tlisp 0.0.2

Lisp interpreter 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
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159

use std::error::Error;
use std::fmt;

#[derive(Debug, PartialEq, Clone)]
pub enum Token {
  Integer(i64),
  Float(f64),
  String(String),
  Symbol(String),
  Quote,
  LParen,
  RParen,
}

impl fmt::Display for Token {
  fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
    use Token::*;
    f.write_str(
      (match self {
        Integer(n) => format!("{}", n),
        Float(n) => format!("{}", n),
        String(s) => format!("{}", s),
        Symbol(s) => format!("{}", s),
        Quote => format!("'"),
        LParen => format!("("),
        RParen => format!(")"),
      })
      .as_str(),
    )
  }
}

#[derive(Debug)]
pub struct TokenError {
  err: String,
}

impl Error for TokenError {}

impl fmt::Display for TokenError {
  fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
    write!(f, "Tokenization error: {}", self.err)
  }
}

pub fn tokenize(input: &str) -> Result<Vec<Token>, TokenError> {
  let mut tokens = Vec::new();
  let mut chars = input.chars().collect::<Vec<char>>();

  if chars.is_empty() {
    return Ok(tokens);
  }

  while chars.len() > 0 {
    let mut ch = chars.remove(0);
    match ch {
      '(' => tokens.push(Token::LParen),
      ')' => tokens.push(Token::RParen),
      '"' => {
        let mut word = String::new();
        while chars.len() > 0 && chars[0] != '"' {
          word.push(chars.remove(0));
        }

        if chars.len() > 0 && chars[0] == '"' {
          chars.remove(0);
        } else {
          return Err(TokenError {
            err: format!("Unterminated string: {}", word),
          });
        }

        tokens.push(Token::String(word));
      }
      ';' => {
        while chars.len() > 0 && chars[0] != '\n' {
          chars.remove(0);
        }
      }
      '\'' => {
        tokens.push(Token::Quote);
      }
      ' ' | '\n' | '\t' => continue,
      _ => {
        let mut word = String::from(ch);

        while chars.len() > 0 && !ch.is_whitespace() && ch != '(' && ch != ')' {
          let peek = chars[0];
          if peek == '(' || peek == ')' {
            break;
          }

          ch = chars.remove(0);
          word.push(ch);
        }

        let word = String::from(word.trim());

        if !word.is_empty() {
          let token = if let Ok(i) = word.parse::<i64>() {
            Token::Integer(i)
          } else if let Ok(f) = word.parse::<f64>() {
            Token::Float(f)
          } else {
            Token::Symbol(word)
          };

          tokens.push(token);
        }
      }
    }
  }

  Ok(tokens)
}

#[cfg(test)]
mod lexer_tests {
  use super::*;

  #[test]
  fn test_add() {
    let program = "(+ 2 2)";
    let tokens = tokenize(program).unwrap();
    assert_eq!(
      tokens,
      vec![
        Token::LParen,
        Token::Symbol("+".to_string()),
        Token::Integer(2),
        Token::Integer(2),
        Token::RParen,
      ]
    );
  }

  #[test]
  fn test_quotation() {
    let program = "'(1  2 3)";
    let tokens = tokenize(program).unwrap();
    assert_eq!(
      tokens,
      vec![
        Token::Quote,
        Token::LParen,
        Token::Integer(1),
        Token::Integer(2),
        Token::Integer(3),
        Token::RParen,
      ]
    )
  }

  #[test]
  fn test_symbol() {
    let list = tokenize("#t").unwrap();
    assert_eq!(list, vec![Token::Symbol("#t".to_string())])
  }
}