gargvishesh commented on code in PR #15965: URL: https://github.com/apache/druid/pull/15965#discussion_r1535066315
########## extensions-core/multi-stage-query/src/main/java/org/apache/druid/msq/exec/ControllerImpl.java: ########## @@ -1719,9 +1731,129 @@ private void publishSegmentsIfNeeded( //noinspection unchecked @SuppressWarnings("unchecked") final Set<DataSegment> segments = (Set<DataSegment>) queryKernel.getResultObjectForStage(finalStageId); + + Function<Set<DataSegment>, Set<DataSegment>> compactionStateAnnotateFunction = Function.identity(); + + Boolean storeCompactionState = (Boolean) task.getQuerySpec() + .getQuery() + .getContext() + .get(Tasks.STORE_COMPACTION_STATE_KEY); + + if (storeCompactionState == null) { + storeCompactionState = Tasks.DEFAULT_STORE_COMPACTION_STATE; + + } + + if (!segments.isEmpty() && storeCompactionState) { + DataSchema dataSchema = ((SegmentGeneratorFrameProcessorFactory) queryKernel.getStageDefinition(finalStageId) + .getProcessorFactory()).getDataSchema(); + + + ShardSpec shardSpec = segments.stream().findFirst().get().getShardSpec(); + + compactionStateAnnotateFunction = compactionStateAnnotateFunction( + task(), + context.jsonMapper(), + dataSchema, + shardSpec, + queryDef.getQueryId() + ); + + } + log.info("Query [%s] publishing %d segments.", queryDef.getQueryId(), segments.size()); - publishAllSegments(segments); + publishAllSegments(compactionStateAnnotateFunction.apply(segments)); + } + } + + public static Function<Set<DataSegment>, Set<DataSegment>> compactionStateAnnotateFunction( + MSQControllerTask task, ObjectMapper jsonMapper, DataSchema dataSchema, ShardSpec shardSpec, String queryId + ) + { + DataSourceMSQDestination destination = (DataSourceMSQDestination) task.getQuerySpec().getDestination(); + if (!destination.isReplaceTimeChunks()) { + // Only do this for replace queries, whether originating directly or via compaction + log.error("Query [%s] skipping storing compaction state in segments as query not of type REPLACE.", queryId); + return Function.identity(); } + + GranularitySpec granularitySpec = dataSchema.getGranularitySpec(); + + if (task.getQuerySpec().getQuery().getContext().get(DruidSqlInsert.SQL_INSERT_SEGMENT_GRANULARITY) == null) { Review Comment: Not required at all actually, since the segmentGranularity extraction function used later will never return null. Removed it. -- 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...@druid.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@druid.apache.org For additional commands, e-mail: commits-h...@druid.apache.org