hi all
following is some code that i use to index the contents of a table ( there
are 18746 records in the table. )
using a database result set , i loop over all the records ,
creating a document object and indexing into ramDirectory and then onto the
fileSystem
when I open a IndexReader and output numDoc i get 18740,
How ever on running the same code, but using a FSDirectory object on
opening a IndexReader I get 18476
has anyone else come across this behaviour ? jdk being used is 1.4.1
public class JournalIndexer extends JournalConstants {
IndexWriter ramWriter ;
Directory ramDirectory;
String dir;
public JournalIndexer(String dir) throws Exception{
this.dir = dir;
ramDirectory = new RAMDirectory();
ramWriter = new IndexWriter( ramDirectory, new SimpleAnalyzer()
,true );
}
public static void main(String args[]) throws Exception {
Statement stmt = connection.createStatement();
JournalIndexer indexer = new JournalIndexer("journals");
int main_counter = 0;
// SELECT ID, JOURNALTITLE, NLM_ID, ISSN, MEDLINE_ABBREVIATION,
ISO_ABBREVIATION, ESSN "+
ResultSet rs = stmt.executeQuery(sqlFetchJournals);
while(rs.next() ){
Journal journal = new Journal();
///set values
main_counter++;
indexer.add( journal );
}
indexer.close();
}
int count = 0;
public void add(Journal journal) throws Exception {
Document j_doc = new Document();
//Field(String name , String string, boolean store, boolean
index, boolean token)
Field id = new Field(ID,""+journal.getId(), true, true, false );
j_doc.add( id );
ramWriter.addDocument( j_doc );
count++;
}
public void close() throws Exception {
IndexWriter fileWriter = new IndexWriter(
FSDirectory.getDirectory(dir,true), new SimpleAnalyzer(),true);
Directory dirs[] = { ramDirectory };
fileWriter.addIndexes( dirs );
fileWriter.optimize();
fileWriter.close();
}
class JournalAnalyzer extends Analyzer {
public TokenStream tokenStream(String field,Reader reader) {
TokenStream result = new WhitespaceTokenizer(reader);
result = new LowerCaseFilter(result);
return result;
}
}
}
---------------------------------------------------------------------
To unsubscribe, e-mail: [EMAIL PROTECTED]
For additional commands, e-mail: [EMAIL PROTECTED]
