manojpec commented on a change in pull request #4352: URL: https://github.com/apache/hudi/pull/4352#discussion_r796261359
########## File path: hudi-common/src/main/java/org/apache/hudi/metadata/HoodieTableMetadataUtil.java ########## @@ -319,9 +616,88 @@ private static void processRollbackMetadata(HoodieActiveTimeline metadataTableTi return records; } + /** + * Convert rollback action metadata to bloom filter index records. + */ + private static List<HoodieRecord> convertFilesToBloomFilterRecords(HoodieEngineContext engineContext, + HoodieTableMetaClient dataMetaClient, + Map<String, List<String>> partitionToDeletedFiles, + Map<String, Map<String, Long>> partitionToAppendedFiles, + String instantTime) { + List<HoodieRecord> records = new LinkedList<>(); + partitionToDeletedFiles.forEach((partitionName, deletedFileList) -> deletedFileList.forEach(deletedFile -> { + if (!FSUtils.isBaseFile(new Path(deletedFile))) { + return; + } + + final String partition = partitionName.equals(EMPTY_PARTITION_NAME) ? NON_PARTITIONED_NAME : partitionName; + records.add(HoodieMetadataPayload.createBloomFilterMetadataRecord( + partition, deletedFile, instantTime, ByteBuffer.allocate(0), true)); + })); + + partitionToAppendedFiles.forEach((partitionName, appendedFileMap) -> { + final String partition = partitionName.equals(EMPTY_PARTITION_NAME) ? NON_PARTITIONED_NAME : partitionName; + appendedFileMap.forEach((appendedFile, length) -> { + if (!FSUtils.isBaseFile(new Path(appendedFile))) { + return; + } + final String pathWithPartition = partitionName + "/" + appendedFile; + final Path appendedFilePath = new Path(dataMetaClient.getBasePath(), pathWithPartition); + try { + HoodieFileReader<IndexedRecord> fileReader = + HoodieFileReaderFactory.getFileReader(dataMetaClient.getHadoopConf(), appendedFilePath); + final BloomFilter fileBloomFilter = fileReader.readBloomFilter(); + if (fileBloomFilter == null) { + LOG.error("Failed to read bloom filter for " + appendedFilePath); + return; + } + ByteBuffer bloomByteBuffer = ByteBuffer.wrap(fileBloomFilter.serializeToString().getBytes()); + HoodieRecord record = HoodieMetadataPayload.createBloomFilterMetadataRecord( + partition, appendedFile, instantTime, bloomByteBuffer, false); + records.add(record); + fileReader.close(); + } catch (IOException e) { + LOG.error("Failed to get bloom filter for file: " + appendedFilePath); + } + }); + }); + return records; + } + + /** + * Convert rollback action metadata to column stats index records. + */ + private static List<HoodieRecord> convertFilesToColumnStatsRecords(HoodieEngineContext engineContext, + HoodieTableMetaClient datasetMetaClient, + Map<String, List<String>> partitionToDeletedFiles, + Map<String, Map<String, Long>> partitionToAppendedFiles, + String instantTime) { + List<HoodieRecord> records = new LinkedList<>(); + List<String> latestColumns = getLatestColumns(datasetMetaClient); + partitionToDeletedFiles.forEach((partitionName, deletedFileList) -> deletedFileList.forEach(deletedFile -> { Review comment: Right, HUDI-3356 will address this. -- 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: commits-unsubscr...@hudi.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org