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
)

type Token struct {
	Type  TokenType
	Value string
}

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

func New(input string) *Lexer {
	l := &Lexer{input: input}
	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++
}

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: "=="}
		} else {
			tok = Token{Type: TokenEqual, Value: "="}
		}
	case '!':
		if l.peekChar() == '=' {
			l.readChar() // consume the current '!'
			tok = Token{Type: TokenNotEqual, Value: "!="}
		} else {
			tok = Token{Type: TokenEOF, Value: ""} // Not supported yet
		}
	case '<':
		if l.peekChar() == '=' {
			l.readChar() // consume the current '<'
			tok = Token{Type: TokenLessEqual, Value: "<="}
		} else {
			tok = Token{Type: TokenLessThan, Value: "<"}
		}
	case '>':
		if l.peekChar() == '=' {
			l.readChar() // consume the current '>'
			tok = Token{Type: TokenGreaterEqual, Value: ">="}
		} else {
			tok = Token{Type: TokenGreaterThan, Value: ">"}
		}
	case ';':
		tok = Token{Type: TokenSemicolon, Value: ";"}
	case '"':
		tok = Token{Type: TokenString, Value: l.readString()}
		return tok
	case '{':
		tok = Token{Type: TokenLeftBrace, Value: "{"}
	case '}':
		tok = Token{Type: TokenRightBrace, Value: "}"}
	case '[':
		tok = Token{Type: TokenLeftBracket, Value: "["}
	case ']':
		tok = Token{Type: TokenRightBracket, Value: "]"}
	case ',':
		tok = Token{Type: TokenComma, Value: ","}
	case '+':
		tok = Token{Type: TokenPlus, Value: "+"}
	case '-':
		tok = Token{Type: TokenMinus, Value: "-"}
	case '*':
		tok = Token{Type: TokenStar, Value: "*"}
	case '/':
		tok = Token{Type: TokenSlash, Value: "/"}
	case '(':
		tok = Token{Type: TokenLeftParen, Value: "("}
	case ')':
		tok = Token{Type: TokenRightParen, Value: ")"}
	case 0:
		tok = Token{Type: TokenEOF, Value: ""}
	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 "true":
				tok.Type = TokenTrue
			case "false":
				tok.Type = TokenFalse
			case "end":
				tok.Type = TokenEnd
			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: ""}
		}
	}

	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()
		l.readChar()

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

		l.skipWhitespace()
	}
}