src/utf8.c

   1 /* Charset handling for GNU tar.
   2
   3    Copyright 2004, 2006-2007, 2013-2014, 2016-2017 Free Software
   4    Foundation, Inc.
   5
   6    This file is part of GNU tar.
   7
   8    GNU tar is free software; you can redistribute it and/or modify
   9    it under the terms of the GNU General Public License as published by
  10    the Free Software Foundation; either version 3 of the License, or
  11    (at your option) any later version.
  12
  13    GNU tar is distributed in the hope that it will be useful,
  14    but WITHOUT ANY WARRANTY; without even the implied warranty of
  15    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  16    GNU General Public License for more details.
  17
  18    You should have received a copy of the GNU General Public License
  19    along with this program.  If not, see <http://www.gnu.org/licenses/>.  */
  20
  21 #include <system.h>
  22 #include <quotearg.h>
  23 #include <localcharset.h>
  24 #include "common.h"
  25 #ifdef HAVE_ICONV_H
  26 # include <iconv.h>
  27 #endif
  28
  29 #ifndef ICONV_CONST
  30 # define ICONV_CONST
  31 #endif
  32
  33 #ifndef HAVE_ICONV
  34
  35 # undef iconv_open
  36 # define iconv_open(tocode, fromcode) ((iconv_t) -1)
  37
  38 # undef iconv
  39 # define iconv(cd, inbuf, inbytesleft, outbuf, outbytesleft) ((size_t) 0)
  40
  41 # undef iconv_close
  42 # define iconv_close(cd) 0
  43
  44 #endif
  45
  46
  47 \f
  48
  49 static iconv_t conv_desc[2] = { (iconv_t) -1, (iconv_t) -1 };
  50
  51 static iconv_t
  52 utf8_init (bool to_utf)
  53 {
  54   if (conv_desc[(int) to_utf] == (iconv_t) -1)
  55     {
  56       if (to_utf)
  57         conv_desc[(int) to_utf] = iconv_open ("UTF-8", locale_charset ());
  58       else
  59         conv_desc[(int) to_utf] = iconv_open (locale_charset (), "UTF-8");
  60     }
  61   return conv_desc[(int) to_utf];
  62 }
  63
  64 bool
  65 utf8_convert (bool to_utf, char const *input, char **output)
  66 {
  67   char ICONV_CONST *ib;
  68   char *ob;
  69   size_t inlen;
  70   size_t outlen;
  71   size_t rc;
  72   iconv_t cd = utf8_init (to_utf);
  73
  74   if (cd == 0)
  75     {
  76       *output = xstrdup (input);
  77       return true;
  78     }
  79   else if (cd == (iconv_t)-1)
  80     return false;
  81
  82   inlen = strlen (input) + 1;
  83   outlen = inlen * MB_LEN_MAX + 1;
  84   ob = *output = xmalloc (outlen);
  85   ib = (char ICONV_CONST *) input;
  86   rc = iconv (cd, &ib, &inlen, &ob, &outlen);
  87   *ob = 0;
  88   return rc != -1;
  89 }
  90 \f
  91
  92 bool
  93 string_ascii_p (char const *p)
  94 {
  95   for (; *p; p++)
  96     if (*p & ~0x7f)
  97       return false;
  98   return true;
  99 }