Perculator

gistfile1.java

package com.varun.perculator;

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

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.core.SimpleAnalyzer;
import org.apache.lucene.index.Term;
import org.apache.lucene.index.memory.MemoryIndex;
import org.apache.lucene.queryparser.classic.ParseException;
import org.apache.lucene.queryparser.classic.QueryParser;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.util.Version;

public class Percolator {

  public static final Version VERSION = Version.LUCENE_43;
  public static final String CONTENT = "content";
  private List<Query> queries;
  private MemoryIndex index;

  public Percolator() {
    queries = new ArrayList<Query>();
    index = new MemoryIndex();
  }

  public void addQuery(String query) throws ParseException {
    Analyzer analyzer = new SimpleAnalyzer(VERSION);
    QueryParser parser = new QueryParser(VERSION, CONTENT, analyzer);
    queries.add(parser.parse(query));
  }
  
  private void addDirectQuery(String string) {
    Query query = new TermQuery(new Term(CONTENT, string));
    queries.add(query);
    
  }

  /*
   * TODO maybe use automation/ trie fields if list<queries> is large( like 1 million registered queries)
   */
  public synchronized List<Query> getMatchingQueries(String doc) {
    
    index.reset();
    index.addField(CONTENT, doc, new SimpleAnalyzer(VERSION));
      
    List<Query> matching = new ArrayList<Query>();
    for (Query query : queries) {
      if (index.search(query) > 0.0f) {
        matching.add(query);
      }
    }

    return matching;
  }


  public static void main(String[] args) throws ParseException {
    
    long start = System.currentTimeMillis();
    Percolator percolator = new Percolator();
    percolator.addDirectQuery("one");
    percolator.addDirectQuery("two");
    percolator.addDirectQuery("three");

    String  docs[] = {
        "one two three",
        "two",
        "three",
        "four"
    };

    for (String doc : docs) {
      System.out.println(doc + " -> " + percolator.getMatchingQueries(doc));
    }
    long end = System.currentTimeMillis();
    System.out.println(end - start);
  }


}