1 /* Test whether a Unicode character is case-ignorable.
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/>. */
27 uc_is_case_ignorable (ucs4_t uc)
29 /* Quoting the Unicode standard:
30 Definition: A character is defined to be "case-ignorable" if it has the
31 value MidLetter {or the value MidNumLet} for the Word_Break property or
32 its General_Category is one of Nonspacing_Mark (Mn), Enclosing_Mark (Me),
33 Format (Cf), Modifier_Letter (Lm), or Modifier_Symbol (Sk).
34 The text marked in braces was added in Unicode 5.1.0, see
35 <http://www.unicode.org/versions/Unicode5.1.0/> section "Update of
36 Definition of case-ignorable". */
38 int wbp = uc_wordbreak_property (uc);
40 return (wbp == WBP_MIDLETTER || wbp == WBP_MIDNUMLET
41 || uc_is_general_category_withtable (uc, UC_CATEGORY_MASK_Mn
45 | UC_CATEGORY_MASK_Sk));