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
|
use std::fmt::Write;
use console::AnsiCodeIterator;
use crate::nonprintable_notation::NonprintableNotation;
/// Expand tabs like an ANSI-enabled expand(1).
pub fn expand_tabs(line: &str, width: usize, cursor: &mut usize) -> String {
let mut buffer = String::with_capacity(line.len() * 2);
for chunk in AnsiCodeIterator::new(line) {
match chunk {
(text, true) => buffer.push_str(text),
(mut text, false) => {
while let Some(index) = text.find('\t') {
// Add previous text.
if index > 0 {
*cursor += index;
buffer.push_str(&text[0..index]);
}
// Add tab.
let spaces = width - (*cursor % width);
*cursor += spaces;
buffer.push_str(&" ".repeat(spaces));
// Next.
text = &text[index + 1..text.len()];
}
*cursor += text.len();
buffer.push_str(text);
}
}
}
buffer
}
fn try_parse_utf8_char(input: &[u8]) -> Option<(char, usize)> {
let str_from_utf8 = |seq| std::str::from_utf8(seq).ok();
let decoded = input
.get(0..1)
.and_then(str_from_utf8)
.map(|c| (c, 1))
.or_else(|| input.get(0..2).and_then(str_from_utf8).map(|c| (c, 2)))
.or_else(|| input.get(0..3).and_then(str_from_utf8).map(|c| (c, 3)))
.or_else(|| input.get(0..4).and_then(str_from_utf8).map(|c| (c, 4)));
decoded.map(|(seq, n)| (seq.chars().next().unwrap(), n))
}
pub fn replace_nonprintable(
input: &[u8],
tab_width: usize,
nonprintable_notation: NonprintableNotation,
) -> String {
let mut output = String::new();
let tab_width = if tab_width == 0 { 4 } else { tab_width };
let mut idx = 0;
let mut line_idx = 0;
let len = input.len();
while idx < len {
if let Some((chr, skip_ahead)) = try_parse_utf8_char(&input[idx..]) {
idx += skip_ahead;
line_idx += 1;
match chr {
// space
' ' => output.push('·'),
// tab
'\t' => {
let tab_stop = tab_width - ((line_idx - 1) % tab_width);
line_idx = 0;
if tab_stop == 1 {
output.push('↹');
} else {
output.push('├');
output.push_str(&"─".repeat(tab_stop - 2));
output.push('┤');
}
}
// line feed
'\x0A' => {
output.push_str(match nonprintable_notation {
NonprintableNotation::Caret => "^J\x0A",
NonprintableNotation::Unicode => "␊\x0A",
});
line_idx = 0;
}
// carriage return
'\x0D' => output.push_str(match nonprintable_notation {
NonprintableNotation::Caret => "^M",
NonprintableNotation::Unicode => "␍",
}),
// null
'\x00' => output.push_str(match nonprintable_notation {
NonprintableNotation::Caret => "^@",
NonprintableNotation::Unicode => "␀",
}),
// bell
'\x07' => output.push_str(match nonprintable_notation {
NonprintableNotation::Caret => "^G",
NonprintableNotation::Unicode => "␇",
}),
// backspace
'\x08' => output.push_str(match nonprintable_notation {
NonprintableNotation::Caret => "^H",
NonprintableNotation::Unicode => "␈",
}),
// escape
'\x1B' => output.push_str(match nonprintable_notation {
NonprintableNotation::Caret => "^[",
NonprintableNotation::Unicode => "␛",
}),
// printable ASCII
c if c.is_ascii_alphanumeric()
|| c.is_ascii_punctuation()
|| c.is_ascii_graphic() =>
{
output.push(c)
}
// everything else
c => output.push_str(&c.escape_unicode().collect::<String>()),
}
} else {
write!(output, "\\x{:02X}", input[idx]).ok();
idx += 1;
}
}
output
}
#[test]
fn test_try_parse_utf8_char() {
assert_eq!(try_parse_utf8_char(&[0x20]), Some((' ', 1)));
assert_eq!(try_parse_utf8_char(&[0x20, 0x20]), Some((' ', 1)));
assert_eq!(try_parse_utf8_char(&[0x20, 0xef]), Some((' ', 1)));
assert_eq!(try_parse_utf8_char(&[0x00]), Some(('\x00', 1)));
assert_eq!(try_parse_utf8_char(&[0x1b]), Some(('\x1b', 1)));
assert_eq!(try_parse_utf8_char(&[0xc3, 0xa4]), Some(('ä', 2)));
assert_eq!(try_parse_utf8_char(&[0xc3, 0xa4, 0xef]), Some(('ä', 2)));
assert_eq!(try_parse_utf8_char(&[0xc3, 0xa4, 0x20]), Some(('ä', 2)));
assert_eq!(try_parse_utf8_char(&[0xe2, 0x82, 0xac]), Some(('€', 3)));
assert_eq!(
try_parse_utf8_char(&[0xe2, 0x82, 0xac, 0xef]),
Some(('€', 3))
);
assert_eq!(
try_parse_utf8_char(&[0xe2, 0x82, 0xac, 0x20]),
Some(('€', 3))
);
assert_eq!(try_parse_utf8_char(&[0xe2, 0x88, 0xb0]), Some(('∰', 3)));
assert_eq!(
try_parse_utf8_char(&[0xf0, 0x9f, 0x8c, 0x82]),
Some(('🌂', 4))
);
assert_eq!(
try_parse_utf8_char(&[0xf0, 0x9f, 0x8c, 0x82, 0xef]),
Some(('🌂', 4))
);
assert_eq!(
try_parse_utf8_char(&[0xf0, 0x9f, 0x8c, 0x82, 0x20]),
Some(('🌂', 4))
);
assert_eq!(try_parse_utf8_char(&[]), None);
assert_eq!(try_parse_utf8_char(&[0xef]), None);
assert_eq!(try_parse_utf8_char(&[0xef, 0x20]), None);
assert_eq!(try_parse_utf8_char(&[0xf0, 0xf0]), None);
}
|
