lib/utf8.c

   1 /*
   2  * Copyright (c) 2015 Ingo Schwarze <schwarze@openbsd.org>
   3  * Copyright (c) 2018 Stefan Sperling <stsp@openbsd.org>
   4  *
   5  * Permission to use, copy, modify, and distribute this software for any
   6  * purpose with or without fee is hereby granted, provided that the above
   7  * copyright notice and this permission notice appear in all copies.
   8  *
   9  * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
  10  * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
  11  * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
  12  * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
  13  * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
  14  * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
  15  * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
  16  */
  17
  18 #include <sys/types.h>
  19
  20 #include <err.h>
  21 #include <stdlib.h>
  22 #include <string.h>
  23 #include <wchar.h>
  24 #include <langinfo.h>
  25
  26 #include "got_compat.h"
  27
  28 #include "got_error.h"
  29 #include "got_utf8.h"
  30
  31 const struct got_error *
  32 got_mbsavis(char** outp, int *widthp, const char *mbs)
  33 {
  34         const char *src;  /* Iterate mbs. */
  35         char     *dst;  /* Iterate *outp. */
  36         wchar_t   wc;
  37         int       total_width;  /* Display width of the whole string. */
  38         int       width;  /* Display width of a single Unicode char. */
  39         int       len;  /* Length in bytes of UTF-8 encoded string. */
  40
  41         len = strlen(mbs);
  42         if ((*outp = malloc(len + 1)) == NULL)
  43                 return got_error_from_errno("malloc");
  44
  45         if (MB_CUR_MAX == 1) {
  46                 memcpy(*outp, mbs, len + 1);
  47                 *widthp = len;
  48                 return NULL;
  49         }
  50
  51         src = mbs;
  52         dst = *outp;
  53         total_width = 0;
  54         while (*src != '\0') {
  55                 if ((len = mbtowc(&wc, src, MB_CUR_MAX)) == -1) {
  56                         total_width++;
  57                         *dst++ = '?';
  58                         src++;
  59                 } else if ((width = wcwidth(wc)) == -1) {
  60                         total_width++;
  61                         *dst++ = '?';
  62                         src += len;
  63                 } else {
  64                         total_width += width;
  65                         while (len-- > 0)
  66                                 *dst++ = *src++;
  67                 }
  68         }
  69         *dst = '\0';
  70         *widthp = total_width;
  71         return NULL;
  72 }
  73
  74 int
  75 got_locale_is_utf8(void)
  76 {
  77         char *codeset = nl_langinfo(CODESET);
  78         return (strcmp(codeset, "UTF-8") == 0);
  79 }