InformationRetrieval.Search.java Source code

Java tutorial

Introduction

Here is the source code for InformationRetrieval.Search.java

Source

package InformationRetrieval;

/*
 * 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.*;
import java.io.BufferedReader;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileReader;
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.DirectoryReader;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.queryparser.classic.ParseException;
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 Search {

    private Search() {
    }

    /** Simple command-line based search demo. 
    * @throws ParseException */
    public static ArrayList<Store> search(String stringQuery) throws IOException, Exception {
        ArrayList<Store> list = null;
        //    String usage =
        //      "Usage:\tjava org.apache.lucene.demo.SearchFiles [-index dir] [-field f] [-repeat n] [-queries file] [-query string] [-raw] [-paging hitsPerPage]\n\nSee http://lucene.apache.org/core/4_1_0/demo/ for details.";
        //    if (args.length > 0 && ("-h".equals(args[0]) || "-help".equals(args[0]))) {
        //      System.out.println(usage);
        //      System.exit(0);
        //    }

        String index = "index";
        String field = "contents";
        String queries = null;
        int repeat = 0;
        boolean raw = false;
        String queryString = null;
        int hitsPerPage = 50;

        //    for(int i = 0;i < args.length;i++) {
        //      if ("-index".equals(args[i])) {
        //        index = args[i+1];
        //        i++;
        //      } else if ("-field".equals(args[i])) {
        //        field = args[i+1];
        //        i++;
        //      } else if ("-queries".equals(args[i])) {
        //        queries = args[i+1];
        //        i++;
        //      } else if ("-query".equals(args[i])) {
        //        queryString = args[i+1];
        //        i++;
        //      } else if ("-repeat".equals(args[i])) {
        //        repeat = Integer.parseInt(args[i+1]);
        //        i++;
        //      } else if ("-raw".equals(args[i])) {
        //        raw = true;
        //      } else if ("-paging".equals(args[i])) {
        //        hitsPerPage = Integer.parseInt(args[i+1]);
        //        if (hitsPerPage <= 0) {
        //          System.err.println("There must be at least 1 hit per page.");
        //          System.exit(1);
        //        }
        //        i++;
        //      }
        //    }

        IndexReader reader = DirectoryReader.open(FSDirectory.open(new File(index)));
        IndexSearcher searcher = new IndexSearcher(reader);
        Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_41);

        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_41, field, analyzer);
        //    while (true) {
        //      if (queries == null && queryString == null) {                        // prompt the user
        //        System.out.println("Enter query: ");
        //      }

        String line = queryString != null ? queryString : stringQuery;

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

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

        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");
        }

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

        if (queryString != null) {
            return null;
        }

        reader.close();
        return list;
    }

    /**
     * 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.
    * @return 
     * 
     */
    public static ArrayList<Store> doPagingSearch(BufferedReader in, IndexSearcher searcher, Query query,
            int hitsPerPage, boolean raw, boolean interactive) throws IOException {

        ArrayList<Store> list1 = new ArrayList<Store>();
        // Collect enough docs to show 5 pages
        TopDocs results = searcher.search(query, 5 * hitsPerPage);
        ScoreDoc[] hits = results.scoreDocs;

        int numTotalHits = results.totalHits;
        // list1.add(numTotalHits +" total matching documents");
        // System.out.println(numTotalHits + " total matching documents");

        int start = 0;
        int end = Math.min(numTotalHits, hitsPerPage);

        while (true) {
            if (end > hits.length) {
                System.out.println("Only results 1 - " + hits.length + " of " + numTotalHits
                        + " total matching documents collected.");
                System.out.println("Collect more (y/n) ?");
                String line = "n";
                if (line.length() == 0 || line.charAt(0) == 'n') {
                    break;
                }

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

            end = Math.min(hits.length, start + hitsPerPage);

            for (int i = start; i < end; i++) {
                if (raw) {
                    // output raw format
                    //list1.add("doc="+hits[i].doc+" score="+hits[i].score);
                    // System.out.println("doc="+hits[i].doc+" score="+hits[i].score);
                    continue;
                }

                Document doc = searcher.doc(hits[i].doc);
                String path = doc.get("path");
                if (path != null) {
                    //   System.out.println((i+1) + ". " + path);
                    //list1.add((i+1) + ". " + path);

                    BufferedReader OutWriter = new BufferedReader(new FileReader(path));
                    String line = OutWriter.readLine();
                    String title1 = OutWriter.readLine();
                    String s1 = "NA", s2 = "NA", s3 = "NA";
                    while (OutWriter.readLine() != null) {
                        s1 = OutWriter.readLine().trim();
                        break;
                    }
                    while (OutWriter.readLine() != null) {
                        s2 = OutWriter.readLine().trim();
                        break;
                    }
                    while (OutWriter.readLine() != null) {
                        //      s3 = OutWriter.readLine().trim();
                        break;
                    }

                    String small = s1 + " " + s2 + " " + s3;
                    Store a = new Store(title1, line, small);
                    list1.add(a);
                    //System.out.println(a.getsnippet() + "--------------------");

                    //System.out.println(a.gettitle());
                    //System.out.println(a.geturl());

                    //System.out.println(line);
                    //fileWriter.write(line);
                    //fileWriter.newLine();

                    String title = doc.get("title");
                    if (title != null) {
                        //    System.out.println("   Title: " + doc.get("title"));
                        // list1.add("   Title: " + doc.get("title"));

                    }
                } else {
                    //  System.out.println((i+1) + ". " + "No path for this document");
                    // list1.add((i+1) + ". " + "No path for this document");

                }

            }

            if (!interactive || end == 0) {
                break;
            }

            if (numTotalHits >= end) {
                boolean quit = false;
                while (true) {
                    System.out.print("Press ");
                    if (start - hitsPerPage >= 0) {
                        System.out.print("(p)revious page, ");
                    }
                    if (start + hitsPerPage < numTotalHits) {
                        System.out.print("(n)ext page, ");
                    }
                    System.out.println("(q)uit or enter number to jump to a page.");

                    String line = "q";
                    if (line.length() == 0 || line.charAt(0) == 'q') {
                        quit = true;
                        break;
                    }
                    if (line.charAt(0) == 'p') {
                        start = Math.max(0, start - hitsPerPage);
                        break;
                    } else if (line.charAt(0) == 'n') {
                        if (start + hitsPerPage < numTotalHits) {
                            start += hitsPerPage;
                        }
                        break;
                    } else {
                        int page = Integer.parseInt(line);
                        if ((page - 1) * hitsPerPage < numTotalHits) {
                            start = (page - 1) * hitsPerPage;
                            break;
                        } else {
                            System.out.println("No such page");
                        }
                    }
                }
                if (quit)
                    break;
                end = Math.min(numTotalHits, start + hitsPerPage);
            }
        }
        return list1;
    }
}