lexer.go

package lexer

import (
	"monkey/token"
)

const (
	UNESCAPED = iota
	ESCAPED
)

type Lexer struct {
	input        string
	position     int  // current position in input (points to current char)
	readPosition int  // current reading position in input (after current char)
	ch           byte // current char under examination
}

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

func (l *Lexer) readChar() {
	if l.readPosition >= len(l.input) {
		l.ch = 0
	} else {
		l.ch = l.input[l.readPosition]
	}
	l.position = l.readPosition
	l.readPosition += 1
}

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

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

func (l *Lexer) readString() string {
	var out []byte
	state := UNESCAPED

	for {
		l.readChar()
		if l.ch == '"' && state == UNESCAPED {
			break
		} else if l.ch == 0 {
			return ""
		}
		switch state {
		case UNESCAPED:
			if l.ch == '\\' {
				state = ESCAPED
			} else {
				out = append(out, l.ch)
			}
		case ESCAPED:
			l.addEscapeCharacters(&out, l.ch)
			state = UNESCAPED
		}
	}
	return string(out)
}

func (l *Lexer) addEscapeCharacters(out *[]byte, ch byte) {
	switch ch {
	case 't':
		*out = append(*out, '\t')
	case 'n':
		*out = append(*out, '\n')
	case 'r':
		*out = append(*out, '\r')
	case '\\', '"':
		*out = append(*out, ch)
	}
}

func (l *Lexer) readNumber() (string, token.TokenType) {
	position := l.position
	count := 0
	var tokenType token.TokenType = token.INT
	for isDigit(l.ch) || l.input[l.position] == '.' {
		if l.input[l.position] == '.' {
			tokenType = token.FLOAT
			count++
		}
		l.readChar()
		if l.position > len(l.input)-1 {
			break
		}
	}

	if count > 1 {
		return l.input[position:l.position], token.ILLEGAL
	}
	return l.input[position:l.position], tokenType
}

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 newToken(tokenType token.TokenType, ch byte) token.Token {
	return token.Token{Type: tokenType, Literal: string(ch)}
}

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

	l.skipWhitespace()

	switch l.ch {
	case '"':
		s := l.readString()
		tok.Type = token.STRING
		tok.Literal = s
	case '=':
		if l.peekChar() == '=' {
			ch := l.ch
			l.readChar()
			literal := string(ch) + string(l.ch)
			tok = token.Token{Literal: literal, Type: token.EQ}
		} else {
			tok = newToken(token.ASSIGN, l.ch)
		}
	case '+':
		tok = newToken(token.PLUS, l.ch)
	case '-':
		tok = newToken(token.MINUS, l.ch)
	case '!':
		if l.peekChar() == '=' {
			ch := l.ch
			l.readChar()
			literal := string(ch) + string(l.ch)
			tok = token.Token{Literal: literal, Type: token.NOT_EQ}
		} else {
			tok = newToken(token.BANG, l.ch)
		}
	case '*':
		tok = newToken(token.ASTERISK, l.ch)
	case '/':
		tok = newToken(token.SLASH, l.ch)
	case '%':
		tok = newToken(token.MODULUS, l.ch)
	case '<':
		tok = newToken(token.LT, l.ch)
	case '>':
		tok = newToken(token.GT, l.ch)
	case ';':
		tok = newToken(token.SEMICOLON, l.ch)
	case '(':
		tok = newToken(token.LPAREN, l.ch)
	case ')':
		tok = newToken(token.RPAREN, l.ch)
	case '[':
		tok = newToken(token.LBRACKET, l.ch)
	case ']':
		tok = newToken(token.RBRACKET, l.ch)
	case ',':
		tok = newToken(token.COMMA, l.ch)
	case ':':
		tok = newToken(token.COLON, l.ch)
	case '{':
		tok = newToken(token.LBRACE, l.ch)
	case '}':
		tok = newToken(token.RBRACE, l.ch)
	case 0:
		tok.Literal = ""
		tok.Type = token.EOF
	default:
		if isLetter(l.ch) {
			tok.Literal = l.readIdentifier()
			tok.Type = token.LookupIdent(tok.Literal)
			return tok
		} else if isDigit(l.ch) {
			tok.Literal, tok.Type = l.readNumber()
			return tok
		} else {
			tok = newToken(token.ILLEGAL, l.ch)
		}
	}
	l.readChar()
	return tok
}

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