1 /* Categories of Unicode characters.
2 Copyright (C) 2002, 2006-2007, 2011 Free Software Foundation, Inc.
3 Written by Bruno Haible <bruno@clisp.org>, 2011.
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/>. */
23 static const char u_category_long_name[30][22] =
36 "Connector Punctuation",
40 "Initial Punctuation",
49 "Paragraph Separator",
58 uc_general_category_long_name (uc_general_category_t category)
60 uint32_t bitmask = category.bitmask;
61 /* bitmask should consist of a single bit. */
64 if ((bitmask & (bitmask - 1)) == 0)
67 /* Take log2 using a variant of Robert Harley's method.
68 Found by Bruno Haible 1996. */
70 static const char ord2_tab[64] =
72 -1, 0, 1, 12, 2, 6, -1, 13, 3, -1, 7, -1, -1, -1, -1, 14,
73 10, 4, -1, -1, 8, -1, -1, 25, -1, -1, -1, -1, -1, 21, 27, 15,
74 31, 11, 5, -1, -1, -1, -1, -1, 9, -1, -1, 24, -1, -1, 20, 26,
75 30, -1, -1, -1, -1, 23, -1, 19, 29, -1, 22, 18, 28, 17, 16, -1
80 bit = ord2_tab[n >> 26];
82 if (bit < sizeof (u_category_long_name) / sizeof (u_category_long_name[0]))
83 return u_category_long_name[bit];
87 if (bitmask == UC_CATEGORY_MASK_L)
89 if (bitmask == UC_CATEGORY_MASK_LC)
90 return "Cased Letter";
91 if (bitmask == UC_CATEGORY_MASK_M)
93 if (bitmask == UC_CATEGORY_MASK_N)
95 if (bitmask == UC_CATEGORY_MASK_P)
97 if (bitmask == UC_CATEGORY_MASK_S)
99 if (bitmask == UC_CATEGORY_MASK_Z)
101 if (bitmask == UC_CATEGORY_MASK_C)