| PREHOOK: query: -- run this test case in minimr to ensure it works in cluster |
| |
| -- list bucketing DML: static partition. multiple skewed columns. |
| -- ds=2008-04-08/hr=11/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME: |
| -- 5263 000000_0 |
| -- 5263 000001_0 |
| -- ds=2008-04-08/hr=11/key=103/value=val_103: |
| -- 99 000000_0 |
| -- 99 000001_0 |
| -- ds=2008-04-08/hr=11/key=484/value=val_484: |
| -- 87 000000_0 |
| -- 87 000001_0 |
| |
| -- create a skewed table |
| create table list_bucketing_static_part (key String, value String) |
| partitioned by (ds String, hr String) |
| skewed by (key) on ('484','51','103') |
| stored as DIRECTORIES |
| STORED AS RCFILE |
| PREHOOK: type: CREATETABLE |
| PREHOOK: Output: database:default |
| PREHOOK: Output: default@list_bucketing_static_part |
| POSTHOOK: query: -- run this test case in minimr to ensure it works in cluster |
| |
| -- list bucketing DML: static partition. multiple skewed columns. |
| -- ds=2008-04-08/hr=11/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME: |
| -- 5263 000000_0 |
| -- 5263 000001_0 |
| -- ds=2008-04-08/hr=11/key=103/value=val_103: |
| -- 99 000000_0 |
| -- 99 000001_0 |
| -- ds=2008-04-08/hr=11/key=484/value=val_484: |
| -- 87 000000_0 |
| -- 87 000001_0 |
| |
| -- create a skewed table |
| create table list_bucketing_static_part (key String, value String) |
| partitioned by (ds String, hr String) |
| skewed by (key) on ('484','51','103') |
| stored as DIRECTORIES |
| STORED AS RCFILE |
| POSTHOOK: type: CREATETABLE |
| POSTHOOK: Output: database:default |
| POSTHOOK: Output: default@list_bucketing_static_part |
| PREHOOK: query: -- list bucketing DML without merge. use bucketize to generate a few small files. |
| explain extended |
| insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11') |
| select key, value from src |
| PREHOOK: type: QUERY |
| POSTHOOK: query: -- list bucketing DML without merge. use bucketize to generate a few small files. |
| explain extended |
| insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11') |
| select key, value from src |
| 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: src |
| Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE |
| GatherStats: false |
| Select Operator |
| expressions: key (type: string), value (type: string) |
| outputColumnNames: _col0, _col1 |
| Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE |
| File Output Operator |
| compressed: false |
| GlobalTableId: 1 |
| #### A masked pattern was here #### |
| NumFilesPerFileSink: 1 |
| Static Partition Specification: ds=2008-04-08/hr=11/ |
| Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE |
| #### A masked pattern was here #### |
| table: |
| input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat |
| output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat |
| properties: |
| bucket_count -1 |
| columns key,value |
| columns.comments |
| columns.types string:string |
| #### A masked pattern was here #### |
| name default.list_bucketing_static_part |
| partition_columns.types string:string |
| serialization.ddl struct list_bucketing_static_part { string key, string value} |
| serialization.format 1 |
| serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe |
| #### A masked pattern was here #### |
| serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe |
| name: default.list_bucketing_static_part |
| TotalFiles: 1 |
| GatherStats: true |
| MultiFileSpray: false |
| Path -> Alias: |
| #### A masked pattern was here #### |
| Path -> Partition: |
| #### A masked pattern was here #### |
| Partition |
| base file name: src |
| input format: org.apache.hadoop.mapred.TextInputFormat |
| output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat |
| properties: |
| COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} |
| bucket_count -1 |
| columns key,value |
| columns.comments 'default','default' |
| columns.types string:string |
| #### A masked pattern was here #### |
| name default.src |
| numFiles 1 |
| numRows 500 |
| rawDataSize 5312 |
| serialization.ddl struct src { string key, string value} |
| serialization.format 1 |
| serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe |
| totalSize 5812 |
| #### 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: |
| COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} |
| bucket_count -1 |
| columns key,value |
| columns.comments 'default','default' |
| columns.types string:string |
| #### A masked pattern was here #### |
| name default.src |
| numFiles 1 |
| numRows 500 |
| rawDataSize 5312 |
| serialization.ddl struct src { string key, string value} |
| serialization.format 1 |
| serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe |
| totalSize 5812 |
| #### A masked pattern was here #### |
| serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe |
| name: default.src |
| name: default.src |
| Truncated Path -> Alias: |
| /src [src] |
| |
| 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: |
| ds 2008-04-08 |
| hr 11 |
| replace: true |
| #### A masked pattern was here #### |
| table: |
| input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat |
| output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat |
| properties: |
| bucket_count -1 |
| columns key,value |
| columns.comments |
| columns.types string:string |
| #### A masked pattern was here #### |
| name default.list_bucketing_static_part |
| partition_columns.types string:string |
| serialization.ddl struct list_bucketing_static_part { string key, string value} |
| serialization.format 1 |
| serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe |
| #### A masked pattern was here #### |
| serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe |
| name: default.list_bucketing_static_part |
| |
| Stage: Stage-2 |
| Stats-Aggr Operator |
| #### A masked pattern was here #### |
| |
| Stage: Stage-3 |
| Merge File Operator |
| Map Operator Tree: |
| RCFile Merge Operator |
| merge level: block |
| Path -> Alias: |
| #### A masked pattern was here #### |
| Path -> Partition: |
| #### A masked pattern was here #### |
| Partition |
| input format: org.apache.hadoop.hive.ql.io.rcfile.merge.RCFileBlockMergeInputFormat |
| output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat |
| properties: |
| bucket_count -1 |
| columns key,value |
| columns.comments |
| columns.types string:string |
| #### A masked pattern was here #### |
| name default.list_bucketing_static_part |
| partition_columns.types string:string |
| serialization.ddl struct list_bucketing_static_part { string key, string value} |
| serialization.format 1 |
| serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe |
| #### A masked pattern was here #### |
| serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe |
| |
| input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat |
| output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat |
| properties: |
| bucket_count -1 |
| columns key,value |
| columns.comments |
| columns.types string:string |
| #### A masked pattern was here #### |
| name default.list_bucketing_static_part |
| partition_columns.types string:string |
| serialization.ddl struct list_bucketing_static_part { string key, string value} |
| serialization.format 1 |
| serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe |
| #### A masked pattern was here #### |
| serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe |
| name: default.list_bucketing_static_part |
| name: default.list_bucketing_static_part |
| input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat |
| Truncated Path -> Alias: |
| #### A masked pattern was here #### |
| |
| Stage: Stage-5 |
| Merge File Operator |
| Map Operator Tree: |
| RCFile Merge Operator |
| merge level: block |
| Path -> Alias: |
| #### A masked pattern was here #### |
| Path -> Partition: |
| #### A masked pattern was here #### |
| Partition |
| input format: org.apache.hadoop.hive.ql.io.rcfile.merge.RCFileBlockMergeInputFormat |
| output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat |
| properties: |
| bucket_count -1 |
| columns key,value |
| columns.comments |
| columns.types string:string |
| #### A masked pattern was here #### |
| name default.list_bucketing_static_part |
| partition_columns.types string:string |
| serialization.ddl struct list_bucketing_static_part { string key, string value} |
| serialization.format 1 |
| serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe |
| #### A masked pattern was here #### |
| serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe |
| |
| input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat |
| output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat |
| properties: |
| bucket_count -1 |
| columns key,value |
| columns.comments |
| columns.types string:string |
| #### A masked pattern was here #### |
| name default.list_bucketing_static_part |
| partition_columns.types string:string |
| serialization.ddl struct list_bucketing_static_part { string key, string value} |
| serialization.format 1 |
| serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe |
| #### A masked pattern was here #### |
| serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe |
| name: default.list_bucketing_static_part |
| name: default.list_bucketing_static_part |
| input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat |
| Truncated Path -> Alias: |
| #### A masked pattern was here #### |
| |
| Stage: Stage-6 |
| Move Operator |
| files: |
| hdfs directory: true |
| #### A masked pattern was here #### |
| |
| PREHOOK: query: insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11') |
| select key, value from src |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@src |
| PREHOOK: Output: default@list_bucketing_static_part@ds=2008-04-08/hr=11 |
| POSTHOOK: query: insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11') |
| select key, value from src |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@src |
| POSTHOOK: Output: default@list_bucketing_static_part@ds=2008-04-08/hr=11 |
| POSTHOOK: Lineage: list_bucketing_static_part PARTITION(ds=2008-04-08,hr=11).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] |
| POSTHOOK: Lineage: list_bucketing_static_part PARTITION(ds=2008-04-08,hr=11).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] |
| PREHOOK: query: -- check DML result |
| show partitions list_bucketing_static_part |
| PREHOOK: type: SHOWPARTITIONS |
| PREHOOK: Input: default@list_bucketing_static_part |
| POSTHOOK: query: -- check DML result |
| show partitions list_bucketing_static_part |
| POSTHOOK: type: SHOWPARTITIONS |
| POSTHOOK: Input: default@list_bucketing_static_part |
| ds=2008-04-08/hr=11 |
| PREHOOK: query: desc formatted list_bucketing_static_part partition (ds='2008-04-08', hr='11') |
| PREHOOK: type: DESCTABLE |
| PREHOOK: Input: default@list_bucketing_static_part |
| POSTHOOK: query: desc formatted list_bucketing_static_part partition (ds='2008-04-08', hr='11') |
| POSTHOOK: type: DESCTABLE |
| POSTHOOK: Input: default@list_bucketing_static_part |
| # col_name data_type comment |
| |
| key string |
| value string |
| |
| # Partition Information |
| # col_name data_type comment |
| |
| ds string |
| hr string |
| |
| # Detailed Partition Information |
| Partition Value: [2008-04-08, 11] |
| Database: default |
| Table: list_bucketing_static_part |
| #### A masked pattern was here #### |
| Partition Parameters: |
| COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} |
| numFiles 4 |
| numRows 500 |
| rawDataSize 4812 |
| totalSize 5520 |
| #### A masked pattern was here #### |
| |
| # Storage Information |
| SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe |
| InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat |
| OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat |
| Compressed: No |
| Num Buckets: -1 |
| Bucket Columns: [] |
| Sort Columns: [] |
| Stored As SubDirectories: Yes |
| Skewed Columns: [key] |
| Skewed Values: [[103], [484], [51]] |
| #### A masked pattern was here #### |
| Skewed Value to Truncated Path: {[103]=/list_bucketing_static_part/ds=2008-04-08/hr=11/key=103, [484]=/list_bucketing_static_part/ds=2008-04-08/hr=11/key=484, [51]=/list_bucketing_static_part/ds=2008-04-08/hr=11/key=51} |
| Storage Desc Params: |
| serialization.format 1 |
