Hi,
I recently stumbled across what I think might be a bug in the QueryParser.
Before I enter it as a bug, I wanted to run it by this group to see if I'm
just not looking at the boolean expression correctly.
Here's the issue:
I created an index with 5 documents, all have one field: "text", with the
following contents:
doc1:text:"Table Chair Spoon"
doc2:text:"Table Chair Spoon Fork"
doc3:text:"Table Spoon Fork"
doc4:text:"Chair Spoon Fork"
doc5:text:"Spoon Fork"
When I enter the query: "Table AND NOT Chair" I get one hit, doc3
When I enter the query: "Table AND (NOT Chair)" I get 0 hits.
I had thought that both queries would return the same results. Is this a
bug, or, am I not understanding the query language correctly?
I'm attaching test code. The program creates an index in the directory
which you pass into the main program.
Thanks!
L
------------------------------------------------------------------------------
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.analysis.SimpleAnalyzer;
import org.apache.lucene.analysis.WhitespaceAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.Hits;
import org.apache.lucene.queryParser.QueryParser;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.PhraseQuery;
import org.apache.lucene.index.Term;
import java.io.File;
import java.io.IOException;
import java.io.FileReader;
public class IndexTest {
public static void create(File indexDir) throws IOException {
IndexWriter writer = new IndexWriter(indexDir, new
WhitespaceAnalyzer(), true);
Document doc = new Document();
doc.add(new Field("text",
"Table Chair Spoon",
Field.Store.YES,
Field.Index.TOKENIZED,
Field.TermVector.NO));
writer.addDocument(doc);
doc = new Document();
doc.add(new Field("text",
"Table Chair Spoon Fork",
Field.Store.YES,
Field.Index.TOKENIZED,
Field.TermVector.NO));
writer.addDocument(doc);
doc = new Document();
doc.add(new Field("text",
"Table Spoon Fork!",
Field.Store.YES,
Field.Index.TOKENIZED,
Field.TermVector.NO));
writer.addDocument(doc);
doc = new Document();
doc.add(new Field("text",
"Chair Spoon Fork",
Field.Store.YES,
Field.Index.TOKENIZED,
Field.TermVector.NO));
writer.addDocument(doc);
doc = new Document();
doc.add(new Field("text",
"Spoon Fork",
Field.Store.YES,
Field.Index.TOKENIZED,
Field.TermVector.NO));
writer.addDocument(doc);
writer.close();
}
public static void query(File indexDir, String queryString) throws
IOException
{
Query query = null;
Hits hits = null;
try {
QueryParser qp = new QueryParser("text",new
WhitespaceAnalyzer());
qp.setDefaultOperator(QueryParser.OR_OPERATOR);
query = qp.parse(queryString);
} catch (Exception qe) {System.out.println(qe.toString());}
if (query == null) return;
System.out.println("Query: " + query.toString());
IndexReader reader = IndexReader.open(indexDir);
IndexSearcher searcher = new IndexSearcher(reader);
hits = searcher.search(query);
System.out.println("Hits: " + hits.length());
for (int i = 0; i < hits.length(); i++)
{
System.out.println( hits.doc(i).get("text") + " ");
}
searcher.close();
reader.close();
}
public static void main(String[] args) throws Exception {
if (args.length != 1) {
throw new Exception("Usage: " + IndexTest.class.getName() +
"<index dir>");
}
File indexDir = new File(args[0]);
create(indexDir);
query(indexDir,"Table AND NOT Chair");
query(indexDir,"Table AND (NOT Chair)");
}
}