PREHOOK: query: -- This tests inferring how data is bucketed/sorted from the operators in the reducer -- and populating that information in partitions' metadata, in particular, this tests -- that operators in the mapper have no effect CREATE TABLE test_table1 (key STRING, value STRING) CLUSTERED BY (key) SORTED BY (key DESC) INTO 2 BUCKETS PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@test_table1 POSTHOOK: query: -- This tests inferring how data is bucketed/sorted from the operators in the reducer -- and populating that information in partitions' metadata, in particular, this tests -- that operators in the mapper have no effect CREATE TABLE test_table1 (key STRING, value STRING) CLUSTERED BY (key) SORTED BY (key DESC) INTO 2 BUCKETS POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@test_table1 PREHOOK: query: CREATE TABLE test_table2 (key STRING, value STRING) CLUSTERED BY (key) SORTED BY (key DESC) INTO 2 BUCKETS PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@test_table2 POSTHOOK: query: CREATE TABLE test_table2 (key STRING, value STRING) CLUSTERED BY (key) SORTED BY (key DESC) INTO 2 BUCKETS POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@test_table2 PREHOOK: query: INSERT OVERWRITE TABLE test_table1 SELECT key, value FROM src PREHOOK: type: QUERY PREHOOK: Input: default@src PREHOOK: Output: default@test_table1 POSTHOOK: query: INSERT OVERWRITE TABLE test_table1 SELECT key, value FROM src POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@test_table1 POSTHOOK: Lineage: test_table1.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: test_table1.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: INSERT OVERWRITE TABLE test_table2 SELECT key, value FROM src PREHOOK: type: QUERY PREHOOK: Input: default@src PREHOOK: Output: default@test_table2 POSTHOOK: query: INSERT OVERWRITE TABLE test_table2 SELECT key, value FROM src POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@test_table2 POSTHOOK: Lineage: test_table2.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: test_table2.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: CREATE TABLE test_table_out (key STRING, value STRING) PARTITIONED BY (part STRING) PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@test_table_out POSTHOOK: query: CREATE TABLE test_table_out (key STRING, value STRING) PARTITIONED BY (part STRING) POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@test_table_out PREHOOK: query: -- Test map group by doesn't affect inference, should not be bucketed or sorted EXPLAIN INSERT OVERWRITE TABLE test_table_out PARTITION (part = '1') SELECT key, count(*) FROM test_table1 GROUP BY key PREHOOK: type: QUERY POSTHOOK: query: -- Test map group by doesn't affect inference, should not be bucketed or sorted EXPLAIN INSERT OVERWRITE TABLE test_table_out PARTITION (part = '1') SELECT key, count(*) FROM test_table1 GROUP BY key POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5 Stage-4 Stage-0 depends on stages: Stage-4, Stage-3, Stage-6 Stage-2 depends on stages: Stage-0 Stage-3 Stage-5 Stage-6 depends on stages: Stage-5 STAGE PLANS: Stage: Stage-1 Map Reduce Map Operator Tree: TableScan alias: test_table1 Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: _col0 (type: string) mode: final outputColumnNames: _col0, _col1 Statistics: Num rows: 29 Data size: 2906 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false Statistics: Num rows: 29 Data size: 2906 Basic stats: COMPLETE Column stats: NONE 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 name: default.test_table_out Stage: Stage-7 Conditional Operator Stage: Stage-4 Move Operator files: hdfs directory: true #### A masked pattern was here #### Stage: Stage-0 Move Operator tables: partition: part 1 replace: true 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 name: default.test_table_out Stage: Stage-2 Stats-Aggr Operator Stage: Stage-3 Map Reduce Map Operator Tree: TableScan 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 name: default.test_table_out Stage: Stage-5 Map Reduce Map Operator Tree: TableScan 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 name: default.test_table_out Stage: Stage-6 Move Operator files: hdfs directory: true #### A masked pattern was here #### PREHOOK: query: INSERT OVERWRITE TABLE test_table_out PARTITION (part = '1') SELECT key, count(*) FROM test_table1 GROUP BY key PREHOOK: type: QUERY PREHOOK: Input: default@test_table1 PREHOOK: Output: default@test_table_out@part=1 POSTHOOK: query: INSERT OVERWRITE TABLE test_table_out PARTITION (part = '1') SELECT key, count(*) FROM test_table1 GROUP BY key POSTHOOK: type: QUERY POSTHOOK: Input: default@test_table1 POSTHOOK: Output: default@test_table_out@part=1 POSTHOOK: Lineage: test_table_out PARTITION(part=1).key SIMPLE [(test_table1)test_table1.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: test_table_out PARTITION(part=1).value EXPRESSION [(test_table1)test_table1.null, ] PREHOOK: query: DESCRIBE FORMATTED test_table_out PARTITION (part = '1') PREHOOK: type: DESCTABLE PREHOOK: Input: default@test_table_out POSTHOOK: query: DESCRIBE FORMATTED test_table_out PARTITION (part = '1') POSTHOOK: type: DESCTABLE POSTHOOK: Input: default@test_table_out # col_name data_type comment key string value string # Partition Information # col_name data_type comment part string # Detailed Partition Information Partition Value: [1] Database: default Table: test_table_out #### A masked pattern was here #### Protect Mode: None #### A masked pattern was here #### Partition Parameters: COLUMN_STATS_ACCURATE true numFiles 1 numRows 0 rawDataSize 0 totalSize 1791 #### A masked pattern was here #### # Storage Information SerDe Library: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe InputFormat: org.apache.hadoop.mapred.TextInputFormat OutputFormat: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat Compressed: No Num Buckets: -1 Bucket Columns: [] Sort Columns: [] Storage Desc Params: serialization.format 1 WARNING: Comparing a bigint and a string may result in a loss of precision. PREHOOK: query: -- Test map group by doesn't affect inference, should be bucketed and sorted by value EXPLAIN INSERT OVERWRITE TABLE test_table_out PARTITION (part = '1') SELECT a.key, a.value FROM ( SELECT key, count(*) AS value FROM test_table1 GROUP BY key ) a JOIN ( SELECT key, value FROM src ) b ON (a.value = b.value) PREHOOK: type: QUERY POSTHOOK: query: -- Test map group by doesn't affect inference, should be bucketed and sorted by value EXPLAIN INSERT OVERWRITE TABLE test_table_out PARTITION (part = '1') SELECT a.key, a.value FROM ( SELECT key, count(*) AS value FROM test_table1 GROUP BY key ) a JOIN ( SELECT key, value FROM src ) b ON (a.value = b.value) POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage Stage-0 depends on stages: Stage-1 Stage-2 depends on stages: Stage-0 STAGE PLANS: Stage: Stage-1 Map Reduce Map Operator Tree: TableScan alias: test_table1 Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: key Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: key (type: string) mode: final outputColumnNames: _col0, _col1 Statistics: Num rows: 29 Data size: 2906 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: UDFToDouble(_col1) is not null (type: boolean) Statistics: Num rows: 15 Data size: 1503 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: UDFToDouble(_col1) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(_col1) (type: double) Statistics: Num rows: 15 Data size: 1503 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string), _col1 (type: bigint) TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: UDFToDouble(value) is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) outputColumnNames: _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: UDFToDouble(_col1) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(_col1) (type: double) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: 0 UDFToDouble(_col1) (type: double) 1 UDFToDouble(_col1) (type: double) outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE 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 name: default.test_table_out Stage: Stage-0 Move Operator tables: partition: part 1 replace: true 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 name: default.test_table_out Stage: Stage-2 Stats-Aggr Operator PREHOOK: query: INSERT OVERWRITE TABLE test_table_out PARTITION (part = '1') SELECT a.key, a.value FROM ( SELECT key, cast(count(*) AS STRING) AS value FROM test_table1 GROUP BY key ) a JOIN ( SELECT key, value FROM src ) b ON (a.value = b.value) PREHOOK: type: QUERY PREHOOK: Input: default@src PREHOOK: Input: default@test_table1 PREHOOK: Output: default@test_table_out@part=1 POSTHOOK: query: INSERT OVERWRITE TABLE test_table_out PARTITION (part = '1') SELECT a.key, a.value FROM ( SELECT key, cast(count(*) AS STRING) AS value FROM test_table1 GROUP BY key ) a JOIN ( SELECT key, value FROM src ) b ON (a.value = b.value) POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Input: default@test_table1 POSTHOOK: Output: default@test_table_out@part=1 POSTHOOK: Lineage: test_table_out PARTITION(part=1).key SIMPLE [(test_table1)test_table1.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: test_table_out PARTITION(part=1).value EXPRESSION [(test_table1)test_table1.null, ] PREHOOK: query: DESCRIBE FORMATTED test_table_out PARTITION (part = '1') PREHOOK: type: DESCTABLE PREHOOK: Input: default@test_table_out POSTHOOK: query: DESCRIBE FORMATTED test_table_out PARTITION (part = '1') POSTHOOK: type: DESCTABLE POSTHOOK: Input: default@test_table_out # col_name data_type comment key string value string # Partition Information # col_name data_type comment part string # Detailed Partition Information Partition Value: [1] Database: default Table: test_table_out #### A masked pattern was here #### Protect Mode: None #### A masked pattern was here #### Partition Parameters: COLUMN_STATS_ACCURATE true numFiles 1 numRows 0 rawDataSize 0 totalSize 0 #### A masked pattern was here #### # Storage Information SerDe Library: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe InputFormat: org.apache.hadoop.mapred.TextInputFormat OutputFormat: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat Compressed: No Num Buckets: 1 Bucket Columns: [value] Sort Columns: [Order(col:value, order:1)] Storage Desc Params: serialization.format 1 PREHOOK: query: -- Test SMB join doesn't affect inference, should not be bucketed or sorted EXPLAIN INSERT OVERWRITE TABLE test_table_out PARTITION (part = '1') SELECT /*+ MAPJOIN(a) */ a.key, b.value FROM test_table1 a JOIN test_table2 b ON a.key = b.key PREHOOK: type: QUERY POSTHOOK: query: -- Test SMB join doesn't affect inference, should not be bucketed or sorted EXPLAIN INSERT OVERWRITE TABLE test_table_out PARTITION (part = '1') SELECT /*+ MAPJOIN(a) */ a.key, b.value FROM test_table1 a JOIN test_table2 b ON a.key = b.key POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage Stage-8 depends on stages: Stage-1 , consists of Stage-5, Stage-4, Stage-6 Stage-5 Stage-0 depends on stages: Stage-5, Stage-4, Stage-7 Stage-3 depends on stages: Stage-0 Stage-4 Stage-6 Stage-7 depends on stages: Stage-6 STAGE PLANS: Stage: Stage-1 Map Reduce Map Operator Tree: TableScan alias: b Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 15 Data size: 3006 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 keys: 0 key (type: string) 1 key (type: string) outputColumnNames: _col0, _col6 Select Operator expressions: _col0 (type: string), _col6 (type: string) 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 name: default.test_table_out Stage: Stage-8 Conditional Operator Stage: Stage-5 Move Operator files: hdfs directory: true #### A masked pattern was here #### Stage: Stage-0 Move Operator tables: partition: part 1 replace: true 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 name: default.test_table_out Stage: Stage-3 Stats-Aggr Operator Stage: Stage-4 Map Reduce Map Operator Tree: TableScan 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 name: default.test_table_out Stage: Stage-6 Map Reduce Map Operator Tree: TableScan 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 name: default.test_table_out Stage: Stage-7 Move Operator files: hdfs directory: true #### A masked pattern was here #### PREHOOK: query: INSERT OVERWRITE TABLE test_table_out PARTITION (part = '1') SELECT /*+ MAPJOIN(a) */ a.key, b.value FROM test_table1 a JOIN test_table2 b ON a.key = b.key PREHOOK: type: QUERY PREHOOK: Input: default@test_table1 PREHOOK: Input: default@test_table2 PREHOOK: Output: default@test_table_out@part=1 POSTHOOK: query: INSERT OVERWRITE TABLE test_table_out PARTITION (part = '1') SELECT /*+ MAPJOIN(a) */ a.key, b.value FROM test_table1 a JOIN test_table2 b ON a.key = b.key POSTHOOK: type: QUERY POSTHOOK: Input: default@test_table1 POSTHOOK: Input: default@test_table2 POSTHOOK: Output: default@test_table_out@part=1 POSTHOOK: Lineage: test_table_out PARTITION(part=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: test_table_out PARTITION(part=1).value SIMPLE [(test_table2)b.FieldSchema(name:value, type:string, comment:null), ] PREHOOK: query: DESCRIBE FORMATTED test_table_out PARTITION (part = '1') PREHOOK: type: DESCTABLE PREHOOK: Input: default@test_table_out POSTHOOK: query: DESCRIBE FORMATTED test_table_out PARTITION (part = '1') POSTHOOK: type: DESCTABLE POSTHOOK: Input: default@test_table_out # col_name data_type comment key string value string # Partition Information # col_name data_type comment part string # Detailed Partition Information Partition Value: [1] Database: default Table: test_table_out #### A masked pattern was here #### Protect Mode: None #### A masked pattern was here #### Partition Parameters: COLUMN_STATS_ACCURATE true numFiles 1 numRows 0 rawDataSize 0 totalSize 11996 #### A masked pattern was here #### # Storage Information SerDe Library: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe InputFormat: org.apache.hadoop.mapred.TextInputFormat OutputFormat: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat Compressed: No Num Buckets: -1 Bucket Columns: [] Sort Columns: [] Storage Desc Params: serialization.format 1 PREHOOK: query: -- Test SMB join doesn't affect inference, should be bucketed and sorted by key EXPLAIN INSERT OVERWRITE TABLE test_table_out PARTITION (part = '1') SELECT /*+ MAPJOIN(a) */ b.value, count(*) FROM test_table1 a JOIN test_table2 b ON a.key = b.key GROUP BY b.value PREHOOK: type: QUERY POSTHOOK: query: -- Test SMB join doesn't affect inference, should be bucketed and sorted by key EXPLAIN INSERT OVERWRITE TABLE test_table_out PARTITION (part = '1') SELECT /*+ MAPJOIN(a) */ b.value, count(*) FROM test_table1 a JOIN test_table2 b ON a.key = b.key GROUP BY b.value POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage Stage-0 depends on stages: Stage-1 Stage-3 depends on stages: Stage-0 STAGE PLANS: Stage: Stage-1 Map Reduce Map Operator Tree: TableScan alias: b Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 15 Data size: 3006 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 keys: 0 key (type: string) 1 key (type: string) outputColumnNames: _col6 Group By Operator aggregations: count() keys: _col6 (type: string) mode: hash outputColumnNames: _col0, _col1 Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial 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 name: default.test_table_out Stage: Stage-0 Move Operator tables: partition: part 1 replace: true 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 name: default.test_table_out Stage: Stage-3 Stats-Aggr Operator PREHOOK: query: INSERT OVERWRITE TABLE test_table_out PARTITION (part = '1') SELECT /*+ MAPJOIN(a) */ b.value, count(*) FROM test_table1 a JOIN test_table2 b ON a.key = b.key GROUP BY b.value PREHOOK: type: QUERY PREHOOK: Input: default@test_table1 PREHOOK: Input: default@test_table2 PREHOOK: Output: default@test_table_out@part=1 POSTHOOK: query: INSERT OVERWRITE TABLE test_table_out PARTITION (part = '1') SELECT /*+ MAPJOIN(a) */ b.value, count(*) FROM test_table1 a JOIN test_table2 b ON a.key = b.key GROUP BY b.value POSTHOOK: type: QUERY POSTHOOK: Input: default@test_table1 POSTHOOK: Input: default@test_table2 POSTHOOK: Output: default@test_table_out@part=1 POSTHOOK: Lineage: test_table_out PARTITION(part=1).key SIMPLE [(test_table2)b.FieldSchema(name:value, type:string, comment:null), ] POSTHOOK: Lineage: test_table_out PARTITION(part=1).value EXPRESSION [(test_table1)a.null, (test_table2)b.null, ] PREHOOK: query: DESCRIBE FORMATTED test_table_out PARTITION (part = '1') PREHOOK: type: DESCTABLE PREHOOK: Input: default@test_table_out POSTHOOK: query: DESCRIBE FORMATTED test_table_out PARTITION (part = '1') POSTHOOK: type: DESCTABLE POSTHOOK: Input: default@test_table_out # col_name data_type comment key string value string # Partition Information # col_name data_type comment part string # Detailed Partition Information Partition Value: [1] Database: default Table: test_table_out #### A masked pattern was here #### Protect Mode: None #### A masked pattern was here #### Partition Parameters: COLUMN_STATS_ACCURATE true numFiles 1 numRows 0 rawDataSize 0 totalSize 3037 #### A masked pattern was here #### # Storage Information SerDe Library: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe InputFormat: org.apache.hadoop.mapred.TextInputFormat OutputFormat: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat Compressed: No Num Buckets: 1 Bucket Columns: [key] Sort Columns: [Order(col:key, order:1)] Storage Desc Params: serialization.format 1