1 /* Test of conversion to UTF-32 from legacy encodings.
2 Copyright (C) 2007-2013 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 /* Magic number for detecting bounds violations. */
30 #define MAGIC 0x1983EFF1
33 new_offsets (size_t n)
35 size_t *offsets = (size_t *) malloc ((n + 1) * sizeof (size_t));
43 static enum iconv_ilseq_handler handlers[] =
44 { iconveh_error, iconveh_question_mark, iconveh_escape_sequence };
50 /* Assume that iconv() supports at least the encodings ASCII, ISO-8859-1,
51 ISO-8859-2, and UTF-8. */
53 /* Test conversion from ISO-8859-1 to UTF-16 with no errors. */
54 for (h = 0; h < SIZEOF (handlers); h++)
56 enum iconv_ilseq_handler handler = handlers[h];
57 static const char input[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337";
58 static const uint32_t expected[] = /* Ärger mit bösen Bübchen ohne Augenmaß */
60 0xC4, 'r', 'g', 'e', 'r', ' ', 'm', 'i', 't', ' ', 'b', 0xF6, 's',
61 'e', 'n', ' ', 'B', 0xFC, 'b', 'c', 'h', 'e', 'n', ' ', 'o', 'h',
62 'n', 'e', ' ', 'A', 'u', 'g', 'e', 'n', 'm', 'a', 0xDF
64 for (o = 0; o < 2; o++)
66 size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
68 uint32_t *result = u32_conv_from_encoding ("ISO-8859-1", handler,
69 input, strlen (input),
72 ASSERT (result != NULL);
73 ASSERT (length == SIZEOF (expected));
74 ASSERT (u32_cmp (result, expected, SIZEOF (expected)) == 0);
77 for (i = 0; i < 37; i++)
78 ASSERT (offsets[i] == i);
79 ASSERT (offsets[37] == MAGIC);
86 /* Test conversion from ISO-8859-2 to UTF-16 with no errors. */
87 for (h = 0; h < SIZEOF (handlers); h++)
89 enum iconv_ilseq_handler handler = handlers[h];
90 static const char input[] = "Rafa\263 Maszkowski"; /* Rafał Maszkowski */
91 static const uint32_t expected[] =
93 'R', 'a', 'f', 'a', 0x0142, ' ', 'M', 'a', 's', 'z', 'k', 'o', 'w',
96 for (o = 0; o < 2; o++)
98 size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
100 uint32_t *result = u32_conv_from_encoding ("ISO-8859-2", handler,
101 input, strlen (input),
104 ASSERT (result != NULL);
105 ASSERT (length == SIZEOF (expected));
106 ASSERT (u32_cmp (result, expected, SIZEOF (expected)) == 0);
109 for (i = 0; i < 16; i++)
110 ASSERT (offsets[i] == i);
111 ASSERT (offsets[16] == MAGIC);
118 /* autodetect_jp is only supported when iconv() support ISO-2022-JP-2. */
119 # if defined _LIBICONV_VERSION || !(defined _AIX || defined __sgi || defined __hpux || defined __osf__ || defined __sun)
120 /* Test conversions from autodetect_jp to UTF-16. */
121 for (h = 0; h < SIZEOF (handlers); h++)
123 enum iconv_ilseq_handler handler = handlers[h];
124 static const char input[] = "\244\263\244\363\244\313\244\301\244\317"; /* こんにちは in EUC-JP */
125 static const uint32_t expected[] = /* こんにちは */
127 0x3053, 0x3093, 0x306B, 0x3061, 0x306F
129 for (o = 0; o < 2; o++)
131 size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
133 uint32_t *result = u32_conv_from_encoding ("autodetect_jp", handler,
134 input, strlen (input),
137 ASSERT (result != NULL);
138 ASSERT (length == SIZEOF (expected));
139 ASSERT (u32_cmp (result, expected, SIZEOF (expected)) == 0);
142 for (i = 0; i < 10; i++)
143 ASSERT (offsets[i] == ((i % 2) == 0 ? i / 2 : (size_t)(-1)));
144 ASSERT (offsets[10] == MAGIC);
150 for (h = 0; h < SIZEOF (handlers); h++)
152 enum iconv_ilseq_handler handler = handlers[h];
153 static const char input[] = "\202\261\202\361\202\311\202\277\202\315"; /* こんにちは in Shift_JIS */
154 static const uint32_t expected[] = /* こんにちは */
156 0x3053, 0x3093, 0x306B, 0x3061, 0x306F
158 for (o = 0; o < 2; o++)
160 size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
162 uint32_t *result = u32_conv_from_encoding ("autodetect_jp", handler,
163 input, strlen (input),
166 ASSERT (result != NULL);
167 ASSERT (length == SIZEOF (expected));
168 ASSERT (u32_cmp (result, expected, SIZEOF (expected)) == 0);
171 for (i = 0; i < 10; i++)
172 ASSERT (offsets[i] == ((i % 2) == 0 ? i / 2 : (size_t)(-1)));
173 ASSERT (offsets[10] == MAGIC);
179 for (h = 0; h < SIZEOF (handlers); h++)
181 enum iconv_ilseq_handler handler = handlers[h];
182 static const char input[] = "\033$B$3$s$K$A$O\033(B"; /* こんにちは in ISO-2022-JP-2 */
183 static const uint32_t expected[] = /* こんにちは */
185 0x3053, 0x3093, 0x306B, 0x3061, 0x306F
187 for (o = 0; o < 2; o++)
189 size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
191 uint32_t *result = u32_conv_from_encoding ("autodetect_jp", handler,
192 input, strlen (input),
195 ASSERT (result != NULL);
196 ASSERT (length == SIZEOF (expected));
197 ASSERT (u32_cmp (result, expected, SIZEOF (expected)) == 0);
200 for (i = 0; i < 16; i++)
201 ASSERT (offsets[i] == (i == 0 ? 0 :
208 ASSERT (offsets[16] == MAGIC);