org.apache.lucene.analysis.standard.StandardTokenizer Maven / Gradle / Ivy

Go to download
Show more of this group Show more artifacts with this name
Show all versions of aem-sdk-api Show documentation
The Adobe Experience Manager SDK
There is a newer version: 2024.11.18751.20241128T090041Z-241100
/*
 * 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.
 */

package org.apache.lucene.analysis.standard;

import java.io.IOException;
import java.io.Reader;

import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.standard.std31.StandardTokenizerImpl31;
import org.apache.lucene.analysis.standard.std34.StandardTokenizerImpl34;
import org.apache.lucene.analysis.standard.std40.StandardTokenizerImpl40;
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.apache.lucene.analysis.tokenattributes.OffsetAttribute;
import org.apache.lucene.analysis.tokenattributes.PositionIncrementAttribute;
import org.apache.lucene.analysis.tokenattributes.TypeAttribute;
import org.apache.lucene.util.Version;

/** A grammar-based tokenizer constructed with JFlex.
 * 
 * As of Lucene version 3.1, this class implements the Word Break rules from the
 * Unicode Text Segmentation algorithm, as specified in 
 * Unicode Standard Annex #29.
 * 

 * 
Many applications have specific tokenizer needs.  If this tokenizer does
 * not suit your application, please consider copying this source code
 * directory to your project and maintaining your own grammar-based tokenizer.
 *
 * 
 * 
You must specify the required {@link Version}
 * compatibility when creating StandardTokenizer:
 * 

 *    As of 3.4, Hiragana and Han characters are no longer wrongly split
 *   from their combining characters. If you use a previous version number,
 *   you get the exact broken behavior for backwards compatibility.
 *   
 As of 3.1, StandardTokenizer implements Unicode text segmentation.
 *   If you use a previous version number, you get the exact behavior of
 *   {@link ClassicTokenizer} for backwards compatibility.
 * 

 */

public final class StandardTokenizer extends Tokenizer {
  /** A private instance of the JFlex-constructed scanner */
  private StandardTokenizerInterface scanner;

  public static final int ALPHANUM          = 0;
  /** @deprecated (3.1) */
  @Deprecated
  public static final int APOSTROPHE        = 1;
  /** @deprecated (3.1) */
  @Deprecated
  public static final int ACRONYM           = 2;
  /** @deprecated (3.1) */
  @Deprecated
  public static final int COMPANY           = 3;
  public static final int EMAIL             = 4;
  /** @deprecated (3.1) */
  @Deprecated
  public static final int HOST              = 5;
  public static final int NUM               = 6;
  /** @deprecated (3.1) */
  @Deprecated
  public static final int CJ                = 7;

  /** @deprecated (3.1) */
  @Deprecated
  public static final int ACRONYM_DEP       = 8;

  public static final int SOUTHEAST_ASIAN = 9;
  public static final int IDEOGRAPHIC = 10;
  public static final int HIRAGANA = 11;
  public static final int KATAKANA = 12;
  public static final int HANGUL = 13;
  
  /** String token types that correspond to token type int constants */
  public static final String [] TOKEN_TYPES = new String [] {
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    "",
    ""
  };
  
  private int skippedPositions;

  private int maxTokenLength = StandardAnalyzer.DEFAULT_MAX_TOKEN_LENGTH;

  /** Set the max allowed token length.  Any token longer
   *  than this is skipped. */
  public void setMaxTokenLength(int length) {
    this.maxTokenLength = length;
  }

  /** @see #setMaxTokenLength */
  public int getMaxTokenLength() {
    return maxTokenLength;
  }

  /**
   * Creates a new instance of the {@link org.apache.lucene.analysis.standard.StandardTokenizer}.  Attaches
   * the input to the newly created JFlex scanner.
   *
   * @param input The input reader
   *
   * See http://issues.apache.org/jira/browse/LUCENE-1068
   */
  public StandardTokenizer(Version matchVersion, Reader input) {
    super(input);
    init(matchVersion);
  }

  /**
   * Creates a new StandardTokenizer with a given {@link org.apache.lucene.util.AttributeSource.AttributeFactory} 
   */
  public StandardTokenizer(Version matchVersion, AttributeFactory factory, Reader input) {
    super(factory, input);
    init(matchVersion);
  }

  private final void init(Version matchVersion) {
    if (matchVersion.onOrAfter(Version.LUCENE_47)) {
      this.scanner = new StandardTokenizerImpl(input);
    } else if (matchVersion.onOrAfter(Version.LUCENE_40)) {
      this.scanner = new StandardTokenizerImpl40(input);
    } else if (matchVersion.onOrAfter(Version.LUCENE_34)) {
      this.scanner = new StandardTokenizerImpl34(input);
    } else if (matchVersion.onOrAfter(Version.LUCENE_31)) {
      this.scanner = new StandardTokenizerImpl31(input);
    } else {
      this.scanner = new ClassicTokenizerImpl(input);
    }
  }

  // this tokenizer generates three attributes:
  // term offset, positionIncrement and type
  private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
  private final OffsetAttribute offsetAtt = addAttribute(OffsetAttribute.class);
  private final PositionIncrementAttribute posIncrAtt = addAttribute(PositionIncrementAttribute.class);
  private final TypeAttribute typeAtt = addAttribute(TypeAttribute.class);

  /*
   * (non-Javadoc)
   *
   * @see org.apache.lucene.analysis.TokenStream#next()
   */
  @Override
  public final boolean incrementToken() throws IOException {
    clearAttributes();
    skippedPositions = 0;

    while(true) {
      int tokenType = scanner.getNextToken();

      if (tokenType == StandardTokenizerInterface.YYEOF) {
        return false;
      }

      if (scanner.yylength() <= maxTokenLength) {
        posIncrAtt.setPositionIncrement(skippedPositions+1);
        scanner.getText(termAtt);
        final int start = scanner.yychar();
        offsetAtt.setOffset(correctOffset(start), correctOffset(start+termAtt.length()));
        // This 'if' should be removed in the next release. For now, it converts
        // invalid acronyms to HOST. When removed, only the 'else' part should
        // remain.
        if (tokenType == StandardTokenizer.ACRONYM_DEP) {
          typeAtt.setType(StandardTokenizer.TOKEN_TYPES[StandardTokenizer.HOST]);
          termAtt.setLength(termAtt.length() - 1); // remove extra '.'
        } else {
          typeAtt.setType(StandardTokenizer.TOKEN_TYPES[tokenType]);
        }
        return true;
      } else
        // When we skip a too-long term, we still increment the
        // position increment
        skippedPositions++;
    }
  }
  
  @Override
  public final void end() throws IOException {
    super.end();
    // set final offset
    int finalOffset = correctOffset(scanner.yychar() + scanner.yylength());
    offsetAtt.setOffset(finalOffset, finalOffset);
    // adjust any skipped tokens
    posIncrAtt.setPositionIncrement(posIncrAtt.getPositionIncrement()+skippedPositions);
  }

  @Override
  public void close() throws IOException {
    super.close();
    scanner.yyreset(input);
  }

  @Override
  public void reset() throws IOException {
    super.reset();
    scanner.yyreset(input);
    skippedPositions = 0;
  }
}