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. */
28 #define SIZEOF(array) (sizeof (array) / sizeof (array[0]))
29 #define ASSERT(expr) \
34 fprintf (stderr, "%s:%d: assertion failed\n", __FILE__, __LINE__); \
44 static enum iconv_ilseq_handler handlers[] =
45 { iconveh_error, iconveh_question_mark, iconveh_escape_sequence };
49 /* Assume that iconv() supports at least the encodings ASCII, ISO-8859-1,
50 ISO-8859-2, and UTF-8. */
52 /* Test conversion from ISO-8859-1 to UTF-8 with no errors. */
53 for (h = 0; h < SIZEOF (handlers); h++)
55 enum iconv_ilseq_handler handler = handlers[h];
56 static const char input[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337";
57 static const uint8_t expected[] = "\303\204rger mit b\303\266sen B\303\274bchen ohne Augenma\303\237";
58 uint8_t *result = u8_strconv_from_encoding (input, "ISO-8859-1", handler);
59 ASSERT (result != NULL);
60 ASSERT (u8_strcmp (result, expected) == 0);
64 /* Test conversion from ISO-8859-2 to UTF-8 with no errors. */
65 for (h = 0; h < SIZEOF (handlers); h++)
67 enum iconv_ilseq_handler handler = handlers[h];
68 static const char input[] = "Rafa\263 Maszkowski"; /* Rafał Maszkowski */
69 static const uint8_t expected[] = "Rafa\305\202 Maszkowski";
70 uint8_t *result = u8_strconv_from_encoding (input, "ISO-8859-2", handler);
71 ASSERT (result != NULL);
72 ASSERT (u8_strcmp (result, expected) == 0);
76 /* autodetect_jp is only supported when iconv() support ISO-2022-JP-2. */
77 # if defined _LIBICONV_VERSION || !(defined _AIX || defined __sgi || defined __hpux || defined __osf__ || defined __sun)
78 /* Test conversions from autodetect_jp to UTF-8. */
79 for (h = 0; h < SIZEOF (handlers); h++)
81 enum iconv_ilseq_handler handler = handlers[h];
82 static const char input[] = "\244\263\244\363\244\313\244\301\244\317"; /* こんにちは in EUC-JP */
83 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 */
84 uint8_t *result = u8_strconv_from_encoding (input, "autodetect_jp", handler);
85 ASSERT (result != NULL);
86 ASSERT (u8_strcmp (result, expected) == 0);
89 for (h = 0; h < SIZEOF (handlers); h++)
91 enum iconv_ilseq_handler handler = handlers[h];
92 static const char input[] = "\202\261\202\361\202\311\202\277\202\315"; /* こんにちは in Shift_JIS */
93 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 */
94 uint8_t *result = u8_strconv_from_encoding (input, "autodetect_jp", handler);
95 ASSERT (result != NULL);
96 ASSERT (u8_strcmp (result, expected) == 0);
99 for (h = 0; h < SIZEOF (handlers); h++)
101 enum iconv_ilseq_handler handler = handlers[h];
102 static const char input[] = "\033$B$3$s$K$A$O\033(B"; /* こんにちは in ISO-2022-JP-2 */
103 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 */
104 uint8_t *result = u8_strconv_from_encoding (input, "autodetect_jp", handler);
105 ASSERT (result != NULL);
106 ASSERT (u8_strcmp (result, expected) == 0);