[GitHub] [pinot] sahoss commented on issue #10316: Add JSON integration tests to LLCRealtimeClusterIntegrationTest

[via GitHub]

sahoss commented on issue #10316:
URL: https://github.com/apache/pinot/issues/10316#issuecomment-1453573271

   So here is my investigation so far:
   
   ### Reproducible example:
   
   **schema.json**
   
   
   ```
   {
     "schemaName": "sample",
     "dimensionFieldSpecs": [
       {
         "name": "data",
         "dataType": "JSON"
       }
     ],
     "metricFieldSpecs": [],
     "dateTimeFieldSpecs": [
       {
         "name": "timestamp",
         "dataType": "LONG",
         "format": "1:MILLISECONDS:EPOCH",
         "granularity": "1:MILLISECONDS"
       }
     ]
   }
   ```
   
   **tableconfig-realtime.json**
   ```
   {
     "tableName": "sample",
     "tableType": "REALTIME",
     "segmentsConfig": {
       "timeColumnName": "timestamp",
       "timeType": "MILLISECONDS",
       "schemaName": "sample",
       "replicasPerPartition": "1"
     },
     "tenants": {},
     "tableIndexConfig": {
       "loadMode": "MMAP",
       "streamConfigs": {
         "streamType": "kafka",
         "stream.kafka.consumer.type": "lowlevel",
         "stream.kafka.topic.name": "sample",
         "stream.kafka.decoder.class.name": 
"org.apache.pinot.plugin.stream.kafka.KafkaJSONMessageDecoder",
         "stream.kafka.consumer.factory.class.name": 
"org.apache.pinot.plugin.stream.kafka20.KafkaConsumerFactory",
         "stream.kafka.broker.list": "localhost:9092",
         "realtime.segment.flush.threshold.time": "3600000",
         "realtime.segment.flush.threshold.rows": "50000",
         "stream.kafka.consumer.prop.auto.offset.reset": "smallest"
       }
     },
     "metadata": {
       "customConfigs": {}
     }
   }
   ```
   
   Input Json record:
   ```
   {"data": {"key1": [], "key2": [1, 2], "key3": "value"}, "timestamp": 
1677851924425}
   
   ```
   
   
   Result stored in segment:
   ```
   {
     "resultTable": {
       "dataSchema": {
         "columnNames": [
           "data",
           "timestamp"
         ],
         "columnDataTypes": [
           "JSON",
           "LONG"
         ]
       },
       "rows": [
         [
           "{\"key2\":[1,2],\"key3\":\"value\"}",
           1677851018568
         ]
       ]
     },
     "exceptions": [],
     "numServersQueried": 1,
     "numServersResponded": 1,
     "numSegmentsQueried": 1,
     "numSegmentsProcessed": 1,
     "numSegmentsMatched": 1,
     "numConsumingSegmentsQueried": 1,
     "numConsumingSegmentsProcessed": 1,
     "numConsumingSegmentsMatched": 1,
     "numDocsScanned": 1,
     "numEntriesScannedInFilter": 0,
     "numEntriesScannedPostFilter": 2,
     "numGroupsLimitReached": false,
     "totalDocs": 5,
     "timeUsedMs": 4,
     "offlineThreadCpuTimeNs": 0,
     "realtimeThreadCpuTimeNs": 0,
     "offlineSystemActivitiesCpuTimeNs": 0,
     "realtimeSystemActivitiesCpuTimeNs": 0,
     "offlineResponseSerializationCpuTimeNs": 0,
     "realtimeResponseSerializationCpuTimeNs": 0,
     "offlineTotalCpuTimeNs": 0,
     "realtimeTotalCpuTimeNs": 0,
     "segmentStatistics": [],
     "traceInfo": {},
     "minConsumingFreshnessTimeMs": 1677851970095,
     "numSegmentsPrunedByBroker": 0,
     "numSegmentsPrunedByServer": 0,
     "numSegmentsPrunedInvalid": 0,
     "numSegmentsPrunedByLimit": 0,
     "numSegmentsPrunedByValue": 0,
     "explainPlanNumEmptyFilterSegments": 0,
     "explainPlanNumMatchAllFilterSegments": 0,
     "numRowsResultSet": 1
   }
   ```


-- 
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...@pinot.apache.org

For queries about this service, please contact Infrastructure at:
us...@infra.apache.org


---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscr...@pinot.apache.org
For additional commands, e-mail: commits-h...@pinot.apache.org