1 /* Test of conversion from UTF-8 to legacy encodings.
2 Copyright (C) 2007-2011 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. */
30 /* Magic number for detecting bounds violations. */
31 #define MAGIC 0x1983EFF1
34 new_offsets (size_t n)
36 size_t *offsets = (size_t *) malloc ((n + 1) * sizeof (size_t));
44 static enum iconv_ilseq_handler handlers[] =
45 { 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 UTF-8 to ISO-8859-1 with no errors. */
55 for (h = 0; h < SIZEOF (handlers); h++)
57 enum iconv_ilseq_handler handler = handlers[h];
58 static const uint8_t input[] = "\303\204rger mit b\303\266sen B\303\274bchen ohne Augenma\303\237";
59 static const char expected[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337";
60 for (o = 0; o < 2; o++)
62 size_t *offsets = (o ? new_offsets (u8_strlen (input)) : NULL);
64 char *result = u8_conv_to_encoding ("ISO-8859-1", handler,
65 input, u8_strlen (input),
68 ASSERT (result != NULL);
69 ASSERT (length == strlen (expected));
70 ASSERT (memcmp (result, expected, length) == 0);
73 for (i = 0; i < 41; i++)
74 ASSERT (offsets[i] == (i < 1 ? i :
75 i == 1 ? (size_t)(-1) :
77 i == 13 ? (size_t)(-1) :
79 i == 20 ? (size_t)(-1) :
81 i == 40 ? (size_t)(-1) :
83 ASSERT (offsets[41] == MAGIC);
90 /* Test conversion from UTF-8 to ISO-8859-1 with EILSEQ. */
91 for (h = 0; h < SIZEOF (handlers); h++)
93 enum iconv_ilseq_handler handler = handlers[h];
94 static const uint8_t input[] = "Rafa\305\202 Maszkowski"; /* RafaĆ Maszkowski */
95 for (o = 0; o < 2; o++)
97 size_t *offsets = (o ? new_offsets (u8_strlen (input)) : NULL);
98 size_t length = 0xdead;
99 char *result = u8_conv_to_encoding ("ISO-8859-1", handler,
100 input, u8_strlen (input),
106 ASSERT (result == NULL);
107 ASSERT (errno == EILSEQ);
108 ASSERT (length == 0xdead);
110 case iconveh_question_mark:
112 static const char expected[] = "Rafa? Maszkowski";
113 static const char expected_translit[] = "Rafal Maszkowski";
114 ASSERT (result != NULL);
115 ASSERT (length == strlen (expected));
116 ASSERT (memcmp (result, expected, length) == 0
117 || memcmp (result, expected_translit, length) == 0);
120 for (i = 0; i < 17; i++)
121 ASSERT (offsets[i] == (i < 5 ? i :
122 i == 5 ? (size_t)(-1) :
124 ASSERT (offsets[17] == MAGIC);
130 case iconveh_escape_sequence:
132 static const char expected[] = "Rafa\\u0142 Maszkowski";
133 ASSERT (result != NULL);
134 ASSERT (length == strlen (expected));
135 ASSERT (memcmp (result, expected, length) == 0);
138 for (i = 0; i < 17; i++)
139 ASSERT (offsets[i] == (i < 5 ? i :
140 i == 5 ? (size_t)(-1) :
142 ASSERT (offsets[17] == MAGIC);
152 /* Test conversion from UTF-8 to ISO-8859-1 with EINVAL. */
153 for (h = 0; h < SIZEOF (handlers); h++)
155 enum iconv_ilseq_handler handler = handlers[h];
156 static const uint8_t input[] = "\342";
157 for (o = 0; o < 2; o++)
159 size_t *offsets = (o ? new_offsets (u8_strlen (input)) : NULL);
161 char *result = u8_conv_to_encoding ("ISO-8859-1", handler,
162 input, u8_strlen (input),
165 ASSERT (result != NULL);
166 ASSERT (length == strlen (""));
169 ASSERT (offsets[0] == 0);
170 ASSERT (offsets[1] == MAGIC);