locale/programs/stringtrans.c

   1 /* Copyright (C) 1996, 1997, 1998 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 not,
  17    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       char *cp;                                                               \
  43       if (bufact + (encoding_method == ENC_UCS4 ? 4 : 1) >= bufmax)           \
  44         {                                                                     \
  45           bufmax *= 2;                                                        \
  46           buf = xrealloc (buf, bufmax);                                       \
  47         }                                                                     \
  48       cp = &buf[bufact];                                                      \
  49       if (encode_char (ch, &cp) < 0)                                          \
  50         {                                                                     \
  51           free (buf);                                                         \
  52           return NULL;                                                        \
  53         }                                                                     \
  54       bufact = cp - buf;                                                      \
  55     }                                                                         \
  56   while (0)
  57
  58
  59 char *
  60 translate_string (char *str, struct charset_t *charset)
  61 {
  62   char *buf;
  63   size_t bufact = 0;
  64   size_t bufmax = 56;
  65
  66   buf = (char *) xmalloc (bufmax);
  67
  68   while (str[0] != '\0')
  69     {
  70       char *tp;
  71       unsigned int value;
  72
  73       if (str[0] != '<')
  74         {
  75           ADDC (*str++);
  76           continue;
  77         }
  78
  79       tp = &str[1];
  80       while (tp[0] != '\0' && tp[0] != '>')
  81         if (tp[0] == '\\')
  82           if (tp[1] != '\0')
  83             tp += 2;
  84           else
  85             ++tp;
  86         else
  87           ++tp;
  88
  89       if (tp[0] == '\0')
  90         {
  91           free (buf);
  92           return NULL;
  93         }
  94
  95       value = charset_find_value (&charset->char_table, str + 1,
  96                                   tp - (str + 1));
  97       if ((wchar_t) value == ILLEGAL_CHAR_VALUE)
  98         {
  99           free (buf);
 100           return NULL;
 101         }
 102       else
 103         /* Encode string using current method.  */
 104         ADDC (value);
 105
 106       str = &tp[1];
 107     }
 108
 109   ADDC ('\0');
 110
 111   return buf;
 112 }
 113
 114
 115 int
 116 encode_char (unsigned int value, char **cpp)
 117 {
 118   switch (encoding_method)
 119     {
 120     case ENC_UCS1:
 121       if (value > 255)
 122         return -1;
 123       *(*cpp)++ = (char) value;
 124       break;
 125
 126     case ENC_UCS4:
 127 #if __BYTE_ORDER == __BIG_ENDIAN
 128       *(*cpp)++ = (char) (value >> 24);
 129       *(*cpp)++ = (char) ((value >> 16) & 0xff);
 130       *(*cpp)++ = (char) ((value >> 8) & 0xff);
 131       *(*cpp)++ = (char) (value & 0xff);
 132 #else
 133       *(*cpp)++ = (char) (value & 0xff);
 134       *(*cpp)++ = (char) ((value >>= 8) & 0xff);
 135       *(*cpp)++ = (char) ((value >>= 8) & 0xff);
 136       *(*cpp)++ = (char) ((value >>= 8) & 0xff);
 137 #endif
 138       break;
 139
 140     default:
 141       return -1;
 142     }
 143
 144   return 0;
 145 }