summaryrefslogtreecommitdiff
path: root/lexer/lexer.go
blob: 4945adfa2e1d19250e5181e48a3353cfdeca4f54 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
package lexer

import "github.com/mewsen/interpreter/token"

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

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()
			literal := string(ch) + string(l.ch)
			tok = token.Token{Type: token.EQ, Literal: literal}
		} else {
			tok = newToken(token.ASSIGN, 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 ',':
		tok = newToken(token.COMMA, 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{Type: token.NOT_EQ, 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 0:
		tok.Literal = ""
		tok.Type = token.EOF
	default:
		if isLetter(l.ch) {
			tok.Literal = l.readIdentifier()
			tok.Type = token.LookupIdentifier(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) readNumber() string {
	position := l.position
	for isDigit(l.ch) {
		l.readChar()
	}

	return l.input[position:l.position]
}

func isDigit(ch byte) bool {
	return '0' <= ch && ch <= '9'
}

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

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

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 (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++
}

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