diff options
Diffstat (limited to 'src/tokenizer.rs')
| -rw-r--r-- | src/tokenizer.rs | 235 |
1 files changed, 0 insertions, 235 deletions
diff --git a/src/tokenizer.rs b/src/tokenizer.rs deleted file mode 100644 index 02bf490..0000000 --- a/src/tokenizer.rs +++ /dev/null @@ -1,235 +0,0 @@ -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 { - // Control operators - "HLT"=>0x00,"NOP" =>0x20,"DB1" =>0x40,"DB2" =>0x60,"DB3" =>0x80,"DB4" =>0xA0,"DB5" =>0xC0,"DB6" =>0xE0, - "JMP"=>0x01,"JMS" =>0x21,"JMP:"=>0x41,"JMS:" =>0x61,"JMPr"=>0x81,"JMSr" =>0xA1,"JMPr:"=>0xC1,"JMSr:" =>0xE1, - "JCN"=>0x02,"JCS" =>0x22,"JCN:"=>0x42,"JCS:" =>0x62,"JCNr"=>0x82,"JCSr" =>0xA2,"JCNr:"=>0xC2,"JCSr:" =>0xE2, - "JCK"=>0x03,"JCK*"=>0x23,"JCK:"=>0x43,"JCK*:"=>0x63,"JCKr"=>0x83,"JCKr*"=>0xA3,"JCKr:"=>0xC3,"JCKr*:"=>0xE3, - "LDA"=>0x04,"LDA*"=>0x24,"LDA:"=>0x44,"LDA*:"=>0x64,"LDAr"=>0x84,"LDAr*"=>0xA4,"LDAr:"=>0xC4,"LDAr*:"=>0xE4, - "STA"=>0x05,"STA*"=>0x25,"STA:"=>0x45,"STA*:"=>0x65,"STAr"=>0x85,"STAr*"=>0xA5,"STAr:"=>0xC5,"STAr*:"=>0xE5, - "LDD"=>0x06,"LDD*"=>0x26,"LDD:"=>0x46,"LDD*:"=>0x66,"LDDr"=>0x86,"LDDr*"=>0xA6,"LDDr:"=>0xC6,"LDDr*:"=>0xE6, - "STD"=>0x07,"STD*"=>0x27,"STD:"=>0x47,"STD*:"=>0x67,"STDr"=>0x87,"STDr*"=>0xA7,"STDr:"=>0xC7,"STDr*:"=>0xE7, - // Stack operators - "PSH"=>0x08,"PSH*"=>0x28,"PSH:"=>0x48,"PSH*:"=>0x68,"PSHr"=>0x88,"PSHr*"=>0xA8,"PSHr:"=>0xC8,"PSHr*:"=>0xE8, - "POP"=>0x09,"POP*"=>0x29,"POP:"=>0x49,"POP*:"=>0x69,"POPr"=>0x89,"POPr*"=>0xA9,"POPr:"=>0xC9,"POPr*:"=>0xE9, - "CPY"=>0x0A,"CPY*"=>0x2A,"CPY:"=>0x4A,"CPY*:"=>0x6A,"CPYr"=>0x8A,"CPYr*"=>0xAA,"CPYr:"=>0xCA,"CPYr*:"=>0xEA, - "SPL"=>0x0B,"SPL*"=>0x2B,"SPL:"=>0x4B,"SPL*:"=>0x6B,"SPLr"=>0x8B,"SPLr*"=>0xAB,"SPLr:"=>0xCB,"SPLr*:"=>0xEB, - "DUP"=>0x0C,"DUP*"=>0x2C,"DUP:"=>0x4C,"DUP*:"=>0x6C,"DUPr"=>0x8C,"DUPr*"=>0xAC,"DUPr:"=>0xCC,"DUPr*:"=>0xEC, - "OVR"=>0x0D,"OVR*"=>0x2D,"OVR:"=>0x4D,"OVR*:"=>0x6D,"OVRr"=>0x8D,"OVRr*"=>0xAD,"OVRr:"=>0xCD,"OVRr*:"=>0xED, - "SWP"=>0x0E,"SWP*"=>0x2E,"SWP:"=>0x4E,"SWP*:"=>0x6E,"SWPr"=>0x8E,"SWPr*"=>0xAE,"SWPr:"=>0xCE,"SWPr*:"=>0xEE, - "ROT"=>0x0F,"ROT*"=>0x2F,"ROT:"=>0x4F,"ROT*:"=>0x6F,"ROTr"=>0x8F,"ROTr*"=>0xAF,"ROTr:"=>0xCF,"ROTr*:"=>0xEF, - // Numeric operators - "ADD"=>0x10,"ADD*"=>0x30,"ADD:"=>0x50,"ADD*:"=>0x70,"ADDr"=>0x90,"ADDr*"=>0xB0,"ADDr:"=>0xD0,"ADDr*:"=>0xF0, - "SUB"=>0x11,"SUB*"=>0x31,"SUB:"=>0x51,"SUB*:"=>0x71,"SUBr"=>0x91,"SUBr*"=>0xB1,"SUBr:"=>0xD1,"SUBr*:"=>0xF1, - "INC"=>0x12,"INC*"=>0x32,"INC:"=>0x52,"INC*:"=>0x72,"INCr"=>0x92,"INCr*"=>0xB2,"INCr:"=>0xD2,"INCr*:"=>0xF2, - "DEC"=>0x13,"DEC*"=>0x33,"DEC:"=>0x53,"DEC*:"=>0x73,"DECr"=>0x93,"DECr*"=>0xB3,"DECr:"=>0xD3,"DECr*:"=>0xF3, - "LTH"=>0x14,"LTH*"=>0x34,"LTH:"=>0x54,"LTH*:"=>0x74,"LTHr"=>0x94,"LTHr*"=>0xB4,"LTHr:"=>0xD4,"LTHr*:"=>0xF4, - "GTH"=>0x15,"GTH*"=>0x35,"GTH:"=>0x55,"GTH*:"=>0x75,"GTHr"=>0x95,"GTHr*"=>0xB5,"GTHr:"=>0xD5,"GTHr*:"=>0xF5, - "EQU"=>0x16,"EQU*"=>0x36,"EQU:"=>0x56,"EQU*:"=>0x76,"EQUr"=>0x96,"EQUr*"=>0xB6,"EQUr:"=>0xD6,"EQUr*:"=>0xF6, - "NQK"=>0x17,"NQK*"=>0x37,"NQK:"=>0x57,"NQK*:"=>0x77,"NQKr"=>0x97,"NQKr*"=>0xB7,"NQKr:"=>0xD7,"NQKr*:"=>0xF7, - // Bitwise operators - "IOR"=>0x18,"IOR*"=>0x38,"IOR:"=>0x58,"IOR*:"=>0x78,"IORr"=>0x98,"IORr*"=>0xB8,"IORr:"=>0xD8,"IORr*:"=>0xF8, - "XOR"=>0x19,"XOR*"=>0x39,"XOR:"=>0x59,"XOR*:"=>0x79,"XORr"=>0x99,"XORr*"=>0xB9,"XORr:"=>0xD9,"XORr*:"=>0xF9, - "AND"=>0x1A,"AND*"=>0x3A,"AND:"=>0x5A,"AND*:"=>0x7A,"ANDr"=>0x9A,"ANDr*"=>0xBA,"ANDr:"=>0xDA,"ANDr*:"=>0xFA, - "NOT"=>0x1B,"NOT*"=>0x3B,"NOT:"=>0x5B,"NOT*:"=>0x7B,"NOTr"=>0x9B,"NOTr*"=>0xBB,"NOTr:"=>0xDB,"NOTr*:"=>0xFB, - "SHF"=>0x1C,"SHF*"=>0x3C,"SHF:"=>0x5C,"SHF*:"=>0x7C,"SHFr"=>0x9C,"SHFr*"=>0xBC,"SHFr:"=>0xDC,"SHFr*:"=>0xFC, - "SHC"=>0x1D,"SHC*"=>0x3D,"SHC:"=>0x5D,"SHC*:"=>0x7D,"SHCr"=>0x9D,"SHCr*"=>0xBD,"SHCr:"=>0xDD,"SHCr*:"=>0xFD, - "TAL"=>0x1E,"TAL*"=>0x3E,"TAL:"=>0x5E,"TAL*:"=>0x7E,"TALr"=>0x9E,"TALr*"=>0xBE,"TALr:"=>0xDE,"TALr*:"=>0xFE, - "REV"=>0x1F,"REV*"=>0x3F,"REV:"=>0x5F,"REV*:"=>0x7F,"REVr"=>0x9F,"REVr*"=>0xBF,"REVr:"=>0xDF,"REVr*:"=>0xFF, - _ => return None, - }) -} |