1 /* Test of normalization insensitive comparison of UTF-8 strings.
2 Copyright (C) 2009 Free Software Foundation, Inc.
4 This program is free software: you can redistribute it and/or modify
5 it under the terms of the GNU General Public License as published by
6 the Free Software Foundation; either version 3 of the License, or
7 (at your option) any later version.
9 This program is distributed in the hope that it will be useful,
10 but WITHOUT ANY WARRANTY; without even the implied warranty of
11 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
12 GNU General Public License for more details.
14 You should have received a copy of the GNU General Public License
15 along with this program. If not, see <http://www.gnu.org/licenses/>. */
17 /* Written by Bruno Haible <bruno@clisp.org>, 2009. */
26 #define SIZEOF(array) (sizeof (array) / sizeof (array[0]))
27 #define ASSERT(expr) \
32 fprintf (stderr, "%s:%d: assertion failed\n", __FILE__, __LINE__); \
39 #include "test-u8-normcmp.h"
42 test_nonascii (int (*my_normcmp) (const uint8_t *, size_t, const uint8_t *, size_t, uninorm_t, int *))
44 /* Normalization effects. */
46 static const uint8_t input1[] = { 'H', 0xC3, 0xB6, 'h', 'l', 'e' };
47 static const uint8_t input2[] = { 'H', 'o', 0xCC, 0x88, 'h', 'l', 'e' };
48 static const uint8_t input3[] = { 'H', 0xC3, 0xB6, 'h', 'l', 'e', 'n' };
49 static const uint8_t input4[] = { 'H', 'o', 0xCC, 0x88, 'h', 'l', 'e', 'n' };
50 static const uint8_t input5[] = { 'H', 'u', 'r', 'z' };
53 ASSERT (my_normcmp (input1, SIZEOF (input1), input2, SIZEOF (input2), UNINORM_NFD, &cmp) == 0);
56 ASSERT (my_normcmp (input2, SIZEOF (input2), input1, SIZEOF (input1), UNINORM_NFD, &cmp) == 0);
59 ASSERT (my_normcmp (input3, SIZEOF (input3), input4, SIZEOF (input4), UNINORM_NFD, &cmp) == 0);
62 ASSERT (my_normcmp (input4, SIZEOF (input4), input3, SIZEOF (input3), UNINORM_NFD, &cmp) == 0);
65 ASSERT (my_normcmp (input2, SIZEOF (input2), input3, SIZEOF (input3), UNINORM_NFD, &cmp) == 0);
68 ASSERT (my_normcmp (input1, SIZEOF (input1), input4, SIZEOF (input4), UNINORM_NFD, &cmp) == 0);
71 ASSERT (my_normcmp (input1, SIZEOF (input1), input5, SIZEOF (input5), UNINORM_NFD, &cmp) == 0);
74 ASSERT (my_normcmp (input2, SIZEOF (input2), input5, SIZEOF (input5), UNINORM_NFD, &cmp) == 0);
77 { /* LATIN CAPITAL LETTER A WITH DIAERESIS */
78 static const uint8_t input1[] = { 0xC3, 0x84 };
79 static const uint8_t input2[] = { 0x41, 0xCC, 0x88 };
82 ASSERT (my_normcmp (input1, SIZEOF (input1), input2, SIZEOF (input2), UNINORM_NFD, &cmp) == 0);
85 { /* LATIN CAPITAL LETTER A WITH DIAERESIS AND MACRON */
86 static const uint8_t input1[] = { 0xC7, 0x9E };
87 static const uint8_t input2[] = { 0x41, 0xCC, 0x88, 0xCC, 0x84 };
90 ASSERT (my_normcmp (input1, SIZEOF (input1), input2, SIZEOF (input2), UNINORM_NFD, &cmp) == 0);
93 { /* GREEK DIALYTIKA AND PERISPOMENI */
94 static const uint8_t input1[] = { 0xE1, 0xBF, 0x81 };
95 static const uint8_t input2[] = { 0xC2, 0xA8, 0xCD, 0x82 };
98 ASSERT (my_normcmp (input1, SIZEOF (input1), input2, SIZEOF (input2), UNINORM_NFD, &cmp) == 0);
101 { /* HANGUL SYLLABLE GEUL */
102 static const uint8_t input1[] = { 0xEA, 0xB8, 0x80 };
103 static const uint8_t input2[] = { 0xEA, 0xB7, 0xB8, 0xE1, 0x86, 0xAF };
104 static const uint8_t input3[] = { 0xE1, 0x84, 0x80, 0xE1, 0x85, 0xB3, 0xE1, 0x86, 0xAF };
107 ASSERT (my_normcmp (input1, SIZEOF (input1), input2, SIZEOF (input2), UNINORM_NFD, &cmp) == 0);
110 ASSERT (my_normcmp (input1, SIZEOF (input1), input3, SIZEOF (input3), UNINORM_NFD, &cmp) == 0);
113 { /* HANGUL SYLLABLE GEU */
114 static const uint8_t input1[] = { 0xEA, 0xB7, 0xB8 };
115 static const uint8_t input2[] = { 0xE1, 0x84, 0x80, 0xE1, 0x85, 0xB3 };
118 ASSERT (my_normcmp (input1, SIZEOF (input1), input2, SIZEOF (input2), UNINORM_NFD, &cmp) == 0);
126 test_ascii (u8_normcmp, UNINORM_NFD);
127 test_nonascii (u8_normcmp);