001    /*
002     * Sonar, open source software quality management tool.
003     * Copyright (C) 2008-2012 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    package org.sonar.squid.recognizer;
022    
023    import java.util.Arrays;
024    import java.util.List;
025    import java.util.Locale;
026    import java.util.StringTokenizer;
027    
028    public class KeywordsDetector extends Detector {
029    
030      private List<String> keywords;
031      private boolean toUpperCase = false;
032    
033      public KeywordsDetector(double probability, String... keywords) {
034        super(probability);
035        this.keywords = Arrays.asList(keywords);
036      }
037    
038      public KeywordsDetector(double probability, boolean toUpperCase, String... keywords) {
039        this(probability, keywords);
040        this.toUpperCase = toUpperCase;
041      }
042    
043      @Override
044      public int scan(String line) {
045        int matchers = 0;
046        if (toUpperCase) {
047          line = line.toUpperCase(Locale.getDefault());
048        }
049        StringTokenizer tokenizer = new StringTokenizer(line, " \t(),{}");
050        while (tokenizer.hasMoreTokens()) {
051          String word = tokenizer.nextToken();
052          if (keywords.contains(word)) {
053            matchers++;
054          }
055        }
056        return matchers;
057      }
058    }