nsivabalan commented on a change in pull request #1091: [HUDI-389] Fixing Index look up to return right partitions for a given key along with fileId with Global Bloom URL: https://github.com/apache/incubator-hudi/pull/1091#discussion_r361068247
########## File path: hudi-client/src/main/java/org/apache/hudi/index/bloom/HoodieGlobalBloomIndex.java ########## @@ -98,26 +92,34 @@ public HoodieGlobalBloomIndex(HoodieWriteConfig config) { String recordKey = partitionRecordKeyPair._2(); String partitionPath = partitionRecordKeyPair._1(); - return indexFileFilter.getMatchingFiles(partitionPath, recordKey).stream() - .map(file -> new Tuple2<>(file, new HoodieKey(recordKey, indexToPartitionMap.get(file)))) + return indexFileFilter.getMatchingFilesAndPartition(partitionPath, recordKey).stream() + .map(partitionFileIdPair -> new Tuple2<>(partitionFileIdPair.getRight(), + new HoodieKey(recordKey, partitionFileIdPair.getLeft()))) .collect(Collectors.toList()); }).flatMap(List::iterator); } - /** * Tagging for global index should only consider the record key. */ @Override protected JavaRDD<HoodieRecord<T>> tagLocationBacktoRecords( JavaPairRDD<HoodieKey, HoodieRecordLocation> keyFilenamePairRDD, JavaRDD<HoodieRecord<T>> recordRDD) { - JavaPairRDD<String, HoodieRecord<T>> rowKeyRecordPairRDD = + + JavaPairRDD<String, HoodieRecord<T>> incomingRowKeyRecordPairRDD = recordRDD.mapToPair(record -> new Tuple2<>(record.getRecordKey(), record)); - // Here as the recordRDD might have more data than rowKeyRDD (some rowKeys' fileId is null), - // so we do left outer join. - return rowKeyRecordPairRDD.leftOuterJoin(keyFilenamePairRDD.mapToPair(p -> new Tuple2<>(p._1.getRecordKey(), p._2))) - .values().map(value -> getTaggedRecord(value._1, Option.ofNullable(value._2.orNull()))); + JavaPairRDD<String, Tuple2<HoodieRecordLocation, HoodieKey>> existingRecordKeyToRecordLocationHoodieKeyMap = + keyFilenamePairRDD.mapToPair(p -> new Tuple2<>(p._1.getRecordKey(), new Tuple2<>(p._2, p._1))); + + return incomingRowKeyRecordPairRDD.leftOuterJoin(existingRecordKeyToRecordLocationHoodieKeyMap).values().map(record -> { + if (record._2().isPresent()) { + // Record key matched to file + return getTaggedRecord(new HoodieRecord<>(record._2.get()._2, record._1.getData()), Option.ofNullable(record._2.get()._1)); Review comment: yeah. thats what we are doing. ---------------------------------------------------------------- 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. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services