jsonrs 1.4.0

Json parser
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
136
137
138
139
140
141
142
143
144
145

mod cursor;
pub mod span;

use cursor::Cursor;
use span::FilePosition;
pub use span::Span;

use crate::{JsonConfig, prelude::*};

use crate::Result;

pub mod token;
use token::{Token, TokenKind};

struct Lexer<'a> {
    c: Cursor<'a>,
    conf: JsonConfig,
}

pub fn tokenize(text: &str, conf: JsonConfig) -> Result<Box<[Token]>> {
    Lexer {
        c: Cursor::new(text),
        conf,
    }
    .tokenize()
}

impl Lexer<'_> {
    fn tokenize(&mut self) -> Result<Box<[Token]>> {
        let mut tokens: Vec<Token> = Vec::new();
        while !self.c.is_finished() {
            self.c.step();
            if let Some(t) = self.scan_token()? {
                tokens.push(t);
            }
        }
        Ok(tokens.into_boxed_slice())
    }
    #[allow(clippy::unnecessary_wraps)]
    fn add_token(&self, token_type: TokenKind) -> Result<Option<Token>> {
        Ok(Some(Token::new(token_type, self.c.get_span())))
    }
    fn scan_token(&mut self) -> Result<Option<Token>> {
        let c = self.c.advance();
        match c {
            '{' => self.add_token(TokenKind::LeftBrace),
            '}' => self.add_token(TokenKind::RightBrace),
            '[' => self.add_token(TokenKind::LSquareBracket),
            ']' => self.add_token(TokenKind::RSquareBracket),
            ',' => self.add_token(TokenKind::Comma),
            '.' => self.add_token(TokenKind::Dot),
            '-' => self.add_token(TokenKind::Minus),
            '+' => self.add_token(TokenKind::Plus),
            ':' => self.add_token(TokenKind::Colon),
            '/' => {
                if self.conf.allow_comments {
                    if self.c.match_next('/') {
                        self.comment()
                    } else if self.c.match_next('*') {
                        self.ml_comment()
                    } else {
                        self.error(&format!("Unexpected character '{c}'"))
                    }
                } else {
                    self.error("Comments are not supported")
                }
            }
            '"' => self.string(),
            ' ' | '\n' | '\r' | '\t' => Ok(None), // Ignore whitespace.
            c => {
                if c.is_numeric() {
                    self.number()
                } else if c.is_alphabetic() {
                    self.keyword()
                } else {
                    self.error(&format!("Unexpected character '{c}'"))?;
                    Ok(None)
                }
            }
        }
    }
    #[allow(clippy::unnecessary_wraps)]
    fn comment(&mut self) -> Result<Option<Token>> {
        self.c.advance_while(|c| *c != '\n');
        Ok(None)
    }
    fn ml_comment(&mut self) -> Result<Option<Token>> {
        while self.c.advance() != '*' || self.c.peek() != '/' {
            if self.c.is_finished() {
                self.error("Non terminated comment block.")?;
            }
        }
        self.c.advance(); /* Consume the / */
        Ok(None)
    }
    fn string(&mut self) -> Result<Option<Token>> {
        let mut scaping = false;
        loop {
            let c = self.c.peek();
            if c == '"' && !scaping {
                break;
            }
            scaping = c == '\\';

            self.c.advance();

            if self.c.is_finished() {
                return self.error("Unterminated string");
            }
        }
        self.c.advance();
        self.add_token(TokenKind::String)
    }
    fn number(&mut self) -> Result<Option<Token>> {
        self.c.advance_while(|c| c.is_numeric());
        if self.c.peek() == '.' && self.c.peek_next().is_numeric() {
            self.c.advance();
            self.c.advance_while(|c| c.is_numeric());
        }
        self.add_token(TokenKind::Number)
    }
    fn keyword(&mut self) -> Result<Option<Token>> {
        self.c.advance_while(|c| c.is_alphanumeric());
        let lexem = self.c.current_lexem();
        let token_type = match lexem {
            "true" => TokenKind::True,
            "false" => TokenKind::False,
            "null" => TokenKind::Null,
            _ => return Err(format!("Unknown keyword '{lexem}'").into()),
        };
        self.add_token(token_type)
    }
    fn error(&mut self, msg: &str) -> Result<Option<Token>> {
        let FilePosition {
            start_line,
            start_col,
            ..
        } = self.c.file_pos();
        let msg = format!("[{start_line}:{start_col}] {msg}");
        Err(msg.into())
    }
}

#[cfg(test)]
mod test;