summaryrefslogtreecommitdiffstats
path: root/src/grep/gnulib-tests/test-striconv.c
blob: 55bd3df8808458d47369e27e9252737c106e73ed (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
/* Test of character set conversion.
   Copyright (C) 2007-2021 Free Software Foundation, Inc.

   This program is free software: you can redistribute it and/or modify
   it under the terms of the GNU General Public License as published by
   the Free Software Foundation; either version 3 of the License, or
   (at your option) any later version.

   This program is distributed in the hope that it will be useful,
   but WITHOUT ANY WARRANTY; without even the implied warranty of
   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
   GNU General Public License for more details.

   You should have received a copy of the GNU General Public License
   along with this program.  If not, see <https://www.gnu.org/licenses/>.  */

/* Written by Bruno Haible <bruno@clisp.org>, 2007.  */

#include <config.h>

#include "striconv.h"

#if HAVE_ICONV
# include <iconv.h>
#endif

#include <errno.h>
#include <stdlib.h>
#include <string.h>

#include "macros.h"

int
main ()
{
#if HAVE_ICONV
  /* Assume that iconv() supports at least the encodings ASCII, ISO-8859-1,
     and UTF-8.  */
  iconv_t cd_88591_to_utf8 = iconv_open ("UTF-8", "ISO-8859-1");
  iconv_t cd_utf8_to_88591 = iconv_open ("ISO-8859-1", "UTF-8");

  ASSERT (cd_88591_to_utf8 != (iconv_t)(-1));
  ASSERT (cd_utf8_to_88591 != (iconv_t)(-1));

  /* ------------------------- Test mem_cd_iconv() ------------------------- */

  /* Test conversion from ISO-8859-1 to UTF-8 with no errors.  */
  {
    static const char input[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337";
    static const char expected[] = "\303\204rger mit b\303\266sen B\303\274bchen ohne Augenma\303\237";
    char *result = NULL;
    size_t length = 0;
    int retval = mem_cd_iconv (input, strlen (input), cd_88591_to_utf8,
                               &result, &length);
    ASSERT (retval == 0);
    ASSERT (length == strlen (expected));
    ASSERT (result != NULL && memcmp (result, expected, strlen (expected)) == 0);
    free (result);
  }

  /* Test conversion from UTF-8 to ISO-8859-1 with no errors.  */
  {
    static const char input[] = "\303\204rger mit b\303\266sen B\303\274bchen ohne Augenma\303\237";
    static const char expected[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337";
    char *result = NULL;
    size_t length = 0;
    int retval = mem_cd_iconv (input, strlen (input), cd_utf8_to_88591,
                               &result, &length);
    ASSERT (retval == 0);
    ASSERT (length == strlen (expected));
    ASSERT (result != NULL && memcmp (result, expected, strlen (expected)) == 0);
    free (result);
  }

  /* Test conversion from UTF-8 to ISO-8859-1 with EILSEQ.  */
  {
    static const char input[] = "\342\202\254"; /* EURO SIGN */
    char *result = NULL;
    size_t length = 0;
    int retval = mem_cd_iconv (input, strlen (input), cd_utf8_to_88591,
                               &result, &length);
    ASSERT (retval == -1 && errno == EILSEQ);
    ASSERT (result == NULL);
  }

  /* Test conversion from UTF-8 to ISO-8859-1 with EINVAL.  */
  {
    static const char input[] = "\342";
    char *result = NULL;
    size_t length = 0;
    int retval = mem_cd_iconv (input, strlen (input), cd_utf8_to_88591,
                               &result, &length);
    ASSERT (retval == 0);
    ASSERT (length == 0);
    free (result);
  }

  /* ------------------------- Test str_cd_iconv() ------------------------- */

  /* Test conversion from ISO-8859-1 to UTF-8 with no errors.  */
  {
    static const char input[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337";
    static const char expected[] = "\303\204rger mit b\303\266sen B\303\274bchen ohne Augenma\303\237";
    char *result = str_cd_iconv (input, cd_88591_to_utf8);
    ASSERT (result != NULL);
    ASSERT (strcmp (result, expected) == 0);
    free (result);
  }

  /* Test conversion from UTF-8 to ISO-8859-1 with no errors.  */
  {
    static const char input[] = "\303\204rger mit b\303\266sen B\303\274bchen ohne Augenma\303\237";
    static const char expected[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337";
    char *result = str_cd_iconv (input, cd_utf8_to_88591);
    ASSERT (result != NULL);
    ASSERT (strcmp (result, expected) == 0);
    free (result);
  }

  /* Test conversion from UTF-8 to ISO-8859-1 with EILSEQ.  */
  {
    static const char input[] = "Costs: 27 \342\202\254"; /* EURO SIGN */
    char *result = str_cd_iconv (input, cd_utf8_to_88591);
    ASSERT (result == NULL && errno == EILSEQ);
  }

  /* Test conversion from UTF-8 to ISO-8859-1 with EINVAL.  */
  {
    static const char input[] = "\342";
    char *result = str_cd_iconv (input, cd_utf8_to_88591);
    ASSERT (result != NULL);
    ASSERT (strcmp (result, "") == 0);
    free (result);
  }

  iconv_close (cd_88591_to_utf8);
  iconv_close (cd_utf8_to_88591);

  /* -------------------------- Test str_iconv() -------------------------- */

  /* Test conversion from ISO-8859-1 to UTF-8 with no errors.  */
  {
    static const char input[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337";
    static const char expected[] = "\303\204rger mit b\303\266sen B\303\274bchen ohne Augenma\303\237";
    char *result = str_iconv (input, "ISO-8859-1", "UTF-8");
    ASSERT (result != NULL);
    ASSERT (strcmp (result, expected) == 0);
    free (result);
  }

  /* Test conversion from UTF-8 to ISO-8859-1 with no errors.  */
  {
    static const char input[] = "\303\204rger mit b\303\266sen B\303\274bchen ohne Augenma\303\237";
    static const char expected[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337";
    char *result = str_iconv (input, "UTF-8", "ISO-8859-1");
    ASSERT (result != NULL);
    ASSERT (strcmp (result, expected) == 0);
    free (result);
  }

  /* Test conversion from UTF-8 to ISO-8859-1 with EILSEQ.  */
  {
    static const char input[] = "Costs: 27 \342\202\254"; /* EURO SIGN */
    char *result = str_iconv (input, "UTF-8", "ISO-8859-1");
    ASSERT (result == NULL && errno == EILSEQ);
  }

  /* Test conversion from UTF-8 to ISO-8859-1 with EINVAL.  */
  {
    static const char input[] = "\342";
    char *result = str_iconv (input, "UTF-8", "ISO-8859-1");
    ASSERT (result != NULL);
    ASSERT (strcmp (result, "") == 0);
    free (result);
  }

#endif

  return 0;
}