| 1 | /* |
|---|---|
| 2 | * Copyright (C) 2007-2010 Júlio Vilmar Gesser. |
| 3 | * Copyright (C) 2011, 2013-2020 The JavaParser Team. |
| 4 | * |
| 5 | * This file is part of JavaParser. |
| 6 | * |
| 7 | * JavaParser can be used either under the terms of |
| 8 | * a) the GNU Lesser General Public License as published by |
| 9 | * the Free Software Foundation, either version 3 of the License, or |
| 10 | * (at your option) any later version. |
| 11 | * b) the terms of the Apache License |
| 12 | * |
| 13 | * You should have received a copy of both licenses in LICENCE.LGPL and |
| 14 | * LICENCE.APACHE. Please refer to those files for details. |
| 15 | * |
| 16 | * JavaParser is distributed in the hope that it will be useful, |
| 17 | * but WITHOUT ANY WARRANTY; without even the implied warranty of |
| 18 | * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
| 19 | * GNU Lesser General Public License for more details. |
| 20 | */ |
| 21 | |
| 22 | package com.github.javaparser; |
| 23 | |
| 24 | import com.github.javaparser.ast.comments.JavadocComment; |
| 25 | import com.github.javaparser.javadoc.Javadoc; |
| 26 | import com.github.javaparser.javadoc.JavadocBlockTag; |
| 27 | import com.github.javaparser.javadoc.description.JavadocDescription; |
| 28 | import java.util.Arrays; |
| 29 | import java.util.Collections; |
| 30 | import java.util.List; |
| 31 | import java.util.regex.Pattern; |
| 32 | import java.util.stream.Collectors; |
| 33 | |
| 34 | import static com.github.javaparser.utils.Utils.*; |
| 35 | |
| 36 | /** |
| 37 | * The class responsible for parsing the content of JavadocComments and producing JavadocDocuments. |
| 38 | * <a href="https://docs.oracle.com/javase/1.5.0/docs/tooldocs/windows/javadoc.html">The Javadoc specification.</a> |
| 39 | */ |
| 40 | class JavadocParser { |
| 41 | |
| 42 | private static String BLOCK_TAG_PREFIX = "@"; |
| 43 | private static Pattern BLOCK_PATTERN = Pattern.compile("^\\s*" + BLOCK_TAG_PREFIX, Pattern.MULTILINE); |
| 44 | |
| 45 | public static Javadoc parse(JavadocComment comment) { |
| 46 | return parse(comment.getContent()); |
| 47 | } |
| 48 | |
| 49 | public static Javadoc parse(String commentContent) { |
| 50 | List<String> cleanLines = cleanLines(normalizeEolInTextBlock(commentContent, SYSTEM_EOL)); |
| 51 | int indexOfFirstBlockTag = cleanLines.stream() |
| 52 | .filter(JavadocParser::isABlockLine) |
| 53 | .map(cleanLines::indexOf) |
| 54 | .findFirst() |
| 55 | .orElse(-1); |
| 56 | List<String> blockLines; |
| 57 | String descriptionText; |
| 58 | if (indexOfFirstBlockTag == -1) { |
| 59 | descriptionText = trimRight(String.join(SYSTEM_EOL, cleanLines)); |
| 60 | blockLines = Collections.emptyList(); |
| 61 | } else { |
| 62 | descriptionText = trimRight(String.join(SYSTEM_EOL, cleanLines.subList(0, indexOfFirstBlockTag))); |
| 63 | |
| 64 | //Combine cleaned lines, but only starting with the first block tag till the end |
| 65 | //In this combined string it is easier to handle multiple lines which actually belong together |
| 66 | String tagBlock = cleanLines.subList(indexOfFirstBlockTag, cleanLines.size()) |
| 67 | .stream() |
| 68 | .collect(Collectors.joining(SYSTEM_EOL)); |
| 69 | |
| 70 | //Split up the entire tag back again, considering now that some lines belong to the same block tag. |
| 71 | //The pattern splits the block at each new line starting with the '@' symbol, thus the symbol |
| 72 | //then needs to be added again so that the block parsers handles everything correctly. |
| 73 | blockLines = BLOCK_PATTERN |
| 74 | .splitAsStream(tagBlock) |
| 75 | .filter(s1 -> !s1.isEmpty()) |
| 76 | .map(s -> BLOCK_TAG_PREFIX + s) |
| 77 | .collect(Collectors.toList()); |
| 78 | } |
| 79 | Javadoc document = new Javadoc(JavadocDescription.parseText(descriptionText)); |
| 80 | blockLines.forEach(l -> document.addBlockTag(parseBlockTag(l))); |
| 81 | return document; |
| 82 | } |
| 83 | |
| 84 | private static JavadocBlockTag parseBlockTag(String line) { |
| 85 | line = line.trim().substring(1); |
| 86 | String tagName = nextWord(line); |
| 87 | String rest = line.substring(tagName.length()).trim(); |
| 88 | return new JavadocBlockTag(tagName, rest); |
| 89 | } |
| 90 | |
| 91 | private static boolean isABlockLine(String line) { |
| 92 | return line.trim().startsWith(BLOCK_TAG_PREFIX); |
| 93 | } |
| 94 | |
| 95 | private static String trimRight(String string) { |
| 96 | while (!string.isEmpty() && Character.isWhitespace(string.charAt(string.length() - 1))) { |
| 97 | string = string.substring(0, string.length() - 1); |
| 98 | } |
| 99 | return string; |
| 100 | } |
| 101 | |
| 102 | private static List<String> cleanLines(String content) { |
| 103 | String[] lines = content.split(SYSTEM_EOL); |
| 104 | if (lines.length == 0) { |
| 105 | return Collections.emptyList(); |
| 106 | } |
| 107 | |
| 108 | List<String> cleanedLines = Arrays.stream(lines).map(l -> { |
| 109 | int asteriskIndex = startsWithAsterisk(l); |
| 110 | if (asteriskIndex == -1) { |
| 111 | return l; |
| 112 | } else { |
| 113 | // if a line starts with space followed by an asterisk drop to the asterisk |
| 114 | // if there is a space immediately after the asterisk drop it also |
| 115 | if (l.length() > (asteriskIndex + 1)) { |
| 116 | |
| 117 | char c = l.charAt(asteriskIndex + 1); |
| 118 | if (c == ' ' || c == '\t') { |
| 119 | return l.substring(asteriskIndex + 2); |
| 120 | } |
| 121 | } |
| 122 | return l.substring(asteriskIndex + 1); |
| 123 | } |
| 124 | }).collect(Collectors.toList()); |
| 125 | // lines containing only whitespace are normalized to empty lines |
| 126 | cleanedLines = cleanedLines.stream().map(l -> l.trim().isEmpty() ? "" : l).collect(Collectors.toList()); |
| 127 | // if the first starts with a space, remove it |
| 128 | if (!cleanedLines.get(0).isEmpty() && (cleanedLines.get(0).charAt(0) == ' ' || cleanedLines.get(0).charAt(0) == '\t')) { |
| 129 | cleanedLines.set(0, cleanedLines.get(0).substring(1)); |
| 130 | } |
| 131 | // drop empty lines at the beginning and at the end |
| 132 | while (cleanedLines.size() > 0 && cleanedLines.get(0).trim().isEmpty()) { |
| 133 | cleanedLines = cleanedLines.subList(1, cleanedLines.size()); |
| 134 | } |
| 135 | while (cleanedLines.size() > 0 && cleanedLines.get(cleanedLines.size() - 1).trim().isEmpty()) { |
| 136 | cleanedLines = cleanedLines.subList(0, cleanedLines.size() - 1); |
| 137 | } |
| 138 | return cleanedLines; |
| 139 | } |
| 140 | |
| 141 | // Visible for testing |
| 142 | static int startsWithAsterisk(String line) { |
| 143 | if (line.startsWith("*")) { |
| 144 | return 0; |
| 145 | } else if ((line.startsWith(" ") || line.startsWith("\t")) && line.length() > 1) { |
| 146 | int res = startsWithAsterisk(line.substring(1)); |
| 147 | if (res == -1) { |
| 148 | return -1; |
| 149 | } else { |
| 150 | return 1 + res; |
| 151 | } |
| 152 | } else { |
| 153 | return -1; |
| 154 | } |
| 155 | } |
| 156 | } |
| 157 |
Members