newlib/libc/iconv/ces/ucs-4.c

   1 /*
   2  * Copyright (c) 2003-2004, Artem B. Bityuckiy
   3  * Copyright (c) 1999,2000, Konstantin Chuguev. All rights reserved.
   4  *
   5  * Redistribution and use in source and binary forms, with or without
   6  * modification, are permitted provided that the following conditions
   7  * are met:
   8  * 1. Redistributions of source code must retain the above copyright
   9  *    notice, this list of conditions and the following disclaimer.
  10  * 2. Redistributions in binary form must reproduce the above copyright
  11  *    notice, this list of conditions and the following disclaimer in the
  12  *    documentation and/or other materials provided with the distribution.
  13  *
  14  * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
  15  * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
  16  * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
  17  * ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
  18  * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
  19  * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
  20  * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
  21  * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
  22  * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
  23  * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
  24  * SUCH DAMAGE.
  25  */
  26 #include "cesbi.h"
  27
  28 #if defined (ICONV_TO_UCS_CES_UCS_4) \
  29  || defined (ICONV_FROM_UCS_CES_UCS_4)
  30
  31 #include <_ansi.h>
  32 #include <reent.h>
  33 #include <stdlib.h>
  34 #include <string.h>
  35 #include <sys/types.h>
  36 #include "../lib/local.h"
  37 #include "../lib/ucsconv.h"
  38 #include "../lib/endian.h"
  39
  40 /*
  41  * BOM isn't supported. UCS-4 is Big Endian. Bad codes are rejected.
  42  * Bad codes: 0x0000FFFF, 0x0000FFFE, 0x0000D800-0x0000DFFF,
  43  * 0x7FFFFFFF-0xFFFFFFFF.
  44  */
  45
  46 #define UCS_4_BIG_ENDIAN     0
  47 #define UCS_4_LITTLE_ENDIAN  1
  48
  49 #define UCS_4   "ucs_4"
  50 #define UCS_4BE "ucs_4be"
  51 #define UCS_4LE "ucs_4le"
  52
  53 static void *
  54 ucs_4_init (struct _reent *rptr,
  55                    const char *encoding)
  56 {
  57   int *data;
  58
  59   if ((data = (int *)_malloc_r (rptr, sizeof(int))) == NULL)
  60     return (void *)NULL;
  61
  62   if (strcmp (encoding, UCS_4LE) == 0)
  63     *data = UCS_4_LITTLE_ENDIAN;
  64   else
  65     *data = UCS_4_BIG_ENDIAN;
  66
  67   return (void *)data;
  68 }
  69
  70 static size_t
  71 ucs_4_close (struct _reent *rptr,
  72                     void *data)
  73 {
  74   _free_r(rptr, data);
  75   return 0;
  76 }
  77
  78
  79 #if defined (ICONV_FROM_UCS_CES_UCS_4)
  80 static size_t
  81 ucs_4_convert_from_ucs (void *data,
  82                                ucs4_t in,
  83                                unsigned char **outbuf,
  84                                size_t *outbytesleft)
  85 {
  86   if ((in  >= 0x0000D800 && in <= 0x0000DFFF) /* Surrogate character */
  87       || in > 0x7FFFFFFF || in == 0x0000FFFF || in == 0x0000FFFE)
  88     return (size_t)ICONV_CES_INVALID_CHARACTER;
  89
  90   if (*outbytesleft < sizeof (ucs4_t))
  91     return (size_t)ICONV_CES_NOSPACE;
  92
  93   if (*((int *)data) == UCS_4_BIG_ENDIAN)
  94     *((ucs4_t *)(*outbuf)) = ICONV_HTOBEL (in);
  95   else
  96     *((ucs4_t *)(*outbuf)) = ICONV_HTOLEL (in);
  97
  98   *outbuf += sizeof (ucs4_t);
  99   *outbytesleft -= sizeof (ucs4_t);
 100
 101   return sizeof (ucs4_t);
 102 }
 103 #endif /* ICONV_FROM_UCS_CES_UCS_4 */
 104
 105 #if defined (ICONV_TO_UCS_CES_UCS_4)
 106 static ucs4_t
 107 ucs_4_convert_to_ucs (void *data,
 108                              const unsigned char **inbuf,
 109                              size_t *inbytesleft)
 110 {
 111   ucs4_t res;
 112
 113   if (*inbytesleft < sizeof (ucs4_t))
 114     return (ucs4_t)ICONV_CES_BAD_SEQUENCE;
 115
 116   if (*((int *)data) == UCS_4_BIG_ENDIAN)
 117     res = ICONV_BETOHL (*((ucs4_t *)(*inbuf)));
 118   else
 119     res = ICONV_LETOHL (*((ucs4_t *)(*inbuf)));
 120
 121   if ((res  >= 0x0000D800 && res <= 0x0000DFFF) /* Surrogate character */
 122       || res > 0x7FFFFFFF || res == 0x0000FFFF || res == 0x0000FFFE)
 123     return (ucs4_t)ICONV_CES_INVALID_CHARACTER;
 124
 125   *inbytesleft -= sizeof (ucs4_t);
 126   *inbuf += sizeof(ucs4_t);
 127
 128   return res;
 129 }
 130 #endif /* ICONV_TO_UCS_CES_UCS_4 */
 131
 132 static int
 133 ucs_4_get_mb_cur_max (void *data)
 134 {
 135   return 4;
 136 }
 137
 138 #if defined (ICONV_TO_UCS_CES_UCS_4)
 139 const iconv_to_ucs_ces_handlers_t
 140 _iconv_to_ucs_ces_handlers_ucs_4 =
 141 {
 142   ucs_4_init,
 143   ucs_4_close,
 144   ucs_4_get_mb_cur_max,
 145   NULL,
 146   NULL,
 147   NULL,
 148   ucs_4_convert_to_ucs
 149 };
 150 #endif
 151
 152 #if defined (ICONV_FROM_UCS_CES_UCS_4)
 153 const iconv_from_ucs_ces_handlers_t
 154 _iconv_from_ucs_ces_handlers_ucs_4 =
 155 {
 156   ucs_4_init,
 157   ucs_4_close,
 158   ucs_4_get_mb_cur_max,
 159   NULL,
 160   NULL,
 161   NULL,
 162   ucs_4_convert_from_ucs
 163 };
 164 #endif
 165
 166 #endif /* ICONV_TO_UCS_CES_UCS_4 || ICONV_FROM_UCS_CES_UCS_4 */
 167