iconvdata/gbgbk.c

   1 /* Mapping tables from GBK to GB2312 and vice versa.
   2    Copyright (C) 1999-2023 Free Software Foundation, Inc.
   3    This file is part of the GNU C Library.
   4
   5    The GNU C Library is free software; you can redistribute it and/or
   6    modify it under the terms of the GNU Lesser General Public
   7    License as published by the Free Software Foundation; either
   8    version 2.1 of the 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    Lesser General Public License for more details.
  14
  15    You should have received a copy of the GNU Lesser General Public
  16    License along with the GNU C Library; if not, see
  17    <https://www.gnu.org/licenses/>.  */
  18
  19 #include <dlfcn.h>
  20 #include <gconv.h>
  21 #include <stdint.h>
  22
  23
  24 /* Definitions used in the body of the `gconv' function.  */
  25 #define CHARSET_NAME            "GBK//"
  26 #define FROM_LOOP               from_gbk_to_gb
  27 #define TO_LOOP                 from_gb_to_gbk
  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           1
  33 #define MAX_NEEDED_TO           2
  34 #define ONE_DIRECTION           0
  35
  36
  37 /* First define the conversion function from GBK to GB2312.  */
  38 #define MIN_NEEDED_INPUT        MIN_NEEDED_FROM
  39 #define MAX_NEEDED_INPUT        MAX_NEEDED_FROM
  40 #define MIN_NEEDED_OUTPUT       MIN_NEEDED_TO
  41 #define MAX_NEEDED_OUTPUT       MAX_NEEDED_TO
  42 #define LOOPFCT                 FROM_LOOP
  43 #define BODY \
  44   {                                                                           \
  45     uint32_t ch = *inptr;                                                     \
  46                                                                               \
  47     if (ch <= 0x7f)                                                           \
  48       *outptr++ = *inptr++;                                                   \
  49     else                                                                      \
  50       {                                                                       \
  51         /* It's a two-byte sequence.  We have to mask out all the sequences   \
  52            which are not in GB2312.  Besides all of them in the range         \
  53            0x8140 to 0xA0FE this also includes in the remaining range the     \
  54            sequences which the second byte being in the range from 0x40 to    \
  55            0xA0 and the following exceptions:                                 \
  56                                                                               \
  57              0xA2A1 to 0xA2A9,                                                \
  58              0xA2AA,                                                          \
  59              0xA6E0 to 0xA6EB,                                                \
  60              0xA6EE to 0xA6F2,                                                \
  61              0xA6F4, 0xA6F5,                                                  \
  62              0xA8BB to 0xA8C0                                                 \
  63                                                                               \
  64            All these characters are not defined in GB2312.  Besides this      \
  65            there is an incomatibility in the mapping.  The Unicode tables     \
  66            say that 0xA1A4 maps in GB2312 to U30FB while in GBK it maps to    \
  67            U00B7.  Similarly, 0xA1AA maps in GB2312 to U2015 while in GBK     \
  68            it maps to U2014.  Since we are free to do whatever we want if     \
  69            a mapping is not available we will not flag this as an error       \
  70            but instead map the two positions.  But this means that the        \
  71            mapping                                                            \
  72                                                                               \
  73                 UCS4 -> GB2312 -> GBK -> UCS4                                 \
  74                                                                               \
  75            might not produce identical text.  */                              \
  76         if (__glibc_unlikely (inptr + 1 >= inend))                            \
  77           {                                                                   \
  78             /* The second character is not available.  Store                  \
  79                the intermediate result.  */                                   \
  80             result = __GCONV_INCOMPLETE_INPUT;                                \
  81             break;                                                            \
  82           }                                                                   \
  83                                                                               \
  84         if (__glibc_unlikely (outend - outptr < 2))                           \
  85           {                                                                   \
  86             /* We ran out of space.  */                                       \
  87             result = __GCONV_FULL_OUTPUT;                                     \
  88             break;                                                            \
  89           }                                                                   \
  90                                                                               \
  91         ch = (ch << 8) | inptr[1];                                            \
  92                                                                               \
  93         /* Map 0xA844 (U2015 in GBK) to 0xA1AA (U2015 in GB2312).  */         \
  94         if (__glibc_unlikely (ch == 0xa844))                                  \
  95           ch = 0xa1aa;                                                        \
  96                                                                               \
  97         /* Now determine whether the character is valid.  */                  \
  98         if (__builtin_expect (ch < 0xa1a1, 0)                                 \
  99             || __builtin_expect (ch > 0xf7fe, 0)                              \
 100             || __builtin_expect (inptr[1] < 0xa1, 0)                          \
 101             /* Now test the exceptions.  */                                   \
 102             || (__builtin_expect (ch >= 0xa2a1, 0)                            \
 103                 && __builtin_expect (ch <= 0xa2aa, 0))                        \
 104             || (__builtin_expect (ch >= 0xa6e0, 0)                            \
 105                 && __builtin_expect (ch <= 0xa6f5, 0))                        \
 106             || (__builtin_expect (ch >= 0xa8bb, 0)                            \
 107                 && __builtin_expect (ch <= 0xa8c0, 0)))                       \
 108           {                                                                   \
 109             /* One of the characters we cannot map.  */                       \
 110             STANDARD_TO_LOOP_ERR_HANDLER (2);                                 \
 111           }                                                                   \
 112                                                                               \
 113         /* Copy the two bytes.  */                                            \
 114         *outptr++ = *inptr++;                                                 \
 115         *outptr++ = *inptr++;                                                 \
 116       }                                                                       \
 117   }
 118 #define LOOP_NEED_FLAGS
 119 #include <iconv/loop.c>
 120
 121
 122 /* Next, define the other direction.  */
 123 #define MIN_NEEDED_INPUT        MIN_NEEDED_TO
 124 #define MAX_NEEDED_INPUT        MAX_NEEDED_TO
 125 #define MIN_NEEDED_OUTPUT       MIN_NEEDED_FROM
 126 #define MAX_NEEDED_OUTPUT       MAX_NEEDED_FROM
 127 #define LOOPFCT                 TO_LOOP
 128 #define BODY \
 129   {                                                                           \
 130     /* We don't have to care about characters we cannot map.  The only        \
 131        problem are the mapping of 0xA1A4 and 0xA1AA but as explained above    \
 132        we do not do anything special here.  */                                \
 133     unsigned char ch = *inptr++;                                              \
 134                                                                               \
 135     if (ch > 0x7f)                                                            \
 136       {                                                                       \
 137         if (__glibc_unlikely (inptr + 1 >= inend))                            \
 138           {                                                                   \
 139             /* The second character is not available.  Store                  \
 140                  the intermediate result.  */                                 \
 141             result = __GCONV_INCOMPLETE_INPUT;                                \
 142             break;                                                            \
 143           }                                                                   \
 144                                                                               \
 145         if (__glibc_unlikely (outend - outptr < 2))                           \
 146           {                                                                   \
 147             /* We ran out of space.  */                                       \
 148             result = __GCONV_FULL_OUTPUT;                                     \
 149             break;                                                            \
 150           }                                                                   \
 151                                                                               \
 152         *outptr++ = ch;                                                       \
 153         ch = *inptr++;                                                        \
 154       }                                                                       \
 155     *outptr++ = ch;                                                           \
 156   }
 157 #include <iconv/loop.c>
 158
 159
 160 /* Now define the toplevel functions.  */
 161 #include <iconv/skeleton.c>