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
|
// Copyright (c) 2009 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 "base/strings/utf_string_conversion_utils.h"
#include "base/third_party/icu/icu_utf.h"
namespace base {
// ReadUnicodeCharacter --------------------------------------------------------
bool ReadUnicodeCharacter(const char* src,
int32_t src_len,
int32_t* char_index,
uint32_t* code_point_out) {
// U8_NEXT expects to be able to use -1 to signal an error, so we must
// use a signed type for code_point. But this function returns false
// on error anyway, so code_point_out is unsigned.
int32_t code_point;
CBU8_NEXT(src, *char_index, src_len, code_point);
*code_point_out = static_cast<uint32_t>(code_point);
// The ICU macro above moves to the next char, we want to point to the last
// char consumed.
(*char_index)--;
// Validate the decoded value.
return IsValidCodepoint(code_point);
}
// WriteUnicodeCharacter -------------------------------------------------------
size_t WriteUnicodeCharacter(uint32_t code_point, std::string* output) {
if (code_point <= 0x7f) {
// Fast path the common case of one byte.
output->push_back(static_cast<char>(code_point));
return 1;
}
// CBU8_APPEND_UNSAFE can append up to 4 bytes.
size_t char_offset = output->length();
size_t original_char_offset = char_offset;
output->resize(char_offset + CBU8_MAX_LENGTH);
CBU8_APPEND_UNSAFE(&(*output)[0], char_offset, code_point);
// CBU8_APPEND_UNSAFE will advance our pointer past the inserted character, so
// it will represent the new length of the string.
output->resize(char_offset);
return char_offset - original_char_offset;
}
// Generalized Unicode converter -----------------------------------------------
template<typename CHAR>
void PrepareForUTF8Output(const CHAR* src,
size_t src_len,
std::string* output) {
output->clear();
if (src_len == 0)
return;
if (src[0] < 0x80) {
// Assume that the entire input will be ASCII.
output->reserve(src_len);
} else {
// Assume that the entire input is non-ASCII and will have 3 bytes per char.
output->reserve(src_len * 3);
}
}
template<typename STRING>
void PrepareForUTF16Or32Output(const char* src,
size_t src_len,
STRING* output) {
output->clear();
if (src_len == 0)
return;
if (static_cast<unsigned char>(src[0]) < 0x80) {
// Assume the input is all ASCII, which means 1:1 correspondence.
output->reserve(src_len);
} else {
// Otherwise assume that the UTF-8 sequences will have 2 bytes for each
// character.
output->reserve(src_len / 2);
}
}
} // namespace base
|
