org.apache.lucene.analysis.standard.std40.StandardTokenizer40 Maven / Gradle / Ivy

Go to download
Show more of this group Show more artifacts with this name
Show all versions of hivemall-all
The newest version!
/*
 * 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.std40;

import java.io.IOException;

import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
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.AttributeFactory;

/** Backcompat standard tokenizer for Lucene 4.0-4.6. This supports Unicode 6.1.
 * 
 * @deprecated Use {@link org.apache.lucene.analysis.standard.StandardTokenizer}
 */
@Deprecated
public final class StandardTokenizer40 extends Tokenizer {
  /** A private instance of the JFlex-constructed scanner */
  private StandardTokenizerImpl40 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.std40.StandardTokenizer40}.
   *
   * See http://issues.apache.org/jira/browse/LUCENE-1068
   */
  public StandardTokenizer40() {
    init();
  }

  /**
   * Creates a new StandardTokenizer40 with a given {@link org.apache.lucene.util.AttributeFactory} 
   */
  public StandardTokenizer40(AttributeFactory factory) {
    super(factory);
    init();
  }

  private final void init() {
    this.scanner = new StandardTokenizerImpl40(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 == StandardTokenizerImpl40.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 == StandardTokenizer40.ACRONYM_DEP) {
          typeAtt.setType(StandardTokenizer40.TOKEN_TYPES[StandardTokenizer40.HOST]);
          termAtt.setLength(termAtt.length() - 1); // remove extra '.'
        } else {
          typeAtt.setType(StandardTokenizer40.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;
  }
}