iconvdata/iso-ir-165.h

   1 /* Tables for conversion to and from ISO-IR-165.
   2    converting from UCS using gaps.
   3    Copyright (C) 2000-2024 Free Software Foundation, Inc.
   4    This file is part of the GNU C Library.
   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 #ifndef _ISO_IR_165_H
  21 #define _ISO_IR_165_H   1
  22
  23 #include <gconv.h>
  24 #include <stdint.h>
  25
  26 struct gap
  27 {
  28   uint16_t start;
  29   uint16_t end;
  30   int32_t idx;
  31 };
  32
  33 /* Table for ISO-IR-165 (CCITT Chinese) to UCS4 conversion.  */
  34 #define ISOIR165_FROMSIZE       0x2284
  35 extern const uint16_t __isoir165_to_tab[ISOIR165_FROMSIZE];
  36
  37
  38 /* XXX If we at some point need an offset value to decode the byte
  39    sequences another parameter can be added.  */
  40 static inline uint32_t
  41 __attribute ((always_inline))
  42 isoir165_to_ucs4 (const unsigned char **s, size_t avail)
  43 {
  44   unsigned char ch = *(*s);
  45   unsigned char ch2;
  46   uint32_t res;
  47
  48   if (ch <= 0x20 || ch >= 0x7f)
  49     return __UNKNOWN_10646_CHAR;
  50
  51   if (avail < 2)
  52     return 0;
  53
  54   ch2 = (*s)[1];
  55   if (ch2 <= 0x20 || ch2 >= 0x7f)
  56     return __UNKNOWN_10646_CHAR;
  57
  58   res = __isoir165_to_tab[(ch - 0x21) * 94 + (ch2 - 0x21)];
  59   if (res == 0)
  60     return __UNKNOWN_10646_CHAR;
  61
  62   *s += 2;
  63   return res;
  64 }
  65
  66
  67 /* Tables for ISO-IR-165 (CCITT Chinese) from UCS4 conversion.  */
  68 extern const struct gap __isoir165_from_idx[];
  69 extern const char __isoir165_from_tab[];
  70
  71 static inline size_t
  72 __attribute ((always_inline))
  73 ucs4_to_isoir165 (uint32_t wch, unsigned char *s, size_t avail)
  74 {
  75   unsigned int ch = (unsigned int) wch;
  76   const char *cp;
  77   const struct gap *rp = __isoir165_from_idx;
  78
  79   if (ch > 0xffe5)
  80     /* This is an illegal character.  */
  81     return __UNKNOWN_10646_CHAR;
  82
  83   while (ch > rp->end)
  84     ++rp;
  85   if (ch < rp->start)
  86     /* This is an illegal character.  */
  87     return __UNKNOWN_10646_CHAR;
  88
  89   /* The two bytes following the index given in this record give the
  90      encoding in ISO-IR-165.  Unless the bytes are zero.  */
  91   cp = &__isoir165_from_tab[(ch + rp->idx) * 2];
  92   if (*cp == '\0')
  93     /* This is an illegal character.  */
  94     return __UNKNOWN_10646_CHAR;
  95
  96   if (avail < 2)
  97     return 0;
  98
  99   s[0] = cp[0];
 100   s[1] = cp[1];
 101
 102   return 2;
 103 }
 104
 105 #endif  /* iso-ir-165.h */