oxc_data_structures 0.155.0

A collection of JavaScript tools written in Rust.
Documentation 
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

//! Rope

pub use ropey::Rope;

/// Get UTF16 line and column from UTF8 offset and source text.
#[expect(clippy::cast_possible_truncation)]
pub fn get_line_column(rope: &Rope, offset: u32, source_text: &str) -> (u32, u32) {
    let offset = offset as usize;
    // Get line number and byte offset of start of line
    let line_index = rope.byte_to_line(offset);
    let line_offset = rope.line_to_byte(line_index);
    // Get column number
    let column_index = source_text[line_offset..offset].encode_utf16().count();
    (line_index as u32, column_index as u32)
}

/// Get UTF8 offset from UTF16 line and column
#[expect(clippy::cast_possible_truncation)]
pub fn get_offset_from_line_and_column(rope: &Rope, line: u32, column: u32) -> u32 {
    let line = line as usize;
    let column = column as usize;
    let line_offset = rope.line_to_byte(line);

    let line_text = rope.line(line);
    let mut utf16_count = 0;
    let mut byte_count = 0;
    for ch in line_text.chars() {
        utf16_count += ch.len_utf16();
        // If adding this character would exceed the target column, return current byte offset
        if utf16_count > column {
            break;
        }
        byte_count += ch.len_utf8();
    }
    // If column equals the line length, return end-of-line byte offset
    (line_offset + byte_count) as u32
}

#[cfg(test)]
mod test {
    use ropey::Rope;

    fn test_line_column(offset: u32, source_text: &str) -> (u32, u32) {
        let rope = Rope::from_str(source_text);
        super::get_line_column(&rope, offset, source_text)
    }

    fn test_offset(line: u32, column: u32, source_text: &str) -> u32 {
        let rope = Rope::from_str(source_text);
        super::get_offset_from_line_and_column(&rope, line, column)
    }

    #[test]
    fn empty_file() {
        assert_eq!(test_line_column(0, ""), (0, 0));
        assert_eq!(test_offset(0, 0, ""), 0);
    }

    #[test]
    fn first_line_start() {
        assert_eq!(test_line_column(0, "foo\nbar\n"), (0, 0));
        assert_eq!(test_offset(0, 0, "foo\nbar\n"), 0);
    }

    #[test]
    fn first_line_middle() {
        assert_eq!(test_line_column(5, "blahblahblah\noops\n"), (0, 5));
        assert_eq!(test_offset(0, 5, "blahblahblah\noops\n"), 5);
    }

    #[test]
    fn later_line_start() {
        assert_eq!(test_line_column(8, "foo\nbar\nblahblahblah"), (2, 0));
        assert_eq!(test_offset(2, 0, "foo\nbar\nblahblahblah"), 8);
    }

    #[test]
    fn later_line_middle() {
        assert_eq!(test_line_column(12, "foo\nbar\nblahblahblah"), (2, 4));
        assert_eq!(test_offset(2, 4, "foo\nbar\nblahblahblah"), 12);
    }

    #[test]
    fn after_2_byte_unicode() {
        assert_eq!("£".len(), 2);
        assert_eq!(utf16_len("£"), 1);
        assert_eq!(test_line_column(4, "£abc"), (0, 3));
        assert_eq!(test_offset(0, 3, "£abc"), 4);
    }

    #[test]
    fn after_3_byte_unicode() {
        assert_eq!("अ".len(), 3);
        assert_eq!(utf16_len("अ"), 1);
        assert_eq!(test_line_column(5, "अabc"), (0, 3));
        assert_eq!(test_offset(0, 3, "अabc"), 5);
    }

    #[test]
    fn after_4_byte_unicode() {
        assert_eq!("🍄".len(), 4);
        assert_eq!(utf16_len("🍄"), 2);
        assert_eq!(test_line_column(6, "🍄abc"), (0, 4));
        assert_eq!(test_offset(0, 4, "🍄abc"), 6);
    }

    #[test]
    fn after_2_byte_unicode_on_previous_line() {
        assert_eq!("£".len(), 2);
        assert_eq!(utf16_len("£"), 1);
        assert_eq!(test_line_column(4, "£\nabc"), (1, 1));
        assert_eq!(test_offset(1, 1, "£\nabc"), 4);
    }

    #[test]
    fn after_3_byte_unicode_on_previous_line() {
        assert_eq!("अ".len(), 3);
        assert_eq!(utf16_len("अ"), 1);
        assert_eq!(test_line_column(5, "अ\nabc"), (1, 1));
        assert_eq!(test_offset(1, 1, "अ\nabc"), 5);
    }

    #[test]
    fn after_4_byte_unicode_on_previous_line() {
        assert_eq!("🍄".len(), 4);
        assert_eq!(utf16_len("🍄"), 2);
        assert_eq!(test_line_column(6, "🍄\nabc"), (1, 1));
        assert_eq!(test_offset(1, 1, "🍄\nabc"), 6);
    }

    #[cfg(test)]
    fn utf16_len(s: &str) -> usize {
        s.encode_utf16().count()
    }
}