iconvdata/gbgbk.c

   1 /* Mapping tables from GBK to GB2312 and vice versa.
   2    Copyright (C) 1999-2019 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 Lesser General Public
   8    License as published by the Free Software Foundation; either
   9    version 2.1 of the 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    Lesser General Public License for more details.
  15
  16    You should have received a copy of the GNU Lesser General Public
  17    License along with the GNU C Library; if not, see
  18    <https://www.gnu.org/licenses/>.  */
  19
  20 #include <dlfcn.h>
  21 #include <gconv.h>
  22 #include <stdint.h>
  23
  24
  25 /* Definitions used in the body of the `gconv' function.  */
  26 #define CHARSET_NAME            "GBK//"
  27 #define FROM_LOOP               from_gbk_to_gb
  28 #define TO_LOOP                 from_gb_to_gbk
  29 #define DEFINE_INIT             1
  30 #define DEFINE_FINI             1
  31 #define MIN_NEEDED_FROM         1
  32 #define MAX_NEEDED_FROM         2
  33 #define MIN_NEEDED_TO           1
  34 #define MAX_NEEDED_TO           2
  35 #define ONE_DIRECTION           0
  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.  Similarly, 0xA1AA maps in GB2312 to U2015 while in GBK     \
  69            it maps to U2014.  Since we are free to do whatever we want if     \
  70            a mapping is not available we will not flag this as an error       \
  71            but instead map the two positions.  But this means that the        \
  72            mapping                                                            \
  73                                                                               \
  74                 UCS4 -> GB2312 -> GBK -> UCS4                                 \
  75                                                                               \
  76            might not produce identical text.  */                              \
  77         if (__glibc_unlikely (inptr + 1 >= inend))                            \
  78           {                                                                   \
  79             /* The second character is not available.  Store                  \
  80                the intermediate result.  */                                   \
  81             result = __GCONV_INCOMPLETE_INPUT;                                \
  82             break;                                                            \
  83           }                                                                   \
  84                                                                               \
  85         if (__glibc_unlikely (outend - outptr < 2))                           \
  86           {                                                                   \
  87             /* We ran out of space.  */                                       \
  88             result = __GCONV_FULL_OUTPUT;                                     \
  89             break;                                                            \
  90           }                                                                   \
  91                                                                               \
  92         ch = (ch << 8) | inptr[1];                                            \
  93                                                                               \
  94         /* Map 0xA844 (U2015 in GBK) to 0xA1AA (U2015 in GB2312).  */         \
  95         if (__glibc_unlikely (ch == 0xa844))                                  \
  96           ch = 0xa1aa;                                                        \
  97                                                                               \
  98         /* Now determine whether the character is valid.  */                  \
  99         if (__builtin_expect (ch < 0xa1a1, 0)                                 \
 100             || __builtin_expect (ch > 0xf7fe, 0)                              \
 101             || __builtin_expect (inptr[1] < 0xa1, 0)                          \
 102             /* Now test the exceptions.  */                                   \
 103             || (__builtin_expect (ch >= 0xa2a1, 0)                            \
 104                 && __builtin_expect (ch <= 0xa2aa, 0))                        \
 105             || (__builtin_expect (ch >= 0xa6e0, 0)                            \
 106                 && __builtin_expect (ch <= 0xa6f5, 0))                        \
 107             || (__builtin_expect (ch >= 0xa8bb, 0)                            \
 108                 && __builtin_expect (ch <= 0xa8c0, 0)))                       \
 109           {                                                                   \
 110             /* One of the characters we cannot map.  */                       \
 111             STANDARD_TO_LOOP_ERR_HANDLER (2);                                 \
 112           }                                                                   \
 113                                                                               \
 114         /* Copy the two bytes.  */                                            \
 115         *outptr++ = *inptr++;                                                 \
 116         *outptr++ = *inptr++;                                                 \
 117       }                                                                       \
 118   }
 119 #define LOOP_NEED_FLAGS
 120 #include <iconv/loop.c>
 121
 122
 123 /* Next, define the other direction.  */
 124 #define MIN_NEEDED_INPUT        MIN_NEEDED_TO
 125 #define MAX_NEEDED_INPUT        MAX_NEEDED_TO
 126 #define MIN_NEEDED_OUTPUT       MIN_NEEDED_FROM
 127 #define MAX_NEEDED_OUTPUT       MAX_NEEDED_FROM
 128 #define LOOPFCT                 TO_LOOP
 129 #define BODY \
 130   {                                                                           \
 131     /* We don't have to care about characters we cannot map.  The only        \
 132        problem are the mapping of 0xA1A4 and 0xA1AA but as explained above    \
 133        we do not do anything special here.  */                                \
 134     unsigned char ch = *inptr++;                                              \
 135                                                                               \
 136     if (ch > 0x7f)                                                            \
 137       {                                                                       \
 138         if (__glibc_unlikely (inptr + 1 >= inend))                            \
 139           {                                                                   \
 140             /* The second character is not available.  Store                  \
 141                  the intermediate result.  */                                 \
 142             result = __GCONV_INCOMPLETE_INPUT;                                \
 143             break;                                                            \
 144           }                                                                   \
 145                                                                               \
 146         if (__glibc_unlikely (outend - outptr < 2))                           \
 147           {                                                                   \
 148             /* We ran out of space.  */                                       \
 149             result = __GCONV_FULL_OUTPUT;                                     \
 150             break;                                                            \
 151           }                                                                   \
 152                                                                               \
 153         *outptr++ = ch;                                                       \
 154         ch = *inptr++;                                                        \
 155       }                                                                       \
 156     *outptr++ = ch;                                                           \
 157   }
 158 #include <iconv/loop.c>
 159
 160
 161 /* Now define the toplevel functions.  */
 162 #include <iconv/skeleton.c>