Branch data Line data Source code
1 : : /* Test of character set conversion.
2 : : Copyright (C) 2007-2012 Free Software Foundation, Inc.
3 : :
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.
8 : :
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.
13 : :
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/>. */
16 : :
17 : : /* Written by Bruno Haible <bruno@clisp.org>, 2007. */
18 : :
19 : : #include <config.h>
20 : :
21 : : #if HAVE_ICONV
22 : : # include <iconv.h>
23 : :
24 : : # ifndef ICONV_CONST
25 : : # define ICONV_CONST /* empty */
26 : : # endif
27 : :
28 : : #include "signature.h"
29 : : SIGNATURE_CHECK (iconv, size_t, (iconv_t, ICONV_CONST char **, size_t *,
30 : : char **, size_t *));
31 : : SIGNATURE_CHECK (iconv_close, int, (iconv_t x));
32 : : SIGNATURE_CHECK (iconv_open, iconv_t, (char const *, char const *));
33 : :
34 : : #endif
35 : :
36 : : #include <errno.h>
37 : : #include <string.h>
38 : :
39 : : #include "macros.h"
40 : :
41 : : int
42 : 1 : main ()
43 : : {
44 : : #if HAVE_ICONV
45 : : /* Assume that iconv() supports at least the encodings ASCII, ISO-8859-1,
46 : : and UTF-8. */
47 : 1 : iconv_t cd_88591_to_utf8 = iconv_open ("UTF-8", "ISO-8859-1");
48 : 1 : iconv_t cd_utf8_to_88591 = iconv_open ("ISO-8859-1", "UTF-8");
49 : :
50 [ - + ]: 1 : ASSERT (cd_88591_to_utf8 != (iconv_t)(-1));
51 [ - + ]: 1 : ASSERT (cd_utf8_to_88591 != (iconv_t)(-1));
52 : :
53 : : /* Test conversion from ISO-8859-1 to UTF-8 with no errors. */
54 : : {
55 : : static const char input[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337";
56 : : static const char expected[] = "\303\204rger mit b\303\266sen B\303\274bchen ohne Augenma\303\237";
57 : : char buf[50];
58 : 1 : const char *inptr = input;
59 : 1 : size_t inbytesleft = strlen (input);
60 : 1 : char *outptr = buf;
61 : 1 : size_t outbytesleft = sizeof (buf);
62 : 1 : size_t res = iconv (cd_88591_to_utf8,
63 : : (ICONV_CONST char **) &inptr, &inbytesleft,
64 : : &outptr, &outbytesleft);
65 [ + - ][ - + ]: 1 : ASSERT (res == 0 && inbytesleft == 0);
66 [ - + ]: 1 : ASSERT (outptr == buf + strlen (expected));
67 [ - + ]: 1 : ASSERT (memcmp (buf, expected, strlen (expected)) == 0);
68 : : }
69 : :
70 : : /* Test conversion from ISO-8859-1 to UTF-8 with E2BIG. */
71 : : {
72 : : static const char input[] = "\304";
73 : : static char buf[2] = { (char)0xDE, (char)0xAD };
74 : 1 : const char *inptr = input;
75 : 1 : size_t inbytesleft = 1;
76 : 1 : char *outptr = buf;
77 : 1 : size_t outbytesleft = 1;
78 : 1 : size_t res = iconv (cd_88591_to_utf8,
79 : : (ICONV_CONST char **) &inptr, &inbytesleft,
80 : : &outptr, &outbytesleft);
81 [ + - ][ - + ]: 1 : ASSERT (res == (size_t)(-1) && errno == E2BIG);
82 [ - + ]: 1 : ASSERT (inbytesleft == 1);
83 [ - + ]: 1 : ASSERT (outbytesleft == 1);
84 [ - + ]: 1 : ASSERT ((unsigned char) buf[1] == 0xAD);
85 [ - + ]: 1 : ASSERT ((unsigned char) buf[0] == 0xDE);
86 : : }
87 : :
88 : : /* Test conversion from UTF-8 to ISO-8859-1 with no errors. */
89 : : {
90 : : static const char input[] = "\303\204rger mit b\303\266sen B\303\274bchen ohne Augenma\303\237";
91 : : static const char expected[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337";
92 : : char buf[50];
93 : 1 : const char *inptr = input;
94 : 1 : size_t inbytesleft = strlen (input);
95 : 1 : char *outptr = buf;
96 : 1 : size_t outbytesleft = sizeof (buf);
97 : 1 : size_t res = iconv (cd_utf8_to_88591,
98 : : (ICONV_CONST char **) &inptr, &inbytesleft,
99 : : &outptr, &outbytesleft);
100 [ + - ][ - + ]: 1 : ASSERT (res == 0 && inbytesleft == 0);
101 [ - + ]: 1 : ASSERT (outptr == buf + strlen (expected));
102 [ - + ]: 1 : ASSERT (memcmp (buf, expected, strlen (expected)) == 0);
103 : : }
104 : :
105 : : /* Test conversion from UTF-8 to ISO-8859-1 with EILSEQ. */
106 : : {
107 : : static const char input[] = "\342\202\254"; /* EURO SIGN */
108 : : char buf[10];
109 : 1 : const char *inptr = input;
110 : 1 : size_t inbytesleft = strlen (input);
111 : 1 : char *outptr = buf;
112 : 1 : size_t outbytesleft = sizeof (buf);
113 : 1 : size_t res = iconv (cd_utf8_to_88591,
114 : : (ICONV_CONST char **) &inptr, &inbytesleft,
115 : : &outptr, &outbytesleft);
116 [ + - ]: 1 : if (res == (size_t)(-1))
117 : : {
118 [ - + ]: 1 : ASSERT (errno == EILSEQ);
119 [ + - ][ - + ]: 1 : ASSERT (inbytesleft == strlen (input) && outptr == buf);
120 : : }
121 : : else
122 : : {
123 [ # # ]: 0 : ASSERT (res == 1);
124 [ # # ]: 0 : ASSERT (inbytesleft == 0);
125 : : }
126 : : }
127 : :
128 : : /* Test conversion from UTF-8 to ISO-8859-1 with EINVAL. */
129 : : {
130 : : static const char input[] = "\342";
131 : : char buf[10];
132 : 1 : const char *inptr = input;
133 : 1 : size_t inbytesleft = 1;
134 : 1 : char *outptr = buf;
135 : 1 : size_t outbytesleft = sizeof (buf);
136 : 1 : size_t res = iconv (cd_utf8_to_88591,
137 : : (ICONV_CONST char **) &inptr, &inbytesleft,
138 : : &outptr, &outbytesleft);
139 [ + - ][ - + ]: 1 : ASSERT (res == (size_t)(-1) && errno == EINVAL);
140 [ + - ][ - + ]: 1 : ASSERT (inbytesleft == 1 && outptr == buf);
141 : : }
142 : :
143 : 1 : iconv_close (cd_88591_to_utf8);
144 : 1 : iconv_close (cd_utf8_to_88591);
145 : : #endif
146 : :
147 : 1 : return 0;
148 : : }
|
