Mako/lexer/lexer.go

package lexer

type TokenType byte

const (
	TokenEOF TokenType = iota
	TokenIdentifier
	TokenString
	TokenNumber
	TokenEqual
	TokenEcho
	TokenSemicolon
	TokenLeftBrace
	TokenRightBrace
	TokenLeftBracket
	TokenRightBracket
	TokenComma
	TokenPlus
	TokenMinus
	TokenStar
	TokenSlash
	TokenLeftParen
	TokenRightParen
	TokenIf
	TokenThen
	TokenElse
	TokenTrue
	TokenFalse
	TokenEqualEqual
	TokenNotEqual
	TokenLessThan
	TokenGreaterThan
	TokenLessEqual
	TokenGreaterEqual
	TokenEnd
	TokenAnd
	TokenOr
	TokenNot
	TokenElseIf
	TokenNil
	TokenFunction
	TokenReturn
)

type Token struct {
	Type  TokenType
	Value string
	Line  int
}

type Lexer struct {
	input   string
	pos     int
	readPos int
	ch      byte
	line    int
}

func New(input string) *Lexer {
	l := &Lexer{input: input, line: 1}
	l.readChar()
	return l
}

func (l *Lexer) readChar() {
	if l.readPos >= len(l.input) {
		l.ch = 0
	} else {
		l.ch = l.input[l.readPos]
	}
	l.pos = l.readPos
	l.readPos++

	if l.ch == '\n' {
		l.line++
	}
}

func (l *Lexer) NextToken() Token {
	var tok Token

	l.skipWhitespace()
	l.skipComment()

	switch l.ch {
	case '=':
		if l.peekChar() == '=' {
			l.readChar() // consume the current '='
			tok = Token{Type: TokenEqualEqual, Value: "==", Line: l.line}
		} else {
			tok = Token{Type: TokenEqual, Value: "=", Line: l.line}
		}
	case '!':
		if l.peekChar() == '=' {
			l.readChar() // consume the current '!'
			tok = Token{Type: TokenNotEqual, Value: "!=", Line: l.line}
		} else {
			tok = Token{Type: TokenEOF, Value: "", Line: l.line} // Not supported yet
		}
	case '<':
		if l.peekChar() == '=' {
			l.readChar() // consume the current '<'
			tok = Token{Type: TokenLessEqual, Value: "<=", Line: l.line}
		} else {
			tok = Token{Type: TokenLessThan, Value: "<", Line: l.line}
		}
	case '>':
		if l.peekChar() == '=' {
			l.readChar() // consume the current '>'
			tok = Token{Type: TokenGreaterEqual, Value: ">=", Line: l.line}
		} else {
			tok = Token{Type: TokenGreaterThan, Value: ">", Line: l.line}
		}
	case '"':
		tok = Token{Type: TokenString, Value: l.readString(), Line: l.line}
		return tok
	case '{':
		tok = Token{Type: TokenLeftBrace, Value: "{", Line: l.line}
	case '}':
		tok = Token{Type: TokenRightBrace, Value: "}", Line: l.line}
	case '[':
		tok = Token{Type: TokenLeftBracket, Value: "[", Line: l.line}
	case ']':
		tok = Token{Type: TokenRightBracket, Value: "]", Line: l.line}
	case ',':
		tok = Token{Type: TokenComma, Value: ",", Line: l.line}
	case '+':
		tok = Token{Type: TokenPlus, Value: "+", Line: l.line}
	case '-':
		tok = Token{Type: TokenMinus, Value: "-", Line: l.line}
	case '*':
		tok = Token{Type: TokenStar, Value: "*", Line: l.line}
	case '/':
		if l.peekChar() == '/' {
			// Comment line, skip it
			l.skipComment()
			return l.NextToken()
		}
		tok = Token{Type: TokenSlash, Value: "/", Line: l.line}
	case '(':
		tok = Token{Type: TokenLeftParen, Value: "(", Line: l.line}
	case ')':
		tok = Token{Type: TokenRightParen, Value: ")", Line: l.line}
	case 0:
		tok = Token{Type: TokenEOF, Value: "", Line: l.line}
	default:
		if isLetter(l.ch) {
			tok.Value = l.readIdentifier()
			switch tok.Value {
			case "echo":
				tok.Type = TokenEcho
			case "if":
				tok.Type = TokenIf
			case "then":
				tok.Type = TokenThen
			case "else":
				tok.Type = TokenElse
			case "elseif":
				tok.Type = TokenElseIf
			case "true":
				tok.Type = TokenTrue
			case "false":
				tok.Type = TokenFalse
			case "end":
				tok.Type = TokenEnd
			case "and":
				tok.Type = TokenAnd
			case "or":
				tok.Type = TokenOr
			case "not":
				tok.Type = TokenNot
			case "nil":
				tok.Type = TokenNil
			case "function":
				tok.Type = TokenFunction
			case "return":
				tok.Type = TokenReturn
			default:
				tok.Type = TokenIdentifier
			}
			return tok
		} else if isDigit(l.ch) {
			tok.Type = TokenNumber
			tok.Value = l.readNumber()
			return tok
		} else {
			tok = Token{Type: TokenEOF, Value: "", Line: l.line}
		}
	}

	l.readChar()
	return tok
}

func (l *Lexer) skipWhitespace() {
	for l.ch == ' ' || l.ch == '\t' || l.ch == '\n' || l.ch == '\r' {
		l.readChar()
	}
}

func (l *Lexer) readIdentifier() string {
	pos := l.pos
	for isLetter(l.ch) || isDigit(l.ch) {
		l.readChar()
	}
	return l.input[pos:l.pos]
}

func (l *Lexer) readNumber() string {
	pos := l.pos
	for isDigit(l.ch) {
		l.readChar()
	}
	return l.input[pos:l.pos]
}

func (l *Lexer) readString() string {
	pos := l.pos + 1
	for {
		l.readChar()
		if l.ch == '"' || l.ch == 0 {
			break
		}
	}
	str := l.input[pos:l.pos]
	l.readChar() // Skip closing quote
	return str
}

func isLetter(ch byte) bool {
	return 'a' <= ch && ch <= 'z' || 'A' <= ch && ch <= 'Z' || ch == '_'
}

func isDigit(ch byte) bool {
	return '0' <= ch && ch <= '9'
}

func (l *Lexer) peekChar() byte {
	if l.readPos >= len(l.input) {
		return 0
	}
	return l.input[l.readPos]
}

func (l *Lexer) skipComment() {
	if l.ch == '/' && l.peekChar() == '/' {
		l.readChar() // Skip first '/'
		l.readChar() // Skip second '/'

		for l.ch != '\n' && l.ch != 0 {
			l.readChar()
		}

		l.skipWhitespace()
	}
}