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 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__); \
41 /* Magic number for detecting bounds violations. */
42 #define MAGIC 0x1983EFF1
45 new_offsets (size_t n)
47 size_t *offsets = (size_t *) malloc ((n + 1) * sizeof (size_t));
55 static enum iconv_ilseq_handler handlers[] =
56 { iconveh_error, iconveh_question_mark, iconveh_escape_sequence };
62 /* Assume that iconv() supports at least the encodings ASCII, ISO-8859-1,
63 ISO-8859-2, and UTF-8. */
65 /* Test conversion from ISO-8859-1 to UTF-16 with no errors. */
66 for (h = 0; h < SIZEOF (handlers); h++)
68 enum iconv_ilseq_handler handler = handlers[h];
69 static const char input[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337";
70 static const uint16_t expected[] = /* Ärger mit bösen Bübchen ohne Augenmaß */
72 0xC4, 'r', 'g', 'e', 'r', ' ', 'm', 'i', 't', ' ', 'b', 0xF6, 's',
73 'e', 'n', ' ', 'B', 0xFC, 'b', 'c', 'h', 'e', 'n', ' ', 'o', 'h',
74 'n', 'e', ' ', 'A', 'u', 'g', 'e', 'n', 'm', 'a', 0xDF
76 for (o = 0; o < 2; o++)
78 size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
79 uint16_t *result = NULL;
81 int retval = u16_conv_from_encoding ("ISO-8859-1", handler,
82 input, strlen (input),
86 ASSERT (length == SIZEOF (expected));
87 ASSERT (result != NULL && u16_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 uint16_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);
112 uint16_t *result = NULL;
114 int retval = u16_conv_from_encoding ("ISO-8859-2", handler,
115 input, strlen (input),
118 ASSERT (retval == 0);
119 ASSERT (length == SIZEOF (expected));
120 ASSERT (result != NULL && u16_cmp (result, expected, SIZEOF (expected)) == 0);
123 for (i = 0; i < 16; i++)
124 ASSERT (offsets[i] == i);
125 ASSERT (offsets[16] == MAGIC);
132 /* autodetect_jp is only supported when iconv() support ISO-2022-JP-2. */
133 # if defined _LIBICONV_VERSION || !(defined _AIX || defined __sgi || defined __hpux || defined __osf__)
134 /* Test conversions from autodetect_jp to UTF-16. */
135 for (h = 0; h < SIZEOF (handlers); h++)
137 enum iconv_ilseq_handler handler = handlers[h];
138 static const char input[] = "\244\263\244\363\244\313\244\301\244\317"; /* こんにちは in EUC-JP */
139 static const uint16_t expected[] = /* こんにちは */
141 0x3053, 0x3093, 0x306B, 0x3061, 0x306F
143 for (o = 0; o < 2; o++)
145 size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
146 uint16_t *result = NULL;
148 int retval = u16_conv_from_encoding ("autodetect_jp", handler,
149 input, strlen (input),
152 ASSERT (retval == 0);
153 ASSERT (length == SIZEOF (expected));
154 ASSERT (result != NULL && u16_cmp (result, expected, SIZEOF (expected)) == 0);
157 for (i = 0; i < 10; i++)
158 ASSERT (offsets[i] == ((i % 2) == 0 ? i / 2 : (size_t)(-1)));
159 ASSERT (offsets[10] == MAGIC);
165 for (h = 0; h < SIZEOF (handlers); h++)
167 enum iconv_ilseq_handler handler = handlers[h];
168 static const char input[] = "\202\261\202\361\202\311\202\277\202\315"; /* こんにちは in Shift_JIS */
169 static const uint16_t expected[] = /* こんにちは */
171 0x3053, 0x3093, 0x306B, 0x3061, 0x306F
173 for (o = 0; o < 2; o++)
175 size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
176 uint16_t *result = NULL;
178 int retval = u16_conv_from_encoding ("autodetect_jp", handler,
179 input, strlen (input),
182 ASSERT (retval == 0);
183 ASSERT (length == SIZEOF (expected));
184 ASSERT (result != NULL && u16_cmp (result, expected, SIZEOF (expected)) == 0);
187 for (i = 0; i < 10; i++)
188 ASSERT (offsets[i] == ((i % 2) == 0 ? i / 2 : (size_t)(-1)));
189 ASSERT (offsets[10] == MAGIC);
195 for (h = 0; h < SIZEOF (handlers); h++)
197 enum iconv_ilseq_handler handler = handlers[h];
198 static const char input[] = "\033$B$3$s$K$A$O\033(B"; /* こんにちは in ISO-2022-JP-2 */
199 static const uint16_t expected[] = /* こんにちは */
201 0x3053, 0x3093, 0x306B, 0x3061, 0x306F
203 for (o = 0; o < 2; o++)
205 size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
206 uint16_t *result = NULL;
208 int retval = u16_conv_from_encoding ("autodetect_jp", handler,
209 input, strlen (input),
212 ASSERT (retval == 0);
213 ASSERT (length == SIZEOF (expected));
214 ASSERT (result != NULL && u16_cmp (result, expected, SIZEOF (expected)) == 0);
217 for (i = 0; i < 16; i++)
218 ASSERT (offsets[i] == (i == 0 ? 0 :
225 ASSERT (offsets[16] == MAGIC);