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. */
32 #define SIZEOF(array) (sizeof (array) / sizeof (array[0]))
33 #define ASSERT(expr) \
38 fprintf (stderr, "%s:%d: assertion failed\n", __FILE__, __LINE__); \
44 /* Magic number for detecting bounds violations. */
45 #define MAGIC 0x1983EFF1
48 new_offsets (size_t n)
50 size_t *offsets = (size_t *) malloc ((n + 1) * sizeof (size_t));
58 static enum iconv_ilseq_handler handlers[] =
59 { iconveh_error, iconveh_question_mark, iconveh_escape_sequence };
65 /* Assume that iconv() supports at least the encodings ASCII, ISO-8859-1,
66 ISO-8859-2, and UTF-8. */
68 /* Test conversion from ISO-8859-1 to UTF-8 with no errors. */
69 for (h = 0; h < SIZEOF (handlers); h++)
71 enum iconv_ilseq_handler handler = handlers[h];
72 static const char input[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337";
73 static const uint8_t expected[] = "\303\204rger mit b\303\266sen B\303\274bchen ohne Augenma\303\237";
74 for (o = 0; o < 2; o++)
76 size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
77 uint8_t *result = NULL;
79 int retval = u8_conv_from_encoding ("ISO-8859-1", handler,
80 input, strlen (input),
84 ASSERT (length == u8_strlen (expected));
85 ASSERT (result != NULL && u8_cmp (result, expected, u8_strlen (expected)) == 0);
88 for (i = 0; i < 37; i++)
89 ASSERT (offsets[i] == (i < 1 ? i :
93 ASSERT (offsets[37] == MAGIC);
100 /* Test conversion from ISO-8859-2 to UTF-8 with no errors. */
101 for (h = 0; h < SIZEOF (handlers); h++)
103 enum iconv_ilseq_handler handler = handlers[h];
104 static const char input[] = "Rafa\263 Maszkowski"; /* Rafał Maszkowski */
105 static const uint8_t expected[] = "Rafa\305\202 Maszkowski";
106 for (o = 0; o < 2; o++)
108 size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
109 uint8_t *result = NULL;
111 int retval = u8_conv_from_encoding ("ISO-8859-2", handler,
112 input, strlen (input),
115 ASSERT (retval == 0);
116 ASSERT (length == u8_strlen (expected));
117 ASSERT (result != NULL && u8_cmp (result, expected, u8_strlen (expected)) == 0);
120 for (i = 0; i < 16; i++)
121 ASSERT (offsets[i] == (i < 5 ? i :
123 ASSERT (offsets[16] == MAGIC);
130 /* autodetect_jp is only supported when iconv() support ISO-2022-JP-2. */
131 # if defined _LIBICONV_VERSION || !(defined _AIX || defined __sgi || defined __hpux || defined __osf__)
132 /* Test conversions from autodetect_jp to UTF-8. */
133 for (h = 0; h < SIZEOF (handlers); h++)
135 enum iconv_ilseq_handler handler = handlers[h];
136 static const char input[] = "\244\263\244\363\244\313\244\301\244\317"; /* こんにちは in EUC-JP */
137 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 */
138 for (o = 0; o < 2; o++)
140 size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
141 uint8_t *result = NULL;
143 int retval = u8_conv_from_encoding ("autodetect_jp", handler,
144 input, strlen (input),
147 ASSERT (retval == 0);
148 ASSERT (length == u8_strlen (expected));
149 ASSERT (result != NULL && u8_cmp (result, expected, u8_strlen (expected)) == 0);
152 for (i = 0; i < 10; i++)
153 ASSERT (offsets[i] == ((i % 2) == 0 ? (i / 2) * 3 : (size_t)(-1)));
154 ASSERT (offsets[10] == MAGIC);
160 for (h = 0; h < SIZEOF (handlers); h++)
162 enum iconv_ilseq_handler handler = handlers[h];
163 static const char input[] = "\202\261\202\361\202\311\202\277\202\315"; /* こんにちは in Shift_JIS */
164 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 */
165 for (o = 0; o < 2; o++)
167 size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
168 uint8_t *result = NULL;
170 int retval = u8_conv_from_encoding ("autodetect_jp", handler,
171 input, strlen (input),
174 ASSERT (retval == 0);
175 ASSERT (length == u8_strlen (expected));
176 ASSERT (result != NULL && u8_cmp (result, expected, u8_strlen (expected)) == 0);
179 for (i = 0; i < 10; i++)
180 ASSERT (offsets[i] == ((i % 2) == 0 ? (i / 2) * 3 : (size_t)(-1)));
181 ASSERT (offsets[10] == MAGIC);
187 for (h = 0; h < SIZEOF (handlers); h++)
189 enum iconv_ilseq_handler handler = handlers[h];
190 static const char input[] = "\033$B$3$s$K$A$O\033(B"; /* こんにちは in ISO-2022-JP-2 */
191 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 */
192 for (o = 0; o < 2; o++)
194 size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
195 uint8_t *result = NULL;
197 int retval = u8_conv_from_encoding ("autodetect_jp", handler,
198 input, strlen (input),
201 ASSERT (retval == 0);
202 ASSERT (length == u8_strlen (expected));
203 ASSERT (result != NULL && u8_cmp (result, expected, u8_strlen (expected)) == 0);
206 for (i = 0; i < 16; i++)
207 ASSERT (offsets[i] == (i == 0 ? 0 :
214 ASSERT (offsets[16] == MAGIC);