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
|
use std::mem::take;
use crate::*;
#[derive(PartialEq)]
enum StringLiteral {
None,
Raw,
NullTerminated,
}
pub struct TokenIterator {
/// The characters that comprise the program souce code.
chars: Vec<char>,
/// The index of the next character to read.
i: usize,
/// The address of the next character to read.
addr: CharAddress,
/// If true, skip over any whitespace characters. If false, stop reading
/// when a whitespace character is encountered.
skip_whitespace: bool,
/// The name of the most recently defined label.
label: String,
/// If not None, each individual character will be tokenised as a ByteLiteral.
parse_string_literal: StringLiteral,
/// The address of the first character of the current token.
start: CharAddress,
/// The address of the final character of the current token.
end: CharAddress,
/// The entire current token.
source: String,
/// The first character of the current token.
prefix: char,
/// The second and remaining characters of the current token.
suffix: String,
}
impl TokenIterator {
/// Create an iterator from a string of program source code.
pub fn from_str(source_code: &str) -> Self {
Self {
chars: source_code.chars().collect(),
i: 0,
addr: CharAddress::zero(),
skip_whitespace: true,
parse_string_literal: StringLiteral::None,
label: String::new(),
start: CharAddress::zero(),
end: CharAddress::zero(),
source: String::new(),
prefix: ' ',
suffix: String::new(),
}
}
/// Append a character to the current token.
fn push(&mut self, c:char) {
self.end = self.addr;
self.source.push(c);
self.suffix.push(c);
self.next(c);
}
/// Move forward to the next source character.
fn next(&mut self, c: char) {
self.addr.column += 1;
self.i += 1;
if c == '\n' {
self.addr.column = 0;
self.addr.line += 1;
}
}
/// Mark the current character as being the first character of a new token.
fn mark_start(&mut self, c:char) {
if c == '"' {
self.parse_string_literal = StringLiteral::NullTerminated;
} else if c == '\'' {
self.parse_string_literal = StringLiteral::Raw;
} else {
self.start=self.addr;
self.end=self.addr;
self.prefix=c;
self.source.push(c);
self.skip_whitespace=false;
}
self.next(c);
}
}
impl Iterator for TokenIterator {
type Item = SyntacticToken;
fn next(&mut self) -> Option<SyntacticToken> {
// Initialise values before reading the next token
let mut is_comment = false;
self.skip_whitespace = true;
// Iterate over source characters until a full token is read
while let Some(c) = self.chars.get(self.i) {
let c = *c;
// Parse individual characters from a string literal
if self.parse_string_literal != StringLiteral::None {
if c == '"' && self.parse_string_literal == StringLiteral::NullTerminated {
self.parse_string_literal = StringLiteral::None;
let token = SyntacticToken {
r#type: SyntacticTokenType::ByteLiteral(0),
source_location: SourceLocation {
source: c.to_string(), start:self.addr, end:self.addr },
error: None,
};
self.next(c);
return Some(token);
} else if c == '\'' && self.parse_string_literal == StringLiteral::Raw {
self.parse_string_literal = StringLiteral::None;
self.next(c);
continue
} else {
self.next(c);
return Some(SyntacticToken {
r#type: SyntacticTokenType::ByteLiteral(c as u8),
source_location: SourceLocation {
source: c.to_string(), start:self.addr, end:self.addr },
error: None,
});
}
}
// Intercept comments
if is_comment {
self.push(c); if c == ')' { break } else { continue }; }
else if self.skip_whitespace && c == '(' {
is_comment = true; self.mark_start(c); continue }
// Allow a semicolon at the end of a token to be handled as a separate token
if self.source.len() > 0 && c == ';' { break }
// Handle the current character
match (is_whitespace(c), self.skip_whitespace) {
(true, true) => self.next(c), // c is the expected leading whitespace
(false, true) => self.mark_start(c), // c is the first character of the token
(false, false) => self.push(c), // c is a character of the token
(true, false) => break, // c is trailing whitespace
}
// Allow literal values to be chained to the end of the previous token
if self.source.len() > 0 && c == ':' { break }
}
// If no source characters were grabbed then we have read through the entire source file
if self.source.len() == 0 { return None; }
// Allow handling macro terminators and symbols of length 1 in the match expression
if self.suffix.len() == 0 { self.prefix = '\0'; }
// Consume the collected characters to be used in the match expression
let full = take(&mut self.source);
let suffix = take(&mut self.suffix);
let mut error = None;
let mut parse_padding_value = |v| {
parse_short(v).or_else(|| {
error = Some(Error::InvalidPaddingValue); Some(0)
}).unwrap()
};
let r#type = match self.prefix {
'(' => { SyntacticTokenType::Comment }
'@' => { SyntacticTokenType::LabelDefinition({self.label=suffix.clone(); suffix}) }
'&' => { SyntacticTokenType::LabelDefinition(format!("{}/{}", self.label, suffix)) }
'$' => { SyntacticTokenType::Padding(parse_padding_value(&suffix)) }
'~' => { SyntacticTokenType::Reference(format!("{}/{}", self.label, suffix)) }
'%' => if let Some(("", sublabel)) = suffix.split_once("~") {
SyntacticTokenType::MacroDefinition(format!("{}/{}", self.label, sublabel))
} else {
SyntacticTokenType::MacroDefinition(suffix)
}
_ => {
if ";" == &full { SyntacticTokenType::MacroDefinitionTerminator }
else if let Some(value) = parse_byte_lit(&full) { SyntacticTokenType::ByteLiteral(value) }
else if let Some(value) = parse_short_lit(&full) { SyntacticTokenType::ShortLiteral(value) }
else if let Some(value) = parse_instruction(&full) { SyntacticTokenType::Instruction(value) }
else { SyntacticTokenType::Reference(full.clone()) }
}
};
Some(SyntacticToken {
r#type,
source_location:SourceLocation::new(full,self.start,self.end),
error,
})
}
}
fn parse_byte_lit(token: &str) -> Option<u8> {
match token.len() { 2 => u8::from_str_radix(token, 16).ok(), _ => None } }
fn parse_short_lit(token: &str) -> Option<u16> {
match token.len() { 4 => u16::from_str_radix(token, 16).ok(), _ => None } }
fn parse_short(token: &str) -> Option<u16> {
match token.len() { 1..=4 => u16::from_str_radix(token, 16).ok(), _ => None } }
fn is_whitespace(c: char) -> bool {
match c { ' '|'\t'|'\n'|'\r'|'['|']'|'(' =>true, _=>false } }
fn parse_instruction(token: &str) -> Option<u8> {
Some(match token {
// Flow control operators
"HLT"=>0x00,"DBG" =>0x20,"NOP" =>0x80, // The remaining op-codes in this line are unclaimed
"JMP"=>0x01,"JSR" =>0x21,"JMP:" =>0x41,"JSR:" =>0x61,"JMPr" =>0x81,"JSRr" =>0xA1,"JMPr:" =>0xC1,"JSRr:" =>0xE1,
"JCN"=>0x02,"JSN" =>0x22,"JCN:" =>0x42,"JSN:" =>0x62,"JCNr" =>0x82,"JSNr" =>0xA2,"JCNr:" =>0xC2,"JSNr:" =>0xE2,
"JKN"=>0x03,"JKN*"=>0x23,"JKN:" =>0x43,"JKN*:"=>0x63,"JKNr" =>0x83,"JKNr*"=>0xA3,"JKNr:" =>0xC3,"JKNr*:"=>0xE3,
// Relational operators
"EQU"=>0x04,"EQU*"=>0x24,"EQU:"=>0x44,"EQU*:"=>0x64,"EQUr"=>0x84,"EQUr*"=>0xA4,"EQUr:"=>0xC4,"EQUr*:"=>0xE4,
"NKQ"=>0x05,"NKQ*"=>0x25,"NKQ:"=>0x45,"NKQ*:"=>0x65,"NKQr"=>0x85,"NKQr*"=>0xA5,"NKQr:"=>0xC5,"NKQr*:"=>0xE5,
"LTH"=>0x06,"LTH*"=>0x26,"LTH:"=>0x46,"LTH*:"=>0x66,"LTHr"=>0x86,"LTHr*"=>0xA6,"LTHr:"=>0xC6,"LTHr*:"=>0xE6,
"GTH"=>0x07,"GTH*"=>0x27,"GTH:"=>0x47,"GTH*:"=>0x67,"GTHr"=>0x87,"GTHr*"=>0xA7,"GTHr:"=>0xC7,"GTHr*:"=>0xE7,
// Memory operators
"LDA"=>0x08,"LDA*"=>0x28,"LDA:"=>0x48,"LDA*:"=>0x68,"LDAr"=>0x88,"LDAr*"=>0xA8,"LDAr:"=>0xC8,"LDAr*:"=>0xE8,
"STA"=>0x09,"STA*"=>0x29,"STA:"=>0x49,"STA*:"=>0x69,"STAr"=>0x89,"STAr*"=>0xA9,"STAr:"=>0xC9,"STAr*:"=>0xE9,
"LKA"=>0x0A,"LKA*"=>0x2A,"LKA:"=>0x4A,"LKA*:"=>0x6A,"LKAr"=>0x8A,"LKAr*"=>0xAA,"LKAr:"=>0xCA,"LKAr*:"=>0xEA,
"SKA"=>0x0B,"SKA*"=>0x2B,"SKA:"=>0x4B,"SKA*:"=>0x6B,"SKAr"=>0x8B,"SKAr*"=>0xAB,"SKAr:"=>0xCB,"SKAr*:"=>0xEB,
// Device operators
"LDD"=>0x0C,"LDD*"=>0x2C,"LDD:"=>0x4C,"LDD*:"=>0x6C,"LDDr"=>0x8C,"LDDr*"=>0xAC,"LDDr:"=>0xCC,"LDDr*:"=>0xEC,
"STD"=>0x0D,"STD*"=>0x2D,"STD:"=>0x4D,"STD*:"=>0x6D,"STDr"=>0x8D,"STDr*"=>0xAD,"STDr:"=>0xCD,"STDr*:"=>0xED,
"SHF"=>0x0E,"SHF*"=>0x2E,"SHF:"=>0x4E,"SHF*:"=>0x6E,"SHFr"=>0x8E,"SHFr*"=>0xAE,"SHFr:"=>0xCE,"SHFr*:"=>0xEE,
"SHC"=>0x0F,"SHC*"=>0x2F,"SHC:"=>0x4F,"SHC*:"=>0x6F,"SHCr"=>0x8F,"SHCr*"=>0xAF,"SHCr:"=>0xCF,"SHCr*:"=>0xEF,
//
"PSH"=>0x10,"PSH*"=>0x30,"PSH:"=>0x50,"PSH*:"=>0x70,"PSHr"=>0x90,"PSHr*"=>0xB0,"PSHr:"=>0xD0,"PSHr*:"=>0xF0,
"PSK"=>0x11,"PSK*"=>0x31,"PSK:"=>0x51,"PSK*:"=>0x71,"PSKr"=>0x91,"PSKr*"=>0xB1,"PSKr:"=>0xD1,"PSKr*:"=>0xF1,
"POP"=>0x12,"POP*"=>0x32,"POP:"=>0x52,"POP*:"=>0x72,"POPr"=>0x92,"POPr*"=>0xB2,"POPr:"=>0xD2,"POPr*:"=>0xF2,
"SPL"=>0x13,"SPL*"=>0x33,"SPL:"=>0x53,"SPL*:"=>0x73,"SPLr"=>0x93,"SPLr*"=>0xB3,"SPLr:"=>0xD3,"SPLr*:"=>0xF3,
// Stack operators
"DUP"=>0x14,"DUP*"=>0x34,"DUP:"=>0x54,"DUP*:"=>0x74,"DUPr"=>0x94,"DUPr*"=>0xB4,"DUPr:"=>0xD4,"DUPr*:"=>0xF4,
"OVR"=>0x15,"OVR*"=>0x35,"OVR:"=>0x55,"OVR*:"=>0x75,"OVRr"=>0x95,"OVRr*"=>0xB5,"OVRr:"=>0xD5,"OVRr*:"=>0xF5,
"SWP"=>0x16,"SWP*"=>0x36,"SWP:"=>0x56,"SWP*:"=>0x76,"SWPr"=>0x96,"SWPr*"=>0xB6,"SWPr:"=>0xD6,"SWPr*:"=>0xF6,
"ROT"=>0x17,"ROT*"=>0x37,"ROT:"=>0x57,"ROT*:"=>0x77,"ROTr"=>0x97,"ROTr*"=>0xB7,"ROTr:"=>0xD7,"ROTr*:"=>0xF7,
// Arithmetic operators
"ADD"=>0x18,"ADD*"=>0x38,"ADD:"=>0x58,"ADD*:"=>0x78,"ADDr"=>0x98,"ADDr*"=>0xB8,"ADDr:"=>0xD8,"ADDr*:"=>0xF8,
"SUB"=>0x19,"SUB*"=>0x39,"SUB:"=>0x59,"SUB*:"=>0x79,"SUBr"=>0x99,"SUBr*"=>0xB9,"SUBr:"=>0xD9,"SUBr*:"=>0xF9,
"INC"=>0x1A,"INC*"=>0x3A,"INC:"=>0x5A,"INC*:"=>0x7A,"INCr"=>0x9A,"INCr*"=>0xBA,"INCr:"=>0xDA,"INCr*:"=>0xFA,
"DEC"=>0x1B,"DEC*"=>0x3B,"DEC:"=>0x5B,"DEC*:"=>0x7B,"DECr"=>0x9B,"DECr*"=>0xBB,"DECr:"=>0xDB,"DECr*:"=>0xFB,
// Logical operators
"AND"=>0x1C,"AND*"=>0x3C,"AND:"=>0x5C,"AND*:"=>0x7C,"ANDr"=>0x9C,"ANDr*"=>0xBC,"ANDr:"=>0xDC,"ANDr*:"=>0xFC,
"NOT"=>0x1D,"NOT*"=>0x3D,"NOT:"=>0x5D,"NOT*:"=>0x7D,"NOTr"=>0x9D,"NOTr*"=>0xBD,"NOTr:"=>0xDD,"NOTr*:"=>0xFD,
"IOR"=>0x1E,"IOR*"=>0x3E,"IOR:"=>0x5E,"IOR*:"=>0x7E,"IORr"=>0x9E,"IORr*"=>0xBE,"IORr:"=>0xDE,"IORr*:"=>0xFE,
"XOR"=>0x1F,"XOR*"=>0x3F,"XOR:"=>0x5F,"XOR*:"=>0x7F,"XORr"=>0x9F,"XORr*"=>0xBF,"XORr:"=>0xDF,"XORr*:"=>0xFF,
_ => return None,
})
}
|
