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
#[derive(Debug, Clone, PartialEq)]
pub enum Token {
Number(f64),
Ident(String),
Plus,
Minus,
Mul,
Div,
Pow,
And,
Or,
Shl,
Shr,
Assign,
LParen,
RParen,
Comma,
}
pub struct Lexer;
impl Lexer {
/// # Tokenize Input String
///
/// Converts a raw input string into a vector of tokens for parsing.
///
/// ## Algorithm
/// 1. Scan characters left-to-right
/// 2. Classify each character/token:
/// - Digits and decimal point → Number token
/// - Letters → Identifier token
/// - Operators and delimiters → Corresponding tokens
/// - Whitespace → Skip
/// 3. Return error on unexpected characters
///
/// ## Examples
/// ```
/// use tcal_rs::calculator::lexer::Lexer;
///
/// let tokens = Lexer::tokenize("2 + 3 * sin(x)").unwrap();
/// // Produces: [Number(2), Plus, Number(3), Mul, Ident("sin"), LParen, Ident("x"), RParen]
/// ```
///
/// # Arguments
/// * `input` - The input string to tokenize
///
/// # Returns
/// `Ok(Vec<Token>)` on success, `Err(String)` with error message on failure
pub fn tokenize(input: &str) -> Result<Vec<Token>, String> {
let mut tokens = Vec::new();
let mut chars = input.chars().peekable();
while let Some(&c) = chars.peek() {
match c {
'0'..='9' | '.' => {
let mut num = String::new();
while let Some(&d) = chars.peek() {
if d.is_ascii_digit() || d == '.' || d == '_' {
if d != '_' {
num.push(d);
}
chars.next();
} else {
break;
}
}
tokens.push(Token::Number(num.parse().unwrap()));
}
'a'..='z' | 'A'..='Z' => {
let mut ident = String::new();
while let Some(&d) = chars.peek() {
if d.is_alphanumeric() {
ident.push(d);
chars.next();
} else {
break;
}
}
tokens.push(Token::Ident(ident));
}
'+' => {
tokens.push(Token::Plus);
chars.next();
}
'-' => {
tokens.push(Token::Minus);
chars.next();
}
'*' => {
tokens.push(Token::Mul);
chars.next();
}
'/' => {
tokens.push(Token::Div);
chars.next();
}
'^' => {
tokens.push(Token::Pow);
chars.next();
}
'&' => {
tokens.push(Token::And);
chars.next();
}
'|' => {
tokens.push(Token::Or);
chars.next();
}
'<' => {
chars.next();
if chars.peek() == Some(&'<') {
chars.next();
tokens.push(Token::Shl);
}
}
'>' => {
chars.next();
if chars.peek() == Some(&'>') {
chars.next();
tokens.push(Token::Shr);
}
}
'=' => {
tokens.push(Token::Assign);
chars.next();
}
'(' => {
tokens.push(Token::LParen);
chars.next();
}
')' => {
tokens.push(Token::RParen);
chars.next();
}
',' => {
tokens.push(Token::Comma);
chars.next();
}
' ' => {
chars.next();
}
_ => return Err(format!("Unexpected char: {}", c)),
}
}
Ok(tokens)
}
}