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

LUCENE-6643: Make lucene/grouping Filter-free. 

git-svn-id: https://svn.apache.org/repos/asf/lucene/dev/trunk@1688591 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Adrien Grand 2015-07-01 08:41:07 +00:00
parent 688c67f8ff
commit a9cc05ced1
4 changed files with 16 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
lucene/CHANGES.txt
View File

@ -152,6 +152,9 @@ API Changes
* LUCENE-6634: PKIndexSplitter now takes a Query instead of a Filter to decide
how to split an index. (Adrien Grand)
* LUCENE-6643: GroupingSearch from lucene/grouping was changed to take a Query
object to define groups instead of a Filter. (Adrien Grand)
Bug fixes
* LUCENE-6500: ParallelCompositeReader did not always call

10
lucene/grouping/src/java/org/apache/lucene/search/grouping/BlockGroupingCollector.java
View File

@ -23,7 +23,6 @@ import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.LeafReaderContext;
import org.apache.lucene.search.DocIdSetIterator;
import org.apache.lucene.search.FieldComparator;
import org.apache.lucene.search.Filter;
import org.apache.lucene.search.LeafCollector;
import org.apache.lucene.search.LeafFieldComparator;
import org.apache.lucene.search.Scorer;
@ -34,6 +33,7 @@ import org.apache.lucene.search.TopDocs;
import org.apache.lucene.search.TopDocsCollector;
import org.apache.lucene.search.TopFieldCollector;
import org.apache.lucene.search.TopScoreDocCollector;
import org.apache.lucene.search.Weight;
import org.apache.lucene.util.ArrayUtil;
import org.apache.lucene.util.PriorityQueue;
@ -73,7 +73,7 @@ public class BlockGroupingCollector extends SimpleCollector {
private final Sort groupSort;
private final int topNGroups;
private final Filter lastDocPerGroup;
private final Weight lastDocPerGroup;
// TODO: specialize into 2 classes, static "create" method:
private final boolean needsScores;
@ -214,10 +214,10 @@ public class BlockGroupingCollector extends SimpleCollector {
* in the withinGroupSort or because you plan to pass true
* for either getSscores or getMaxScores to {@link
* #getTopGroups}
* @param lastDocPerGroup a {@link Filter} that marks the
* @param lastDocPerGroup a {@link Weight} that marks the
* last document in each group.
*/
public BlockGroupingCollector(Sort groupSort, int topNGroups, boolean needsScores, Filter lastDocPerGroup) throws IOException {
public BlockGroupingCollector(Sort groupSort, int topNGroups, boolean needsScores, Weight lastDocPerGroup) throws IOException {
if (topNGroups < 1) {
throw new IllegalArgumentException("topNGroups must be >= 1 (got " + topNGroups + ")");
@ -480,7 +480,7 @@ public class BlockGroupingCollector extends SimpleCollector {
subDocUpto = 0;
docBase = readerContext.docBase;
//System.out.println("setNextReader base=" + docBase + " r=" + readerContext.reader);
lastDocPerGroupBits = lastDocPerGroup.getDocIdSet(readerContext, readerContext.reader().getLiveDocs()).iterator();
lastDocPerGroupBits = lastDocPerGroup.scorer(readerContext);
groupEndDocID = -1;
currentReaderContext = readerContext;

11
lucene/grouping/src/java/org/apache/lucene/search/grouping/GroupingSearch.java
View File

@ -20,12 +20,12 @@ package org.apache.lucene.search.grouping;
import org.apache.lucene.queries.function.ValueSource;
import org.apache.lucene.search.CachingCollector;
import org.apache.lucene.search.Collector;
import org.apache.lucene.search.Filter;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.MultiCollector;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.Sort;
import org.apache.lucene.search.SortField;
import org.apache.lucene.search.Weight;
import org.apache.lucene.search.grouping.function.FunctionAllGroupHeadsCollector;
import org.apache.lucene.search.grouping.function.FunctionAllGroupsCollector;
import org.apache.lucene.search.grouping.function.FunctionFirstPassGroupingCollector;
@ -55,7 +55,7 @@ public class GroupingSearch {
private final String groupField;
private final ValueSource groupFunction;
private final Map<?, ?> valueSourceContext;
private final Filter groupEndDocs;
private final Query groupEndDocs;
private Sort groupSort = Sort.RELEVANCE;
private Sort sortWithinGroup;
@ -101,13 +101,13 @@ public class GroupingSearch {
* Constructor for grouping documents by doc block.
* This constructor can only be used when documents belonging in a group are indexed in one block.
*
* @param groupEndDocs The filter that marks the last document in all doc blocks
* @param groupEndDocs The query that marks the last document in all doc blocks
*/
public GroupingSearch(Filter groupEndDocs) {
public GroupingSearch(Query groupEndDocs) {
this(null, null, null, groupEndDocs);
}
private GroupingSearch(String groupField, ValueSource groupFunction, Map<?, ?> valueSourceContext, Filter groupEndDocs) {
private GroupingSearch(String groupField, ValueSource groupFunction, Map<?, ?> valueSourceContext, Query groupEndDocs) {
this.groupField = groupField;
this.groupFunction = groupFunction;
this.valueSourceContext = valueSourceContext;
@ -233,6 +233,7 @@ public class GroupingSearch {
protected TopGroups<?> groupByDocBlock(IndexSearcher searcher, Query query, int groupOffset, int groupLimit) throws IOException {
int topN = groupOffset + groupLimit;
final Weight groupEndDocs = searcher.createNormalizedWeight(this.groupEndDocs, false);
BlockGroupingCollector c = new BlockGroupingCollector(groupSort, topN, includeScores, groupEndDocs);
searcher.search(query, c);
int topNInsideGroup = groupDocsOffset + groupDocsLimit;

7
lucene/grouping/src/test/org/apache/lucene/search/grouping/TestGrouping.java
View File

@ -51,14 +51,11 @@ import org.apache.lucene.index.Term;
import org.apache.lucene.queries.function.ValueSource;
import org.apache.lucene.queries.function.valuesource.BytesRefFieldSource;
import org.apache.lucene.search.CachingCollector;
import org.apache.lucene.search.CachingWrapperQuery;
import org.apache.lucene.search.Collector;
import org.apache.lucene.search.FieldDoc;
import org.apache.lucene.search.Filter;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.MultiCollector;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.QueryWrapperFilter;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.Sort;
import org.apache.lucene.search.SortField;
@ -798,7 +795,7 @@ public class TestGrouping extends LuceneTestCase {
// group, so we can use single pass collector
dirBlocks = newDirectory();
rBlocks = getDocBlockReader(dirBlocks, groupDocs);
final Filter lastDocInBlock = new QueryWrapperFilter(new TermQuery(new Term("groupend", "x")));
final Query lastDocInBlock = new TermQuery(new Term("groupend", "x"));
final NumericDocValues docIDToIDBlocks = MultiDocValues.getNumericValues(rBlocks, "id");
assertNotNull(docIDToIDBlocks);
@ -1054,7 +1051,7 @@ public class TestGrouping extends LuceneTestCase {
}
final boolean needsScores = getScores || getMaxScores || docSort == null;
final BlockGroupingCollector c3 = new BlockGroupingCollector(groupSort, groupOffset+topNGroups, needsScores, lastDocInBlock);
final BlockGroupingCollector c3 = new BlockGroupingCollector(groupSort, groupOffset+topNGroups, needsScores, sBlocks.createNormalizedWeight(lastDocInBlock, false));
final TermAllGroupsCollector allGroupsCollector2;
final Collector c4;
if (doAllGroups) {