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

Reduce specialization in TopScoreDocCollector. (#14038) 

The specialization of `SimpleCollector` vs. `PagingCollector` only helps save a
null check, so it's probably not worth the complexity. Benchmarks cannot see a
difference with this change.
This commit is contained in:
Adrien Grand 2024-12-04 15:12:26 +01:00
parent 4947c0f746
commit 17bd129cea
3 changed files with 135 additions and 223 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

167
lucene/core/src/java/org/apache/lucene/search/TopScoreDocCollector.java
View File

@ -29,87 +29,19 @@ import org.apache.lucene.index.LeafReaderContext;
* <p><b>NOTE</b>: The values {@link Float#NaN} and {@link Float#NEGATIVE_INFINITY} are not valid
* scores. This collector will not properly collect hits with such scores.
*/
public abstract class TopScoreDocCollector extends TopDocsCollector<ScoreDoc> {
/** Scorable leaf collector */
public abstract static class ScorerLeafCollector implements LeafCollector {
protected Scorable scorer;
@Override
public void setScorer(Scorable scorer) throws IOException {
this.scorer = scorer;
}
}
static class SimpleTopScoreDocCollector extends TopScoreDocCollector {
SimpleTopScoreDocCollector(
int numHits, int totalHitsThreshold, MaxScoreAccumulator minScoreAcc) {
super(numHits, totalHitsThreshold, minScoreAcc);
}
@Override
public LeafCollector getLeafCollector(LeafReaderContext context) throws IOException {
// reset the minimum competitive score
docBase = context.docBase;
minCompetitiveScore = 0f;
return new ScorerLeafCollector() {
@Override
public void setScorer(Scorable scorer) throws IOException {
super.setScorer(scorer);
if (minScoreAcc == null) {
updateMinCompetitiveScore(scorer);
} else {
updateGlobalMinCompetitiveScore(scorer);
}
}
@Override
public void collect(int doc) throws IOException {
float score = scorer.score();
int hitCountSoFar = ++totalHits;
if (minScoreAcc != null && (hitCountSoFar & minScoreAcc.modInterval) == 0) {
updateGlobalMinCompetitiveScore(scorer);
}
if (score <= pqTop.score) {
// Note: for queries that match lots of hits, this is the common case: most hits are not
// competitive.
if (hitCountSoFar == totalHitsThreshold + 1) {
// we just reached totalHitsThreshold, we can start setting the min
// competitive score now
updateMinCompetitiveScore(scorer);
}
// Since docs are returned in-order (i.e., increasing doc Id), a document
// with equal score to pqTop.score cannot compete since HitQueue favors
// documents with lower doc Ids. Therefore reject those docs too.
} else {
collectCompetitiveHit(doc, score);
}
}
private void collectCompetitiveHit(int doc, float score) throws IOException {
pqTop.doc = doc + docBase;
pqTop.score = score;
pqTop = pq.updateTop();
updateMinCompetitiveScore(scorer);
}
};
}
}
static class PagingTopScoreDocCollector extends TopScoreDocCollector {
public class TopScoreDocCollector extends TopDocsCollector<ScoreDoc> {
private final ScoreDoc after;
final int totalHitsThreshold;
final MaxScoreAccumulator minScoreAcc;
PagingTopScoreDocCollector(
// prevents instantiation
TopScoreDocCollector(
int numHits, ScoreDoc after, int totalHitsThreshold, MaxScoreAccumulator minScoreAcc) {
super(numHits, totalHitsThreshold, minScoreAcc);
super(new HitQueue(numHits, true));
this.after = after;
this.totalHitsThreshold = totalHitsThreshold;
this.minScoreAcc = minScoreAcc;
}
@Override
@ -133,15 +65,35 @@ public abstract class TopScoreDocCollector extends TopDocsCollector<ScoreDoc> {
}
@Override
public LeafCollector getLeafCollector(LeafReaderContext context) throws IOException {
docBase = context.docBase;
final int afterDoc = after.doc - context.docBase;
minCompetitiveScore = 0f;
public ScoreMode scoreMode() {
return totalHitsThreshold == Integer.MAX_VALUE ? ScoreMode.COMPLETE : ScoreMode.TOP_SCORES;
}
@Override
public LeafCollector getLeafCollector(LeafReaderContext context) throws IOException {
final int docBase = context.docBase;
final ScoreDoc after = this.after;
final float afterScore;
final int afterDoc;
if (after == null) {
afterScore = Float.POSITIVE_INFINITY;
afterDoc = DocIdSetIterator.NO_MORE_DOCS;
} else {
afterScore = after.score;
afterDoc = after.doc - context.docBase;
}
return new LeafCollector() {
private Scorable scorer;
// HitQueue implements getSentinelObject to return a ScoreDoc, so we know
// that at this point top() is already initialized.
private ScoreDoc pqTop = pq.top();
private float minCompetitiveScore;
return new ScorerLeafCollector() {
@Override
public void setScorer(Scorable scorer) throws IOException {
super.setScorer(scorer);
this.scorer = scorer;
if (minScoreAcc == null) {
updateMinCompetitiveScore(scorer);
} else {
@ -159,8 +111,7 @@ public abstract class TopScoreDocCollector extends TopDocsCollector<ScoreDoc> {
updateGlobalMinCompetitiveScore(scorer);
}
float afterScore = after.score;
if (score > afterScore || (score == afterScore && doc <= afterDoc)) {
if (after != null && (score > afterScore || (score == afterScore && doc <= afterDoc))) {
// hit was collected on a previous page
if (totalHitsRelation == TotalHits.Relation.EQUAL_TO) {
// we just reached totalHitsThreshold, we can start setting the min
@ -193,42 +144,8 @@ public abstract class TopScoreDocCollector extends TopDocsCollector<ScoreDoc> {
pqTop = pq.updateTop();
updateMinCompetitiveScore(scorer);
}
};
}
}
int docBase;
ScoreDoc pqTop;
final int totalHitsThreshold;
final MaxScoreAccumulator minScoreAcc;
float minCompetitiveScore;
// prevents instantiation
TopScoreDocCollector(int numHits, int totalHitsThreshold, MaxScoreAccumulator minScoreAcc) {
super(new HitQueue(numHits, true));
// HitQueue implements getSentinelObject to return a ScoreDoc, so we know
// that at this point top() is already initialized.
pqTop = pq.top();
this.totalHitsThreshold = totalHitsThreshold;
this.minScoreAcc = minScoreAcc;
}
@Override
protected TopDocs newTopDocs(ScoreDoc[] results, int start) {
if (results == null) {
return EMPTY_TOPDOCS;
}
return new TopDocs(new TotalHits(totalHits, totalHitsRelation), results);
}
@Override
public ScoreMode scoreMode() {
return totalHitsThreshold == Integer.MAX_VALUE ? ScoreMode.COMPLETE : ScoreMode.TOP_SCORES;
}
protected void updateGlobalMinCompetitiveScore(Scorable scorer) throws IOException {
private void updateGlobalMinCompetitiveScore(Scorable scorer) throws IOException {
assert minScoreAcc != null;
long maxMinScore = minScoreAcc.getRaw();
if (maxMinScore != Long.MIN_VALUE) {
@ -245,14 +162,12 @@ public abstract class TopScoreDocCollector extends TopDocsCollector<ScoreDoc> {
}
}
protected void updateMinCompetitiveScore(Scorable scorer) throws IOException {
private void updateMinCompetitiveScore(Scorable scorer) throws IOException {
if (totalHits > totalHitsThreshold) {
// since we tie-break on doc id and collect in doc id order, we can require
// the next float
// since we tie-break on doc id and collect in doc id order, we can require the next float
// pqTop is never null since TopScoreDocCollector fills the priority queue with sentinel
// values
// if the top element is a sentinel value, its score will be -Infty and the below logic is
// still valid
// values if the top element is a sentinel value, its score will be -Infty and the below
// logic is still valid
float localMinScore = Math.nextUp(pqTop.score);
if (localMinScore > minCompetitiveScore) {
scorer.setMinCompetitiveScore(localMinScore);
@ -266,4 +181,6 @@ public abstract class TopScoreDocCollector extends TopDocsCollector<ScoreDoc> {
}
}
}
};
}
}

8
lucene/core/src/java/org/apache/lucene/search/TopScoreDocCollectorManager.java
View File

@ -125,13 +125,7 @@ public class TopScoreDocCollectorManager
@Override
public TopScoreDocCollector newCollector() {
if (after == null) {
return new TopScoreDocCollector.SimpleTopScoreDocCollector(
numHits, totalHitsThreshold, minScoreAcc);
} else {
return new TopScoreDocCollector.PagingTopScoreDocCollector(
numHits, after, totalHitsThreshold, minScoreAcc);
}
return new TopScoreDocCollector(numHits, after, totalHitsThreshold, minScoreAcc);
}
@Override

7
lucene/sandbox/src/java/org/apache/lucene/sandbox/search/LargeNumHitsTopDocsCollector.java
View File

@ -32,7 +32,6 @@ import org.apache.lucene.search.Scorable;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.ScoreMode;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.search.TopScoreDocCollector;
import org.apache.lucene.search.TotalHits;
/**
@ -63,11 +62,13 @@ public final class LargeNumHitsTopDocsCollector implements Collector {
@Override
public LeafCollector getLeafCollector(LeafReaderContext context) {
final int docBase = context.docBase;
return new TopScoreDocCollector.ScorerLeafCollector() {
return new LeafCollector() {
private Scorable scorer;
@Override
public void setScorer(Scorable scorer) throws IOException {
super.setScorer(scorer);
this.scorer = scorer;
}
@Override