nsivabalan commented on a change in pull request #1187: [HUDI-499] Allow update partition path with GLOBAL_BLOOM URL: https://github.com/apache/incubator-hudi/pull/1187#discussion_r369560088
########## File path: hudi-client/src/main/java/org/apache/hudi/index/bloom/HoodieGlobalBloomIndex.java ########## @@ -114,14 +117,24 @@ public HoodieGlobalBloomIndex(HoodieWriteConfig config) { keyLocationPairRDD.mapToPair(p -> new Tuple2<>(p._1.getRecordKey(), new Tuple2<>(p._2, p._1))); // Here as the recordRDD might have more data than rowKeyRDD (some rowKeys' fileId is null), so we do left outer join. - return incomingRowKeyRecordPairRDD.leftOuterJoin(existingRecordKeyToRecordLocationHoodieKeyMap).values().map(record -> { + return incomingRowKeyRecordPairRDD.leftOuterJoin(existingRecordKeyToRecordLocationHoodieKeyMap).values().flatMap(record -> { final HoodieRecord<T> hoodieRecord = record._1; final Optional<Tuple2<HoodieRecordLocation, HoodieKey>> recordLocationHoodieKeyPair = record._2; if (recordLocationHoodieKeyPair.isPresent()) { // Record key matched to file - return getTaggedRecord(new HoodieRecord<>(recordLocationHoodieKeyPair.get()._2, hoodieRecord.getData()), Option.ofNullable(recordLocationHoodieKeyPair.get()._1)); + if (config.getGlobalBloomIndexShouldUpdatePartitionPath() + && !recordLocationHoodieKeyPair.get()._2.getPartitionPath().equals(hoodieRecord.getPartitionPath())) { + HoodieRecord<T> emptyRecord = new HoodieRecord(recordLocationHoodieKeyPair.get()._2, + new EmptyHoodieRecordPayload()); + HoodieRecord<T> taggedRecord = getTaggedRecord(hoodieRecord, Option.empty()); + return Arrays.asList(emptyRecord, taggedRecord).iterator(); + } else { + return Collections.singletonList( Review comment: can we add a comment here mentioning which branch this else part serves. For eg, "Either if partition path matches from incoming record to those in index, or if config value for partition path update is set to false, choose the partition path from index and update the record, ignoring the partition from incoming record". ---------------------------------------------------------------- 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