aboutsummaryrefslogtreecommitdiff
path: root/lexer/lexer.go
diff options
context:
space:
mode:
Diffstat (limited to 'lexer/lexer.go')
-rw-r--r--lexer/lexer.go135
1 files changed, 135 insertions, 0 deletions
diff --git a/lexer/lexer.go b/lexer/lexer.go
new file mode 100644
index 0000000..cffd925
--- /dev/null
+++ b/lexer/lexer.go
@@ -0,0 +1,135 @@
+package lexer
+
+import "monkey/token"
+
+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 New(input string) *Lexer {
+ l := &Lexer{input: input}
+ l.readChar()
+ return l
+}
+
+func (l *Lexer) NextToken() token.Token {
+ var tok token.Token
+
+ l.skipWhitespace()
+
+ switch l.ch {
+ case '=':
+ if l.peekChar() == '=' {
+ ch := l.ch
+ l.readChar()
+ tok = token.Token{Type: token.EQ, Literal: string(ch) + string(l.ch)}
+ } 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()
+ tok = token.Token{Type: token.NOT_EQ, Literal: string(ch) + string(l.ch)}
+ } else {
+ 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)
+ case ';':
+ tok = newToken(token.SEMICOLON, l.ch)
+ case ',':
+ tok = newToken(token.COMMA, l.ch)
+ case '{':
+ tok = newToken(token.LBRACE, l.ch)
+ case '}':
+ tok = newToken(token.RBRACE, l.ch)
+ case '(':
+ tok = newToken(token.LPAREN, l.ch)
+ case ')':
+ tok = newToken(token.RPAREN, 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.Type = token.INT
+ tok.Literal = l.readNumber()
+ return tok
+ } else {
+ tok = newToken(token.ILLEGAL, l.ch)
+ }
+ }
+
+ 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) 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) peekChar() byte {
+ if l.readPosition >= len(l.input) {
+ return 0
+ } else {
+ return l.input[l.readPosition]
+ }
+}
+
+func (l *Lexer) readIdentifier() string {
+ position := l.position
+ for isLetter(l.ch) {
+ l.readChar()
+ }
+ return l.input[position:l.position]
+}
+
+func (l *Lexer) readNumber() string {
+ position := l.position
+ for isDigit(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 newToken(tokenType token.TokenType, ch byte) token.Token {
+ return token.Token{Type: tokenType, Literal: string(ch)}
+}