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
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408//! # Lexical Analysis
//!
//! This module handles the lexical analysis phase of the compiler, converting
//! raw source code into a stream of tokens. It uses the `logos` crate for
//! efficient tokenization.
//!
//! ## Supported Tokens
//!
//! The lexer recognizes tokens for the C subset including:
//! - Keywords: `int`, `float`, `if`, `else`, `for`, `return`
//! - Operators: `+`, `-`, `*`, `/`, `=`, `==`, `!=`, `<`, `>`, etc.
//! - Literals: Integer and floating-point numbers
//! - Identifiers: Variable and function names
//! - Punctuation: `(`, `)`, `{`, `}`, `;`, `,`, etc.
//!
//! ## Implementation
//!
//! Uses the `logos` procedural macro to define token patterns and generate
//! the lexer automatically. Handles whitespace, comments, and error recovery.
use crate::error::LexerError;
use logos::Logos;
/// Represents the tokens produced by the lexer.
#[derive(Logos, Debug, PartialEq, Clone)]
#[logos(skip r"[ \t\n\f]+")] // Skip whitespace
#[logos(skip r"//[^\n]*")] // Skip single-line comments
pub enum Token {
/// Integer keyword
#[token("int")]
Int,
/// Float keyword
#[token("float")]
Float,
/// String keyword (for const char*)
#[token("string")]
StringType,
/// If keyword
#[token("if")]
If,
/// Else keyword
#[token("else")]
Else,
/// For keyword
#[token("for")]
For,
/// Return keyword
#[token("return")]
Return,
/// Extern keyword
#[token("extern")]
Extern,
#[regex(r"[a-zA-Z_][a-zA-Z0-9_]*", |lex| lex.slice().to_owned())]
Identifier(String),
/// Float literal
#[regex(r"\d+\.\d+", |lex| lex.slice().parse::<f64>().unwrap())]
FloatLiteral(f64),
/// Integer literal
#[regex(r"\d+", |lex| lex.slice().parse::<i64>().unwrap())]
IntLiteral(i64),
/// String literal
#[regex(r#""([^"\\]|\\.)*""#, |lex| {
// Strip surrounding quotes and unescape common C-style escapes
let s = lex.slice();
let inner = &s[1..s.len()-1];
unescape_c_string(inner)
})]
StringLiteral(String),
/// Include directive: #include <header.h>
#[regex(r"#include\s*<[^>]+>", |lex| {
let s = lex.slice();
let start = s.find('<').map(|i| i+1).unwrap_or(0);
let end = s.find('>').unwrap_or(s.len());
s[start..end].to_string()
})]
Include(String),
/// Less than or equal operator
#[token("<=")]
LessEqual,
/// Greater than or equal operator
#[token(">=")]
GreaterEqual,
/// Equal operator
#[token("==")]
Equal,
/// Not equal operator
#[token("!=")]
NotEqual,
/// Less than operator
#[token("<")]
LessThan,
/// Greater than operator
#[token(">")]
GreaterThan,
/// Assignment operator
#[token("=")]
Assign,
/// Plus operator
#[token("+")]
Plus,
/// Minus operator
#[token("-")]
Minus,
/// Multiply operator
#[token("*")]
Multiply,
/// Divide operator
#[token("/")]
Divide,
/// Semicolon
#[token(";")]
Semicolon,
/// Comma
#[token(",")]
Comma,
/// Left parenthesis
#[token("(")]
LParen,
/// Right parenthesis
#[token(")")]
RParen,
/// Left brace
#[token("{")]
LBrace,
/// Right brace
#[token("}")]
RBrace,
/// Ellipsis for variadic functions
#[token("...")]
Ellipsis,
}
/// Lexes the input source code into a vector of tokens.
///
/// # Arguments
///
/// * `input` - The source code string to tokenize.
///
/// # Returns
///
/// A `Result` containing a vector of tokens or a lexing error.
pub fn lex(input: &str) -> Result<Vec<Token>, LexerError> {
let lexer = Token::lexer(input);
let mut tokens = Vec::new();
for token in lexer {
match token {
Ok(t) => tokens.push(t),
Err(_) => return Err(LexerError),
}
}
Ok(tokens)
}
// Helper: Unescape a C-style string body (no surrounding quotes)
fn unescape_c_string(s: &str) -> String {
let mut out = String::with_capacity(s.len());
let mut chars = s.chars();
while let Some(c) = chars.next() {
if c == '\\' {
match chars.next() {
Some('n') => out.push('\n'),
Some('t') => out.push('\t'),
Some('r') => out.push('\r'),
Some('\'') => out.push('\''),
Some('"') => out.push('"'),
Some('0') => out.push('\0'),
Some('x') => {
// parse up to two hex digits
let hi = chars.next();
let lo = if let Some(_c2) = hi {
chars.next()
} else {
None
};
if let (Some(h), Some(l)) = (hi, lo) {
if let (Some(hv), Some(lv)) = (h.to_digit(16), l.to_digit(16)) {
let val = (hv * 16 + lv) as u8;
out.push(val as char);
} else {
out.push('x');
out.push(h);
out.push(l);
}
} else if let Some(h) = hi {
if let Some(hv) = h.to_digit(16) {
let val = hv as u8;
out.push(val as char);
} else {
out.push('x');
out.push(h);
}
}
}
Some(other) => {
// Unknown escape, keep as-is
out.push(other);
}
None => out.push('\\'),
}
} else {
out.push(c);
}
}
out
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn test_simple_declaration() {
let input = "int x = 5;";
let expected = vec![
Token::Int,
Token::Identifier("x".to_string()),
Token::Assign,
Token::IntLiteral(5),
Token::Semicolon,
];
assert_eq!(lex(input).unwrap(), expected);
}
#[test]
fn test_float_declaration() {
let input = "float y = 3.14;";
let expected = vec![
Token::Float,
Token::Identifier("y".to_string()),
Token::Assign,
Token::FloatLiteral(3.14),
Token::Semicolon,
];
assert_eq!(lex(input).unwrap(), expected);
}
#[test]
fn test_arithmetic_expression() {
let input = "x + y * 2";
let expected = vec![
Token::Identifier("x".to_string()),
Token::Plus,
Token::Identifier("y".to_string()),
Token::Multiply,
Token::IntLiteral(2),
];
assert_eq!(lex(input).unwrap(), expected);
}
#[test]
fn test_comparison() {
let input = "a == b";
let expected = vec![
Token::Identifier("a".to_string()),
Token::Equal,
Token::Identifier("b".to_string()),
];
assert_eq!(lex(input).unwrap(), expected);
}
#[test]
fn test_invalid_input() {
let input = "int x = @;";
assert!(lex(input).is_err());
}
#[test]
fn test_string_literal_unescape() {
let input = r#"int main() { printf("Hello\n"); }"#;
let tokens = lex(input).unwrap();
// find StringLiteral token
assert!(
tokens
.iter()
.any(|t| matches!(t, Token::StringLiteral(s) if s == "Hello\n"))
);
}
#[test]
fn test_function_declaration() {
let input = "int add(int a, int b) { return a + b; }";
let expected = vec![
Token::Int,
Token::Identifier("add".to_string()),
Token::LParen,
Token::Int,
Token::Identifier("a".to_string()),
Token::Comma,
Token::Int,
Token::Identifier("b".to_string()),
Token::RParen,
Token::LBrace,
Token::Return,
Token::Identifier("a".to_string()),
Token::Plus,
Token::Identifier("b".to_string()),
Token::Semicolon,
Token::RBrace,
];
assert_eq!(lex(input).unwrap(), expected);
}
#[test]
fn test_if_statement() {
let input = "if (x > 0) { return x; } else { return 0; }";
let expected = vec![
Token::If,
Token::LParen,
Token::Identifier("x".to_string()),
Token::GreaterThan,
Token::IntLiteral(0),
Token::RParen,
Token::LBrace,
Token::Return,
Token::Identifier("x".to_string()),
Token::Semicolon,
Token::RBrace,
Token::Else,
Token::LBrace,
Token::Return,
Token::IntLiteral(0),
Token::Semicolon,
Token::RBrace,
];
assert_eq!(lex(input).unwrap(), expected);
}
#[test]
fn test_for_loop() {
let input = "for (int i = 0; i < 10; i = i + 1) { x = x + i; }";
let expected = vec![
Token::For,
Token::LParen,
Token::Int,
Token::Identifier("i".to_string()),
Token::Assign,
Token::IntLiteral(0),
Token::Semicolon,
Token::Identifier("i".to_string()),
Token::LessThan,
Token::IntLiteral(10),
Token::Semicolon,
Token::Identifier("i".to_string()),
Token::Assign,
Token::Identifier("i".to_string()),
Token::Plus,
Token::IntLiteral(1),
Token::RParen,
Token::LBrace,
Token::Identifier("x".to_string()),
Token::Assign,
Token::Identifier("x".to_string()),
Token::Plus,
Token::Identifier("i".to_string()),
Token::Semicolon,
Token::RBrace,
];
assert_eq!(lex(input).unwrap(), expected);
}
#[test]
fn test_comments_and_whitespace() {
let input = "int x = 5; // this is a comment\nfloat y;";
let expected = vec![
Token::Int,
Token::Identifier("x".to_string()),
Token::Assign,
Token::IntLiteral(5),
Token::Semicolon,
Token::Float,
Token::Identifier("y".to_string()),
Token::Semicolon,
];
assert_eq!(lex(input).unwrap(), expected);
}
}