This repository was archived by the owner on Jun 10, 2022. It is now read-only.
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathLexer.java
More file actions
411 lines (365 loc) · 14.1 KB
/
Lexer.java
File metadata and controls
411 lines (365 loc) · 14.1 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
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
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
import java.io.File;
import java.io.FileNotFoundException;
import java.util.Scanner;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
public class Lexer {
private String fileName;
public Token head = null, tail = null;
public int position, line;
Lexer(String fN) {
fileName = fN;
}
public Token run() {
String data = "";
position = 0;
line = 1;
Pattern p;
Matcher m;
try {
File myFile = new File(fileName);
Scanner myReader = new Scanner(myFile);
while (myReader.hasNextLine()) {
data += myReader.nextLine() + "\n";
}
data = data.substring(0, data.length() - 1);
myReader.close();
} catch (FileNotFoundException e) {
System.out.println("File not found.");
return new Token("File not found.");
}
while (position < data.length()) {
String t = data.substring(position, position + 1);
String regex = "^-|[a-zA-Z0-9 \\[\\]{}(),:;\"=\n\t]$";
p = Pattern.compile(regex);
m = p.matcher(t);
if (m.find()) {
if (t.equals("\n")) {
// System.out.println("Newline character");
line++;
position++;
continue;
}
if (t.equals(" ")) {
position++;
continue;
}
if (t.equals("\t")) {
position++;
//System.out.println(line);
continue;
}
switch (t) {
case "(":
position++;
addToken(new Token(t, "Left Parenthesis", line));
continue;
case ")":
position++;
addToken(new Token(t, "Right Parenthesis", line));
continue;
case "{":
position++;
addToken(new Token(t, "Left Curly Bracket", line));
continue;
case "}":
position++;
addToken(new Token(t, "Right Curly Bracket", line));
continue;
case ";":
position++;
addToken(new Token(t, "Semi-colon", line));
continue;
case ",":
position++;
addToken(new Token(t, "Comma", line));
continue;
case "[":
position++;
addToken(new Token(t, "Left Square Bracket", line));
continue;
case "]":
position++;
addToken(new Token(t, "Left Square Bracket", line));
continue;
case ":":
position++;
t = data.substring(position, position + 1);
if (t.equals("=")) {
position++;
addToken(new Token(":=", "Assign", line));
} else {
System.out.println("LEXICAL ERROR");
System.out.println("On line " + line
+ " the : is not followed by an = to look as :=. In correct assign format.");
return new Token("LEXICAL ERROR");
}
break;
}
regex = "-|[0-9]";
p = Pattern.compile(regex);
m = p.matcher(t);
if (m.find()) {
position++;
if (!addToken(scanForNumbers(position, data))) {
return new Token("LEXICAL ERROR");
}
continue;
}
regex = "[A-Z]";
p = Pattern.compile(regex);
m = p.matcher(t);
if (m.find()) {
position++;
System.out.println("LEXICAL ERROR");
System.out.println("On line " + line + " the error of starting with a capital letter is not allowed. (" + t + ")");
return new Token("LEXICAL ERROR");
}
if (t.equals("\"")) {
position++;
if (!addToken(scanForShortString(position, data))) {
return new Token("LEXICAL ERROR");
}
continue;
}
regex = "-|[0-9]";
p = Pattern.compile(regex);
m = p.matcher(t);
if (m.find()) {
position++;
if (!addToken(scanForNumbers(position, data))) {
return new Token("LEXICAL ERROR");
}
continue;
}
regex = "[a-z]";
p = Pattern.compile(regex);
m = p.matcher(t);
if (m.find()) {
if (!addToken(scanForText(position, data))) {
return new Token("LEXICAL ERROR");
}
continue;
}
// use substring for the rest of the tokens and regular expressions.
} else {
String temp = data.substring(position, position + 1);
System.out.println("LEXICAL ERROR");
System.out.println("The character " + t + " on line " + line + " is not allowed. (" + temp + ")");
return new Token("LEXICAL ERROR");
}
}
return head;
}
public boolean addToken(Token t) {
if (t == null) {
return false;
}
if (head == null) {
head = t;
tail = t;
return true;
}
tail.next = t;
tail = t;
return true;
}
public Token scanForShortString(int pos, String data) {
Pattern p;
Matcher m;
int count = 0;
while (count <= 15) {
if (pos + count == data.length()) {
break;
}
String regex = "\"";
p = Pattern.compile(regex);
m = p.matcher(data.substring(pos + count, pos + count + 1));
if (m.find()) {
break;
}
count++;
}
String regex = "^([A-Z]|[0-9]|[ ]){0,15}\"$";
p = Pattern.compile(regex);
m = p.matcher(data.substring(pos, pos + count + 1));
if (m.find()) {
position = pos + count + 1;
return new Token(data.substring(pos - 1, pos + count + 1), "ShortString", line);
}
String temp = data.substring(pos - 1, pos + count + 1);
System.out.println("LEXICAL ERROR");
System.out.println("The string on line " + line + " is not the correct format for a ShortString.(" + temp + ")");
return null;
}
public Token scanForNumbers(int pos, String data) {
Pattern p;
Matcher m;
int count = 0;
String regex = "[0-9]";
if (!(pos < data.length())) {
if (data.substring(pos - 1, pos).equals("-")) {
System.out.println("LEXICAL ERROR");
System.out.println("On line " + line + " the minus is not followed by any value");
} else {
return new Token(data.substring(pos - 1, pos), "Number", line);
}
}
p = Pattern.compile(regex);
m = p.matcher(data.substring(pos, pos + 1));
while (m.find()) {
if (pos + count == data.length()) {
break;
} else {
count++;
m = p.matcher(data.substring(pos + count, pos + count + 1));
}
}
regex = "^([-]?[1-9]+[0-9]*)$|^0$";
p = Pattern.compile(regex);
m = p.matcher(data.substring(pos - 1, pos + count));
if (m.find()) {
position = pos + count;
return new Token(data.substring(pos - 1, pos + count), "ShortString", line);
}
String temp = data.substring(pos - 1, pos + count);
if (data.substring(pos - 1, pos).equals("0")) {
if (count > 0) {
System.out.println("LEXICAL ERROR");
System.out.println("On line " + line + " the zero cannot be a leading character in a number. (" + temp + ")");
return null;
}
}
if (data.substring(pos - 1, pos).equals("-")) {
if (count == 0) {
System.out.println("LEXICAL ERROR");
System.out.println("On line " + line + " the negative sign needs a value.(" + temp + ")");
} else {
System.out.println("LEXICAL ERROR");
System.out.println("On line " + line + " the negative sign cannot be followed by a zero.(" + temp + ")");
}
return null;
}
System.out.println("LEXICAL ERROR");
System.out.println("On line " + line + ", it is not a number.(" + temp + ")");
return null;
}
public Token scanForText(int pos, String data) {
// pos is start of the text and not the second character
Pattern p;
Matcher m;
int count = 1;
String regex = "^[a-z]([a-z]|[0-9])*$";
if (pos + 1 != data.length()) {
p = Pattern.compile(regex);
m = p.matcher(data.substring(pos, pos + count + 1));
while (m.find()) {
if (pos + count + 1 == data.length()) {
break;
}
count++;
// System.out.println(count);
m = p.matcher(data.substring(pos, pos + count + 1));
}
}
regex = "(^add$)|(^sub$)|(^mult$)|(^larger$)";
p = Pattern.compile(regex);
m = p.matcher(data.substring(pos, pos + count));
if (m.find()) {
position = pos + count;
return new Token(data.substring(pos, pos + count), "Number operators", line);
}
regex = "(^input$)|(^output$)";
p = Pattern.compile(regex);
m = p.matcher(data.substring(pos, pos + count));
if (m.find()) {
position = pos + count;
return new Token(data.substring(pos, pos + count), "I/O character", line);
}
regex = "(^eq$)";
p = Pattern.compile(regex);
m = p.matcher(data.substring(pos, pos + count));
if (m.find()) {
position = pos + count;
return new Token(data.substring(pos, pos + count), "Comparison operator", line);
}
regex = "(^and$)|(^or$)|(^not$)";
p = Pattern.compile(regex);
m = p.matcher(data.substring(pos, pos + count));
if (m.find()) {
position = pos + count;
return new Token(data.substring(pos, pos + count), "Boolean operator", line);
}
regex = "(^num$)|(^bool$)|(^string$)";
p = Pattern.compile(regex);
m = p.matcher(data.substring(pos, pos + count));
if (m.find()) {
position = pos + count;
return new Token(data.substring(pos, pos + count), "Variable type", line);
}
regex = "(^true$)|(^false$)";
p = Pattern.compile(regex);
m = p.matcher(data.substring(pos, pos + count));
if (m.find()) {
position = pos + count;
return new Token(data.substring(pos, pos + count), "Boolean value", line);
}
regex = "(^proc$)";
p = Pattern.compile(regex);
m = p.matcher(data.substring(pos, pos + count));
if (m.find()) {
position = pos + count;
return new Token(data.substring(pos, pos + count), "Procedure definition", line);
}
regex = "(^main$)";
p = Pattern.compile(regex);
m = p.matcher(data.substring(pos, pos + count));
if (m.find()) {
position = pos + count;
return new Token(data.substring(pos, pos + count), "Main Procedure definition", line);
}
regex = "(^arr$)";
p = Pattern.compile(regex);
m = p.matcher(data.substring(pos, pos + count));
if (m.find()) {
position = pos + count;
return new Token(data.substring(pos, pos + count), "Array", line);
}
regex = "(^halt$)|(^return$)";
p = Pattern.compile(regex);
m = p.matcher(data.substring(pos, pos + count));
if (m.find()) {
position = pos + count;
return new Token(data.substring(pos, pos + count), "Algorithm end", line);
}
regex = "(^if$)|(^then$)|(^else$)|(^do$)|(^until$)|(^while$)|(^call$)";
p = Pattern.compile(regex);
m = p.matcher(data.substring(pos, pos + count));
if (m.find()) {
position = pos + count;
return new Token(data.substring(pos, pos + count),
"Instruction " + data.substring(pos, pos + 1).toUpperCase() + data.substring(pos + 1, pos + count), line);
}
regex = "[a-z]([a-z]|[0-9])*";
p = Pattern.compile(regex);
m = p.matcher(data.substring(pos, pos + count));
if (m.find()) {
position = pos + count;
return new Token(data.substring(pos, pos + count), "userDefinedName", line);
}
String temp = data.substring(pos, pos + count);
System.out.println("LEXICAL ERROR");
System.out.println("On line " + line + ", there is no acceptable format given. (" + temp + ")");
return null;
}
public void printTokens() {
int count = 0;
Token curr = head;
while (curr != null) {
System.out.println("Token: " + curr.value + "\tType: " + curr.type);
curr = curr.next;
count++;
}
System.out.println("Token count: " + count);
}
}