PREHOOK: query: DROP TABLE Employee_Part PREHOOK: type: DROPTABLE POSTHOOK: query: DROP TABLE Employee_Part POSTHOOK: type: DROPTABLE PREHOOK: query: CREATE TABLE Employee_Part(employeeID int, employeeName String) partitioned by (employeeSalary double) row format delimited fields terminated by '|' stored as textfile PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@Employee_Part POSTHOOK: query: CREATE TABLE Employee_Part(employeeID int, employeeName String) partitioned by (employeeSalary double) row format delimited fields terminated by '|' stored as textfile POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@Employee_Part PREHOOK: query: LOAD DATA LOCAL INPATH "../../data/files/employee.dat" INTO TABLE Employee_Part partition(employeeSalary=2000.0) PREHOOK: type: LOAD #### A masked pattern was here #### PREHOOK: Output: default@employee_part POSTHOOK: query: LOAD DATA LOCAL INPATH "../../data/files/employee.dat" INTO TABLE Employee_Part partition(employeeSalary=2000.0) POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@employee_part POSTHOOK: Output: default@employee_part@employeesalary=2000.0 PREHOOK: query: LOAD DATA LOCAL INPATH "../../data/files/employee.dat" INTO TABLE Employee_Part partition(employeeSalary=4000.0) PREHOOK: type: LOAD #### A masked pattern was here #### PREHOOK: Output: default@employee_part POSTHOOK: query: LOAD DATA LOCAL INPATH "../../data/files/employee.dat" INTO TABLE Employee_Part partition(employeeSalary=4000.0) POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@employee_part POSTHOOK: Output: default@employee_part@employeesalary=4000.0 PREHOOK: query: explain analyze table Employee_Part partition (employeeSalary=2000.0) compute statistics for columns employeeID PREHOOK: type: QUERY POSTHOOK: query: explain analyze table Employee_Part partition (employeeSalary=2000.0) compute statistics for columns employeeID POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-0 is a root stage Stage-1 is a root stage STAGE PLANS: Stage: Stage-0 Map Reduce Map Operator Tree: TableScan alias: employee_part Select Operator expressions: 2000.0 (type: double), employeeid (type: int) outputColumnNames: employeesalary, employeeid Group By Operator aggregations: compute_stats(employeeid, 16) keys: employeesalary (type: double) mode: hash outputColumnNames: _col0, _col1 Reduce Output Operator key expressions: _col0 (type: double) sort order: + Map-reduce partition columns: _col0 (type: double) value expressions: _col1 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0) keys: KEY._col0 (type: double) mode: mergepartial outputColumnNames: _col0, _col1 Select Operator expressions: _col1 (type: struct), _col0 (type: double) outputColumnNames: _col0, _col1 File Output Operator compressed: false table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-1 Column Stats Work Column Stats Desc: Columns: employeeID Column Types: int Table: employee_part PREHOOK: query: explain extended analyze table Employee_Part partition (employeeSalary=2000.0) compute statistics for columns employeeID PREHOOK: type: QUERY POSTHOOK: query: explain extended analyze table Employee_Part partition (employeeSalary=2000.0) compute statistics for columns employeeID POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: TOK_ANALYZE TOK_TAB TOK_TABNAME Employee_Part TOK_PARTSPEC TOK_PARTVAL employeeSalary 2000.0 columns TOK_TABCOLNAME employeeID STAGE DEPENDENCIES: Stage-0 is a root stage Stage-1 is a root stage STAGE PLANS: Stage: Stage-0 Map Reduce Map Operator Tree: TableScan alias: employee_part GatherStats: false Select Operator expressions: 2000.0 (type: double), employeeid (type: int) outputColumnNames: employeesalary, employeeid Group By Operator aggregations: compute_stats(employeeid, 16) keys: employeesalary (type: double) mode: hash outputColumnNames: _col0, _col1 Reduce Output Operator key expressions: _col0 (type: double) sort order: + Map-reduce partition columns: _col0 (type: double) tag: -1 value expressions: _col1 (type: struct) auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: employeesalary=2000.0 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat partition values: employeesalary 2000.0 properties: COLUMN_STATS_ACCURATE true bucket_count -1 columns employeeid,employeename columns.comments columns.types int:string field.delim | #### A masked pattern was here #### name default.employee_part numFiles 1 numRows 0 partition_columns employeesalary partition_columns.types double rawDataSize 0 serialization.ddl struct employee_part { i32 employeeid, string employeename} serialization.format | serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 105 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 columns employeeid,employeename columns.comments columns.types int:string field.delim | #### A masked pattern was here #### name default.employee_part partition_columns employeesalary partition_columns.types double serialization.ddl struct employee_part { i32 employeeid, string employeename} serialization.format | serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.employee_part name: default.employee_part Truncated Path -> Alias: /employee_part/employeesalary=2000.0 [employee_part] Needs Tagging: false Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0) keys: KEY._col0 (type: double) mode: mergepartial outputColumnNames: _col0, _col1 Select Operator expressions: _col1 (type: struct), _col0 (type: double) outputColumnNames: _col0, _col1 File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: columns _col0,_col1 columns.types struct:double escape.delim \ hive.serialization.extend.nesting.levels true serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TotalFiles: 1 GatherStats: false MultiFileSpray: false Stage: Stage-1 Column Stats Work Column Stats Desc: Columns: employeeID Column Types: int Table: employee_part Is Table Level Stats: false PREHOOK: query: analyze table Employee_Part partition (employeeSalary=2000.0) compute statistics for columns employeeID PREHOOK: type: QUERY PREHOOK: Input: default@employee_part PREHOOK: Input: default@employee_part@employeesalary=2000.0 #### A masked pattern was here #### POSTHOOK: query: analyze table Employee_Part partition (employeeSalary=2000.0) compute statistics for columns employeeID POSTHOOK: type: QUERY POSTHOOK: Input: default@employee_part POSTHOOK: Input: default@employee_part@employeesalary=2000.0 #### A masked pattern was here #### PREHOOK: query: explain analyze table Employee_Part partition (employeeSalary=4000.0) compute statistics for columns employeeID PREHOOK: type: QUERY POSTHOOK: query: explain analyze table Employee_Part partition (employeeSalary=4000.0) compute statistics for columns employeeID POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-0 is a root stage Stage-1 is a root stage STAGE PLANS: Stage: Stage-0 Map Reduce Map Operator Tree: TableScan alias: employee_part Select Operator expressions: 4000.0 (type: double), employeeid (type: int) outputColumnNames: employeesalary, employeeid Group By Operator aggregations: compute_stats(employeeid, 16) keys: employeesalary (type: double) mode: hash outputColumnNames: _col0, _col1 Reduce Output Operator key expressions: _col0 (type: double) sort order: + Map-reduce partition columns: _col0 (type: double) value expressions: _col1 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0) keys: KEY._col0 (type: double) mode: mergepartial outputColumnNames: _col0, _col1 Select Operator expressions: _col1 (type: struct), _col0 (type: double) outputColumnNames: _col0, _col1 File Output Operator compressed: false table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-1 Column Stats Work Column Stats Desc: Columns: employeeID Column Types: int Table: employee_part PREHOOK: query: explain extended analyze table Employee_Part partition (employeeSalary=4000.0) compute statistics for columns employeeID PREHOOK: type: QUERY POSTHOOK: query: explain extended analyze table Employee_Part partition (employeeSalary=4000.0) compute statistics for columns employeeID POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: TOK_ANALYZE TOK_TAB TOK_TABNAME Employee_Part TOK_PARTSPEC TOK_PARTVAL employeeSalary 4000.0 columns TOK_TABCOLNAME employeeID STAGE DEPENDENCIES: Stage-0 is a root stage Stage-1 is a root stage STAGE PLANS: Stage: Stage-0 Map Reduce Map Operator Tree: TableScan alias: employee_part GatherStats: false Select Operator expressions: 4000.0 (type: double), employeeid (type: int) outputColumnNames: employeesalary, employeeid Group By Operator aggregations: compute_stats(employeeid, 16) keys: employeesalary (type: double) mode: hash outputColumnNames: _col0, _col1 Reduce Output Operator key expressions: _col0 (type: double) sort order: + Map-reduce partition columns: _col0 (type: double) tag: -1 value expressions: _col1 (type: struct) auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: employeesalary=4000.0 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat partition values: employeesalary 4000.0 properties: COLUMN_STATS_ACCURATE true bucket_count -1 columns employeeid,employeename columns.comments columns.types int:string field.delim | #### A masked pattern was here #### name default.employee_part numFiles 1 numRows 0 partition_columns employeesalary partition_columns.types double rawDataSize 0 serialization.ddl struct employee_part { i32 employeeid, string employeename} serialization.format | serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 105 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 columns employeeid,employeename columns.comments columns.types int:string field.delim | #### A masked pattern was here #### name default.employee_part partition_columns employeesalary partition_columns.types double serialization.ddl struct employee_part { i32 employeeid, string employeename} serialization.format | serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.employee_part name: default.employee_part Truncated Path -> Alias: /employee_part/employeesalary=4000.0 [employee_part] Needs Tagging: false Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0) keys: KEY._col0 (type: double) mode: mergepartial outputColumnNames: _col0, _col1 Select Operator expressions: _col1 (type: struct), _col0 (type: double) outputColumnNames: _col0, _col1 File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: columns _col0,_col1 columns.types struct:double escape.delim \ hive.serialization.extend.nesting.levels true serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TotalFiles: 1 GatherStats: false MultiFileSpray: false Stage: Stage-1 Column Stats Work Column Stats Desc: Columns: employeeID Column Types: int Table: employee_part Is Table Level Stats: false PREHOOK: query: analyze table Employee_Part partition (employeeSalary=4000.0) compute statistics for columns employeeID PREHOOK: type: QUERY PREHOOK: Input: default@employee_part PREHOOK: Input: default@employee_part@employeesalary=4000.0 #### A masked pattern was here #### POSTHOOK: query: analyze table Employee_Part partition (employeeSalary=4000.0) compute statistics for columns employeeID POSTHOOK: type: QUERY POSTHOOK: Input: default@employee_part POSTHOOK: Input: default@employee_part@employeesalary=4000.0 #### A masked pattern was here #### PREHOOK: query: explain analyze table Employee_Part partition (employeeSalary=2000.0) compute statistics for columns PREHOOK: type: QUERY POSTHOOK: query: explain analyze table Employee_Part partition (employeeSalary=2000.0) compute statistics for columns POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-0 is a root stage Stage-1 is a root stage STAGE PLANS: Stage: Stage-0 Map Reduce Map Operator Tree: TableScan alias: employee_part Select Operator expressions: 2000.0 (type: double), employeeid (type: int), employeename (type: string) outputColumnNames: employeesalary, employeeid, employeename Group By Operator aggregations: compute_stats(employeeid, 16), compute_stats(employeename, 16) keys: employeesalary (type: double) mode: hash outputColumnNames: _col0, _col1, _col2 Reduce Output Operator key expressions: _col0 (type: double) sort order: + Map-reduce partition columns: _col0 (type: double) value expressions: _col1 (type: struct), _col2 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) keys: KEY._col0 (type: double) mode: mergepartial outputColumnNames: _col0, _col1, _col2 Select Operator expressions: _col1 (type: struct), _col2 (type: struct), _col0 (type: double) outputColumnNames: _col0, _col1, _col2 File Output Operator compressed: false table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-1 Column Stats Work Column Stats Desc: Columns: employeeid, employeename Column Types: int, string Table: employee_part PREHOOK: query: analyze table Employee_Part partition (employeeSalary=2000.0) compute statistics for columns PREHOOK: type: QUERY PREHOOK: Input: default@employee_part PREHOOK: Input: default@employee_part@employeesalary=2000.0 #### A masked pattern was here #### POSTHOOK: query: analyze table Employee_Part partition (employeeSalary=2000.0) compute statistics for columns POSTHOOK: type: QUERY POSTHOOK: Input: default@employee_part POSTHOOK: Input: default@employee_part@employeesalary=2000.0 #### A masked pattern was here #### PREHOOK: query: describe formatted Employee_Part.employeeID partition (employeeSalary=2000.0) PREHOOK: type: DESCTABLE PREHOOK: Input: default@employee_part POSTHOOK: query: describe formatted Employee_Part.employeeID partition (employeeSalary=2000.0) POSTHOOK: type: DESCTABLE POSTHOOK: Input: default@employee_part # col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment employeeID int 16 34 1 14 from deserializer PREHOOK: query: describe formatted Employee_Part.employeeName partition (employeeSalary=2000.0) PREHOOK: type: DESCTABLE PREHOOK: Input: default@employee_part POSTHOOK: query: describe formatted Employee_Part.employeeName partition (employeeSalary=2000.0) POSTHOOK: type: DESCTABLE POSTHOOK: Input: default@employee_part # col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment employeeName string 1 9 4.3076923076923075 6 from deserializer PREHOOK: query: explain analyze table Employee_Part compute statistics for columns PREHOOK: type: QUERY POSTHOOK: query: explain analyze table Employee_Part compute statistics for columns POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-0 is a root stage Stage-1 is a root stage STAGE PLANS: Stage: Stage-0 Map Reduce Map Operator Tree: TableScan alias: employee_part Select Operator expressions: employeesalary (type: double), employeeid (type: int), employeename (type: string) outputColumnNames: employeesalary, employeeid, employeename Group By Operator aggregations: compute_stats(employeeid, 16), compute_stats(employeename, 16) keys: employeesalary (type: double) mode: hash outputColumnNames: _col0, _col1, _col2 Reduce Output Operator key expressions: _col0 (type: double) sort order: + Map-reduce partition columns: _col0 (type: double) value expressions: _col1 (type: struct), _col2 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) keys: KEY._col0 (type: double) mode: mergepartial outputColumnNames: _col0, _col1, _col2 Select Operator expressions: _col1 (type: struct), _col2 (type: struct), _col0 (type: double) outputColumnNames: _col0, _col1, _col2 File Output Operator compressed: false table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-1 Column Stats Work Column Stats Desc: Columns: employeeid, employeename Column Types: int, string Table: employee_part PREHOOK: query: analyze table Employee_Part compute statistics for columns PREHOOK: type: QUERY PREHOOK: Input: default@employee_part PREHOOK: Input: default@employee_part@employeesalary=2000.0 PREHOOK: Input: default@employee_part@employeesalary=4000.0 #### A masked pattern was here #### POSTHOOK: query: analyze table Employee_Part compute statistics for columns POSTHOOK: type: QUERY POSTHOOK: Input: default@employee_part POSTHOOK: Input: default@employee_part@employeesalary=2000.0 POSTHOOK: Input: default@employee_part@employeesalary=4000.0 #### A masked pattern was here #### PREHOOK: query: describe formatted Employee_Part.employeeID partition(employeeSalary=2000.0) PREHOOK: type: DESCTABLE PREHOOK: Input: default@employee_part POSTHOOK: query: describe formatted Employee_Part.employeeID partition(employeeSalary=2000.0) POSTHOOK: type: DESCTABLE POSTHOOK: Input: default@employee_part # col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment employeeID int 16 34 1 14 from deserializer PREHOOK: query: describe formatted Employee_Part.employeeID partition(employeeSalary=4000.0) PREHOOK: type: DESCTABLE PREHOOK: Input: default@employee_part POSTHOOK: query: describe formatted Employee_Part.employeeID partition(employeeSalary=4000.0) POSTHOOK: type: DESCTABLE POSTHOOK: Input: default@employee_part # col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment employeeID int 16 34 1 14 from deserializer PREHOOK: query: explain analyze table Employee_Part compute statistics for columns PREHOOK: type: QUERY POSTHOOK: query: explain analyze table Employee_Part compute statistics for columns POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-0 is a root stage Stage-1 is a root stage STAGE PLANS: Stage: Stage-0 Map Reduce Map Operator Tree: TableScan alias: employee_part Select Operator expressions: employeeid (type: int), employeename (type: string) outputColumnNames: employeeid, employeename Group By Operator aggregations: compute_stats(employeeid, 16), compute_stats(employeename, 16) mode: hash outputColumnNames: _col0, _col1 Reduce Output Operator sort order: value expressions: _col0 (type: struct), _col1 (type: struct) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) mode: mergepartial outputColumnNames: _col0, _col1 Select Operator expressions: _col0 (type: struct), _col1 (type: struct) outputColumnNames: _col0, _col1 File Output Operator compressed: false table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-1 Column Stats Work Column Stats Desc: Columns: employeeid, employeename Column Types: int, string Table: employee_part PREHOOK: query: analyze table Employee_Part compute statistics for columns PREHOOK: type: QUERY PREHOOK: Input: default@employee_part PREHOOK: Input: default@employee_part@employeesalary=2000.0 PREHOOK: Input: default@employee_part@employeesalary=4000.0 #### A masked pattern was here #### POSTHOOK: query: analyze table Employee_Part compute statistics for columns POSTHOOK: type: QUERY POSTHOOK: Input: default@employee_part POSTHOOK: Input: default@employee_part@employeesalary=2000.0 POSTHOOK: Input: default@employee_part@employeesalary=4000.0 #### A masked pattern was here #### PREHOOK: query: describe formatted Employee_Part.employeeID PREHOOK: type: DESCTABLE PREHOOK: Input: default@employee_part POSTHOOK: query: describe formatted Employee_Part.employeeID POSTHOOK: type: DESCTABLE POSTHOOK: Input: default@employee_part # col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment employeeID int 16 34 2 14 from deserializer