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 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-8 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 uint8_t expected[] = "\303\204rger mit b\303\266sen B\303\274bchen ohne Augenma\303\237";
64 for (o = 0; o < 2; o++)
66 size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
67 uint8_t *result = NULL;
69 int retval = u8_conv_from_encoding ("ISO-8859-1", handler,
70 input, strlen (input),
74 ASSERT (length == u8_strlen (expected));
75 ASSERT (result != NULL && u8_cmp (result, expected, u8_strlen (expected)) == 0);
78 for (i = 0; i < 37; i++)
79 ASSERT (offsets[i] == (i < 1 ? i :
83 ASSERT (offsets[37] == MAGIC);
90 /* Test conversion from ISO-8859-2 to UTF-8 with no errors. */
91 for (h = 0; h < SIZEOF (handlers); h++)
93 enum iconv_ilseq_handler handler = handlers[h];
94 static const char input[] = "Rafa\263 Maszkowski"; /* Rafał Maszkowski */
95 static const uint8_t expected[] = "Rafa\305\202 Maszkowski";
96 for (o = 0; o < 2; o++)
98 size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
99 uint8_t *result = NULL;
101 int retval = u8_conv_from_encoding ("ISO-8859-2", handler,
102 input, strlen (input),
105 ASSERT (retval == 0);
106 ASSERT (length == u8_strlen (expected));
107 ASSERT (result != NULL && u8_cmp (result, expected, u8_strlen (expected)) == 0);
110 for (i = 0; i < 16; i++)
111 ASSERT (offsets[i] == (i < 5 ? i :
113 ASSERT (offsets[16] == MAGIC);
120 /* autodetect_jp is only supported when iconv() support ISO-2022-JP-2. */
121 # if defined _LIBICONV_VERSION || !(defined _AIX || defined __sgi || defined __hpux || defined __osf__)
122 /* Test conversions from autodetect_jp to UTF-8. */
123 for (h = 0; h < SIZEOF (handlers); h++)
125 enum iconv_ilseq_handler handler = handlers[h];
126 static const char input[] = "\244\263\244\363\244\313\244\301\244\317"; /* こんにちは in EUC-JP */
127 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 */
128 for (o = 0; o < 2; o++)
130 size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
131 uint8_t *result = NULL;
133 int retval = u8_conv_from_encoding ("autodetect_jp", handler,
134 input, strlen (input),
137 ASSERT (retval == 0);
138 ASSERT (length == u8_strlen (expected));
139 ASSERT (result != NULL && u8_cmp (result, expected, u8_strlen (expected)) == 0);
142 for (i = 0; i < 10; i++)
143 ASSERT (offsets[i] == ((i % 2) == 0 ? (i / 2) * 3 : (size_t)(-1)));
144 ASSERT (offsets[10] == MAGIC);
150 for (h = 0; h < SIZEOF (handlers); h++)
152 enum iconv_ilseq_handler handler = handlers[h];
153 static const char input[] = "\202\261\202\361\202\311\202\277\202\315"; /* こんにちは in Shift_JIS */
154 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 */
155 for (o = 0; o < 2; o++)
157 size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
158 uint8_t *result = NULL;
160 int retval = u8_conv_from_encoding ("autodetect_jp", handler,
161 input, strlen (input),
164 ASSERT (retval == 0);
165 ASSERT (length == u8_strlen (expected));
166 ASSERT (result != NULL && u8_cmp (result, expected, u8_strlen (expected)) == 0);
169 for (i = 0; i < 10; i++)
170 ASSERT (offsets[i] == ((i % 2) == 0 ? (i / 2) * 3 : (size_t)(-1)));
171 ASSERT (offsets[10] == MAGIC);
177 for (h = 0; h < SIZEOF (handlers); h++)
179 enum iconv_ilseq_handler handler = handlers[h];
180 static const char input[] = "\033$B$3$s$K$A$O\033(B"; /* こんにちは in ISO-2022-JP-2 */
181 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 */
182 for (o = 0; o < 2; o++)
184 size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
185 uint8_t *result = NULL;
187 int retval = u8_conv_from_encoding ("autodetect_jp", handler,
188 input, strlen (input),
191 ASSERT (retval == 0);
192 ASSERT (length == u8_strlen (expected));
193 ASSERT (result != NULL && u8_cmp (result, expected, u8_strlen (expected)) == 0);
196 for (i = 0; i < 16; i++)
197 ASSERT (offsets[i] == (i == 0 ? 0 :
204 ASSERT (offsets[16] == MAGIC);