001 /*
002 * Sonar, open source software quality management tool.
003 * Copyright (C) 2008-2011 SonarSource
004 * mailto:contact AT sonarsource DOT com
005 *
006 * Sonar is free software; you can redistribute it and/or
007 * modify it under the terms of the GNU Lesser General Public
008 * License as published by the Free Software Foundation; either
009 * version 3 of the License, or (at your option) any later version.
010 *
011 * Sonar is distributed in the hope that it will be useful,
012 * but WITHOUT ANY WARRANTY; without even the implied warranty of
013 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
014 * Lesser General Public License for more details.
015 *
016 * You should have received a copy of the GNU Lesser General Public
017 * License along with Sonar; if not, write to the Free Software
018 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02
019 */
020
021 /**
022 * BSD-style license; for more info see http://pmd.sourceforge.net/license.html
023 */
024 package org.sonar.duplications.cpd;
025
026 import net.sourceforge.pmd.cpd.*;
027 import net.sourceforge.pmd.util.FileFinder;
028
029 import java.io.File;
030 import java.io.FileNotFoundException;
031 import java.io.IOException;
032 import java.util.HashMap;
033 import java.util.Iterator;
034 import java.util.List;
035 import java.util.Map;
036
037 public class CPD {
038
039 private Map<String, SourceCode> source = new HashMap<String, SourceCode>();
040 private CPDListener listener = new CPDNullListener();
041 private Tokens tokens = new Tokens();
042 private int minimumTileSize;
043 private MatchAlgorithm matchAlgorithm;
044 private Language language;
045 private boolean loadSourceCodeSlices = true;
046 private String encoding = System.getProperty("file.encoding");
047
048 public CPD(int minimumTileSize, Language language) {
049 TokenEntry.clearImages(); // workaround for bug 1947823
050 this.minimumTileSize = minimumTileSize;
051 this.language = language;
052 }
053
054 public void setCpdListener(CPDListener cpdListener) {
055 this.listener = cpdListener;
056 }
057
058 public void setEncoding(String encoding) {
059 this.encoding = encoding;
060 }
061
062 public void setLoadSourceCodeSlices(boolean loadSourceCodeSlices) {
063 this.loadSourceCodeSlices = loadSourceCodeSlices;
064 }
065
066 public void go() {
067 TokenEntry.clearImages();
068 matchAlgorithm = new MatchAlgorithm(source, tokens, minimumTileSize, listener);
069 matchAlgorithm.setLoadSourceCodeSlices(loadSourceCodeSlices);
070 matchAlgorithm.findMatches();
071 }
072
073 public Iterator<Match> getMatches() {
074 return matchAlgorithm.matches();
075 }
076
077 public void add(File file) throws IOException {
078 add(1, file);
079 }
080
081 public void addAllInDirectory(String dir) throws IOException {
082 addDirectory(dir, false);
083 }
084
085 public void addRecursively(String dir) throws IOException {
086 addDirectory(dir, true);
087 }
088
089 public void add(List<File> files) throws IOException {
090 for (File f : files) {
091 add(files.size(), f);
092 }
093 }
094
095 private void addDirectory(String dir, boolean recurse) throws IOException {
096 if (!(new File(dir)).exists()) {
097 throw new FileNotFoundException("Couldn't find directory " + dir);
098 }
099 FileFinder finder = new FileFinder();
100 // TODO - could use SourceFileSelector here
101 add(finder.findFilesFrom(dir, language.getFileFilter(), recurse));
102 }
103
104 private void add(int fileCount, File file) throws IOException {
105 if (!file.getCanonicalPath().equals(new File(file.getAbsolutePath()).getCanonicalPath())) {
106 System.out.println("Skipping " + file + " since it appears to be a symlink");
107 return;
108 }
109
110 listener.addedFile(fileCount, file);
111 SourceCode sourceCode = new SourceCode(new FileCodeLoaderWithoutCache(file, encoding));
112 language.getTokenizer().tokenize(sourceCode, tokens);
113 source.put(sourceCode.getFileName(), sourceCode);
114 }
115
116
117 }