGS LIGHT UP AND HORIZONTAL [A] */
+   {'w', '+', 0x252C, 0}, /* BOX DRAWINGS LIGHT DOWN AND HORIZONTAL [A] */
+   {'x', '|', 0x2502, 0}, /* BOX DRAWINGS LIGHT VERTICAL [A] */
+   {'y', '<', 0x2264, 0}, /* LESS-THAN OR EQUAL TO (ncurses addition) [A]. */
+   {'z', '>', 0x2265, 0}, /* GREATER-THAN OR EQUAL TO (ncurses addition) [A] */
+   {'{', '*', 0x03C0, 0}, /* GREEK SMALL LETTER PI (ncurses addition) [A]. */
+   {'|', '!', 0x2260, 0}, /* NOT EQUAL TO (ncurses addition) [A]. */
+   {'}', 'f', 0x00A3, 0}, /* POUND SIGN (ncurses addition) [N] */
+   {'~', 'o', 0x00B7, 0xFF65},/* MIDDLE DOT [HALFWIDTH KATAKANA MIDDLE DOT] */
+   {0, 0, 0, 0}
 };
 
 #define ACS_MODE_NONE	       -1
@@ -288,7 +290,12 @@
 	acs = UTF8_ACS_Map;
 	while (acs->vt100_char != 0)
 	  {
-	     ACS_Map[acs->vt100_char] = acs->unicode;
+	     if (SLwchar_wcwidth(acs->unicode) == 1)
+	       ACS_Map[acs->vt100_char] = acs->unicode;
+	     else if (acs->unicode_not_ambiguous)
+	       ACS_Map[acs->vt100_char] = acs->unicode_not_ambiguous;
+	     else
+	       ACS_Map[acs->vt100_char] = acs->ascii;
 	     acs++;
 	  }
 	break;
diff -urN slang-2.1.3/src/slwcwidth.c slang-2.1.3-wcwidth/src/slwcwidth.c
--- slang-2.1.3/src/slwcwidth.c	2007-01-11 01:09:07.000000000 +0900
+++ slang-2.1.3-wcwidth/src/slwcwidth.c	2008-03-04 19:08:17.000000000 +0900
@@ -24,8 +24,13 @@
 #include "slang.h"
 #include "_slang.h"
 
+#ifndef HAVE_GNU_WCWIDTH
 #define DEFINE_PSLWC_WIDTH_TABLE
 #include "slwcwidth.h"
+#else
+#include <wchar.h>
+#define SL_WIDTH_ALOOKUP(y,x) y = wcwidth((wchar_t)x)
+#endif
 
 static int Ignore_Double_Width = 0;
 int SLwchar_wcwidth (SLwchar_Type ch)