Учитывая документ {'foo', 'bar', 'baz'}, я хочу сопоставить, используя SpanNearQuery, с токенами {'baz', 'extra'}
Но это не удается.
Как мне обойти это?
Образец теста (с использованием люцена 2.9.1) со следующими результатами:
- givenSingleMatch - ПРОЙДЕН
- givenTwoMatches - ПРОЙДЕН
- givenThreeMatches - ПРОЙДЕН
- givenSingleMatch_andExtraTerm - НЕИСПРАВНОСТЬ
...
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.Term;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.search.spans.SpanNearQuery;
import org.apache.lucene.search.spans.SpanQuery;
import org.apache.lucene.search.spans.SpanTermQuery;
import org.apache.lucene.store.RAMDirectory;
import org.apache.lucene.util.Version;
import org.junit.After;
import org.junit.Assert;
import org.junit.Before;
import org.junit.Test;
import java.io.IOException;
public class SpanNearQueryTest {
private RAMDirectory directory = null;
private static final String BAZ = "baz";
private static final String BAR = "bar";
private static final String FOO = "foo";
private static final String TERM_FIELD = "text";
@Before
public void given() throws IOException {
directory = new RAMDirectory();
IndexWriter writer = new IndexWriter(
directory,
new StandardAnalyzer(Version.LUCENE_29),
IndexWriter.MaxFieldLength.UNLIMITED);
Document doc = new Document();
doc.add(new Field(TERM_FIELD, FOO, Field.Store.NO, Field.Index.ANALYZED));
doc.add(new Field(TERM_FIELD, BAR, Field.Store.NO, Field.Index.ANALYZED));
doc.add(new Field(TERM_FIELD, BAZ, Field.Store.NO, Field.Index.ANALYZED));
writer.addDocument(doc);
writer.commit();
writer.optimize();
writer.close();
}
@After
public void cleanup() {
directory.close();
}
@Test
public void givenSingleMatch() throws IOException {
SpanNearQuery spanNearQuery = new SpanNearQuery(
new SpanQuery[] {
new SpanTermQuery(new Term(TERM_FIELD, FOO))
}, Integer.MAX_VALUE, false);
TopDocs topDocs = new IndexSearcher(IndexReader.open(directory)).search(spanNearQuery, 100);
Assert.assertEquals("Should have made a match.", 1, topDocs.scoreDocs.length);
}
@Test
public void givenTwoMatches() throws IOException {
SpanNearQuery spanNearQuery = new SpanNearQuery(
new SpanQuery[] {
new SpanTermQuery(new Term(TERM_FIELD, FOO)),
new SpanTermQuery(new Term(TERM_FIELD, BAR))
}, Integer.MAX_VALUE, false);
TopDocs topDocs = new IndexSearcher(IndexReader.open(directory)).search(spanNearQuery, 100);
Assert.assertEquals("Should have made a match.", 1, topDocs.scoreDocs.length);
}
@Test
public void givenThreeMatches() throws IOException {
SpanNearQuery spanNearQuery = new SpanNearQuery(
new SpanQuery[] {
new SpanTermQuery(new Term(TERM_FIELD, FOO)),
new SpanTermQuery(new Term(TERM_FIELD, BAR)),
new SpanTermQuery(new Term(TERM_FIELD, BAZ))
}, Integer.MAX_VALUE, false);
TopDocs topDocs = new IndexSearcher(IndexReader.open(directory)).search(spanNearQuery, 100);
Assert.assertEquals("Should have made a match.", 1, topDocs.scoreDocs.length);
}
@Test
public void givenSingleMatch_andExtraTerm() throws IOException {
SpanNearQuery spanNearQuery = new SpanNearQuery(
new SpanQuery[] {
new SpanTermQuery(new Term(TERM_FIELD, BAZ)),
new SpanTermQuery(new Term(TERM_FIELD, "EXTRA"))
},
Integer.MAX_VALUE, false);
TopDocs topDocs = new IndexSearcher(IndexReader.open(directory)).search(spanNearQuery, 100);
Assert.assertEquals("Should have made a match.", 1, topDocs.scoreDocs.length);
}
}
