Apache
/
lucene
mirror of https://github.com/apache/lucene.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Merge remote-tracking branch 'origin/master'

This commit is contained in:
Noble Paul 2016-10-19 00:54:30 +05:30
parent ffa5c4ba2c b78f2219f4
commit 53129ba670
6 changed files with 134 additions and 69 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

39
lucene/backward-codecs/src/java/org/apache/lucene/codecs/lucene54/Lucene54DocValuesProducer.java
View File

@ -491,7 +491,44 @@ final class Lucene54DocValuesProducer extends DocValuesProducer implements Close
docsWithField = getLiveBits(entry.missingOffset, maxDoc);
}
}
return new LegacyNumericDocValuesWrapper(docsWithField, getNumeric(entry));
final LongValues values = getNumeric(entry);
return new NumericDocValues() {
int doc = -1;
long value;
@Override
public long longValue() throws IOException {
return value;
}
@Override
public int docID() {
return doc;
}
@Override
public int nextDoc() throws IOException {
return advance(doc + 1);
}
@Override
public int advance(int target) throws IOException {
for (int doc = target; doc < maxDoc; ++doc) {
value = values.get(doc);
if (value != 0 || docsWithField.get(doc)) {
return this.doc = doc;
}
}
return doc = NO_MORE_DOCS;
}
@Override
public long cost() {
return maxDoc;
}
};
}
@Override

69
lucene/codecs/src/java/org/apache/lucene/codecs/memory/MemoryDocValuesProducer.java
View File

@ -42,7 +42,6 @@ import org.apache.lucene.util.FixedBitSet;
import org.apache.lucene.util.IOUtils;
import org.apache.lucene.util.IntsRef;
import org.apache.lucene.util.IntsRefBuilder;
import org.apache.lucene.util.LongValues;
import org.apache.lucene.util.PagedBytes;
import org.apache.lucene.util.RamUsageEstimator;
import org.apache.lucene.util.fst.BytesRefFSTEnum.InputOutput;
@ -371,7 +370,12 @@ class MemoryDocValuesProducer extends DocValuesProducer {
ramBytesUsed.addAndGet(reader.ramBytesUsed());
numericInfo.put(field.name, Accountables.namedAccountable("block compressed", reader));
}
return reader;
return new LegacyNumericDocValues() {
@Override
public long get(int docID) {
return reader.get(docID);
}
};
case GCD_COMPRESSED:
final long min = data.readLong();
final long mult = data.readLong();
@ -568,51 +572,26 @@ class MemoryDocValuesProducer extends DocValuesProducer {
}
addr = res;
}
if (values instanceof LongValues) {
// probably not the greatest codec choice for this situation, but we support it
final LongValues longValues = (LongValues) values;
return new LegacySortedNumericDocValuesWrapper(new LegacySortedNumericDocValues() {
long startOffset;
long endOffset;
@Override
public void setDocument(int doc) {
startOffset = (int) addr.get(doc);
endOffset = (int) addr.get(doc+1L);
}
return new LegacySortedNumericDocValuesWrapper(new LegacySortedNumericDocValues() {
int startOffset;
int endOffset;
@Override
public void setDocument(int doc) {
startOffset = (int) addr.get(doc);
endOffset = (int) addr.get(doc+1);
}
@Override
public long valueAt(int index) {
return longValues.get(startOffset + index);
}
@Override
public long valueAt(int index) {
return values.get(startOffset + index);
}
@Override
public int count() {
return (int) (endOffset - startOffset);
}
}, maxDoc);
} else {
return new LegacySortedNumericDocValuesWrapper(new LegacySortedNumericDocValues() {
int startOffset;
int endOffset;
@Override
public void setDocument(int doc) {
startOffset = (int) addr.get(doc);
endOffset = (int) addr.get(doc+1);
}
@Override
public long valueAt(int index) {
return values.get(startOffset + index);
}
@Override
public int count() {
return (endOffset - startOffset);
}
}, maxDoc);
}
@Override
public int count() {
return (endOffset - startOffset);
}
}, maxDoc);
}
}

21
lucene/core/src/java/org/apache/lucene/util/LongValues.java
View File

@ -16,21 +16,9 @@
*/
package org.apache.lucene.util;
import org.apache.lucene.index.LegacyNumericDocValues;
import org.apache.lucene.index.NumericDocValues;
import org.apache.lucene.util.packed.PackedInts;
/** Abstraction over an array of longs.
* This class extends NumericDocValues so that we don't need to add another
* level of abstraction every time we want eg. to use the {@link PackedInts}
* utility classes to represent a {@link LegacyNumericDocValues} instance.
* @lucene.internal
*
* @deprecated Switch to {@link NumericDocValues} instead. */
@Deprecated
// TODO: cutover to iterator once codecs have all cutover?
public abstract class LongValues extends LegacyNumericDocValues {
* @lucene.internal */
public abstract class LongValues {
/** An instance that returns the provided value. */
public static final LongValues IDENTITY = new LongValues() {
@ -45,9 +33,4 @@ public abstract class LongValues extends LegacyNumericDocValues {
/** Get value at <code>index</code>. */
public abstract long get(long index);
@Override
public long get(int idx) {
return get((long) idx);
}
}

6
lucene/core/src/test/org/apache/lucene/util/packed/TestDirectPacked.java
View File

@ -19,12 +19,12 @@ package org.apache.lucene.util.packed;
import java.util.Random;
import org.apache.lucene.index.LegacyNumericDocValues;
import org.apache.lucene.store.ByteArrayDataInput;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.IOContext;
import org.apache.lucene.store.IndexInput;
import org.apache.lucene.store.IndexOutput;
import org.apache.lucene.util.LongValues;
import org.apache.lucene.util.LuceneTestCase;
import org.apache.lucene.util.TestUtil;
import org.apache.lucene.util.packed.DirectReader;
@ -46,7 +46,7 @@ public class TestDirectPacked extends LuceneTestCase {
writer.finish();
output.close();
IndexInput input = dir.openInput("foo", IOContext.DEFAULT);
LegacyNumericDocValues reader = DirectReader.getInstance(input.randomAccessSlice(0, input.length()), bitsPerValue, 0);
LongValues reader = DirectReader.getInstance(input.randomAccessSlice(0, input.length()), bitsPerValue, 0);
assertEquals(1, reader.get(0));
assertEquals(0, reader.get(1));
assertEquals(2, reader.get(2));
@ -110,7 +110,7 @@ public class TestDirectPacked extends LuceneTestCase {
writer.finish();
output.close();
IndexInput input = directory.openInput(name, IOContext.DEFAULT);
LegacyNumericDocValues reader = DirectReader.getInstance(input.randomAccessSlice(0, input.length()), bitsRequired, offset);
LongValues reader = DirectReader.getInstance(input.randomAccessSlice(0, input.length()), bitsRequired, offset);
for (int j = 0; j < original.length; j++) {
assertEquals("bpv=" + bpv, original[j], reader.get(j));
}

2
lucene/join/src/java/org/apache/lucene/search/join/ToParentBlockJoinQuery.java
View File

@ -203,7 +203,7 @@ public class ToParentBlockJoinQuery extends Query {
public abstract int[] swapChildDocs(int[] other);
}
static class BlockJoinScorer extends ChildrenMatchesScorer{
static class BlockJoinScorer extends ChildrenMatchesScorer {
private final Scorer childScorer;
private final BitSet parentBits;
private final ScoreMode scoreMode;

66
lucene/join/src/test/org/apache/lucene/search/join/TestBlockJoin.java
View File

@ -187,7 +187,73 @@ public class TestBlockJoin extends LuceneTestCase {
dir.close();
}
// You must use ToParentBlockJoinSearcher if you want to do BQ SHOULD queries:
public void testBQShouldJoinedChild() throws Exception {
final Directory dir = newDirectory();
final RandomIndexWriter w = new RandomIndexWriter(random(), dir);
final List<Document> docs = new ArrayList<>();
docs.add(makeJob("java", 2007));
docs.add(makeJob("python", 2010));
docs.add(makeResume("Lisa", "United Kingdom"));
w.addDocuments(docs);
docs.clear();
docs.add(makeJob("ruby", 2005));
docs.add(makeJob("java", 2006));
docs.add(makeResume("Frank", "United States"));
w.addDocuments(docs);
IndexReader r = w.getReader();
w.close();
IndexSearcher s = new ToParentBlockJoinIndexSearcher(r);
//IndexSearcher s = newSearcher(r, false);
//IndexSearcher s = new IndexSearcher(r);
// Create a filter that defines "parent" documents in the index - in this case resumes
BitSetProducer parentsFilter = new QueryBitSetProducer(new TermQuery(new Term("docType", "resume")));
CheckJoinIndex.check(r, parentsFilter);
// Define child document criteria (finds an example of relevant work experience)
BooleanQuery.Builder childQuery = new BooleanQuery.Builder();
childQuery.add(new BooleanClause(new TermQuery(new Term("skill", "java")), Occur.MUST));
childQuery.add(new BooleanClause(IntPoint.newRangeQuery("year", 2006, 2011), Occur.MUST));
// Define parent document criteria (find a resident in the UK)
Query parentQuery = new TermQuery(new Term("country", "United Kingdom"));
// Wrap the child document query to 'join' any matches
// up to corresponding parent:
ToParentBlockJoinQuery childJoinQuery = new ToParentBlockJoinQuery(childQuery.build(), parentsFilter, ScoreMode.Avg);
// Combine the parent and nested child queries into a single query for a candidate
BooleanQuery.Builder fullQuery = new BooleanQuery.Builder();
fullQuery.add(new BooleanClause(parentQuery, Occur.SHOULD));
fullQuery.add(new BooleanClause(childJoinQuery, Occur.SHOULD));
ToParentBlockJoinCollector c = new ToParentBlockJoinCollector(Sort.RELEVANCE, 1, true, true);
s.search(fullQuery.build(), c);
TopGroups<Integer> results = c.getTopGroups(childJoinQuery, null, 0, 10, 0, true);
assertEquals(1, results.totalGroupedHitCount);
assertEquals(1, results.groups.length);
final GroupDocs<Integer> group = results.groups[0];
assertEquals(1, group.totalHits);
assertFalse(Float.isNaN(group.score));
Document childDoc = s.doc(group.scoreDocs[0].doc);
//System.out.println(" doc=" + group.scoreDocs[0].doc);
assertEquals("java", childDoc.get("skill"));
assertNotNull(group.groupValue);
Document parentDoc = s.doc(group.groupValue);
assertEquals("Lisa", parentDoc.get("name"));
r.close();
dir.close();
}
public void testSimple() throws Exception {
final Directory dir = newDirectory();