1 /* Test of conversion to UTF-8 from legacy encodings.
2 Copyright (C) 2007-2009 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__); \
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-8 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 uint8_t expected[] = "\303\204rger mit b\303\266sen B\303\274bchen ohne Augenma\303\237";
72 for (o = 0; o < 2; o++)
74 size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
76 uint8_t *result = u8_conv_from_encoding ("ISO-8859-1", handler,
77 input, strlen (input),
80 ASSERT (result != NULL);
81 ASSERT (length == u8_strlen (expected));
82 ASSERT (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);
107 uint8_t *result = u8_conv_from_encoding ("ISO-8859-2", handler,
108 input, strlen (input),
111 ASSERT (result != NULL);
112 ASSERT (length == u8_strlen (expected));
113 ASSERT (u8_cmp (result, expected, u8_strlen (expected)) == 0);
116 for (i = 0; i < 16; i++)
117 ASSERT (offsets[i] == (i < 5 ? i :
119 ASSERT (offsets[16] == MAGIC);
126 /* autodetect_jp is only supported when iconv() support ISO-2022-JP-2. */
127 # if defined _LIBICONV_VERSION || !(defined _AIX || defined __sgi || defined __hpux || defined __osf__ || defined __sun)
128 /* Test conversions from autodetect_jp to UTF-8. */
129 for (h = 0; h < SIZEOF (handlers); h++)
131 enum iconv_ilseq_handler handler = handlers[h];
132 static const char input[] = "\244\263\244\363\244\313\244\301\244\317"; /* こんにちは in EUC-JP */
133 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 */
134 for (o = 0; o < 2; o++)
136 size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
138 uint8_t *result = u8_conv_from_encoding ("autodetect_jp", handler,
139 input, strlen (input),
142 ASSERT (result != NULL);
143 ASSERT (length == u8_strlen (expected));
144 ASSERT (u8_cmp (result, expected, u8_strlen (expected)) == 0);
147 for (i = 0; i < 10; i++)
148 ASSERT (offsets[i] == ((i % 2) == 0 ? (i / 2) * 3 : (size_t)(-1)));
149 ASSERT (offsets[10] == MAGIC);
155 for (h = 0; h < SIZEOF (handlers); h++)
157 enum iconv_ilseq_handler handler = handlers[h];
158 static const char input[] = "\202\261\202\361\202\311\202\277\202\315"; /* こんにちは in Shift_JIS */
159 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 */
160 for (o = 0; o < 2; o++)
162 size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
164 uint8_t *result = u8_conv_from_encoding ("autodetect_jp", handler,
165 input, strlen (input),
168 ASSERT (result != NULL);
169 ASSERT (length == u8_strlen (expected));
170 ASSERT (u8_cmp (result, expected, u8_strlen (expected)) == 0);
173 for (i = 0; i < 10; i++)
174 ASSERT (offsets[i] == ((i % 2) == 0 ? (i / 2) * 3 : (size_t)(-1)));
175 ASSERT (offsets[10] == MAGIC);
181 for (h = 0; h < SIZEOF (handlers); h++)
183 enum iconv_ilseq_handler handler = handlers[h];
184 static const char input[] = "\033$B$3$s$K$A$O\033(B"; /* こんにちは in ISO-2022-JP-2 */
185 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 */
186 for (o = 0; o < 2; o++)
188 size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
190 uint8_t *result = u8_conv_from_encoding ("autodetect_jp", handler,
191 input, strlen (input),
194 ASSERT (result != NULL);
195 ASSERT (length == u8_strlen (expected));
196 ASSERT (u8_cmp (result, expected, u8_strlen (expected)) == 0);
199 for (i = 0; i < 16; i++)
200 ASSERT (offsets[i] == (i == 0 ? 0 :
207 ASSERT (offsets[16] == MAGIC);