Socialify

Folder ..

Viewing lexer.go
168 lines (151 loc) • 4.0 KB

  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
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
package lexer

import "mana/tokens"

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
}

// New returns a new Lexer instance.
func New(input string) *Lexer {
	var l *Lexer = &Lexer{input: input}
	l.readChar()
	return l
}

// NextToken returns the next token in the input string.
func (l *Lexer) NextToken() tokens.Token {
	var tok tokens.Token

	l.skipWhitespace()

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

	l.readChar()
	return tok
}

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

// newToken returns a new Token instance.
func newToken(tokenType tokens.TokenType, ch byte) tokens.Token {
	return tokens.Token{Type: tokenType, Literal: string(ch)}
}

// isLetter returns true if the given character is a letter.
func isLetter(ch byte) bool {
	return 'a' <= ch && ch <= 'z' || 'A' <= ch && ch <= 'Z' || ch == '_'
}

// isDigit returns true if the given character is a digit.
func isDigit(ch byte) bool {
	return '0' <= ch && ch <= '9'
}

// readChar reads the next character in the input and advances the position in the input string.
func (l *Lexer) readChar() {
	if l.readPosition >= len(l.input) {
		l.ch = 0 // ASCII code for "NUL" character
	} else {
		l.ch = l.input[l.readPosition]
	}
	l.position = l.readPosition
	l.readPosition++
}

// peekChar returns the next character in the input string without advancing the position in the input string.
func (l *Lexer) peekChar() byte {
	if l.readPosition >= len(l.input) {
		return 0 // ASCII code for "NUL" character
	} else {
		return l.input[l.readPosition]
	}
}

// readIdentifier reads an identifier and advances the position in the input string until it encounters a non-letter character.
func (l *Lexer) readIdentifier() string {
	var position int = l.position
	for isLetter(l.ch) {
		l.readChar()
	}
	return l.input[position:l.position]
}

// readNumber reads a number and advances the position in the input string until it encounters a non-digit character.
func (l *Lexer) readNumber() string {
	var position int = l.position
	for isDigit(l.ch) {
		l.readChar()
	}
	return l.input[position:l.position]
}

func (l *Lexer) readString() string {
	position := l.position + 1
	for {
		l.readChar()
		if l.ch == '"' || l.ch == 0 {
			break
		}
	}

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