1 /* Canonical decomposition of Unicode characters.
2 Copyright (C) 2009-2013 Free Software Foundation, Inc.
3 Written by Bruno Haible <bruno@clisp.org>, 2009.
5 This program is free software: you can redistribute it and/or modify it
6 under the terms of the GNU Lesser General Public License as published
7 by the Free Software Foundation; either version 3 of the License, or
8 (at your option) any later version.
10 This program 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.
15 You should have received a copy of the GNU Lesser General Public License
16 along with this program. If not, see <http://www.gnu.org/licenses/>. */
25 #include "decomposition-table.h"
28 uc_canonical_decomposition (ucs4_t uc, ucs4_t *decomposition)
30 if (uc >= 0xAC00 && uc < 0xD7A4)
32 /* Hangul syllable. See Unicode standard, chapter 3, section
33 "Hangul Syllable Decomposition", See also the clarification at
34 <http://www.unicode.org/versions/Unicode5.1.0/>, section
35 "Clarification of Hangul Jamo Handling". */
49 decomposition[0] = 0x1100 + l;
50 decomposition[1] = 0x1161 + v;
55 #if 1 /* Return the pairwise decomposition, not the full decomposition. */
56 decomposition[0] = 0xAC00 + uc - t; /* = 0xAC00 + (l * 21 + v) * 28; */
57 decomposition[1] = 0x11A7 + t;
66 decomposition[0] = 0x1100 + l;
67 decomposition[1] = 0x1161 + v;
68 decomposition[2] = 0x11A7 + t;
73 else if (uc < 0x110000)
75 unsigned short entry = decomp_index (uc);
76 /* An entry of (unsigned short)(-1) denotes an absent entry.
77 Otherwise, bit 15 of the entry tells whether the decomposition
78 is a canonical one. */
81 const unsigned char *p;
85 p = &gl_uninorm_decomp_chars_table[3 * entry];
86 element = (p[0] << 16) | (p[1] << 8) | p[2];
87 /* The first element has 5 bits for the decomposition type. */
88 if (((element >> 18) & 0x1f) != UC_DECOMP_CANONICAL)
93 /* Every element has an 18 bits wide Unicode code point. */
94 *decomposition = element & 0x3ffff;
95 /* Bit 23 tells whether there are more elements, */
96 if ((element & (1 << 23)) == 0)
99 element = (p[0] << 16) | (p[1] << 8) | p[2];