iconvdata/euc-cn.c

   1 /* Mapping tables for EUC-CN handling.
   2    Copyright (C) 1998, 1999, 2000 Free Software Foundation, Inc.
   3    This file is part of the GNU C Library.
   4    Contributed by Ulrich Drepper <drepper@cygnus.com>, 1998.
   5
   6    The GNU C Library is free software; you can redistribute it and/or
   7    modify it under the terms of the GNU Library General Public License as
   8    published by the Free Software Foundation; either version 2 of the
   9    License, or (at your option) any later version.
  10
  11    The GNU C Library is distributed in the hope that it will be useful,
  12    but WITHOUT ANY WARRANTY; without even the implied warranty of
  13    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  14    Library General Public License for more details.
  15
  16    You should have received a copy of the GNU Library General Public
  17    License along with the GNU C Library; see the file COPYING.LIB.  If not,
  18    write to the Free Software Foundation, Inc., 59 Temple Place - Suite 330,
  19    Boston, MA 02111-1307, USA.  */
  20
  21 #include <gb2312.h>
  22 #include <stdint.h>
  23
  24 /* Definitions used in the body of the `gconv' function.  */
  25 #define CHARSET_NAME            "EUC-CN//"
  26 #define FROM_LOOP               from_euc_cn
  27 #define TO_LOOP                 to_euc_cn
  28 #define DEFINE_INIT             1
  29 #define DEFINE_FINI             1
  30 #define MIN_NEEDED_FROM         1
  31 #define MAX_NEEDED_FROM         2
  32 #define MIN_NEEDED_TO           4
  33
  34
  35 /* First define the conversion function from EUC-CN to UCS4.  */
  36 #define MIN_NEEDED_INPUT        MIN_NEEDED_FROM
  37 #define MAX_NEEDED_INPUT        MAX_NEEDED_FROM
  38 #define MIN_NEEDED_OUTPUT       MIN_NEEDED_TO
  39 #define LOOPFCT                 FROM_LOOP
  40 #define BODY \
  41   {                                                                           \
  42     uint32_t ch = *inptr;                                                     \
  43                                                                               \
  44     if (ch <= 0x7f)                                                           \
  45       ++inptr;                                                                \
  46     else                                                                      \
  47       if ((__builtin_expect (ch, 0xa1) <= 0xa0 && ch != 0x8e && ch != 0x8f)   \
  48           || __builtin_expect (ch, 0xfe) > 0xfe)                              \
  49         {                                                                     \
  50           /* This is illegal.  */                                             \
  51           if (! ignore_errors_p ())                                           \
  52             {                                                                 \
  53               result = __GCONV_ILLEGAL_INPUT;                                 \
  54               break;                                                          \
  55             }                                                                 \
  56                                                                               \
  57           ++inptr;                                                            \
  58           ++*converted;                                                       \
  59           continue;                                                           \
  60         }                                                                     \
  61       else                                                                    \
  62         {                                                                     \
  63           /* Two or more byte character.  First test whether the              \
  64              next character is also available.  */                            \
  65           const unsigned char *endp;                                          \
  66                                                                               \
  67           if (NEED_LENGTH_TEST && __builtin_expect (inptr + 1 >= inend, 0))   \
  68             {                                                                 \
  69               /* The second character is not available.  Store                \
  70                  the intermediate result.  */                                 \
  71               result = __GCONV_INCOMPLETE_INPUT;                              \
  72               break;                                                          \
  73             }                                                                 \
  74                                                                               \
  75           ch = inptr[1];                                                      \
  76                                                                               \
  77           /* All second bytes of a multibyte character must be >= 0xa1. */    \
  78           if (__builtin_expect (ch, 0xa1) < 0xa1)                             \
  79             {                                                                 \
  80               if (! ignore_errors_p ())                                       \
  81                 {                                                             \
  82                   /* This is an illegal character.  */                        \
  83                   result = __GCONV_ILLEGAL_INPUT;                             \
  84                   break;                                                      \
  85                 }                                                             \
  86                                                                               \
  87               ++inptr;                                                        \
  88               ++*converted;                                                   \
  89               continue;                                                       \
  90             }                                                                 \
  91                                                                               \
  92           /* This is code set 1: GB 2312-80.  */                              \
  93           endp = inptr;                                                       \
  94                                                                               \
  95           ch = gb2312_to_ucs4 (&endp, 2, 0x80);                               \
  96           if (__builtin_expect (ch, 0) == __UNKNOWN_10646_CHAR)               \
  97             {                                                                 \
  98               /* This is an illegal character.  */                            \
  99               if (! ignore_errors_p ())                                       \
 100                 {                                                             \
 101                   /* This is an illegal character.  */                        \
 102                   result = __GCONV_ILLEGAL_INPUT;                             \
 103                   break;                                                      \
 104                 }                                                             \
 105                                                                               \
 106               inptr += 2;                                                     \
 107               ++*converted;                                                   \
 108               continue;                                                       \
 109             }                                                                 \
 110                                                                               \
 111           inptr += 2;                                                         \
 112         }                                                                     \
 113                                                                               \
 114     put32 (outptr, ch);                                                       \
 115     outptr += 4;                                                              \
 116   }
 117 #include <iconv/loop.c>
 118
 119
 120 /* Next, define the other direction.  */
 121 #define MIN_NEEDED_INPUT        MIN_NEEDED_TO
 122 #define MIN_NEEDED_OUTPUT       MIN_NEEDED_FROM
 123 #define MAX_NEEDED_OUTPUT       MAX_NEEDED_FROM
 124 #define LOOPFCT                 TO_LOOP
 125 #define BODY \
 126   {                                                                           \
 127     uint32_t ch = get32 (inptr);                                              \
 128                                                                               \
 129     if (ch <= L'\x7f')                                                        \
 130       /* It's plain ASCII.  */                                                \
 131       *outptr++ = (unsigned char) ch;                                         \
 132     else                                                                      \
 133       {                                                                       \
 134         size_t found;                                                         \
 135                                                                               \
 136         found = ucs4_to_gb2312 (ch, outptr,                                   \
 137                                 (NEED_LENGTH_TEST                             \
 138                                  ? outend - outptr : MAX_NEEDED_OUTPUT));     \
 139         if (!NEED_LENGTH_TEST || __builtin_expect (found, 1) != 0)            \
 140           {                                                                   \
 141             if (__builtin_expect (found, 0) == __UNKNOWN_10646_CHAR)          \
 142               {                                                               \
 143                 /* Illegal character.  */                                     \
 144                 if (! ignore_errors_p ())                                     \
 145                   {                                                           \
 146                     result = __GCONV_ILLEGAL_INPUT;                           \
 147                     break;                                                    \
 148                   }                                                           \
 149                                                                               \
 150                 inptr += 4;                                                   \
 151                 ++*converted;                                                 \
 152                 continue;                                                     \
 153               }                                                               \
 154                                                                               \
 155             /* It's a GB 2312 character, adjust it for EUC-CN.  */            \
 156             *outptr++ += 0x80;                                                \
 157             *outptr++ += 0x80;                                                \
 158           }                                                                   \
 159         else                                                                  \
 160           {                                                                   \
 161             /* We ran out of space.  */                                       \
 162             result = __GCONV_FULL_OUTPUT;                                     \
 163             break;                                                            \
 164           }                                                                   \
 165       }                                                                       \
 166     inptr += 4;                                                               \
 167   }
 168 #include <iconv/loop.c>
 169
 170
 171 /* Now define the toplevel functions.  */
 172 #include <iconv/skeleton.c>