ce188d4d |
1 | /* |
2 | * Copyright (C) 2001 Edmund Grimley Evans <edmundo@rano.org> |
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 2 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 along |
15 | * with this program; if not, write to the Free Software Foundation, Inc., |
16 | * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. |
17 | */ |
18 | |
19 | #ifdef HAVE_CONFIG_H |
20 | # include <config.h> |
21 | #endif |
22 | |
23 | #include <assert.h> |
24 | #include <string.h> |
25 | |
26 | #include "charset.h" |
27 | |
28 | void test_any(struct charset *charset) |
29 | { |
30 | int wc; |
31 | char s[2]; |
32 | |
33 | assert(charset); |
34 | |
35 | /* Decoder */ |
36 | |
37 | assert(charset_mbtowc(charset, 0, 0, 0) == 0); |
38 | assert(charset_mbtowc(charset, 0, 0, 1) == 0); |
39 | assert(charset_mbtowc(charset, 0, (char *)(-1), 0) == 0); |
40 | |
41 | assert(charset_mbtowc(charset, 0, "a", 0) == 0); |
42 | assert(charset_mbtowc(charset, 0, "", 1) == 0); |
43 | assert(charset_mbtowc(charset, 0, "b", 1) == 1); |
44 | assert(charset_mbtowc(charset, 0, "", 2) == 0); |
45 | assert(charset_mbtowc(charset, 0, "c", 2) == 1); |
46 | |
47 | wc = 'x'; |
48 | assert(charset_mbtowc(charset, &wc, "a", 0) == 0 && wc == 'x'); |
49 | assert(charset_mbtowc(charset, &wc, "", 1) == 0 && wc == 0); |
50 | assert(charset_mbtowc(charset, &wc, "b", 1) == 1 && wc == 'b'); |
51 | assert(charset_mbtowc(charset, &wc, "", 2) == 0 && wc == 0); |
52 | assert(charset_mbtowc(charset, &wc, "c", 2) == 1 && wc == 'c'); |
53 | |
54 | /* Encoder */ |
55 | |
56 | assert(charset_wctomb(charset, 0, 0) == 0); |
57 | |
58 | s[0] = s[1] = '.'; |
59 | assert(charset_wctomb(charset, s, 0) == 1 && |
60 | s[0] == '\0' && s[1] == '.'); |
61 | assert(charset_wctomb(charset, s, 'x') == 1 && |
62 | s[0] == 'x' && s[1] == '.'); |
63 | } |
64 | |
65 | void test_utf8() |
66 | { |
67 | struct charset *charset; |
68 | int wc; |
69 | char s[8]; |
70 | |
71 | charset = charset_find("UTF-8"); |
72 | test_any(charset); |
73 | |
74 | /* Decoder */ |
75 | wc = 0; |
76 | assert(charset_mbtowc(charset, &wc, "\177", 1) == 1 && wc == 127); |
77 | assert(charset_mbtowc(charset, &wc, "\200", 2) == -1); |
78 | assert(charset_mbtowc(charset, &wc, "\301\277", 9) == -1); |
79 | assert(charset_mbtowc(charset, &wc, "\302\200", 1) == -1); |
80 | assert(charset_mbtowc(charset, &wc, "\302\200", 2) == 2 && wc == 128); |
81 | assert(charset_mbtowc(charset, &wc, "\302\200", 3) == 2 && wc == 128); |
82 | assert(charset_mbtowc(charset, &wc, "\340\237\200", 9) == -1); |
83 | assert(charset_mbtowc(charset, &wc, "\340\240\200", 9) == 3 && |
84 | wc == 1 << 11); |
85 | assert(charset_mbtowc(charset, &wc, "\360\217\277\277", 9) == -1); |
86 | assert(charset_mbtowc(charset, &wc, "\360\220\200\200", 9) == 4 && |
87 | wc == 1 << 16); |
88 | assert(charset_mbtowc(charset, &wc, "\370\207\277\277\277", 9) == -1); |
89 | assert(charset_mbtowc(charset, &wc, "\370\210\200\200\200", 9) == 5 && |
90 | wc == 1 << 21); |
91 | assert(charset_mbtowc(charset, &wc, "\374\203\277\277\277\277", 9) == -1); |
92 | assert(charset_mbtowc(charset, &wc, "\374\204\200\200\200\200", 9) == 6 && |
93 | wc == 1 << 26); |
94 | assert(charset_mbtowc(charset, &wc, "\375\277\277\277\277\277", 9) == 6 && |
95 | wc == 0x7fffffff); |
96 | |
97 | assert(charset_mbtowc(charset, &wc, "\302\000", 2) == -1); |
98 | assert(charset_mbtowc(charset, &wc, "\302\300", 2) == -1); |
99 | assert(charset_mbtowc(charset, &wc, "\340\040\200", 9) == -1); |
100 | assert(charset_mbtowc(charset, &wc, "\340\340\200", 9) == -1); |
101 | assert(charset_mbtowc(charset, &wc, "\340\240\000", 9) == -1); |
102 | assert(charset_mbtowc(charset, &wc, "\340\240\300", 9) == -1); |
103 | assert(charset_mbtowc(charset, &wc, "\360\020\200\200", 9) == -1); |
104 | assert(charset_mbtowc(charset, &wc, "\360\320\200\200", 9) == -1); |
105 | assert(charset_mbtowc(charset, &wc, "\360\220\000\200", 9) == -1); |
106 | assert(charset_mbtowc(charset, &wc, "\360\220\300\200", 9) == -1); |
107 | assert(charset_mbtowc(charset, &wc, "\360\220\200\000", 9) == -1); |
108 | assert(charset_mbtowc(charset, &wc, "\360\220\200\300", 9) == -1); |
109 | assert(charset_mbtowc(charset, &wc, "\375\077\277\277\277\277", 9) == -1); |
110 | assert(charset_mbtowc(charset, &wc, "\375\377\277\277\277\277", 9) == -1); |
111 | assert(charset_mbtowc(charset, &wc, "\375\277\077\277\277\277", 9) == -1); |
112 | assert(charset_mbtowc(charset, &wc, "\375\277\377\277\277\277", 9) == -1); |
113 | assert(charset_mbtowc(charset, &wc, "\375\277\277\277\077\277", 9) == -1); |
114 | assert(charset_mbtowc(charset, &wc, "\375\277\277\277\377\277", 9) == -1); |
115 | assert(charset_mbtowc(charset, &wc, "\375\277\277\277\277\077", 9) == -1); |
116 | assert(charset_mbtowc(charset, &wc, "\375\277\277\277\277\377", 9) == -1); |
117 | |
118 | assert(charset_mbtowc(charset, &wc, "\376\277\277\277\277\277", 9) == -1); |
119 | assert(charset_mbtowc(charset, &wc, "\377\277\277\277\277\277", 9) == -1); |
120 | |
121 | /* Encoder */ |
122 | safe_strncpy(s, ".......", sizeof(s)); |
123 | assert(charset_wctomb(charset, s, 1 << 31) == -1 && |
124 | !strcmp(s, ".......")); |
125 | assert(charset_wctomb(charset, s, 127) == 1 && |
126 | !strcmp(s, "\177......")); |
127 | assert(charset_wctomb(charset, s, 128) == 2 && |
128 | !strcmp(s, "\302\200.....")); |
129 | assert(charset_wctomb(charset, s, 0x7ff) == 2 && |
130 | !strcmp(s, "\337\277.....")); |
131 | assert(charset_wctomb(charset, s, 0x800) == 3 && |
132 | !strcmp(s, "\340\240\200....")); |
133 | assert(charset_wctomb(charset, s, 0xffff) == 3 && |
134 | !strcmp(s, "\357\277\277....")); |
135 | assert(charset_wctomb(charset, s, 0x10000) == 4 && |
136 | !strcmp(s, "\360\220\200\200...")); |
137 | assert(charset_wctomb(charset, s, 0x1fffff) == 4 && |
138 | !strcmp(s, "\367\277\277\277...")); |
139 | assert(charset_wctomb(charset, s, 0x200000) == 5 && |
140 | !strcmp(s, "\370\210\200\200\200..")); |
141 | assert(charset_wctomb(charset, s, 0x3ffffff) == 5 && |
142 | !strcmp(s, "\373\277\277\277\277..")); |
143 | assert(charset_wctomb(charset, s, 0x4000000) == 6 && |
144 | !strcmp(s, "\374\204\200\200\200\200.")); |
145 | assert(charset_wctomb(charset, s, 0x7fffffff) == 6 && |
146 | !strcmp(s, "\375\277\277\277\277\277.")); |
147 | } |
148 | |
149 | void test_ascii() |
150 | { |
151 | struct charset *charset; |
152 | int wc; |
153 | char s[3]; |
154 | |
155 | charset = charset_find("us-ascii"); |
156 | test_any(charset); |
157 | |
158 | /* Decoder */ |
159 | wc = 0; |
160 | assert(charset_mbtowc(charset, &wc, "\177", 2) == 1 && wc == 127); |
161 | assert(charset_mbtowc(charset, &wc, "\200", 2) == -1); |
162 | |
163 | /* Encoder */ |
164 | safe_strncpy(s, "..", sizeof(s)); |
165 | assert(charset_wctomb(charset, s, 256) == -1 && !strcmp(s, "..")); |
166 | assert(charset_wctomb(charset, s, 255) == -1); |
167 | assert(charset_wctomb(charset, s, 128) == -1); |
168 | assert(charset_wctomb(charset, s, 127) == 1 && !strcmp(s, "\177.")); |
169 | } |
170 | |
171 | void test_iso1() |
172 | { |
173 | struct charset *charset; |
174 | int wc; |
175 | char s[3]; |
176 | |
177 | charset = charset_find("iso-8859-1"); |
178 | test_any(charset); |
179 | |
180 | /* Decoder */ |
181 | wc = 0; |
182 | assert(charset_mbtowc(charset, &wc, "\302\200", 9) == 1 && wc == 0xc2); |
183 | |
184 | /* Encoder */ |
185 | safe_strncpy(s, "..", sizeof(s)); |
186 | assert(charset_wctomb(charset, s, 256) == -1 && !strcmp(s, "..")); |
187 | assert(charset_wctomb(charset, s, 255) == 1 && !strcmp(s, "\377.")); |
188 | assert(charset_wctomb(charset, s, 128) == 1 && !strcmp(s, "\200.")); |
189 | } |
190 | |
191 | void test_iso2() |
192 | { |
193 | struct charset *charset; |
194 | int wc; |
195 | char s[3]; |
196 | |
197 | charset = charset_find("iso-8859-2"); |
198 | test_any(charset); |
199 | |
200 | /* Decoder */ |
201 | wc = 0; |
202 | assert(charset_mbtowc(charset, &wc, "\302\200", 9) == 1 && wc == 0xc2); |
203 | assert(charset_mbtowc(charset, &wc, "\377", 2) == 1 && wc == 0x2d9); |
204 | |
205 | /* Encoder */ |
206 | safe_strncpy(s, "..", sizeof(s)); |
207 | assert(charset_wctomb(charset, s, 256) == -1 && !strcmp(s, "..")); |
208 | assert(charset_wctomb(charset, s, 255) == -1 && !strcmp(s, "..")); |
209 | assert(charset_wctomb(charset, s, 258) == 1 && !strcmp(s, "\303.")); |
210 | assert(charset_wctomb(charset, s, 128) == 1 && !strcmp(s, "\200.")); |
211 | } |
212 | |
213 | void test_convert() |
214 | { |
215 | const char *p; |
216 | char *q, *r; |
217 | char s[256]; |
218 | size_t n, n2; |
219 | int i; |
220 | |
221 | p = "\000x\302\200\375\277\277\277\277\277"; |
222 | assert(charset_convert("UTF-8", "UTF-8", p, 10, &q, &n) == 0 && |
223 | n == 10 && !strcmp(p, q)); |
224 | assert(charset_convert("UTF-8", "UTF-8", "x\301\277y", 4, &q, &n) == 2 && |
225 | n == 4 && !strcmp(q, "x##y")); |
226 | assert(charset_convert("UTF-8", "UTF-8", "x\301\277y", 4, 0, &n) == 2 && |
227 | n == 4); |
228 | assert(charset_convert("UTF-8", "UTF-8", "x\301\277y", 4, &q, 0) == 2 && |
229 | !strcmp(q, "x##y")); |
230 | assert(charset_convert("UTF-8", "iso-8859-1", |
231 | "\302\200\304\200x", 5, &q, &n) == 1 && |
232 | n == 3 && !strcmp(q, "\200?x")); |
233 | assert(charset_convert("iso-8859-1", "UTF-8", |
234 | "\000\200\377", 3, &q, &n) == 0 && |
235 | n == 5 && !memcmp(q, "\000\302\200\303\277", 5)); |
236 | assert(charset_convert("iso-8859-1", "iso-8859-1", |
237 | "\000\200\377", 3, &q, &n) == 0 && |
238 | n == 3 && !memcmp(q, "\000\200\377", 3)); |
239 | |
240 | assert(charset_convert("iso-8859-2", "utf-8", "\300", 1, &q, &n) == 0 && |
241 | n == 2 && !strcmp(q, "\305\224")); |
242 | assert(charset_convert("utf-8", "iso-8859-2", "\305\224", 2, &q, &n) == 0 && |
243 | n == 1 && !strcmp(q, "\300")); |
244 | |
245 | for (i = 0; i < 256; i++) |
246 | s[i] = i; |
247 | |
248 | assert(charset_convert("iso-8859-2", "utf-8", s, 256, &q, &n) == 0); |
249 | assert(charset_convert("utf-8", "iso-8859-2", q, n, &r, &n2) == 0); |
250 | assert(n2 == 256 && !memcmp(r, s, n2)); |
251 | } |
252 | |
253 | int main() |
254 | { |
255 | test_utf8(); |
256 | test_ascii(); |
257 | test_iso1(); |
258 | test_iso2(); |
259 | |
260 | test_convert(); |
261 | |
262 | return 0; |
263 | } |