1 /* Case-mapping contexts of UTF-8/UTF-16/UTF-32 substring.
2 Copyright (C) 2009 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/>. */
19 /* The context of a prefix string combines the information of the "Before C"
20 conditions of the Unicode Standard,
21 <http://www.unicode.org/versions/Unicode5.0.0/ch03.pdf>, section 3.13,
22 table 3-14 "Context Specification for Casing".
24 casing_prefix_context_t contains the following fields:
26 // Helper for evaluating the FINAL_SIGMA condition:
27 // Last character that was not case-ignorable.
28 ucs4_t last_char_except_ignorable;
30 // Helper for evaluating the AFTER_SOFT_DOTTED and AFTER_I conditions:
31 // Last character that was of combining class 230 ("Above") or 0.
32 ucs4_t last_char_normal_or_above;
34 Three bits would be sufficient to carry the context information, but
35 that would require to invoke uc_is_cased and uc_is_property_soft_dotted
36 ahead of time, more often than actually needed. */
39 /* The context of a suffix string combines the information of the "After C"
40 conditions of the Unicode Standard,
41 <http://www.unicode.org/versions/Unicode5.0.0/ch03.pdf>, section 3.13,
42 table 3-14 "Context Specification for Casing".
44 casing_suffix_context_t contains the following fields:
46 // For evaluating the FINAL_SIGMA condition:
47 // First character that was not case-ignorable.
48 ucs4_t first_char_except_ignorable;
50 // For evaluating the MORE_ABOVE condition:
51 // Bit 0 is set if the suffix contains a character of combining class
52 // 230 (Above) with no character of combining class 0 or 230 (Above)
55 // For evaluating the BEFORE_DOT condition:
56 // Bit 1 is set if the suffix contains a COMBINING DOT ABOVE (U+0307)
57 // with no character of combining class 0 or 230 (Above) before it.
61 Three bits would be sufficient to carry the context information, but
62 that would require to invoke uc_is_cased ahead of time, more often than
64 #define SCC_MORE_ABOVE_MASK 1
65 #define SCC_BEFORE_DOT_MASK 2