brainfuck interpreter
brainfuck
cli
rust
change tokenizer to return Token structs with line/column info
- updated tokenizer to produce Token values instead of raw bytes,
storing byte value along with source position
- adjusted parse_brackets and VM::run to destructure the new Token type
for comparison and display
- paves the way for nicer error messages in the future
+44
-11
+4
-3
src/evaluator.rs
+4
-3
src/evaluator.rs
···
1
+
use crate::lexer::Token;
1
2
use clap::ValueEnum;
2
3
use std::fmt;
3
4
use std::io::Write;
···
276
277
277
278
pub fn run<R: std::io::BufRead, W: std::io::Write>(
278
279
&mut self,
279
-
tokens: &[u8],
280
+
tokens: &[Token],
280
281
jump_map: &[usize],
281
282
mut reader: R,
282
283
mut writer: W,
···
294
295
"\nTape: {}[{}] ",
295
296
self.data_pointer, self.tape[self.data_pointer]
296
297
);
297
-
print!("\nInst: '{}' @ {}", current as char, self.inst_pointer);
298
+
print!("\nInst: '{}' @ {}", current.byte as char, self.inst_pointer);
298
299
}
299
300
300
-
match current {
301
+
match current.byte {
301
302
b'>' => {
302
303
self.move_right()?;
303
304
}
+35
-5
src/lexer.rs
+35
-5
src/lexer.rs
···
1
-
pub fn tokenizer(input: &str) -> Vec<u8> {
2
-
input
3
-
.bytes()
4
-
.filter(|&b| matches!(b, b'>' | b'<' | b'+' | b'-' | b'.' | b',' | b'[' | b']'))
5
-
.collect()
1
+
#[derive(Copy, Clone, Debug)]
2
+
pub struct Token {
3
+
pub byte: u8,
4
+
pub line: usize,
5
+
pub col: usize,
6
+
}
7
+
8
+
pub fn tokenizer(input: &str) -> Vec<Token> {
9
+
let mut tokens = Vec::new();
10
+
let mut token = Token {
11
+
byte: b'0',
12
+
line: 0,
13
+
col: 0,
14
+
};
15
+
let mut current_line: usize = 1;
16
+
let mut current_col: usize = 1;
17
+
18
+
for b in input.bytes() {
19
+
if b == b'\n' {
20
+
current_line += 1;
21
+
current_col = 1;
22
+
continue;
23
+
}
24
+
25
+
if matches!(b, b'>' | b'<' | b'+' | b'-' | b'.' | b',' | b'[' | b']') {
26
+
token.byte = b;
27
+
token.line = current_line;
28
+
token.col = current_col;
29
+
tokens.push(token);
30
+
}
31
+
32
+
current_col += 1;
33
+
}
34
+
35
+
tokens
6
36
}
+5
-3
src/parser.rs
+5
-3
src/parser.rs
···
1
+
use crate::lexer::Token;
2
+
// use crate::lexer::tokenizer;
1
3
use std::fmt;
2
4
3
5
#[derive(Debug)]
···
21
23
22
24
impl std::error::Error for SyntaxError {}
23
25
24
-
pub fn parse_brackets(tokens: &[u8]) -> Result<Vec<usize>, SyntaxError> {
26
+
pub fn parse_brackets(tokens: &[Token]) -> Result<Vec<usize>, SyntaxError> {
25
27
let mut jump_map = vec![0; tokens.len()];
26
28
let mut balance = Vec::new();
27
29
28
30
for (pos, &e) in tokens.iter().enumerate() {
29
-
if e == b'[' {
31
+
if e.byte == b'[' {
30
32
balance.push(pos);
31
-
} else if e == b']' {
33
+
} else if e.byte == b']' {
32
34
match balance.pop() {
33
35
Some(pop) => {
34
36
jump_map[pos] = pop;