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
|
//! `LineIndex` maps flat `TextSize` offsets into `(Line, Column)`
//! representation.
use std::iter;
use rustc_hash::FxHashMap;
use stdx::partition_point;
use syntax::{TextRange, TextSize};
#[derive(Clone, Debug, PartialEq, Eq)]
pub struct LineIndex {
/// Offset the the beginning of each line, zero-based
pub(crate) newlines: Vec<TextSize>,
/// List of non-ASCII characters on each line
pub(crate) utf16_lines: FxHashMap<u32, Vec<Utf16Char>>,
}
#[derive(Clone, Copy, Debug, PartialEq, Eq, Hash)]
pub struct LineCol {
/// Zero-based
pub line: u32,
/// Zero-based
pub col_utf16: u32,
}
#[derive(Clone, Debug, Hash, PartialEq, Eq)]
pub(crate) struct Utf16Char {
/// Start offset of a character inside a line, zero-based
pub(crate) start: TextSize,
/// End offset of a character inside a line, zero-based
pub(crate) end: TextSize,
}
impl Utf16Char {
/// Returns the length in 8-bit UTF-8 code units.
fn len(&self) -> TextSize {
self.end - self.start
}
/// Returns the length in 16-bit UTF-16 code units.
fn len_utf16(&self) -> usize {
if self.len() == TextSize::from(4) {
2
} else {
1
}
}
}
impl LineIndex {
pub fn new(text: &str) -> LineIndex {
let mut utf16_lines = FxHashMap::default();
let mut utf16_chars = Vec::new();
let mut newlines = vec![0.into()];
let mut curr_row = 0.into();
let mut curr_col = 0.into();
let mut line = 0;
for c in text.chars() {
let c_len = TextSize::of(c);
curr_row += c_len;
if c == '\n' {
newlines.push(curr_row);
// Save any utf-16 characters seen in the previous line
if !utf16_chars.is_empty() {
utf16_lines.insert(line, utf16_chars);
utf16_chars = Vec::new();
}
// Prepare for processing the next line
curr_col = 0.into();
line += 1;
continue;
}
if !c.is_ascii() {
utf16_chars.push(Utf16Char { start: curr_col, end: curr_col + c_len });
}
curr_col += c_len;
}
// Save any utf-16 characters seen in the last line
if !utf16_chars.is_empty() {
utf16_lines.insert(line, utf16_chars);
}
LineIndex { newlines, utf16_lines }
}
pub fn line_col(&self, offset: TextSize) -> LineCol {
let line = partition_point(&self.newlines, |&it| it <= offset) - 1;
let line_start_offset = self.newlines[line];
let col = offset - line_start_offset;
LineCol { line: line as u32, col_utf16: self.utf8_to_utf16_col(line as u32, col) as u32 }
}
pub fn offset(&self, line_col: LineCol) -> TextSize {
//FIXME: return Result
let col = self.utf16_to_utf8_col(line_col.line, line_col.col_utf16);
self.newlines[line_col.line as usize] + col
}
pub fn lines(&self, range: TextRange) -> impl Iterator<Item = TextRange> + '_ {
let lo = partition_point(&self.newlines, |&it| it < range.start());
let hi = partition_point(&self.newlines, |&it| it <= range.end());
let all = iter::once(range.start())
.chain(self.newlines[lo..hi].iter().copied())
.chain(iter::once(range.end()));
all.clone()
.zip(all.skip(1))
.map(|(lo, hi)| TextRange::new(lo, hi))
.filter(|it| !it.is_empty())
}
fn utf8_to_utf16_col(&self, line: u32, col: TextSize) -> usize {
let mut res: usize = col.into();
if let Some(utf16_chars) = self.utf16_lines.get(&line) {
for c in utf16_chars {
if c.end <= col {
res -= usize::from(c.len()) - c.len_utf16();
} else {
// From here on, all utf16 characters come *after* the character we are mapping,
// so we don't need to take them into account
break;
}
}
}
res
}
fn utf16_to_utf8_col(&self, line: u32, mut col: u32) -> TextSize {
if let Some(utf16_chars) = self.utf16_lines.get(&line) {
for c in utf16_chars {
if col > u32::from(c.start) {
col += u32::from(c.len()) - c.len_utf16() as u32;
} else {
// From here on, all utf16 characters come *after* the character we are mapping,
// so we don't need to take them into account
break;
}
}
}
col.into()
}
}
#[cfg(test)]
mod tests;
|
