001////////////////////////////////////////////////////////////////////////////////
002// checkstyle: Checks Java source code for adherence to a set of rules.
003// Copyright (C) 2001-2021 the original author or authors.
004//
005// This library is free software; you can redistribute it and/or
006// modify it under the terms of the GNU Lesser General Public
007// License as published by the Free Software Foundation; either
008// version 2.1 of the License, or (at your option) any later version.
009//
010// This library is distributed in the hope that it will be useful,
011// but WITHOUT ANY WARRANTY; without even the implied warranty of
012// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
013// Lesser General Public License for more details.
014//
015// You should have received a copy of the GNU Lesser General Public
016// License along with this library; if not, write to the Free Software
017// Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
018////////////////////////////////////////////////////////////////////////////////
019
020package com.puppycrawl.tools.checkstyle.checks.javadoc.utils;
021
022import java.util.ArrayList;
023import java.util.List;
024import java.util.regex.Matcher;
025import java.util.regex.Pattern;
026
027import com.puppycrawl.tools.checkstyle.api.LineColumn;
028
029/**
030 * Tools for extracting inline tags from Javadoc comments.
031 *
032 */
033public final class InlineTagUtil {
034
035    /**
036     * Inline tag pattern.
037     */
038    private static final Pattern INLINE_TAG_PATTERN = Pattern.compile(
039            "\\{@(\\p{Alpha}+)\\b(.*?)}", Pattern.DOTALL);
040
041    /** Pattern to recognize leading "*" characters in Javadoc. */
042    private static final Pattern JAVADOC_PREFIX_PATTERN = Pattern.compile(
043        "^\\s*\\*", Pattern.MULTILINE);
044
045    /** Pattern matching whitespace, used by {@link InlineTagUtil#collapseWhitespace(String)}. */
046    private static final Pattern WHITESPACE_PATTERN = Pattern.compile("\\s+");
047
048    /** Pattern matching a newline. */
049    private static final Pattern NEWLINE_PATTERN = Pattern.compile("\\n");
050
051    /** Line feed character. */
052    private static final String LINE_FEED = "\n";
053
054    /** Carriage return character. */
055    private static final String CARRIAGE_RETURN = "\r";
056
057    /** Prevent instantiation. */
058    private InlineTagUtil() {
059    }
060
061    /**
062     * Extract inline Javadoc tags from the given comment.
063     *
064     * @param lines The Javadoc comment (as lines).
065     * @return The extracted inline Javadoc tags.
066     * @throws IllegalArgumentException when comment lines contain newlines
067     */
068    public static List<TagInfo> extractInlineTags(String... lines) {
069        for (String line : lines) {
070            if (line.contains(LINE_FEED) || line.contains(CARRIAGE_RETURN)) {
071                throw new IllegalArgumentException("comment lines cannot contain newlines");
072            }
073        }
074
075        final String commentText = convertLinesToString(lines);
076        final Matcher inlineTagMatcher = INLINE_TAG_PATTERN.matcher(commentText);
077
078        final List<TagInfo> tags = new ArrayList<>();
079
080        while (inlineTagMatcher.find()) {
081            final String tagName = inlineTagMatcher.group(1);
082
083            // Remove the leading asterisks (in case the tag spans a line) and collapse
084            // the whitespace.
085            String matchedTagValue = inlineTagMatcher.group(2);
086            matchedTagValue = removeLeadingJavaDoc(matchedTagValue);
087            matchedTagValue = collapseWhitespace(matchedTagValue);
088
089            final String tagValue = matchedTagValue;
090
091            final int startIndex = inlineTagMatcher.start(1);
092            final LineColumn position = getLineColumnOfIndex(commentText,
093                // correct start index offset
094                startIndex - 1);
095
096            tags.add(new TagInfo(tagName, tagValue, position));
097        }
098
099        return tags;
100    }
101
102    /**
103     * Convert array of string to single String.
104     *
105     * @param lines A number of lines, in order.
106     * @return The lines, joined together with newlines, as a single string.
107     */
108    private static String convertLinesToString(String... lines) {
109        final StringBuilder builder = new StringBuilder(1024);
110        for (String line : lines) {
111            builder.append(line);
112            builder.append(LINE_FEED);
113        }
114        return builder.toString();
115    }
116
117    /**
118     * Get LineColumn from string till index.
119     *
120     * @param source Source string.
121     * @param index An index into the string.
122     * @return A position in the source representing what line and column that index appears on.
123     */
124    private static LineColumn getLineColumnOfIndex(String source, int index) {
125        final String precedingText = source.subSequence(0, index).toString();
126        final String[] precedingLines = NEWLINE_PATTERN.split(precedingText);
127        final String lastLine = precedingLines[precedingLines.length - 1];
128        return new LineColumn(precedingLines.length, lastLine.length());
129    }
130
131    /**
132     * Collapse whitespaces.
133     *
134     * @param str Source string.
135     * @return The given string with all whitespace collapsed.
136     */
137    private static String collapseWhitespace(String str) {
138        final Matcher matcher = WHITESPACE_PATTERN.matcher(str);
139        return matcher.replaceAll(" ").trim();
140    }
141
142    /**
143     * Remove leading JavaDoc.
144     *
145     * @param source A string to remove leading Javadoc from.
146     * @return The given string with leading Javadoc "*" characters from each line removed.
147     */
148    private static String removeLeadingJavaDoc(String source) {
149        final Matcher matcher = JAVADOC_PREFIX_PATTERN.matcher(source);
150        return matcher.replaceAll("");
151    }
152
153}