http://git-wip-us.apache.org/repos/asf/hive/blob/f562dfb5/ql/src/test/results/clientpositive/llap/extrapolate_part_stats_partial_ndv.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/extrapolate_part_stats_partial_ndv.q.out b/ql/src/test/results/clientpositive/llap/extrapolate_part_stats_partial_ndv.q.out new file mode 100644 index 0000000..839c30e --- /dev/null +++ b/ql/src/test/results/clientpositive/llap/extrapolate_part_stats_partial_ndv.q.out @@ -0,0 +1,1301 @@ +PREHOOK: query: drop table if exists ext_loc +PREHOOK: type: DROPTABLE +POSTHOOK: query: drop table if exists ext_loc +POSTHOOK: type: DROPTABLE +PREHOOK: query: create table ext_loc ( + state string, + locid double, + cnt decimal, + zip int, + year string +) row format delimited fields terminated by '|' stored as textfile +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@ext_loc +POSTHOOK: query: create table ext_loc ( + state string, + locid double, + cnt decimal, + zip int, + year string +) row format delimited fields terminated by '|' stored as textfile +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@ext_loc +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/extrapolate_stats_partial_ndv.txt' OVERWRITE INTO TABLE ext_loc +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@ext_loc +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/extrapolate_stats_partial_ndv.txt' OVERWRITE INTO TABLE ext_loc +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@ext_loc +PREHOOK: query: drop table if exists loc_orc_1d +PREHOOK: type: DROPTABLE +POSTHOOK: query: drop table if exists loc_orc_1d +POSTHOOK: type: DROPTABLE +PREHOOK: query: create table loc_orc_1d ( + state string, + locid double, + cnt decimal, + zip int +) partitioned by(year string) stored as orc +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@loc_orc_1d +POSTHOOK: query: create table loc_orc_1d ( + state string, + locid double, + cnt decimal, + zip int +) partitioned by(year string) stored as orc +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@loc_orc_1d +PREHOOK: query: insert overwrite table loc_orc_1d partition(year) select * from ext_loc +PREHOOK: type: QUERY +PREHOOK: Input: default@ext_loc +PREHOOK: Output: default@loc_orc_1d +POSTHOOK: query: insert overwrite table loc_orc_1d partition(year) select * from ext_loc +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ext_loc +POSTHOOK: Output: default@loc_orc_1d@year=2000 +POSTHOOK: Output: default@loc_orc_1d@year=2001 +POSTHOOK: Output: default@loc_orc_1d@year=2002 +POSTHOOK: Output: default@loc_orc_1d@year=2003 +POSTHOOK: Lineage: loc_orc_1d PARTITION(year=2000).cnt SIMPLE [(ext_loc)ext_loc.FieldSchema(name:cnt, type:decimal(10,0), comment:null), ] +POSTHOOK: Lineage: loc_orc_1d PARTITION(year=2000).locid SIMPLE [(ext_loc)ext_loc.FieldSchema(name:locid, type:double, comment:null), ] +POSTHOOK: Lineage: loc_orc_1d PARTITION(year=2000).state SIMPLE [(ext_loc)ext_loc.FieldSchema(name:state, type:string, comment:null), ] +POSTHOOK: Lineage: loc_orc_1d PARTITION(year=2000).zip SIMPLE [(ext_loc)ext_loc.FieldSchema(name:zip, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc_1d PARTITION(year=2001).cnt SIMPLE [(ext_loc)ext_loc.FieldSchema(name:cnt, type:decimal(10,0), comment:null), ] +POSTHOOK: Lineage: loc_orc_1d PARTITION(year=2001).locid SIMPLE [(ext_loc)ext_loc.FieldSchema(name:locid, type:double, comment:null), ] +POSTHOOK: Lineage: loc_orc_1d PARTITION(year=2001).state SIMPLE [(ext_loc)ext_loc.FieldSchema(name:state, type:string, comment:null), ] +POSTHOOK: Lineage: loc_orc_1d PARTITION(year=2001).zip SIMPLE [(ext_loc)ext_loc.FieldSchema(name:zip, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc_1d PARTITION(year=2002).cnt SIMPLE [(ext_loc)ext_loc.FieldSchema(name:cnt, type:decimal(10,0), comment:null), ] +POSTHOOK: Lineage: loc_orc_1d PARTITION(year=2002).locid SIMPLE [(ext_loc)ext_loc.FieldSchema(name:locid, type:double, comment:null), ] +POSTHOOK: Lineage: loc_orc_1d PARTITION(year=2002).state SIMPLE [(ext_loc)ext_loc.FieldSchema(name:state, type:string, comment:null), ] +POSTHOOK: Lineage: loc_orc_1d PARTITION(year=2002).zip SIMPLE [(ext_loc)ext_loc.FieldSchema(name:zip, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc_1d PARTITION(year=2003).cnt SIMPLE [(ext_loc)ext_loc.FieldSchema(name:cnt, type:decimal(10,0), comment:null), ] +POSTHOOK: Lineage: loc_orc_1d PARTITION(year=2003).locid SIMPLE [(ext_loc)ext_loc.FieldSchema(name:locid, type:double, comment:null), ] +POSTHOOK: Lineage: loc_orc_1d PARTITION(year=2003).state SIMPLE [(ext_loc)ext_loc.FieldSchema(name:state, type:string, comment:null), ] +POSTHOOK: Lineage: loc_orc_1d PARTITION(year=2003).zip SIMPLE [(ext_loc)ext_loc.FieldSchema(name:zip, type:int, comment:null), ] +PREHOOK: query: analyze table loc_orc_1d partition(year='2001') compute statistics for columns state,locid,cnt,zip +PREHOOK: type: QUERY +PREHOOK: Input: default@loc_orc_1d +PREHOOK: Input: default@loc_orc_1d@year=2001 +#### A masked pattern was here #### +POSTHOOK: query: analyze table loc_orc_1d partition(year='2001') compute statistics for columns state,locid,cnt,zip +POSTHOOK: type: QUERY +POSTHOOK: Input: default@loc_orc_1d +POSTHOOK: Input: default@loc_orc_1d@year=2001 +#### A masked pattern was here #### +PREHOOK: query: analyze table loc_orc_1d partition(year='2002') compute statistics for columns state,locid,cnt,zip +PREHOOK: type: QUERY +PREHOOK: Input: default@loc_orc_1d +PREHOOK: Input: default@loc_orc_1d@year=2002 +#### A masked pattern was here #### +POSTHOOK: query: analyze table loc_orc_1d partition(year='2002') compute statistics for columns state,locid,cnt,zip +POSTHOOK: type: QUERY +POSTHOOK: Input: default@loc_orc_1d +POSTHOOK: Input: default@loc_orc_1d@year=2002 +#### A masked pattern was here #### +PREHOOK: query: describe formatted loc_orc_1d PARTITION(year='2001') state +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@loc_orc_1d +POSTHOOK: query: describe formatted loc_orc_1d PARTITION(year='2001') state +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@loc_orc_1d +# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment + +state string 0 3 0.75 2 from deserializer +PREHOOK: query: describe formatted loc_orc_1d PARTITION(year='2002') state +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@loc_orc_1d +POSTHOOK: query: describe formatted loc_orc_1d PARTITION(year='2002') state +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@loc_orc_1d +# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment + +state string 0 6 3.0 3 from deserializer +PREHOOK: query: describe formatted loc_orc_1d PARTITION(year='2001') locid +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@loc_orc_1d +POSTHOOK: query: describe formatted loc_orc_1d PARTITION(year='2001') locid +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@loc_orc_1d +# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment + +locid double 1.0 4.0 0 5 from deserializer +PREHOOK: query: describe formatted loc_orc_1d PARTITION(year='2002') locid +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@loc_orc_1d +POSTHOOK: query: describe formatted loc_orc_1d PARTITION(year='2002') locid +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@loc_orc_1d +# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment + +locid double 1.0 5.0 0 6 from deserializer +PREHOOK: query: describe formatted loc_orc_1d PARTITION(year='2001') cnt +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@loc_orc_1d +POSTHOOK: query: describe formatted loc_orc_1d PARTITION(year='2001') cnt +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@loc_orc_1d +# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment + +cnt decimal(10,0) 10 2000 0 5 from deserializer +PREHOOK: query: describe formatted loc_orc_1d PARTITION(year='2002') cnt +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@loc_orc_1d +POSTHOOK: query: describe formatted loc_orc_1d PARTITION(year='2002') cnt +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@loc_orc_1d +# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment + +cnt decimal(10,0) 10 910 0 4 from deserializer +PREHOOK: query: describe formatted loc_orc_1d PARTITION(year='2001') zip +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@loc_orc_1d +POSTHOOK: query: describe formatted loc_orc_1d PARTITION(year='2001') zip +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@loc_orc_1d +# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment + +zip int 43201 94087 0 4 from deserializer +PREHOOK: query: describe formatted loc_orc_1d PARTITION(year='2002') zip +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@loc_orc_1d +POSTHOOK: query: describe formatted loc_orc_1d PARTITION(year='2002') zip +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@loc_orc_1d +# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment + +zip int 43201 94087 0 4 from deserializer +PREHOOK: query: explain extended select state,locid,cnt,zip from loc_orc_1d +PREHOOK: type: QUERY +POSTHOOK: query: explain extended select state,locid,cnt,zip from loc_orc_1d +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: -1 + Partition Description: + Partition + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + partition values: + year 2000 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + bucket_count -1 + columns state,locid,cnt,zip + columns.comments + columns.types string:double:decimal(10,0):int +#### A masked pattern was here #### + name default.loc_orc_1d + numFiles 1 + numRows 2 + partition_columns year + partition_columns.types string + rawDataSize 416 + serialization.ddl struct loc_orc_1d { string state, double locid, decimal(10,0) cnt, i32 zip} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 531 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + bucket_count -1 + columns state,locid,cnt,zip + columns.comments + columns.types string:double:decimal(10,0):int +#### A masked pattern was here #### + name default.loc_orc_1d + partition_columns year + partition_columns.types string + serialization.ddl struct loc_orc_1d { string state, double locid, decimal(10,0) cnt, i32 zip} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.loc_orc_1d + name: default.loc_orc_1d + Partition + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + partition values: + year 2001 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"cnt":"true","locid":"true","state":"true","zip":"true"}} + bucket_count -1 + columns state,locid,cnt,zip + columns.comments + columns.types string:double:decimal(10,0):int +#### A masked pattern was here #### + name default.loc_orc_1d + numFiles 1 + numRows 4 + partition_columns year + partition_columns.types string + rawDataSize 832 + serialization.ddl struct loc_orc_1d { string state, double locid, decimal(10,0) cnt, i32 zip} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 562 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + bucket_count -1 + columns state,locid,cnt,zip + columns.comments + columns.types string:double:decimal(10,0):int +#### A masked pattern was here #### + name default.loc_orc_1d + partition_columns year + partition_columns.types string + serialization.ddl struct loc_orc_1d { string state, double locid, decimal(10,0) cnt, i32 zip} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.loc_orc_1d + name: default.loc_orc_1d + Partition + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + partition values: + year 2002 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"cnt":"true","locid":"true","state":"true","zip":"true"}} + bucket_count -1 + columns state,locid,cnt,zip + columns.comments + columns.types string:double:decimal(10,0):int +#### A masked pattern was here #### + name default.loc_orc_1d + numFiles 1 + numRows 6 + partition_columns year + partition_columns.types string + rawDataSize 1266 + serialization.ddl struct loc_orc_1d { string state, double locid, decimal(10,0) cnt, i32 zip} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 580 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + bucket_count -1 + columns state,locid,cnt,zip + columns.comments + columns.types string:double:decimal(10,0):int +#### A masked pattern was here #### + name default.loc_orc_1d + partition_columns year + partition_columns.types string + serialization.ddl struct loc_orc_1d { string state, double locid, decimal(10,0) cnt, i32 zip} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.loc_orc_1d + name: default.loc_orc_1d + Partition + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + partition values: + year 2003 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + bucket_count -1 + columns state,locid,cnt,zip + columns.comments + columns.types string:double:decimal(10,0):int +#### A masked pattern was here #### + name default.loc_orc_1d + numFiles 1 + numRows 8 + partition_columns year + partition_columns.types string + rawDataSize 1672 + serialization.ddl struct loc_orc_1d { string state, double locid, decimal(10,0) cnt, i32 zip} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 602 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + bucket_count -1 + columns state,locid,cnt,zip + columns.comments + columns.types string:double:decimal(10,0):int +#### A masked pattern was here #### + name default.loc_orc_1d + partition_columns year + partition_columns.types string + serialization.ddl struct loc_orc_1d { string state, double locid, decimal(10,0) cnt, i32 zip} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.loc_orc_1d + name: default.loc_orc_1d + Processor Tree: + TableScan + alias: loc_orc_1d + GatherStats: false + Select Operator + expressions: state (type: string), locid (type: double), cnt (type: decimal(10,0)), zip (type: int) + outputColumnNames: _col0, _col1, _col2, _col3 + ListSink + +PREHOOK: query: analyze table loc_orc_1d partition(year='2000') compute statistics for columns state,locid,cnt,zip +PREHOOK: type: QUERY +PREHOOK: Input: default@loc_orc_1d +PREHOOK: Input: default@loc_orc_1d@year=2000 +#### A masked pattern was here #### +POSTHOOK: query: analyze table loc_orc_1d partition(year='2000') compute statistics for columns state,locid,cnt,zip +POSTHOOK: type: QUERY +POSTHOOK: Input: default@loc_orc_1d +POSTHOOK: Input: default@loc_orc_1d@year=2000 +#### A masked pattern was here #### +PREHOOK: query: analyze table loc_orc_1d partition(year='2003') compute statistics for columns state,locid,cnt,zip +PREHOOK: type: QUERY +PREHOOK: Input: default@loc_orc_1d +PREHOOK: Input: default@loc_orc_1d@year=2003 +#### A masked pattern was here #### +POSTHOOK: query: analyze table loc_orc_1d partition(year='2003') compute statistics for columns state,locid,cnt,zip +POSTHOOK: type: QUERY +POSTHOOK: Input: default@loc_orc_1d +POSTHOOK: Input: default@loc_orc_1d@year=2003 +#### A masked pattern was here #### +PREHOOK: query: describe formatted loc_orc_1d PARTITION(year='2000') state +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@loc_orc_1d +POSTHOOK: query: describe formatted loc_orc_1d PARTITION(year='2000') state +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@loc_orc_1d +# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment + +state string 0 2 0.5 1 from deserializer +PREHOOK: query: describe formatted loc_orc_1d PARTITION(year='2003') state +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@loc_orc_1d +POSTHOOK: query: describe formatted loc_orc_1d PARTITION(year='2003') state +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@loc_orc_1d +# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment + +state string 0 4 1.25 4 from deserializer +PREHOOK: query: describe formatted loc_orc_1d PARTITION(year='2000') locid +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@loc_orc_1d +POSTHOOK: query: describe formatted loc_orc_1d PARTITION(year='2000') locid +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@loc_orc_1d +# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment + +locid double 1.0 2.0 0 2 from deserializer +PREHOOK: query: describe formatted loc_orc_1d PARTITION(year='2003') locid +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@loc_orc_1d +POSTHOOK: query: describe formatted loc_orc_1d PARTITION(year='2003') locid +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@loc_orc_1d +# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment + +locid double 1.0 31.0 0 6 from deserializer +PREHOOK: query: describe formatted loc_orc_1d PARTITION(year='2000') cnt +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@loc_orc_1d +POSTHOOK: query: describe formatted loc_orc_1d PARTITION(year='2000') cnt +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@loc_orc_1d +# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment + +cnt decimal(10,0) 1000 1010 0 3 from deserializer +PREHOOK: query: describe formatted loc_orc_1d PARTITION(year='2003') cnt +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@loc_orc_1d +POSTHOOK: query: describe formatted loc_orc_1d PARTITION(year='2003') cnt +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@loc_orc_1d +# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment + +cnt decimal(10,0) 1000 2000 0 3 from deserializer +PREHOOK: query: describe formatted loc_orc_1d PARTITION(year='2000') zip +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@loc_orc_1d +POSTHOOK: query: describe formatted loc_orc_1d PARTITION(year='2000') zip +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@loc_orc_1d +# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment + +zip int 94086 94087 0 2 from deserializer +PREHOOK: query: describe formatted loc_orc_1d PARTITION(year='2003') zip +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@loc_orc_1d +POSTHOOK: query: describe formatted loc_orc_1d PARTITION(year='2003') zip +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@loc_orc_1d +# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment + +zip int 43201 94087 0 4 from deserializer +PREHOOK: query: explain extended select state,locid,cnt,zip from loc_orc_1d +PREHOOK: type: QUERY +POSTHOOK: query: explain extended select state,locid,cnt,zip from loc_orc_1d +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: -1 + Partition Description: + Partition + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + partition values: + year 2000 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"cnt":"true","locid":"true","state":"true","zip":"true"}} + bucket_count -1 + columns state,locid,cnt,zip + columns.comments + columns.types string:double:decimal(10,0):int +#### A masked pattern was here #### + name default.loc_orc_1d + numFiles 1 + numRows 2 + partition_columns year + partition_columns.types string + rawDataSize 416 + serialization.ddl struct loc_orc_1d { string state, double locid, decimal(10,0) cnt, i32 zip} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 531 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + bucket_count -1 + columns state,locid,cnt,zip + columns.comments + columns.types string:double:decimal(10,0):int +#### A masked pattern was here #### + name default.loc_orc_1d + partition_columns year + partition_columns.types string + serialization.ddl struct loc_orc_1d { string state, double locid, decimal(10,0) cnt, i32 zip} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.loc_orc_1d + name: default.loc_orc_1d + Partition + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + partition values: + year 2001 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"cnt":"true","locid":"true","state":"true","zip":"true"}} + bucket_count -1 + columns state,locid,cnt,zip + columns.comments + columns.types string:double:decimal(10,0):int +#### A masked pattern was here #### + name default.loc_orc_1d + numFiles 1 + numRows 4 + partition_columns year + partition_columns.types string + rawDataSize 832 + serialization.ddl struct loc_orc_1d { string state, double locid, decimal(10,0) cnt, i32 zip} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 562 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + bucket_count -1 + columns state,locid,cnt,zip + columns.comments + columns.types string:double:decimal(10,0):int +#### A masked pattern was here #### + name default.loc_orc_1d + partition_columns year + partition_columns.types string + serialization.ddl struct loc_orc_1d { string state, double locid, decimal(10,0) cnt, i32 zip} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.loc_orc_1d + name: default.loc_orc_1d + Partition + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + partition values: + year 2002 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"cnt":"true","locid":"true","state":"true","zip":"true"}} + bucket_count -1 + columns state,locid,cnt,zip + columns.comments + columns.types string:double:decimal(10,0):int +#### A masked pattern was here #### + name default.loc_orc_1d + numFiles 1 + numRows 6 + partition_columns year + partition_columns.types string + rawDataSize 1266 + serialization.ddl struct loc_orc_1d { string state, double locid, decimal(10,0) cnt, i32 zip} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 580 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + bucket_count -1 + columns state,locid,cnt,zip + columns.comments + columns.types string:double:decimal(10,0):int +#### A masked pattern was here #### + name default.loc_orc_1d + partition_columns year + partition_columns.types string + serialization.ddl struct loc_orc_1d { string state, double locid, decimal(10,0) cnt, i32 zip} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.loc_orc_1d + name: default.loc_orc_1d + Partition + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + partition values: + year 2003 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"cnt":"true","locid":"true","state":"true","zip":"true"}} + bucket_count -1 + columns state,locid,cnt,zip + columns.comments + columns.types string:double:decimal(10,0):int +#### A masked pattern was here #### + name default.loc_orc_1d + numFiles 1 + numRows 8 + partition_columns year + partition_columns.types string + rawDataSize 1672 + serialization.ddl struct loc_orc_1d { string state, double locid, decimal(10,0) cnt, i32 zip} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 602 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + bucket_count -1 + columns state,locid,cnt,zip + columns.comments + columns.types string:double:decimal(10,0):int +#### A masked pattern was here #### + name default.loc_orc_1d + partition_columns year + partition_columns.types string + serialization.ddl struct loc_orc_1d { string state, double locid, decimal(10,0) cnt, i32 zip} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.loc_orc_1d + name: default.loc_orc_1d + Processor Tree: + TableScan + alias: loc_orc_1d + GatherStats: false + Select Operator + expressions: state (type: string), locid (type: double), cnt (type: decimal(10,0)), zip (type: int) + outputColumnNames: _col0, _col1, _col2, _col3 + ListSink + +PREHOOK: query: drop table if exists loc_orc_2d +PREHOOK: type: DROPTABLE +POSTHOOK: query: drop table if exists loc_orc_2d +POSTHOOK: type: DROPTABLE +PREHOOK: query: create table loc_orc_2d ( + state string, + locid int, + cnt decimal +) partitioned by(zip int, year string) stored as orc +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@loc_orc_2d +POSTHOOK: query: create table loc_orc_2d ( + state string, + locid int, + cnt decimal +) partitioned by(zip int, year string) stored as orc +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@loc_orc_2d +PREHOOK: query: insert overwrite table loc_orc_2d partition(zip, year) select * from ext_loc +PREHOOK: type: QUERY +PREHOOK: Input: default@ext_loc +PREHOOK: Output: default@loc_orc_2d +POSTHOOK: query: insert overwrite table loc_orc_2d partition(zip, year) select * from ext_loc +POSTHOOK: type: QUERY +POSTHOOK: Input: default@ext_loc +POSTHOOK: Output: default@loc_orc_2d@zip=43201/year=2001 +POSTHOOK: Output: default@loc_orc_2d@zip=43201/year=2002 +POSTHOOK: Output: default@loc_orc_2d@zip=43201/year=2003 +POSTHOOK: Output: default@loc_orc_2d@zip=94086/year=2000 +POSTHOOK: Output: default@loc_orc_2d@zip=94086/year=2001 +POSTHOOK: Output: default@loc_orc_2d@zip=94086/year=2002 +POSTHOOK: Output: default@loc_orc_2d@zip=94086/year=2003 +POSTHOOK: Output: default@loc_orc_2d@zip=94087/year=2000 +POSTHOOK: Output: default@loc_orc_2d@zip=94087/year=2001 +POSTHOOK: Output: default@loc_orc_2d@zip=94087/year=2002 +POSTHOOK: Output: default@loc_orc_2d@zip=94087/year=2003 +POSTHOOK: Lineage: loc_orc_2d PARTITION(zip=43201,year=2001).cnt SIMPLE [(ext_loc)ext_loc.FieldSchema(name:cnt, type:decimal(10,0), comment:null), ] +POSTHOOK: Lineage: loc_orc_2d PARTITION(zip=43201,year=2001).locid EXPRESSION [(ext_loc)ext_loc.FieldSchema(name:locid, type:double, comment:null), ] +POSTHOOK: Lineage: loc_orc_2d PARTITION(zip=43201,year=2001).state SIMPLE [(ext_loc)ext_loc.FieldSchema(name:state, type:string, comment:null), ] +POSTHOOK: Lineage: loc_orc_2d PARTITION(zip=43201,year=2002).cnt SIMPLE [(ext_loc)ext_loc.FieldSchema(name:cnt, type:decimal(10,0), comment:null), ] +POSTHOOK: Lineage: loc_orc_2d PARTITION(zip=43201,year=2002).locid EXPRESSION [(ext_loc)ext_loc.FieldSchema(name:locid, type:double, comment:null), ] +POSTHOOK: Lineage: loc_orc_2d PARTITION(zip=43201,year=2002).state SIMPLE [(ext_loc)ext_loc.FieldSchema(name:state, type:string, comment:null), ] +POSTHOOK: Lineage: loc_orc_2d PARTITION(zip=43201,year=2003).cnt SIMPLE [(ext_loc)ext_loc.FieldSchema(name:cnt, type:decimal(10,0), comment:null), ] +POSTHOOK: Lineage: loc_orc_2d PARTITION(zip=43201,year=2003).locid EXPRESSION [(ext_loc)ext_loc.FieldSchema(name:locid, type:double, comment:null), ] +POSTHOOK: Lineage: loc_orc_2d PARTITION(zip=43201,year=2003).state SIMPLE [(ext_loc)ext_loc.FieldSchema(name:state, type:string, comment:null), ] +POSTHOOK: Lineage: loc_orc_2d PARTITION(zip=94086,year=2000).cnt SIMPLE [(ext_loc)ext_loc.FieldSchema(name:cnt, type:decimal(10,0), comment:null), ] +POSTHOOK: Lineage: loc_orc_2d PARTITION(zip=94086,year=2000).locid EXPRESSION [(ext_loc)ext_loc.FieldSchema(name:locid, type:double, comment:null), ] +POSTHOOK: Lineage: loc_orc_2d PARTITION(zip=94086,year=2000).state SIMPLE [(ext_loc)ext_loc.FieldSchema(name:state, type:string, comment:null), ] +POSTHOOK: Lineage: loc_orc_2d PARTITION(zip=94086,year=2001).cnt SIMPLE [(ext_loc)ext_loc.FieldSchema(name:cnt, type:decimal(10,0), comment:null), ] +POSTHOOK: Lineage: loc_orc_2d PARTITION(zip=94086,year=2001).locid EXPRESSION [(ext_loc)ext_loc.FieldSchema(name:locid, type:double, comment:null), ] +POSTHOOK: Lineage: loc_orc_2d PARTITION(zip=94086,year=2001).state SIMPLE [(ext_loc)ext_loc.FieldSchema(name:state, type:string, comment:null), ] +POSTHOOK: Lineage: loc_orc_2d PARTITION(zip=94086,year=2002).cnt SIMPLE [(ext_loc)ext_loc.FieldSchema(name:cnt, type:decimal(10,0), comment:null), ] +POSTHOOK: Lineage: loc_orc_2d PARTITION(zip=94086,year=2002).locid EXPRESSION [(ext_loc)ext_loc.FieldSchema(name:locid, type:double, comment:null), ] +POSTHOOK: Lineage: loc_orc_2d PARTITION(zip=94086,year=2002).state SIMPLE [(ext_loc)ext_loc.FieldSchema(name:state, type:string, comment:null), ] +POSTHOOK: Lineage: loc_orc_2d PARTITION(zip=94086,year=2003).cnt SIMPLE [(ext_loc)ext_loc.FieldSchema(name:cnt, type:decimal(10,0), comment:null), ] +POSTHOOK: Lineage: loc_orc_2d PARTITION(zip=94086,year=2003).locid EXPRESSION [(ext_loc)ext_loc.FieldSchema(name:locid, type:double, comment:null), ] +POSTHOOK: Lineage: loc_orc_2d PARTITION(zip=94086,year=2003).state SIMPLE [(ext_loc)ext_loc.FieldSchema(name:state, type:string, comment:null), ] +POSTHOOK: Lineage: loc_orc_2d PARTITION(zip=94087,year=2000).cnt SIMPLE [(ext_loc)ext_loc.FieldSchema(name:cnt, type:decimal(10,0), comment:null), ] +POSTHOOK: Lineage: loc_orc_2d PARTITION(zip=94087,year=2000).locid EXPRESSION [(ext_loc)ext_loc.FieldSchema(name:locid, type:double, comment:null), ] +POSTHOOK: Lineage: loc_orc_2d PARTITION(zip=94087,year=2000).state SIMPLE [(ext_loc)ext_loc.FieldSchema(name:state, type:string, comment:null), ] +POSTHOOK: Lineage: loc_orc_2d PARTITION(zip=94087,year=2001).cnt SIMPLE [(ext_loc)ext_loc.FieldSchema(name:cnt, type:decimal(10,0), comment:null), ] +POSTHOOK: Lineage: loc_orc_2d PARTITION(zip=94087,year=2001).locid EXPRESSION [(ext_loc)ext_loc.FieldSchema(name:locid, type:double, comment:null), ] +POSTHOOK: Lineage: loc_orc_2d PARTITION(zip=94087,year=2001).state SIMPLE [(ext_loc)ext_loc.FieldSchema(name:state, type:string, comment:null), ] +POSTHOOK: Lineage: loc_orc_2d PARTITION(zip=94087,year=2002).cnt SIMPLE [(ext_loc)ext_loc.FieldSchema(name:cnt, type:decimal(10,0), comment:null), ] +POSTHOOK: Lineage: loc_orc_2d PARTITION(zip=94087,year=2002).locid EXPRESSION [(ext_loc)ext_loc.FieldSchema(name:locid, type:double, comment:null), ] +POSTHOOK: Lineage: loc_orc_2d PARTITION(zip=94087,year=2002).state SIMPLE [(ext_loc)ext_loc.FieldSchema(name:state, type:string, comment:null), ] +POSTHOOK: Lineage: loc_orc_2d PARTITION(zip=94087,year=2003).cnt SIMPLE [(ext_loc)ext_loc.FieldSchema(name:cnt, type:decimal(10,0), comment:null), ] +POSTHOOK: Lineage: loc_orc_2d PARTITION(zip=94087,year=2003).locid EXPRESSION [(ext_loc)ext_loc.FieldSchema(name:locid, type:double, comment:null), ] +POSTHOOK: Lineage: loc_orc_2d PARTITION(zip=94087,year=2003).state SIMPLE [(ext_loc)ext_loc.FieldSchema(name:state, type:string, comment:null), ] +PREHOOK: query: analyze table loc_orc_2d partition(zip=94086, year='2001') compute statistics for columns state,locid,cnt +PREHOOK: type: QUERY +PREHOOK: Input: default@loc_orc_2d +PREHOOK: Input: default@loc_orc_2d@zip=94086/year=2001 +#### A masked pattern was here #### +POSTHOOK: query: analyze table loc_orc_2d partition(zip=94086, year='2001') compute statistics for columns state,locid,cnt +POSTHOOK: type: QUERY +POSTHOOK: Input: default@loc_orc_2d +POSTHOOK: Input: default@loc_orc_2d@zip=94086/year=2001 +#### A masked pattern was here #### +PREHOOK: query: analyze table loc_orc_2d partition(zip=94087, year='2002') compute statistics for columns state,locid,cnt +PREHOOK: type: QUERY +PREHOOK: Input: default@loc_orc_2d +PREHOOK: Input: default@loc_orc_2d@zip=94087/year=2002 +#### A masked pattern was here #### +POSTHOOK: query: analyze table loc_orc_2d partition(zip=94087, year='2002') compute statistics for columns state,locid,cnt +POSTHOOK: type: QUERY +POSTHOOK: Input: default@loc_orc_2d +POSTHOOK: Input: default@loc_orc_2d@zip=94087/year=2002 +#### A masked pattern was here #### +PREHOOK: query: describe formatted loc_orc_2d partition(zip=94086, year='2001') state +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@loc_orc_2d +POSTHOOK: query: describe formatted loc_orc_2d partition(zip=94086, year='2001') state +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@loc_orc_2d +# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment + +state string 0 2 0.5 1 from deserializer +PREHOOK: query: describe formatted loc_orc_2d partition(zip=94087, year='2002') state +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@loc_orc_2d +POSTHOOK: query: describe formatted loc_orc_2d partition(zip=94087, year='2002') state +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@loc_orc_2d +# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment + +state string 0 4 3.0 3 from deserializer +PREHOOK: query: describe formatted loc_orc_2d partition(zip=94086, year='2001') locid +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@loc_orc_2d +POSTHOOK: query: describe formatted loc_orc_2d partition(zip=94086, year='2001') locid +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@loc_orc_2d +# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment + +locid int 2 3 0 2 from deserializer +PREHOOK: query: describe formatted loc_orc_2d partition(zip=94087, year='2002') locid +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@loc_orc_2d +POSTHOOK: query: describe formatted loc_orc_2d partition(zip=94087, year='2002') locid +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@loc_orc_2d +# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment + +locid int 1 5 0 3 from deserializer +PREHOOK: query: describe formatted loc_orc_2d partition(zip=94086, year='2001') cnt +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@loc_orc_2d +POSTHOOK: query: describe formatted loc_orc_2d partition(zip=94086, year='2001') cnt +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@loc_orc_2d +# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment + +cnt decimal(10,0) 1000 2000 0 2 from deserializer +PREHOOK: query: describe formatted loc_orc_2d partition(zip=94087, year='2002') cnt +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@loc_orc_2d +POSTHOOK: query: describe formatted loc_orc_2d partition(zip=94087, year='2002') cnt +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@loc_orc_2d +# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment + +cnt decimal(10,0) 10 100 0 2 from deserializer +PREHOOK: query: explain extended select state,locid,cnt,zip from loc_orc_2d +PREHOOK: type: QUERY +POSTHOOK: query: explain extended select state,locid,cnt,zip from loc_orc_2d +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: -1 + Partition Description: + Partition + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + partition values: + year 2001 + zip 43201 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + bucket_count -1 + columns state,locid,cnt + columns.comments + columns.types string:int:decimal(10,0) +#### A masked pattern was here #### + name default.loc_orc_2d + numFiles 1 + numRows 1 + partition_columns zip/year + partition_columns.types int:string + rawDataSize 202 + serialization.ddl struct loc_orc_2d { string state, i32 locid, decimal(10,0) cnt} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 386 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + bucket_count -1 + columns state,locid,cnt + columns.comments + columns.types string:int:decimal(10,0) +#### A masked pattern was here #### + name default.loc_orc_2d + partition_columns zip/year + partition_columns.types int:string + serialization.ddl struct loc_orc_2d { string state, i32 locid, decimal(10,0) cnt} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.loc_orc_2d + name: default.loc_orc_2d + Partition + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + partition values: + year 2002 + zip 43201 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + bucket_count -1 + columns state,locid,cnt + columns.comments + columns.types string:int:decimal(10,0) +#### A masked pattern was here #### + name default.loc_orc_2d + numFiles 1 + numRows 2 + partition_columns zip/year + partition_columns.types int:string + rawDataSize 406 + serialization.ddl struct loc_orc_2d { string state, i32 locid, decimal(10,0) cnt} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 409 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + bucket_count -1 + columns state,locid,cnt + columns.comments + columns.types string:int:decimal(10,0) +#### A masked pattern was here #### + name default.loc_orc_2d + partition_columns zip/year + partition_columns.types int:string + serialization.ddl struct loc_orc_2d { string state, i32 locid, decimal(10,0) cnt} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.loc_orc_2d + name: default.loc_orc_2d + Partition + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + partition values: + year 2003 + zip 43201 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + bucket_count -1 + columns state,locid,cnt + columns.comments + columns.types string:int:decimal(10,0) +#### A masked pattern was here #### + name default.loc_orc_2d + numFiles 1 + numRows 3 + partition_columns zip/year + partition_columns.types int:string + rawDataSize 603 + serialization.ddl struct loc_orc_2d { string state, i32 locid, decimal(10,0) cnt} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 423 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + bucket_count -1 + columns state,locid,cnt + columns.comments + columns.types string:int:decimal(10,0) +#### A masked pattern was here #### + name default.loc_orc_2d + partition_columns zip/year + partition_columns.types int:string + serialization.ddl struct loc_orc_2d { string state, i32 locid, decimal(10,0) cnt} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.loc_orc_2d + name: default.loc_orc_2d + Partition + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + partition values: + year 2000 + zip 94086 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + bucket_count -1 + columns state,locid,cnt + columns.comments + columns.types string:int:decimal(10,0) +#### A masked pattern was here #### + name default.loc_orc_2d + numFiles 1 + numRows 1 + partition_columns zip/year + partition_columns.types int:string + rawDataSize 201 + serialization.ddl struct loc_orc_2d { string state, i32 locid, decimal(10,0) cnt} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 383 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + bucket_count -1 + columns state,locid,cnt + columns.comments + columns.types string:int:decimal(10,0) +#### A masked pattern was here #### + name default.loc_orc_2d + partition_columns zip/year + partition_columns.types int:string + serialization.ddl struct loc_orc_2d { string state, i32 locid, decimal(10,0) cnt} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.loc_orc_2d + name: default.loc_orc_2d + Partition + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + partition values: + year 2001 + zip 94086 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"cnt":"true","locid":"true","state":"true"}} + bucket_count -1 + columns state,locid,cnt + columns.comments + columns.types string:int:decimal(10,0) +#### A masked pattern was here #### + name default.loc_orc_2d + numFiles 1 + numRows 2 + partition_columns zip/year + partition_columns.types int:string + rawDataSize 400 + serialization.ddl struct loc_orc_2d { string state, i32 locid, decimal(10,0) cnt} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 394 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + bucket_count -1 + columns state,locid,cnt + columns.comments + columns.types string:int:decimal(10,0) +#### A masked pattern was here #### + name default.loc_orc_2d + partition_columns zip/year + partition_columns.types int:string + serialization.ddl struct loc_orc_2d { string state, i32 locid, decimal(10,0) cnt} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.loc_orc_2d + name: default.loc_orc_2d + Partition + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + partition values: + year 2002 + zip 94086 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + bucket_count -1 + columns state,locid,cnt + columns.comments + columns.types string:int:decimal(10,0) +#### A masked pattern was here #### + name default.loc_orc_2d + numFiles 1 + numRows 1 + partition_columns zip/year + partition_columns.types int:string + rawDataSize 203 + serialization.ddl struct loc_orc_2d { string state, i32 locid, decimal(10,0) cnt} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 387 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + bucket_count -1 + columns state,locid,cnt + columns.comments + columns.types string:int:decimal(10,0) +#### A masked pattern was here #### + name default.loc_orc_2d + partition_columns zip/year + partition_columns.types int:string + serialization.ddl struct loc_orc_2d { string state, i32 locid, decimal(10,0) cnt} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.loc_orc_2d + name: default.loc_orc_2d + Partition + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + partition values: + year 2003 + zip 94086 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + bucket_count -1 + columns state,locid,cnt + columns.comments + columns.types string:int:decimal(10,0) +#### A masked pattern was here #### + name default.loc_orc_2d + numFiles 1 + numRows 2 + partition_columns zip/year + partition_columns.types int:string + rawDataSize 404 + serialization.ddl struct loc_orc_2d { string state, i32 locid, decimal(10,0) cnt} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 409 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + bucket_count -1 + columns state,locid,cnt + columns.comments + columns.types string:int:decimal(10,0) +#### A masked pattern was here #### + name default.loc_orc_2d + partition_columns zip/year + partition_columns.types int:string + serialization.ddl struct loc_orc_2d { string state, i32 locid, decimal(10,0) cnt} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.loc_orc_2d + name: default.loc_orc_2d + Partition + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + partition values: + year 2000 + zip 94087 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + bucket_count -1 + columns state,locid,cnt + columns.comments + columns.types string:int:decimal(10,0) +#### A masked pattern was here #### + name default.loc_orc_2d + numFiles 1 + numRows 1 + partition_columns zip/year + partition_columns.types int:string + rawDataSize 200 + serialization.ddl struct loc_orc_2d { string state, i32 locid, decimal(10,0) cnt} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 366 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + bucket_count -1 + columns state,locid,cnt + columns.comments + columns.types string:int:decimal(10,0) +#### A masked pattern was here #### + name default.loc_orc_2d + partition_columns zip/year + partition_columns.types int:string + serialization.ddl struct loc_orc_2d { string state, i32 locid, decimal(10,0) cnt} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.loc_orc_2d + name: default.loc_orc_2d + Partition + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + partition values: + year 2001 + zip 94087 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + bucket_count -1 + columns state,locid,cnt + columns.comments + columns.types string:int:decimal(10,0) +#### A masked pattern was here #### + name default.loc_orc_2d + numFiles 1 + numRows 1 + partition_columns zip/year + partition_columns.types int:string + rawDataSize 200 + serialization.ddl struct loc_orc_2d { string state, i32 locid, decimal(10,0) cnt} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 361 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + bucket_count -1 + columns state,locid,cnt + columns.comments + columns.types string:int:decimal(10,0) +#### A masked pattern was here #### + name default.loc_orc_2d + partition_columns zip/year + partition_columns.types int:string + serialization.ddl struct loc_orc_2d { string state, i32 locid, decimal(10,0) cnt} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.loc_orc_2d + name: default.loc_orc_2d + Partition + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + partition values: + year 2002 + zip 94087 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"cnt":"true","locid":"true","state":"true"}} + bucket_count -1 + columns state,locid,cnt + columns.comments + columns.types string:int:decimal(10,0) +#### A masked pattern was here #### + name default.loc_orc_2d + numFiles 1 + numRows 3 + partition_columns zip/year + partition_columns.types int:string + rawDataSize 609 + serialization.ddl struct loc_orc_2d { string state, i32 locid, decimal(10,0) cnt} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 412 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + bucket_count -1 + columns state,locid,cnt + columns.comments + columns.types string:int:decimal(10,0) +#### A masked pattern was here #### + name default.loc_orc_2d + partition_columns zip/year + partition_columns.types int:string + serialization.ddl struct loc_orc_2d { string state, i32 locid, decimal(10,0) cnt} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.loc_orc_2d + name: default.loc_orc_2d + Partition + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + partition values: + year 2003 + zip 94087 + properties: + COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} + bucket_count -1 + columns state,locid,cnt + columns.comments + columns.types string:int:decimal(10,0) +#### A masked pattern was here #### + name default.loc_orc_2d + numFiles 1 + numRows 3 + partition_columns zip/year + partition_columns.types int:string + rawDataSize 600 + serialization.ddl struct loc_orc_2d { string state, i32 locid, decimal(10,0) cnt} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 412 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + bucket_count -1 + columns state,locid,cnt + columns.comments + columns.types string:int:decimal(10,0) +#### A masked pattern was here #### + name default.loc_orc_2d + partition_columns zip/year + partition_columns.types int:string + serialization.ddl struct loc_orc_2d { string state, i32 locid, decimal(10,0) cnt} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.loc_orc_2d + name: default.loc_orc_2d + Processor Tree: + TableScan + alias: loc_orc_2d + GatherStats: false + Select Operator + expressions: state (type: string), locid (type: int), cnt (type: decimal(10,0)), zip (type: int) + outputColumnNames: _col0, _col1, _col2, _col3 + ListSink +
http://git-wip-us.apache.org/repos/asf/hive/blob/f562dfb5/ql/src/test/results/clientpositive/llap/groupby_grouping_id2.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/groupby_grouping_id2.q.out b/ql/src/test/results/clientpositive/llap/groupby_grouping_id2.q.out new file mode 100644 index 0000000..544a7ae --- /dev/null +++ b/ql/src/test/results/clientpositive/llap/groupby_grouping_id2.q.out @@ -0,0 +1,234 @@ +PREHOOK: query: CREATE TABLE T1(key INT, value INT) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@T1 +POSTHOOK: query: CREATE TABLE T1(key INT, value INT) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@T1 +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/groupby_groupingid.txt' INTO TABLE T1 +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@t1 +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/groupby_groupingid.txt' INTO TABLE T1 +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@t1 +PREHOOK: query: -- SORT_QUERY_RESULTS + +SELECT key, value, GROUPING__ID, count(*) from T1 GROUP BY key, value WITH ROLLUP +PREHOOK: type: QUERY +PREHOOK: Input: default@t1 +#### A masked pattern was here #### +POSTHOOK: query: -- SORT_QUERY_RESULTS + +SELECT key, value, GROUPING__ID, count(*) from T1 GROUP BY key, value WITH ROLLUP +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1 +#### A masked pattern was here #### +1 1 3 1 +1 NULL 1 2 +1 NULL 3 1 +2 2 3 1 +2 NULL 1 1 +3 3 3 1 +3 NULL 1 2 +3 NULL 3 1 +4 5 3 1 +4 NULL 1 1 +NULL NULL 0 6 +PREHOOK: query: SELECT GROUPING__ID, count(*) +FROM +( +SELECT key, value, GROUPING__ID, count(*) from T1 GROUP BY key, value WITH ROLLUP +) t +GROUP BY GROUPING__ID +PREHOOK: type: QUERY +PREHOOK: Input: default@t1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT GROUPING__ID, count(*) +FROM +( +SELECT key, value, GROUPING__ID, count(*) from T1 GROUP BY key, value WITH ROLLUP +) t +GROUP BY GROUPING__ID +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1 +#### A masked pattern was here #### +0 1 +1 4 +3 6 +PREHOOK: query: SELECT t1.GROUPING__ID, t2.GROUPING__ID FROM (SELECT GROUPING__ID FROM T1 GROUP BY key,value WITH ROLLUP) t1 +JOIN +(SELECT GROUPING__ID FROM T1 GROUP BY key, value WITH ROLLUP) t2 +ON t1.GROUPING__ID = t2.GROUPING__ID +PREHOOK: type: QUERY +PREHOOK: Input: default@t1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT t1.GROUPING__ID, t2.GROUPING__ID FROM (SELECT GROUPING__ID FROM T1 GROUP BY key,value WITH ROLLUP) t1 +JOIN +(SELECT GROUPING__ID FROM T1 GROUP BY key, value WITH ROLLUP) t2 +ON t1.GROUPING__ID = t2.GROUPING__ID +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1 +#### A masked pattern was here #### +0 0 +1 1 +1 1 +1 1 +1 1 +1 1 +1 1 +1 1 +1 1 +1 1 +1 1 +1 1 +1 1 +1 1 +1 1 +1 1 +1 1 +3 3 +3 3 +3 3 +3 3 +3 3 +3 3 +3 3 +3 3 +3 3 +3 3 +3 3 +3 3 +3 3 +3 3 +3 3 +3 3 +3 3 +3 3 +3 3 +3 3 +3 3 +3 3 +3 3 +3 3 +3 3 +3 3 +3 3 +3 3 +3 3 +3 3 +3 3 +3 3 +3 3 +3 3 +3 3 +3 3 +PREHOOK: query: SELECT key, value, GROUPING__ID, count(*) from T1 GROUP BY key, value WITH ROLLUP +PREHOOK: type: QUERY +PREHOOK: Input: default@t1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT key, value, GROUPING__ID, count(*) from T1 GROUP BY key, value WITH ROLLUP +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1 +#### A masked pattern was here #### +1 1 3 1 +1 NULL 1 2 +1 NULL 3 1 +2 2 3 1 +2 NULL 1 1 +3 3 3 1 +3 NULL 1 2 +3 NULL 3 1 +4 5 3 1 +4 NULL 1 1 +NULL NULL 0 6 +PREHOOK: query: SELECT GROUPING__ID, count(*) +FROM +( +SELECT key, value, GROUPING__ID, count(*) from T1 GROUP BY key, value WITH ROLLUP +) t +GROUP BY GROUPING__ID +PREHOOK: type: QUERY +PREHOOK: Input: default@t1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT GROUPING__ID, count(*) +FROM +( +SELECT key, value, GROUPING__ID, count(*) from T1 GROUP BY key, value WITH ROLLUP +) t +GROUP BY GROUPING__ID +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1 +#### A masked pattern was here #### +0 1 +1 4 +3 6 +PREHOOK: query: SELECT t1.GROUPING__ID, t2.GROUPING__ID FROM (SELECT GROUPING__ID FROM T1 GROUP BY key,value WITH ROLLUP) t1 +JOIN +(SELECT GROUPING__ID FROM T1 GROUP BY key, value WITH ROLLUP) t2 +ON t1.GROUPING__ID = t2.GROUPING__ID +PREHOOK: type: QUERY +PREHOOK: Input: default@t1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT t1.GROUPING__ID, t2.GROUPING__ID FROM (SELECT GROUPING__ID FROM T1 GROUP BY key,value WITH ROLLUP) t1 +JOIN +(SELECT GROUPING__ID FROM T1 GROUP BY key, value WITH ROLLUP) t2 +ON t1.GROUPING__ID = t2.GROUPING__ID +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1 +#### A masked pattern was here #### +0 0 +1 1 +1 1 +1 1 +1 1 +1 1 +1 1 +1 1 +1 1 +1 1 +1 1 +1 1 +1 1 +1 1 +1 1 +1 1 +1 1 +3 3 +3 3 +3 3 +3 3 +3 3 +3 3 +3 3 +3 3 +3 3 +3 3 +3 3 +3 3 +3 3 +3 3 +3 3 +3 3 +3 3 +3 3 +3 3 +3 3 +3 3 +3 3 +3 3 +3 3 +3 3 +3 3 +3 3 +3 3 +3 3 +3 3 +3 3 +3 3 +3 3 +3 3 +3 3 +3 3