Created
June 19, 2015 05:18
-
-
Save rjernst/4c0bb396b9ad981387af to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Index: src/java/org/apache/lucene/search/ConjunctionDISI.java | |
=================================================================== | |
--- src/java/org/apache/lucene/search/ConjunctionDISI.java (revision 1681184) | |
+++ src/java/org/apache/lucene/search/ConjunctionDISI.java (working copy) | |
@@ -38,13 +38,7 @@ | |
final List<DocIdSetIterator> allIterators = new ArrayList<>(); | |
final List<TwoPhaseIterator> twoPhaseIterators = new ArrayList<>(); | |
for (DocIdSetIterator iter : iterators) { | |
- TwoPhaseIterator twoPhaseIter = TwoPhaseIterator.asTwoPhaseIterator(iter); | |
- if (twoPhaseIter != null) { | |
- allIterators.add(twoPhaseIter.approximation()); | |
- twoPhaseIterators.add(twoPhaseIter); | |
- } else { // no approximation support, use the iterator as-is | |
- allIterators.add(iter); | |
- } | |
+ collapseSubs(iter, allIterators, twoPhaseIterators); | |
} | |
if (twoPhaseIterators.isEmpty()) { | |
@@ -54,6 +48,25 @@ | |
} | |
} | |
+ // collapse sub conjunctions into this conjunction | |
+ private static void collapseSubs(DocIdSetIterator disi, List<DocIdSetIterator> allIterators, List<TwoPhaseIterator> twoPhaseIterators) { | |
+ if (disi instanceof ConjunctionDISI) { | |
+ ConjunctionDISI conjunction = (ConjunctionDISI)disi; | |
+ collapseSubs(conjunction.lead, allIterators, twoPhaseIterators); | |
+ for (DocIdSetIterator sub : conjunction.others) { | |
+ collapseSubs(sub, allIterators, twoPhaseIterators); | |
+ } | |
+ } else { | |
+ TwoPhaseIterator twoPhaseIter = TwoPhaseIterator.asTwoPhaseIterator(disi); | |
+ if (twoPhaseIter != null) { | |
+ allIterators.add(twoPhaseIter.approximation()); | |
+ twoPhaseIterators.add(twoPhaseIter); | |
+ } else { // no approximation support, use the iterator as-is | |
+ allIterators.add(disi); | |
+ } | |
+ } | |
+ } | |
+ | |
final DocIdSetIterator lead; | |
final DocIdSetIterator[] others; | |
Index: src/test/org/apache/lucene/search/TestConjunctionDISI.java | |
=================================================================== | |
--- src/test/org/apache/lucene/search/TestConjunctionDISI.java (revision 1681184) | |
+++ src/test/org/apache/lucene/search/TestConjunctionDISI.java (working copy) | |
@@ -19,6 +19,8 @@ | |
import java.io.IOException; | |
import java.util.Arrays; | |
+import java.util.LinkedList; | |
+import java.util.List; | |
import org.apache.lucene.util.BitDocIdSet; | |
import org.apache.lucene.util.FixedBitSet; | |
@@ -244,4 +246,45 @@ | |
} | |
} | |
+ public void testCollapseSubConjunctions() throws IOException { | |
+ final int iters = atLeast(100); | |
+ for (int iter = 0; iter < iters; ++iter) { | |
+ final int maxDoc = TestUtil.nextInt(random(), 100, 10000); | |
+ final int numIterators = TestUtil.nextInt(random(), 5, 10); | |
+ final FixedBitSet[] sets = new FixedBitSet[numIterators]; | |
+ final List<DocIdSetIterator> iterators = new LinkedList<>(); | |
+ for (int i = 0; i < numIterators; ++i) { | |
+ final FixedBitSet set = randomSet(maxDoc); | |
+ if (random().nextBoolean()) { | |
+ // simple iterator | |
+ sets[i] = set; | |
+ iterators.add(new BitDocIdSet(set).iterator()); | |
+ } else { | |
+ // scorer with approximation | |
+ final FixedBitSet confirmed = clearRandomBits(set); | |
+ sets[i] = confirmed; | |
+ final TwoPhaseIterator approximation = approximation(new BitDocIdSet(set).iterator(), confirmed); | |
+ iterators.add(scorer(approximation)); | |
+ } | |
+ } | |
+ | |
+ // make some sub sequences into sub conjunctions | |
+ final int subIters = atLeast(3); | |
+ for (int subIter = 0; subIter < subIters && iterators.size() > 3; ++subIter) { | |
+ final int subSeqStart = TestUtil.nextInt(random(), 0, iterators.size() - 2); | |
+ final int subSeqEnd = TestUtil.nextInt(random(), subSeqStart + 2, iterators.size()); | |
+ System.out.println("cutting [" + subSeqStart + ":" + subSeqEnd + ") from iterators of size " + iterators.size()); | |
+ final ConjunctionDISI subConjunction = ConjunctionDISI.intersect(iterators.subList(subSeqStart, subSeqEnd)); | |
+ iterators.set(subSeqStart, subConjunction); | |
+ int toRemove = subSeqEnd - subSeqStart - 1; | |
+ while (toRemove-- > 0) { | |
+ iterators.remove(subSeqStart + 1); | |
+ } | |
+ } | |
+ | |
+ final ConjunctionDISI conjunction = ConjunctionDISI.intersect(iterators); | |
+ assertEquals(intersect(sets), toBitSet(maxDoc, conjunction)); | |
+ } | |
+ } | |
+ | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment