ntu.searchengine.Searcher.java Source code

Introduction

Here is the source code for ntu.searchengine.Searcher.java

Source

/*
 * To change this license header, choose License Headers in Project Properties.
 * To change this template file, choose Tools | Templates
 * and open the template in the editor.
 */
package ntu.searchengine;

import java.io.IOException;
import java.nio.file.Paths;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.Map;

//import com.sun.scenario.effect.impl.sw.sse.SSEBlend_SRC_OUTPeer;
import ntu.searchengine.scoring.ScoringFiltering;
import ntu.searchengine.ui.SearchResultModel;
import org.apache.lucene.analysis.miscellaneous.PerFieldAnalyzerWrapper;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexableField;
import org.apache.lucene.queryparser.classic.ParseException;
import org.apache.lucene.search.*;
import org.apache.lucene.store.FSDirectory;

/**
 *
 * @author espen1
 */
public class Searcher {

    private final DirectoryReader rdr;
    private final IndexSearcher is;
    private final CustomQueryParser parser;

    public Searcher(String indexDir) throws IOException {
        rdr = DirectoryReader.open(FSDirectory.open(Paths.get(indexDir)));
        is = new IndexSearcher(rdr);
        PerFieldAnalyzerWrapper aWrapper = FieldAnalyzerFactory.getAnalyzer();
        if (Main.boosting) {
            Map<String, Float> boosts = new HashMap<>();
            //Title, author, journal, booktitle
            float[] boostsValues = { 5, 3, 1, 1 };
            int index = 0;
            for (String field : FieldConstants.getSearchableFields()) {
                boosts.put(field, boostsValues[index]);
                index++;
            }
            parser = new CustomQueryParser(FieldConstants.getSearchableFields(), aWrapper, boosts);
        } else {
            parser = new CustomQueryParser(FieldConstants.getSearchableFields(), aWrapper);
        }
    }

    public ArrayList<SearchResultModel> search(String queryString) throws ParseException, IOException {
        parser.prepare(queryString);
        Query query = parser.parse(queryString);
        TopDocs hits = null;
        if (Main.sortResultByDocId) { //If we sort the documents the score field will be NaN
            //Sort by doc number
            final Sort sort = new Sort(new SortedNumericSortField(FieldConstants.DOCNAME, SortField.Type.INT));
            hits = is.search(query, Main.topNResult, sort);
        } else {
            hits = is.search(query, Main.topNResult);
        }

        System.out.println("Result for query: " + queryString);
        ArrayList<SearchResultModel> result = getResult(hits, query);
        return ScoringFiltering.filterScores(result);
    }

    public ArrayList<SearchResultModel> getResult(TopDocs hits, Query query) throws IOException {
        ArrayList<SearchResultModel> results = new ArrayList<>();
        for (ScoreDoc scoreDoc : hits.scoreDocs) {

            System.out.println("================================");
            String explanation = is.explain(query, scoreDoc.doc).toString();
            System.out.println(explanation);
            Document doc = is.doc(scoreDoc.doc);
            String output = getFieldValues(doc);
            float score = scoreDoc.score;
            System.out.println("Result score: " + score);
            System.out.println(output);
            results.add(new SearchResultModel(explanation, output, score, doc));
        }
        return results;
    }

    public String getFieldValues(Document doc) {
        String output = "";
        for (IndexableField f : doc.getFields()) {
            output += f.name() + ":" + f.stringValue() + '\n';
        }
        return output;
    }

    public void close() throws IOException {
        rdr.close();
    }
}