1 /* Test of conversion to UTF-32 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. */
30 #define SIZEOF(array) (sizeof (array) / sizeof (array[0]))
31 #define ASSERT(expr) if (!(expr)) abort ();
36 static enum iconv_ilseq_handler handlers[] =
37 { iconveh_error, iconveh_question_mark, iconveh_escape_sequence };
41 /* Assume that iconv() supports at least the encodings ASCII, ISO-8859-1,
42 ISO-8859-2, and UTF-8. */
44 /* Test conversion from ISO-8859-1 to UTF-16 with no errors. */
45 for (h = 0; h < SIZEOF (handlers); h++)
47 enum iconv_ilseq_handler handler = handlers[h];
48 static const char input[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337";
49 static const uint32_t expected[] = /* Ärger mit bösen Bübchen ohne Augenmaß */
51 0xC4, 'r', 'g', 'e', 'r', ' ', 'm', 'i', 't', ' ', 'b', 0xF6, 's',
52 'e', 'n', ' ', 'B', 0xFC, 'b', 'c', 'h', 'e', 'n', ' ', 'o', 'h',
53 'n', 'e', ' ', 'A', 'u', 'g', 'e', 'n', 'm', 'a', 0xDF, 0
55 uint32_t *result = u32_strconv_from_encoding (input, "ISO-8859-1", handler);
56 ASSERT (result != NULL);
57 ASSERT (u32_strcmp (result, expected) == 0);
61 /* Test conversion from ISO-8859-2 to UTF-16 with no errors. */
62 for (h = 0; h < SIZEOF (handlers); h++)
64 enum iconv_ilseq_handler handler = handlers[h];
65 static const char input[] = "Rafa\263 Maszkowski"; /* Rafał Maszkowski */
66 static const uint32_t expected[] =
68 'R', 'a', 'f', 'a', 0x0142, ' ', 'M', 'a', 's', 'z', 'k', 'o', 'w',
71 uint32_t *result = u32_strconv_from_encoding (input, "ISO-8859-2", handler);
72 ASSERT (result != NULL);
73 ASSERT (u32_strcmp (result, expected) == 0);
77 /* Test conversions from autodetect_jp to UTF-16. */
78 for (h = 0; h < SIZEOF (handlers); h++)
80 enum iconv_ilseq_handler handler = handlers[h];
81 static const char input[] = "\244\263\244\363\244\313\244\301\244\317"; /* こんにちは in EUC-JP */
82 static const uint32_t expected[] = /* こんにちは */
84 0x3053, 0x3093, 0x306B, 0x3061, 0x306F, 0
86 uint32_t *result = u32_strconv_from_encoding (input, "autodetect_jp", handler);
87 ASSERT (result != NULL);
88 ASSERT (u32_strcmp (result, expected) == 0);
91 for (h = 0; h < SIZEOF (handlers); h++)
93 enum iconv_ilseq_handler handler = handlers[h];
94 static const char input[] = "\202\261\202\361\202\311\202\277\202\315"; /* こんにちは in Shift_JIS */
95 static const uint32_t expected[] = /* こんにちは */
97 0x3053, 0x3093, 0x306B, 0x3061, 0x306F, 0
99 uint32_t *result = u32_strconv_from_encoding (input, "autodetect_jp", handler);
100 ASSERT (result != NULL);
101 ASSERT (u32_strcmp (result, expected) == 0);
104 for (h = 0; h < SIZEOF (handlers); h++)
106 enum iconv_ilseq_handler handler = handlers[h];
107 static const char input[] = "\033$B$3$s$K$A$O\033(B"; /* こんにちは in ISO-2022-JP-2 */
108 static const uint32_t expected[] = /* こんにちは */
110 0x3053, 0x3093, 0x306B, 0x3061, 0x306F, 0
112 uint32_t *result = u32_strconv_from_encoding (input, "autodetect_jp", handler);
113 ASSERT (result != NULL);
114 ASSERT (u32_strcmp (result, expected) == 0);