boa_parser 0.21.1

ECMAScript parser for the Boa JavaScript engine.
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

//! Boa's lexing for ECMAScript comments.

use crate::lexer::{Cursor, Error, Token, TokenKind, Tokenizer};
use crate::source::ReadChar;
use boa_ast::PositionGroup;
use boa_interner::Interner;

/// Lexes a single line comment.
///
/// Assumes that the initial '//' is already consumed.
///
/// More information:
///  - [ECMAScript reference][spec]
///  - [MDN documentation][mdn]
///
/// [spec]: https://tc39.es/ecma262/#sec-comments
/// [mdn]: https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Lexical_grammar
pub(super) struct SingleLineComment;

impl<R> Tokenizer<R> for SingleLineComment {
    fn lex(
        &mut self,
        cursor: &mut Cursor<R>,
        start_pos: PositionGroup,
        _interner: &mut Interner,
    ) -> Result<Token, Error>
    where
        R: ReadChar,
    {
        // Skip either to the end of the line or to the end of the input
        while let Some(ch) = cursor.peek_char()? {
            let tried_ch = char::try_from(ch);
            match tried_ch {
                Ok(c) if c == '\r' || c == '\n' || c == '\u{2028}' || c == '\u{2029}' => break,
                _ => {}
            }
            cursor.next_char().expect("Comment character vanished");
        }
        Ok(Token::new_by_position_group(
            TokenKind::Comment,
            start_pos,
            cursor.pos_group(),
        ))
    }
}

/// Lexes a block (multi-line) comment.
///
/// Assumes that the initial '/*' is already consumed.
///
/// More information:
///  - [ECMAScript reference][spec]
///  - [MDN documentation][mdn]
///
/// [spec]: https://tc39.es/ecma262/#sec-comments
/// [mdn]: https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Lexical_grammar
pub(super) struct MultiLineComment;

impl<R> Tokenizer<R> for MultiLineComment {
    fn lex(
        &mut self,
        cursor: &mut Cursor<R>,
        start_pos: PositionGroup,
        _interner: &mut Interner,
    ) -> Result<Token, Error>
    where
        R: ReadChar,
    {
        let mut new_line = false;
        while let Some(ch) = cursor.next_char()? {
            let tried_ch = char::try_from(ch);
            match tried_ch {
                Ok(c) if c == '*' && cursor.next_if(0x2F /* / */)? => {
                    return Ok(Token::new_by_position_group(
                        if new_line {
                            TokenKind::LineTerminator
                        } else {
                            TokenKind::Comment
                        },
                        start_pos,
                        cursor.pos_group(),
                    ));
                }
                Ok(c) if c == '\r' || c == '\n' || c == '\u{2028}' || c == '\u{2029}' => {
                    new_line = true;
                }
                _ => {}
            }
        }

        Err(Error::syntax(
            "unterminated multiline comment",
            cursor.pos(),
        ))
    }
}

/// Lexes a first line Hashbang comment
///
/// More information:
///  - [ECMAScript reference][spec]
///
/// [spec]: https://tc39.es/ecma262/#sec-ecmascript-language-lexical-grammar
pub(super) struct HashbangComment;

impl<R> Tokenizer<R> for HashbangComment {
    fn lex(
        &mut self,
        cursor: &mut Cursor<R>,
        start_pos: PositionGroup,
        _interner: &mut Interner,
    ) -> Result<Token, Error>
    where
        R: ReadChar,
    {
        while let Some(ch) = cursor.next_char()? {
            let tried_ch = char::try_from(ch);
            match tried_ch {
                Ok(c) if c == '\r' || c == '\n' || c == '\u{2028}' || c == '\u{2029}' => break,
                _ => {}
            }
        }

        Ok(Token::new_by_position_group(
            TokenKind::Comment,
            start_pos,
            cursor.pos_group(),
        ))
    }
}