lucene-general mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Nuno Lopes <dsmn...@gmail.com>
Subject Fwd: Problem with output in the SearchFile example
Date Tue, 15 Oct 2013 18:48:50 GMT
Good Night,

I have the following data.txt:
-------txt---------------
Nuno Rui Sergio
Abraham
Diogo
Bela Nuno Rui
Rui
Nuno Sergio
----------------------------
I want to search the following string: Nuno. For this i used the example
provided by your website.

 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.DirectoryReader;
    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 SearchFiles {

      private SearchFiles() {}

      /** Simple command-line based search demo. */
      public static void main(String[] args) throws Exception {
        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.";

         //  args[0] ="Artigo de IE 8060152";
      //  String[] teste = null;
        // teste[0]="artigo";
          //System.out.println("--> "+args.length);
//        if (teste.length > 0 && ("-h".equals(args[0]) ||
"-help".equals(args[0]))) {
//          System.out.println(usage);
//          System.exit(0);
//        }

        String index =
"C:\\Users\\javas\\Documents\\NetBeansProjects\\Brincadeira";
        String field = "Nuno";
        String queries = "data.txt";
        int repeat = 0;
        boolean raw = true;
        String queryString = null;
        int hitsPerPage = 10;



//        for(int i = 0;i < teste.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_45);

        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_45, 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;
          }
            System.out.println(line.toString());
          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;
          }
        }
        reader.close();
      }

      /**
139       * This demonstrates a typical paging search scenario, where the
search engine presents
140       * pages of size n to the user. The user can then go to the next
page if interested in
141       * the next hits.
142       *
143       * When the query is executed for the first time, then only enough
results are collected
144       * to fill 5 result pages. If the user wants to page beyond this
limit, then the query
145       * is executed another time and all hits are collected.
146       *
147       */
      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 = 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 = in.readLine();
            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
              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);
              String title = doc.get("title");
              if (title != null) {
                System.out.println("   Title: " + doc.get("title"));
              }
            } else {
              System.out.println((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 = in.readLine();
              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);
          }
        }
      }
    }

My problem is that the output said that 0 matches were found when should
return 3.
Can you help me please.

Best regardings,

Nuno Sérgio Lopes.

Mime
  • Unnamed multipart/alternative (inline, None, 0 bytes)
View raw message