1 /* Test of conversion to UTF-8 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-8 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 uint8_t expected[] = "\303\204rger mit b\303\266sen B\303\274bchen ohne Augenma\303\237";
71 for (o = 0; o < 2; o++)
73 size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
74 uint8_t *result = NULL;
76 int retval = u8_conv_from_encoding ("ISO-8859-1", handler,
77 input, strlen (input),
81 ASSERT (length == u8_strlen (expected));
82 ASSERT (result != NULL && u8_cmp (result, expected, u8_strlen (expected)) == 0);
85 for (i = 0; i < 37; i++)
86 ASSERT (offsets[i] == (i < 1 ? i :
90 ASSERT (offsets[37] == MAGIC);
97 /* Test conversion from ISO-8859-2 to UTF-8 with no errors. */
98 for (h = 0; h < SIZEOF (handlers); h++)
100 enum iconv_ilseq_handler handler = handlers[h];
101 static const char input[] = "Rafa\263 Maszkowski"; /* Rafał Maszkowski */
102 static const uint8_t expected[] = "Rafa\305\202 Maszkowski";
103 for (o = 0; o < 2; o++)
105 size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
106 uint8_t *result = NULL;
108 int retval = u8_conv_from_encoding ("ISO-8859-2", handler,
109 input, strlen (input),
112 ASSERT (retval == 0);
113 ASSERT (length == u8_strlen (expected));
114 ASSERT (result != NULL && u8_cmp (result, expected, u8_strlen (expected)) == 0);
117 for (i = 0; i < 16; i++)
118 ASSERT (offsets[i] == (i < 5 ? i :
120 ASSERT (offsets[16] == MAGIC);
127 /* autodetect_jp is only supported when iconv() support ISO-2022-JP-2. */
128 # if defined _LIBICONV_VERSION || !(defined _AIX || defined __sgi || defined __hpux || defined __osf__)
129 /* Test conversions from autodetect_jp to UTF-8. */
130 for (h = 0; h < SIZEOF (handlers); h++)
132 enum iconv_ilseq_handler handler = handlers[h];
133 static const char input[] = "\244\263\244\363\244\313\244\301\244\317"; /* こんにちは in EUC-JP */
134 static const uint8_t expected[] = "\343\201\223\343\202\223\343\201\253\343\201\241\343\201\257"; /* こんにちは */
135 for (o = 0; o < 2; o++)
137 size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
138 uint8_t *result = NULL;
140 int retval = u8_conv_from_encoding ("autodetect_jp", handler,
141 input, strlen (input),
144 ASSERT (retval == 0);
145 ASSERT (length == u8_strlen (expected));
146 ASSERT (result != NULL && u8_cmp (result, expected, u8_strlen (expected)) == 0);
149 for (i = 0; i < 10; i++)
150 ASSERT (offsets[i] == ((i % 2) == 0 ? (i / 2) * 3 : (size_t)(-1)));
151 ASSERT (offsets[10] == MAGIC);
157 for (h = 0; h < SIZEOF (handlers); h++)
159 enum iconv_ilseq_handler handler = handlers[h];
160 static const char input[] = "\202\261\202\361\202\311\202\277\202\315"; /* こんにちは in Shift_JIS */
161 static const uint8_t expected[] = "\343\201\223\343\202\223\343\201\253\343\201\241\343\201\257"; /* こんにちは */
162 for (o = 0; o < 2; o++)
164 size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
165 uint8_t *result = NULL;
167 int retval = u8_conv_from_encoding ("autodetect_jp", handler,
168 input, strlen (input),
171 ASSERT (retval == 0);
172 ASSERT (length == u8_strlen (expected));
173 ASSERT (result != NULL && u8_cmp (result, expected, u8_strlen (expected)) == 0);
176 for (i = 0; i < 10; i++)
177 ASSERT (offsets[i] == ((i % 2) == 0 ? (i / 2) * 3 : (size_t)(-1)));
178 ASSERT (offsets[10] == MAGIC);
184 for (h = 0; h < SIZEOF (handlers); h++)
186 enum iconv_ilseq_handler handler = handlers[h];
187 static const char input[] = "\033$B$3$s$K$A$O\033(B"; /* こんにちは in ISO-2022-JP-2 */
188 static const uint8_t expected[] = "\343\201\223\343\202\223\343\201\253\343\201\241\343\201\257"; /* こんにちは */
189 for (o = 0; o < 2; o++)
191 size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
192 uint8_t *result = NULL;
194 int retval = u8_conv_from_encoding ("autodetect_jp", handler,
195 input, strlen (input),
198 ASSERT (retval == 0);
199 ASSERT (length == u8_strlen (expected));
200 ASSERT (result != NULL && u8_cmp (result, expected, u8_strlen (expected)) == 0);
203 for (i = 0; i < 16; i++)
204 ASSERT (offsets[i] == (i == 0 ? 0 :
211 ASSERT (offsets[16] == MAGIC);