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 */
020package org.sonar.colorizer;
021
022import org.sonar.channel.CodeReader;
023
024import java.util.Collections;
025import java.util.HashSet;
026import java.util.Set;
027import java.util.regex.Matcher;
028import java.util.regex.Pattern;
029
030/**
031 * Detect case-sensitive keywords
032 */
033public class KeywordsTokenizer extends NotThreadSafeTokenizer {
034
035  private final String tagBefore;
036  private final String tagAfter;
037  private boolean caseInsensitive = false;
038  private Matcher matcher;
039  private final StringBuilder tmpBuilder = new StringBuilder();
040  private static final String DEFAULT_REGEX = "[a-zA-Z_][a-zA-Z0-9_]*+";
041
042  private Set<String> keywords = new HashSet<String>();
043
044  public KeywordsTokenizer(String tagBefore, String tagAfter, Set<String> keywords) {
045    this(tagBefore, tagAfter, keywords, DEFAULT_REGEX);
046  }
047
048  public KeywordsTokenizer(String tagBefore, String tagAfter, Set<String> keywords, String regex) {
049    this.tagBefore = tagBefore;
050    this.tagAfter = tagAfter;
051    this.keywords = keywords;
052    this.matcher = Pattern.compile(regex).matcher("");
053  }
054
055  public KeywordsTokenizer(String tagBefore, String tagAfter, String... keywords) {
056    this.tagBefore = tagBefore;
057    this.tagAfter = tagAfter;
058    Collections.addAll(this.keywords, keywords);
059    this.matcher = Pattern.compile(DEFAULT_REGEX).matcher("");
060  }
061
062  @Override
063  public boolean consume(CodeReader code, HtmlCodeBuilder codeBuilder) {
064    if (code.popTo(matcher, tmpBuilder) > 0) {
065      if (isKeyword(tmpBuilder.toString())) {
066        codeBuilder.appendWithoutTransforming(tagBefore);
067        codeBuilder.append(tmpBuilder);
068        codeBuilder.appendWithoutTransforming(tagAfter);
069      } else {
070        codeBuilder.append(tmpBuilder);
071      }
072      tmpBuilder.delete(0, tmpBuilder.length());
073      return true;
074    }
075    return false;
076  }
077
078  private boolean isKeyword(String word) {
079    if ( !caseInsensitive && keywords.contains(word)) {
080      return true;
081    } else if (caseInsensitive && keywords.contains(word.toUpperCase())) {
082      return true;
083    }
084    return false;
085  }
086
087  public void setCaseInsensitive(boolean caseInsensitive) {
088    this.caseInsensitive = caseInsensitive;
089  }
090
091  @Override
092  public KeywordsTokenizer clone() {
093    KeywordsTokenizer clone = new KeywordsTokenizer(tagBefore, tagAfter, keywords, matcher.pattern().pattern());
094    clone.caseInsensitive = caseInsensitive;
095    return clone;
096  }
097}