summaryrefslogtreecommitdiff
path: root/lib/uninorm/decomposition.c
blob: ec5a3d79498f4164d4b5874c9d440024eb465c91 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
/* Decomposition of Unicode characters.
   Copyright (C) 2009-2022 Free Software Foundation, Inc.
   Written by Bruno Haible <bruno@clisp.org>, 2009.

   This file is free software.
   It is dual-licensed under "the GNU LGPLv3+ or the GNU GPLv2+".
   You can redistribute it and/or modify it under either
     - the terms of the GNU Lesser General Public License as published
       by the Free Software Foundation, either version 3, or (at your
       option) any later version, or
     - the terms of the GNU General Public License as published by the
       Free Software Foundation; either version 2, or (at your option)
       any later version, or
     - the same dual license "the GNU LGPLv3+ or the GNU GPLv2+".

   This file is distributed in the hope that it will be useful,
   but WITHOUT ANY WARRANTY; without even the implied warranty of
   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
   Lesser General Public License and the GNU General Public License
   for more details.

   You should have received a copy of the GNU Lesser General Public
   License and of the GNU General Public License along with this
   program.  If not, see <https://www.gnu.org/licenses/>.  */

#include <config.h>

/* Specification.  */
#include "uninorm.h"

#include "uninorm/decomposition-table.h"

int
uc_decomposition (ucs4_t uc, int *decomp_tag, ucs4_t *decomposition)
{
  if (uc >= 0xAC00 && uc < 0xD7A4)
    {
      /* Hangul syllable.  See Unicode standard, chapter 3, section
         "Hangul Syllable Decomposition",  See also the clarification at
         <https://www.unicode.org/versions/Unicode5.1.0/>, section
         "Clarification of Hangul Jamo Handling".  */
      unsigned int t;

      uc -= 0xAC00;
      t = uc % 28;

      *decomp_tag = UC_DECOMP_CANONICAL;
      if (t == 0)
        {
          unsigned int v, l;

          uc = uc / 28;
          v = uc % 21;
          l = uc / 21;

          decomposition[0] = 0x1100 + l;
          decomposition[1] = 0x1161 + v;
          return 2;
        }
      else
        {
#if 1 /* Return the pairwise decomposition, not the full decomposition.  */
          decomposition[0] = 0xAC00 + uc - t; /* = 0xAC00 + (l * 21 + v) * 28; */
          decomposition[1] = 0x11A7 + t;
          return 2;
#else
          unsigned int v, l;

          uc = uc / 28;
          v = uc % 21;
          l = uc / 21;

          decomposition[0] = 0x1100 + l;
          decomposition[1] = 0x1161 + v;
          decomposition[2] = 0x11A7 + t;
          return 3;
#endif
        }
    }
  else if (uc < 0x110000)
    {
      unsigned short entry = decomp_index (uc);
      if (entry != (unsigned short)(-1))
        {
          const unsigned char *p;
          unsigned int element;
          unsigned int length;

          p = &gl_uninorm_decomp_chars_table[3 * (entry & 0x7FFF)];
          element = (p[0] << 16) | (p[1] << 8) | p[2];
          /* The first element has 5 bits for the decomposition type.  */
          *decomp_tag = (element >> 18) & 0x1f;
          length = 1;
          for (;;)
            {
              /* Every element has an 18 bits wide Unicode code point.  */
              *decomposition = element & 0x3ffff;
              /* Bit 23 tells whether there are more elements,  */
              if ((element & (1 << 23)) == 0)
                break;
              p += 3;
              element = (p[0] << 16) | (p[1] << 8) | p[2];
              decomposition++;
              length++;
            }
          return length;
        }
    }
  return -1;
}