iconvdata/gbgbk.c

   1 /* Mapping tables from GBK to GB2312 and vice versa.
   2    Copyright (C) 1999, 2000 Free Software Foundation, Inc.
   3    This file is part of the GNU C Library.
   4    Contributed by Ulrich Drepper <drepper@cygnus.com>, 1999.
   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 <dlfcn.h>
  22 #include <gconv.h>
  23 #include <stdint.h>
  24
  25
  26 /* Definitions used in the body of the `gconv' function.  */
  27 #define CHARSET_NAME            "GBK//"
  28 #define FROM_LOOP               from_gbk_to_gb
  29 #define TO_LOOP                 from_gb_to_gbk
  30 #define DEFINE_INIT             1
  31 #define DEFINE_FINI             1
  32 #define MIN_NEEDED_FROM         1
  33 #define MAX_NEEDED_FROM         2
  34 #define MIN_NEEDED_TO           1
  35 #define MAX_NEEDED_TO           2
  36
  37
  38 /* First define the conversion function from GBK to GB2312.  */
  39 #define MIN_NEEDED_INPUT        MIN_NEEDED_FROM
  40 #define MAX_NEEDED_INPUT        MAX_NEEDED_FROM
  41 #define MIN_NEEDED_OUTPUT       MIN_NEEDED_TO
  42 #define MAX_NEEDED_OUTPUT       MAX_NEEDED_TO
  43 #define LOOPFCT                 FROM_LOOP
  44 #define BODY \
  45   {                                                                           \
  46     uint32_t ch = *inptr;                                                     \
  47                                                                               \
  48     if (ch <= 0x7f)                                                           \
  49       *outptr++ = *inptr++;                                                   \
  50     else                                                                      \
  51       {                                                                       \
  52         /* It's a two-byte sequence.  We have to mask out all the sequences   \
  53            which are not in GB2312.  Besides all of them in the range         \
  54            0x8140 to 0xA0FE this also includes in the remaining range the     \
  55            sequences which the second byte being in the range from 0x40 to    \
  56            0xA0 and the following exceptions:                                 \
  57                                                                               \
  58              0xA2A1 to 0xA2A9,                                                \
  59              0xA2AA,                                                          \
  60              0xA6E0 to 0xA6EB,                                                \
  61              0xA6EE to 0xA6F2,                                                \
  62              0xA6F4, 0xA6F5,                                                  \
  63              0xA8BB to 0xA8C0                                                 \
  64                                                                               \
  65            All these characters are not defined in GB2312.  Besides this      \
  66            there is an incomatibility in the mapping.  The Unicode tables     \
  67            say that 0xA1A4 maps in GB2312 to U30FB while in GBK it maps to    \
  68            U00B7.  Since we are free to do whatever we want if a mapping      \
  69            is not available we will not flag this as an error but instead     \
  70            map the two positions.  But this means that the mapping            \
  71                                                                               \
  72                 UCS4 -> GB2312 -> GBK -> UCS4                                 \
  73                                                                               \
  74            might not produce identical text.  */                              \
  75         if (__builtin_expect (inptr + 1 >= inend, 0))                         \
  76           {                                                                   \
  77             /* The second character is not available.  Store                  \
  78                the intermediate result.  */                                   \
  79             result = __GCONV_INCOMPLETE_INPUT;                                \
  80             break;                                                            \
  81           }                                                                   \
  82                                                                               \
  83         if (__builtin_expect (outend - outptr < 2, 0))                        \
  84           {                                                                   \
  85             /* We ran out of space.  */                                       \
  86             result = __GCONV_FULL_OUTPUT;                                     \
  87             break;                                                            \
  88           }                                                                   \
  89                                                                               \
  90         ch = (ch << 8) | inptr[1];                                            \
  91                                                                               \
  92         /* Now determine whether the character is valid.  */                  \
  93         if (__builtin_expect (ch, 0xa1a1) < 0xa1a1                            \
  94             || __builtin_expect (ch, 0xa1a1) > 0xf7fe                         \
  95             || __builtin_expect (inptr[1], 0xa1) < 0xa1                       \
  96             /* Now test the exceptions.  */                                   \
  97             || (__builtin_expect (ch, 0xa1a1) >= 0xa2a1                       \
  98                 && __builtin_expect (ch, 0xa1a1) <= 0xa2aa)                   \
  99             || (__builtin_expect (ch, 0xa1a1) >= 0xa6e0                       \
 100                 && __builtin_expect (ch, 0xa1a1) <= 0xa6f5)                   \
 101             || (__builtin_expect (ch, 0xa1a1) >= 0xa8bb                       \
 102                 && __builtin_expect (ch, 0xa1a1) <= 0xa8c0))                  \
 103           {                                                                   \
 104             /* One of the characters we cannot map.  */                       \
 105             STANDARD_ERR_HANDLER (2);                                         \
 106           }                                                                   \
 107                                                                               \
 108         /* Copy the two bytes.  */                                            \
 109         *outptr++ = *inptr++;                                                 \
 110         *outptr++ = *inptr++;                                                 \
 111       }                                                                       \
 112   }
 113 #define LOOP_NEED_FLAGS
 114 #include <iconv/loop.c>
 115
 116
 117 /* Next, define the other direction.  */
 118 #define MIN_NEEDED_INPUT        MIN_NEEDED_TO
 119 #define MAX_NEEDED_INPUT        MAX_NEEDED_TO
 120 #define MIN_NEEDED_OUTPUT       MIN_NEEDED_FROM
 121 #define MAX_NEEDED_OUTPUT       MAX_NEEDED_FROM
 122 #define LOOPFCT                 TO_LOOP
 123 #define BODY \
 124   {                                                                           \
 125     /* We don't have to care about characters we cannot map.  The only        \
 126        problem is the mapping of 0xA1A4 but as explained above we do not      \
 127        do anything special here.  */                                          \
 128     unsigned char ch = *inptr++;                                              \
 129                                                                               \
 130     if (ch > 0x7f)                                                            \
 131       {                                                                       \
 132         if (__builtin_expect (inptr + 1 >= inend, 0))                         \
 133           {                                                                   \
 134             /* The second character is not available.  Store                  \
 135                  the intermediate result.  */                                 \
 136             result = __GCONV_INCOMPLETE_INPUT;                                \
 137             break;                                                            \
 138           }                                                                   \
 139                                                                               \
 140         if (__builtin_expect (outend - outptr < 2, 0))                        \
 141           {                                                                   \
 142             /* We ran out of space.  */                                       \
 143             result = __GCONV_FULL_OUTPUT;                                     \
 144             break;                                                            \
 145           }                                                                   \
 146                                                                               \
 147         *outptr++ = ch;                                                       \
 148         ch = *inptr++;                                                        \
 149       }                                                                       \
 150     *outptr++ = ch;                                                           \
 151   }
 152 #include <iconv/loop.c>
 153
 154
 155 /* Now define the toplevel functions.  */
 156 #include <iconv/skeleton.c>