src/utf8.c

   1 /* Charset handling for GNU tar.
   2
   3    Copyright 2004-2024 Free Software Foundation, Inc.
   4
   5    This file is part of GNU tar.
   6
   7    GNU tar is free software; you can redistribute it and/or modify
   8    it under the terms of the GNU General Public License as published by
   9    the Free Software Foundation; either version 3 of the License, or
  10    (at your option) any later version.
  11
  12    GNU tar is distributed in the hope that it will be useful,
  13    but WITHOUT ANY WARRANTY; without even the implied warranty of
  14    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  15    GNU General Public License for more details.
  16
  17    You should have received a copy of the GNU General Public License
  18    along with this program.  If not, see <http://www.gnu.org/licenses/>.  */
  19
  20 #include <system.h>
  21 #include <quotearg.h>
  22 #include <localcharset.h>
  23 #include "common.h"
  24 #ifdef HAVE_ICONV_H
  25 # include <iconv.h>
  26 #endif
  27
  28 #ifndef ICONV_CONST
  29 # define ICONV_CONST
  30 #endif
  31
  32 #ifndef HAVE_ICONV
  33
  34 # undef iconv_open
  35 # define iconv_open(tocode, fromcode) ((iconv_t) -1)
  36
  37 # undef iconv
  38 # define iconv(cd, inbuf, inbytesleft, outbuf, outbytesleft) (errno = ENOSYS, (size_t) -1)
  39
  40 # undef iconv_close
  41 # define iconv_close(cd) 0
  42
  43 # undef iconv_t
  44 # define iconv_t int
  45
  46 #endif
  47
  48
  49 \f
  50
  51 static iconv_t conv_desc[2] = { (iconv_t) -1, (iconv_t) -1 };
  52
  53 static iconv_t
  54 utf8_init (bool to_utf)
  55 {
  56   if (conv_desc[(int) to_utf] == (iconv_t) -1)
  57     {
  58       if (to_utf)
  59         conv_desc[(int) to_utf] = iconv_open ("UTF-8", locale_charset ());
  60       else
  61         conv_desc[(int) to_utf] = iconv_open (locale_charset (), "UTF-8");
  62     }
  63   return conv_desc[(int) to_utf];
  64 }
  65
  66 bool
  67 utf8_convert (bool to_utf, char const *input, char **output)
  68 {
  69   char ICONV_CONST *ib;
  70   char *ob, *ret;
  71   size_t inlen;
  72   size_t outlen;
  73   iconv_t cd = utf8_init (to_utf);
  74
  75   if (cd == 0)
  76     {
  77       *output = xstrdup (input);
  78       return true;
  79     }
  80   else if (cd == (iconv_t)-1)
  81     return false;
  82
  83   inlen = strlen (input) + 1;
  84   outlen = inlen * MB_LEN_MAX + 1;
  85   ob = ret = xmalloc (outlen);
  86   ib = (char ICONV_CONST *) input;
  87   /* According to POSIX, "if iconv() encounters a character in the input
  88      buffer that is valid, but for which an identical character does not
  89      exist in the target codeset, iconv() shall perform an
  90      implementation-defined conversion on this character." It will "update
  91      the variables pointed to by the arguments to reflect the extent of the
  92      conversion and return the number of non-identical conversions performed".
  93      On error, it returns -1.
  94      In other words, non-zero return always indicates failure, either because
  95      the input was not fully converted, or because it was converted in a
  96      non-reversible way.
  97    */
  98   if (iconv (cd, &ib, &inlen, &ob, &outlen) != 0)
  99     {
 100       free (ret);
 101       return false;
 102     }
 103   *ob = 0;
 104   *output = ret;
 105   return true;
 106 }
 107 \f
 108
 109 bool
 110 string_ascii_p (char const *p)
 111 {
 112   for (; *p; p++)
 113     if (*p & ~0x7f)
 114       return false;
 115   return true;
 116 }