aboutsummaryrefslogtreecommitdiff
path: root/src/assembler.rs
blob: 56e278358efd01e8ce254064f35ec15d5eb9d437 (plain)
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
use crate::instructions::Instruction;
use std::collections::HashMap;

fn tokenize(line: &str) -> Vec<String> {
    line.split([' ', ',', '\t'])
        .filter(|s| !s.is_empty())
        .map(|s| s.to_lowercase())
        .collect()
}

// Returns corrensponding u8 value of the register
fn parse_reg(s: &str) -> u8 {
    match s {
        "a" => 0,
        "b" => 1,
        "c" => 2,
        "d" => 3,
        _ => panic!("Unknown register {}", s),
    }
}

fn is_reg(s: &str) -> bool {
    matches!(s, "a" | "b" | "c" | "d")
}

fn instr_size(tokens: &[String]) -> u16 {
    match tokens[0].as_str() {
        "mov" | "add" | "sub" | "jmp" | "jz" | "jnz" | "cmp" | "mul" | "div" | "call" => 3,
        "sys" => 2,
        "hlt" | "ret" => 1,
        _ => panic!("Unknown instruction {}", tokens[0]),
    }
}

fn first_pass(source: &str) -> HashMap<String, u16> {
    let mut symbols = HashMap::new();
    let mut addr: u16 = 0;

    for line in source.lines() {
        let line = line.trim();

        // Ignoring comments and empty lines
        if line.is_empty() || line.starts_with(";") {
            continue;
        }

        // Labels (ends with ":")
        if line.ends_with(":") {
            let label = line.trim_end_matches(":").to_string();
            symbols.insert(label, addr);
            continue;
        }

        let tokens = tokenize(line);
        addr += instr_size(&tokens);
    }

    symbols
}

pub fn assembler(source: &str) -> Vec<u8> {
    let symbols = first_pass(source);
    let mut bytes = Vec::new();

    for (line_no, line) in source.lines().enumerate() {
        let line = line.trim();

        // Comments in assembly start with ";"
        if line.is_empty() || line.starts_with(';') || line.ends_with(":") {
            continue;
        }

        let tokens = tokenize(line);

        match tokens[0].as_str() {
            "mov" => {
                // mov reg, imm
                let r1 = parse_reg(&tokens[1]);
                if is_reg(&tokens[2]) {
                    let r2 = parse_reg(&tokens[2]);
                    bytes.push(Instruction::MOV_RR as u8);
                    bytes.push(r1);
                    bytes.push(r2);
                } else {
                    let imm: u8 = tokens[2].parse().unwrap();
                    bytes.push(Instruction::MOV_RI as u8);
                    bytes.push(r1);
                    bytes.push(imm);
                }
            }

            "add" => {
                // add a, b
                let r1 = parse_reg(&tokens[1]);

                if is_reg(&tokens[2]) {
                    let r2 = parse_reg(&tokens[2]);
                    bytes.push(Instruction::ADD_RR as u8);
                    bytes.push(r1);
                    bytes.push(r2);
                } else {
                    let imm: u8 = tokens[2].parse().unwrap();
                    bytes.push(Instruction::ADD_RI as u8);
                    bytes.push(r1);
                    bytes.push(imm);
                }
            }

            "sub" => {
                // sub a, b
                let r1 = parse_reg(&tokens[1]);
                if is_reg(&tokens[2]) {
                    let r2 = parse_reg(&tokens[2]);
                    bytes.push(Instruction::SUB_RR as u8);
                    bytes.push(r1);
                    bytes.push(r2);
                } else {
                    let imm: u8 = tokens[2].parse().unwrap();
                    bytes.push(Instruction::SUB_RI as u8);
                    bytes.push(r1);
                    bytes.push(imm);
                }
            }

            "jmp" | "jz" | "jnz" => {
                let opcode = match tokens[0].as_str() {
                    "jmp" => Instruction::JMP,
                    "jz" => Instruction::JZ,
                    "jnz" => Instruction::JNZ,
                    _ => unreachable!(),
                };

                let label = &tokens[1];
                let addr = *symbols.get(label).expect("Uknown label");

                bytes.push(opcode as u8);
                bytes.push((addr & 0xFF) as u8); // low
                bytes.push((addr >> 8) as u8); // high
            }

            "cmp" => {
                let r1 = parse_reg(&tokens[1]);
                if tokens[2].chars().all(|c| c.is_ascii_digit()) {
                    let imm: u8 = tokens[2].parse().unwrap();
                    bytes.push(Instruction::CMP_RI as u8);
                    bytes.push(r1);
                    bytes.push(imm);
                } else {
                    let r2 = parse_reg(&tokens[2]);
                    bytes.push(Instruction::CMP_RR as u8);
                    bytes.push(r1);
                    bytes.push(r2);
                }
            }

            "mul" => {
                let r1 = parse_reg(&tokens[1]);
                let r2 = parse_reg(&tokens[2]);

                bytes.push(Instruction::MUL as u8);
                bytes.push(r1);
                bytes.push(r2);
            }

            "div" => {
                let r1 = parse_reg(&tokens[1]);
                let r2 = parse_reg(&tokens[2]);

                bytes.push(Instruction::DIV as u8);
                bytes.push(r1);
                bytes.push(r2);
            }

            "call" => {
                let addr = *symbols.get(&tokens[1]).expect("Unknown label");

                bytes.push(Instruction::CALL as u8);
                bytes.push((addr & 0xFF) as u8); // low
                bytes.push((addr >> 8) as u8); // high
            }

            "ret" => {
                bytes.push(Instruction::RET as u8);
            }

            "hlt" => {
                bytes.push(Instruction::HLT as u8);
            }

            "sys" => {
                let imm = tokens[1].parse().unwrap();
                bytes.push(Instruction::SYS as u8);
                bytes.push(imm);
            }

            _ => panic!("Line {}: unknown instruction", line_no + 1),
        }
    }

    bytes
}