Nitin-Kashyap commented on code in PR #27784: URL: https://github.com/apache/doris/pull/27784#discussion_r1418803158
########## fe/fe-core/src/main/java/org/apache/doris/planner/external/HiveScanNode.java: ########## @@ -423,4 +430,37 @@ protected TFileCompressType getFileCompressType(FileSplit fileSplit) throws User } return compressType; } + + @Override + public DataPartition constructInputPartitionByDistributionInfo() { + if (hmsTable.isBucketedTable()) { + DistributionInfo distributionInfo = hmsTable.getDefaultDistributionInfo(); + if (!(distributionInfo instanceof HashDistributionInfo)) { + return DataPartition.RANDOM; + } + List<Column> distributeColumns = ((HiveExternalDistributionInfo) distributionInfo).getDistributionColumns(); + List<Expr> dataDistributeExprs = Lists.newArrayList(); + for (Column column : distributeColumns) { + SlotRef slotRef = new SlotRef(desc.getRef().getName(), column.getName()); + dataDistributeExprs.add(slotRef); + } + return DataPartition.hashPartitioned(dataDistributeExprs, THashType.SPARK_MURMUR32); + } + + return DataPartition.RANDOM; + } + + public HMSExternalTable getHiveTable() { + return hmsTable; + } + + @Override + public THashType getHashType() { + if (hmsTable.isBucketedTable() + && hmsTable.getDefaultDistributionInfo() instanceof HashDistributionInfo) { Review Comment: hmsTable.isBucketedTable() shall retun true only when its generated by Spark; I share remove the spark specific check once we add hive support as well..  -- 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...@doris.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@doris.apache.org For additional commands, e-mail: commits-h...@doris.apache.org