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
184
185
186
187
188
|
use core::char;
use core::fmt::{self, Write};
use core::mem;
use core::str as core_str;
// https://tools.ietf.org/html/rfc3629
static UTF8_CHAR_WIDTH: [u8; 256] = [
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, // 0x1F
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, // 0x3F
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, // 0x5F
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, // 0x7F
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, // 0x9F
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, // 0xBF
0, 0, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, // 0xDF
3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, // 0xEF
4, 4, 4, 4, 4, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 0xFF
];
/// Given a first byte, determines how many bytes are in this UTF-8 character.
#[inline]
pub fn utf8_char_width(b: u8) -> usize {
UTF8_CHAR_WIDTH[b as usize] as usize
}
/// Lossy UTF-8 string.
pub struct Utf8Lossy {
bytes: [u8],
}
impl Utf8Lossy {
pub fn from_bytes(bytes: &[u8]) -> &Utf8Lossy {
// SAFETY: Both use the same memory layout, and UTF-8 correctness isn't required.
unsafe { mem::transmute(bytes) }
}
pub fn chunks(&self) -> Utf8LossyChunksIter<'_> {
Utf8LossyChunksIter {
source: &self.bytes,
}
}
}
/// Iterator over lossy UTF-8 string
pub struct Utf8LossyChunksIter<'a> {
source: &'a [u8],
}
#[derive(PartialEq, Eq, Debug)]
pub struct Utf8LossyChunk<'a> {
/// Sequence of valid chars.
/// Can be empty between broken UTF-8 chars.
pub valid: &'a str,
/// Single broken char, empty if none.
/// Empty iff iterator item is last.
pub broken: &'a [u8],
}
impl<'a> Iterator for Utf8LossyChunksIter<'a> {
type Item = Utf8LossyChunk<'a>;
fn next(&mut self) -> Option<Utf8LossyChunk<'a>> {
if self.source.is_empty() {
return None;
}
const TAG_CONT_U8: u8 = 128;
fn safe_get(xs: &[u8], i: usize) -> u8 {
*xs.get(i).unwrap_or(&0)
}
let mut i = 0;
while i < self.source.len() {
let i_ = i;
// SAFETY: `i` starts at `0`, is less than `self.source.len()`, and
// only increases, so `0 <= i < self.source.len()`.
let byte = unsafe { *self.source.get_unchecked(i) };
i += 1;
if byte < 128 {
} else {
let w = utf8_char_width(byte);
macro_rules! error {
() => {{
// SAFETY: We have checked up to `i` that source is valid UTF-8.
unsafe {
let r = Utf8LossyChunk {
valid: core_str::from_utf8_unchecked(&self.source[0..i_]),
broken: &self.source[i_..i],
};
self.source = &self.source[i..];
return Some(r);
}
}};
}
match w {
2 => {
if safe_get(self.source, i) & 192 != TAG_CONT_U8 {
error!();
}
i += 1;
}
3 => {
match (byte, safe_get(self.source, i)) {
(0xE0, 0xA0..=0xBF) => (),
(0xE1..=0xEC, 0x80..=0xBF) => (),
(0xED, 0x80..=0x9F) => (),
(0xEE..=0xEF, 0x80..=0xBF) => (),
_ => {
error!();
}
}
i += 1;
if safe_get(self.source, i) & 192 != TAG_CONT_U8 {
error!();
}
i += 1;
}
4 => {
match (byte, safe_get(self.source, i)) {
(0xF0, 0x90..=0xBF) => (),
(0xF1..=0xF3, 0x80..=0xBF) => (),
(0xF4, 0x80..=0x8F) => (),
_ => {
error!();
}
}
i += 1;
if safe_get(self.source, i) & 192 != TAG_CONT_U8 {
error!();
}
i += 1;
if safe_get(self.source, i) & 192 != TAG_CONT_U8 {
error!();
}
i += 1;
}
_ => {
error!();
}
}
}
}
let r = Utf8LossyChunk {
// SAFETY: We have checked that the entire source is valid UTF-8.
valid: unsafe { core_str::from_utf8_unchecked(self.source) },
broken: &[],
};
self.source = &[];
Some(r)
}
}
impl fmt::Display for Utf8Lossy {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
// If we're the empty string then our iterator won't actually yield
// anything, so perform the formatting manually
if self.bytes.is_empty() {
return "".fmt(f);
}
for Utf8LossyChunk { valid, broken } in self.chunks() {
// If we successfully decoded the whole chunk as a valid string then
// we can return a direct formatting of the string which will also
// respect various formatting flags if possible.
if valid.len() == self.bytes.len() {
assert!(broken.is_empty());
return valid.fmt(f);
}
f.write_str(valid)?;
if !broken.is_empty() {
f.write_char(char::REPLACEMENT_CHARACTER)?;
}
}
Ok(())
}
}
|
