iconvdata/euc-cn.c

   1 /* Mapping tables for EUC-CN handling.
   2    Copyright (C) 1998-2023 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 <gb2312.h>
  21 #include <stdint.h>
  22
  23 /* Definitions used in the body of the `gconv' function.  */
  24 #define CHARSET_NAME            "EUC-CN//"
  25 #define FROM_LOOP               from_euc_cn
  26 #define TO_LOOP                 to_euc_cn
  27 #define DEFINE_INIT             1
  28 #define DEFINE_FINI             1
  29 #define MIN_NEEDED_FROM         1
  30 #define MAX_NEEDED_FROM         2
  31 #define MIN_NEEDED_TO           4
  32 #define ONE_DIRECTION           0
  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 <= 0xa0, 0) && ch != 0x8e && ch != 0x8f)      \
  48           || __builtin_expect (ch > 0xfe, 0))                                 \
  49         {                                                                     \
  50           /* This is illegal.  */                                             \
  51           STANDARD_FROM_LOOP_ERR_HANDLER (1);                                 \
  52         }                                                                     \
  53       else                                                                    \
  54         {                                                                     \
  55           /* Two or more byte character.  First test whether the              \
  56              next byte is also available.  */                                 \
  57           const unsigned char *endp;                                          \
  58                                                                               \
  59           if (__glibc_unlikely (inptr + 1 >= inend))                          \
  60             {                                                                 \
  61               /* The second character is not available.  Store                \
  62                  the intermediate result.  */                                 \
  63               result = __GCONV_INCOMPLETE_INPUT;                              \
  64               break;                                                          \
  65             }                                                                 \
  66                                                                               \
  67           ch = inptr[1];                                                      \
  68                                                                               \
  69           /* All second bytes of a multibyte character must be >= 0xa1. */    \
  70           if (__glibc_unlikely (ch < 0xa1))                                   \
  71             STANDARD_FROM_LOOP_ERR_HANDLER (1);                               \
  72                                                                               \
  73           /* This is code set 1: GB 2312-80.  */                              \
  74           endp = inptr;                                                       \
  75                                                                               \
  76           ch = gb2312_to_ucs4 (&endp, 2, 0x80);                               \
  77           if (__glibc_unlikely (ch == __UNKNOWN_10646_CHAR))                  \
  78             {                                                                 \
  79               /* This is an illegal character.  */                            \
  80               STANDARD_FROM_LOOP_ERR_HANDLER (2);                             \
  81             }                                                                 \
  82                                                                               \
  83           inptr += 2;                                                         \
  84         }                                                                     \
  85                                                                               \
  86     put32 (outptr, ch);                                                       \
  87     outptr += 4;                                                              \
  88   }
  89 #define LOOP_NEED_FLAGS
  90 #define ONEBYTE_BODY \
  91   {                                                                           \
  92     if (c < 0x80)                                                             \
  93       return c;                                                               \
  94     else                                                                      \
  95       return WEOF;                                                            \
  96   }
  97 #include <iconv/loop.c>
  98
  99
 100 /* Next, define the other direction.  */
 101 #define MIN_NEEDED_INPUT        MIN_NEEDED_TO
 102 #define MIN_NEEDED_OUTPUT       MIN_NEEDED_FROM
 103 #define MAX_NEEDED_OUTPUT       MAX_NEEDED_FROM
 104 #define LOOPFCT                 TO_LOOP
 105 #define BODY \
 106   {                                                                           \
 107     uint32_t ch = get32 (inptr);                                              \
 108                                                                               \
 109     if (ch <= L'\x7f')                                                        \
 110       /* It's plain ASCII.  */                                                \
 111       *outptr++ = (unsigned char) ch;                                         \
 112     else                                                                      \
 113       {                                                                       \
 114         size_t found;                                                         \
 115                                                                               \
 116         found = ucs4_to_gb2312 (ch, outptr, outend - outptr);                 \
 117         if (__builtin_expect (found, 1) != 0)                                 \
 118           {                                                                   \
 119             if (__builtin_expect (found, 0) == __UNKNOWN_10646_CHAR)          \
 120               {                                                               \
 121                 UNICODE_TAG_HANDLER (ch, 4);                                  \
 122                                                                               \
 123                 /* Illegal character.  */                                     \
 124                 STANDARD_TO_LOOP_ERR_HANDLER (4);                             \
 125               }                                                               \
 126                                                                               \
 127             /* It's a GB 2312 character, adjust it for EUC-CN.  */            \
 128             *outptr++ += 0x80;                                                \
 129             *outptr++ += 0x80;                                                \
 130           }                                                                   \
 131         else                                                                  \
 132           {                                                                   \
 133             /* We ran out of space.  */                                       \
 134             result = __GCONV_FULL_OUTPUT;                                     \
 135             break;                                                            \
 136           }                                                                   \
 137       }                                                                       \
 138     inptr += 4;                                                               \
 139   }
 140 #define LOOP_NEED_FLAGS
 141 #include <iconv/loop.c>
 142
 143
 144 /* Now define the toplevel functions.  */
 145 #include <iconv/skeleton.c>