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
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
|
package com.craftinginterpreters.lox;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.List;
import java.util.Map;
import static com.craftinginterpreters.lox.TokenType.*;
class Scanner {
private final String source;
private final List<Token> tokens = new ArrayList<>();
private int start = 0;
private int current = 0;
private int line = 1;
private static final Map<String, TokenType> keywords;
static {
keywords = new HashMap<>();
keywords.put("and", AND);
keywords.put("class", CLASS);
keywords.put("else", ELSE);
keywords.put("false", FALSE);
keywords.put("for", FOR);
keywords.put("fun", FUN);
keywords.put("if", IF);
keywords.put("nil", NIL);
keywords.put("or", OR);
keywords.put("print", PRINT);
keywords.put("return", RETURN);
keywords.put("super", SUPER);
keywords.put("this", THIS);
keywords.put("true", TRUE);
keywords.put("var", VAR);
keywords.put("while", WHILE);
}
Scanner(String source) {
this.source = source;
}
List<Token> scanTokens() {
while (!isAtEnd()) {
// We are at the beginning of the next lexeme.
start = current;
scanToken();
}
tokens.add(new Token(EOF, "", null, line));
return tokens;
}
private void scanToken() {
char c = advance();
switch (c) {
case '(': addToken(LEFT_PAREN); break;
case ')': addToken(RIGHT_PAREN); break;
case '{': addToken(LEFT_BRACE); break;
case '}': addToken(RIGHT_BRACE); break;
case ',': addToken(COMMA); break;
case '.': addToken(DOT); break;
case '-': addToken(MINUS); break;
case '+': addToken(PLUS); break;
case ';': addToken(SEMICOLON); break;
case '*': addToken(STAR); break;
case '!':
addToken(match('=') ? BANG_EQUAL : BANG);
break;
case '=':
addToken(match('=') ? EQUAL_EQUAL : EQUAL);
break;
case '<':
addToken(match('=') ? LESS_EQUAL : LESS);
break;
case '>':
addToken(match('=') ? GREATER_EQUAL : GREATER);
break;
case '/':
if (match('/')) {
// A comment goes until the end of the line.
while (peek() != '\n' && !isAtEnd()) advance();
} else {
addToken(SLASH);
}
break;
case ' ':
case '\r':
case '\t':
// Ignore whitespace.
break;
// I guess this code isn't meant to run on Mac OS 9 and before.
case '\n':
line++;
break;
case '"': string(); break;
default:
if (isDigit(c)) {
number();
} else if (isAlpha(c)) {
identifier();
} else {
Lox.error(line, "Unexpected character.");
}
break;
}
}
private void identifier() {
while (isAlphaNumeric(peek())) advance();
String text = source.substring(start, current);
TokenType type = keywords.get(text);
if (type == null) type = IDENTIFIER;
addToken(type);
}
private void number() {
while (isDigit(peek())) advance();
// Look for a fractional part.
if (peek() == '.' && isDigit(peekNext())) {
// Consume the "."
advance();
while (isDigit(peek())) advance();
}
addToken(NUMBER,
Double.parseDouble(source.substring(start, current)));
}
// I guess we won't be able to include escaped characters in the string? At
// least not escaped " characters.
private void string() {
while (peek() != '"' && !isAtEnd()) {
if (peek() == '\n') line++;
advance();
}
if (isAtEnd()) {
Lox.error(line, "Unterminated string.");
return;
}
// The closing ".
advance();
// Trim the surrounding quotes.
String value = source.substring(start + 1, current - 1);
addToken(STRING, value);
}
private boolean match(char expected) {
if (isAtEnd()) return false;
if (source.charAt(current) != expected) return false;
current++;
return true;
}
private char peek() {
if (isAtEnd()) return '\0';
return source.charAt(current);
}
private char peekNext() {
if (current + 1 >= source.length()) return '\0';
return source.charAt(current + 1);
}
private boolean isAlpha(char c) {
return (c >= 'a' && c <= 'z') ||
(c >= 'A' && c <= 'Z') ||
c == '_';
}
private boolean isAlphaNumeric(char c) {
return isAlpha(c) || isDigit(c);
}
private boolean isDigit(char c) {
return c >= '0' && c <= '9';
}
private boolean isAtEnd() {
return current >= source.length();
}
private char advance() {
current++;
return source.charAt(current - 1);
}
private void addToken(TokenType type) {
addToken(type, null);
}
private void addToken(TokenType type, Object literal) {
String text = source.substring(start, current);
tokens.add(new Token(type, text, literal, line));
}
}
|
