1 /* Test of conversion to UTF-32 from legacy encodings.
2 Copyright (C) 2007-2009 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>, 2007. */
29 #define SIZEOF(array) (sizeof (array) / sizeof (array[0]))
30 #define ASSERT(expr) \
35 fprintf (stderr, "%s:%d: assertion failed\n", __FILE__, __LINE__); \
42 /* Magic number for detecting bounds violations. */
43 #define MAGIC 0x1983EFF1
46 new_offsets (size_t n)
48 size_t *offsets = (size_t *) malloc ((n + 1) * sizeof (size_t));
56 static enum iconv_ilseq_handler handlers[] =
57 { iconveh_error, iconveh_question_mark, iconveh_escape_sequence };
63 /* Assume that iconv() supports at least the encodings ASCII, ISO-8859-1,
64 ISO-8859-2, and UTF-8. */
66 /* Test conversion from ISO-8859-1 to UTF-16 with no errors. */
67 for (h = 0; h < SIZEOF (handlers); h++)
69 enum iconv_ilseq_handler handler = handlers[h];
70 static const char input[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337";
71 static const uint32_t expected[] = /* Ärger mit bösen Bübchen ohne Augenmaß */
73 0xC4, 'r', 'g', 'e', 'r', ' ', 'm', 'i', 't', ' ', 'b', 0xF6, 's',
74 'e', 'n', ' ', 'B', 0xFC, 'b', 'c', 'h', 'e', 'n', ' ', 'o', 'h',
75 'n', 'e', ' ', 'A', 'u', 'g', 'e', 'n', 'm', 'a', 0xDF
77 for (o = 0; o < 2; o++)
79 size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
81 uint32_t *result = u32_conv_from_encoding ("ISO-8859-1", handler,
82 input, strlen (input),
85 ASSERT (result != NULL);
86 ASSERT (length == SIZEOF (expected));
87 ASSERT (u32_cmp (result, expected, SIZEOF (expected)) == 0);
90 for (i = 0; i < 37; i++)
91 ASSERT (offsets[i] == i);
92 ASSERT (offsets[37] == MAGIC);
99 /* Test conversion from ISO-8859-2 to UTF-16 with no errors. */
100 for (h = 0; h < SIZEOF (handlers); h++)
102 enum iconv_ilseq_handler handler = handlers[h];
103 static const char input[] = "Rafa\263 Maszkowski"; /* Rafał Maszkowski */
104 static const uint32_t expected[] =
106 'R', 'a', 'f', 'a', 0x0142, ' ', 'M', 'a', 's', 'z', 'k', 'o', 'w',
109 for (o = 0; o < 2; o++)
111 size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
113 uint32_t *result = u32_conv_from_encoding ("ISO-8859-2", handler,
114 input, strlen (input),
117 ASSERT (result != NULL);
118 ASSERT (length == SIZEOF (expected));
119 ASSERT (u32_cmp (result, expected, SIZEOF (expected)) == 0);
122 for (i = 0; i < 16; i++)
123 ASSERT (offsets[i] == i);
124 ASSERT (offsets[16] == MAGIC);
131 /* autodetect_jp is only supported when iconv() support ISO-2022-JP-2. */
132 # if defined _LIBICONV_VERSION || !(defined _AIX || defined __sgi || defined __hpux || defined __osf__)
133 /* Test conversions from autodetect_jp to UTF-16. */
134 for (h = 0; h < SIZEOF (handlers); h++)
136 enum iconv_ilseq_handler handler = handlers[h];
137 static const char input[] = "\244\263\244\363\244\313\244\301\244\317"; /* こんにちは in EUC-JP */
138 static const uint32_t expected[] = /* こんにちは */
140 0x3053, 0x3093, 0x306B, 0x3061, 0x306F
142 for (o = 0; o < 2; o++)
144 size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
146 uint32_t *result = u32_conv_from_encoding ("autodetect_jp", handler,
147 input, strlen (input),
150 ASSERT (result != NULL);
151 ASSERT (length == SIZEOF (expected));
152 ASSERT (u32_cmp (result, expected, SIZEOF (expected)) == 0);
155 for (i = 0; i < 10; i++)
156 ASSERT (offsets[i] == ((i % 2) == 0 ? i / 2 : (size_t)(-1)));
157 ASSERT (offsets[10] == MAGIC);
163 for (h = 0; h < SIZEOF (handlers); h++)
165 enum iconv_ilseq_handler handler = handlers[h];
166 static const char input[] = "\202\261\202\361\202\311\202\277\202\315"; /* こんにちは in Shift_JIS */
167 static const uint32_t expected[] = /* こんにちは */
169 0x3053, 0x3093, 0x306B, 0x3061, 0x306F
171 for (o = 0; o < 2; o++)
173 size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
175 uint32_t *result = u32_conv_from_encoding ("autodetect_jp", handler,
176 input, strlen (input),
179 ASSERT (result != NULL);
180 ASSERT (length == SIZEOF (expected));
181 ASSERT (u32_cmp (result, expected, SIZEOF (expected)) == 0);
184 for (i = 0; i < 10; i++)
185 ASSERT (offsets[i] == ((i % 2) == 0 ? i / 2 : (size_t)(-1)));
186 ASSERT (offsets[10] == MAGIC);
192 for (h = 0; h < SIZEOF (handlers); h++)
194 enum iconv_ilseq_handler handler = handlers[h];
195 static const char input[] = "\033$B$3$s$K$A$O\033(B"; /* こんにちは in ISO-2022-JP-2 */
196 static const uint32_t expected[] = /* こんにちは */
198 0x3053, 0x3093, 0x306B, 0x3061, 0x306F
200 for (o = 0; o < 2; o++)
202 size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
204 uint32_t *result = u32_conv_from_encoding ("autodetect_jp", handler,
205 input, strlen (input),
208 ASSERT (result != NULL);
209 ASSERT (length == SIZEOF (expected));
210 ASSERT (u32_cmp (result, expected, SIZEOF (expected)) == 0);
213 for (i = 0; i < 16; i++)
214 ASSERT (offsets[i] == (i == 0 ? 0 :
221 ASSERT (offsets[16] == MAGIC);