locale/programs/stringtrans.c

   1 /* Copyright (C) 1996 Free Software Foundation, Inc.
   2 This file is part of the GNU C Library.
   3 Contributed by Ulrich Drepper <drepper@gnu.ai.mit.edu>, 1996.
   4
   5 The GNU C Library is free software; you can redistribute it and/or
   6 modify it under the terms of the GNU Library General Public License as
   7 published by the Free Software Foundation; either version 2 of the
   8 License, or (at your option) any later version.
   9
  10 The GNU C Library is distributed in the hope that it will be useful,
  11 but WITHOUT ANY WARRANTY; without even the implied warranty of
  12 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  13 Library General Public License for more details.
  14
  15 You should have received a copy of the GNU Library General Public
  16 License along with the GNU C Library; see the file COPYING.LIB.  If
  17 not, write to the Free Software Foundation, Inc., 59 Temple Place - Suite 330,
  18 Boston, MA 02111-1307, USA.  */
  19
  20 #ifdef HAVE_CONFIG_H
  21 # include <config.h>
  22 #endif
  23
  24 #include <assert.h>
  25 #include <stdlib.h>
  26
  27 #include "charset.h"
  28 #include "stringtrans.h"
  29
  30
  31 /* Global variable.  */
  32 enum encoding_method encoding_method = ENC_UCS4;
  33
  34
  35 void *xmalloc (size_t __n);
  36 void *xrealloc (void *__p, size_t __n);
  37
  38
  39 #define ADDC(ch)                                                            \
  40   do                                                                        \
  41     {                                                                       \
  42       if (bufact == bufmax)                                                 \
  43         {                                                                   \
  44           bufmax *= 2;                                                      \
  45           buf = xrealloc (buf, bufmax);                                     \
  46         }                                                                   \
  47       buf[bufact++] = (ch);                                                 \
  48     }                                                                       \
  49   while (0)
  50
  51
  52 char *
  53 translate_string (char *str, struct charset_t *charset)
  54 {
  55   char *buf;
  56   size_t bufact = 0;
  57   size_t bufmax = 56;
  58
  59   buf = (char *) xmalloc (bufmax);
  60
  61   while (str[0] != '\0')
  62     {
  63       char *tp;
  64       unsigned int value;
  65
  66       if (str[0] != '<')
  67         {
  68           ADDC (*str++);
  69           continue;
  70         }
  71
  72       tp = &str[1];
  73       while (tp[0] != '\0' && tp[0] != '>')
  74         if (tp[0] == '\\')
  75           if (tp[1] != '\0')
  76             tp += 2;
  77           else
  78             ++tp;
  79         else
  80           ++tp;
  81
  82       if (tp[0] == '\0')
  83         {
  84           free (buf);
  85           return NULL;
  86         }
  87
  88       value = charset_find_value (charset, str + 1, tp - (str + 1));
  89       if (value == ILLEGAL_CHAR_VALUE)
  90         {
  91           free (buf);
  92           return NULL;
  93         }
  94       else
  95         {
  96           /* Encode string using current method.  */
  97           char *cp;
  98
  99           if (bufmax - bufact < 8)
 100             {
 101               bufmax *= 2;
 102               buf = (char *) xrealloc (buf, bufmax);
 103             }
 104
 105           cp = &buf[bufact];
 106           if (encode_char (value, &cp) < 0)
 107             {
 108               free (buf);
 109               return NULL;
 110             }
 111           bufact = cp - buf;
 112         }
 113
 114       str = &tp[1];
 115     }
 116
 117   ADDC ('\0');
 118
 119   return buf;;
 120 }
 121
 122
 123 int
 124 encode_char (unsigned int value, char **cpp)
 125 {
 126   switch (encoding_method)
 127     {
 128     case ENC_UCS1:
 129       if (value > 255)
 130         return -11;
 131       *(*cpp)++ = (char) value;
 132       break;
 133
 134     case ENC_UCS4:
 135       *(*cpp)++ = (char) (value >> 24);
 136       *(*cpp)++ = (char) ((value >> 16) & 0xff);
 137       *(*cpp)++ = (char) ((value >> 8) & 0xff);
 138       *(*cpp)++ = (char) (value & 0xff);
 139       break;
 140
 141     default:
 142       return -1;
 143     }
 144
 145   return 0;
 146 }