uwe at thetaphi
Oct 12, 2009, 11:11 AM
Post #14 of 14
(1001 views)
Permalink
|
The source code attachment got somehow lost:
import org.apache.lucene.analysis.WhitespaceAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.NumericField;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.Term;
import org.apache.lucene.store.RAMDirectory;
import org.apache.lucene.search.*;
import org.apache.lucene.queryParser.QueryParser;
import org.apache.lucene.util.LuceneTestCase;
import org.apache.lucene.util.NumericUtils;
public class TestNRQWithQueryParser extends LuceneTestCase {
public void test() throws Exception {
RAMDirectory directory = new RAMDirectory();
IndexWriter writer = new IndexWriter(directory, new
WhitespaceAnalyzer(), true, IndexWriter.MaxFieldLength.UNLIMITED);
for (int l=-5000; l<=5000; l++) {
Document doc = new Document();
doc.add(new Field("text", "the big brown", Field.Store.NO,
Field.Index.ANALYZED));
doc.add(new NumericField("trie", Field.Store.NO,
true).setIntValue(l));
writer.addDocument(doc);
}
writer.close();
Searcher searcher=new IndexSearcher(directory, true);
QueryParser parser = new QueryParser("text", new WhitespaceAnalyzer()) {
@Override
protected Query newRangeQuery(String field, String part1, String
part2, boolean inclusive) {
if ("trie".equals(field)) {
return NumericRangeQuery.newIntRange(field,
Integer.parseInt(part1), Integer.parseInt(part2), inclusive, inclusive);
} else {
return super.newRangeQuery(field, part1, part2, inclusive);
}
}
@Override
protected Query newTermQuery(Term term) {
if("trie".equals(term.field())) {
return new TermQuery(new Term(term.field(),
NumericUtils.intToPrefixCoded(Integer.parseInt(term.text()))));
} else {
return super.newTermQuery(term);
}
}
};
TopDocs td;
td = searcher.search(parser.parse("+trie:[20 TO 30]"), 5000);
assertEquals(11, td.totalHits);
td = searcher.search(parser.parse("+trie:[-4999 TO -4000]"), 5000);
assertEquals(1000, td.totalHits);
td = searcher.search(parser.parse("the big brown +trie:[-4999 TO
-4000]"), 5000);
assertEquals(1000, td.totalHits);
td = searcher.search(parser.parse("+trie:77"), 5000);
assertEquals(1, td.totalHits);
td = searcher.search(parser.parse("+trie:5001"), 5000);
assertEquals(0, td.totalHits);
td = searcher.search(parser.parse("the big brown +trie:\"-2\""), 5000);
assertEquals(1, td.totalHits);
td = searcher.search(parser.parse("+trie:\"-5001\""), 5000);
assertEquals(0, td.totalHits);
searcher.close();
directory.close();
}
}
-----
Uwe Schindler
H.-H.-Meier-Allee 63, D-28213 Bremen
http://www.thetaphi.de
eMail: uwe [at] thetaphi
> -----Original Message-----
> From: Uwe Schindler [mailto:uwe [at] thetaphi]
> Sent: Monday, October 12, 2009 8:10 PM
> To: java-user [at] lucene
> Subject: RE: How do you properly use NumericField
>
> Hallo Paul,
>
> I implemented what you wanted in the applied testcase. Works without
> problems. Your error was, that in the TermQuery creation you placed a
> precisionStep in the shift value parameter which is incorrect.
>
> By the way: Lucene 2.9.1 and Lucene 3.0 will be optimized for ranges like
> [1
> TO 1], because this is now as fast as a TermQuery, but you can
> NumericRangeQuery for it (and do not need to encode the terms). Just
> replace
> the TermQuery with NumericUtils in the newTermQuery method by a
> NumericRangeQuery with upper and lower bound equal (and not exclusive).
>
> Please note: negative numbers in the query parser may lead to problems,
> because of this they needed to be placed in "" ("-" is the sign for
> exclusion terms). The test may fail with other Analyzers that corrupt your
> numbers.
>
> Uwe
>
> > -----Original Message-----
> > From: Uwe Schindler [mailto:uwe [at] thetaphi]
> > Sent: Monday, October 12, 2009 5:49 PM
> > To: java-user [at] lucene; paul_t100 [at] fastmail
> > Subject: RE: How do you properly use NumericField
> >
> > Can you print the upper and lower term or the term you received in
> > newRangeQuery and newTermQuery also to System.out? Maybe it is converted
> > somehow by your Analyzer, that is used for parsing the query.
> >
> > -----
> > Uwe Schindler
> > H.-H.-Meier-Allee 63, D-28213 Bremen
> > http://www.thetaphi.de
> > eMail: uwe [at] thetaphi
> >
> >
> > > -----Original Message-----
> > > From: Paul Taylor [mailto:paul_t100 [at] fastmail]
> > > Sent: Monday, October 12, 2009 1:00 PM
> > > To: java-user [at] lucene
> > > Subject: Re: How do you properly use NumericField
> > >
> > > Uwe Schindler wrote:
> > > > I forgot: The format of numeric fields is also not plain text,
> because
> > > of
> > > > this a simple TermQuery as generated by your query parser will not
> > work,
> > > > too.
> > > >
> > > > If you want to hit numeric values without a NumericRangeQuery with
> > lower
> > > and
> > > > upper bound equal, you have to use NumericUtils to translate the
> term
> > > text,
> > > > e.g. new TermQuery(new Term("field",
> > > > NumericUtils.intToPrefixCoded(value,precstep)))
> > > >
> > > > If you want support for this in QueryParser, you have to override
> > > > QueryParser.newTermQuery as explained before for newRangeQuery. By
> the
> > > way,
> > > > Solr does this in exactly that way.
> > > >
> > > > Uwe
> > > >
> > >
> > > Ok, Im trying my best here but still cannot get range or single term
> > > query searching to work.
> > >
> > > package org.musicbrainz.search.servlet;
> > >
> > > import junit.framework.TestCase;
> > > import org.apache.lucene.analysis.Analyzer;
> > > import org.apache.lucene.document.Document;
> > > import org.apache.lucene.document.NumericField;
> > > import org.apache.lucene.index.IndexWriter;
> > > import org.apache.lucene.index.Term;
> > > import org.apache.lucene.queryParser.QueryParser;
> > > import org.apache.lucene.search.*;
> > > import org.apache.lucene.store.RAMDirectory;
> > > import org.apache.lucene.util.NumericUtils;
> > > import org.musicbrainz.search.index.TrackAnalyzer;
> > >
> > > public class NumericFieldTest extends TestCase {
> > >
> > > public void testNumericFields() throws Exception {
> > > Analyzer analyzer = new TrackAnalyzer();
> > > RAMDirectory dir = new RAMDirectory();
> > > IndexWriter writer = new IndexWriter(dir, analyzer, true,
> > > IndexWriter.MaxFieldLength.LIMITED);
> > > Document doc = new Document();
> > > NumericField nf = new NumericField("dur");
> > > nf.setIntValue(123);
> > > writer.addDocument(doc);
> > > writer.close();
> > >
> > > IndexSearcher searcher = new IndexSearcher(dir,true);
> > > {
> > >
> > > Query q = new
> > > MusicbrainzQueryParser("dur",analyzer).parse("[12 TO 124]");
> > > assertEquals(1, searcher.search(q,10).totalHits);
> > >
> > >
> > > q = new
> MusicbrainzQueryParser("dur",analyzer).parse("123");
> > > assertEquals(1, searcher.search(q,10).totalHits);
> > >
> > >
> > > }
> > > }
> > >
> > > static class MusicbrainzQueryParser extends QueryParser {
> > >
> > > public MusicbrainzQueryParser(String field, Analyzer a) {
> > > super(field, a);
> > > System.out.println("init parser");
> > > }
> > >
> > > public Query newRangeQuery(String field,
> > > String part1,
> > > String part2,
> > > boolean inclusive)
> > > {
> > > System.out.println("RangeQuery");
> > > TermRangeQuery query = (TermRangeQuery)
> > > super.newRangeQuery(field, part1, part2,
> > > inclusive);
> > >
> > > if ("dur".equals(field)) {
> > > System.out.println("durRangeQuery");
> > >
> > > return NumericRangeQuery.newIntRange(
> > > "dur",
> > > Integer.parseInt(query.getLowerTerm()),
> > > Integer.parseInt(query.getUpperTerm()),
> > > query.includesLower(),
> > > query.includesUpper());
> > > } else {
> > > return query;
> > > }
> > > }
> > >
> > > protected Query newTermQuery(Term term)
> > > {
> > > System.out.println("newTermQuery");
> > > if(term.field().equals("dur")) {
> > > System.out.println("dur,newTermQuery");
> > > TermQuery tq = new TermQuery(new Term("field",
> > >
> > >
> >
> NumericUtils.intToPrefixCoded(Integer.parseInt(term.text()),NumericUtils.P
> > > RECISION_STEP_DEFAULT)));
> > > return tq;
> > > }
> > > else {
> > > return super.newTermQuery(term);
> > > }
> > > }
> > > }
> > >
> > > }
> > >
> > > ---------------------------------------------------------------------
> > > To unsubscribe, e-mail: java-user-unsubscribe [at] lucene
> > > For additional commands, e-mail: java-user-help [at] lucene
> >
> >
> >
> > ---------------------------------------------------------------------
> > To unsubscribe, e-mail: java-user-unsubscribe [at] lucene
> > For additional commands, e-mail: java-user-help [at] lucene
>
|
