lucene-java-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "John Christopher Groppe" <jgro...@acm.org>
Subject Error reading documents from file index lucene 2.0
Date Fri, 16 Jun 2006 19:17:44 GMT
I've encountered a very vexing problem with Lucene 2.0.0.  I am able
to create and search an index, but if I attempt get a document out of
the index, an IO exception is thrown.  The type of exception depends
on the size of the index.  If the index is very small, say fewer than
10 documents I do not get the error.  If the index is a Ram index I do
not get any errors.

Am I doing something wrong, or is this a bug.  I am running:

Lucene 2.0.0
Java 1.5.0_07
Windows XP Pro SP2

Here is my test code followed by the Exception stack trace.

Any help is greatly appreciated.  Thanks.

John

import java.util.Iterator;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.queryParser.QueryParser;
import org.apache.lucene.search.Hit;
import org.apache.lucene.search.Hits;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.store.RAMDirectory;

public class SearchTest {

    private static final String[][] ALBUM_DATA = {
        {"51271", "#1 Def Spot Jam [EDITED]", "#1 Def Spot Jam
[EDITED]", "Rap/Hip Hop", "0", "1016", "Various Artists", "Various
Artists"},
        {"51270", "#1 Def Spot Jam [EXPLICIT]", "#1 Def Spot Jam
[EXPLICIT]", "Rap/Hip Hop", "1", "1016", "Various Artists", "Various
Artists"},
        {"64967", "#1 Record/Radio City", "#1 Record/Radio City",
"Rock", "0", "663", "Big Star", "Big Star"},
        {"35141", "#1 [EXPLICIT]","#1 [EXPLICIT]","Alternative Rock",
"1", "9686", "Fischerspooner", "Fischerspooner"},
        {"55322", "#1's", "#1's", "Jazz/Blues", "0", "2759", "Louis
Jordan", "Louis Jordan"},
        {"59738", "#1's", "#1's", "R&B/Soul", "0", "6660", "Destiny's
Child", "Destiny's Child"},
        {"25384",  "001", "001", "Alternative Rock", "0", "7733",
"Dovetail Joint", "Dovetail Joint"},
        {"2719", "02", "02", "Pop", "0", "807", "O-Town", "O-Town"},
        {"35398", "02: Avalon Remixed","02: Avalon Remixed","Pop",
"0","9770","Avalon","Avalon"},
        {"33073","0304","0304","Pop","0","1116","Jewel","Jewel"},
        {"27876","05:22:09:12 Off","05:22:09:12 Off","Alternative
Rock","0","8945","Front 242","Front 242"},
        {"24513","1 Fille And 4 Types","1 fille & 4
types","Pop","0","5074","Celine Dion","Celine Dion"},
        {"23074","1+1","1+1","Jazz/Blues","0","3568","Wayne
Shorter","Wayne Shorter"},
        {"15045","1,000 Fires","1,000 Fires","Pop","0","2888","Traci
Lords","Traci Lords"},
        {"42193","1.22.03.Acoustic","1.22.03.Acoustic","Pop","0","823","Maroon
5","Maroon 5"},
        {"22537","10","10","Rap/Hip Hop","0","3631","LL Cool J","LL Cool J"}
    };

    public static final String FIELD_ID = "id";
    public static final String FIELD_TITLE = "title";
    public static final String FIELD_TITLE_ORIGINAL = "titleOriginal";
    public static final String FIELD_GENRES = "genres";
    public static final String FIELD_EXPLICIT = "explicit";
    public static final String FIELD_ID_ARTIST = "idArtist";
    public static final String FIELD_ARTIST = "artist";
    public static final String FIELD_ARTIST_ORIGINAL = "artistOriginal";
    public static final String FIELD_MEDIA = "media";
    public static final String MEDIA_SONG = "s";
    public static final String MEDIA_ALBUM = "a";

    public static void readAlbums(IndexWriter indexWriter) throws Exception {
        for (int i = 0; i < ALBUM_DATA.length; i++) {
            String[] line = ALBUM_DATA[i];
            Document doc = new Document();
            Field idField = new Field(FIELD_ID, line[0],
Field.Store.YES, Field.Index.NO);
            doc.add(idField);
            Field titleFieldOriginal = new Field(FIELD_TITLE_ORIGINAL,
line[2], Field.Store.YES, Field.Index.TOKENIZED);
            doc.add(titleFieldOriginal);
            Field genreField = new Field(FIELD_GENRES, line[3],
Field.Store.YES, Field.Index.TOKENIZED);
            doc.add(genreField);
            Field explicitField = new Field(FIELD_EXPLICIT, line[4],
Field.Store.YES, Field.Index.UN_TOKENIZED);
            doc.add(explicitField);
            Field artistIdField = new Field(FIELD_ID_ARTIST, line[5],
Field.Store.YES, Field.Index.NO);
            doc.add(artistIdField);
            Field artistFieldOriginal = new
Field(FIELD_ARTIST_ORIGINAL, line[7], Field.Store.YES,
Field.Index.TOKENIZED);
            doc.add(artistFieldOriginal);
            indexWriter.addDocument(doc);
        }
    }

    public static void main(String[] args) throws Exception {
        // create index
        Directory directory = null;
        directory = FSDirectory.getDirectory("index", true);
        // RamDirectory Works!!!
        //directory = new RAMDirectory();
        IndexWriter indexWriter = new IndexWriter(directory, new
StandardAnalyzer(), true);
        indexWriter.setUseCompoundFile(false);
        readAlbums(indexWriter);
        System.out.println("Albums Indexed = " + indexWriter.docCount());
        indexWriter.optimize();
        indexWriter.close();

        // search index
        IndexSearcher indexSearcher = new IndexSearcher(directory);
        QueryParser parser = new
QueryParser(SearchTest.FIELD_ARTIST_ORIGINAL, new StandardAnalyzer());
        // serach for albums by various artists
        Query query = parser.parse("various");
        Hits hits = indexSearcher.search(query);
        indexSearcher.close();
        System.out.println("Hits found:" + hits.length());
        Iterator<Hit> i = hits.iterator();
        while(i.hasNext()) {
            Hit hit = i.next();
            System.out.println("Artist: " +
hit.get(SearchTest.FIELD_ARTIST_ORIGINAL) + " , album: " +
hit.get(SearchTest.FIELD_TITLE_ORIGINAL));
        }

    }

}

// output
Albums Indexed = 16
Hits found:2
Exception in thread "main" java.io.IOException: No such file or directory
        at java.io.RandomAccessFile.readBytes(Native Method)
        at java.io.RandomAccessFile.read(RandomAccessFile.java:315)
        at org.apache.lucene.store.FSIndexInput.readInternal(FSDirectory.java:454)
        at org.apache.lucene.store.BufferedIndexInput.refill(BufferedIndexInput.java:64)
        at org.apache.lucene.store.BufferedIndexInput.readByte(BufferedIndexInput.java:33)
        at org.apache.lucene.store.IndexInput.readInt(IndexInput.java:46)
        at org.apache.lucene.store.IndexInput.readLong(IndexInput.java:69)
        at org.apache.lucene.index.FieldsReader.doc(FieldsReader.java:62)
        at org.apache.lucene.index.SegmentReader.document(SegmentReader.java:284)
        at org.apache.lucene.search.IndexSearcher.doc(IndexSearcher.java:83)
        at org.apache.lucene.search.Hits.doc(Hits.java:103)
        at org.apache.lucene.search.Hit.fetchTheHit(Hit.java:77)
        at org.apache.lucene.search.Hit.getDocument(Hit.java:54)
        at org.apache.lucene.search.Hit.get(Hit.java:101)
        at SearchTest.main(SearchTest.java:91)

---------------------------------------------------------------------
To unsubscribe, e-mail: java-user-unsubscribe@lucene.apache.org
For additional commands, e-mail: java-user-help@lucene.apache.org


Mime
View raw message