klex 0.1.2

A simple lexer (tokenizer) generator for 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

// Test lexer with _ token (should be treated as Whitespace)

%%
[a-zA-Z_][a-zA-Z0-9_]* -> Id
[0-9]+ -> Number
\+ -> Plus
\- -> Minus
[ \t]+ -> _
\n -> Newline
%Id [0-9]+ -> IdNumber
%Plus [0-9]+ -> PositiveNumber
%%
#[cfg(test)]
mod tests {
    use super::*;

    #[test]
    fn test_underscore_token_as_whitespace() {
        // Test that _ token doesn't update context (behaves like Whitespace)
        let input = "var 123 +456 -789";
        let mut lexer = Lexer::from_str(input);
        
        // First token: Id
        let token = lexer.next_token().unwrap();
        println!("Token 1: kind={:?}, value='{}'", token.kind, token.text);
        assert_eq!(token.kind, TokenKind::Id);
        assert_eq!(token.text, "var");
        
        // Second token: _ (whitespace, should not update context)
        let token = lexer.next_token().unwrap();
        println!("Token 2: kind={:?}, value='{}'", token.kind, token.text);
        assert_eq!(token.kind, TokenKind::Whitespace);
        assert_eq!(token.text, " ");
        
        // Third token: Should be IdNumber (because _ didn't update context)
        let token = lexer.next_token().unwrap();
        println!("Token 3: kind={:?}, value='{}'", token.kind, token.text);
        assert_eq!(token.kind, TokenKind::IdNumber);
        assert_eq!(token.text, "123");
        
        // Fourth token: _ (whitespace)
        let token = lexer.next_token().unwrap();
        println!("Token 4: kind={:?}, value='{}'", token.kind, token.text);
        assert_eq!(token.kind, TokenKind::Whitespace);
        
        // Fifth token: Plus
        let token = lexer.next_token().unwrap();
        println!("Token 5: kind={:?}, value='{}'", token.kind, token.text);
        assert_eq!(token.kind, TokenKind::Plus);
        assert_eq!(token.text, "+");
        
        // Sixth token: Should be PositiveNumber (because _ didn't update context)
        let token = lexer.next_token().unwrap();
        println!("Token 6: kind={:?}, value='{}'", token.kind, token.text);
        assert_eq!(token.kind, TokenKind::PositiveNumber);
        assert_eq!(token.text, "456");
    }

    #[test]
    fn test_underscore_vs_regular_token() {
        // Compare behavior: _ should not update context, but regular tokens should
        let input = "a 1";
        let mut lexer = Lexer::from_str(input);
        
        // First: Id "a"
        let token1 = lexer.next_token().unwrap();
        assert_eq!(token1.kind, TokenKind::Id);
        
        // Second: _ (whitespace - doesn't update context)
        let token2 = lexer.next_token().unwrap();
        assert_eq!(token2.kind, TokenKind::Whitespace);
        
        // Third: Should be IdNumber because context is still Id (not _)
        let token3 = lexer.next_token().unwrap();
        assert_eq!(token3.kind, TokenKind::IdNumber);
    }

    #[test]
    fn test_multiple_whitespace_tokens() {
        // Test multiple _ tokens in a row
        let input = "x   123";
        let mut lexer = Lexer::from_str(input);
        
        let token1 = lexer.next_token().unwrap();
        assert_eq!(token1.kind, TokenKind::Id);
        assert_eq!(token1.text, "x");
        
        // Multiple spaces should be captured as one _ token
        let token2 = lexer.next_token().unwrap();
        assert_eq!(token2.kind, TokenKind::Whitespace);
        assert_eq!(token2.text, "   ");
        
        // Should still be IdNumber because _ doesn't update context
        let token3 = lexer.next_token().unwrap();
        assert_eq!(token3.kind, TokenKind::IdNumber);
        assert_eq!(token3.text, "123");
    }
}