1 /* Test of u8_check() function.
2 Copyright (C) 2010-2023 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 /* Written by Bruno Haible <bruno@clisp.org>, 2010. */
18
19 #include <config.h>
20
21 #include "unistr.h"
22
23 #include "macros.h"
24
25 int
26 main ()
27 {
28 /* Test empty string. */
29 {
30 static const uint8_t input[] = "";
31 ASSERT (u8_check (input, 0) == NULL);
32 }
33
34 /* Test valid non-empty string. */
35 {
36 static const uint8_t input[] = /* "Данило Шеган" */
37 "\320\224\320\260\320\275\320\270\320\273\320\276 \320\250\320\265\320\263\320\260\320\275";
38 ASSERT (u8_check (input, sizeof (input) - 1) == NULL);
39 }
40
41 /* Test out-of-range character with 4 bytes: U+110000. */
42 {
43 static const uint8_t input[] = "\320\224\320\260\364\220\200\200";
44 ASSERT (u8_check (input, sizeof (input) - 1) == input + 4);
45 }
46
47 /* Test out-of-range character with 5 bytes: U+200000. */
48 {
49 static const uint8_t input[] = "\320\224\320\260\370\210\200\200\200";
50 ASSERT (u8_check (input, sizeof (input) - 1) == input + 4);
51 }
52
53 /* Test out-of-range character with 6 bytes: U+4000000. */
54 {
55 static const uint8_t input[] = "\320\224\320\260\374\204\200\200\200\200";
56 ASSERT (u8_check (input, sizeof (input) - 1) == input + 4);
57 }
58
59 /* Test invalid lead byte. */
60 {
61 static const uint8_t input[] = "\320\224\320\260\376\200\200\200\200\200";
62 ASSERT (u8_check (input, sizeof (input) - 1) == input + 4);
63 }
64 {
65 static const uint8_t input[] = "\320\224\320\260\377\200\200\200\200\200";
66 ASSERT (u8_check (input, sizeof (input) - 1) == input + 4);
67 }
68
69 /* Test overlong 2-byte character. */
70 {
71 static const uint8_t input[] = "\320\224\320\260\301\200";
72 ASSERT (u8_check (input, sizeof (input) - 1) == input + 4);
73 }
74
75 /* Test overlong 3-byte character. */
76 {
77 static const uint8_t input[] = "\320\224\320\260\340\200\277";
78 ASSERT (u8_check (input, sizeof (input) - 1) == input + 4);
79 }
80
81 /* Test overlong 4-byte character. */
82 {
83 static const uint8_t input[] = "\320\224\320\260\360\200\277\277";
84 ASSERT (u8_check (input, sizeof (input) - 1) == input + 4);
85 }
86
87 /* Test invalid bytes in 2-byte character. */
88 {
89 static const uint8_t input[] = "\320\224\320\260\302\200";
90 ASSERT (u8_check (input, sizeof (input) - 1) == NULL);
91 }
92 {
93 static const uint8_t input[] = "\320\224\320\260\302\100";
94 ASSERT (u8_check (input, sizeof (input) - 1) == input + 4);
95 }
96 {
97 static const uint8_t input[] = "\320\224\320\260\302\300";
98 ASSERT (u8_check (input, sizeof (input) - 1) == input + 4);
99 }
100
101 /* Test invalid bytes in 3-byte character. */
102 {
103 static const uint8_t input[] = "\320\224\320\260\342\200\200";
104 ASSERT (u8_check (input, sizeof (input) - 1) == NULL);
105 }
106 {
107 static const uint8_t input[] = "\320\224\320\260\342\100\200";
108 ASSERT (u8_check (input, sizeof (input) - 1) == input + 4);
109 }
110 {
111 static const uint8_t input[] = "\320\224\320\260\342\300\200";
112 ASSERT (u8_check (input, sizeof (input) - 1) == input + 4);
113 }
114 {
115 static const uint8_t input[] = "\320\224\320\260\342\200\100";
116 ASSERT (u8_check (input, sizeof (input) - 1) == input + 4);
117 }
118 {
119 static const uint8_t input[] = "\320\224\320\260\342\200\300";
120 ASSERT (u8_check (input, sizeof (input) - 1) == input + 4);
121 }
122
123 /* Test invalid bytes in 4-byte character. */
124 {
125 static const uint8_t input[] = "\320\224\320\260\362\200\200\200";
126 ASSERT (u8_check (input, sizeof (input) - 1) == NULL);
127 }
128 {
129 static const uint8_t input[] = "\320\224\320\260\362\100\200\200";
130 ASSERT (u8_check (input, sizeof (input) - 1) == input + 4);
131 }
132 {
133 static const uint8_t input[] = "\320\224\320\260\362\300\200\200";
134 ASSERT (u8_check (input, sizeof (input) - 1) == input + 4);
135 }
136 {
137 static const uint8_t input[] = "\320\224\320\260\362\200\100\200";
138 ASSERT (u8_check (input, sizeof (input) - 1) == input + 4);
139 }
140 {
141 static const uint8_t input[] = "\320\224\320\260\362\200\300\200";
142 ASSERT (u8_check (input, sizeof (input) - 1) == input + 4);
143 }
144 {
145 static const uint8_t input[] = "\320\224\320\260\362\200\200\100";
146 ASSERT (u8_check (input, sizeof (input) - 1) == input + 4);
147 }
148 {
149 static const uint8_t input[] = "\320\224\320\260\362\200\200\300";
150 ASSERT (u8_check (input, sizeof (input) - 1) == input + 4);
151 }
152
153 /* Test truncated/incomplete 2-byte character. */
154 {
155 static const uint8_t input[] = "\320\224\320\260\302";
156 ASSERT (u8_check (input, sizeof (input) - 1) == input + 4);
157 }
158
159 /* Test truncated/incomplete 3-byte character. */
160 {
161 static const uint8_t input[] = "\320\224\320\260\342\200";
162 ASSERT (u8_check (input, sizeof (input) - 1) == input + 4);
163 }
164
165 /* Test truncated/incomplete 4-byte character. */
166 {
167 static const uint8_t input[] = "\320\224\320\260\362\200\200";
168 ASSERT (u8_check (input, sizeof (input) - 1) == input + 4);
169 }
170
171 /* Test missing lead byte. */
172 {
173 static const uint8_t input[] = "\320\224\320\260\200\200\200\200\200";
174 ASSERT (u8_check (input, sizeof (input) - 1) == input + 4);
175 }
176
177 /* Test surrogate codepoints. */
178 {
179 static const uint8_t input[] = "\320\224\320\260\355\240\200\355\260\200";
180 ASSERT (u8_check (input, sizeof (input) - 1) == input + 4);
181 }
182 {
183 static const uint8_t input[] = "\320\224\320\260\355\260\200";
184 ASSERT (u8_check (input, sizeof (input) - 1) == input + 4);
185 }
186
187 return 0;
188 }