A new option is added, called "cjkwidth [on|off]". When it

is enabled, it treats CJK ambiguous characters as full width.
This feature is very helpful for reading legacy CJK applications'
output which assume all CJK characters are full width.
This option is default off.

The patch is obtained from
http://www.mhsin.org/~mhsin/patches/screen/patch-cjkwidth
The credit belongs to Michael Hsin <mhsin _at mhsin.org>.
It also has been submitted to upstream:
http://savannah.gnu.org/bugs/?func=detailitem&item_id=16666

PR:		ports/96167
Submitted by:	rafan
Approved by:	maintainer timeout (3 months and 2 weeks)

2 files changed, 232 insertions, 0 deletions

diff --git a/sysutils/screen/Makefile b/sysutils/screen/Makefile
index 7cdb328035b4..68ed1d61f77e 100644
--- a/sysutils/screen/Makefile
+++ b/sysutils/screen/Makefile
@@ -40,6 +40,11 @@ CFLAGS+=	-DCOLORS256
 CFLAGS+=	-DNONETHACK
 .endif
 
+# treat CJK ambiguous characters as full width via option "cjkwidth"
+.if defined(WITH_CJK)
+EXTRA_PATCHES+=	${.CURDIR}/files/opt-cjkwidth
+.endif
+
 post-patch:
 	@${RM} ${WRKSRC}/doc/screen.info*
 
diff --git a/sysutils/screen/files/opt-cjkwidth b/sysutils/screen/files/opt-cjkwidth
new file mode 100644
index 000000000000..69a6deef495c
--- /dev/null
+++ b/sysutils/screen/files/opt-cjkwidth
@@ -0,0 +1,227 @@
+--- ansi.c.orig	Tue Jun 17 08:00:47 2003
++++ ansi.c	Wed Jun 18 00:55:21 2003
+@@ -701,7 +701,7 @@
+ 	      curr->w_rend.font = 0;
+ 	    }
+ #  ifdef DW_CHARS
+-	  if (curr->w_encoding == UTF8 && c >= 0x1100 && utf8_isdouble(c))
++	  if (curr->w_encoding == UTF8 && utf8_isdouble(c))
+ 	    curr->w_mbcs = 0xff;
+ #  endif
+ 	  if (curr->w_encoding == UTF8 && c >= 0x0300 && utf8_iscomb(c))
+--- comm.c.orig	Mon Sep  8 22:25:08 2003
++++ comm.c	Fri May  6 19:06:12 2005
+@@ -112,6 +112,9 @@
+ #endif
+   { "charset",          NEED_FORE|ARGS_1 },
+   { "chdir",		ARGS_01 },
++#ifdef DW_CHARS
++  { "cjkwidth",		ARGS_01 },
++#endif
+   { "clear",		NEED_FORE|ARGS_0 },
+   { "colon",		NEED_LAYER|ARGS_01 },
+   { "command",		NEED_DISPLAY|ARGS_02 },
+--- encoding.c.orig	Mon Sep  8 22:25:23 2003
++++ encoding.c	Fri May  6 20:05:24 2005
+@@ -35,6 +35,10 @@
+ 
+ extern char *screenencodings;
+ 
++#ifdef DW_CHARS
++extern int cjkwidth;
++#endif
++
+ static int  encmatch __P((char *, char *));
+ # ifdef UTF8
+ static int   recode_char __P((int, int, int));
+@@ -845,22 +849,107 @@
+ }
+ 
+ #ifdef DW_CHARS
++struct interval {
++  int first;
++  int last;
++};
++
++/* auxiliary function for binary search in interval table */
++static int bisearch(int ucs, const struct interval *table, int max) {
++  int min = 0;
++  int mid;
++
++  if (ucs < table[0].first || ucs > table[max].last)
++    return 0;
++  while (max >= min) {
++    mid = (min + max) / 2;
++    if (ucs > table[mid].last)
++      min = mid + 1;
++    else if (ucs < table[mid].first)
++      max = mid - 1;
++    else
++      return 1;
++  }
++
++  return 0;
++}
++
+ int
+ utf8_isdouble(c)
+ int c;
+ {
+-  return
+-    (c >= 0x1100 &&
+-     (c <= 0x115f ||                    /* Hangul Jamo init. consonants */
+-      (c >= 0x2e80 && c <= 0xa4cf && (c & ~0x0011) != 0x300a &&
+-       c != 0x303f) ||                  /* CJK ... Yi */
+-      (c >= 0xac00 && c <= 0xd7a3) || /* Hangul Syllables */
+-      (c >= 0xdf00 && c <= 0xdfff) || /* dw combining sequence */
+-      (c >= 0xf900 && c <= 0xfaff) || /* CJK Compatibility Ideographs */
+-      (c >= 0xfe30 && c <= 0xfe6f) || /* CJK Compatibility Forms */
+-      (c >= 0xff00 && c <= 0xff5f) || /* Fullwidth Forms */
+-      (c >= 0xffe0 && c <= 0xffe6) ||
+-      (c >= 0x20000 && c <= 0x2ffff)));
++  /* sorted list of non-overlapping intervals of East Asian Ambiguous
++   * characters, generated by "uniset +WIDTH-A -cat=Me -cat=Mn -cat=Cf c" */
++  static const struct interval ambiguous[] = {
++    { 0x00A1, 0x00A1 }, { 0x00A4, 0x00A4 }, { 0x00A7, 0x00A8 },
++    { 0x00AA, 0x00AA }, { 0x00AE, 0x00AE }, { 0x00B0, 0x00B4 },
++    { 0x00B6, 0x00BA }, { 0x00BC, 0x00BF }, { 0x00C6, 0x00C6 },
++    { 0x00D0, 0x00D0 }, { 0x00D7, 0x00D8 }, { 0x00DE, 0x00E1 },
++    { 0x00E6, 0x00E6 }, { 0x00E8, 0x00EA }, { 0x00EC, 0x00ED },
++    { 0x00F0, 0x00F0 }, { 0x00F2, 0x00F3 }, { 0x00F7, 0x00FA },
++    { 0x00FC, 0x00FC }, { 0x00FE, 0x00FE }, { 0x0101, 0x0101 },
++    { 0x0111, 0x0111 }, { 0x0113, 0x0113 }, { 0x011B, 0x011B },
++    { 0x0126, 0x0127 }, { 0x012B, 0x012B }, { 0x0131, 0x0133 },
++    { 0x0138, 0x0138 }, { 0x013F, 0x0142 }, { 0x0144, 0x0144 },
++    { 0x0148, 0x014B }, { 0x014D, 0x014D }, { 0x0152, 0x0153 },
++    { 0x0166, 0x0167 }, { 0x016B, 0x016B }, { 0x01CE, 0x01CE },
++    { 0x01D0, 0x01D0 }, { 0x01D2, 0x01D2 }, { 0x01D4, 0x01D4 },
++    { 0x01D6, 0x01D6 }, { 0x01D8, 0x01D8 }, { 0x01DA, 0x01DA },
++    { 0x01DC, 0x01DC }, { 0x0251, 0x0251 }, { 0x0261, 0x0261 },
++    { 0x02C4, 0x02C4 }, { 0x02C7, 0x02C7 }, { 0x02C9, 0x02CB },
++    { 0x02CD, 0x02CD }, { 0x02D0, 0x02D0 }, { 0x02D8, 0x02DB },
++    { 0x02DD, 0x02DD }, { 0x02DF, 0x02DF }, { 0x0391, 0x03A1 },
++    { 0x03A3, 0x03A9 }, { 0x03B1, 0x03C1 }, { 0x03C3, 0x03C9 },
++    { 0x0401, 0x0401 }, { 0x0410, 0x044F }, { 0x0451, 0x0451 },
++    { 0x2010, 0x2010 }, { 0x2013, 0x2016 }, { 0x2018, 0x2019 },
++    { 0x201C, 0x201D }, { 0x2020, 0x2022 }, { 0x2024, 0x2027 },
++    { 0x2030, 0x2030 }, { 0x2032, 0x2033 }, { 0x2035, 0x2035 },
++    { 0x203B, 0x203B }, { 0x203E, 0x203E }, { 0x2074, 0x2074 },
++    { 0x207F, 0x207F }, { 0x2081, 0x2084 }, { 0x20AC, 0x20AC },
++    { 0x2103, 0x2103 }, { 0x2105, 0x2105 }, { 0x2109, 0x2109 },
++    { 0x2113, 0x2113 }, { 0x2116, 0x2116 }, { 0x2121, 0x2122 },
++    { 0x2126, 0x2126 }, { 0x212B, 0x212B }, { 0x2153, 0x2154 },
++    { 0x215B, 0x215E }, { 0x2160, 0x216B }, { 0x2170, 0x2179 },
++    { 0x2190, 0x2199 }, { 0x21B8, 0x21B9 }, { 0x21D2, 0x21D2 },
++    { 0x21D4, 0x21D4 }, { 0x21E7, 0x21E7 }, { 0x2200, 0x2200 },
++    { 0x2202, 0x2203 }, { 0x2207, 0x2208 }, { 0x220B, 0x220B },
++    { 0x220F, 0x220F }, { 0x2211, 0x2211 }, { 0x2215, 0x2215 },
++    { 0x221A, 0x221A }, { 0x221D, 0x2220 }, { 0x2223, 0x2223 },
++    { 0x2225, 0x2225 }, { 0x2227, 0x222C }, { 0x222E, 0x222E },
++    { 0x2234, 0x2237 }, { 0x223C, 0x223D }, { 0x2248, 0x2248 },
++    { 0x224C, 0x224C }, { 0x2252, 0x2252 }, { 0x2260, 0x2261 },
++    { 0x2264, 0x2267 }, { 0x226A, 0x226B }, { 0x226E, 0x226F },
++    { 0x2282, 0x2283 }, { 0x2286, 0x2287 }, { 0x2295, 0x2295 },
++    { 0x2299, 0x2299 }, { 0x22A5, 0x22A5 }, { 0x22BF, 0x22BF },
++    { 0x2312, 0x2312 }, { 0x2460, 0x24E9 }, { 0x24EB, 0x254B },
++    { 0x2550, 0x2573 }, { 0x2580, 0x258F }, { 0x2592, 0x2595 },
++    { 0x25A0, 0x25A1 }, { 0x25A3, 0x25A9 }, { 0x25B2, 0x25B3 },
++    { 0x25B6, 0x25B7 }, { 0x25BC, 0x25BD }, { 0x25C0, 0x25C1 },
++    { 0x25C6, 0x25C8 }, { 0x25CB, 0x25CB }, { 0x25CE, 0x25D1 },
++    { 0x25E2, 0x25E5 }, { 0x25EF, 0x25EF }, { 0x2605, 0x2606 },
++    { 0x2609, 0x2609 }, { 0x260E, 0x260F }, { 0x2614, 0x2615 },
++    { 0x261C, 0x261C }, { 0x261E, 0x261E }, { 0x2640, 0x2640 },
++    { 0x2642, 0x2642 }, { 0x2660, 0x2661 }, { 0x2663, 0x2665 },
++    { 0x2667, 0x266A }, { 0x266C, 0x266D }, { 0x266F, 0x266F },
++    { 0x273D, 0x273D }, { 0x2776, 0x277F }, { 0xE000, 0xF8FF },
++    { 0xFFFD, 0xFFFD }, { 0xF0000, 0xFFFFD }, { 0x100000, 0x10FFFD }
++  };
++
++  return ((c >= 0x1100 &&
++           (c <= 0x115f ||                    /* Hangul Jamo init. consonants */
++            c == 0x2329 || c == 0x232a ||
++            (c >= 0x2e80 && c <= 0xa4cf &&
++             c != 0x303f) ||                  /* CJK ... Yi */
++            (c >= 0xac00 && c <= 0xd7a3) || /* Hangul Syllables */
++            (c >= 0xf900 && c <= 0xfaff) || /* CJK Compatibility Ideographs */
++            (c >= 0xfe30 && c <= 0xfe6f) || /* CJK Compatibility Forms */
++            (c >= 0xff00 && c <= 0xff60) || /* Fullwidth Forms */
++            (c >= 0xffe0 && c <= 0xffe6) ||
++            (c >= 0x20000 && c <= 0x2fffd) ||
++            (c >= 0x30000 && c <= 0x3fffd))) ||
++          (cjkwidth &&
++           bisearch(c, ambiguous,
++	            sizeof(ambiguous) / sizeof(struct interval) - 1)));
+ }
+ #endif
+ 
+--- process.c.orig	Thu Sep 18 20:53:54 2003
++++ process.c	Fri May  6 19:43:53 2005
+@@ -103,6 +103,9 @@
+ #ifdef UTF8
+ extern char *screenencodings;
+ #endif
++#ifdef DW_CHARS
++extern int cjkwidth;
++#endif
+ 
+ static int  CheckArgNum __P((int, char **));
+ static void ClearAction __P((struct action *));
+@@ -3821,6 +3824,15 @@
+ 	    Msg(0, "idle off");
+ 	}
+       break;
++#ifdef DW_CHARS
++    case RC_CJKWIDTH:
++      if(ParseSwitch(act, &cjkwidth) == 0)
++      {
++        if(msgok)
++          Msg(0, "Treat ambiguous width characters as %s width", cjkwidth ? "full" : "half");
++      }
++      break;
++#endif
+     default:
+ #ifdef HAVE_BRAILLE
+       /* key == -2: input from braille keybord, msgok always 0 */
+--- screen.c.orig	Mon Sep  8 22:26:41 2003
++++ screen.c	Sat May  7 05:16:38 2005
+@@ -221,6 +221,10 @@
+ char *screenencodings;
+ #endif
+ 
++#ifdef DW_CHARS
++int cjkwidth;
++#endif
++
+ #ifdef NETHACK
+ int nethackflag = 0;
+ #endif
+@@ -468,6 +472,9 @@
+   InitBuiltinTabs();
+   screenencodings = SaveStr(SCREENENCODINGS);
+ #endif
++#ifdef DW_CHARS
++  cjkwidth = 0;
++#endif
+   nwin = nwin_undef;
+   nwin_options = nwin_undef;
+   strcpy(screenterm, "screen");
+@@ -762,6 +769,19 @@
+       debug1("environment says encoding=%d\n", nwin_options.encoding);
+ #endif
+     }
++# ifdef DW_CHARS
++  {
++    char *s;
++    if((s = getenv("LC_ALL")) || (s = getenv("LC_CTYPE")) ||
++       (s = getenv("LANG")))
++    {
++      if(!strncmp(s, "zh_", 3) || !strncmp(s, "ja_", 3) || !strncmp(s, "ko_", 3))
++      {
++        cjkwidth = 1;
++      }
++    }
++  }
++#endif
+ #endif
+   if (SockMatch && strlen(SockMatch) >= MAXSTR)
+     Panic(0, "Ridiculously long socketname - try again.");