1 /* Test of conversion to UTF-8 from legacy encodings.
2 Copyright (C) 2007-2011 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 /* Magic number for detecting bounds violations. */
30 #define MAGIC 0x1983EFF1
33 new_offsets (size_t n)
35 size_t *offsets = (size_t *) malloc ((n + 1) * sizeof (size_t));
43 static enum iconv_ilseq_handler handlers[] =
44 { iconveh_error, iconveh_question_mark, iconveh_escape_sequence };
50 /* Assume that iconv() supports at least the encodings ASCII, ISO-8859-1,
51 ISO-8859-2, and UTF-8. */
53 /* Test conversion from ISO-8859-1 to UTF-8 with no errors. */
54 for (h = 0; h < SIZEOF (handlers); h++)
56 enum iconv_ilseq_handler handler = handlers[h];
57 static const char input[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337";
58 static const uint8_t expected[] = "\303\204rger mit b\303\266sen B\303\274bchen ohne Augenma\303\237";
59 for (o = 0; o < 2; o++)
61 size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
63 uint8_t *result = u8_conv_from_encoding ("ISO-8859-1", handler,
64 input, strlen (input),
67 ASSERT (result != NULL);
68 ASSERT (length == u8_strlen (expected));
69 ASSERT (u8_cmp (result, expected, u8_strlen (expected)) == 0);
72 for (i = 0; i < 37; i++)
73 ASSERT (offsets[i] == (i < 1 ? i :
77 ASSERT (offsets[37] == MAGIC);
84 /* Test conversion from ISO-8859-2 to UTF-8 with no errors. */
85 for (h = 0; h < SIZEOF (handlers); h++)
87 enum iconv_ilseq_handler handler = handlers[h];
88 static const char input[] = "Rafa\263 Maszkowski"; /* Rafał Maszkowski */
89 static const uint8_t expected[] = "Rafa\305\202 Maszkowski";
90 for (o = 0; o < 2; o++)
92 size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
94 uint8_t *result = u8_conv_from_encoding ("ISO-8859-2", handler,
95 input, strlen (input),
98 ASSERT (result != NULL);
99 ASSERT (length == u8_strlen (expected));
100 ASSERT (u8_cmp (result, expected, u8_strlen (expected)) == 0);
103 for (i = 0; i < 16; i++)
104 ASSERT (offsets[i] == (i < 5 ? i :
106 ASSERT (offsets[16] == MAGIC);
113 /* autodetect_jp is only supported when iconv() support ISO-2022-JP-2. */
114 # if defined _LIBICONV_VERSION || !(defined _AIX || defined __sgi || defined __hpux || defined __osf__ || defined __sun)
115 /* Test conversions from autodetect_jp to UTF-8. */
116 for (h = 0; h < SIZEOF (handlers); h++)
118 enum iconv_ilseq_handler handler = handlers[h];
119 static const char input[] = "\244\263\244\363\244\313\244\301\244\317"; /* こんにちは in EUC-JP */
120 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 */
121 for (o = 0; o < 2; o++)
123 size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
125 uint8_t *result = u8_conv_from_encoding ("autodetect_jp", handler,
126 input, strlen (input),
129 ASSERT (result != NULL);
130 ASSERT (length == u8_strlen (expected));
131 ASSERT (u8_cmp (result, expected, u8_strlen (expected)) == 0);
134 for (i = 0; i < 10; i++)
135 ASSERT (offsets[i] == ((i % 2) == 0 ? (i / 2) * 3 : (size_t)(-1)));
136 ASSERT (offsets[10] == MAGIC);
142 for (h = 0; h < SIZEOF (handlers); h++)
144 enum iconv_ilseq_handler handler = handlers[h];
145 static const char input[] = "\202\261\202\361\202\311\202\277\202\315"; /* こんにちは in Shift_JIS */
146 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 */
147 for (o = 0; o < 2; o++)
149 size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
151 uint8_t *result = u8_conv_from_encoding ("autodetect_jp", handler,
152 input, strlen (input),
155 ASSERT (result != NULL);
156 ASSERT (length == u8_strlen (expected));
157 ASSERT (u8_cmp (result, expected, u8_strlen (expected)) == 0);
160 for (i = 0; i < 10; i++)
161 ASSERT (offsets[i] == ((i % 2) == 0 ? (i / 2) * 3 : (size_t)(-1)));
162 ASSERT (offsets[10] == MAGIC);
168 for (h = 0; h < SIZEOF (handlers); h++)
170 enum iconv_ilseq_handler handler = handlers[h];
171 static const char input[] = "\033$B$3$s$K$A$O\033(B"; /* こんにちは in ISO-2022-JP-2 */
172 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 */
173 for (o = 0; o < 2; o++)
175 size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
177 uint8_t *result = u8_conv_from_encoding ("autodetect_jp", handler,
178 input, strlen (input),
181 ASSERT (result != NULL);
182 ASSERT (length == u8_strlen (expected));
183 ASSERT (u8_cmp (result, expected, u8_strlen (expected)) == 0);
186 for (i = 0; i < 16; i++)
187 ASSERT (offsets[i] == (i == 0 ? 0 :
194 ASSERT (offsets[16] == MAGIC);