src/utf8.c

   1 /* Charset handling for GNU tar.
   2
   3    Copyright (C) 2004, 2006, 2007 Free Software Foundation, Inc.
   4
   5    This program is free software; you can redistribute it and/or modify it
   6    under the terms of the GNU General Public License as published by the
   7    Free Software Foundation; either version 3, or (at your option) any later
   8    version.
   9
  10    This program is distributed in the hope that it will be useful, but
  11    WITHOUT ANY WARRANTY; without even the implied warranty of
  12    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General
  13    Public License for more details.
  14
  15    You should have received a copy of the GNU General Public License along
  16    with this program; if not, write to the Free Software Foundation, Inc.,
  17    51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.  */
  18
  19 #include <system.h>
  20 #include <quotearg.h>
  21 #include <localcharset.h>
  22 #include "common.h"
  23 #ifdef HAVE_ICONV_H
  24 # include <iconv.h>
  25 #endif
  26
  27 #ifndef ICONV_CONST
  28 # define ICONV_CONST
  29 #endif
  30
  31 #ifndef HAVE_ICONV
  32
  33 # undef iconv_open
  34 # define iconv_open(tocode, fromcode) ((iconv_t) -1)
  35
  36 # undef iconv
  37 # define iconv(cd, inbuf, inbytesleft, outbuf, outbytesleft) ((size_t) 0)
  38
  39 # undef iconv_close
  40 # define iconv_close(cd) 0
  41
  42 #endif
  43
  44
  45 \f
  46
  47 static iconv_t conv_desc[2] = { (iconv_t) -1, (iconv_t) -1 };
  48
  49 static iconv_t
  50 utf8_init (bool to_utf)
  51 {
  52   if (conv_desc[(int) to_utf] == (iconv_t) -1)
  53     {
  54       if (to_utf)
  55         conv_desc[(int) to_utf] = iconv_open ("UTF-8", locale_charset ());
  56       else
  57         conv_desc[(int) to_utf] = iconv_open (locale_charset (), "UTF-8");
  58     }
  59   return conv_desc[(int) to_utf];
  60 }
  61
  62 bool
  63 utf8_convert (bool to_utf, char const *input, char **output)
  64 {
  65   char ICONV_CONST *ib;
  66   char *ob;
  67   size_t inlen;
  68   size_t outlen;
  69   size_t rc;
  70   iconv_t cd = utf8_init (to_utf);
  71
  72   if (cd == 0)
  73     {
  74       *output = xstrdup (input);
  75       return true;
  76     }
  77   else if (cd == (iconv_t)-1)
  78     return false;
  79
  80   inlen = strlen (input) + 1;
  81   outlen = inlen * MB_LEN_MAX + 1;
  82   ob = *output = xmalloc (outlen);
  83   ib = (char ICONV_CONST *) input;
  84   rc = iconv (cd, &ib, &inlen, &ob, &outlen);
  85   *ob = 0;
  86   return rc != -1;
  87 }
  88 \f
  89
  90 bool
  91 string_ascii_p (char const *p)
  92 {
  93   for (; *p; p++)
  94     if (*p & ~0x7f)
  95       return false;
  96   return true;
  97 }