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
|
// { dg-require-iconv "UCS-2BE" }
// { dg-require-iconv "ISO-8859-15" }
// 2000-08-22 Benjamin Kosnik <bkoz@cygnus.com>
// Copyright (C) 2000, 2001, 2002, 2003, 2004, 2005, 2006, 2007, 2009
// Free Software Foundation
//
// This file is part of the GNU ISO C++ Library. This library 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, or (at your option)
// any later version.
// This library 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 library; see the file COPYING3. If not see
// <http://www.gnu.org/licenses/>.
// 22.2.1.5 - Template class codecvt [lib.locale.codecvt]
#include <locale>
#include <cstring>
#include <testsuite_hooks.h>
#include <ext/codecvt_specializations.h>
/*
> how do I check that these conversions are correct?
Very easy. Since all the characters are from ASCII you simply
zero-extend the values.
drepper$ echo 'black pearl jasmine tea' | od -t x1
0000000 62 6c 61 63 6b 20 70 65 61 72 6c 20 6a 61 73 6d
0000020 69 6e 65 20 74 65 61 0a
So the UCS-2 string is
0x0062, 0x006c, 0x0061, ...
You get the idea. With iconv() you have to take care of the
byte-order, though. UCS-2 can mean little- or big endian. Looking at
your result
> $9 = 25856
it shows that the other byte-order is used (25856 == 0x6500).
*/
// Partial specialization using encoding_state.
// codecvt<unicode_t, char, encoding_state>
// UNICODE - UCS2 (big endian)
void test01()
{
using namespace std;
typedef codecvt_base::result result;
typedef unsigned short int_type;
typedef char ext_type;
typedef __gnu_cxx::encoding_state state_type;
typedef codecvt<int_type, ext_type, state_type> unicode_codecvt;
typedef char_traits<int_type> int_traits;
typedef char_traits<ext_type> ext_traits;
bool test __attribute__((unused)) = true;
const ext_type* e_lit = "black pearl jasmine tea";
int size = strlen(e_lit);
char i_lit_base[50] __attribute__((aligned(__alignof__(int_type)))) =
{
0x00, 0x62, 0x00, 0x6c, 0x00, 0x61, 0x00, 0x63, 0x00, 0x6b, 0x00, 0x20,
0x00, 0x70, 0x00, 0x65, 0x00, 0x61, 0x00, 0x72, 0x00, 0x6c, 0x00, 0x20,
0x00, 0x6a, 0x00, 0x61, 0x00, 0x73, 0x00, 0x6d, 0x00, 0x69, 0x00, 0x6e,
0x00, 0x65, 0x00, 0x20, 0x00, 0x74, 0x00, 0x65, 0x00, 0x61, 0x00, 0xa0
};
const int_type* i_lit = reinterpret_cast<int_type*>(i_lit_base);
const ext_type* efrom_next;
const int_type* ifrom_next;
ext_type* e_arr = new ext_type[size + 1];
ext_type* eto_next;
int_type* i_arr = new int_type[size + 1];
int_type* ito_next;
// construct a locale object with the specialized facet.
locale loc(locale::classic(), new unicode_codecvt);
// sanity check the constructed locale has the specialized facet.
VERIFY( has_facet<unicode_codecvt>(loc) );
const unicode_codecvt& cvt = use_facet<unicode_codecvt>(loc);
// in
// unicode_codecvt::state_type state01("UCS-2BE", "ISO-8859-15", 0xfeff, 0);
unicode_codecvt::state_type state01("UCS-2BE", "ISO-8859-15", 0, 0);
// internal encoding is bigger because of bom
result r1 = cvt.in(state01, e_lit, e_lit + size, efrom_next,
i_arr, i_arr + size + 1, ito_next);
VERIFY( r1 == codecvt_base::ok );
VERIFY( !int_traits::compare(i_arr, i_lit, size) );
VERIFY( efrom_next == e_lit + size );
VERIFY( ito_next == i_arr + size );
// out
unicode_codecvt::state_type state02("UCS-2BE", "ISO-8859-15", 0, 0);
result r2 = cvt.out(state02, i_lit, i_lit + size, ifrom_next,
e_arr, e_arr + size, eto_next);
VERIFY( r2 == codecvt_base::ok );
VERIFY( !ext_traits::compare(e_arr, e_lit, size) );
VERIFY( ifrom_next == i_lit + size );
VERIFY( eto_next == e_arr + size );
// unshift
ext_traits::copy(e_arr, e_lit, size);
unicode_codecvt::state_type state03("UCS-2BE", "ISO-8859-15", 0, 0);
result r3 = cvt.unshift(state03, e_arr, e_arr + size, eto_next);
VERIFY( r3 == codecvt_base::noconv );
VERIFY( !ext_traits::compare(e_arr, e_lit, size) );
VERIFY( eto_next == e_arr );
int i = cvt.encoding();
VERIFY( i == 2 ); // Target-dependent.
VERIFY( !cvt.always_noconv() );
unicode_codecvt::state_type state04("UCS-2BE", "ISO-8859-15", 0, 0);
int j = cvt.length(state03, e_lit, e_lit + size, 5);
VERIFY( j == 5 );
int k = cvt.max_length();
VERIFY( k == 1 );
delete [] e_arr;
delete [] i_arr;
}
int main ()
{
test01();
return 0;
}
|
