edu.siena.cs.sawus.search.Searcher.java Source code

Introduction

Here is the source code for edu.siena.cs.sawus.search.Searcher.java

Source

package edu.siena.cs.sawus.search;

/**
 * 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.io.BufferedReader;
import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStreamReader;
import java.util.Date;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.queryparser.classic.QueryParser;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;

/** Simple command-line based search demo. */
public class Searcher {

    public Searcher() {
    }

    /** Simple command-line based search demo. */
    public static void search(String index) throws Exception {

        String field = "contents";
        String queries = null;
        int repeat = 0;
        boolean raw = false;
        String queryString = null;
        int hitsPerPage = 10;

        IndexReader reader = IndexReader.open(FSDirectory.open(new File(index)));
        IndexSearcher searcher = new IndexSearcher(reader);
        Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_40);

        BufferedReader in = null;
        if (queries != null) {
            in = new BufferedReader(new InputStreamReader(new FileInputStream(queries), "UTF-8"));
        } else {
            in = new BufferedReader(new InputStreamReader(System.in, "UTF-8"));
        }
        QueryParser parser = new QueryParser(Version.LUCENE_40, field, analyzer);
        while (true) {
            if (queries == null && queryString == null) { // prompt the user
                System.out.println("Enter query: ");
            }

            String line = queryString != null ? queryString : in.readLine();

            if (line == null || line.length() == -1) {
                break;
            }

            line = line.trim();
            if (line.length() == 0) {
                break;
            }

            Query query = parser.parse(line);
            System.out.println("Searching for: " + query.toString(field));

            if (repeat > 0) { // repeat & time as benchmark
                Date start = new Date();
                for (int i = 0; i < repeat; i++) {
                    searcher.search(query, null, 100);
                }
                Date end = new Date();
                System.out.println("Time: " + (end.getTime() - start.getTime()) + "ms");
            }

            doPagingSearch(in, searcher, query, hitsPerPage, raw, queries == null && queryString == null);

            if (queryString != null) {
                break;
            }
        }
        //searcher.close();
        reader.close();
    }

    /**
     * This demonstrates a typical paging search scenario, where the search engine presents 
     * pages of size n to the user. The user can then go to the next page if interested in
     * the next hits.
     * 
     * When the query is executed for the first time, then only enough results are collected
     * to fill 5 result pages. If the user wants to page beyond this limit, then the query
     * is executed another time and all hits are collected.
     * 
     */
    public static void doPagingSearch(BufferedReader in, IndexSearcher searcher, Query query, int hitsPerPage,
            boolean raw, boolean interactive) throws IOException {

        // Collect enough docs to show 5 pages
        TopDocs results = searcher.search(query, 5 * hitsPerPage);
        ScoreDoc[] hits = results.scoreDocs;

        int numTotalHits = results.totalHits;
        System.out.println(numTotalHits + " total matching documents");

        int start = 0;
        int end = numTotalHits;

        hits = searcher.search(query, numTotalHits).scoreDocs;

        for (int i = start; i < end; i++) {

            Document doc = searcher.doc(hits[i].doc);
            String path = doc.get("file");
            if (path != null) {
                System.out.println((i + 1) + ". " + path);
                String docID = doc.get("doc_id");
                if (docID != null) {
                    System.out.println("DocID:\t" + docID);
                }
                String title = doc.get("title");
                if (title != null) {
                    System.out.println("Title:\t" + doc.get("title").replaceAll("\n", " "));
                }
                String content = doc.get("contents");
                if (content != null) {
                    System.out.println(content);
                }
            } else {
                System.out.println((i + 1) + ". " + "No path for this document");
            }

        }
    }
}