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
|
// Copyright 2017 The Abseil Authors.
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
// https://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
//
// UTF8 utilities, implemented to reduce dependencies.
#ifndef ABSL_STRINGS_INTERNAL_UTF8_H_
#define ABSL_STRINGS_INTERNAL_UTF8_H_
#include <cstddef>
#include <cstdint>
#include "absl/base/config.h"
namespace absl {
ABSL_NAMESPACE_BEGIN
namespace strings_internal {
// For Unicode code points 0 through 0x10FFFF, EncodeUTF8Char writes
// out the UTF-8 encoding into buffer, and returns the number of chars
// it wrote.
//
// As described in https://tools.ietf.org/html/rfc3629#section-3 , the encodings
// are:
// 00 - 7F : 0xxxxxxx
// 80 - 7FF : 110xxxxx 10xxxxxx
// 800 - FFFF : 1110xxxx 10xxxxxx 10xxxxxx
// 10000 - 10FFFF : 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx
//
// Values greater than 0x10FFFF are not supported and may or may not write
// characters into buffer, however never will more than kMaxEncodedUTF8Size
// bytes be written, regardless of the value of utf8_char.
enum { kMaxEncodedUTF8Size = 4 };
size_t EncodeUTF8Char(char* buffer, char32_t utf8_char);
struct ShiftState {
bool saw_high_surrogate = false;
unsigned char bits = 0;
};
// Converts `wc` from UTF-16 or UTF-32 to UTF-8 and writes to `buf`. `buf` is
// assumed to have enough space for the output. `s` is used to carry state
// between successive calls with a UTF-16 surrogate pair. Returns the number of
// chars written, or `static_cast<size_t>(-1)` on failure.
//
// This is basically std::wcrtomb(), but always outputting UTF-8 instead of
// respecting the current locale.
size_t WideToUtf8(wchar_t wc, char* buf, ShiftState& s);
} // namespace strings_internal
ABSL_NAMESPACE_END
} // namespace absl
#endif // ABSL_STRINGS_INTERNAL_UTF8_H_
|
