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
|
package Compiler;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.List;
import java.util.Map;
public class TokenScanner {
private String sourceCode;
List<Token> tokens = new ArrayList<>();
private int tokenStart=0;
private int currentLoc=0;
//Extract tokens from the source code by reading character by character
List<Token> extractTokens(String sourceCode){
this.sourceCode=sourceCode;
while (!checkEOF()){
tokenStart=currentLoc;
readToken();
}
tokens.add(new Token(TokenType.EOF, "", null));
return tokens;
}
//Extract a single token
private void readToken(){
char checkChar = sourceCode.charAt(currentLoc);
switch(checkChar){
case ' ':break;
case '\n':break;
case '\r':break;
case '\t':
break;
case '(': createTokenNull(TokenType.LEFT_PAREN); break;
case ')': createTokenNull(TokenType.RIGHT_PAREN); break;
case '+': createTokenNull(TokenType.PLUS); break;
case '-': createTokenNull(TokenType.MINUS); break;
case '*': createTokenNull(TokenType.STAR); break;
case '/': createTokenNull(TokenType.SLASH); break;
case ';': createTokenNull(TokenType.SEMI_COLON); break;
case ',': createTokenNull(TokenType.COMMA); break;
//Some tokens are multiple characters long (==, <=) etc
//so need to check next char as well
case '=':
if (checkNextChar('=')){
createTokenNull(TokenType.EQUALITY);
break;
} else {
createTokenNull(TokenType.EQUALS);
break;
}
case ':':
if (checkNextChar(':')){
createTokenNull(TokenType.DEFINE);
break;
} else {
createTokenNull(TokenType.COLON);
break;
}
case '<':
if (checkNextChar('=')){
createTokenNull(TokenType.LESS_EQUAL);
break;
} else {
createTokenNull(TokenType.LESS);
break;
}
case '>':
if (checkNextChar('=')){
createTokenNull(TokenType.GREATER_EQUAL);
break;
} else {
createTokenNull(TokenType.GREATER);
break;
}
case '"':
while(lookAhead()!='"' && !checkEOF()){
currentLoc++;
}
if(checkEOF()){
Language.displayError("Strings must end with \"");
break;
}
currentLoc++;
createToken(TokenType.STRING, sourceCode.substring(tokenStart, currentLoc+1));
break;
default:
//Check for numer
if (checkIsDigit(checkChar)){
String type = "int";
while (checkIsDigit(lookAhead())){
currentLoc++;
}
//Check if number contains a decimal point
if (lookAhead()=='.' && checkIsDigit(lookTwoAhead())){
type="double";
currentLoc++;
while (checkIsDigit(lookAhead())){
currentLoc++;
}
}
if (type.equals("double")){
createToken(TokenType.NUMBER, Double.parseDouble(sourceCode.substring(tokenStart, currentLoc+1)));
} else{
createToken(TokenType.NUMBER, Integer.parseInt(sourceCode.substring(tokenStart, currentLoc+1)));
}
}
else if (checkIsAlpha(checkChar)){
while (checkIsAlpha(lookAhead())){
currentLoc++;
}
String text = sourceCode.substring(tokenStart, currentLoc+1);
TokenType type = keywords.get(text);
if(type == null){
createToken(TokenType.IDENTIFIER, text);
} else{
createToken(type, text);
}
} else {
Language.displayError("Unexpected Character");
}
}
currentLoc++;
}
//Test for end of file
private boolean checkEOF(){
return currentLoc>=sourceCode.length();
}
//Create a token without a value
private void createTokenNull(TokenType type){
createToken(type, null);
}
//Create token
private void createToken(TokenType type, Object value){
String tokenText = sourceCode.substring(tokenStart, currentLoc+1);
tokens.add(new Token(type, tokenText, value));
}
//Check if the next char matches a given char
private boolean checkNextChar(char matchChar){
if (checkEOF()){
return false;
}
if (sourceCode.charAt(currentLoc+1)==matchChar){
currentLoc++;
return true;
}
return false;
}
//Look at the next char in the source code
private char lookAhead(){
if (currentLoc+1>=sourceCode.length()){
return ' ';
} else {
return sourceCode.charAt(currentLoc+1);
}
}
//Look 2 chars ahead in the source code
private char lookTwoAhead(){
if (currentLoc+2>=sourceCode.length()){
return ' ';
} else {
return sourceCode.charAt(currentLoc+2);
}
}
//Check if a given char is a digit
private boolean checkIsDigit(char checkChar){
return checkChar>='0' && checkChar<='9';
}
private boolean checkIsAlpha(char checkChar){
return ('a'<=checkChar && checkChar<='z')||
('A'<=checkChar && checkChar<='Z');
}
private static final Map<String, TokenType> keywords;
static {
keywords = new HashMap<>();
keywords.put("int", TokenType.INT);
keywords.put("len", TokenType.LEN);
keywords.put("real", TokenType.REAL);
keywords.put("character", TokenType.STRING);
keywords.put("print", TokenType.PRINT);
keywords.put("endprint", TokenType.ENDPRINT);
keywords.put("if", TokenType.IF);
keywords.put("then", TokenType.THEN);
keywords.put("end", TokenType.END);
keywords.put("else", TokenType.ELSE);
keywords.put("do", TokenType.DO);
}
}
|
