summaryrefslogtreecommitdiff
path: root/libgo/go/net/http/lex.go
blob: 52b6481c14e725b2229e91916c1298e55b4a3cff (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
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
// Copyright 2009 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.

package http

import (
	"strings"
	"unicode/utf8"
)

// This file deals with lexical matters of HTTP

var isTokenTable = [127]bool{
	'!':  true,
	'#':  true,
	'$':  true,
	'%':  true,
	'&':  true,
	'\'': true,
	'*':  true,
	'+':  true,
	'-':  true,
	'.':  true,
	'0':  true,
	'1':  true,
	'2':  true,
	'3':  true,
	'4':  true,
	'5':  true,
	'6':  true,
	'7':  true,
	'8':  true,
	'9':  true,
	'A':  true,
	'B':  true,
	'C':  true,
	'D':  true,
	'E':  true,
	'F':  true,
	'G':  true,
	'H':  true,
	'I':  true,
	'J':  true,
	'K':  true,
	'L':  true,
	'M':  true,
	'N':  true,
	'O':  true,
	'P':  true,
	'Q':  true,
	'R':  true,
	'S':  true,
	'T':  true,
	'U':  true,
	'W':  true,
	'V':  true,
	'X':  true,
	'Y':  true,
	'Z':  true,
	'^':  true,
	'_':  true,
	'`':  true,
	'a':  true,
	'b':  true,
	'c':  true,
	'd':  true,
	'e':  true,
	'f':  true,
	'g':  true,
	'h':  true,
	'i':  true,
	'j':  true,
	'k':  true,
	'l':  true,
	'm':  true,
	'n':  true,
	'o':  true,
	'p':  true,
	'q':  true,
	'r':  true,
	's':  true,
	't':  true,
	'u':  true,
	'v':  true,
	'w':  true,
	'x':  true,
	'y':  true,
	'z':  true,
	'|':  true,
	'~':  true,
}

func isToken(r rune) bool {
	i := int(r)
	return i < len(isTokenTable) && isTokenTable[i]
}

func isNotToken(r rune) bool {
	return !isToken(r)
}

// headerValuesContainsToken reports whether any string in values
// contains the provided token, ASCII case-insensitively.
func headerValuesContainsToken(values []string, token string) bool {
	for _, v := range values {
		if headerValueContainsToken(v, token) {
			return true
		}
	}
	return false
}

// isOWS reports whether b is an optional whitespace byte, as defined
// by RFC 7230 section 3.2.3.
func isOWS(b byte) bool { return b == ' ' || b == '\t' }

// trimOWS returns x with all optional whitespace removes from the
// beginning and end.
func trimOWS(x string) string {
	// TODO: consider using strings.Trim(x, " \t") instead,
	// if and when it's fast enough. See issue 10292.
	// But this ASCII-only code will probably always beat UTF-8
	// aware code.
	for len(x) > 0 && isOWS(x[0]) {
		x = x[1:]
	}
	for len(x) > 0 && isOWS(x[len(x)-1]) {
		x = x[:len(x)-1]
	}
	return x
}

// headerValueContainsToken reports whether v (assumed to be a
// 0#element, in the ABNF extension described in RFC 7230 section 7)
// contains token amongst its comma-separated tokens, ASCII
// case-insensitively.
func headerValueContainsToken(v string, token string) bool {
	v = trimOWS(v)
	if comma := strings.IndexByte(v, ','); comma != -1 {
		return tokenEqual(trimOWS(v[:comma]), token) || headerValueContainsToken(v[comma+1:], token)
	}
	return tokenEqual(v, token)
}

// lowerASCII returns the ASCII lowercase version of b.
func lowerASCII(b byte) byte {
	if 'A' <= b && b <= 'Z' {
		return b + ('a' - 'A')
	}
	return b
}

// tokenEqual reports whether t1 and t2 are equal, ASCII case-insensitively.
func tokenEqual(t1, t2 string) bool {
	if len(t1) != len(t2) {
		return false
	}
	for i, b := range t1 {
		if b >= utf8.RuneSelf {
			// No UTF-8 or non-ASCII allowed in tokens.
			return false
		}
		if lowerASCII(byte(b)) != lowerASCII(t2[i]) {
			return false
		}
	}
	return true
}

// isLWS reports whether b is linear white space, according
// to http://www.w3.org/Protocols/rfc2616/rfc2616-sec2.html#sec2.2
//      LWS            = [CRLF] 1*( SP | HT )
func isLWS(b byte) bool { return b == ' ' || b == '\t' }

// isCTL reports whether b is a control byte, according
// to http://www.w3.org/Protocols/rfc2616/rfc2616-sec2.html#sec2.2
//      CTL            = <any US-ASCII control character
//                       (octets 0 - 31) and DEL (127)>
func isCTL(b byte) bool {
	const del = 0x7f // a CTL
	return b < ' ' || b == del
}