blob: 64a05d8b47689efa199249c37a586d3551437301 (
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
|
// Copyright (C) 2021 Scott Lamb <slamb@slamb.org>
// SPDX-License-Identifier: MIT OR Apache-2.0
//! Builds and offers lookup on a table of byte values to the character
//! classes the respective bytes are part of. Most classes are referenced from
//! [RFC 7235 Appendix B: Imported ABNF](https://datatracker.ietf.org/doc/html/rfc7235#appendix-B)
//! or [RFC 7235 Appendix C: Collected ABNF](https://datatracker.ietf.org/doc/html/rfc7235#appendix-C).
pub(crate) const C_TCHAR: u8 = 1;
pub(crate) const C_QDTEXT: u8 = 2;
pub(crate) const C_ESCAPABLE: u8 = 4;
pub(crate) const C_OWS: u8 = 8;
pub(crate) const C_ATTR: u8 = 16;
static TABLE: [u8; 128] = build_table();
pub(crate) fn char_classes(b: u8) -> u8 {
*TABLE.get(usize::from(b)).unwrap_or(&0)
}
const fn build_table() -> [u8; 128] {
// It'd be nice to use array::from_fn here, but it wasn't stablized until Rust 1.63.
let mut table = [0u8; 128];
let mut i = 0;
while i < 128 {
let b = i as u8;
let mut classes = 0;
if is_tchar(b) {
classes |= C_TCHAR;
}
if is_qdtext(b) {
classes |= C_QDTEXT;
}
if is_escapable(b) {
classes |= C_ESCAPABLE;
}
if is_ows(b) {
classes |= C_OWS;
}
if is_attr(b) {
classes |= C_ATTR;
}
table[i] = classes;
i += 1;
}
table
}
/// Returns if the byte is a `tchar` as defined in
/// [RFC 7230 section 3.2.6](https://datatracker.ietf.org/doc/html/rfc7230#section-3.2.6).
const fn is_tchar(b: u8) -> bool {
// tchar = "!" / "#" / "$" / "%" / "&" / "'" / "*"
// / "+" / "-" / "." / "^" / "_" / "`" / "|" / "~"
// / DIGIT / ALPHA
// ; any VCHAR, except delimiters
matches!(b,
b'!'
| b'#'
| b'$'
| b'%'
| b'&'
| b'\''
| b'*'
| b'+'
| b'-'
| b'.'
| b'^'
| b'_'
| b'`'
| b'|'
| b'~'
| b'0'..=b'9'
| b'a'..=b'z'
| b'A'..=b'Z')
}
/// Returns true if the byte is a valid `qdtext` (excluding `obs-text`), as defined in
/// [RFC 7230 section 3.2.6](https://datatracker.ietf.org/doc/html/rfc7230#section-3.2.6).
///
/// ```text
/// quoted-string = DQUOTE *( qdtext / quoted-pair ) DQUOTE
/// qdtext = HTAB / SP /%x21 / %x23-5B / %x5D-7E / obs-text
/// obs-text = %x80-FF
/// quoted-pair = "\" ( HTAB / SP / VCHAR / obs-text )
/// VCHAR = %x21-7E
/// ; visible (printing) characters
/// ```
const fn is_qdtext(b: u8) -> bool {
matches!(b, b'\t' | b' ' | 0x21 | 0x23..=0x5B | 0x5D..=0x7E)
}
/// Returns true if the byte is a valid end of a `quoted-pair`, as defined in
/// [RFC 7230 section 3.2.6](https://datatracker.ietf.org/doc/html/rfc7230#section-3.2.6).
const fn is_escapable(b: u8) -> bool {
matches!(b, b'\t' | b' ' | 0x21..=0x7E | 0x80..=0xFF)
}
/// Returns true if the byte is a valid `attr-char` as defined in
/// [RFC 5987 section 3.2.1](https://datatracker.ietf.org/doc/html/rfc5987#section-3.2.1).
///
/// ```text
/// attr-char = ALPHA / DIGIT
/// / "!" / "#" / "$" / "&" / "+" / "-" / "."
/// / "^" / "_" / "`" / "|" / "~"
/// ; token except ( "*" / "'" / "%" )
/// ```
const fn is_attr(b: u8) -> bool {
matches!(b,
b'a'..=b'z'
| b'A'..=b'Z'
| b'0'..=b'9'
| b'!'
| b'#'
| b'$'
| b'&'
| b'+'
| b'-'
| b'.'
| b'^'
| b'_'
| b'`'
| b'|'
| b'~')
}
/// Returns true if the byte is valid optional whitespace as in [RFC 7230 section
/// 3.2.3](https://datatracker.ietf.org/doc/html/rfc7230#section-3.2.3).
///
/// ```text
/// OWS = *( SP / HTAB )
/// ; optional whitespace
/// ```
const fn is_ows(b: u8) -> bool {
matches!(b, b' ' | b'\t')
}
|
