Line data Source code
1 : /* Test of character set conversion.
2 : Copyright (C) 2007-2020 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 <https://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 : #if defined __MVS__ && defined __IBMC__
51 : /* String literals below are in ASCII, not EBCDIC. */
52 : # pragma convert("ISO8859-1")
53 : # define CONVERT_ENABLED
54 : #endif
55 :
56 1 : ASSERT (cd_88591_to_utf8 != (iconv_t)(-1));
57 1 : ASSERT (cd_utf8_to_88591 != (iconv_t)(-1));
58 :
59 : /* Test conversion from ISO-8859-1 to UTF-8 with no errors. */
60 : {
61 : static const char input[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337";
62 : static const char expected[] = "\303\204rger mit b\303\266sen B\303\274bchen ohne Augenma\303\237";
63 : char buf[50];
64 1 : const char *inptr = input;
65 1 : size_t inbytesleft = strlen (input);
66 1 : char *outptr = buf;
67 1 : size_t outbytesleft = sizeof (buf);
68 1 : size_t res = iconv (cd_88591_to_utf8,
69 : (ICONV_CONST char **) &inptr, &inbytesleft,
70 : &outptr, &outbytesleft);
71 1 : ASSERT (res == 0 && inbytesleft == 0);
72 1 : ASSERT (outptr == buf + strlen (expected));
73 1 : ASSERT (memcmp (buf, expected, strlen (expected)) == 0);
74 : }
75 :
76 : /* Test conversion from ISO-8859-1 to UTF-8 with E2BIG. */
77 : {
78 : static const char input[] = "\304";
79 : static char buf[2] = { (char)0xDE, (char)0xAD };
80 1 : const char *inptr = input;
81 1 : size_t inbytesleft = 1;
82 1 : char *outptr = buf;
83 1 : size_t outbytesleft = 1;
84 1 : size_t res = iconv (cd_88591_to_utf8,
85 : (ICONV_CONST char **) &inptr, &inbytesleft,
86 : &outptr, &outbytesleft);
87 1 : ASSERT (res == (size_t)(-1) && errno == E2BIG);
88 1 : ASSERT (inbytesleft == 1);
89 1 : ASSERT (outbytesleft == 1);
90 1 : ASSERT ((unsigned char) buf[1] == 0xAD);
91 1 : ASSERT ((unsigned char) buf[0] == 0xDE);
92 : }
93 :
94 : /* Test conversion from UTF-8 to ISO-8859-1 with no errors. */
95 : {
96 : static const char input[] = "\303\204rger mit b\303\266sen B\303\274bchen ohne Augenma\303\237";
97 : static const char expected[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337";
98 : char buf[50];
99 1 : const char *inptr = input;
100 1 : size_t inbytesleft = strlen (input);
101 1 : char *outptr = buf;
102 1 : size_t outbytesleft = sizeof (buf);
103 1 : size_t res = iconv (cd_utf8_to_88591,
104 : (ICONV_CONST char **) &inptr, &inbytesleft,
105 : &outptr, &outbytesleft);
106 1 : ASSERT (res == 0 && inbytesleft == 0);
107 1 : ASSERT (outptr == buf + strlen (expected));
108 1 : ASSERT (memcmp (buf, expected, strlen (expected)) == 0);
109 : }
110 :
111 : /* Test conversion from UTF-8 to ISO-8859-1 with EILSEQ. */
112 : {
113 : static const char input[] = "\342\202\254"; /* EURO SIGN */
114 : char buf[10];
115 1 : const char *inptr = input;
116 1 : size_t inbytesleft = strlen (input);
117 1 : char *outptr = buf;
118 1 : size_t outbytesleft = sizeof (buf);
119 1 : size_t res = iconv (cd_utf8_to_88591,
120 : (ICONV_CONST char **) &inptr, &inbytesleft,
121 : &outptr, &outbytesleft);
122 1 : if (res == (size_t)(-1))
123 : {
124 1 : ASSERT (errno == EILSEQ);
125 1 : ASSERT (inbytesleft == strlen (input) && outptr == buf);
126 : }
127 : else
128 : {
129 0 : ASSERT (res == 1);
130 0 : ASSERT (inbytesleft == 0);
131 : }
132 : }
133 :
134 : /* Test conversion from UTF-8 to ISO-8859-1 with EINVAL. */
135 : {
136 : static const char input[] = "\342";
137 : char buf[10];
138 1 : const char *inptr = input;
139 1 : size_t inbytesleft = 1;
140 1 : char *outptr = buf;
141 1 : size_t outbytesleft = sizeof (buf);
142 1 : size_t res = iconv (cd_utf8_to_88591,
143 : (ICONV_CONST char **) &inptr, &inbytesleft,
144 : &outptr, &outbytesleft);
145 1 : ASSERT (res == (size_t)(-1) && errno == EINVAL);
146 1 : ASSERT (inbytesleft == 1 && outptr == buf);
147 : }
148 :
149 1 : iconv_close (cd_88591_to_utf8);
150 1 : iconv_close (cd_utf8_to_88591);
151 :
152 : #ifdef CONVERT_ENABLED
153 : # pragma convert(pop)
154 : #endif
155 :
156 : #endif /* HAVE_ICONV */
157 :
158 1 : return 0;
159 : }
|