1 | /* German regular expression tests. |
2 | Copyright (C) 2002-2022 Free Software Foundation, Inc. |
3 | This file is part of the GNU C Library. |
4 | |
5 | The GNU C Library is free software; you can redistribute it and/or |
6 | modify it under the terms of the GNU Lesser General Public |
7 | License as published by the Free Software Foundation; either |
8 | version 2.1 of the License, or (at your option) any later version. |
9 | |
10 | The GNU C Library 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. |
14 | |
15 | You should have received a copy of the GNU Lesser General Public |
16 | License along with the GNU C Library; if not, see |
17 | <https://www.gnu.org/licenses/>. */ |
18 | |
19 | #include <sys/types.h> |
20 | #include <mcheck.h> |
21 | #include <regex.h> |
22 | #include <stdio.h> |
23 | #include <stdlib.h> |
24 | #include <locale.h> |
25 | |
26 | /* Tests supposed to match. */ |
27 | struct |
28 | { |
29 | const char *pattern; |
30 | const char *string; |
31 | int flags, nmatch; |
32 | regmatch_t rm[5]; |
33 | } tests[] = { |
34 | /* U+00C4 \xc3\x84 LATIN CAPITAL LETTER A WITH DIAERESIS |
35 | U+00D6 \xc3\x96 LATIN CAPITAL LETTER O WITH DIAERESIS |
36 | U+00E4 \xc3\xa4 LATIN SMALL LETTER A WITH DIAERESIS |
37 | U+00F6 \xc3\xb6 LATIN SMALL LETTER O WITH DIAERESIS */ |
38 | { "\xc3\x84\xc3\x96*\xc3\xb6$" , "aB\xc3\xa4\xc3\xb6\xc3\xb6\xc3\x96" , REG_ICASE, 2, |
39 | { { 2, 10 }, { -1, -1 } } }, |
40 | { "[\xc3\x84x]\xc3\x96*\xc3\xb6$" , "aB\xc3\x84\xc3\xb6\xc3\xb6\xc3\x96" , REG_ICASE, 2, |
41 | { { 2, 10 }, { -1, -1 } } }, |
42 | { "[\xc3\x84x]\xc3\x96*\xc3\xb6$" , "aB\xc3\xa4\xc3\xb6\xc3\xb6\xc3\x96" , REG_ICASE, 2, |
43 | { { 2, 10 }, { -1, -1 } } }, |
44 | { "[^x]\xc3\x96*\xc3\xb6$" , "aB\xc3\xa4\xc3\xb6\xc3\xb6\xc3\x96" , REG_ICASE, 2, |
45 | { { 2, 10 }, { -1, -1 } } }, |
46 | |
47 | /* Tests for bug 9697: |
48 | U+00DF \xc3\x9f LATIN SMALL LETTER SHARP S |
49 | U+02DA \xcb\x9a RING ABOVE |
50 | U+02E2 \xcb\xa2 MODIFIER LETTER SMALL S */ |
51 | { "[a-z]|[^a-z]" , "\xcb\xa2" , REG_EXTENDED, 2, |
52 | { { 0, 2 }, { -1, -1 } } }, |
53 | { "[a-z]" , "\xc3\x9f" , REG_EXTENDED, 2, |
54 | { { 0, 2 }, { -1, -1 } } }, |
55 | { "[^a-z]" , "\xcb\x9a" , REG_EXTENDED, 2, |
56 | { { 0, 2 }, { -1, -1 } } }, |
57 | }; |
58 | |
59 | |
60 | static int |
61 | do_test (void) |
62 | { |
63 | regex_t re; |
64 | regmatch_t rm[5]; |
65 | size_t i; |
66 | int n, ret = 0; |
67 | |
68 | setlocale (LC_ALL, "de_DE.UTF-8" ); |
69 | for (i = 0; i < sizeof (tests) / sizeof (tests[0]); ++i) |
70 | { |
71 | n = regcomp (preg: &re, pattern: tests[i].pattern, cflags: tests[i].flags); |
72 | if (n != 0) |
73 | { |
74 | char buf[500]; |
75 | regerror (errcode: n, preg: &re, errbuf: buf, errbuf_size: sizeof (buf)); |
76 | printf (format: "regcomp %zd failed: %s\n" , i, buf); |
77 | ret = 1; |
78 | continue; |
79 | } |
80 | |
81 | if (regexec (preg: &re, String: tests[i].string, nmatch: tests[i].nmatch, pmatch: rm, eflags: 0)) |
82 | { |
83 | printf (format: "regexec %zd failed\n" , i); |
84 | ret = 1; |
85 | regfree (preg: &re); |
86 | continue; |
87 | } |
88 | |
89 | for (n = 0; n < tests[i].nmatch; ++n) |
90 | if (rm[n].rm_so != tests[i].rm[n].rm_so |
91 | || rm[n].rm_eo != tests[i].rm[n].rm_eo) |
92 | { |
93 | if (tests[i].rm[n].rm_so == -1 && tests[i].rm[n].rm_eo == -1) |
94 | break; |
95 | printf (format: "regexec match failure rm[%d] %d..%d\n" , |
96 | n, rm[n].rm_so, rm[n].rm_eo); |
97 | ret = 1; |
98 | break; |
99 | } |
100 | |
101 | regfree (preg: &re); |
102 | } |
103 | |
104 | return ret; |
105 | } |
106 | |
107 | #define TEST_FUNCTION do_test () |
108 | #include "../test-skeleton.c" |
109 | |