1 /* Test of conversion to UTF-16 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. */
30 #define SIZEOF(array) (sizeof (array) / sizeof (array[0]))
31 #define ASSERT(expr) \
36 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 uint16_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);
80 uint16_t *result = NULL;
82 int retval = u16_conv_from_encoding ("ISO-8859-1", handler,
83 input, strlen (input),
87 ASSERT (length == SIZEOF (expected));
88 ASSERT (result != NULL && u16_cmp (result, expected, SIZEOF (expected)) == 0);
91 for (i = 0; i < 37; i++)
92 ASSERT (offsets[i] == i);
93 ASSERT (offsets[37] == MAGIC);
100 /* Test conversion from ISO-8859-2 to UTF-16 with no errors. */
101 for (h = 0; h < SIZEOF (handlers); h++)
103 enum iconv_ilseq_handler handler = handlers[h];
104 static const char input[] = "Rafa\263 Maszkowski"; /* Rafał Maszkowski */
105 static const uint16_t expected[] =
107 'R', 'a', 'f', 'a', 0x0142, ' ', 'M', 'a', 's', 'z', 'k', 'o', 'w',
110 for (o = 0; o < 2; o++)
112 size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
113 uint16_t *result = NULL;
115 int retval = u16_conv_from_encoding ("ISO-8859-2", handler,
116 input, strlen (input),
119 ASSERT (retval == 0);
120 ASSERT (length == SIZEOF (expected));
121 ASSERT (result != NULL && u16_cmp (result, expected, SIZEOF (expected)) == 0);
124 for (i = 0; i < 16; i++)
125 ASSERT (offsets[i] == i);
126 ASSERT (offsets[16] == MAGIC);
133 /* autodetect_jp is only supported when iconv() support ISO-2022-JP-2. */
134 # if defined _LIBICONV_VERSION || !(defined _AIX || defined __sgi || defined __hpux || defined __osf__)
135 /* Test conversions from autodetect_jp to UTF-16. */
136 for (h = 0; h < SIZEOF (handlers); h++)
138 enum iconv_ilseq_handler handler = handlers[h];
139 static const char input[] = "\244\263\244\363\244\313\244\301\244\317"; /* こんにちは in EUC-JP */
140 static const uint16_t expected[] = /* こんにちは */
142 0x3053, 0x3093, 0x306B, 0x3061, 0x306F
144 for (o = 0; o < 2; o++)
146 size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
147 uint16_t *result = NULL;
149 int retval = u16_conv_from_encoding ("autodetect_jp", handler,
150 input, strlen (input),
153 ASSERT (retval == 0);
154 ASSERT (length == SIZEOF (expected));
155 ASSERT (result != NULL && u16_cmp (result, expected, SIZEOF (expected)) == 0);
158 for (i = 0; i < 10; i++)
159 ASSERT (offsets[i] == ((i % 2) == 0 ? i / 2 : (size_t)(-1)));
160 ASSERT (offsets[10] == MAGIC);
166 for (h = 0; h < SIZEOF (handlers); h++)
168 enum iconv_ilseq_handler handler = handlers[h];
169 static const char input[] = "\202\261\202\361\202\311\202\277\202\315"; /* こんにちは in Shift_JIS */
170 static const uint16_t expected[] = /* こんにちは */
172 0x3053, 0x3093, 0x306B, 0x3061, 0x306F
174 for (o = 0; o < 2; o++)
176 size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
177 uint16_t *result = NULL;
179 int retval = u16_conv_from_encoding ("autodetect_jp", handler,
180 input, strlen (input),
183 ASSERT (retval == 0);
184 ASSERT (length == SIZEOF (expected));
185 ASSERT (result != NULL && u16_cmp (result, expected, SIZEOF (expected)) == 0);
188 for (i = 0; i < 10; i++)
189 ASSERT (offsets[i] == ((i % 2) == 0 ? i / 2 : (size_t)(-1)));
190 ASSERT (offsets[10] == MAGIC);
196 for (h = 0; h < SIZEOF (handlers); h++)
198 enum iconv_ilseq_handler handler = handlers[h];
199 static const char input[] = "\033$B$3$s$K$A$O\033(B"; /* こんにちは in ISO-2022-JP-2 */
200 static const uint16_t expected[] = /* こんにちは */
202 0x3053, 0x3093, 0x306B, 0x3061, 0x306F
204 for (o = 0; o < 2; o++)
206 size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
207 uint16_t *result = NULL;
209 int retval = u16_conv_from_encoding ("autodetect_jp", handler,
210 input, strlen (input),
213 ASSERT (retval == 0);
214 ASSERT (length == SIZEOF (expected));
215 ASSERT (result != NULL && u16_cmp (result, expected, SIZEOF (expected)) == 0);
218 for (i = 0; i < 16; i++)
219 ASSERT (offsets[i] == (i == 0 ? 0 :
226 ASSERT (offsets[16] == MAGIC);