mirror of https://github.com/apache/lucene.git
LUCENE-1599: Add clone support for SpanQuerys. SpanRegexQuery counts on this functionality and does not work correctly without it.
git-svn-id: https://svn.apache.org/repos/asf/lucene/java/trunk@791280 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
parent
21fba4ee7b
commit
e04abc52e7
|
@ -349,6 +349,10 @@ Bug fixes
|
||||||
16. LUCENE-1681: Fix infinite loop caused by a call to DocValues methods
|
16. LUCENE-1681: Fix infinite loop caused by a call to DocValues methods
|
||||||
getMinValue, getMaxValue, getAverageValue. (Simon Willnauer via Mark Miller)
|
getMinValue, getMaxValue, getAverageValue. (Simon Willnauer via Mark Miller)
|
||||||
|
|
||||||
|
17. LUCENE-1599: Add clone support for SpanQuerys. SpanRegexQuery counts
|
||||||
|
on this functionality and does not work correctly without it.
|
||||||
|
(Mark Miller)
|
||||||
|
|
||||||
New features
|
New features
|
||||||
|
|
||||||
1. LUCENE-1411: Added expert API to open an IndexWriter on a prior
|
1. LUCENE-1411: Added expert API to open an IndexWriter on a prior
|
||||||
|
|
|
@ -17,32 +17,46 @@ package org.apache.lucene.search.regex;
|
||||||
* limitations under the License.
|
* limitations under the License.
|
||||||
*/
|
*/
|
||||||
|
|
||||||
|
import java.io.IOException;
|
||||||
|
|
||||||
import junit.framework.TestCase;
|
import junit.framework.TestCase;
|
||||||
import org.apache.lucene.store.RAMDirectory;
|
|
||||||
import org.apache.lucene.index.IndexWriter;
|
|
||||||
import org.apache.lucene.index.Term;
|
|
||||||
import org.apache.lucene.analysis.SimpleAnalyzer;
|
import org.apache.lucene.analysis.SimpleAnalyzer;
|
||||||
|
import org.apache.lucene.analysis.standard.StandardAnalyzer;
|
||||||
import org.apache.lucene.document.Document;
|
import org.apache.lucene.document.Document;
|
||||||
import org.apache.lucene.document.Field;
|
import org.apache.lucene.document.Field;
|
||||||
import org.apache.lucene.search.IndexSearcher;
|
import org.apache.lucene.index.CorruptIndexException;
|
||||||
|
import org.apache.lucene.index.IndexWriter;
|
||||||
|
import org.apache.lucene.index.Term;
|
||||||
import org.apache.lucene.search.Hits;
|
import org.apache.lucene.search.Hits;
|
||||||
import org.apache.lucene.search.spans.SpanTermQuery;
|
import org.apache.lucene.search.IndexSearcher;
|
||||||
|
import org.apache.lucene.search.MultiSearcher;
|
||||||
|
import org.apache.lucene.search.spans.SpanFirstQuery;
|
||||||
import org.apache.lucene.search.spans.SpanNearQuery;
|
import org.apache.lucene.search.spans.SpanNearQuery;
|
||||||
import org.apache.lucene.search.spans.SpanQuery;
|
import org.apache.lucene.search.spans.SpanQuery;
|
||||||
import org.apache.lucene.search.spans.SpanFirstQuery;
|
import org.apache.lucene.store.Directory;
|
||||||
|
import org.apache.lucene.store.LockObtainFailedException;
|
||||||
|
import org.apache.lucene.store.RAMDirectory;
|
||||||
|
|
||||||
public class TestSpanRegexQuery extends TestCase {
|
public class TestSpanRegexQuery extends TestCase {
|
||||||
|
Directory indexStoreA = new RAMDirectory();
|
||||||
|
|
||||||
|
Directory indexStoreB = new RAMDirectory();
|
||||||
|
|
||||||
public void testSpanRegex() throws Exception {
|
public void testSpanRegex() throws Exception {
|
||||||
RAMDirectory directory = new RAMDirectory();
|
RAMDirectory directory = new RAMDirectory();
|
||||||
IndexWriter writer = new IndexWriter(directory, new SimpleAnalyzer(), true);
|
IndexWriter writer = new IndexWriter(directory, new SimpleAnalyzer(), true);
|
||||||
Document doc = new Document();
|
Document doc = new Document();
|
||||||
// doc.add(new Field("field", "the quick brown fox jumps over the lazy dog", Field.Store.NO, Field.Index.ANALYZED));
|
// doc.add(new Field("field", "the quick brown fox jumps over the lazy dog",
|
||||||
|
// Field.Store.NO, Field.Index.ANALYZED));
|
||||||
// writer.addDocument(doc);
|
// writer.addDocument(doc);
|
||||||
// doc = new Document();
|
// doc = new Document();
|
||||||
doc.add(new Field("field", "auto update", Field.Store.NO, Field.Index.ANALYZED));
|
doc.add(new Field("field", "auto update", Field.Store.NO,
|
||||||
|
Field.Index.ANALYZED));
|
||||||
writer.addDocument(doc);
|
writer.addDocument(doc);
|
||||||
doc = new Document();
|
doc = new Document();
|
||||||
doc.add(new Field("field", "first auto update", Field.Store.NO, Field.Index.ANALYZED));
|
doc.add(new Field("field", "first auto update", Field.Store.NO,
|
||||||
|
Field.Index.ANALYZED));
|
||||||
writer.addDocument(doc);
|
writer.addDocument(doc);
|
||||||
writer.optimize();
|
writer.optimize();
|
||||||
writer.close();
|
writer.close();
|
||||||
|
@ -50,8 +64,63 @@ public class TestSpanRegexQuery extends TestCase {
|
||||||
IndexSearcher searcher = new IndexSearcher(directory);
|
IndexSearcher searcher = new IndexSearcher(directory);
|
||||||
SpanRegexQuery srq = new SpanRegexQuery(new Term("field", "aut.*"));
|
SpanRegexQuery srq = new SpanRegexQuery(new Term("field", "aut.*"));
|
||||||
SpanFirstQuery sfq = new SpanFirstQuery(srq, 1);
|
SpanFirstQuery sfq = new SpanFirstQuery(srq, 1);
|
||||||
// SpanNearQuery query = new SpanNearQuery(new SpanQuery[] {srq, stq}, 6, true);
|
// SpanNearQuery query = new SpanNearQuery(new SpanQuery[] {srq, stq}, 6,
|
||||||
|
// true);
|
||||||
Hits hits = searcher.search(sfq);
|
Hits hits = searcher.search(sfq);
|
||||||
assertEquals(1, hits.length());
|
assertEquals(1, hits.length());
|
||||||
}
|
}
|
||||||
|
|
||||||
|
public void testSpanRegexBug() throws CorruptIndexException, IOException {
|
||||||
|
createRAMDirectories();
|
||||||
|
|
||||||
|
SpanRegexQuery srq = new SpanRegexQuery(new Term("field", "a.*"));
|
||||||
|
SpanRegexQuery stq = new SpanRegexQuery(new Term("field", "b.*"));
|
||||||
|
SpanNearQuery query = new SpanNearQuery(new SpanQuery[] { srq, stq }, 6,
|
||||||
|
true);
|
||||||
|
|
||||||
|
// 1. Search the same store which works
|
||||||
|
IndexSearcher[] arrSearcher = new IndexSearcher[2];
|
||||||
|
arrSearcher[0] = new IndexSearcher(indexStoreA);
|
||||||
|
arrSearcher[1] = new IndexSearcher(indexStoreB);
|
||||||
|
MultiSearcher searcher = new MultiSearcher(arrSearcher);
|
||||||
|
Hits hits = searcher.search(query);
|
||||||
|
arrSearcher[0].close();
|
||||||
|
arrSearcher[1].close();
|
||||||
|
|
||||||
|
// Will fail here
|
||||||
|
// We expect 2 but only one matched
|
||||||
|
// The rewriter function only write it once on the first IndexSearcher
|
||||||
|
// So it's using term: a1 b1 to search on the second IndexSearcher
|
||||||
|
// As a result, it won't match the document in the second IndexSearcher
|
||||||
|
assertEquals(2, hits.length());
|
||||||
|
indexStoreA.close();
|
||||||
|
indexStoreB.close();
|
||||||
|
}
|
||||||
|
|
||||||
|
private void createRAMDirectories() throws CorruptIndexException,
|
||||||
|
LockObtainFailedException, IOException {
|
||||||
|
// creating a document to store
|
||||||
|
Document lDoc = new Document();
|
||||||
|
lDoc.add(new Field("field", "a1 b1", Field.Store.NO,
|
||||||
|
Field.Index.ANALYZED_NO_NORMS));
|
||||||
|
|
||||||
|
// creating a document to store
|
||||||
|
Document lDoc2 = new Document();
|
||||||
|
lDoc2.add(new Field("field", "a2 b2", Field.Store.NO,
|
||||||
|
Field.Index.ANALYZED_NO_NORMS));
|
||||||
|
|
||||||
|
// creating first index writer
|
||||||
|
IndexWriter writerA = new IndexWriter(indexStoreA, new StandardAnalyzer(),
|
||||||
|
true, IndexWriter.MaxFieldLength.LIMITED);
|
||||||
|
writerA.addDocument(lDoc);
|
||||||
|
writerA.optimize();
|
||||||
|
writerA.close();
|
||||||
|
|
||||||
|
// creating second index writer
|
||||||
|
IndexWriter writerB = new IndexWriter(indexStoreB, new StandardAnalyzer(),
|
||||||
|
true, IndexWriter.MaxFieldLength.LIMITED);
|
||||||
|
writerB.addDocument(lDoc2);
|
||||||
|
writerB.optimize();
|
||||||
|
writerB.close();
|
||||||
|
}
|
||||||
}
|
}
|
||||||
|
|
|
@ -33,7 +33,7 @@ import org.apache.lucene.util.ToStringUtils;
|
||||||
/** Matches spans which are near one another. One can specify <i>slop</i>, the
|
/** Matches spans which are near one another. One can specify <i>slop</i>, the
|
||||||
* maximum number of intervening unmatched positions, as well as whether
|
* maximum number of intervening unmatched positions, as well as whether
|
||||||
* matches are required to be in-order. */
|
* matches are required to be in-order. */
|
||||||
public class SpanNearQuery extends SpanQuery {
|
public class SpanNearQuery extends SpanQuery implements Cloneable {
|
||||||
private List clauses;
|
private List clauses;
|
||||||
private int slop;
|
private int slop;
|
||||||
private boolean inOrder;
|
private boolean inOrder;
|
||||||
|
@ -152,6 +152,17 @@ public class SpanNearQuery extends SpanQuery {
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
public Object clone() {
|
||||||
|
int sz = clauses.size();
|
||||||
|
SpanQuery[] newClauses = new SpanQuery[sz];
|
||||||
|
|
||||||
|
for (int i = 0; i < sz; i++) {
|
||||||
|
SpanQuery clause = (SpanQuery) clauses.get(i);
|
||||||
|
newClauses[i] = (SpanQuery) clause.clone();
|
||||||
|
}
|
||||||
|
return new SpanNearQuery(newClauses, slop, inOrder);
|
||||||
|
}
|
||||||
|
|
||||||
/** Returns true iff <code>o</code> is equal to this. */
|
/** Returns true iff <code>o</code> is equal to this. */
|
||||||
public boolean equals(Object o) {
|
public boolean equals(Object o) {
|
||||||
if (this == o) return true;
|
if (this == o) return true;
|
||||||
|
|
|
@ -27,7 +27,7 @@ import java.util.Collection;
|
||||||
import java.util.Set;
|
import java.util.Set;
|
||||||
|
|
||||||
/** Removes matches which overlap with another SpanQuery. */
|
/** Removes matches which overlap with another SpanQuery. */
|
||||||
public class SpanNotQuery extends SpanQuery {
|
public class SpanNotQuery extends SpanQuery implements Cloneable {
|
||||||
private SpanQuery include;
|
private SpanQuery include;
|
||||||
private SpanQuery exclude;
|
private SpanQuery exclude;
|
||||||
|
|
||||||
|
@ -68,6 +68,9 @@ public class SpanNotQuery extends SpanQuery {
|
||||||
return buffer.toString();
|
return buffer.toString();
|
||||||
}
|
}
|
||||||
|
|
||||||
|
public Object clone() {
|
||||||
|
return new SpanNotQuery((SpanQuery)include.clone(),(SpanQuery) exclude.clone());
|
||||||
|
}
|
||||||
|
|
||||||
public Spans getSpans(final IndexReader reader) throws IOException {
|
public Spans getSpans(final IndexReader reader) throws IOException {
|
||||||
return new PayloadSpans() {
|
return new PayloadSpans() {
|
||||||
|
|
|
@ -31,7 +31,7 @@ import org.apache.lucene.util.ToStringUtils;
|
||||||
import org.apache.lucene.search.Query;
|
import org.apache.lucene.search.Query;
|
||||||
|
|
||||||
/** Matches the union of its clauses.*/
|
/** Matches the union of its clauses.*/
|
||||||
public class SpanOrQuery extends SpanQuery {
|
public class SpanOrQuery extends SpanQuery implements Cloneable {
|
||||||
private List clauses;
|
private List clauses;
|
||||||
private String field;
|
private String field;
|
||||||
|
|
||||||
|
@ -80,6 +80,18 @@ public class SpanOrQuery extends SpanQuery {
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
public Object clone() {
|
||||||
|
int sz = clauses.size();
|
||||||
|
SpanQuery[] newClauses = new SpanQuery[sz];
|
||||||
|
|
||||||
|
for (int i = 0; i < sz; i++) {
|
||||||
|
SpanQuery clause = (SpanQuery) clauses.get(i);
|
||||||
|
newClauses[i] = (SpanQuery) clause.clone();
|
||||||
|
}
|
||||||
|
SpanOrQuery soq = new SpanOrQuery(newClauses);
|
||||||
|
return soq;
|
||||||
|
}
|
||||||
|
|
||||||
public Query rewrite(IndexReader reader) throws IOException {
|
public Query rewrite(IndexReader reader) throws IOException {
|
||||||
SpanOrQuery clone = null;
|
SpanOrQuery clone = null;
|
||||||
for (int i = 0 ; i < clauses.size(); i++) {
|
for (int i = 0 ; i < clauses.size(); i++) {
|
||||||
|
|
Loading…
Reference in New Issue