blob: f45b04b8b06b154dbf41e0acfa85207179533f2e (
plain)
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
|
// Copyright (c) 2010 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.
#ifndef BASE_I18N_CHAR_ITERATOR_H_
#define BASE_I18N_CHAR_ITERATOR_H_
#pragma once
#include <string>
#include "base/basictypes.h"
#include "base/string16.h"
// The CharIterator classes iterate through the characters in UTF8 and
// UTF16 strings. Example usage:
//
// UTF8CharIterator iter(&str);
// while (!iter.End()) {
// VLOG(1) << iter.get();
// iter.Advance();
// }
#if defined(OS_WIN)
typedef unsigned char uint8_t;
#endif
namespace base {
class UTF8CharIterator {
public:
// Requires |str| to live as long as the UTF8CharIterator does.
UTF8CharIterator(const std::string* str);
~UTF8CharIterator() {}
// Return the starting array index of the current character within the
// string.
int32 array_pos() const { return array_pos_; }
// Return the logical index of the current character, independent of the
// number of bytes each character takes.
int32 char_pos() const { return char_pos_; }
// Return the current char.
int32 get() const { return char_; }
// Returns true if we're at the end of the string.
bool end() const { return array_pos_ == len_; }
// Advance to the next actual character. Returns false if we're at the
// end of the string.
bool Advance();
private:
// The string we're iterating over.
const uint8_t* str_;
// The length of the encoded string.
int32 len_;
// Array index.
int32 array_pos_;
// The next array index.
int32 next_pos_;
// Character index.
int32 char_pos_;
// The current character.
int32 char_;
DISALLOW_COPY_AND_ASSIGN(UTF8CharIterator);
};
class UTF16CharIterator {
public:
// Requires |str| to live as long as the UTF16CharIterator does.
UTF16CharIterator(const string16* str);
UTF16CharIterator(const char16* str, size_t str_len);
~UTF16CharIterator() {}
// Return the starting array index of the current character within the
// string.
int32 array_pos() const { return array_pos_; }
// Return the logical index of the current character, independent of the
// number of codewords each character takes.
int32 char_pos() const { return char_pos_; }
// Return the current char.
int32 get() const { return char_; }
// Returns true if we're at the end of the string.
bool end() const { return array_pos_ == len_; }
// Advance to the next actual character. Returns false if we're at the
// end of the string.
bool Advance();
private:
// Fills in the current character we found and advances to the next
// character, updating all flags as necessary.
void ReadChar();
// The string we're iterating over.
const char16* str_;
// The length of the encoded string.
int32 len_;
// Array index.
int32 array_pos_;
// The next array index.
int32 next_pos_;
// Character index.
int32 char_pos_;
// The current character.
int32 char_;
DISALLOW_COPY_AND_ASSIGN(UTF16CharIterator);
};
} // namespace base
#endif // BASE_I18N_CHAR_ITERATOR_H_
|
