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
|
// Copyright 2014 The Chromium Authors. All rights reserved.
// Use of this source code is governed by a BSD-style license that can be
// found in the LICENSE file.
#include "net/base/net_string_util.h"
#include "base/i18n/i18n_constants.h"
#include "base/i18n/icu_string_conversions.h"
#include "base/strings/string_util.h"
#include "third_party/icu/source/common/unicode/ucnv.h"
namespace net {
const char* const kCharsetLatin1 = base::kCodepageLatin1;
bool ConvertToUtf8(const std::string& text, const char* charset,
std::string* output) {
output->clear();
UErrorCode err = U_ZERO_ERROR;
UConverter* converter(ucnv_open(charset, &err));
if (U_FAILURE(err))
return false;
// A single byte in a legacy encoding can be expanded to 3 bytes in UTF-8.
// A 'two-byte character' in a legacy encoding can be expanded to 4 bytes
// in UTF-8. Therefore, the expansion ratio is 3 at most. Add one for a
// trailing '\0'.
size_t output_length = text.length() * 3 + 1;
char* buf = WriteInto(output, output_length);
output_length = ucnv_toAlgorithmic(UCNV_UTF8, converter, buf, output_length,
text.data(), text.length(), &err);
ucnv_close(converter);
if (U_FAILURE(err)) {
output->clear();
return false;
}
output->resize(output_length);
return true;
}
bool ConvertToUtf8AndNormalize(const std::string& text, const char* charset,
std::string* output) {
return base::ConvertToUtf8AndNormalize(text, charset, output);
}
bool ConvertToUTF16(const std::string& text, const char* charset,
base::string16* output) {
return base::CodepageToUTF16(text, charset,
base::OnStringConversionError::FAIL, output);
}
bool ConvertToUTF16WithSubstitutions(const std::string& text,
const char* charset,
base::string16* output) {
return base::CodepageToUTF16(text, charset,
base::OnStringConversionError::SUBSTITUTE,
output);
}
} // namespace net
|
