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>

1 files changed, 7 insertions, 24 deletions

diff --git a/include/unicode.h b/include/unicode.h
index e11f2f9da..f1a252cc7 100644
--- a/include/unicode.h
+++ b/include/unicode.h
@@ -13,13 +13,16 @@ enum {
 
 #if !ENABLE_FEATURE_ASSUME_UNICODE
 
-# define bb_mbstrlen(string) strlen(string)
+# define unicode_strlen(string) strlen(string)
+# define unicode_scrlen(string) TODO
 # define unicode_status UNICODE_OFF
 # define init_unicode() ((void)0)
 
 #else
 
-size_t bb_mbstrlen(const char *string) FAST_FUNC;
+size_t FAST_FUNC unicode_strlen(const char *string);
+char* FAST_FUNC unicode_cut_nchars(unsigned width, const char *src);
+unsigned FAST_FUNC unicode_padding_to_width(unsigned width, const char *src);
 
 # if ENABLE_LOCALE_SUPPORT
 
@@ -30,7 +33,7 @@ void init_unicode(void) FAST_FUNC;
 
 # else
 
-/* Crude "locale support" which knows only C and Unicode locales */
+/* Homegrown Unicode support. It knows only C and Unicode locales. */
 
 #  if !ENABLE_FEATURE_CHECK_UNICODE_IN_ENV
 #   define unicode_status UNICODE_ON
@@ -52,6 +55,7 @@ void init_unicode(void) FAST_FUNC;
 #  define iswspace  bb_iswspace
 #  define iswalnum  bb_iswalnum
 #  define iswpunct  bb_iswpunct
+#  define wcwidth   bb_wcwidth
 
 typedef int32_t wint_t;
 typedef struct {
@@ -68,27 +72,6 @@ int iswpunct(wint_t wc) FAST_FUNC;
 
 # endif /* !LOCALE_SUPPORT */
 
-
-# if 0 /* TODO: better support for printfing Unicode fields: */
-
-/* equivalent to printf("%-20.20s", str) */
-char unicode_buffer[20 * MB_CUR_MAX];
-printf("%s", unicode_exact(20, str, unicode_buffer);
-/* no need to free() anything */
-
-/* equivalent to printf("%-20s", str) */
-char *malloced = unicode_minimum(20, str);
-printf("%s", malloced);
-free(malloced); /* ugh */
-
-/* equivalent to printf("%-20s", str), better one */
-printf("%s%*s", str, unicode_pad_to_width(str, 20), "");
-/* equivalent to printf("%20s", str) */
-printf("%*s%s", unicode_pad_to_width(str, 20), "", str);
-
-# endif
-
-
 #endif /* FEATURE_ASSUME_UNICODE */
 
 #endif