File: utf8converttest.cc

package info (click to toggle)
xapian-omega 1.0.7-3+lenny2
  • links: PTS
  • area: main
  • in suites: lenny
  • size: 2,424 kB
  • ctags: 744
  • sloc: sh: 9,112; cpp: 7,954; makefile: 245; perl: 119
file content (85 lines) | stat: -rw-r--r-- 2,811 bytes parent folder | download
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
/* utf8converttest.cc: test convert_to_utf8()
 *
 * Copyright (C) 2008 Olly Betts
 *
 * 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 2 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, write to the Free Software
 * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301
 * USA
 */

#include <config.h>

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

#include "utf8convert.h"

using namespace std;

struct testcase {
    const char * charset;
    const char * dump;
    size_t len;
    const char * utf8;
};

static const testcase tests[] = {
    { "utf8", "Hello world", 0, "Hello world" },
    { "iso-8859-1", "Hello world", 0, "Hello world" },
    { "us-ascii", "Hello world", 0, "Hello world" },
    { "iso-8859-1", "Hello\xa0world", 0, "Hello\xc2\xa0world" },
    { "ISO-8859-1", "Hello\xa0world", 0, "Hello\xc2\xa0world" },
    { "ISO8859-1", "Hello\xa0world", 0, "Hello\xc2\xa0world" },
    { "8859_1", "Hello\xa0world", 0, "Hello\xc2\xa0world" },
    { "UTF16BE", "\0T\0e\0s\0t", 8, "Test" },
    { "UTF16", "\xfe\xff\0T\0e\0s\0t", 10, "Test" },
    { "UTF16LE", "T\0e\0s\0t\0", 8, "Test" },
    { "UTF16", "\xff\xfeT\0e\0s\0t\0", 10, "Test" },
    { "UCS-2BE", "\0T\0e\0s\0t", 8, "Test" },
    { "UCS-2LE", "T\0e\0s\0t\0", 8, "Test" },
    { "UTF16BE", "\xdb\xff\xdf\xfd", 0, "\xf4\x8f\xbf\xbd" },
    { "UTF16", "\xfe\xff\xdb\xff\xdf\xfd", 0, "\xf4\x8f\xbf\xbd" },
    { "UTF16LE", "\xff\xdb\xfd\xdf", 0, "\xf4\x8f\xbf\xbd" },
    { "UTF16", "\xff\xfe\xff\xdb\xfd\xdf", 0, "\xf4\x8f\xbf\xbd" },
// GNU libiconv doesn't seem to handle these as expected:
#ifndef USE_ICONV
    { "UCS-2", "\xfe\xff\0T\0e\0s\0t", 10, "Test" },
    { "UCS-2", "\xff\xfeT\0e\0s\0t\0", 10, "Test" },
    // If there's no BOM, we're supposed to assume BE.
    { "UTF16", "\xdb\xff\xdf\xfd", 0, "\xf4\x8f\xbf\xbd" },
#endif
    { 0, 0, 0, 0 }
};

int
main()
{
    for (size_t i = 0; tests[i].charset; ++i) {
	size_t len = tests[i].len;
	string dump;
	if (len) {
	    dump.assign(tests[i].dump, len);
	} else {
	    dump.assign(tests[i].dump);
	}
	convert_to_utf8(dump, tests[i].charset);
	if (tests[i].utf8 != dump) {
	    cout << "Converting from " << tests[i].charset << "\n"
		    "Expected [" << tests[i].utf8 << "]\n"
		    "Got      [" << dump << "]" << endl;
	    exit(1);
	}
    }
}