1 /* Grapheme cluster breaks in Unicode strings.
2 Copyright (C) 2010 Free Software Foundation, Inc.
3 Written by Ben Pfaff <blp@cs.stanford.edu>, 2010.
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/>. */
30 /* ========================================================================= */
32 /* Property defined in Unicode Standard Annex #29, section "Grapheme Cluster
34 <http://unicode.org/reports/tr29/#Grapheme_Cluster_Boundaries> */
36 /* Possible values of the Grapheme_Cluster_Break property.
37 This enumeration may be extended in the future. */
54 /* Return the Grapheme_Cluster_Break property of a Unicode character. */
56 uc_graphemeclusterbreak_property (ucs4_t uc);
58 /* ========================================================================= */
60 /* Grapheme cluster breaks. */
62 /* Returns true if there is an grapheme cluster boundary between Unicode code
63 points A and B. A "grapheme cluster" is an approximation to a
64 user-perceived character, which sometimes corresponds to multiple code
65 points. For example, an English letter followed by an acute accent can be
66 expressed as two consecutive Unicode code points, but it is perceived by the
67 user as only a single character and therefore constitutes a single grapheme
70 Implements extended (not legacy) grapheme cluster rules, because UAX #29
71 indicates that they are preferred.
73 Use A == 0 or B == 0 to indicate start of text or end of text,
76 uc_is_grapheme_cluster_break (ucs4_t a, ucs4_t b);
78 /* ========================================================================= */
85 #endif /* _UNIGBRK_H */