honeymoose
/
OpenSearch
mirror of https://github.com/honeymoose/OpenSearch.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Fix AOOBE when setting min_doc_count to 0 in significant_terms (#60823) 

This commit fixes the computation of the subset size on empty buckets (doc count of 0).
The aggregator test refactoring in #60683 revealed this bug.
This commit is contained in:
Jim Ferenczi 2020-08-06 18:01:54 +02:00 committed by jimczi
parent fb7c431d8d
commit 14980ff97e
1 changed files with 9 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
server/src/main/java/org/elasticsearch/search/aggregations/bucket/terms/GlobalOrdinalsStringTermsAggregator.java
View File

@ -797,9 +797,14 @@ public class GlobalOrdinalsStringTermsAggregator extends AbstractStringTermsAggr
return new SignificantStringTerms.Bucket(new BytesRef(), 0, 0, 0, 0, null, format, 0); return new SignificantStringTerms.Bucket(new BytesRef(), 0, 0, 0, 0, null, format, 0);
} }
private long subsetSize(long owningBucketOrd) {
// if the owningBucketOrd is not in the array that means the bucket is empty so the size has to be 0
return owningBucketOrd < subsetSizes.size() ? subsetSizes.get(owningBucketOrd) : 0;
}
@Override @Override
BucketUpdater<SignificantStringTerms.Bucket> bucketUpdater(long owningBucketOrd) throws IOException { BucketUpdater<SignificantStringTerms.Bucket> bucketUpdater(long owningBucketOrd) throws IOException {
long subsetSize = subsetSizes.get(owningBucketOrd); long subsetSize = subsetSize(owningBucketOrd);
return (spare, globalOrd, bucketOrd, docCount) -> { return (spare, globalOrd, bucketOrd, docCount) -> {
spare.bucketOrd = bucketOrd; spare.bucketOrd = bucketOrd;
oversizedCopy(lookupGlobalOrd.apply(globalOrd), spare.termBytes); oversizedCopy(lookupGlobalOrd.apply(globalOrd), spare.termBytes);
@ -839,7 +844,7 @@ public class GlobalOrdinalsStringTermsAggregator extends AbstractStringTermsAggr
bucketCountThresholds.getMinDocCount(), bucketCountThresholds.getMinDocCount(),
metadata(), metadata(),
format, format,
subsetSizes.get(owningBucketOrd), subsetSize(owningBucketOrd),
supersetSize, supersetSize,
significanceHeuristic, significanceHeuristic,
Arrays.asList(topBuckets) Arrays.asList(topBuckets)