1 /* Test of conversion to UTF-32 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-16 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 uint32_t expected[] = /* Ärger mit bösen Bübchen ohne Augenmaß */
59 0xC4, 'r', 'g', 'e', 'r', ' ', 'm', 'i', 't', ' ', 'b', 0xF6, 's',
60 'e', 'n', ' ', 'B', 0xFC, 'b', 'c', 'h', 'e', 'n', ' ', 'o', 'h',
61 'n', 'e', ' ', 'A', 'u', 'g', 'e', 'n', 'm', 'a', 0xDF, 0
63 uint32_t *result = u32_strconv_from_encoding (input, "ISO-8859-1", handler);
64 ASSERT (result != NULL);
65 ASSERT (u32_strcmp (result, expected) == 0);
69 /* Test conversion from ISO-8859-2 to UTF-16 with no errors. */
70 for (h = 0; h < SIZEOF (handlers); h++)
72 enum iconv_ilseq_handler handler = handlers[h];
73 static const char input[] = "Rafa\263 Maszkowski"; /* Rafał Maszkowski */
74 static const uint32_t expected[] =
76 'R', 'a', 'f', 'a', 0x0142, ' ', 'M', 'a', 's', 'z', 'k', 'o', 'w',
79 uint32_t *result = u32_strconv_from_encoding (input, "ISO-8859-2", handler);
80 ASSERT (result != NULL);
81 ASSERT (u32_strcmp (result, expected) == 0);
85 /* autodetect_jp is only supported when iconv() support ISO-2022-JP-2. */
86 # if defined _LIBICONV_VERSION || !(defined _AIX || defined __sgi || defined __hpux || defined __osf__ || defined __sun)
87 /* Test conversions from autodetect_jp to UTF-16. */
88 for (h = 0; h < SIZEOF (handlers); h++)
90 enum iconv_ilseq_handler handler = handlers[h];
91 static const char input[] = "\244\263\244\363\244\313\244\301\244\317"; /* こんにちは in EUC-JP */
92 static const uint32_t expected[] = /* こんにちは */
94 0x3053, 0x3093, 0x306B, 0x3061, 0x306F, 0
96 uint32_t *result = u32_strconv_from_encoding (input, "autodetect_jp", handler);
97 ASSERT (result != NULL);
98 ASSERT (u32_strcmp (result, expected) == 0);
101 for (h = 0; h < SIZEOF (handlers); h++)
103 enum iconv_ilseq_handler handler = handlers[h];
104 static const char input[] = "\202\261\202\361\202\311\202\277\202\315"; /* こんにちは in Shift_JIS */
105 static const uint32_t expected[] = /* こんにちは */
107 0x3053, 0x3093, 0x306B, 0x3061, 0x306F, 0
109 uint32_t *result = u32_strconv_from_encoding (input, "autodetect_jp", handler);
110 ASSERT (result != NULL);
111 ASSERT (u32_strcmp (result, expected) == 0);
114 for (h = 0; h < SIZEOF (handlers); h++)
116 enum iconv_ilseq_handler handler = handlers[h];
117 static const char input[] = "\033$B$3$s$K$A$O\033(B"; /* こんにちは in ISO-2022-JP-2 */
118 static const uint32_t expected[] = /* こんにちは */
120 0x3053, 0x3093, 0x306B, 0x3061, 0x306F, 0
122 uint32_t *result = u32_strconv_from_encoding (input, "autodetect_jp", handler);
123 ASSERT (result != NULL);
124 ASSERT (u32_strcmp (result, expected) == 0);