Done with lexer (chap1)

Signed-off-by: jmug <u.g.a.mariano@gmail.com>

pkg/lexer/lexer.go

@@ -0,0 +1,141 @@
+package lexer
+
+import "code.jmug.me/jmug/interpreter-in-go/pkg/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) NextToken() token.Token {
+	l.skipWhitespace()
+	var tok token.Token
+	switch l.ch {
+	case '=':
+		if l.peekChar() == '=' {
+			ch := l.ch
+			l.readChar()
+			literal := string(ch) + string(l.ch)
+			tok.Type = token.EQ
+			tok.Literal = literal
+		} 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.Type = token.NOT_EQ
+			tok.Literal = literal
+		} 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.LT, l.ch)
+	case '>':
+		tok = newToken(token.GT, l.ch)
+	case ',':
+		tok = newToken(token.COMMA, 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.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)
+			// Don't let it fall through because readIdentifier calls readChar.
+			return tok
+		} else if isDigit(l.ch) {
+			tok.Literal = l.readNumber()
+			tok.Type = token.INT
+			// Don't let it fall through because readNumber calls readChar.
+			return tok
+		} else {
+			tok = newToken(token.ILLEGAL, l.ch)
+		}
+	}
+	l.readChar()
+	return tok
+}
+
+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
+	}
+	return l.input[l.readPosition]
+}
+
+func (l *Lexer) readIdentifier() string {
+	position := l.position
+	for isLetter(l.ch) {
+		l.readChar()
+	}
+	// Slicing until l.position instead of readPosition because the last read
+	// char was not a letter.
+	return l.input[position:l.position]
+}
+
+func (l *Lexer) readNumber() string {
+	position := l.position
+	for isDigit(l.ch) {
+		l.readChar()
+	}
+	// Slicing until l.position instead of readPosition because the last read
+	// char was not a letter.
+	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 newToken(tokenType token.TokenType, ch byte) token.Token {
+	return token.Token{Type: tokenType, Literal: string(ch)}
+}
+
+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'
+}

pkg/lexer/lexer_test.go

@@ -0,0 +1,126 @@
+package lexer
+
+import (
+	"testing"
+
+	"code.jmug.me/jmug/interpreter-in-go/pkg/token"
+)
+
+func TestNextToken(t *testing.T) {
+	input := `let five = 5;
+let ten = 10;
+
+let add = fn(x, y) {
+  x + y;
+};
+
+let result = add(five, ten);
+!-/*5;
+5 < 10 > 5;
+
+if (5 < 10) {
+	return true;
+} else {
+	return false;
+}
+
+10 == 10;
+10 != 9;
+`
+
+	tests := []struct {
+		expectedType    token.TokenType
+		expectedLiteral string
+	}{
+		{token.LET, "let"},
+		{token.IDENT, "five"},
+		{token.ASSIGN, "="},
+		{token.INT, "5"},
+		{token.SEMICOLON, ";"},
+		{token.LET, "let"},
+		{token.IDENT, "ten"},
+		{token.ASSIGN, "="},
+		{token.INT, "10"},
+		{token.SEMICOLON, ";"},
+		{token.LET, "let"},
+		{token.IDENT, "add"},
+		{token.ASSIGN, "="},
+		{token.FUNCTION, "fn"},
+		{token.LPAREN, "("},
+		{token.IDENT, "x"},
+		{token.COMMA, ","},
+		{token.IDENT, "y"},
+		{token.RPAREN, ")"},
+		{token.LBRACE, "{"},
+		{token.IDENT, "x"},
+		{token.PLUS, "+"},
+		{token.IDENT, "y"},
+		{token.SEMICOLON, ";"},
+		{token.RBRACE, "}"},
+		{token.SEMICOLON, ";"},
+		{token.LET, "let"},
+		{token.IDENT, "result"},
+		{token.ASSIGN, "="},
+		{token.IDENT, "add"},
+		{token.LPAREN, "("},
+		{token.IDENT, "five"},
+		{token.COMMA, ","},
+		{token.IDENT, "ten"},
+		{token.RPAREN, ")"},
+		{token.SEMICOLON, ";"},
+		{token.BANG, "!"},
+		{token.MINUS, "-"},
+		{token.SLASH, "/"},
+		{token.ASTERISK, "*"},
+		{token.INT, "5"},
+		{token.SEMICOLON, ";"},
+		{token.INT, "5"},
+		{token.LT, "<"},
+		{token.INT, "10"},
+		{token.GT, ">"},
+		{token.INT, "5"},
+		{token.SEMICOLON, ";"},
+		{token.IF, "if"},
+		{token.LPAREN, "("},
+		{token.INT, "5"},
+		{token.LT, "<"},
+		{token.INT, "10"},
+		{token.RPAREN, ")"},
+		{token.LBRACE, "{"},
+		{token.RETURN, "return"},
+		{token.TRUE, "true"},
+		{token.SEMICOLON, ";"},
+		{token.RBRACE, "}"},
+		{token.ELSE, "else"},
+		{token.LBRACE, "{"},
+		{token.RETURN, "return"},
+		{token.FALSE, "false"},
+		{token.SEMICOLON, ";"},
+		{token.RBRACE, "}"},
+		{token.INT, "10"},
+		{token.EQ, "=="},
+		{token.INT, "10"},
+		{token.SEMICOLON, ";"},
+		{token.INT, "10"},
+		{token.NOT_EQ, "!="},
+		{token.INT, "9"},
+		{token.SEMICOLON, ";"},
+		{token.EOF, ""},
+	}
+
+	l := New(input)
+
+	for i, tt := range tests {
+		tok := l.NextToken()
+
+		if tok.Type != tt.expectedType {
+			t.Fatalf("tests[%d] - tokentype wrong. expected=%q, got=%q",
+				i, tt.expectedType, tok.Type)
+		}
+
+		if tok.Literal != tt.expectedLiteral {
+			t.Fatalf("tests[%d] - literal wrong. expected=%q, got=%q",
+				i, tt.expectedLiteral, tok.Literal)
+		}
+	}
+}

pkg/token/token.go

@@ -0,0 +1,64 @@
+package token
+
+type TokenType string
+
+const (
+	ILLEGAL = "ILLEGAL"
+	EOF     = "EOF"
+
+	// Identifiers + Literals
+	IDENT = "IDENT"
+	INT   = "INT"
+
+	// Operators
+	ASSIGN   = "="
+	PLUS     = "+"
+	MINUS    = "-"
+	BANG     = "!"
+	ASTERISK = "*"
+	SLASH    = "/"
+	LT       = "<"
+	GT       = ">"
+	EQ       = "=="
+	NOT_EQ   = "!="
+
+	// Delimiters
+	COMMA     = ","
+	SEMICOLON = ";"
+
+	LPAREN = "("
+	RPAREN = ")"
+	LBRACE = "{"
+	RBRACE = "}"
+
+	// Keywords
+	FUNCTION = "FUNCTION"
+	LET      = "LET"
+	TRUE     = "TRUE"
+	FALSE    = "FALSE"
+	IF       = "IF"
+	ELSE     = "ELSE"
+	RETURN   = "RETURN"
+)
+
+var keywords = map[string]TokenType{
+	"fn":     FUNCTION,
+	"let":    LET,
+	"true":   TRUE,
+	"false":  FALSE,
+	"if":     IF,
+	"else":   ELSE,
+	"return": RETURN,
+}
+
+type Token struct {
+	Type    TokenType
+	Literal string
+}
+
+func LookupIdent(ident string) TokenType {
+	if typ, ok := keywords[ident]; ok {
+		return typ
+	}
+	return IDENT
+}