1 /* Test of c32isxdigit() function.
2 Copyright (C) 2020-2023 Free Software Foundation, Inc.
3
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.
8
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.
13
14 You should have received a copy of the GNU General Public License
15 along with this program. If not, see <https://www.gnu.org/licenses/>. */
16
17 #include <config.h>
18
19 #include <uchar.h>
20
21 #include "signature.h"
22 SIGNATURE_CHECK (c32isxdigit, int, (wint_t));
23
24 #include <locale.h>
25 #include <stdlib.h>
26 #include <string.h>
27 #include <wchar.h>
28
29 #include "macros.h"
30
31 /* Returns the value of c32isxdigit for the multibyte character s[0..n-1]. */
32 static int
33 for_character (const char *s, size_t n)
34 {
35 mbstate_t state;
36 char32_t wc;
37 size_t ret;
38
39 memset (&state, '\0', sizeof (mbstate_t));
40 wc = (char32_t) 0xBADFACE;
41 ret = mbrtoc32 (&wc, s, n, &state);
42 ASSERT (ret == n);
43
44 return c32isxdigit (wc);
45 }
46
47 int
48 main (int argc, char *argv[])
49 {
50 int is;
51 char buf[4];
52
53 /* configure should already have checked that the locale is supported. */
54 if (setlocale (LC_ALL, "") == NULL)
55 return 1;
56
57 /* Test WEOF. */
58 is = c32isxdigit (WEOF);
59 ASSERT (is == 0);
60
61 /* Test single-byte characters.
62 ISO C 99 sections 7.25.2.1.12 and 6.4.4.1 specify that the hexadecimal
63 digits include only the ASCII 0 ... 9 A ... F a ... f characters. */
64 {
65 int c;
66
67 for (c = 0; c < 0x100; c++)
68 switch (c)
69 {
70 case '\t': case '\v': case '\f':
71 case ' ': case '!': case '"': case '#': case '%':
72 case '&': case '\'': case '(': case ')': case '*':
73 case '+': case ',': case '-': case '.': case '/':
74 case '0': case '1': case '2': case '3': case '4':
75 case '5': case '6': case '7': case '8': case '9':
76 case ':': case ';': case '<': case '=': case '>':
77 case '?':
78 case 'A': case 'B': case 'C': case 'D': case 'E':
79 case 'F': case 'G': case 'H': case 'I': case 'J':
80 case 'K': case 'L': case 'M': case 'N': case 'O':
81 case 'P': case 'Q': case 'R': case 'S': case 'T':
82 case 'U': case 'V': case 'W': case 'X': case 'Y':
83 case 'Z':
84 case '[': case '\\': case ']': case '^': case '_':
85 case 'a': case 'b': case 'c': case 'd': case 'e':
86 case 'f': case 'g': case 'h': case 'i': case 'j':
87 case 'k': case 'l': case 'm': case 'n': case 'o':
88 case 'p': case 'q': case 'r': case 's': case 't':
89 case 'u': case 'v': case 'w': case 'x': case 'y':
90 case 'z': case '{': case '|': case '}': case '~':
91 /* c is in the ISO C "basic character set". */
92 buf[0] = (unsigned char) c;
93 is = for_character (buf, 1);
94 switch (c)
95 {
96 case '0': case '1': case '2': case '3': case '4':
97 case '5': case '6': case '7': case '8': case '9':
98 case 'A': case 'B': case 'C': case 'D': case 'E': case 'F':
99 case 'a': case 'b': case 'c': case 'd': case 'e': case 'f':
100 ASSERT (is != 0);
101 break;
102 default:
103 ASSERT (is == 0);
104 break;
105 }
106 break;
107 }
108 }
109
110 if (argc > 1)
111 switch (argv[1][0])
112 {
113 case '0':
114 /* C locale; tested above. */
115 return 0;
116
117 case '1':
118 /* Locale encoding is ISO-8859-1 or ISO-8859-15. */
119 {
120 /* U+00B2 SUPERSCRIPT TWO */
121 is = for_character ("\262", 1);
122 ASSERT (is == 0);
123 /* U+00B3 SUPERSCRIPT THREE */
124 is = for_character ("\263", 1);
125 ASSERT (is == 0);
126 /* U+00B9 SUPERSCRIPT ONE */
127 is = for_character ("\271", 1);
128 ASSERT (is == 0);
129 }
130 return 0;
131
132 case '2':
133 /* Locale encoding is EUC-JP. */
134 {
135 /* U+FF11 FULLWIDTH DIGIT ONE */
136 is = for_character ("\243\261", 2);
137 ASSERT (is == 0);
138 /* U+FF21 FULLWIDTH LATIN CAPITAL LETTER A */
139 is = for_character ("\243\301", 2);
140 ASSERT (is == 0);
141 /* U+FF41 FULLWIDTH LATIN SMALL LETTER A */
142 is = for_character ("\243\341", 2);
143 ASSERT (is == 0);
144 }
145 return 0;
146
147 case '3':
148 /* Locale encoding is UTF-8. */
149 {
150 /* U+00B2 SUPERSCRIPT TWO */
151 is = for_character ("\302\262", 2);
152 ASSERT (is == 0);
153 /* U+00B3 SUPERSCRIPT THREE */
154 is = for_character ("\302\263", 2);
155 ASSERT (is == 0);
156 /* U+00B9 SUPERSCRIPT ONE */
157 is = for_character ("\302\271", 2);
158 ASSERT (is == 0);
159 /* U+0663 ARABIC-INDIC DIGIT THREE */
160 is = for_character ("\331\243", 2);
161 ASSERT (is == 0);
162 /* U+2070 SUPERSCRIPT ZERO */
163 is = for_character ("\342\201\260", 3);
164 ASSERT (is == 0);
165 /* U+2079 SUPERSCRIPT NINE */
166 is = for_character ("\342\201\271", 3);
167 ASSERT (is == 0);
168 /* U+FF11 FULLWIDTH DIGIT ONE */
169 is = for_character ("\357\274\221", 3);
170 ASSERT (is == 0);
171 /* U+FF21 FULLWIDTH LATIN CAPITAL LETTER A */
172 is = for_character ("\357\274\241", 3);
173 ASSERT (is == 0);
174 /* U+FF41 FULLWIDTH LATIN SMALL LETTER A */
175 is = for_character ("\357\275\201", 3);
176 ASSERT (is == 0);
177 /* U+1D7D1 MATHEMATICAL BOLD DIGIT THREE */
178 is = for_character ("\360\235\237\221", 4);
179 ASSERT (is == 0);
180 /* U+1D7DB MATHEMATICAL DOUBLE-STRUCK DIGIT THREE */
181 is = for_character ("\360\235\237\233", 4);
182 ASSERT (is == 0);
183 /* U+1D7E5 MATHEMATICAL SANS-SERIF DIGIT THREE */
184 is = for_character ("\360\235\237\245", 4);
185 ASSERT (is == 0);
186 /* U+1D7EF MATHEMATICAL SANS-SERIF BOLD DIGIT THREE */
187 is = for_character ("\360\235\237\257", 4);
188 ASSERT (is == 0);
189 /* U+1D7F9 MATHEMATICAL MONOSPACE DIGIT THREE */
190 is = for_character ("\360\235\237\271", 4);
191 ASSERT (is == 0);
192 /* U+E0033 TAG DIGIT THREE */
193 is = for_character ("\363\240\200\263", 4);
194 ASSERT (is == 0);
195 /* U+E0041 TAG LATIN CAPITAL LETTER A */
196 is = for_character ("\363\240\201\201", 4);
197 ASSERT (is == 0);
198 }
199 return 0;
200
201 case '4':
202 /* Locale encoding is GB18030. */
203 #if (defined __GLIBC__ && __GLIBC__ == 2 && __GLIBC_MINOR__ >= 13 && __GLIBC_MINOR__ <= 15) || (GL_CHAR32_T_IS_UNICODE && (defined __NetBSD__ || defined __sun))
204 fputs ("Skipping test: The GB18030 converter in this system's iconv is broken.\n", stderr);
205 return 77;
206 #endif
207 {
208 /* U+00B2 SUPERSCRIPT TWO */
209 is = for_character ("\201\060\205\065", 4);
210 ASSERT (is == 0);
211 /* U+00B3 SUPERSCRIPT THREE */
212 is = for_character ("\201\060\205\066", 4);
213 ASSERT (is == 0);
214 /* U+00B9 SUPERSCRIPT ONE */
215 is = for_character ("\201\060\206\061", 4);
216 ASSERT (is == 0);
217 /* U+0663 ARABIC-INDIC DIGIT THREE */
218 is = for_character ("\201\061\211\071", 4);
219 ASSERT (is == 0);
220 /* U+2070 SUPERSCRIPT ZERO */
221 is = for_character ("\201\066\255\062", 4);
222 ASSERT (is == 0);
223 /* U+2079 SUPERSCRIPT NINE */
224 is = for_character ("\201\066\256\061", 4);
225 ASSERT (is == 0);
226 /* U+FF11 FULLWIDTH DIGIT ONE */
227 is = for_character ("\243\261", 2);
228 ASSERT (is == 0);
229 /* U+FF21 FULLWIDTH LATIN CAPITAL LETTER A */
230 is = for_character ("\243\301", 2);
231 ASSERT (is == 0);
232 /* U+FF41 FULLWIDTH LATIN SMALL LETTER A */
233 is = for_character ("\243\341", 2);
234 ASSERT (is == 0);
235 /* U+1D7D1 MATHEMATICAL BOLD DIGIT THREE */
236 is = for_character ("\224\063\353\071", 4);
237 ASSERT (is == 0);
238 /* U+1D7DB MATHEMATICAL DOUBLE-STRUCK DIGIT THREE */
239 is = for_character ("\224\063\354\071", 4);
240 ASSERT (is == 0);
241 /* U+1D7E5 MATHEMATICAL SANS-SERIF DIGIT THREE */
242 is = for_character ("\224\063\355\071", 4);
243 ASSERT (is == 0);
244 /* U+1D7EF MATHEMATICAL SANS-SERIF BOLD DIGIT THREE */
245 is = for_character ("\224\063\356\071", 4);
246 ASSERT (is == 0);
247 /* U+1D7F9 MATHEMATICAL MONOSPACE DIGIT THREE */
248 is = for_character ("\224\063\357\071", 4);
249 ASSERT (is == 0);
250 /* U+E0033 TAG DIGIT THREE */
251 is = for_character ("\323\066\232\071", 4);
252 ASSERT (is == 0);
253 /* U+E0041 TAG LATIN CAPITAL LETTER A */
254 is = for_character ("\323\066\234\063", 4);
255 ASSERT (is == 0);
256 }
257 return 0;
258
259 }
260
261 return 1;
262 }