1 /* Test of conversion to UTF-32 from legacy encodings.
2 Copyright (C) 2007 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 2, or (at your option)
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, write to the Free Software Foundation,
16 Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. */
18 /* Written by Bruno Haible <bruno@clisp.org>, 2007. */
31 #define SIZEOF(array) (sizeof (array) / sizeof (array[0]))
32 #define ASSERT(expr) if (!(expr)) abort ();
34 /* Magic number for detecting bounds violations. */
35 #define MAGIC 0x1983EFF1
38 new_offsets (size_t n)
40 size_t *offsets = (size_t *) malloc ((n + 1) * sizeof (size_t));
48 static enum iconv_ilseq_handler handlers[] =
49 { iconveh_error, iconveh_question_mark, iconveh_escape_sequence };
55 /* Assume that iconv() supports at least the encodings ASCII, ISO-8859-1,
56 ISO-8859-2, and UTF-8. */
58 /* Test conversion from ISO-8859-1 to UTF-16 with no errors. */
59 for (h = 0; h < SIZEOF (handlers); h++)
61 enum iconv_ilseq_handler handler = handlers[h];
62 static const char input[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337";
63 static const uint32_t expected[] = /* Ärger mit bösen Bübchen ohne Augenmaß */
65 0xC4, 'r', 'g', 'e', 'r', ' ', 'm', 'i', 't', ' ', 'b', 0xF6, 's',
66 'e', 'n', ' ', 'B', 0xFC, 'b', 'c', 'h', 'e', 'n', ' ', 'o', 'h',
67 'n', 'e', ' ', 'A', 'u', 'g', 'e', 'n', 'm', 'a', 0xDF
69 for (o = 0; o < 2; o++)
71 size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
72 uint32_t *result = NULL;
74 int retval = u32_conv_from_encoding ("ISO-8859-1", handler,
75 input, strlen (input),
79 ASSERT (length == SIZEOF (expected));
80 ASSERT (result != NULL && u32_cmp (result, expected, SIZEOF (expected)) == 0);
83 for (i = 0; i < 37; i++)
84 ASSERT (offsets[i] == i);
85 ASSERT (offsets[37] == MAGIC);
92 /* Test conversion from ISO-8859-2 to UTF-16 with no errors. */
93 for (h = 0; h < SIZEOF (handlers); h++)
95 enum iconv_ilseq_handler handler = handlers[h];
96 static const char input[] = "Rafa\263 Maszkowski"; /* Rafał Maszkowski */
97 static const uint32_t expected[] =
99 'R', 'a', 'f', 'a', 0x0142, ' ', 'M', 'a', 's', 'z', 'k', 'o', 'w',
102 for (o = 0; o < 2; o++)
104 size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
105 uint32_t *result = NULL;
107 int retval = u32_conv_from_encoding ("ISO-8859-2", handler,
108 input, strlen (input),
111 ASSERT (retval == 0);
112 ASSERT (length == SIZEOF (expected));
113 ASSERT (result != NULL && u32_cmp (result, expected, SIZEOF (expected)) == 0);
116 for (i = 0; i < 16; i++)
117 ASSERT (offsets[i] == i);
118 ASSERT (offsets[16] == MAGIC);
125 /* autodetect_jp is only supported when iconv() support ISO-2022-JP-2. */
126 # if defined _LIBICONV_VERSION || !(defined _AIX || defined __sgi || defined __hpux || defined __osf__)
127 /* Test conversions from autodetect_jp to UTF-16. */
128 for (h = 0; h < SIZEOF (handlers); h++)
130 enum iconv_ilseq_handler handler = handlers[h];
131 static const char input[] = "\244\263\244\363\244\313\244\301\244\317"; /* こんにちは in EUC-JP */
132 static const uint32_t expected[] = /* こんにちは */
134 0x3053, 0x3093, 0x306B, 0x3061, 0x306F
136 for (o = 0; o < 2; o++)
138 size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
139 uint32_t *result = NULL;
141 int retval = u32_conv_from_encoding ("autodetect_jp", handler,
142 input, strlen (input),
145 ASSERT (retval == 0);
146 ASSERT (length == SIZEOF (expected));
147 ASSERT (result != NULL && u32_cmp (result, expected, SIZEOF (expected)) == 0);
150 for (i = 0; i < 10; i++)
151 ASSERT (offsets[i] == ((i % 2) == 0 ? i / 2 : (size_t)(-1)));
152 ASSERT (offsets[10] == MAGIC);
158 for (h = 0; h < SIZEOF (handlers); h++)
160 enum iconv_ilseq_handler handler = handlers[h];
161 static const char input[] = "\202\261\202\361\202\311\202\277\202\315"; /* こんにちは in Shift_JIS */
162 static const uint32_t expected[] = /* こんにちは */
164 0x3053, 0x3093, 0x306B, 0x3061, 0x306F
166 for (o = 0; o < 2; o++)
168 size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
169 uint32_t *result = NULL;
171 int retval = u32_conv_from_encoding ("autodetect_jp", handler,
172 input, strlen (input),
175 ASSERT (retval == 0);
176 ASSERT (length == SIZEOF (expected));
177 ASSERT (result != NULL && u32_cmp (result, expected, SIZEOF (expected)) == 0);
180 for (i = 0; i < 10; i++)
181 ASSERT (offsets[i] == ((i % 2) == 0 ? i / 2 : (size_t)(-1)));
182 ASSERT (offsets[10] == MAGIC);
188 for (h = 0; h < SIZEOF (handlers); h++)
190 enum iconv_ilseq_handler handler = handlers[h];
191 static const char input[] = "\033$B$3$s$K$A$O\033(B"; /* こんにちは in ISO-2022-JP-2 */
192 static const uint32_t expected[] = /* こんにちは */
194 0x3053, 0x3093, 0x306B, 0x3061, 0x306F
196 for (o = 0; o < 2; o++)
198 size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
199 uint32_t *result = NULL;
201 int retval = u32_conv_from_encoding ("autodetect_jp", handler,
202 input, strlen (input),
205 ASSERT (retval == 0);
206 ASSERT (length == SIZEOF (expected));
207 ASSERT (result != NULL && u32_cmp (result, expected, SIZEOF (expected)) == 0);
210 for (i = 0; i < 16; i++)
211 ASSERT (offsets[i] == (i == 0 ? 0 :
218 ASSERT (offsets[16] == MAGIC);