hit-lacus commented on issue #944: KYLIN-4246 Fix for null value and non-exist value in json parser. URL: https://github.com/apache/kylin/pull/944#issuecomment-554588899 ### Model and Cube and SQL ```json { "uuid": "11e2bbd5-f0f5-ac36-7877-61bfe1edafcc", "last_modified": 1573865791073, "version": "3.0.0.20500", "name": "TestNullRT", "owner": "ADMIN", "is_draft": false, "description": "", "fact_table": "DEFAULT.TESTNULL", "lookups": [], "dimensions": [ { "table": "TESTNULL", "columns": [ "REQUIRED_DIMENSION_1", "OPTIONAL_DIMENSION_1", "HOUR_START", "MINUTE_START" ], "id": 1 } ], "metrics": [ "TESTNULL.MEASURE_1" ], "filter_condition": "", "partition_desc": { "partition_date_column": null, "partition_time_column": null, "partition_date_start": 0, "partition_date_format": "yyyy-MM-dd", "partition_time_format": "HH:mm:ss", "partition_type": "APPEND", "partition_condition_builder": "org.apache.kylin.metadata.model.PartitionDesc$DefaultPartitionConditionBuilder" }, "capacity": "MEDIUM" } ``` ```json { "uuid": "f58ad99b-b325-f2ca-6acb-c9abd8bcd595", "last_modified": 1573866225347, "version": "3.0.0.20500", "name": "TestNullCube", "is_draft": false, "model_name": "TestNullRT", "description": "", "null_string": null, "dimensions": [ { "name": "REQUIRED_DIMENSION_1", "table": "TESTNULL", "column": "REQUIRED_DIMENSION_1", "derived": null }, { "name": "OPTIONAL_DIMENSION_1", "table": "TESTNULL", "column": "OPTIONAL_DIMENSION_1", "derived": null }, { "name": "HOUR_START", "table": "TESTNULL", "column": "HOUR_START", "derived": null }, { "name": "MINUTE_START", "table": "TESTNULL", "column": "MINUTE_START", "derived": null } ], "measures": [ { "name": "_COUNT_", "function": { "expression": "COUNT", "parameter": { "type": "constant", "value": "1" }, "returntype": "bigint" } }, { "name": "SUM_MEASURE_1", "function": { "expression": "SUM", "parameter": { "type": "column", "value": "TESTNULL.MEASURE_1" }, "returntype": "bigint" } } ], "dictionaries": [], "rowkey": { "rowkey_columns": [ { "column": "TESTNULL.REQUIRED_DIMENSION_1", "encoding": "dict", "encoding_version": 1, "isShardBy": false }, { "column": "TESTNULL.OPTIONAL_DIMENSION_1", "encoding": "dict", "encoding_version": 1, "isShardBy": false }, { "column": "TESTNULL.HOUR_START", "encoding": "time", "encoding_version": 1, "isShardBy": false }, { "column": "TESTNULL.MINUTE_START", "encoding": "time", "encoding_version": 1, "isShardBy": false } ] }, "hbase_mapping": { "column_family": [ { "name": "F1", "columns": [ { "qualifier": "M", "measure_refs": [ "_COUNT_", "SUM_MEASURE_1" ] } ] } ] }, "aggregation_groups": [ { "includes": [ "TESTNULL.REQUIRED_DIMENSION_1", "TESTNULL.OPTIONAL_DIMENSION_1", "TESTNULL.HOUR_START", "TESTNULL.MINUTE_START" ], "select_rule": { "hierarchy_dims": [], "mandatory_dims": [], "joint_dims": [] } } ], "signature": "yxjdGQqJwieSRlxHdhDwww==", "notify_list": [], "status_need_notify": [ "ERROR", "DISCARDED", "SUCCEED" ], "partition_date_start": 0, "partition_date_end": 3153600000000, "auto_merge_time_ranges": [ 604800000, 2419200000 ], "volatile_range": 0, "retention_range": 0, "engine_type": 2, "storage_type": 3, "override_kylin_properties": { "kylin.stream.cube.window": "600", "kylin.stream.cube.duration": "300", "kylin.stream.index.checkpoint.intervals": "300", "kylin.cube.algorithm": "INMEM", "kylin.stream.segment.retention.policy": "fullBuild" }, "cuboid_black_list": [], "parent_forward": 3, "mandatory_dimension_set_list": [], "snapshot_table_desc_list": [] } ``` ```sql select count(*) as total_row from NULLTEST select REQUIRED_DIMENSION_1, OPTIONAL_DIMENSION_1 ,count(*) as row_count, sum(measure_1) as sum_1 from NULLTEST where OPTIONAL_DIMENSION_1 is not null group by REQUIRED_DIMENSION_1, OPTIONAL_DIMENSION_1 order by REQUIRED_DIMENSION_1, OPTIONAL_DIMENSION_1 select REQUIRED_DIMENSION_1, OPTIONAL_DIMENSION_1 ,count(*) as row_count, sum(measure_1) as sum_1 from NULLTEST where OPTIONAL_DIMENSION_1 is null group by REQUIRED_DIMENSION_1, OPTIONAL_DIMENSION_1 order by REQUIRED_DIMENSION_1, OPTIONAL_DIMENSION_1 select REQUIRED_DIMENSION_1, OPTIONAL_DIMENSION_1 ,count(*) as row_count, sum(measure_1) as sum_1 from NULLTEST group by REQUIRED_DIMENSION_1, OPTIONAL_DIMENSION_1 order by REQUIRED_DIMENSION_1, OPTIONAL_DIMENSION_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. For queries about this service, please contact Infrastructure at: [email protected] With regards, Apache Git Services
