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
|
/*
* Copyright (C) 2007-2010 Júlio Vilmar Gesser.
* Copyright (C) 2011, 2013-2015 The JavaParser Team.
*
* This file is part of JavaParser.
*
* JavaParser is free software: you can redistribute it and/or modify
* it under the terms of 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.
*
* 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.
*
* You should have received a copy of the GNU Lesser General Public License
* along with JavaParser. If not, see <http://www.gnu.org/licenses/>.
*/
package com.github.javaparser.ast.comments;
import java.io.*;
import java.nio.charset.Charset;
import java.util.*;
/**
* This parser cares exclusively about comments.
*/
public class CommentsParser {
private enum State {
CODE,
IN_LINE_COMMENT,
IN_BLOCK_COMMENT,
IN_STRING;
}
private static final int COLUMNS_PER_TAB = 4;
public CommentsCollection parse(final String source) throws IOException, UnsupportedEncodingException {
InputStream in = new ByteArrayInputStream(source.getBytes(Charset.defaultCharset()));
return parse(in, Charset.defaultCharset().name());
}
public CommentsCollection parse(final InputStream in, final String charsetName) throws IOException, UnsupportedEncodingException {
boolean lastWasASlashR = false;
BufferedReader br = new BufferedReader(new InputStreamReader(in, charsetName));
CommentsCollection comments = new CommentsCollection();
int r;
Deque prevTwoChars = new LinkedList<Character>(Arrays.asList('z','z'));
State state = State.CODE;
LineComment currentLineComment = null;
BlockComment currentBlockComment = null;
StringBuffer currentContent = null;
int currLine = 1;
int currCol = 1;
while ((r=br.read()) != -1){
char c = (char)r;
if (c=='\r'){
lastWasASlashR = true;
} else if (c=='\n'&&lastWasASlashR){
lastWasASlashR=false;
continue;
} else {
lastWasASlashR=false;
}
switch (state) {
case CODE:
if (prevTwoChars.peekLast().equals('/') && c == '/') {
currentLineComment = new LineComment();
currentLineComment.setBeginLine(currLine);
currentLineComment.setBeginColumn(currCol - 1);
state = State.IN_LINE_COMMENT;
currentContent = new StringBuffer();
} else if (prevTwoChars.peekLast().equals('/') && c == '*') {
currentBlockComment = new BlockComment();
currentBlockComment.setBeginLine(currLine);
currentBlockComment.setBeginColumn(currCol - 1);
state = State.IN_BLOCK_COMMENT;
currentContent = new StringBuffer();
} else if (c == '"') {
state = State.IN_STRING;
} else {
// nothing to do
}
break;
case IN_LINE_COMMENT:
if (c=='\n' || c=='\r'){
currentLineComment.setContent(currentContent.toString());
currentLineComment.setEndLine(currLine);
currentLineComment.setEndColumn(currCol);
comments.addComment(currentLineComment);
state = State.CODE;
} else {
currentContent.append(c);
}
break;
case IN_BLOCK_COMMENT:
if (prevTwoChars.peekLast().equals('*') && c=='/' && !prevTwoChars.peekFirst().equals('/')){
// delete last character
String content = currentContent.deleteCharAt(currentContent.toString().length()-1).toString();
if (content.startsWith("*")){
JavadocComment javadocComment = new JavadocComment();
javadocComment.setContent(content.substring(1));
javadocComment.setBeginLine(currentBlockComment.getBeginLine());
javadocComment.setBeginColumn(currentBlockComment.getBeginColumn());
javadocComment.setEndLine(currLine);
javadocComment.setEndColumn(currCol+1);
comments.addComment(javadocComment);
} else {
currentBlockComment.setContent(content);
currentBlockComment.setEndLine(currLine);
currentBlockComment.setEndColumn(currCol+1);
comments.addComment(currentBlockComment);
}
state = State.CODE;
} else {
currentContent.append(c=='\r'?'\n':c);
}
break;
case IN_STRING:
if (!prevTwoChars.peekLast().equals('\\') && c == '"') {
state = State.CODE;
}
break;
default:
throw new RuntimeException("Unexpected");
}
switch (c){
case '\n':
case '\r':
currLine+=1;
currCol = 1;
break;
case '\t':
currCol+=COLUMNS_PER_TAB;
break;
default:
currCol+=1;
}
prevTwoChars.remove();
prevTwoChars.add(c);
}
if (state==State.IN_LINE_COMMENT){
currentLineComment.setContent(currentContent.toString());
currentLineComment.setEndLine(currLine);
currentLineComment.setEndColumn(currCol);
comments.addComment(currentLineComment);
}
return comments;
}
}
|
