Mailing-List: contact java-user-help@lucene.apache.org; run by ezmlm
Precedence: bulk
Reply-To: java-user@lucene.apache.org
Received-SPF: pass (athena.apache.org: domain of a85533109@gmail.com
 designates 209.85.217.170 as permitted sender)
DomainKey-Signature: a=rsa-sha1; c=nofws;
        d=gmail.com; s=gamma;
        h=mime-version:date:message-id:subject:from:to:content-type
         :content-transfer-encoding;
        b=Sohx7SXYH7EcQCvy9rYuLOVTQ/8mimzZWNYEPatdkETstiVyCMMA+pHFS/hyLkL5Q4
         3lc8r+Qd0H31B0AVHHvkZkvIxSiTbuW8eA44xefcqRcG2Y6hzNhykW4PWied4TCeAb6W
         nBvdHEw7fWEK7p2yqsab9PJlxwkEMjoQy67Ss=
MIME-Version: 1.0
Date: Thu, 5 Mar 2009 16:17:37 +0100
Message-ID: <324177540903050717x597318dfs69669c536526c8e8@mail.gmail.com>
Subject: indexing but not tokenizing
From: John Marks <a85533109@gmail.com>
To: java-user@lucene.apache.org
Content-Type: text/plain; charset=ISO-8859-1
Content-Transfer-Encoding: quoted-printable

Hi all,

I'm not able to see what's wrong in the following sample code.
I'm indexing a document with 5 fields, using five different indexing strate=
gies.
I'm fine the the results for 4 of them, but field B is causing me some
trouble in understanding what's going on.

The value of field B is X (uppercase).
The analyzer is a SimpleAnalyzer, which I use on the QueryParser as well.
But when I search for X (uppercase) on field B, the X is converted to lower=
case.
Now, I know that SimpleAnalyzer converts to lowercase, but I was
expecting it not to do so on field B, which is NOT_ANALYZED.

How should I fix my code?

Thank you in advance!
-John


--- code ---


package test;

import org.apache.lucene.analysis.SimpleAnalyzer;
import org.apache.lucene.store.RAMDirectory;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.TopDocCollector;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.queryParser.QueryParser;


public class Test
{
=A0 public static void main(String[] args)
=A0 {
=A0=A0=A0 try
=A0=A0=A0 {
=A0=A0=A0=A0=A0 RAMDirectory idx =3D new RAMDirectory();
=A0=A0=A0=A0=A0 SimpleAnalyzer analyzer =3D new SimpleAnalyzer();

=A0=A0=A0=A0=A0 IndexWriter writer =3D new IndexWriter(idx, analyzer, true,
=A0=A0=A0=A0=A0=A0=A0=A0=A0 IndexWriter.MaxFieldLength.LIMITED);

=A0=A0=A0=A0=A0 Document doc =3D new Document();
=A0=A0=A0=A0=A0 doc.add(new Field("A", "X",
=A0=A0=A0=A0=A0=A0=A0=A0=A0 Field.Store.YES, Field.Index.NO));
=A0=A0=A0=A0=A0 doc.add(new Field("B", "X",
=A0=A0=A0=A0=A0=A0=A0=A0=A0 Field.Store.YES, Field.Index.NOT_ANALYZED));
=A0=A0=A0=A0=A0 doc.add(new Field("C", "X",
=A0=A0=A0=A0=A0=A0=A0=A0=A0 Field.Store.YES, Field.Index.ANALYZED));
=A0=A0=A0=A0=A0 doc.add(new Field("D", "x",
=A0=A0=A0=A0=A0=A0=A0=A0=A0 Field.Store.NO, Field.Index.NOT_ANALYZED));
=A0=A0=A0=A0=A0 doc.add(new Field("E", "X",
=A0=A0=A0=A0=A0=A0=A0=A0=A0 Field.Store.NO, Field.Index.ANALYZED));
=A0=A0=A0=A0=A0 writer.addDocument(doc);
=A0=A0=A0=A0=A0 writer.close();

=A0=A0=A0=A0=A0 IndexSearcher searcher =3D new IndexSearcher(idx);
=A0=A0=A0=A0=A0 String field =3D "B";
=A0=A0=A0=A0=A0 QueryParser parser =3D new QueryParser(field, analyzer);
=A0=A0=A0=A0=A0 Query query =3D parser.parse("X");
=A0=A0=A0=A0=A0 System.out.println("Query: " + query.toString());

=A0=A0=A0=A0=A0 TopDocCollector collector =3D new TopDocCollector(1);
=A0=A0=A0=A0=A0 searcher.search(query, collector);
=A0=A0=A0=A0=A0 int numHits =3D collector.getTotalHits();
=A0=A0=A0=A0=A0 System.out.println(numHits + " total matching documents");

=A0=A0=A0=A0=A0 if ( numHits > 0)
=A0=A0=A0=A0=A0 {
=A0=A0=A0=A0=A0=A0=A0 ScoreDoc[] hits =3D collector.topDocs().scoreDocs;
=A0=A0=A0=A0=A0=A0=A0 doc =3D searcher.doc(hits[0].doc);
=A0=A0=A0=A0=A0=A0=A0 System.out.println("A: " + doc.get("A"));
=A0=A0=A0=A0=A0=A0=A0 System.out.println("B: " + doc.get("B"));
=A0=A0=A0=A0=A0=A0=A0 System.out.println("C: " + doc.get("C"));
=A0=A0=A0=A0=A0=A0=A0 System.out.println("D: " + doc.get("D"));
=A0=A0=A0=A0=A0=A0=A0 System.out.println("E: " + doc.get("E"));
=A0=A0=A0=A0=A0 }
=A0=A0=A0 }
=A0=A0=A0 catch (Exception e)
=A0=A0=A0 {
=A0=A0=A0=A0=A0 System.out.println(" caught a " + e.getClass() + "\n with m=
essage: "
=A0=A0=A0=A0=A0=A0=A0=A0=A0 + e.getMessage());
=A0=A0=A0 }
=A0 }

}

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