libbb: better unicode width support. Hopefully fixes bug 839.

Also opens up a possibility to make other unicode stuff smaller
and more correct later. but:

function                                             old     new   delta
static.combining                                       -     516    +516
bb_wcwidth                                             -     328    +328
unicode_cut_nchars                                     -     141    +141
mbstowc_internal                                       -      93     +93
in_table                                               -      78     +78
cal_main                                             899     961     +62
static.combining0x10000                                -      40     +40
unicode_strlen                                         -      31     +31
bb_mbstrlen                                           31       -     -31
bb_mbstowcs                                          173     102     -71
------------------------------------------------------------------------------
(add/remove: 7/1 grow/shrink: 1/1 up/down: 1289/-102)        Total: 1187 bytes

Uses code of Markus Kuhn, which is in public domain:
http://www.cl.cam.ac.uk/~mgk25/ucs/wcwidth.c
"Permission to use, copy, modify, and distribute this software
 for any purpose and without fee is hereby granted. The author
 disclaims all warranties with regard to this software."

Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>

4 files changed, 28 insertions, 12 deletions

diff --git a/coreutils/cal.c b/coreutils/cal.c
index e6f9af937..5ecb9131d 100644
--- a/coreutils/cal.c
+++ b/coreutils/cal.c
@@ -16,8 +16,8 @@
  *
  * Major size reduction... over 50% (>1.5k) on i386.
  */
-
 #include "libbb.h"
+#include "unicode.h"
 
 /* We often use "unsigned" intead of "int", it's easier to div on most CPUs */
 
@@ -83,9 +83,16 @@ int cal_main(int argc UNUSED_PARAM, char **argv)
         time_t now;
         unsigned month, year, flags, i;
         char *month_names[12];
-        char day_headings[28];  /* 28 for julian, 21 for nonjulian */
+        /* normal heading: */
+        /* "Su Mo Tu We Th Fr Sa" */
+        /* -j heading: */
+        /* " Su  Mo  Tu  We  Th  Fr  Sa" */
+        char day_headings[ENABLE_FEATURE_ASSUME_UNICODE ? 28 * 6 : 28];
+        IF_FEATURE_ASSUME_UNICODE(char *hp = day_headings;)
         char buf[40];
 
+        init_unicode();
+
         flags = getopt32(argv, "jy");
         /* This sets julian = flags & 1: */
         option_mask32 &= 1;
@@ -122,15 +129,24 @@ int cal_main(int argc UNUSED_PARAM, char **argv)
 
                 if (i < 7) {
                         zero_tm.tm_wday = i;
-//FIXME: unicode
-//Bug 839:
-//testcase with doublewidth Japanese chars: "LANG=zh_TW.utf8 cal"
-//perhaps use wc[s]width() to probe terminal width
                         /* abbreviated weekday name according to locale */
                         strftime(buf, sizeof(buf), "%a", &zero_tm);
+#if ENABLE_FEATURE_ASSUME_UNICODE
+                        if (julian)
+                                *hp++ = ' ';
+                        {
+                                char *two_wchars = unicode_cut_nchars(2, buf);
+                                strcpy(hp, two_wchars);
+                                free(two_wchars);
+                        }
+                        hp += strlen(hp);
+                        *hp++ = ' ';
+#else
                         strncpy(day_headings + i * (3+julian) + julian, buf, 2);
+#endif
                 }
         } while (++i < 12);
+        IF_FEATURE_ASSUME_UNICODE(hp[-1] = '\0';)
 
         if (month) {
                 unsigned row, len, days[MAXDAYS];
diff --git a/coreutils/df.c b/coreutils/df.c
index bcde78393..ae68f0831 100644
--- a/coreutils/df.c
+++ b/coreutils/df.c
@@ -178,7 +178,7 @@ int df_main(int argc UNUSED_PARAM, char **argv)
 #endif
 
 #if ENABLE_FEATURE_ASSUME_UNICODE
-                        dev_len = bb_mbstrlen(device);
+                        dev_len = unicode_strlen(device);
                         if (dev_len > 20) {
                                 printf("%s\n%20s", device, "");
                         } else {
diff --git a/coreutils/expand.c b/coreutils/expand.c
index 649b4c175..2f6a708b5 100644
--- a/coreutils/expand.c
+++ b/coreutils/expand.c
@@ -49,7 +49,7 @@ static void expand(FILE *file, unsigned tab_size, unsigned opt)
                                 unsigned len;
                                 *ptr = '\0';
 # if ENABLE_FEATURE_ASSUME_UNICODE
-                                len = bb_mbstrlen(ptr_strbeg);
+                                len = unicode_strlen(ptr_strbeg);
 # else
                                 len = ptr - ptr_strbeg;
 # endif
@@ -105,7 +105,7 @@ static void unexpand(FILE *file, unsigned tab_size, unsigned opt)
                                 char c;
                                 c = ptr[n];
                                 ptr[n] = '\0';
-                                len = bb_mbstrlen(ptr);
+                                len = unicode_strlen(ptr);
                                 ptr[n] = c;
                         }
 # else
diff --git a/coreutils/ls.c b/coreutils/ls.c
index b8da1adbb..e7544474b 100644
--- a/coreutils/ls.c
+++ b/coreutils/ls.c
@@ -550,7 +550,7 @@ static void showfiles(struct dnode **dn, unsigned nfiles)
         } else {
                 /* find the longest file name, use that as the column width */
                 for (i = 0; dn[i]; i++) {
-                        int len = bb_mbstrlen(dn[i]->name);
+                        int len = unicode_strlen(dn[i]->name);
                         if (column_width < len)
                                 column_width = len;
                 }
@@ -742,7 +742,7 @@ static int print_name(const char *name)
 {
         if (option_mask32 & OPT_Q) {
 #if ENABLE_FEATURE_ASSUME_UNICODE
-                unsigned len = 2 + bb_mbstrlen(name);
+                unsigned len = 2 + unicode_strlen(name);
 #else
                 unsigned len = 2;
 #endif
@@ -762,7 +762,7 @@ static int print_name(const char *name)
         /* No -Q: */
 #if ENABLE_FEATURE_ASSUME_UNICODE
         fputs(name, stdout);
-        return bb_mbstrlen(name);
+        return unicode_strlen(name);
 #else
         return printf("%s", name);
 #endif