-
Notifications
You must be signed in to change notification settings - Fork 1.1k
/
JavaToken.java
326 lines (280 loc) · 10.2 KB
/
JavaToken.java
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
/*
* Copyright (C) 2007-2010 Júlio Vilmar Gesser.
* Copyright (C) 2011, 2013-2016 The JavaParser Team.
*
* This file is part of JavaParser.
*
* JavaParser can be used either under the terms of
* a) the GNU Lesser General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
* b) the terms of the Apache License
*
* You should have received a copy of both licenses in LICENCE.LGPL and
* LICENCE.APACHE. Please refer to those files for details.
*
* JavaParser is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU Lesser General Public License for more details.
*/
package com.github.javaparser;
import java.util.List;
import java.util.Optional;
import static com.github.javaparser.utils.CodeGenerationUtils.f;
import static com.github.javaparser.utils.Utils.EOL;
import static com.github.javaparser.utils.Utils.assertNotNull;
/**
* A token from a parsed source file.
* (Awkwardly named "Java"Token since JavaCC already generates an internal class Token.)
* It is a node in a double linked list called token list.
*/
public class JavaToken {
public static final JavaToken INVALID = new JavaToken();
private Range range;
private int kind;
private String text;
private JavaToken previousToken = null;
private JavaToken nextToken = null;
private JavaToken() {
this(null, 0, "INVALID", null, null);
}
public JavaToken(int kind, String text) {
this(null, kind, text, null, null);
}
JavaToken(Token token, List<JavaToken> tokens) {
Range range = Range.range(token.beginLine, token.beginColumn, token.endLine, token.endColumn);
String text = token.image;
// You could be puzzled by the following lines
//
// The reason why these lines are necessary is the fact that Java is ambiguous. There are cases where the
// sequence of characters ">>>" and ">>" should be recognized as the single tokens ">>>" and ">>". In other
// cases however we want to split those characters in single GT tokens (">").
//
// For example, in expressions ">>" and ">>>" are valid, while when defining types we could have this:
//
// List<List<Set<String>>>>
//
// You can see that the sequence ">>>>" should be interpreted as four consecutive ">" tokens closing a type
// parameter list.
//
// The JavaCC handle this case by first recognizing always the longest token, and then depending on the context
// putting back the unused chars in the stream. However in those cases the token provided is invalid: it has an
// image corresponding to the text originally recognized, without considering that after some characters could
// have been put back into the stream.
//
// So in the case of:
//
// List<List<Set<String>>>>
// ___ -> recognized as ">>>", then ">>" put back in the stream but
// Token(type=GT, image=">>>") passed to this class
// ___ -> recognized as ">>>", then ">>" put back in the stream but
// Token(type=GT, image=">>>") passed to this class
// __ -> recognized as ">>", then ">" put back in the stream but
// Token(type=GT, image=">>") passed to this class
// _ -> Token(type=GT, image=">") good!
//
// So given the image could be wrong but the type is correct, we look at the type of the token and we fix
// the image. Everybody is happy and we can keep this horrible thing as our little secret.
if (token.kind == GeneratedJavaParserConstants.GT) {
range = Range.range(token.beginLine, token.beginColumn, token.endLine, token.beginColumn);
text = ">";
} else if (token.kind == GeneratedJavaParserConstants.RSIGNEDSHIFT) {
range = Range.range(token.beginLine, token.beginColumn, token.endLine, token.beginColumn + 1);
text = ">>";
}
this.range = range;
this.kind = token.kind;
this.text = text;
if (!tokens.isEmpty()) {
final JavaToken previousToken = tokens.get(tokens.size() - 1);
this.previousToken = previousToken;
previousToken.nextToken = this;
} else {
previousToken = null;
}
}
/**
* Create a token of a certain kind.
*/
public JavaToken(int kind) {
String content = GeneratedJavaParserConstants.tokenImage[kind];
if (content.startsWith("\"")) {
content = content.substring(1, content.length() - 1);
}
if (TokenTypes.isEndOfLineToken(kind)) {
content = EOL;
} else if (TokenTypes.isWhitespace(kind)) {
content = " ";
}
this.kind = kind;
this.text = content;
}
public JavaToken(Range range, int kind, String text, JavaToken previousToken, JavaToken nextToken) {
assertNotNull(text);
this.range = range;
this.kind = kind;
this.text = text;
this.previousToken = previousToken;
this.nextToken = nextToken;
}
public Optional<Range> getRange() {
return Optional.ofNullable(range);
}
public int getKind() {
return kind;
}
void setKind(int kind) {
this.kind = kind;
}
public String getText() {
return text;
}
public Optional<JavaToken> getNextToken() {
return Optional.ofNullable(nextToken);
}
public Optional<JavaToken> getPreviousToken() {
return Optional.ofNullable(previousToken);
}
public void setRange(Range range) {
this.range = range;
}
public void setText(String text) {
this.text = text;
}
public String asString() {
return text;
}
@Override
public String toString() {
return f("\"%s\" <%s> %s",
getText(),
getKind(),
getRange().map(Range::toString).orElse("(?)-(?)"));
}
/**
* Used by the parser while constructing nodes. No tokens should be invalid when the parser is done.
*/
public boolean valid() {
return !invalid();
}
/**
* Used by the parser while constructing nodes. No tokens should be invalid when the parser is done.
*/
public boolean invalid() {
return this == INVALID;
}
/**
* Used by the parser while constructing nodes. No tokens should be invalid when the parser is done.
*/
public JavaToken orIfInvalid(JavaToken anotherToken) {
assertNotNull(anotherToken);
if (valid() || anotherToken.invalid()) {
return this;
}
return anotherToken;
}
public enum Category {
WHITESPACE_NO_EOL, EOL, COMMENT, IDENTIFIER, KEYWORD, LITERAL, SEPARATOR, OPERATOR;
public boolean isWhitespaceOrComment() {
return isWhitespace() || this == COMMENT;
}
public boolean isWhitespace() {
return this == WHITESPACE_NO_EOL || this == EOL;
}
public boolean isEndOfLine() {
return this == EOL;
}
public boolean isComment() {
return this == COMMENT;
}
public boolean isWhitespaceButNotEndOfLine() {
return this == WHITESPACE_NO_EOL;
}
public boolean isIdentifier() {
return this == IDENTIFIER;
}
public boolean isKeyword() {
return this == KEYWORD;
}
public boolean isLiteral() {
return this == LITERAL;
}
public boolean isSeparator() {
return this == SEPARATOR;
}
public boolean isOperator() {
return this == OPERATOR;
}
}
public JavaToken.Category getCategory() {
return TokenTypes.getCategory(kind);
}
/**
* Inserts newToken into the token list just before this token.
*/
public void insert(JavaToken newToken) {
assertNotNull(newToken);
getPreviousToken().ifPresent(p -> {
p.nextToken = newToken;
newToken.previousToken = p;
});
previousToken = newToken;
newToken.nextToken = this;
}
/**
* Inserts newToken into the token list just after this token.
*/
public void insertAfter(JavaToken newToken) {
assertNotNull(newToken);
getNextToken().ifPresent(n -> {
n.previousToken = newToken;
newToken.nextToken = n;
});
nextToken = newToken;
newToken.previousToken = this;
}
/**
* Links the tokens around the current token together, making the current token disappear from the list.
*/
public void deleteToken() {
final Optional<JavaToken> nextToken = getNextToken();
final Optional<JavaToken> previousToken = getPreviousToken();
previousToken.ifPresent(p -> p.nextToken = nextToken.orElse(null));
nextToken.ifPresent(n -> n.previousToken = previousToken.orElse(null));
}
/**
* Replaces the current token with newToken.
*/
public void replaceToken(JavaToken newToken) {
assertNotNull(newToken);
getPreviousToken().ifPresent(p -> {
p.nextToken = newToken;
newToken.previousToken = p;
});
getNextToken().ifPresent(n -> {
n.previousToken = newToken;
newToken.nextToken = n;
});
}
/**
* @return the last token in the token list.
*/
public JavaToken findLastToken() {
JavaToken current = this;
while (current.getNextToken().isPresent()) {
current = current.getNextToken().get();
}
return current;
}
/**
* @return the first token in the token list.
*/
public JavaToken findFirstToken() {
JavaToken current = this;
while (current.getPreviousToken().isPresent()) {
current = current.getPreviousToken().get();
}
return current;
}
}