alvinalexander.com | career | drupal | java | mac | mysql | perl | scala | uml | unix  

Lucene example source code file (FieldPhraseList.java)

This example Lucene source code file (FieldPhraseList.java) is included in the DevDaily.com "Java Source Code Warehouse" project. The intent of this project is to help you "Learn Java by Example" TM.

Java - Lucene tags/keywords

arraylist, fieldphraselist, linkedlist, linkedlist, override, queryphrasemap, string, stringbuilder, stringbuilder, terminfo, toffs, toffs, util, weightedphraseinfo, weightedphraseinfo

The Lucene FieldPhraseList.java source code

package org.apache.lucene.search.vectorhighlight;
/**
 * 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.
 */

import java.util.ArrayList;
import java.util.LinkedList;
import java.util.List;

import org.apache.lucene.search.vectorhighlight.FieldQuery.QueryPhraseMap;
import org.apache.lucene.search.vectorhighlight.FieldTermStack.TermInfo;

/**
 * FieldPhraseList has a list of WeightedPhraseInfo that is used by FragListBuilder
 * to create a FieldFragList object.
 */
public class FieldPhraseList {

  LinkedList<WeightedPhraseInfo> phraseList = new LinkedList();

  /**
   * a constructor.
   * 
   * @param fieldTermStack FieldTermStack object
   * @param fieldQuery FieldQuery object
   */
  public FieldPhraseList( FieldTermStack fieldTermStack, FieldQuery fieldQuery ){
    final String field = fieldTermStack.getFieldName();

    LinkedList<TermInfo> phraseCandidate = new LinkedList();
    QueryPhraseMap currMap = null;
    QueryPhraseMap nextMap = null;
    while( !fieldTermStack.isEmpty() ){
      
      phraseCandidate.clear();

      TermInfo ti = fieldTermStack.pop();
      currMap = fieldQuery.getFieldTermMap( field, ti.getText() );

      // if not found, discard top TermInfo from stack, then try next element
      if( currMap == null ) continue;
      
      // if found, search the longest phrase
      phraseCandidate.add( ti );
      while( true ){
        ti = fieldTermStack.pop();
        nextMap = null;
        if( ti != null )
          nextMap = currMap.getTermMap( ti.getText() );
        if( ti == null || nextMap == null ){
          if( ti != null )
            fieldTermStack.push( ti );
          if( currMap.isValidTermOrPhrase( phraseCandidate ) ){
            addIfNoOverlap( new WeightedPhraseInfo( phraseCandidate, currMap.getBoost(), currMap.getTermOrPhraseNumber() ) );
          }
          else{
            while( phraseCandidate.size() > 1 ){
              fieldTermStack.push( phraseCandidate.removeLast() );
              currMap = fieldQuery.searchPhrase( field, phraseCandidate );
              if( currMap != null ){
                addIfNoOverlap( new WeightedPhraseInfo( phraseCandidate, currMap.getBoost(), currMap.getTermOrPhraseNumber() ) );
                break;
              }
            }
          }
          break;
        }
        else{
          phraseCandidate.add( ti );
          currMap = nextMap;
        }
      }
    }
  }
  
  void addIfNoOverlap( WeightedPhraseInfo wpi ){
    for( WeightedPhraseInfo existWpi : phraseList ){
      if( existWpi.isOffsetOverlap( wpi ) ) return;
    }
    phraseList.add( wpi );
  }
  
  public static class WeightedPhraseInfo {

    String text;  // unnecessary member, just exists for debugging purpose
    List<Toffs> termsOffsets;   // usually termsOffsets.size() == 1,
                            // but if position-gap > 1 and slop > 0 then size() could be greater than 1
    float boost;  // query boost
    int seqnum;
    
    public WeightedPhraseInfo( LinkedList<TermInfo> terms, float boost ){
      this( terms, boost, 0 );
    }
    
    public WeightedPhraseInfo( LinkedList<TermInfo> terms, float boost, int number ){
      this.boost = boost;
      this.seqnum = number;
      termsOffsets = new ArrayList<Toffs>( terms.size() );
      TermInfo ti = terms.get( 0 );
      termsOffsets.add( new Toffs( ti.getStartOffset(), ti.getEndOffset() ) );
      if( terms.size() == 1 ){
        text = ti.getText();
        return;
      }
      StringBuilder sb = new StringBuilder();
      sb.append( ti.getText() );
      int pos = ti.getPosition();
      for( int i = 1; i < terms.size(); i++ ){
        ti = terms.get( i );
        sb.append( ti.getText() );
        if( ti.getPosition() - pos == 1 ){
          Toffs to = termsOffsets.get( termsOffsets.size() - 1 );
          to.setEndOffset( ti.getEndOffset() );
        }
        else{
          termsOffsets.add( new Toffs( ti.getStartOffset(), ti.getEndOffset() ) );
        }
        pos = ti.getPosition();
      }
      text = sb.toString();
    }
    
    public int getStartOffset(){
      return termsOffsets.get( 0 ).startOffset;
    }
    
    public int getEndOffset(){
      return termsOffsets.get( termsOffsets.size() - 1 ).endOffset;
    }
    
    public boolean isOffsetOverlap( WeightedPhraseInfo other ){
      int so = getStartOffset();
      int eo = getEndOffset();
      int oso = other.getStartOffset();
      int oeo = other.getEndOffset();
      if( so <= oso && oso < eo ) return true;
      if( so < oeo && oeo <= eo ) return true;
      if( oso <= so && so < oeo ) return true;
      if( oso < eo && eo <= oeo ) return true;
      return false;
    }
    
    @Override
    public String toString(){
      StringBuilder sb = new StringBuilder();
      sb.append( text ).append( '(' ).append( boost ).append( ")(" );
      for( Toffs to : termsOffsets ){
        sb.append( to );
      }
      sb.append( ')' );
      return sb.toString();
    }
    
    public static class Toffs {
      int startOffset;
      int endOffset;
      public Toffs( int startOffset, int endOffset ){
        this.startOffset = startOffset;
        this.endOffset = endOffset;
      }
      public void setEndOffset( int endOffset ){
        this.endOffset = endOffset;
      }
      public int getStartOffset(){
        return startOffset;
      }
      public int getEndOffset(){
        return endOffset;
      }
      @Override
      public String toString(){
        StringBuilder sb = new StringBuilder();
        sb.append( '(' ).append( startOffset ).append( ',' ).append( endOffset ).append( ')' );
        return sb.toString();
      }
    }
  }
}

Other Lucene examples (source code examples)

Here is a short list of links related to this Lucene FieldPhraseList.java source code file:

... this post is sponsored by my books ...

#1 New Release!

FP Best Seller

 

new blog posts

 

Copyright 1998-2021 Alvin Alexander, alvinalexander.com
All Rights Reserved.

A percentage of advertising revenue from
pages under the /java/jwarehouse URI on this website is
paid back to open source projects.