blob: 340e0d9aee363ec6712c3c2a99aabb0d9156e573 (
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
129
|
// Copyright (C) 2015 The Android Open Source Project
//
// 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
//
// http://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.
#include "tokenizer.h"
namespace init {
Tokenizer::Tokenizer(const std::string& data)
: data_(data), eof_(false), pos_(0), tok_start_(0) {
current_.type = TOK_START;
if (data.size() > 0) {
cur_char_ = data[0];
} else {
eof_ = true;
cur_char_ = '\0';
}
}
Tokenizer::~Tokenizer() {}
const Tokenizer::Token& Tokenizer::current() {
return current_;
}
bool Tokenizer::Next() {
while (!eof_) {
AdvWhiteSpace();
// Check for comments.
if (cur_char_ == '#') {
AdvChar();
// Skip rest of line
while (!eof_ && cur_char_ != '\n') {
AdvChar();
}
}
if (eof_) {
break;
}
if (cur_char_ == '\0') {
AdvChar();
} else if (cur_char_ == '\n') {
current_.type = TOK_NEWLINE;
current_.text.clear();
AdvChar();
return true;
} else if (cur_char_ == '\\') {
AdvChar(); // skip backslash
// This is line continuation so
// do not generated TOK_NEWLINE at
// the next \n.
AdvUntil('\n');
AdvChar(); // skip \n
} else if (cur_char_ == '\"') {
AdvChar();
StartText();
// Grab everything until the next quote.
AdvUntil('\"');
EndText();
AdvChar(); // skip quote.
return true;
} else {
StartText();
AdvText();
EndText();
return true;
}
}
current_.type = TOK_END;
current_.text.clear();
return false;
}
void Tokenizer::AdvChar() {
pos_++;
if (pos_ < data_.size()) {
cur_char_ = data_[pos_];
} else {
eof_ = true;
cur_char_ = '\0';
}
}
void Tokenizer::AdvWhiteSpace() {
while (cur_char_ == '\t' || cur_char_ == '\r' || cur_char_ == ' ') {
AdvChar();
}
}
void Tokenizer::AdvUntil(char x) {
while (!eof_ && cur_char_ != x) {
AdvChar();
}
}
void Tokenizer::AdvText() {
while (cur_char_ != '\t' && cur_char_ != '\r' && cur_char_ != '\0' &&
cur_char_ != ' ' && cur_char_ != '\n' && cur_char_ != '#') {
AdvChar();
}
}
void Tokenizer::StartText() {
current_.text.clear();
tok_start_ = pos_;
current_.type = TOK_TEXT;
}
void Tokenizer::EndText() {
if (pos_ != tok_start_) {
current_.text.append(data_, tok_start_, pos_ - tok_start_);
}
}
} // namespace init
|
