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. */
31 #define SIZEOF(array) (sizeof (array) / sizeof (array[0]))
32 #define ASSERT(expr) \
37 fprintf (stderr, "%s:%d: assertion failed\n", __FILE__, __LINE__); \
46 static enum iconv_ilseq_handler handlers[] =
47 { iconveh_error, iconveh_question_mark, iconveh_escape_sequence };
51 /* Assume that iconv() supports at least the encodings ASCII, ISO-8859-1,
52 ISO-8859-2, and UTF-8. */
54 /* Test conversion from ISO-8859-1 to UTF-16 with no errors. */
55 for (h = 0; h < SIZEOF (handlers); h++)
57 enum iconv_ilseq_handler handler = handlers[h];
58 static const char input[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337";
59 static const uint32_t expected[] = /* Ärger mit bösen Bübchen ohne Augenmaß */
61 0xC4, 'r', 'g', 'e', 'r', ' ', 'm', 'i', 't', ' ', 'b', 0xF6, 's',
62 'e', 'n', ' ', 'B', 0xFC, 'b', 'c', 'h', 'e', 'n', ' ', 'o', 'h',
63 'n', 'e', ' ', 'A', 'u', 'g', 'e', 'n', 'm', 'a', 0xDF, 0
65 uint32_t *result = u32_strconv_from_encoding (input, "ISO-8859-1", handler);
66 ASSERT (result != NULL);
67 ASSERT (u32_strcmp (result, expected) == 0);
71 /* Test conversion from ISO-8859-2 to UTF-16 with no errors. */
72 for (h = 0; h < SIZEOF (handlers); h++)
74 enum iconv_ilseq_handler handler = handlers[h];
75 static const char input[] = "Rafa\263 Maszkowski"; /* Rafał Maszkowski */
76 static const uint32_t expected[] =
78 'R', 'a', 'f', 'a', 0x0142, ' ', 'M', 'a', 's', 'z', 'k', 'o', 'w',
81 uint32_t *result = u32_strconv_from_encoding (input, "ISO-8859-2", handler);
82 ASSERT (result != NULL);
83 ASSERT (u32_strcmp (result, expected) == 0);
87 /* autodetect_jp is only supported when iconv() support ISO-2022-JP-2. */
88 # if defined _LIBICONV_VERSION || !(defined _AIX || defined __sgi || defined __hpux || defined __osf__)
89 /* Test conversions from autodetect_jp to UTF-16. */
90 for (h = 0; h < SIZEOF (handlers); h++)
92 enum iconv_ilseq_handler handler = handlers[h];
93 static const char input[] = "\244\263\244\363\244\313\244\301\244\317"; /* こんにちは in EUC-JP */
94 static const uint32_t expected[] = /* こんにちは */
96 0x3053, 0x3093, 0x306B, 0x3061, 0x306F, 0
98 uint32_t *result = u32_strconv_from_encoding (input, "autodetect_jp", handler);
99 ASSERT (result != NULL);
100 ASSERT (u32_strcmp (result, expected) == 0);
103 for (h = 0; h < SIZEOF (handlers); h++)
105 enum iconv_ilseq_handler handler = handlers[h];
106 static const char input[] = "\202\261\202\361\202\311\202\277\202\315"; /* こんにちは in Shift_JIS */
107 static const uint32_t expected[] = /* こんにちは */
109 0x3053, 0x3093, 0x306B, 0x3061, 0x306F, 0
111 uint32_t *result = u32_strconv_from_encoding (input, "autodetect_jp", handler);
112 ASSERT (result != NULL);
113 ASSERT (u32_strcmp (result, expected) == 0);
116 for (h = 0; h < SIZEOF (handlers); h++)
118 enum iconv_ilseq_handler handler = handlers[h];
119 static const char input[] = "\033$B$3$s$K$A$O\033(B"; /* こんにちは in ISO-2022-JP-2 */
120 static const uint32_t expected[] = /* こんにちは */
122 0x3053, 0x3093, 0x306B, 0x3061, 0x306F, 0
124 uint32_t *result = u32_strconv_from_encoding (input, "autodetect_jp", handler);
125 ASSERT (result != NULL);
126 ASSERT (u32_strcmp (result, expected) == 0);