source: main/trunk/greenstone2/common-src/indexers/lucene-gs/src/org/greenstone/LuceneWrapper4/GS2StandardAnalyzer.java@ 29148

package org.greenstone.LuceneWrapper4;

/**
 * Licensed to the Apache Software Foundation (ASF) under one or more
 * contributor license agreements.  See the NOTICE file distributed with
 * this work for additional information regarding copyright ownership.
 * The ASF licenses this file to You under the Apache License, Version 2.0
 * (the "License"); you may not use this file except in compliance with
 * the License.  You may obtain a copy of the License at
 *
 *     http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */

// Modified so the class is *not* final
//
// This is an interim measure.  
//
// We should rewrite GS2Analyzer so it inherits directly from
// StopwordAnalyzeBase and uses ASCIIFoldingFilter rather than
// ISOLatin1AccentFilter as the latter is deprecated and the former is
// a superset


import org.apache.lucene.analysis.*;
import org.apache.lucene.util.Version;

import org.apache.lucene.analysis.core.StopAnalyzer;
import org.apache.lucene.analysis.core.*; // StopFilter, StandardFilter, LowerCaseFilter
import org.apache.lucene.analysis.standard.StandardFilter;
import org.apache.lucene.analysis.standard.StandardTokenizer;
import org.apache.lucene.analysis.util.*;


import java.io.File;
import java.io.FileReader;
import java.io.IOException;
import java.io.Reader;
import java.util.Set;

/**
 * Filters {@link StandardTokenizer} with {@link StandardFilter}, {@link
 * LowerCaseFilter} and {@link StopFilter}, using a list of
 * English stop words.
 *
 * <a name="version"/>
 * <p>You must specify the required {@link Version}
 * compatibility when creating StandardAnalyzer:
 * <ul>
 *   <li> As of 3.1, StandardTokenizer implements Unicode text segmentation,
 *        and StopFilter correctly handles Unicode 4.0 supplementary characters
 *        in stopwords.  {@link ClassicTokenizer} and {@link ClassicAnalyzer} 
 *        are the pre-3.1 implementations of StandardTokenizer and
 *        StandardAnalyzer.
 *   <li> As of 2.9, StopFilter preserves position increments
 *   <li> As of 2.4, Tokens incorrectly identified as acronyms
 *        are corrected (see <a href="https://issues.apache.org/jira/browse/LUCENE-1068">LUCENE-1068</a>)
 * </ul>
 */
public class GS2StandardAnalyzer extends StopwordAnalyzerBase {

  /** Default maximum allowed token length */
  public static final int DEFAULT_MAX_TOKEN_LENGTH = 255;

  protected int maxTokenLength = DEFAULT_MAX_TOKEN_LENGTH;

  /**
   * Specifies whether deprecated acronyms should be replaced with HOST type.
   * See {@linkplain "https://issues.apache.org/jira/browse/LUCENE-1068"}
   */
  protected final boolean replaceInvalidAcronym;

  /** An unmodifiable set containing some common English words that are usually not
  useful for searching. */
  public static final CharArraySet STOP_WORDS_SET = StopAnalyzer.ENGLISH_STOP_WORDS_SET; 

  /** Builds an analyzer with the given stop words.
   * @param matchVersion Lucene version to match See {@link
   * <a href="#version">above</a>}
   * @param stopWords stop words */
  public GS2StandardAnalyzer(Version matchVersion, CharArraySet stopWords) {
      // Creates a CharArraySet from a file.
      //protected static CharArraySet   loadStopwordSet(File stopwords, Version matchVersion)

    super(matchVersion, stopWords);
    replaceInvalidAcronym = true;//= matchVersion.onOrAfter(Version.LUCENE_24);
  }

  /** Builds an analyzer with the default stop words ({@link
   * #STOP_WORDS_SET}).
   * @param matchVersion Lucene version to match See {@link
   * <a href="#version">above</a>}
   */
  public GS2StandardAnalyzer(Version matchVersion) {
    this(matchVersion, STOP_WORDS_SET);
  }

  /** Builds an analyzer with the stop words from the given file.
   * @see WordlistLoader#getWordSet(File)
   * @param matchVersion Lucene version to match See {@link
   * <a href="#version">above</a>}
   * @param stopwords File to read stop words from */
  public GS2StandardAnalyzer(Version matchVersion, File stopwords) throws IOException {
      this(matchVersion, WordlistLoader.getWordSet(new FileReader(stopwords), matchVersion));
  }

  /** Builds an analyzer with the stop words from the given reader.
   * @see WordlistLoader#getWordSet(Reader)
   * @param matchVersion Lucene version to match See {@link
   * <a href="#version">above</a>}
   * @param stopwords Reader to read stop words from */
  public GS2StandardAnalyzer(Version matchVersion, Reader stopwords) throws IOException {
      this(matchVersion, WordlistLoader.getWordSet(stopwords, matchVersion));
  }

  /**
   * Set maximum allowed token length.  If a token is seen
   * that exceeds this length then it is discarded.  This
   * setting only takes effect the next time tokenStream or
   * reusableTokenStream is called.
   */
  public void setMaxTokenLength(int length) {
    maxTokenLength = length;
  }
    
  /**
   * @see #setMaxTokenLength
   */
  public int getMaxTokenLength() {
    return maxTokenLength;
  }

  @Override
  protected TokenStreamComponents createComponents(final String fieldName, final Reader reader) {
    final StandardTokenizer src = new StandardTokenizer(matchVersion, reader);
    src.setMaxTokenLength(maxTokenLength);
    //src.setReplaceInvalidAcronym(replaceInvalidAcronym); // now true by default, see http://lucene.apache.org/core/3_0_3/api/all/org/apache/lucene/analysis/standard/StandardTokenizer.html
    TokenStream tok = new StandardFilter(matchVersion, src);
    tok = new LowerCaseFilter(matchVersion, tok);
    tok = new StopFilter(matchVersion, tok, stopwords);
    return new TokenStreamComponents(src, tok) {
      @Override
      protected void setReader(final Reader reader) throws IOException {
      // previously called reset(Reader), now called setReader(Reader), but with mostly the same method description:
      // https://lucene.apache.org/core/3_6_0/api/all/org/apache/lucene/analysis/ReusableAnalyzerBase.TokenStreamComponents.html
      // http://lucene.apache.org/core/4_8_1/core/org/apache/lucene/analysis/Analyzer.TokenStreamComponents.html
      // New method should throw an exception, not return false if unable to reset

        src.setMaxTokenLength(GS2StandardAnalyzer.this.maxTokenLength);
        super.setReader(reader);
      }
    };
  }
}