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. */
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 uint16_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 uint16_t *result = NULL;
74 int retval = u16_conv_from_encoding ("ISO-8859-1", handler,
75 input, strlen (input),
79 ASSERT (length == SIZEOF (expected));
80 ASSERT (result != NULL && u16_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 uint16_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 uint16_t *result = NULL;
107 int retval = u16_conv_from_encoding ("ISO-8859-2", handler,
108 input, strlen (input),
111 ASSERT (retval == 0);
112 ASSERT (length == SIZEOF (expected));
113 ASSERT (result != NULL && u16_cmp (result, expected, SIZEOF (expected)) == 0);
116 for (i = 0; i < 16; i++)
117 ASSERT (offsets[i] == i);
118 ASSERT (offsets[16] == MAGIC);
125 /* Test conversions from autodetect_jp to UTF-16. */
126 for (h = 0; h < SIZEOF (handlers); h++)
128 enum iconv_ilseq_handler handler = handlers[h];
129 static const char input[] = "\244\263\244\363\244\313\244\301\244\317"; /* こんにちは in EUC-JP */
130 static const uint16_t expected[] = /* こんにちは */
132 0x3053, 0x3093, 0x306B, 0x3061, 0x306F
134 for (o = 0; o < 2; o++)
136 size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
137 uint16_t *result = NULL;
139 int retval = u16_conv_from_encoding ("autodetect_jp", handler,
140 input, strlen (input),
143 ASSERT (retval == 0);
144 ASSERT (length == SIZEOF (expected));
145 ASSERT (result != NULL && u16_cmp (result, expected, SIZEOF (expected)) == 0);
148 for (i = 0; i < 10; i++)
149 ASSERT (offsets[i] == ((i % 2) == 0 ? i / 2 : (size_t)(-1)));
150 ASSERT (offsets[10] == MAGIC);
156 for (h = 0; h < SIZEOF (handlers); h++)
158 enum iconv_ilseq_handler handler = handlers[h];
159 static const char input[] = "\202\261\202\361\202\311\202\277\202\315"; /* こんにちは in Shift_JIS */
160 static const uint16_t expected[] = /* こんにちは */
162 0x3053, 0x3093, 0x306B, 0x3061, 0x306F
164 for (o = 0; o < 2; o++)
166 size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
167 uint16_t *result = NULL;
169 int retval = u16_conv_from_encoding ("autodetect_jp", handler,
170 input, strlen (input),
173 ASSERT (retval == 0);
174 ASSERT (length == SIZEOF (expected));
175 ASSERT (result != NULL && u16_cmp (result, expected, SIZEOF (expected)) == 0);
178 for (i = 0; i < 10; i++)
179 ASSERT (offsets[i] == ((i % 2) == 0 ? i / 2 : (size_t)(-1)));
180 ASSERT (offsets[10] == MAGIC);
186 for (h = 0; h < SIZEOF (handlers); h++)
188 enum iconv_ilseq_handler handler = handlers[h];
189 static const char input[] = "\033$B$3$s$K$A$O\033(B"; /* こんにちは in ISO-2022-JP-2 */
190 static const uint16_t expected[] = /* こんにちは */
192 0x3053, 0x3093, 0x306B, 0x3061, 0x306F
194 for (o = 0; o < 2; o++)
196 size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
197 uint16_t *result = NULL;
199 int retval = u16_conv_from_encoding ("autodetect_jp", handler,
200 input, strlen (input),
203 ASSERT (retval == 0);
204 ASSERT (length == SIZEOF (expected));
205 ASSERT (result != NULL && u16_cmp (result, expected, SIZEOF (expected)) == 0);
208 for (i = 0; i < 16; i++)
209 ASSERT (offsets[i] == (i == 0 ? 0 :
216 ASSERT (offsets[16] == MAGIC);