bryndenZh commented on code in PR #6407:
URL: https://github.com/apache/paimon/pull/6407#discussion_r2452305121
##########
paimon-core/src/main/java/org/apache/paimon/index/IndexFileHandler.java:
##########
@@ -87,6 +101,123 @@ public Optional<IndexFileMeta> scanHashIndex(
return result.isEmpty() ? Optional.empty() :
Optional.of(result.get(0));
}
+ public void withCacheMetrics(@Nullable CacheMetrics cacheMetrics) {
+ this.cacheMetrics = cacheMetrics;
+ }
+
+ @Nullable
+ // Construct DataFile -> DeletionFile based on IndexFileMeta
+ public Map<String, DeletionFile> extractDeletionFileByMeta(
+ BinaryRow partition, Integer bucket, IndexFileMeta fileMeta) {
+ if (fileMeta.dvRanges() != null && fileMeta.dvRanges().size() > 0) {
+ Map<String, DeletionFile> result = new HashMap<>();
+ for (DeletionVectorMeta dvMeta : fileMeta.dvRanges().values()) {
+ result.put(
+ dvMeta.dataFileName(),
+ new DeletionFile(
+ dvIndex(partition,
bucket).path(fileMeta).toString(),
+ dvMeta.offset(),
+ dvMeta.length(),
+ dvMeta.cardinality()));
+ }
+ return result;
+ }
+ return null;
+ }
+
+ // Scan DV index file of given partition buckets
+ // returns <DataFile: DeletionFile> map grouped by partition and bucket
+ public Map<Pair<BinaryRow, Integer>, Map<String, DeletionFile>>
scanDVIndex(
+ Snapshot snapshot, Set<Pair<BinaryRow, Integer>> partitionBuckets)
{
+ Map<Pair<BinaryRow, Integer>, List<IndexFileMeta>> partitionFileMetas =
+ scan(
+ snapshot,
+ DELETION_VECTORS_INDEX,
+
partitionBuckets.stream().map(Pair::getLeft).collect(Collectors.toSet()));
+ Map<Pair<BinaryRow, Integer>, Map<String, DeletionFile>> result = new
HashMap<>();
+ partitionBuckets.forEach(
Review Comment:
I think unnecessary buckets need to be filtered out?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
