1 /* Test of conversion to UTF-8 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-8 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 uint8_t expected[] = "\303\204rger mit b\303\266sen B\303\274bchen ohne Augenma\303\237";
50 uint8_t *result = u8_strconv_from_encoding (input, "ISO-8859-1", handler);
51 ASSERT (result != NULL);
52 ASSERT (u8_strcmp (result, expected) == 0);
56 /* Test conversion from ISO-8859-2 to UTF-8 with no errors. */
57 for (h = 0; h < SIZEOF (handlers); h++)
59 enum iconv_ilseq_handler handler = handlers[h];
60 static const char input[] = "Rafa\263 Maszkowski"; /* Rafał Maszkowski */
61 static const uint8_t expected[] = "Rafa\305\202 Maszkowski";
62 uint8_t *result = u8_strconv_from_encoding (input, "ISO-8859-2", handler);
63 ASSERT (result != NULL);
64 ASSERT (u8_strcmp (result, expected) == 0);
68 /* autodetect_jp is only supported when iconv() support ISO-2022-JP-2. */
69 # if defined _LIBICONV_VERSION || !(defined _AIX || defined __sgi || defined __hpux || defined __osf__)
70 /* Test conversions from autodetect_jp to UTF-8. */
71 for (h = 0; h < SIZEOF (handlers); h++)
73 enum iconv_ilseq_handler handler = handlers[h];
74 static const char input[] = "\244\263\244\363\244\313\244\301\244\317"; /* こんにちは in EUC-JP */
75 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 */
76 uint8_t *result = u8_strconv_from_encoding (input, "autodetect_jp", handler);
77 ASSERT (result != NULL);
78 ASSERT (u8_strcmp (result, expected) == 0);
81 for (h = 0; h < SIZEOF (handlers); h++)
83 enum iconv_ilseq_handler handler = handlers[h];
84 static const char input[] = "\202\261\202\361\202\311\202\277\202\315"; /* こんにちは in Shift_JIS */
85 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 */
86 uint8_t *result = u8_strconv_from_encoding (input, "autodetect_jp", handler);
87 ASSERT (result != NULL);
88 ASSERT (u8_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[] = "\033$B$3$s$K$A$O\033(B"; /* こんにちは in ISO-2022-JP-2 */
95 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 */
96 uint8_t *result = u8_strconv_from_encoding (input, "autodetect_jp", handler);
97 ASSERT (result != NULL);
98 ASSERT (u8_strcmp (result, expected) == 0);