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
|
/*
* 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 com.github.javaparser.ast.comments.JavadocComment;
import com.github.javaparser.javadoc.Javadoc;
import com.github.javaparser.javadoc.JavadocBlockTag;
import com.github.javaparser.javadoc.description.JavadocDescription;
import java.util.Arrays;
import java.util.Collections;
import java.util.List;
import java.util.regex.Pattern;
import java.util.stream.Collectors;
import static com.github.javaparser.utils.Utils.*;
import static com.github.javaparser.utils.Utils.nextWord;
/**
* The class responsible for parsing the content of JavadocComments and produce JavadocDocuments.
*/
class JavadocParser {
private static String BLOCK_TAG_PREFIX = "@";
private static Pattern BLOCK_PATTERN = Pattern.compile("^" + BLOCK_TAG_PREFIX, Pattern.MULTILINE);
public static Javadoc parse(JavadocComment comment) {
return parse(comment.getContent());
}
public static Javadoc parse(String commentContent) {
List<String> cleanLines = cleanLines(normalizeEolInTextBlock(commentContent, EOL));
int indexOfFirstBlockTag = cleanLines.stream()
.filter(JavadocParser::isABlockLine)
.map(cleanLines::indexOf)
.findFirst()
.orElse(-1);
List<String> blockLines;
String descriptionText;
if (indexOfFirstBlockTag == -1) {
descriptionText = trimRight(String.join(EOL, cleanLines));
blockLines = Collections.emptyList();
} else {
descriptionText = trimRight(String.join(EOL, cleanLines.subList(0, indexOfFirstBlockTag)));
//Combine cleaned lines, but only starting with the first block tag till the end
//In this combined string it is easier to handle multiple lines which actually belong together
String tagBlock = cleanLines.subList(indexOfFirstBlockTag, cleanLines.size())
.stream()
.collect(Collectors.joining(EOL));
//Split up the entire tag back again, considering now that some lines belong to the same block tag.
//The pattern splits the block at each new line starting with the '@' symbol, thus the symbol
//then needs to be added again so that the block parsers handles everything correctly.
blockLines = BLOCK_PATTERN
.splitAsStream(tagBlock)
.filter(STRING_NOT_EMPTY)
.map(s -> BLOCK_TAG_PREFIX + s)
.collect(Collectors.toList());
}
Javadoc document = new Javadoc(JavadocDescription.parseText(descriptionText));
blockLines.forEach(l -> document.addBlockTag(parseBlockTag(l)));
return document;
}
private static JavadocBlockTag parseBlockTag(String line) {
line = line.trim().substring(1);
String tagName = nextWord(line);
String rest = line.substring(tagName.length()).trim();
return new JavadocBlockTag(tagName, rest);
}
private static boolean isABlockLine(String line) {
return line.trim().startsWith(BLOCK_TAG_PREFIX);
}
private static String trimRight(String string) {
while (!string.isEmpty() && Character.isWhitespace(string.charAt(string.length() - 1))) {
string = string.substring(0, string.length() - 1);
}
return string;
}
private static List<String> cleanLines(String content) {
String[] lines = content.split(EOL);
List<String> cleanedLines = Arrays.stream(lines).map(l -> {
int asteriskIndex = startsWithAsterisk(l);
if (asteriskIndex == -1) {
return l;
} else {
// if a line starts with space followed by an asterisk drop to the asterisk
// if there is a space immediately after the asterisk drop it also
if (l.length() > (asteriskIndex + 1)) {
char c = l.charAt(asteriskIndex + 1);
if (c == ' ' || c == '\t') {
return l.substring(asteriskIndex + 2);
}
}
return l.substring(asteriskIndex + 1);
}
}).collect(Collectors.toList());
// lines containing only whitespace are normalized to empty lines
cleanedLines = cleanedLines.stream().map(l -> l.trim().isEmpty() ? "" : l).collect(Collectors.toList());
// if the first starts with a space, remove it
if (!cleanedLines.get(0).isEmpty() && (cleanedLines.get(0).charAt(0) == ' ' || cleanedLines.get(0).charAt(0) == '\t')) {
cleanedLines.set(0, cleanedLines.get(0).substring(1));
}
// drop empty lines at the beginning and at the end
while (cleanedLines.size() > 0 && cleanedLines.get(0).trim().isEmpty()) {
cleanedLines = cleanedLines.subList(1, cleanedLines.size());
}
while (cleanedLines.size() > 0 && cleanedLines.get(cleanedLines.size() - 1).trim().isEmpty()) {
cleanedLines = cleanedLines.subList(0, cleanedLines.size() - 1);
}
return cleanedLines;
}
// Visible for testing
static int startsWithAsterisk(String line) {
if (line.startsWith("*")) {
return 0;
} else if ((line.startsWith(" ") || line.startsWith("\t")) && line.length() > 1) {
int res = startsWithAsterisk(line.substring(1));
if (res == -1) {
return -1;
} else {
return 1 + res;
}
} else {
return -1;
}
}
}
|
