001    /*
002     * Sonar, open source software quality management tool.
003     * Copyright (C) 2009 SonarSource SA
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    package org.sonar.squid.recognizer;
021    
022    import java.util.Arrays;
023    import java.util.List;
024    import java.util.StringTokenizer;
025    
026    public class KeywordsDetector extends Detector {
027    
028      private List<String> keywords;
029      private boolean      toUpperCase = false;
030    
031      public KeywordsDetector(double probability, String... keywords) {
032        super(probability);
033        this.keywords = Arrays.asList(keywords);
034      }
035    
036      public KeywordsDetector(double probability, boolean toUpperCase, String... keywords) {
037        this(probability, keywords);
038        this.toUpperCase = toUpperCase;
039      }
040    
041      @Override
042      public int scan(String line) {
043        int matchers = 0;
044        if (toUpperCase) {
045          line = line.toUpperCase();
046        }
047        StringTokenizer tokenizer = new StringTokenizer(line, " \t(),{}");
048        while (tokenizer.hasMoreTokens()) {
049          String word = tokenizer.nextToken();
050          if (keywords.contains(word)) {
051            matchers++;
052          }
053        }
054        return matchers;
055      }
056    }