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
|
// Copyright (C) 2017-2022 Free Software Foundation, Inc.
//
// 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/>.
// { dg-do run { target c++11 } }
#include <codecvt>
#include <locale>
#include <string>
#include <testsuite_hooks.h>
using std::wstring_convert;
using std::codecvt_utf8;
void
test01()
{
std::string src = (const char*)u8"1234\U00001111\U0001ffff";
wstring_convert<codecvt_utf8<char16_t>, char16_t> c("bad", u"BAD");
// utf-8 to ucs2 conversion should fail on character outside BMP
auto ucs2 = c.from_bytes(src);
VERIFY( ucs2 == u"BAD" );
VERIFY( c.converted() == 7 );
// ucs2 to utf-8 conversion should fail on invalid ucs2 input:
std::u16string utf16 = u"1234\U00001111\U0001ffff";
auto out = c.to_bytes(utf16);
VERIFY( out == "bad" );
VERIFY( c.converted() == 5 );
// And should also fail on incomplete surrogate pair (not return partial):
out = c.to_bytes(utf16.substr(0, utf16.size()-1));
VERIFY( out == "bad" );
VERIFY( c.converted() == 5 );
}
void
test02()
{
std::string src = (const char*)u8"1234\U00001111\U0001ffff";
wstring_convert<codecvt_utf8<char16_t, 0x1000>, char16_t> c("bad", u"BAD");
// utf-8 to ucs2 conversion should fail on character above Maxcode=0x1000
auto ucs2 = c.from_bytes(src);
VERIFY( ucs2 == u"BAD" );
VERIFY( c.converted() == 4 );
}
void
test03()
{
std::string src = (const char*)u8"1234\U00001111\U0001ffff";
wstring_convert<codecvt_utf8<char32_t, 0x10000>, char32_t> c("bad", U"BAD");
// utf-8 to ucs4 conversion should fail on character above Maxcode=0x10000
auto ucs4 = c.from_bytes(src);
VERIFY( ucs4 == U"BAD" );
VERIFY( c.converted() == 7 );
}
void
test04()
{
std::string src = (const char*)u8"1234\U00001111\U0001ffff";
wstring_convert<codecvt_utf8<char32_t, 0x1000>, char32_t> c("bad", U"BAD");
// utf-8 to ucs4 conversion should fail on character above Maxcode=0x1000
auto ucs4 = c.from_bytes(src);
VERIFY( ucs4 == U"BAD" );
VERIFY( c.converted() == 4 );
}
int
main()
{
test01();
test02();
test03();
test04();
}
|
