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
/*!
A simple character‑based lexer that turns source text into a stream
of `Token`s, handling identifiers, numbers, operators, and whitespace.
*/
use crate::token;
/// The lexer to convert source code into tokens representing the source code.
#[derive(Debug)]
pub struct Lexer<'a> {
/// the input source code to tokenize
input: &'a str,
/// current position in input (points to current char)
position: usize,
/// current reading position in input (after current char)
read_position: usize,
/// current char under examination
ch: Option<char>,
}
impl<'a> Lexer<'a> {
/// Create a new lexer over the given input string.
///
/// This will initialize the internal state and read the first character,
/// so the lexer is ready to produce tokens via `next_token()`.
pub fn new(input: &'a str) -> Self {
let mut lexer = Self {
input,
position: 0,
read_position: 0,
ch: None,
};
// put the lexer in an initial working state referencing the first
// character
lexer.read_char();
lexer
}
/// Update the lexer state to reflect the next character in the input, if
/// any, and advance the position in the input.
fn read_char(&mut self) {
// check if we have reached end of the input
if self.read_position >= self.input.len() {
self.ch = None
} else {
let remainder = &self.input[self.read_position..];
if let Some((_, c)) = remainder.char_indices().next() {
self.ch = Some(c);
self.position = self.read_position;
// advance the read position to be a character ahead of the
// current character position
self.read_position += c.len_utf8();
return;
}
}
// reached EOF
self.ch = None;
self.position = self.read_position;
}
/// Determine and return the next token in the input from the current
/// character position.
pub fn next_token(&mut self) -> token::Token {
// consume character(s) until no whitespace
while matches!(self.ch, Some(c) if c.is_whitespace()) {
self.read_char();
}
let token = match self.ch {
// Single character tokens
Some('+') => token::Token::Plus,
Some('-') => token::Token::Minus,
Some('/') => token::Token::Slash,
Some('*') => token::Token::Asterisk,
Some('<') => token::Token::Lt,
Some('>') => token::Token::Gt,
Some(';') => token::Token::Semicolon,
Some('(') => token::Token::LParen,
Some(')') => token::Token::RParen,
Some(',') => token::Token::Comma,
Some('{') => token::Token::LBrace,
Some('}') => token::Token::RBrace,
Some('[') => token::Token::LBracket,
Some(']') => token::Token::RBracket,
Some(':') => token::Token::Colon,
Some('"') => {
let str = self.read_string();
return token::Token::String(str);
}
// Multi-character tokens (e.g., identifier, integer, etc.)
Some(c) if c.is_ascii_alphabetic() => {
let ident = self.read_indentifier();
return token::lookup_ident(&ident);
}
Some(c) if c.is_ascii_digit() => {
let literal = self.read_number();
return token::Token::Int(literal);
}
Some('=') => {
if self.peek_char() == Some('=') {
self.read_char();
self.read_char();
return token::Token::Eq;
}
self.read_char();
return token::Token::Assign;
}
Some('!') => {
if self.peek_char() == Some('=') {
self.read_char();
self.read_char();
return token::Token::NotEq;
} else {
self.read_char();
return token::Token::Bang;
}
}
// Unknown single character
Some(_) => token::Token::Illegal,
// Reached EOF
None => token::Token::Eof,
};
// advance past the consumed character
self.read_char();
token
}
/// Reads in an identifier and advances the lexer's position until it
/// encounters a non-letter character
fn read_indentifier(&mut self) -> String {
let start = self.position;
// identifiers can be alphanumeric separated by underscores
while matches!(self.ch, Some(c) if c.is_ascii_alphanumeric() || c == '_') {
self.read_char();
}
self.input[start..self.position].to_string()
}
/// Reads in a number and advances the lexer's position until it encounters
/// a non-numeric character. Only supports integer values.
fn read_number(&mut self) -> i32 {
let start = self.position;
while matches!(self.ch, Some(c) if c.is_ascii_digit()) {
self.read_char();
}
self.input[start..self.position]
.parse()
.expect("Invalid number encountered")
}
/// Read a string value from the opening quotation character.
fn read_string(&mut self) -> String {
// Skip opening quotation
self.read_char();
let position = self.position;
while let Some(ch) = self.ch {
if ch == '"' {
break;
}
self.read_char();
}
let str = self.input[position..self.position].to_string();
// Move past closing quotation
self.read_char();
str
}
/// Peeks the next character from the current position of the lexer.
fn peek_char(&self) -> Option<char> {
self.input[self.read_position..].chars().next()
}
}
#[cfg(test)]
mod tests {
use super::*;
/// Verify that the lexer produces the expected token stream from its
/// input.
fn verify_expected_next_token(expected: &[token::Token], lexer: &mut Lexer) {
for (i, expected_tk) in expected.iter().enumerate() {
let token: token::Token = lexer.next_token();
assert_eq!(
token,
expected_tk.clone(),
"expected[{}] - wrong token. expected={:?}, actual={:?}",
i,
expected_tk,
token
);
}
}
#[test]
fn test_unichar_next_token() {
let input = "=+(){},;[]";
let mut l = Lexer::new(input);
let expected: Vec<token::Token> = vec![
token::Token::Assign,
token::Token::Plus,
token::Token::LParen,
token::Token::RParen,
token::Token::LBrace,
token::Token::RBrace,
token::Token::Comma,
token::Token::Semicolon,
token::Token::LBracket,
token::Token::RBracket,
token::Token::Eof,
];
verify_expected_next_token(&expected, &mut l);
}
#[test]
fn mixed_chars() {
let input = r#"let five = 5;
let ten = 10;
let add = fn(x, y) {
x + y;
};
let result = add(five, ten);
!-/*5;
5 < 10 > 5;
if (5 < 10) {
return true;
} else {
return false;
}
10 == 10;
10 != 9;
"foobar"
"foo bar"
[1, 2];
{"foo": "bar"}"#;
let mut l = Lexer::new(input);
let expected: Vec<token::Token> = vec![
token::Token::Let,
token::Token::Ident("five".to_string()),
token::Token::Assign,
token::Token::Int(5),
token::Token::Semicolon,
token::Token::Let,
token::Token::Ident("ten".to_string()),
token::Token::Assign,
token::Token::Int(10),
token::Token::Semicolon,
token::Token::Let,
token::Token::Ident("add".to_string()),
token::Token::Assign,
token::Token::Function,
token::Token::LParen,
token::Token::Ident("x".to_string()),
token::Token::Comma,
token::Token::Ident("y".to_string()),
token::Token::RParen,
token::Token::LBrace,
token::Token::Ident("x".to_string()),
token::Token::Plus,
token::Token::Ident("y".to_string()),
token::Token::Semicolon,
token::Token::RBrace,
token::Token::Semicolon,
token::Token::Let,
token::Token::Ident("result".to_string()),
token::Token::Assign,
token::Token::Ident("add".to_string()),
token::Token::LParen,
token::Token::Ident("five".to_string()),
token::Token::Comma,
token::Token::Ident("ten".to_string()),
token::Token::RParen,
token::Token::Semicolon,
token::Token::Bang,
token::Token::Minus,
token::Token::Slash,
token::Token::Asterisk,
token::Token::Int(5),
token::Token::Semicolon,
token::Token::Int(5),
token::Token::Lt,
token::Token::Int(10),
token::Token::Gt,
token::Token::Int(5),
token::Token::Semicolon,
token::Token::If,
token::Token::LParen,
token::Token::Int(5),
token::Token::Lt,
token::Token::Int(10),
token::Token::RParen,
token::Token::LBrace,
token::Token::Return,
token::Token::True,
token::Token::Semicolon,
token::Token::RBrace,
token::Token::Else,
token::Token::LBrace,
token::Token::Return,
token::Token::False,
token::Token::Semicolon,
token::Token::RBrace,
token::Token::Int(10),
token::Token::Eq,
token::Token::Int(10),
token::Token::Semicolon,
token::Token::Int(10),
token::Token::NotEq,
token::Token::Int(9),
token::Token::Semicolon,
token::Token::String("foobar".to_string()),
token::Token::String("foo bar".to_string()),
token::Token::LBracket,
token::Token::Int(1),
token::Token::Comma,
token::Token::Int(2),
token::Token::RBracket,
token::Token::Semicolon,
token::Token::LBrace,
token::Token::String("foo".to_string()),
token::Token::Colon,
token::Token::String("bar".to_string()),
token::Token::RBrace,
token::Token::Eof,
];
verify_expected_next_token(&expected, &mut l);
}
}