manojpec commented on a change in pull request #4352:
URL: https://github.com/apache/hudi/pull/4352#discussion_r796987999
##########
File path:
hudi-common/src/main/java/org/apache/hudi/metadata/BaseTableMetadata.java
##########
@@ -146,12 +156,123 @@ protected BaseTableMetadata(HoodieEngineContext
engineContext, HoodieMetadataCon
.getAllFilesInPartitions(partitions);
}
+ @Override
+ public Option<ByteBuffer> getBloomFilter(final String partitionName, final
String fileName)
+ throws HoodieMetadataException {
+ if (!isBloomFilterIndexEnabled) {
+ LOG.error("Metadata bloom filter index is disabled!");
+ return Option.empty();
+ }
+
+ final Pair<String, String> partitionFileName = Pair.of(partitionName,
fileName);
+ Map<Pair<String, String>, ByteBuffer> bloomFilters =
getBloomFilters(Collections.singletonList(partitionFileName));
+ if (bloomFilters.isEmpty()) {
+ LOG.error("Meta index: missing bloom filter for partition: " +
partitionName + ", file: " + fileName);
+ return Option.empty();
+ }
+
+ ValidationUtils.checkState(bloomFilters.containsKey(partitionFileName));
+ return Option.of(bloomFilters.get(partitionFileName));
+ }
+
+ @Override
+ public Map<Pair<String, String>, ByteBuffer> getBloomFilters(final
List<Pair<String, String>> partitionNameFileNameList)
+ throws HoodieMetadataException {
+ if (!isBloomFilterIndexEnabled) {
+ LOG.error("Metadata bloom filter index is disabled!");
+ return Collections.emptyMap();
+ }
+ if (partitionNameFileNameList.isEmpty()) {
+ return Collections.emptyMap();
+ }
+
+ HoodieTimer timer = new HoodieTimer().startTimer();
+ Set<String> partitionIDFileIDSortedStrings = new TreeSet<>();
+ Map<String, Pair<String, String>> fileToKeyMap = new HashMap<>();
+ partitionNameFileNameList.forEach(partitionNameFileNamePair -> {
+ final String bloomKey = new
PartitionIndexID(partitionNameFileNamePair.getLeft()).asBase64EncodedString()
Review comment:
fixed
--
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]
