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
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
|
// Copyright 2017 The Chromium Authors
// Use of this source code is governed by a BSD-style license that can be
// found in the LICENSE file.
#include "third_party/blink/renderer/platform/network/header_field_tokenizer.h"
#include "third_party/blink/renderer/platform/wtf/text/string_builder.h"
#include "third_party/blink/renderer/platform/wtf/text/string_view.h"
namespace blink {
namespace {
using Mode = HeaderFieldTokenizer::Mode;
bool IsTokenCharacter(Mode mode, UChar c) {
// TODO(cvazac) change this to use LChar
// TODO(cvazac) Check HTTPArchive for usage and possible deprecation.
// According to https://tools.ietf.org/html/rfc7230#appendix-B, the
// following characters (ASCII decimal) should not be included in a TOKEN:
// 123 ('{')
// 125 ('}')
// 127 (delete)
if (c >= 128)
return false;
if (c < 0x20)
return false;
switch (c) {
case ' ':
case ';':
case '"':
return false;
case '(':
case ')':
case '<':
case '>':
case '@':
case ',':
case ':':
case '\\':
case '/':
case '[':
case ']':
case '?':
case '=':
return mode == Mode::kRelaxed;
default:
return true;
}
}
} // namespace
HeaderFieldTokenizer::HeaderFieldTokenizer(const String& header_field)
: index_(0u), input_(header_field) {
SkipOptionalWhitespace();
}
HeaderFieldTokenizer::HeaderFieldTokenizer(HeaderFieldTokenizer&&) = default;
bool HeaderFieldTokenizer::Consume(char c) {
// TODO(cvazac) change this to use LChar
DCHECK_NE(c, ' ');
DCHECK_NE(c, '\t');
if (IsConsumed() || input_[index_] != c)
return false;
++index_;
SkipOptionalWhitespace();
return true;
}
bool HeaderFieldTokenizer::ConsumeQuotedString(String& output) {
StringBuilder builder;
DCHECK_EQ('"', input_[index_]);
++index_;
while (!IsConsumed()) {
if (input_[index_] == '"') {
output = builder.ToString();
++index_;
SkipOptionalWhitespace();
return true;
}
if (input_[index_] == '\\') {
++index_;
if (IsConsumed())
return false;
}
builder.Append(input_[index_]);
++index_;
}
return false;
}
bool HeaderFieldTokenizer::ConsumeToken(Mode mode, StringView& output) {
DCHECK(output.IsNull());
auto start = index_;
while (!IsConsumed() && IsTokenCharacter(mode, input_[index_]))
++index_;
if (start == index_)
return false;
output = StringView(input_, start, index_ - start);
SkipOptionalWhitespace();
return true;
}
bool HeaderFieldTokenizer::ConsumeTokenOrQuotedString(Mode mode,
String& output) {
if (IsConsumed())
return false;
if (input_[index_] == '"')
return ConsumeQuotedString(output);
StringView view;
if (!ConsumeToken(mode, view))
return false;
output = view.ToString();
return true;
}
void HeaderFieldTokenizer::SkipOptionalWhitespace() {
while (!IsConsumed() && (input_[index_] == ' ' || input_[index_] == '\t'))
++index_;
}
void HeaderFieldTokenizer::ConsumeBeforeAnyCharMatch(Vector<LChar> chars) {
// TODO(cvazac) move this to HeaderFieldTokenizer c'tor
DCHECK(input_.Is8Bit());
DCHECK_GT(chars.size(), 0U);
DCHECK_LT(chars.size(), 3U);
while (!IsConsumed()) {
for (const auto& c : chars) {
if (c == input_[index_]) {
return;
}
}
++index_;
}
}
} // namespace blink
|
