monkey/lexer/lexer.go

117 lines
2.2 KiB
Go
Raw Normal View History

2021-11-30 19:02:01 +00:00
package lexer
2021-11-30 19:45:39 +00:00
import (
"gitlab.com/Tyrel/monkey/token"
)
type Lexer struct {
input string
position int
readPosition int
ch byte
}
func New(input string) *Lexer {
l := &Lexer{input: input}
l.readChar()
return l
}
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) NextToken() token.Token {
var tok token.Token
2021-11-30 20:27:22 +00:00
l.skipWhitespace()
2021-11-30 19:45:39 +00:00
switch l.ch {
case '=':
tok = newToken(token.ASSIGN, l.ch)
case '+':
tok = newToken(token.PLUS, l.ch)
2021-11-30 20:43:13 +00:00
case '-':
tok = newToken(token.MINUS, l.ch)
case '!':
tok = newToken(token.BANG, l.ch)
case '/':
tok = newToken(token.SLASH, l.ch)
case '*':
tok = newToken(token.ASTERISK, l.ch)
case '<':
tok = newToken(token.LT, l.ch)
case '>':
tok = newToken(token.GT, l.ch)
2021-11-30 19:45:39 +00:00
case '(':
tok = newToken(token.LPAREN, l.ch)
case ')':
tok = newToken(token.RPAREN, l.ch)
case '{':
tok = newToken(token.LBRACE, l.ch)
case '}':
tok = newToken(token.RBRACE, l.ch)
case ',':
tok = newToken(token.COMMA, l.ch)
case ';':
tok = newToken(token.SEMICOLON, l.ch)
case 0:
tok.Literal = ""
tok.Type = token.EOF
2021-11-30 20:27:22 +00:00
default:
if isLetter(l.ch) {
tok.Literal = l.readIdentifier()
tok.Type = token.LookupIdent(tok.Literal)
return tok
} else if isDigit(l.ch) {
tok.Type = token.INT
tok.Literal = l.readNumber()
return tok
} else {
tok = newToken(token.ILLEGAL, l.ch)
}
2021-11-30 19:45:39 +00:00
}
l.readChar()
return tok
}
func newToken(tokenType token.TokenType, ch byte) token.Token {
return token.Token{Type: tokenType, Literal: string(ch)}
}
2021-11-30 20:27:22 +00:00
func (l *Lexer) readIdentifier() string {
position := l.position
for isLetter(l.ch) {
l.readChar()
}
return l.input[position:l.position]
}
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) skipWhitespace() {
for l.ch == ' ' || l.ch == '\t' || l.ch == '\n' || l.ch == '\r' {
l.readChar()
}
}
func (l *Lexer) readNumber() string {
position := l.position
for isDigit(l.ch) {
l.readChar()
}
return l.input[position:l.position]
}