PREHOOK: query: -- SORT_QUERY_RESULTS DROP TABLE part_staging PREHOOK: type: DROPTABLE POSTHOOK: query: -- SORT_QUERY_RESULTS DROP TABLE part_staging POSTHOOK: type: DROPTABLE PREHOOK: query: DROP TABLE part_orc PREHOOK: type: DROPTABLE POSTHOOK: query: DROP TABLE part_orc POSTHOOK: type: DROPTABLE PREHOOK: query: -- NOTE: This test is a copy of ptf. -- NOTE: We cannot vectorize "pure" table functions (e.g. NOOP) -- given their blackbox nature. So only queries without table functions and -- NOTE: with windowing will be vectorized. -- data setup CREATE TABLE part_staging( p_partkey INT, p_name STRING, p_mfgr STRING, p_brand STRING, p_type STRING, p_size INT, p_container STRING, p_retailprice DOUBLE, p_comment STRING ) PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@part_staging POSTHOOK: query: -- NOTE: This test is a copy of ptf. -- NOTE: We cannot vectorize "pure" table functions (e.g. NOOP) -- given their blackbox nature. So only queries without table functions and -- NOTE: with windowing will be vectorized. -- data setup CREATE TABLE part_staging( p_partkey INT, p_name STRING, p_mfgr STRING, p_brand STRING, p_type STRING, p_size INT, p_container STRING, p_retailprice DOUBLE, p_comment STRING ) POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@part_staging PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/part_tiny.txt' overwrite into table part_staging PREHOOK: type: LOAD #### A masked pattern was here #### PREHOOK: Output: default@part_staging POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/part_tiny.txt' overwrite into table part_staging POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@part_staging PREHOOK: query: CREATE TABLE part_orc( p_partkey INT, p_name STRING, p_mfgr STRING, p_brand STRING, p_type STRING, p_size INT, p_container STRING, p_retailprice DOUBLE, p_comment STRING ) STORED AS ORC PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@part_orc POSTHOOK: query: CREATE TABLE part_orc( p_partkey INT, p_name STRING, p_mfgr STRING, p_brand STRING, p_type STRING, p_size INT, p_container STRING, p_retailprice DOUBLE, p_comment STRING ) STORED AS ORC POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@part_orc PREHOOK: query: DESCRIBE EXTENDED part_orc PREHOOK: type: DESCTABLE PREHOOK: Input: default@part_orc POSTHOOK: query: DESCRIBE EXTENDED part_orc POSTHOOK: type: DESCTABLE POSTHOOK: Input: default@part_orc p_partkey int p_name string p_mfgr string p_brand string p_type string p_size int p_container string p_retailprice double p_comment string #### A masked pattern was here #### PREHOOK: query: insert into table part_orc select * from part_staging PREHOOK: type: QUERY PREHOOK: Input: default@part_staging PREHOOK: Output: default@part_orc POSTHOOK: query: insert into table part_orc select * from part_staging POSTHOOK: type: QUERY POSTHOOK: Input: default@part_staging POSTHOOK: Output: default@part_orc POSTHOOK: Lineage: part_orc.p_brand SIMPLE [(part_staging)part_staging.FieldSchema(name:p_brand, type:string, comment:null), ] POSTHOOK: Lineage: part_orc.p_comment SIMPLE [(part_staging)part_staging.FieldSchema(name:p_comment, type:string, comment:null), ] POSTHOOK: Lineage: part_orc.p_container SIMPLE [(part_staging)part_staging.FieldSchema(name:p_container, type:string, comment:null), ] POSTHOOK: Lineage: part_orc.p_mfgr SIMPLE [(part_staging)part_staging.FieldSchema(name:p_mfgr, type:string, comment:null), ] POSTHOOK: Lineage: part_orc.p_name SIMPLE [(part_staging)part_staging.FieldSchema(name:p_name, type:string, comment:null), ] POSTHOOK: Lineage: part_orc.p_partkey SIMPLE [(part_staging)part_staging.FieldSchema(name:p_partkey, type:int, comment:null), ] POSTHOOK: Lineage: part_orc.p_retailprice SIMPLE [(part_staging)part_staging.FieldSchema(name:p_retailprice, type:double, comment:null), ] POSTHOOK: Lineage: part_orc.p_size SIMPLE [(part_staging)part_staging.FieldSchema(name:p_size, type:int, comment:null), ] POSTHOOK: Lineage: part_orc.p_type SIMPLE [(part_staging)part_staging.FieldSchema(name:p_type, type:string, comment:null), ] PREHOOK: query: --1. test1 explain extended select p_mfgr, p_name, p_size, rank() over (partition by p_mfgr order by p_name) as r, dense_rank() over (partition by p_mfgr order by p_name) as dr, sum(p_retailprice) over (partition by p_mfgr order by p_name rows between unbounded preceding and current row) as s1 from noop(on part_orc partition by p_mfgr order by p_name ) PREHOOK: type: QUERY POSTHOOK: query: --1. test1 explain extended select p_mfgr, p_name, p_size, rank() over (partition by p_mfgr order by p_name) as r, dense_rank() over (partition by p_mfgr order by p_name) as dr, sum(p_retailprice) over (partition by p_mfgr order by p_name rows between unbounded preceding and current row) as s1 from noop(on part_orc partition by p_mfgr order by p_name ) POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: TOK_QUERY TOK_FROM TOK_PTBLFUNCTION noop TOK_TABREF TOK_TABNAME part_orc TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name TOK_INSERT TOK_DESTINATION TOK_DIR TOK_TMP_FILE TOK_SELECT TOK_SELEXPR TOK_TABLE_OR_COL p_mfgr TOK_SELEXPR TOK_TABLE_OR_COL p_name TOK_SELEXPR TOK_TABLE_OR_COL p_size TOK_SELEXPR TOK_FUNCTION rank TOK_WINDOWSPEC TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name r TOK_SELEXPR TOK_FUNCTION dense_rank TOK_WINDOWSPEC TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name dr TOK_SELEXPR TOK_FUNCTION sum TOK_TABLE_OR_COL p_retailprice TOK_WINDOWSPEC TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name TOK_WINDOWRANGE preceding unbounded current s1 STAGE DEPENDENCIES: Stage-1 is a root stage Stage-2 depends on stages: Stage-1 Stage-0 depends on stages: Stage-2 STAGE PLANS: Stage: Stage-1 Map Reduce Map Operator Tree: TableScan alias: part_orc Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE GatherStats: false Reduce Output Operator key expressions: p_mfgr (type: string), p_name (type: string) sort order: ++ Map-reduce partition columns: p_mfgr (type: string) Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: p_size (type: int), p_retailprice (type: double) auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: part_orc input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat properties: COLUMN_STATS_ACCURATE true bucket_count -1 columns p_partkey,p_name,p_mfgr,p_brand,p_type,p_size,p_container,p_retailprice,p_comment columns.comments columns.types int:string:string:string:string:int:string:double:string #### A masked pattern was here #### name default.part_orc numFiles 1 numRows 26 rawDataSize 16042 serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde totalSize 2655 #### 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: COLUMN_STATS_ACCURATE true bucket_count -1 columns p_partkey,p_name,p_mfgr,p_brand,p_type,p_size,p_container,p_retailprice,p_comment columns.comments columns.types int:string:string:string:string:int:string:double:string #### A masked pattern was here #### name default.part_orc numFiles 1 numRows 26 rawDataSize 16042 serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde totalSize 2655 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.part_orc name: default.part_orc Truncated Path -> Alias: /part_orc [part_orc] Execution mode: vectorized Needs Tagging: false Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int), VALUE._col5 (type: double) outputColumnNames: _col1, _col2, _col5, _col7 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: part_orc output shape: _col1: string, _col2: string, _col5: int, _col7: double type: TABLE Partition table definition input alias: ptf_1 name: noop order by: _col1 output shape: _col1: string, _col2: string, _col5: int, _col7: double partition by: _col2 raw input shape: Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5,_col7 columns.types string,string,int,double escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe TotalFiles: 1 GatherStats: false MultiFileSpray: false Stage: Stage-2 Map Reduce Map Operator Tree: TableScan GatherStats: false Reduce Output Operator key expressions: _col2 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col2 (type: string) Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col5 (type: int), _col7 (type: double) auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: -mr-10002 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5,_col7 columns.types string,string,int,double escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5,_col7 columns.types string,string,int,double escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Truncated Path -> Alias: #### A masked pattern was here #### Needs Tagging: false Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int), VALUE._col5 (type: double) outputColumnNames: _col1, _col2, _col5, _col7 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: ptf_0 output shape: _col1: string, _col2: string, _col5: int, _col7: double type: WINDOWING Windowing table definition input alias: ptf_1 name: windowingtablefunction order by: _col1 partition by: _col2 raw input shape: window functions: window function definition alias: rank_window_0 arguments: _col1 name: rank window function: GenericUDAFRankEvaluator window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true window function definition alias: dense_rank_window_1 arguments: _col1 name: dense_rank window function: GenericUDAFDenseRankEvaluator window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true window function definition alias: sum_window_2 arguments: _col7 name: sum window function: GenericUDAFSumDouble window frame: PRECEDING(MAX)~ Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col2 (type: string), _col1 (type: string), _col5 (type: int), rank_window_0 (type: int), dense_rank_window_1 (type: int), sum_window_2 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE #### 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,_col2,_col3,_col4,_col5 columns.types string:string:int:int:int:double escape.delim \ hive.serialization.extend.additional.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-0 Fetch Operator limit: -1 Processor Tree: ListSink PREHOOK: query: select p_mfgr, p_name, p_size, rank() over (partition by p_mfgr order by p_name) as r, dense_rank() over (partition by p_mfgr order by p_name) as dr, sum(p_retailprice) over (partition by p_mfgr order by p_name rows between unbounded preceding and current row) as s1 from noop(on part_orc partition by p_mfgr order by p_name ) PREHOOK: type: QUERY PREHOOK: Input: default@part_orc #### A masked pattern was here #### POSTHOOK: query: select p_mfgr, p_name, p_size, rank() over (partition by p_mfgr order by p_name) as r, dense_rank() over (partition by p_mfgr order by p_name) as dr, sum(p_retailprice) over (partition by p_mfgr order by p_name rows between unbounded preceding and current row) as s1 from noop(on part_orc partition by p_mfgr order by p_name ) POSTHOOK: type: QUERY POSTHOOK: Input: default@part_orc #### A masked pattern was here #### Manufacturer#1 almond antique burnished rose metallic 2 1 1 1173.15 Manufacturer#1 almond antique burnished rose metallic 2 1 1 2346.3 Manufacturer#1 almond antique chartreuse lavender yellow 34 3 2 4100.06 Manufacturer#1 almond antique salmon chartreuse burlywood 6 4 3 5702.650000000001 Manufacturer#1 almond aquamarine burnished black steel 28 5 4 7117.070000000001 Manufacturer#1 almond aquamarine pink moccasin thistle 42 6 5 8749.730000000001 Manufacturer#2 almond antique violet chocolate turquoise 14 1 1 1690.68 Manufacturer#2 almond antique violet turquoise frosted 40 2 2 3491.38 Manufacturer#2 almond aquamarine midnight light salmon 2 3 3 5523.360000000001 Manufacturer#2 almond aquamarine rose maroon antique 25 4 4 7222.02 Manufacturer#2 almond aquamarine sandy cyan gainsboro 18 5 5 8923.62 Manufacturer#3 almond antique chartreuse khaki white 17 1 1 1671.68 Manufacturer#3 almond antique forest lavender goldenrod 14 2 2 2861.95 Manufacturer#3 almond antique metallic orange dim 19 3 3 4272.34 Manufacturer#3 almond antique misty red olive 1 4 4 6195.32 Manufacturer#3 almond antique olive coral navajo 45 5 5 7532.61 Manufacturer#4 almond antique gainsboro frosted violet 10 1 1 1620.67 Manufacturer#4 almond antique violet mint lemon 39 2 2 2996.09 Manufacturer#4 almond aquamarine floral ivory bisque 27 3 3 4202.35 Manufacturer#4 almond aquamarine yellow dodger mint 7 4 4 6047.27 Manufacturer#4 almond azure aquamarine papaya violet 12 5 5 7337.620000000001 Manufacturer#5 almond antique blue firebrick mint 31 1 1 1789.69 Manufacturer#5 almond antique medium spring khaki 6 2 2 3401.3500000000004 Manufacturer#5 almond antique sky peru orange 2 3 3 5190.08 Manufacturer#5 almond aquamarine dodger light gainsboro 46 4 4 6208.18 Manufacturer#5 almond azure blanched chiffon midnight 23 5 5 7672.66 PREHOOK: query: -- 2. testJoinWithNoop explain extended select p_mfgr, p_name, p_size, p_size - lag(p_size,1,p_size) over (partition by p_mfgr order by p_name) as deltaSz from noop (on (select p1.* from part_orc p1 join part_orc p2 on p1.p_partkey = p2.p_partkey) j distribute by j.p_mfgr sort by j.p_name) PREHOOK: type: QUERY POSTHOOK: query: -- 2. testJoinWithNoop explain extended select p_mfgr, p_name, p_size, p_size - lag(p_size,1,p_size) over (partition by p_mfgr order by p_name) as deltaSz from noop (on (select p1.* from part_orc p1 join part_orc p2 on p1.p_partkey = p2.p_partkey) j distribute by j.p_mfgr sort by j.p_name) POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: TOK_QUERY TOK_FROM TOK_PTBLFUNCTION noop TOK_SUBQUERY TOK_QUERY TOK_FROM TOK_JOIN TOK_TABREF TOK_TABNAME part_orc p1 TOK_TABREF TOK_TABNAME part_orc p2 = . TOK_TABLE_OR_COL p1 p_partkey . TOK_TABLE_OR_COL p2 p_partkey TOK_INSERT TOK_DESTINATION TOK_DIR TOK_TMP_FILE TOK_SELECT TOK_SELEXPR TOK_ALLCOLREF TOK_TABNAME p1 j TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY . TOK_TABLE_OR_COL j p_mfgr TOK_SORTBY TOK_TABSORTCOLNAMEASC . TOK_TABLE_OR_COL j p_name TOK_INSERT TOK_DESTINATION TOK_DIR TOK_TMP_FILE TOK_SELECT TOK_SELEXPR TOK_TABLE_OR_COL p_mfgr TOK_SELEXPR TOK_TABLE_OR_COL p_name TOK_SELEXPR TOK_TABLE_OR_COL p_size TOK_SELEXPR - TOK_TABLE_OR_COL p_size TOK_FUNCTION lag TOK_TABLE_OR_COL p_size 1 TOK_TABLE_OR_COL p_size TOK_WINDOWSPEC TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name deltaSz STAGE DEPENDENCIES: Stage-1 is a root stage Stage-2 depends on stages: Stage-1 Stage-3 depends on stages: Stage-2 Stage-0 depends on stages: Stage-3 STAGE PLANS: Stage: Stage-1 Map Reduce Map Operator Tree: TableScan alias: p1 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: p_partkey is not null (type: boolean) Statistics: Num rows: 13 Data size: 8021 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: p_partkey (type: int) sort order: + Map-reduce partition columns: p_partkey (type: int) Statistics: Num rows: 13 Data size: 8021 Basic stats: COMPLETE Column stats: NONE tag: 0 value expressions: p_name (type: string), p_mfgr (type: string), p_size (type: int) auto parallelism: false TableScan alias: p2 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: p_partkey is not null (type: boolean) Statistics: Num rows: 13 Data size: 8021 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: p_partkey (type: int) sort order: + Map-reduce partition columns: p_partkey (type: int) Statistics: Num rows: 13 Data size: 8021 Basic stats: COMPLETE Column stats: NONE tag: 1 auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: part_orc input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat properties: COLUMN_STATS_ACCURATE true bucket_count -1 columns p_partkey,p_name,p_mfgr,p_brand,p_type,p_size,p_container,p_retailprice,p_comment columns.comments columns.types int:string:string:string:string:int:string:double:string #### A masked pattern was here #### name default.part_orc numFiles 1 numRows 26 rawDataSize 16042 serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde totalSize 2655 #### 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: COLUMN_STATS_ACCURATE true bucket_count -1 columns p_partkey,p_name,p_mfgr,p_brand,p_type,p_size,p_container,p_retailprice,p_comment columns.comments columns.types int:string:string:string:string:int:string:double:string #### A masked pattern was here #### name default.part_orc numFiles 1 numRows 26 rawDataSize 16042 serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde totalSize 2655 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.part_orc name: default.part_orc Truncated Path -> Alias: /part_orc [j:p1, j:p2] Execution mode: vectorized Needs Tagging: true Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: 0 p_partkey (type: int) 1 p_partkey (type: int) outputColumnNames: _col1, _col2, _col5 Statistics: Num rows: 14 Data size: 8823 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5 columns.types string,string,int escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe TotalFiles: 1 GatherStats: false MultiFileSpray: false Stage: Stage-2 Map Reduce Map Operator Tree: TableScan GatherStats: false Reduce Output Operator key expressions: _col2 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col2 (type: string) Statistics: Num rows: 14 Data size: 8823 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col5 (type: int) auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: -mr-10002 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5 columns.types string,string,int escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5 columns.types string,string,int escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Truncated Path -> Alias: #### A masked pattern was here #### Needs Tagging: false Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int) outputColumnNames: _col1, _col2, _col5 Statistics: Num rows: 14 Data size: 8823 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: j output shape: _col1: string, _col2: string, _col5: int type: SUBQUERY Partition table definition input alias: ptf_1 name: noop order by: _col1 output shape: _col1: string, _col2: string, _col5: int partition by: _col2 raw input shape: Statistics: Num rows: 14 Data size: 8823 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5 columns.types string,string,int escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe TotalFiles: 1 GatherStats: false MultiFileSpray: false Stage: Stage-3 Map Reduce Map Operator Tree: TableScan GatherStats: false Reduce Output Operator key expressions: _col2 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col2 (type: string) Statistics: Num rows: 14 Data size: 8823 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col5 (type: int) auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: -mr-10003 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5 columns.types string,string,int escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5 columns.types string,string,int escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Truncated Path -> Alias: #### A masked pattern was here #### Needs Tagging: false Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int) outputColumnNames: _col1, _col2, _col5 Statistics: Num rows: 14 Data size: 8823 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: ptf_0 output shape: _col1: string, _col2: string, _col5: int type: WINDOWING Windowing table definition input alias: ptf_1 name: windowingtablefunction order by: _col1 partition by: _col2 raw input shape: window functions: window function definition alias: lag_window_0 arguments: _col5, 1, _col5 name: lag window function: GenericUDAFLagEvaluator window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true Statistics: Num rows: 14 Data size: 8823 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col2 (type: string), _col1 (type: string), _col5 (type: int), (_col5 - lag_window_0) (type: int) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 14 Data size: 8823 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 Statistics: Num rows: 14 Data size: 8823 Basic stats: COMPLETE Column stats: NONE #### 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,_col2,_col3 columns.types string:string:int:int escape.delim \ hive.serialization.extend.additional.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-0 Fetch Operator limit: -1 Processor Tree: ListSink PREHOOK: query: select p_mfgr, p_name, p_size, p_size - lag(p_size,1,p_size) over (partition by p_mfgr order by p_name) as deltaSz from noop (on (select p1.* from part_orc p1 join part_orc p2 on p1.p_partkey = p2.p_partkey) j distribute by j.p_mfgr sort by j.p_name) PREHOOK: type: QUERY PREHOOK: Input: default@part_orc #### A masked pattern was here #### POSTHOOK: query: select p_mfgr, p_name, p_size, p_size - lag(p_size,1,p_size) over (partition by p_mfgr order by p_name) as deltaSz from noop (on (select p1.* from part_orc p1 join part_orc p2 on p1.p_partkey = p2.p_partkey) j distribute by j.p_mfgr sort by j.p_name) POSTHOOK: type: QUERY POSTHOOK: Input: default@part_orc #### A masked pattern was here #### Manufacturer#1 almond antique burnished rose metallic 2 0 Manufacturer#1 almond antique burnished rose metallic 2 0 Manufacturer#1 almond antique burnished rose metallic 2 0 Manufacturer#1 almond antique burnished rose metallic 2 0 Manufacturer#1 almond antique chartreuse lavender yellow 34 32 Manufacturer#1 almond antique salmon chartreuse burlywood 6 -28 Manufacturer#1 almond aquamarine burnished black steel 28 22 Manufacturer#1 almond aquamarine pink moccasin thistle 42 14 Manufacturer#2 almond antique violet chocolate turquoise 14 0 Manufacturer#2 almond antique violet turquoise frosted 40 26 Manufacturer#2 almond aquamarine midnight light salmon 2 -38 Manufacturer#2 almond aquamarine rose maroon antique 25 23 Manufacturer#2 almond aquamarine sandy cyan gainsboro 18 -7 Manufacturer#3 almond antique chartreuse khaki white 17 0 Manufacturer#3 almond antique forest lavender goldenrod 14 -3 Manufacturer#3 almond antique metallic orange dim 19 5 Manufacturer#3 almond antique misty red olive 1 -18 Manufacturer#3 almond antique olive coral navajo 45 44 Manufacturer#4 almond antique gainsboro frosted violet 10 0 Manufacturer#4 almond antique violet mint lemon 39 29 Manufacturer#4 almond aquamarine floral ivory bisque 27 -12 Manufacturer#4 almond aquamarine yellow dodger mint 7 -20 Manufacturer#4 almond azure aquamarine papaya violet 12 5 Manufacturer#5 almond antique blue firebrick mint 31 0 Manufacturer#5 almond antique medium spring khaki 6 -25 Manufacturer#5 almond antique sky peru orange 2 -4 Manufacturer#5 almond aquamarine dodger light gainsboro 46 44 Manufacturer#5 almond azure blanched chiffon midnight 23 -23 PREHOOK: query: -- 3. testOnlyPTF explain extended select p_mfgr, p_name, p_size from noop(on part_orc partition by p_mfgr order by p_name) PREHOOK: type: QUERY POSTHOOK: query: -- 3. testOnlyPTF explain extended select p_mfgr, p_name, p_size from noop(on part_orc partition by p_mfgr order by p_name) POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: TOK_QUERY TOK_FROM TOK_PTBLFUNCTION noop TOK_TABREF TOK_TABNAME part_orc TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name TOK_INSERT TOK_DESTINATION TOK_DIR TOK_TMP_FILE TOK_SELECT TOK_SELEXPR TOK_TABLE_OR_COL p_mfgr TOK_SELEXPR TOK_TABLE_OR_COL p_name TOK_SELEXPR TOK_TABLE_OR_COL p_size STAGE DEPENDENCIES: Stage-1 is a root stage Stage-0 depends on stages: Stage-1 STAGE PLANS: Stage: Stage-1 Map Reduce Map Operator Tree: TableScan alias: part_orc Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE GatherStats: false Reduce Output Operator key expressions: p_mfgr (type: string), p_name (type: string) sort order: ++ Map-reduce partition columns: p_mfgr (type: string) Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: p_size (type: int) auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: part_orc input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat properties: COLUMN_STATS_ACCURATE true bucket_count -1 columns p_partkey,p_name,p_mfgr,p_brand,p_type,p_size,p_container,p_retailprice,p_comment columns.comments columns.types int:string:string:string:string:int:string:double:string #### A masked pattern was here #### name default.part_orc numFiles 1 numRows 26 rawDataSize 16042 serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde totalSize 2655 #### 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: COLUMN_STATS_ACCURATE true bucket_count -1 columns p_partkey,p_name,p_mfgr,p_brand,p_type,p_size,p_container,p_retailprice,p_comment columns.comments columns.types int:string:string:string:string:int:string:double:string #### A masked pattern was here #### name default.part_orc numFiles 1 numRows 26 rawDataSize 16042 serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde totalSize 2655 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.part_orc name: default.part_orc Truncated Path -> Alias: /part_orc [part_orc] Execution mode: vectorized Needs Tagging: false Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int) outputColumnNames: _col1, _col2, _col5 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: part_orc output shape: _col1: string, _col2: string, _col5: int type: TABLE Partition table definition input alias: ptf_1 name: noop order by: _col1 output shape: _col1: string, _col2: string, _col5: int partition by: _col2 raw input shape: Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col2 (type: string), _col1 (type: string), _col5 (type: int) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE #### 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,_col2 columns.types string:string:int escape.delim \ hive.serialization.extend.additional.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-0 Fetch Operator limit: -1 Processor Tree: ListSink PREHOOK: query: select p_mfgr, p_name, p_size from noop(on part_orc partition by p_mfgr order by p_name) PREHOOK: type: QUERY PREHOOK: Input: default@part_orc #### A masked pattern was here #### POSTHOOK: query: select p_mfgr, p_name, p_size from noop(on part_orc partition by p_mfgr order by p_name) POSTHOOK: type: QUERY POSTHOOK: Input: default@part_orc #### A masked pattern was here #### Manufacturer#1 almond antique burnished rose metallic 2 Manufacturer#1 almond antique burnished rose metallic 2 Manufacturer#1 almond antique chartreuse lavender yellow 34 Manufacturer#1 almond antique salmon chartreuse burlywood 6 Manufacturer#1 almond aquamarine burnished black steel 28 Manufacturer#1 almond aquamarine pink moccasin thistle 42 Manufacturer#2 almond antique violet chocolate turquoise 14 Manufacturer#2 almond antique violet turquoise frosted 40 Manufacturer#2 almond aquamarine midnight light salmon 2 Manufacturer#2 almond aquamarine rose maroon antique 25 Manufacturer#2 almond aquamarine sandy cyan gainsboro 18 Manufacturer#3 almond antique chartreuse khaki white 17 Manufacturer#3 almond antique forest lavender goldenrod 14 Manufacturer#3 almond antique metallic orange dim 19 Manufacturer#3 almond antique misty red olive 1 Manufacturer#3 almond antique olive coral navajo 45 Manufacturer#4 almond antique gainsboro frosted violet 10 Manufacturer#4 almond antique violet mint lemon 39 Manufacturer#4 almond aquamarine floral ivory bisque 27 Manufacturer#4 almond aquamarine yellow dodger mint 7 Manufacturer#4 almond azure aquamarine papaya violet 12 Manufacturer#5 almond antique blue firebrick mint 31 Manufacturer#5 almond antique medium spring khaki 6 Manufacturer#5 almond antique sky peru orange 2 Manufacturer#5 almond aquamarine dodger light gainsboro 46 Manufacturer#5 almond azure blanched chiffon midnight 23 PREHOOK: query: -- 4. testPTFAlias explain extended select p_mfgr, p_name, p_size, rank() over (partition by p_mfgr order by p_name) as r, dense_rank() over (partition by p_mfgr order by p_name) as dr, sum(p_retailprice) over (partition by p_mfgr order by p_name rows between unbounded preceding and current row) as s1 from noop(on part_orc partition by p_mfgr order by p_name ) abc PREHOOK: type: QUERY POSTHOOK: query: -- 4. testPTFAlias explain extended select p_mfgr, p_name, p_size, rank() over (partition by p_mfgr order by p_name) as r, dense_rank() over (partition by p_mfgr order by p_name) as dr, sum(p_retailprice) over (partition by p_mfgr order by p_name rows between unbounded preceding and current row) as s1 from noop(on part_orc partition by p_mfgr order by p_name ) abc POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: TOK_QUERY TOK_FROM TOK_PTBLFUNCTION noop abc TOK_TABREF TOK_TABNAME part_orc TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name TOK_INSERT TOK_DESTINATION TOK_DIR TOK_TMP_FILE TOK_SELECT TOK_SELEXPR TOK_TABLE_OR_COL p_mfgr TOK_SELEXPR TOK_TABLE_OR_COL p_name TOK_SELEXPR TOK_TABLE_OR_COL p_size TOK_SELEXPR TOK_FUNCTION rank TOK_WINDOWSPEC TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name r TOK_SELEXPR TOK_FUNCTION dense_rank TOK_WINDOWSPEC TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name dr TOK_SELEXPR TOK_FUNCTION sum TOK_TABLE_OR_COL p_retailprice TOK_WINDOWSPEC TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name TOK_WINDOWRANGE preceding unbounded current s1 STAGE DEPENDENCIES: Stage-1 is a root stage Stage-2 depends on stages: Stage-1 Stage-0 depends on stages: Stage-2 STAGE PLANS: Stage: Stage-1 Map Reduce Map Operator Tree: TableScan alias: part_orc Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE GatherStats: false Reduce Output Operator key expressions: p_mfgr (type: string), p_name (type: string) sort order: ++ Map-reduce partition columns: p_mfgr (type: string) Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: p_size (type: int), p_retailprice (type: double) auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: part_orc input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat properties: COLUMN_STATS_ACCURATE true bucket_count -1 columns p_partkey,p_name,p_mfgr,p_brand,p_type,p_size,p_container,p_retailprice,p_comment columns.comments columns.types int:string:string:string:string:int:string:double:string #### A masked pattern was here #### name default.part_orc numFiles 1 numRows 26 rawDataSize 16042 serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde totalSize 2655 #### 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: COLUMN_STATS_ACCURATE true bucket_count -1 columns p_partkey,p_name,p_mfgr,p_brand,p_type,p_size,p_container,p_retailprice,p_comment columns.comments columns.types int:string:string:string:string:int:string:double:string #### A masked pattern was here #### name default.part_orc numFiles 1 numRows 26 rawDataSize 16042 serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde totalSize 2655 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.part_orc name: default.part_orc Truncated Path -> Alias: /part_orc [part_orc] Execution mode: vectorized Needs Tagging: false Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int), VALUE._col5 (type: double) outputColumnNames: _col1, _col2, _col5, _col7 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: part_orc output shape: _col1: string, _col2: string, _col5: int, _col7: double type: TABLE Partition table definition input alias: abc name: noop order by: _col1 output shape: _col1: string, _col2: string, _col5: int, _col7: double partition by: _col2 raw input shape: Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5,_col7 columns.types string,string,int,double escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe TotalFiles: 1 GatherStats: false MultiFileSpray: false Stage: Stage-2 Map Reduce Map Operator Tree: TableScan GatherStats: false Reduce Output Operator key expressions: _col2 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col2 (type: string) Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col5 (type: int), _col7 (type: double) auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: -mr-10002 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5,_col7 columns.types string,string,int,double escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5,_col7 columns.types string,string,int,double escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Truncated Path -> Alias: #### A masked pattern was here #### Needs Tagging: false Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int), VALUE._col5 (type: double) outputColumnNames: _col1, _col2, _col5, _col7 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: ptf_0 output shape: _col1: string, _col2: string, _col5: int, _col7: double type: WINDOWING Windowing table definition input alias: ptf_1 name: windowingtablefunction order by: _col1 partition by: _col2 raw input shape: window functions: window function definition alias: rank_window_0 arguments: _col1 name: rank window function: GenericUDAFRankEvaluator window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true window function definition alias: dense_rank_window_1 arguments: _col1 name: dense_rank window function: GenericUDAFDenseRankEvaluator window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true window function definition alias: sum_window_2 arguments: _col7 name: sum window function: GenericUDAFSumDouble window frame: PRECEDING(MAX)~ Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col2 (type: string), _col1 (type: string), _col5 (type: int), rank_window_0 (type: int), dense_rank_window_1 (type: int), sum_window_2 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE #### 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,_col2,_col3,_col4,_col5 columns.types string:string:int:int:int:double escape.delim \ hive.serialization.extend.additional.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-0 Fetch Operator limit: -1 Processor Tree: ListSink PREHOOK: query: select p_mfgr, p_name, p_size, rank() over (partition by p_mfgr order by p_name) as r, dense_rank() over (partition by p_mfgr order by p_name) as dr, sum(p_retailprice) over (partition by p_mfgr order by p_name rows between unbounded preceding and current row) as s1 from noop(on part_orc partition by p_mfgr order by p_name ) abc PREHOOK: type: QUERY PREHOOK: Input: default@part_orc #### A masked pattern was here #### POSTHOOK: query: select p_mfgr, p_name, p_size, rank() over (partition by p_mfgr order by p_name) as r, dense_rank() over (partition by p_mfgr order by p_name) as dr, sum(p_retailprice) over (partition by p_mfgr order by p_name rows between unbounded preceding and current row) as s1 from noop(on part_orc partition by p_mfgr order by p_name ) abc POSTHOOK: type: QUERY POSTHOOK: Input: default@part_orc #### A masked pattern was here #### Manufacturer#1 almond antique burnished rose metallic 2 1 1 1173.15 Manufacturer#1 almond antique burnished rose metallic 2 1 1 2346.3 Manufacturer#1 almond antique chartreuse lavender yellow 34 3 2 4100.06 Manufacturer#1 almond antique salmon chartreuse burlywood 6 4 3 5702.650000000001 Manufacturer#1 almond aquamarine burnished black steel 28 5 4 7117.070000000001 Manufacturer#1 almond aquamarine pink moccasin thistle 42 6 5 8749.730000000001 Manufacturer#2 almond antique violet chocolate turquoise 14 1 1 1690.68 Manufacturer#2 almond antique violet turquoise frosted 40 2 2 3491.38 Manufacturer#2 almond aquamarine midnight light salmon 2 3 3 5523.360000000001 Manufacturer#2 almond aquamarine rose maroon antique 25 4 4 7222.02 Manufacturer#2 almond aquamarine sandy cyan gainsboro 18 5 5 8923.62 Manufacturer#3 almond antique chartreuse khaki white 17 1 1 1671.68 Manufacturer#3 almond antique forest lavender goldenrod 14 2 2 2861.95 Manufacturer#3 almond antique metallic orange dim 19 3 3 4272.34 Manufacturer#3 almond antique misty red olive 1 4 4 6195.32 Manufacturer#3 almond antique olive coral navajo 45 5 5 7532.61 Manufacturer#4 almond antique gainsboro frosted violet 10 1 1 1620.67 Manufacturer#4 almond antique violet mint lemon 39 2 2 2996.09 Manufacturer#4 almond aquamarine floral ivory bisque 27 3 3 4202.35 Manufacturer#4 almond aquamarine yellow dodger mint 7 4 4 6047.27 Manufacturer#4 almond azure aquamarine papaya violet 12 5 5 7337.620000000001 Manufacturer#5 almond antique blue firebrick mint 31 1 1 1789.69 Manufacturer#5 almond antique medium spring khaki 6 2 2 3401.3500000000004 Manufacturer#5 almond antique sky peru orange 2 3 3 5190.08 Manufacturer#5 almond aquamarine dodger light gainsboro 46 4 4 6208.18 Manufacturer#5 almond azure blanched chiffon midnight 23 5 5 7672.66 PREHOOK: query: -- 5. testPTFAndWhereWithWindowing explain extended select p_mfgr, p_name, p_size, rank() over (partition by p_mfgr order by p_name) as r, dense_rank() over (partition by p_mfgr order by p_name) as dr, p_size, p_size - lag(p_size,1,p_size) over (partition by p_mfgr order by p_name) as deltaSz from noop(on part_orc partition by p_mfgr order by p_name ) PREHOOK: type: QUERY POSTHOOK: query: -- 5. testPTFAndWhereWithWindowing explain extended select p_mfgr, p_name, p_size, rank() over (partition by p_mfgr order by p_name) as r, dense_rank() over (partition by p_mfgr order by p_name) as dr, p_size, p_size - lag(p_size,1,p_size) over (partition by p_mfgr order by p_name) as deltaSz from noop(on part_orc partition by p_mfgr order by p_name ) POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: TOK_QUERY TOK_FROM TOK_PTBLFUNCTION noop TOK_TABREF TOK_TABNAME part_orc TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name TOK_INSERT TOK_DESTINATION TOK_DIR TOK_TMP_FILE TOK_SELECT TOK_SELEXPR TOK_TABLE_OR_COL p_mfgr TOK_SELEXPR TOK_TABLE_OR_COL p_name TOK_SELEXPR TOK_TABLE_OR_COL p_size TOK_SELEXPR TOK_FUNCTION rank TOK_WINDOWSPEC TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name r TOK_SELEXPR TOK_FUNCTION dense_rank TOK_WINDOWSPEC TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name dr TOK_SELEXPR TOK_TABLE_OR_COL p_size TOK_SELEXPR - TOK_TABLE_OR_COL p_size TOK_FUNCTION lag TOK_TABLE_OR_COL p_size 1 TOK_TABLE_OR_COL p_size TOK_WINDOWSPEC TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name deltaSz STAGE DEPENDENCIES: Stage-1 is a root stage Stage-2 depends on stages: Stage-1 Stage-0 depends on stages: Stage-2 STAGE PLANS: Stage: Stage-1 Map Reduce Map Operator Tree: TableScan alias: part_orc Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE GatherStats: false Reduce Output Operator key expressions: p_mfgr (type: string), p_name (type: string) sort order: ++ Map-reduce partition columns: p_mfgr (type: string) Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: p_size (type: int) auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: part_orc input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat properties: COLUMN_STATS_ACCURATE true bucket_count -1 columns p_partkey,p_name,p_mfgr,p_brand,p_type,p_size,p_container,p_retailprice,p_comment columns.comments columns.types int:string:string:string:string:int:string:double:string #### A masked pattern was here #### name default.part_orc numFiles 1 numRows 26 rawDataSize 16042 serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde totalSize 2655 #### 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: COLUMN_STATS_ACCURATE true bucket_count -1 columns p_partkey,p_name,p_mfgr,p_brand,p_type,p_size,p_container,p_retailprice,p_comment columns.comments columns.types int:string:string:string:string:int:string:double:string #### A masked pattern was here #### name default.part_orc numFiles 1 numRows 26 rawDataSize 16042 serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde totalSize 2655 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.part_orc name: default.part_orc Truncated Path -> Alias: /part_orc [part_orc] Execution mode: vectorized Needs Tagging: false Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int) outputColumnNames: _col1, _col2, _col5 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: part_orc output shape: _col1: string, _col2: string, _col5: int type: TABLE Partition table definition input alias: ptf_1 name: noop order by: _col1 output shape: _col1: string, _col2: string, _col5: int partition by: _col2 raw input shape: Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5 columns.types string,string,int escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe TotalFiles: 1 GatherStats: false MultiFileSpray: false Stage: Stage-2 Map Reduce Map Operator Tree: TableScan GatherStats: false Reduce Output Operator key expressions: _col2 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col2 (type: string) Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col5 (type: int) auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: -mr-10002 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5 columns.types string,string,int escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5 columns.types string,string,int escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Truncated Path -> Alias: #### A masked pattern was here #### Needs Tagging: false Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int) outputColumnNames: _col1, _col2, _col5 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: ptf_0 output shape: _col1: string, _col2: string, _col5: int type: WINDOWING Windowing table definition input alias: ptf_1 name: windowingtablefunction order by: _col1 partition by: _col2 raw input shape: window functions: window function definition alias: rank_window_0 arguments: _col1 name: rank window function: GenericUDAFRankEvaluator window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true window function definition alias: dense_rank_window_1 arguments: _col1 name: dense_rank window function: GenericUDAFDenseRankEvaluator window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true window function definition alias: lag_window_2 arguments: _col5, 1, _col5 name: lag window function: GenericUDAFLagEvaluator window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col2 (type: string), _col1 (type: string), _col5 (type: int), rank_window_0 (type: int), dense_rank_window_1 (type: int), _col5 (type: int), (_col5 - lag_window_2) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE #### 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,_col2,_col3,_col4,_col5,_col6 columns.types string:string:int:int:int:int:int escape.delim \ hive.serialization.extend.additional.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-0 Fetch Operator limit: -1 Processor Tree: ListSink PREHOOK: query: select p_mfgr, p_name, p_size, rank() over (partition by p_mfgr order by p_name) as r, dense_rank() over (partition by p_mfgr order by p_name) as dr, p_size, p_size - lag(p_size,1,p_size) over (partition by p_mfgr order by p_name) as deltaSz from noop(on part_orc partition by p_mfgr order by p_name ) PREHOOK: type: QUERY PREHOOK: Input: default@part_orc #### A masked pattern was here #### POSTHOOK: query: select p_mfgr, p_name, p_size, rank() over (partition by p_mfgr order by p_name) as r, dense_rank() over (partition by p_mfgr order by p_name) as dr, p_size, p_size - lag(p_size,1,p_size) over (partition by p_mfgr order by p_name) as deltaSz from noop(on part_orc partition by p_mfgr order by p_name ) POSTHOOK: type: QUERY POSTHOOK: Input: default@part_orc #### A masked pattern was here #### Manufacturer#1 almond antique burnished rose metallic 2 1 1 2 0 Manufacturer#1 almond antique burnished rose metallic 2 1 1 2 0 Manufacturer#1 almond antique chartreuse lavender yellow 34 3 2 34 32 Manufacturer#1 almond antique salmon chartreuse burlywood 6 4 3 6 -28 Manufacturer#1 almond aquamarine burnished black steel 28 5 4 28 22 Manufacturer#1 almond aquamarine pink moccasin thistle 42 6 5 42 14 Manufacturer#2 almond antique violet chocolate turquoise 14 1 1 14 0 Manufacturer#2 almond antique violet turquoise frosted 40 2 2 40 26 Manufacturer#2 almond aquamarine midnight light salmon 2 3 3 2 -38 Manufacturer#2 almond aquamarine rose maroon antique 25 4 4 25 23 Manufacturer#2 almond aquamarine sandy cyan gainsboro 18 5 5 18 -7 Manufacturer#3 almond antique chartreuse khaki white 17 1 1 17 0 Manufacturer#3 almond antique forest lavender goldenrod 14 2 2 14 -3 Manufacturer#3 almond antique metallic orange dim 19 3 3 19 5 Manufacturer#3 almond antique misty red olive 1 4 4 1 -18 Manufacturer#3 almond antique olive coral navajo 45 5 5 45 44 Manufacturer#4 almond antique gainsboro frosted violet 10 1 1 10 0 Manufacturer#4 almond antique violet mint lemon 39 2 2 39 29 Manufacturer#4 almond aquamarine floral ivory bisque 27 3 3 27 -12 Manufacturer#4 almond aquamarine yellow dodger mint 7 4 4 7 -20 Manufacturer#4 almond azure aquamarine papaya violet 12 5 5 12 5 Manufacturer#5 almond antique blue firebrick mint 31 1 1 31 0 Manufacturer#5 almond antique medium spring khaki 6 2 2 6 -25 Manufacturer#5 almond antique sky peru orange 2 3 3 2 -4 Manufacturer#5 almond aquamarine dodger light gainsboro 46 4 4 46 44 Manufacturer#5 almond azure blanched chiffon midnight 23 5 5 23 -23 PREHOOK: query: -- 6. testSWQAndPTFAndGBy explain extended select p_mfgr, p_name, p_size, rank() over (partition by p_mfgr order by p_name) as r, dense_rank() over (partition by p_mfgr order by p_name) as dr, p_size, p_size - lag(p_size,1,p_size) over (partition by p_mfgr order by p_name) as deltaSz from noop(on part_orc partition by p_mfgr order by p_name ) group by p_mfgr, p_name, p_size PREHOOK: type: QUERY POSTHOOK: query: -- 6. testSWQAndPTFAndGBy explain extended select p_mfgr, p_name, p_size, rank() over (partition by p_mfgr order by p_name) as r, dense_rank() over (partition by p_mfgr order by p_name) as dr, p_size, p_size - lag(p_size,1,p_size) over (partition by p_mfgr order by p_name) as deltaSz from noop(on part_orc partition by p_mfgr order by p_name ) group by p_mfgr, p_name, p_size POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: TOK_QUERY TOK_FROM TOK_PTBLFUNCTION noop TOK_TABREF TOK_TABNAME part_orc TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name TOK_INSERT TOK_DESTINATION TOK_DIR TOK_TMP_FILE TOK_SELECT TOK_SELEXPR TOK_TABLE_OR_COL p_mfgr TOK_SELEXPR TOK_TABLE_OR_COL p_name TOK_SELEXPR TOK_TABLE_OR_COL p_size TOK_SELEXPR TOK_FUNCTION rank TOK_WINDOWSPEC TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name r TOK_SELEXPR TOK_FUNCTION dense_rank TOK_WINDOWSPEC TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name dr TOK_SELEXPR TOK_TABLE_OR_COL p_size TOK_SELEXPR - TOK_TABLE_OR_COL p_size TOK_FUNCTION lag TOK_TABLE_OR_COL p_size 1 TOK_TABLE_OR_COL p_size TOK_WINDOWSPEC TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name deltaSz TOK_GROUPBY TOK_TABLE_OR_COL p_mfgr TOK_TABLE_OR_COL p_name TOK_TABLE_OR_COL p_size STAGE DEPENDENCIES: Stage-1 is a root stage Stage-2 depends on stages: Stage-1 Stage-3 depends on stages: Stage-2 Stage-0 depends on stages: Stage-3 STAGE PLANS: Stage: Stage-1 Map Reduce Map Operator Tree: TableScan alias: part_orc Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE GatherStats: false Reduce Output Operator key expressions: p_mfgr (type: string), p_name (type: string) sort order: ++ Map-reduce partition columns: p_mfgr (type: string) Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: p_size (type: int) auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: part_orc input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat properties: COLUMN_STATS_ACCURATE true bucket_count -1 columns p_partkey,p_name,p_mfgr,p_brand,p_type,p_size,p_container,p_retailprice,p_comment columns.comments columns.types int:string:string:string:string:int:string:double:string #### A masked pattern was here #### name default.part_orc numFiles 1 numRows 26 rawDataSize 16042 serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde totalSize 2655 #### 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: COLUMN_STATS_ACCURATE true bucket_count -1 columns p_partkey,p_name,p_mfgr,p_brand,p_type,p_size,p_container,p_retailprice,p_comment columns.comments columns.types int:string:string:string:string:int:string:double:string #### A masked pattern was here #### name default.part_orc numFiles 1 numRows 26 rawDataSize 16042 serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde totalSize 2655 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.part_orc name: default.part_orc Truncated Path -> Alias: /part_orc [part_orc] Execution mode: vectorized Needs Tagging: false Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int) outputColumnNames: _col1, _col2, _col5 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: part_orc output shape: _col1: string, _col2: string, _col5: int type: TABLE Partition table definition input alias: ptf_1 name: noop order by: _col1 output shape: _col1: string, _col2: string, _col5: int partition by: _col2 raw input shape: Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col2 (type: string), _col1 (type: string), _col5 (type: int) outputColumnNames: _col2, _col1, _col5 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: _col2 (type: string), _col1 (type: string), _col5 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col0,_col1,_col2 columns.types string,string,int escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe TotalFiles: 1 GatherStats: false MultiFileSpray: false Stage: Stage-2 Map Reduce Map Operator Tree: TableScan GatherStats: false Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: int) Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE tag: -1 auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: -mr-10002 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col0,_col1,_col2 columns.types string,string,int escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col0,_col1,_col2 columns.types string,string,int escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Truncated Path -> Alias: #### A masked pattern was here #### Needs Tagging: false Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 13 Data size: 8021 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col0,_col1,_col2 columns.types string,string,int escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe TotalFiles: 1 GatherStats: false MultiFileSpray: false Stage: Stage-3 Map Reduce Map Operator Tree: TableScan GatherStats: false Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 13 Data size: 8021 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col2 (type: int) auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: -mr-10003 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col0,_col1,_col2 columns.types string,string,int escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col0,_col1,_col2 columns.types string,string,int escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Truncated Path -> Alias: #### A masked pattern was here #### Needs Tagging: false Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), VALUE._col0 (type: int) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 13 Data size: 8021 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: ptf_0 output shape: _col0: string, _col1: string, _col2: int type: WINDOWING Windowing table definition input alias: ptf_1 name: windowingtablefunction order by: _col1 partition by: _col0 raw input shape: window functions: window function definition alias: rank_window_0 arguments: _col1 name: rank window function: GenericUDAFRankEvaluator window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true window function definition alias: dense_rank_window_1 arguments: _col1 name: dense_rank window function: GenericUDAFDenseRankEvaluator window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true window function definition alias: lag_window_2 arguments: _col2, 1, _col2 name: lag window function: GenericUDAFLagEvaluator window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true Statistics: Num rows: 13 Data size: 8021 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int), rank_window_0 (type: int), dense_rank_window_1 (type: int), _col2 (type: int), (_col2 - lag_window_2) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 Statistics: Num rows: 13 Data size: 8021 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 Statistics: Num rows: 13 Data size: 8021 Basic stats: COMPLETE Column stats: NONE #### 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,_col2,_col3,_col4,_col5,_col6 columns.types string:string:int:int:int:int:int escape.delim \ hive.serialization.extend.additional.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-0 Fetch Operator limit: -1 Processor Tree: ListSink PREHOOK: query: select p_mfgr, p_name, p_size, rank() over (partition by p_mfgr order by p_name) as r, dense_rank() over (partition by p_mfgr order by p_name) as dr, p_size, p_size - lag(p_size,1,p_size) over (partition by p_mfgr order by p_name) as deltaSz from noop(on part_orc partition by p_mfgr order by p_name ) group by p_mfgr, p_name, p_size PREHOOK: type: QUERY PREHOOK: Input: default@part_orc #### A masked pattern was here #### POSTHOOK: query: select p_mfgr, p_name, p_size, rank() over (partition by p_mfgr order by p_name) as r, dense_rank() over (partition by p_mfgr order by p_name) as dr, p_size, p_size - lag(p_size,1,p_size) over (partition by p_mfgr order by p_name) as deltaSz from noop(on part_orc partition by p_mfgr order by p_name ) group by p_mfgr, p_name, p_size POSTHOOK: type: QUERY POSTHOOK: Input: default@part_orc #### A masked pattern was here #### Manufacturer#1 almond antique burnished rose metallic 2 1 1 2 0 Manufacturer#1 almond antique chartreuse lavender yellow 34 2 2 34 32 Manufacturer#1 almond antique salmon chartreuse burlywood 6 3 3 6 -28 Manufacturer#1 almond aquamarine burnished black steel 28 4 4 28 22 Manufacturer#1 almond aquamarine pink moccasin thistle 42 5 5 42 14 Manufacturer#2 almond antique violet chocolate turquoise 14 1 1 14 0 Manufacturer#2 almond antique violet turquoise frosted 40 2 2 40 26 Manufacturer#2 almond aquamarine midnight light salmon 2 3 3 2 -38 Manufacturer#2 almond aquamarine rose maroon antique 25 4 4 25 23 Manufacturer#2 almond aquamarine sandy cyan gainsboro 18 5 5 18 -7 Manufacturer#3 almond antique chartreuse khaki white 17 1 1 17 0 Manufacturer#3 almond antique forest lavender goldenrod 14 2 2 14 -3 Manufacturer#3 almond antique metallic orange dim 19 3 3 19 5 Manufacturer#3 almond antique misty red olive 1 4 4 1 -18 Manufacturer#3 almond antique olive coral navajo 45 5 5 45 44 Manufacturer#4 almond antique gainsboro frosted violet 10 1 1 10 0 Manufacturer#4 almond antique violet mint lemon 39 2 2 39 29 Manufacturer#4 almond aquamarine floral ivory bisque 27 3 3 27 -12 Manufacturer#4 almond aquamarine yellow dodger mint 7 4 4 7 -20 Manufacturer#4 almond azure aquamarine papaya violet 12 5 5 12 5 Manufacturer#5 almond antique blue firebrick mint 31 1 1 31 0 Manufacturer#5 almond antique medium spring khaki 6 2 2 6 -25 Manufacturer#5 almond antique sky peru orange 2 3 3 2 -4 Manufacturer#5 almond aquamarine dodger light gainsboro 46 4 4 46 44 Manufacturer#5 almond azure blanched chiffon midnight 23 5 5 23 -23 PREHOOK: query: -- 7. testJoin explain extended select abc.* from noop(on part_orc partition by p_mfgr order by p_name ) abc join part_orc p1 on abc.p_partkey = p1.p_partkey PREHOOK: type: QUERY POSTHOOK: query: -- 7. testJoin explain extended select abc.* from noop(on part_orc partition by p_mfgr order by p_name ) abc join part_orc p1 on abc.p_partkey = p1.p_partkey POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: TOK_QUERY TOK_FROM TOK_JOIN TOK_PTBLFUNCTION noop abc TOK_TABREF TOK_TABNAME part_orc TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name TOK_TABREF TOK_TABNAME part_orc p1 = . TOK_TABLE_OR_COL abc p_partkey . TOK_TABLE_OR_COL p1 p_partkey TOK_INSERT TOK_DESTINATION TOK_DIR TOK_TMP_FILE TOK_SELECT TOK_SELEXPR TOK_ALLCOLREF TOK_TABNAME abc STAGE DEPENDENCIES: Stage-1 is a root stage Stage-2 depends on stages: Stage-1 Stage-0 depends on stages: Stage-2 STAGE PLANS: Stage: Stage-1 Map Reduce Map Operator Tree: TableScan alias: part_orc Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE GatherStats: false Reduce Output Operator key expressions: p_mfgr (type: string), p_name (type: string) sort order: ++ Map-reduce partition columns: p_mfgr (type: string) Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: p_partkey (type: int), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: part_orc input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat properties: COLUMN_STATS_ACCURATE true bucket_count -1 columns p_partkey,p_name,p_mfgr,p_brand,p_type,p_size,p_container,p_retailprice,p_comment columns.comments columns.types int:string:string:string:string:int:string:double:string #### A masked pattern was here #### name default.part_orc numFiles 1 numRows 26 rawDataSize 16042 serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde totalSize 2655 #### 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: COLUMN_STATS_ACCURATE true bucket_count -1 columns p_partkey,p_name,p_mfgr,p_brand,p_type,p_size,p_container,p_retailprice,p_comment columns.comments columns.types int:string:string:string:string:int:string:double:string #### A masked pattern was here #### name default.part_orc numFiles 1 numRows 26 rawDataSize 16042 serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde totalSize 2655 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.part_orc name: default.part_orc Truncated Path -> Alias: /part_orc [part_orc] Execution mode: vectorized Needs Tagging: false Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string), VALUE._col3 (type: int), VALUE._col4 (type: string), VALUE._col5 (type: double), VALUE._col6 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: part_orc output shape: _col0: int, _col1: string, _col2: string, _col3: string, _col4: string, _col5: int, _col6: string, _col7: double, _col8: string type: TABLE Partition table definition input alias: abc name: noop order by: _col1 output shape: _col0: int, _col1: string, _col2: string, _col3: string, _col4: string, _col5: int, _col6: string, _col7: double, _col8: string partition by: _col2 raw input shape: Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE Filter Operator isSamplingPred: false predicate: _col0 is not null (type: boolean) Statistics: Num rows: 13 Data size: 8021 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col0,_col1,_col2,_col3,_col4,_col5,_col6,_col7,_col8 columns.types int,string,string,string,string,int,string,double,string escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe TotalFiles: 1 GatherStats: false MultiFileSpray: false Stage: Stage-2 Map Reduce Map Operator Tree: TableScan GatherStats: false Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 13 Data size: 8021 Basic stats: COMPLETE Column stats: NONE tag: 0 value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) auto parallelism: false TableScan alias: p1 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: p_partkey is not null (type: boolean) Statistics: Num rows: 13 Data size: 8021 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: p_partkey (type: int) sort order: + Map-reduce partition columns: p_partkey (type: int) Statistics: Num rows: 13 Data size: 8021 Basic stats: COMPLETE Column stats: NONE tag: 1 auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: -mr-10002 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col0,_col1,_col2,_col3,_col4,_col5,_col6,_col7,_col8 columns.types int,string,string,string,string,int,string,double,string escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col0,_col1,_col2,_col3,_col4,_col5,_col6,_col7,_col8 columns.types int,string,string,string,string,int,string,double,string escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe #### A masked pattern was here #### Partition base file name: part_orc input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat properties: COLUMN_STATS_ACCURATE true bucket_count -1 columns p_partkey,p_name,p_mfgr,p_brand,p_type,p_size,p_container,p_retailprice,p_comment columns.comments columns.types int:string:string:string:string:int:string:double:string #### A masked pattern was here #### name default.part_orc numFiles 1 numRows 26 rawDataSize 16042 serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde totalSize 2655 #### 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: COLUMN_STATS_ACCURATE true bucket_count -1 columns p_partkey,p_name,p_mfgr,p_brand,p_type,p_size,p_container,p_retailprice,p_comment columns.comments columns.types int:string:string:string:string:int:string:double:string #### A masked pattern was here #### name default.part_orc numFiles 1 numRows 26 rawDataSize 16042 serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde totalSize 2655 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.part_orc name: default.part_orc Truncated Path -> Alias: /part_orc [p1] #### A masked pattern was here #### Needs Tagging: true Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 p_partkey (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 14 Data size: 8823 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 Statistics: Num rows: 14 Data size: 8823 Basic stats: COMPLETE Column stats: NONE #### 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,_col2,_col3,_col4,_col5,_col6,_col7,_col8 columns.types int:string:string:string:string:int:string:double:string escape.delim \ hive.serialization.extend.additional.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-0 Fetch Operator limit: -1 Processor Tree: ListSink PREHOOK: query: select abc.* from noop(on part_orc partition by p_mfgr order by p_name ) abc join part_orc p1 on abc.p_partkey = p1.p_partkey PREHOOK: type: QUERY PREHOOK: Input: default@part_orc #### A masked pattern was here #### POSTHOOK: query: select abc.* from noop(on part_orc partition by p_mfgr order by p_name ) abc join part_orc p1 on abc.p_partkey = p1.p_partkey POSTHOOK: type: QUERY POSTHOOK: Input: default@part_orc #### A masked pattern was here #### 105685 almond antique violet chocolate turquoise Manufacturer#2 Brand#22 MEDIUM ANODIZED COPPER 14 MED CAN 1690.68 ly pending requ 110592 almond antique salmon chartreuse burlywood Manufacturer#1 Brand#15 PROMO BURNISHED NICKEL 6 JUMBO PKG 1602.59 to the furiously 112398 almond antique metallic orange dim Manufacturer#3 Brand#32 MEDIUM BURNISHED BRASS 19 JUMBO JAR 1410.39 ole car 121152 almond antique burnished rose metallic Manufacturer#1 Brand#14 PROMO PLATED TIN 2 JUMBO BOX 1173.15 e pinto beans h 121152 almond antique burnished rose metallic Manufacturer#1 Brand#14 PROMO PLATED TIN 2 JUMBO BOX 1173.15 e pinto beans h 121152 almond antique burnished rose metallic Manufacturer#1 Brand#14 PROMO PLATED TIN 2 JUMBO BOX 1173.15 e pinto beans h 121152 almond antique burnished rose metallic Manufacturer#1 Brand#14 PROMO PLATED TIN 2 JUMBO BOX 1173.15 e pinto beans h 132666 almond aquamarine rose maroon antique Manufacturer#2 Brand#24 SMALL POLISHED NICKEL 25 MED BOX 1698.66 even 144293 almond antique olive coral navajo Manufacturer#3 Brand#34 STANDARD POLISHED STEEL 45 JUMBO CAN 1337.29 ag furiously about 146985 almond aquamarine midnight light salmon Manufacturer#2 Brand#23 MEDIUM BURNISHED COPPER 2 SM CASE 2031.98 s cajole caref 15103 almond aquamarine dodger light gainsboro Manufacturer#5 Brand#53 ECONOMY BURNISHED STEEL 46 LG PACK 1018.1 packages hinder carefu 155733 almond antique sky peru orange Manufacturer#5 Brand#53 SMALL PLATED BRASS 2 WRAP DRUM 1788.73 furiously. bra 17273 almond antique forest lavender goldenrod Manufacturer#3 Brand#35 PROMO ANODIZED TIN 14 JUMBO CASE 1190.27 along the 17927 almond aquamarine yellow dodger mint Manufacturer#4 Brand#41 ECONOMY BRUSHED COPPER 7 SM PKG 1844.92 ites. eve 191709 almond antique violet turquoise frosted Manufacturer#2 Brand#22 ECONOMY POLISHED STEEL 40 MED BOX 1800.7 haggle 192697 almond antique blue firebrick mint Manufacturer#5 Brand#52 MEDIUM BURNISHED TIN 31 LG DRUM 1789.69 ickly ir 195606 almond aquamarine sandy cyan gainsboro Manufacturer#2 Brand#25 STANDARD PLATED TIN 18 SM PKG 1701.6 ic de 33357 almond azure aquamarine papaya violet Manufacturer#4 Brand#41 STANDARD ANODIZED TIN 12 WRAP CASE 1290.35 reful 40982 almond antique misty red olive Manufacturer#3 Brand#32 ECONOMY PLATED COPPER 1 LG PKG 1922.98 c foxes can s 42669 almond antique medium spring khaki Manufacturer#5 Brand#51 STANDARD BURNISHED TIN 6 MED CAN 1611.66 sits haggl 45261 almond aquamarine floral ivory bisque Manufacturer#4 Brand#42 SMALL PLATED STEEL 27 WRAP CASE 1206.26 careful 48427 almond antique violet mint lemon Manufacturer#4 Brand#42 PROMO POLISHED STEEL 39 SM CASE 1375.42 hely ironic i 49671 almond antique gainsboro frosted violet Manufacturer#4 Brand#41 SMALL BRUSHED BRASS 10 SM BOX 1620.67 ccounts run quick 65667 almond aquamarine pink moccasin thistle Manufacturer#1 Brand#12 LARGE BURNISHED STEEL 42 JUMBO CASE 1632.66 e across the expr 78486 almond azure blanched chiffon midnight Manufacturer#5 Brand#52 LARGE BRUSHED BRASS 23 MED BAG 1464.48 hely blith 85768 almond antique chartreuse lavender yellow Manufacturer#1 Brand#12 LARGE BRUSHED STEEL 34 SM BAG 1753.76 refull 86428 almond aquamarine burnished black steel Manufacturer#1 Brand#12 STANDARD ANODIZED STEEL 28 WRAP BAG 1414.42 arefully 90681 almond antique chartreuse khaki white Manufacturer#3 Brand#31 MEDIUM BURNISHED TIN 17 SM CASE 1671.68 are slyly after the sl PREHOOK: query: -- 8. testJoinRight explain extended select abc.* from part_orc p1 join noop(on part_orc partition by p_mfgr order by p_name ) abc on abc.p_partkey = p1.p_partkey PREHOOK: type: QUERY POSTHOOK: query: -- 8. testJoinRight explain extended select abc.* from part_orc p1 join noop(on part_orc partition by p_mfgr order by p_name ) abc on abc.p_partkey = p1.p_partkey POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: TOK_QUERY TOK_FROM TOK_JOIN TOK_TABREF TOK_TABNAME part_orc p1 TOK_PTBLFUNCTION noop abc TOK_TABREF TOK_TABNAME part_orc TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name = . TOK_TABLE_OR_COL abc p_partkey . TOK_TABLE_OR_COL p1 p_partkey TOK_INSERT TOK_DESTINATION TOK_DIR TOK_TMP_FILE TOK_SELECT TOK_SELEXPR TOK_ALLCOLREF TOK_TABNAME abc STAGE DEPENDENCIES: Stage-2 is a root stage Stage-1 depends on stages: Stage-2 Stage-0 depends on stages: Stage-1 STAGE PLANS: Stage: Stage-2 Map Reduce Map Operator Tree: TableScan alias: part_orc Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE GatherStats: false Reduce Output Operator key expressions: p_mfgr (type: string), p_name (type: string) sort order: ++ Map-reduce partition columns: p_mfgr (type: string) Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: p_partkey (type: int), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: part_orc input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat properties: COLUMN_STATS_ACCURATE true bucket_count -1 columns p_partkey,p_name,p_mfgr,p_brand,p_type,p_size,p_container,p_retailprice,p_comment columns.comments columns.types int:string:string:string:string:int:string:double:string #### A masked pattern was here #### name default.part_orc numFiles 1 numRows 26 rawDataSize 16042 serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde totalSize 2655 #### 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: COLUMN_STATS_ACCURATE true bucket_count -1 columns p_partkey,p_name,p_mfgr,p_brand,p_type,p_size,p_container,p_retailprice,p_comment columns.comments columns.types int:string:string:string:string:int:string:double:string #### A masked pattern was here #### name default.part_orc numFiles 1 numRows 26 rawDataSize 16042 serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde totalSize 2655 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.part_orc name: default.part_orc Truncated Path -> Alias: /part_orc [part_orc] Execution mode: vectorized Needs Tagging: false Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string), VALUE._col3 (type: int), VALUE._col4 (type: string), VALUE._col5 (type: double), VALUE._col6 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: part_orc output shape: _col0: int, _col1: string, _col2: string, _col3: string, _col4: string, _col5: int, _col6: string, _col7: double, _col8: string type: TABLE Partition table definition input alias: abc name: noop order by: _col1 output shape: _col0: int, _col1: string, _col2: string, _col3: string, _col4: string, _col5: int, _col6: string, _col7: double, _col8: string partition by: _col2 raw input shape: Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE Filter Operator isSamplingPred: false predicate: _col0 is not null (type: boolean) Statistics: Num rows: 13 Data size: 8021 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col0,_col1,_col2,_col3,_col4,_col5,_col6,_col7,_col8 columns.types int,string,string,string,string,int,string,double,string escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe TotalFiles: 1 GatherStats: false MultiFileSpray: false Stage: Stage-1 Map Reduce Map Operator Tree: TableScan alias: p1 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: p_partkey is not null (type: boolean) Statistics: Num rows: 13 Data size: 8021 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: p_partkey (type: int) sort order: + Map-reduce partition columns: p_partkey (type: int) Statistics: Num rows: 13 Data size: 8021 Basic stats: COMPLETE Column stats: NONE tag: 0 auto parallelism: false TableScan GatherStats: false Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 13 Data size: 8021 Basic stats: COMPLETE Column stats: NONE tag: 1 value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: -mr-10002 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col0,_col1,_col2,_col3,_col4,_col5,_col6,_col7,_col8 columns.types int,string,string,string,string,int,string,double,string escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col0,_col1,_col2,_col3,_col4,_col5,_col6,_col7,_col8 columns.types int,string,string,string,string,int,string,double,string escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe #### A masked pattern was here #### Partition base file name: part_orc input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat properties: COLUMN_STATS_ACCURATE true bucket_count -1 columns p_partkey,p_name,p_mfgr,p_brand,p_type,p_size,p_container,p_retailprice,p_comment columns.comments columns.types int:string:string:string:string:int:string:double:string #### A masked pattern was here #### name default.part_orc numFiles 1 numRows 26 rawDataSize 16042 serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde totalSize 2655 #### 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: COLUMN_STATS_ACCURATE true bucket_count -1 columns p_partkey,p_name,p_mfgr,p_brand,p_type,p_size,p_container,p_retailprice,p_comment columns.comments columns.types int:string:string:string:string:int:string:double:string #### A masked pattern was here #### name default.part_orc numFiles 1 numRows 26 rawDataSize 16042 serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde totalSize 2655 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.part_orc name: default.part_orc Truncated Path -> Alias: /part_orc [p1] #### A masked pattern was here #### Needs Tagging: true Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: 0 p_partkey (type: int) 1 _col0 (type: int) outputColumnNames: _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 Statistics: Num rows: 14 Data size: 8823 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col12 (type: int), _col13 (type: string), _col14 (type: string), _col15 (type: string), _col16 (type: string), _col17 (type: int), _col18 (type: string), _col19 (type: double), _col20 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 14 Data size: 8823 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 Statistics: Num rows: 14 Data size: 8823 Basic stats: COMPLETE Column stats: NONE #### 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,_col2,_col3,_col4,_col5,_col6,_col7,_col8 columns.types int:string:string:string:string:int:string:double:string escape.delim \ hive.serialization.extend.additional.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-0 Fetch Operator limit: -1 Processor Tree: ListSink PREHOOK: query: select abc.* from part_orc p1 join noop(on part_orc partition by p_mfgr order by p_name ) abc on abc.p_partkey = p1.p_partkey PREHOOK: type: QUERY PREHOOK: Input: default@part_orc #### A masked pattern was here #### POSTHOOK: query: select abc.* from part_orc p1 join noop(on part_orc partition by p_mfgr order by p_name ) abc on abc.p_partkey = p1.p_partkey POSTHOOK: type: QUERY POSTHOOK: Input: default@part_orc #### A masked pattern was here #### 105685 almond antique violet chocolate turquoise Manufacturer#2 Brand#22 MEDIUM ANODIZED COPPER 14 MED CAN 1690.68 ly pending requ 110592 almond antique salmon chartreuse burlywood Manufacturer#1 Brand#15 PROMO BURNISHED NICKEL 6 JUMBO PKG 1602.59 to the furiously 112398 almond antique metallic orange dim Manufacturer#3 Brand#32 MEDIUM BURNISHED BRASS 19 JUMBO JAR 1410.39 ole car 121152 almond antique burnished rose metallic Manufacturer#1 Brand#14 PROMO PLATED TIN 2 JUMBO BOX 1173.15 e pinto beans h 121152 almond antique burnished rose metallic Manufacturer#1 Brand#14 PROMO PLATED TIN 2 JUMBO BOX 1173.15 e pinto beans h 121152 almond antique burnished rose metallic Manufacturer#1 Brand#14 PROMO PLATED TIN 2 JUMBO BOX 1173.15 e pinto beans h 121152 almond antique burnished rose metallic Manufacturer#1 Brand#14 PROMO PLATED TIN 2 JUMBO BOX 1173.15 e pinto beans h 132666 almond aquamarine rose maroon antique Manufacturer#2 Brand#24 SMALL POLISHED NICKEL 25 MED BOX 1698.66 even 144293 almond antique olive coral navajo Manufacturer#3 Brand#34 STANDARD POLISHED STEEL 45 JUMBO CAN 1337.29 ag furiously about 146985 almond aquamarine midnight light salmon Manufacturer#2 Brand#23 MEDIUM BURNISHED COPPER 2 SM CASE 2031.98 s cajole caref 15103 almond aquamarine dodger light gainsboro Manufacturer#5 Brand#53 ECONOMY BURNISHED STEEL 46 LG PACK 1018.1 packages hinder carefu 155733 almond antique sky peru orange Manufacturer#5 Brand#53 SMALL PLATED BRASS 2 WRAP DRUM 1788.73 furiously. bra 17273 almond antique forest lavender goldenrod Manufacturer#3 Brand#35 PROMO ANODIZED TIN 14 JUMBO CASE 1190.27 along the 17927 almond aquamarine yellow dodger mint Manufacturer#4 Brand#41 ECONOMY BRUSHED COPPER 7 SM PKG 1844.92 ites. eve 191709 almond antique violet turquoise frosted Manufacturer#2 Brand#22 ECONOMY POLISHED STEEL 40 MED BOX 1800.7 haggle 192697 almond antique blue firebrick mint Manufacturer#5 Brand#52 MEDIUM BURNISHED TIN 31 LG DRUM 1789.69 ickly ir 195606 almond aquamarine sandy cyan gainsboro Manufacturer#2 Brand#25 STANDARD PLATED TIN 18 SM PKG 1701.6 ic de 33357 almond azure aquamarine papaya violet Manufacturer#4 Brand#41 STANDARD ANODIZED TIN 12 WRAP CASE 1290.35 reful 40982 almond antique misty red olive Manufacturer#3 Brand#32 ECONOMY PLATED COPPER 1 LG PKG 1922.98 c foxes can s 42669 almond antique medium spring khaki Manufacturer#5 Brand#51 STANDARD BURNISHED TIN 6 MED CAN 1611.66 sits haggl 45261 almond aquamarine floral ivory bisque Manufacturer#4 Brand#42 SMALL PLATED STEEL 27 WRAP CASE 1206.26 careful 48427 almond antique violet mint lemon Manufacturer#4 Brand#42 PROMO POLISHED STEEL 39 SM CASE 1375.42 hely ironic i 49671 almond antique gainsboro frosted violet Manufacturer#4 Brand#41 SMALL BRUSHED BRASS 10 SM BOX 1620.67 ccounts run quick 65667 almond aquamarine pink moccasin thistle Manufacturer#1 Brand#12 LARGE BURNISHED STEEL 42 JUMBO CASE 1632.66 e across the expr 78486 almond azure blanched chiffon midnight Manufacturer#5 Brand#52 LARGE BRUSHED BRASS 23 MED BAG 1464.48 hely blith 85768 almond antique chartreuse lavender yellow Manufacturer#1 Brand#12 LARGE BRUSHED STEEL 34 SM BAG 1753.76 refull 86428 almond aquamarine burnished black steel Manufacturer#1 Brand#12 STANDARD ANODIZED STEEL 28 WRAP BAG 1414.42 arefully 90681 almond antique chartreuse khaki white Manufacturer#3 Brand#31 MEDIUM BURNISHED TIN 17 SM CASE 1671.68 are slyly after the sl PREHOOK: query: -- 9. testNoopWithMap explain extended select p_mfgr, p_name, p_size, rank() over (partition by p_mfgr order by p_name, p_size desc) as r from noopwithmap(on part_orc partition by p_mfgr order by p_name, p_size desc) PREHOOK: type: QUERY POSTHOOK: query: -- 9. testNoopWithMap explain extended select p_mfgr, p_name, p_size, rank() over (partition by p_mfgr order by p_name, p_size desc) as r from noopwithmap(on part_orc partition by p_mfgr order by p_name, p_size desc) POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: TOK_QUERY TOK_FROM TOK_PTBLFUNCTION noopwithmap TOK_TABREF TOK_TABNAME part_orc TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name TOK_TABSORTCOLNAMEDESC TOK_TABLE_OR_COL p_size TOK_INSERT TOK_DESTINATION TOK_DIR TOK_TMP_FILE TOK_SELECT TOK_SELEXPR TOK_TABLE_OR_COL p_mfgr TOK_SELEXPR TOK_TABLE_OR_COL p_name TOK_SELEXPR TOK_TABLE_OR_COL p_size TOK_SELEXPR TOK_FUNCTION rank TOK_WINDOWSPEC TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name TOK_TABSORTCOLNAMEDESC TOK_TABLE_OR_COL p_size r STAGE DEPENDENCIES: Stage-1 is a root stage Stage-2 depends on stages: Stage-1 Stage-0 depends on stages: Stage-2 STAGE PLANS: Stage: Stage-1 Map Reduce Map Operator Tree: TableScan alias: part_orc Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE GatherStats: false PTF Operator Function definitions: Input definition input alias: part_orc output shape: p_name: string, p_mfgr: string, p_size: int type: TABLE Partition table definition input alias: ptf_1 name: noopwithmap order by: p_name, p_size(DESC) output shape: p_name: string, p_mfgr: string, p_size: int partition by: p_mfgr raw input shape: transforms raw input: true Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE Map-side function: true Reduce Output Operator key expressions: p_mfgr (type: string), p_name (type: string), p_size (type: int) sort order: ++- Map-reduce partition columns: p_mfgr (type: string) Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE tag: -1 auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: part_orc input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat properties: COLUMN_STATS_ACCURATE true bucket_count -1 columns p_partkey,p_name,p_mfgr,p_brand,p_type,p_size,p_container,p_retailprice,p_comment columns.comments columns.types int:string:string:string:string:int:string:double:string #### A masked pattern was here #### name default.part_orc numFiles 1 numRows 26 rawDataSize 16042 serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde totalSize 2655 #### 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: COLUMN_STATS_ACCURATE true bucket_count -1 columns p_partkey,p_name,p_mfgr,p_brand,p_type,p_size,p_container,p_retailprice,p_comment columns.comments columns.types int:string:string:string:string:int:string:double:string #### A masked pattern was here #### name default.part_orc numFiles 1 numRows 26 rawDataSize 16042 serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde totalSize 2655 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.part_orc name: default.part_orc Truncated Path -> Alias: /part_orc [part_orc] Needs Tagging: false Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), KEY.reducesinkkey2 (type: int) outputColumnNames: _col1, _col2, _col5 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: part_orc output shape: _col1: string, _col2: string, _col5: int type: TABLE Partition table definition input alias: ptf_1 name: noopwithmap order by: _col1, _col5(DESC) output shape: _col1: string, _col2: string, _col5: int partition by: _col2 raw input shape: transforms raw input: true Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5 columns.types string,string,int escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe TotalFiles: 1 GatherStats: false MultiFileSpray: false Stage: Stage-2 Map Reduce Map Operator Tree: TableScan GatherStats: false Reduce Output Operator key expressions: _col2 (type: string), _col1 (type: string), _col5 (type: int) sort order: ++- Map-reduce partition columns: _col2 (type: string) Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE tag: -1 auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: -mr-10002 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5 columns.types string,string,int escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5 columns.types string,string,int escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Truncated Path -> Alias: #### A masked pattern was here #### Needs Tagging: false Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), KEY.reducesinkkey2 (type: int) outputColumnNames: _col1, _col2, _col5 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: ptf_0 output shape: _col1: string, _col2: string, _col5: int type: WINDOWING Windowing table definition input alias: ptf_1 name: windowingtablefunction order by: _col1, _col5(DESC) partition by: _col2 raw input shape: window functions: window function definition alias: rank_window_0 arguments: _col1, _col5 name: rank window function: GenericUDAFRankEvaluator window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col2 (type: string), _col1 (type: string), _col5 (type: int), rank_window_0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE #### 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,_col2,_col3 columns.types string:string:int:int escape.delim \ hive.serialization.extend.additional.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-0 Fetch Operator limit: -1 Processor Tree: ListSink PREHOOK: query: select p_mfgr, p_name, p_size, rank() over (partition by p_mfgr order by p_name, p_size desc) as r from noopwithmap(on part_orc partition by p_mfgr order by p_name, p_size desc) PREHOOK: type: QUERY PREHOOK: Input: default@part_orc #### A masked pattern was here #### POSTHOOK: query: select p_mfgr, p_name, p_size, rank() over (partition by p_mfgr order by p_name, p_size desc) as r from noopwithmap(on part_orc partition by p_mfgr order by p_name, p_size desc) POSTHOOK: type: QUERY POSTHOOK: Input: default@part_orc #### A masked pattern was here #### Manufacturer#1 almond antique burnished rose metallic 2 1 Manufacturer#1 almond antique burnished rose metallic 2 1 Manufacturer#1 almond antique chartreuse lavender yellow 34 3 Manufacturer#1 almond antique salmon chartreuse burlywood 6 4 Manufacturer#1 almond aquamarine burnished black steel 28 5 Manufacturer#1 almond aquamarine pink moccasin thistle 42 6 Manufacturer#2 almond antique violet chocolate turquoise 14 1 Manufacturer#2 almond antique violet turquoise frosted 40 2 Manufacturer#2 almond aquamarine midnight light salmon 2 3 Manufacturer#2 almond aquamarine rose maroon antique 25 4 Manufacturer#2 almond aquamarine sandy cyan gainsboro 18 5 Manufacturer#3 almond antique chartreuse khaki white 17 1 Manufacturer#3 almond antique forest lavender goldenrod 14 2 Manufacturer#3 almond antique metallic orange dim 19 3 Manufacturer#3 almond antique misty red olive 1 4 Manufacturer#3 almond antique olive coral navajo 45 5 Manufacturer#4 almond antique gainsboro frosted violet 10 1 Manufacturer#4 almond antique violet mint lemon 39 2 Manufacturer#4 almond aquamarine floral ivory bisque 27 3 Manufacturer#4 almond aquamarine yellow dodger mint 7 4 Manufacturer#4 almond azure aquamarine papaya violet 12 5 Manufacturer#5 almond antique blue firebrick mint 31 1 Manufacturer#5 almond antique medium spring khaki 6 2 Manufacturer#5 almond antique sky peru orange 2 3 Manufacturer#5 almond aquamarine dodger light gainsboro 46 4 Manufacturer#5 almond azure blanched chiffon midnight 23 5 PREHOOK: query: -- 10. testNoopWithMapWithWindowing explain extended select p_mfgr, p_name, p_size, rank() over (partition by p_mfgr order by p_name) as r, dense_rank() over (partition by p_mfgr order by p_name) as dr, sum(p_retailprice) over (partition by p_mfgr order by p_name rows between unbounded preceding and current row) as s1 from noopwithmap(on part_orc partition by p_mfgr order by p_name) PREHOOK: type: QUERY POSTHOOK: query: -- 10. testNoopWithMapWithWindowing explain extended select p_mfgr, p_name, p_size, rank() over (partition by p_mfgr order by p_name) as r, dense_rank() over (partition by p_mfgr order by p_name) as dr, sum(p_retailprice) over (partition by p_mfgr order by p_name rows between unbounded preceding and current row) as s1 from noopwithmap(on part_orc partition by p_mfgr order by p_name) POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: TOK_QUERY TOK_FROM TOK_PTBLFUNCTION noopwithmap TOK_TABREF TOK_TABNAME part_orc TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name TOK_INSERT TOK_DESTINATION TOK_DIR TOK_TMP_FILE TOK_SELECT TOK_SELEXPR TOK_TABLE_OR_COL p_mfgr TOK_SELEXPR TOK_TABLE_OR_COL p_name TOK_SELEXPR TOK_TABLE_OR_COL p_size TOK_SELEXPR TOK_FUNCTION rank TOK_WINDOWSPEC TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name r TOK_SELEXPR TOK_FUNCTION dense_rank TOK_WINDOWSPEC TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name dr TOK_SELEXPR TOK_FUNCTION sum TOK_TABLE_OR_COL p_retailprice TOK_WINDOWSPEC TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name TOK_WINDOWRANGE preceding unbounded current s1 STAGE DEPENDENCIES: Stage-1 is a root stage Stage-2 depends on stages: Stage-1 Stage-0 depends on stages: Stage-2 STAGE PLANS: Stage: Stage-1 Map Reduce Map Operator Tree: TableScan alias: part_orc Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE GatherStats: false PTF Operator Function definitions: Input definition input alias: part_orc output shape: p_name: string, p_mfgr: string, p_size: int, p_retailprice: double type: TABLE Partition table definition input alias: ptf_1 name: noopwithmap order by: p_name output shape: p_name: string, p_mfgr: string, p_size: int, p_retailprice: double partition by: p_mfgr raw input shape: transforms raw input: true Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE Map-side function: true Reduce Output Operator key expressions: p_mfgr (type: string), p_name (type: string) sort order: ++ Map-reduce partition columns: p_mfgr (type: string) Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: p_size (type: int), p_retailprice (type: double) auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: part_orc input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat properties: COLUMN_STATS_ACCURATE true bucket_count -1 columns p_partkey,p_name,p_mfgr,p_brand,p_type,p_size,p_container,p_retailprice,p_comment columns.comments columns.types int:string:string:string:string:int:string:double:string #### A masked pattern was here #### name default.part_orc numFiles 1 numRows 26 rawDataSize 16042 serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde totalSize 2655 #### 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: COLUMN_STATS_ACCURATE true bucket_count -1 columns p_partkey,p_name,p_mfgr,p_brand,p_type,p_size,p_container,p_retailprice,p_comment columns.comments columns.types int:string:string:string:string:int:string:double:string #### A masked pattern was here #### name default.part_orc numFiles 1 numRows 26 rawDataSize 16042 serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde totalSize 2655 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.part_orc name: default.part_orc Truncated Path -> Alias: /part_orc [part_orc] Needs Tagging: false Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int), VALUE._col5 (type: double) outputColumnNames: _col1, _col2, _col5, _col7 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: part_orc output shape: _col1: string, _col2: string, _col5: int, _col7: double type: TABLE Partition table definition input alias: ptf_1 name: noopwithmap order by: _col1 output shape: _col1: string, _col2: string, _col5: int, _col7: double partition by: _col2 raw input shape: transforms raw input: true Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5,_col7 columns.types string,string,int,double escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe TotalFiles: 1 GatherStats: false MultiFileSpray: false Stage: Stage-2 Map Reduce Map Operator Tree: TableScan GatherStats: false Reduce Output Operator key expressions: _col2 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col2 (type: string) Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col5 (type: int), _col7 (type: double) auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: -mr-10002 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5,_col7 columns.types string,string,int,double escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5,_col7 columns.types string,string,int,double escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Truncated Path -> Alias: #### A masked pattern was here #### Needs Tagging: false Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int), VALUE._col5 (type: double) outputColumnNames: _col1, _col2, _col5, _col7 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: ptf_0 output shape: _col1: string, _col2: string, _col5: int, _col7: double type: WINDOWING Windowing table definition input alias: ptf_1 name: windowingtablefunction order by: _col1 partition by: _col2 raw input shape: window functions: window function definition alias: rank_window_0 arguments: _col1 name: rank window function: GenericUDAFRankEvaluator window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true window function definition alias: dense_rank_window_1 arguments: _col1 name: dense_rank window function: GenericUDAFDenseRankEvaluator window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true window function definition alias: sum_window_2 arguments: _col7 name: sum window function: GenericUDAFSumDouble window frame: PRECEDING(MAX)~ Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col2 (type: string), _col1 (type: string), _col5 (type: int), rank_window_0 (type: int), dense_rank_window_1 (type: int), sum_window_2 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE #### 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,_col2,_col3,_col4,_col5 columns.types string:string:int:int:int:double escape.delim \ hive.serialization.extend.additional.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-0 Fetch Operator limit: -1 Processor Tree: ListSink PREHOOK: query: select p_mfgr, p_name, p_size, rank() over (partition by p_mfgr order by p_name) as r, dense_rank() over (partition by p_mfgr order by p_name) as dr, sum(p_retailprice) over (partition by p_mfgr order by p_name rows between unbounded preceding and current row) as s1 from noopwithmap(on part_orc partition by p_mfgr order by p_name) PREHOOK: type: QUERY PREHOOK: Input: default@part_orc #### A masked pattern was here #### POSTHOOK: query: select p_mfgr, p_name, p_size, rank() over (partition by p_mfgr order by p_name) as r, dense_rank() over (partition by p_mfgr order by p_name) as dr, sum(p_retailprice) over (partition by p_mfgr order by p_name rows between unbounded preceding and current row) as s1 from noopwithmap(on part_orc partition by p_mfgr order by p_name) POSTHOOK: type: QUERY POSTHOOK: Input: default@part_orc #### A masked pattern was here #### Manufacturer#1 almond antique burnished rose metallic 2 1 1 1173.15 Manufacturer#1 almond antique burnished rose metallic 2 1 1 2346.3 Manufacturer#1 almond antique chartreuse lavender yellow 34 3 2 4100.06 Manufacturer#1 almond antique salmon chartreuse burlywood 6 4 3 5702.650000000001 Manufacturer#1 almond aquamarine burnished black steel 28 5 4 7117.070000000001 Manufacturer#1 almond aquamarine pink moccasin thistle 42 6 5 8749.730000000001 Manufacturer#2 almond antique violet chocolate turquoise 14 1 1 1690.68 Manufacturer#2 almond antique violet turquoise frosted 40 2 2 3491.38 Manufacturer#2 almond aquamarine midnight light salmon 2 3 3 5523.360000000001 Manufacturer#2 almond aquamarine rose maroon antique 25 4 4 7222.02 Manufacturer#2 almond aquamarine sandy cyan gainsboro 18 5 5 8923.62 Manufacturer#3 almond antique chartreuse khaki white 17 1 1 1671.68 Manufacturer#3 almond antique forest lavender goldenrod 14 2 2 2861.95 Manufacturer#3 almond antique metallic orange dim 19 3 3 4272.34 Manufacturer#3 almond antique misty red olive 1 4 4 6195.32 Manufacturer#3 almond antique olive coral navajo 45 5 5 7532.61 Manufacturer#4 almond antique gainsboro frosted violet 10 1 1 1620.67 Manufacturer#4 almond antique violet mint lemon 39 2 2 2996.09 Manufacturer#4 almond aquamarine floral ivory bisque 27 3 3 4202.35 Manufacturer#4 almond aquamarine yellow dodger mint 7 4 4 6047.27 Manufacturer#4 almond azure aquamarine papaya violet 12 5 5 7337.620000000001 Manufacturer#5 almond antique blue firebrick mint 31 1 1 1789.69 Manufacturer#5 almond antique medium spring khaki 6 2 2 3401.3500000000004 Manufacturer#5 almond antique sky peru orange 2 3 3 5190.08 Manufacturer#5 almond aquamarine dodger light gainsboro 46 4 4 6208.18 Manufacturer#5 almond azure blanched chiffon midnight 23 5 5 7672.66 PREHOOK: query: -- 11. testHavingWithWindowingPTFNoGBY explain extended select p_mfgr, p_name, p_size, rank() over (partition by p_mfgr order by p_name) as r, dense_rank() over (partition by p_mfgr order by p_name) as dr, sum(p_retailprice) over (partition by p_mfgr order by p_name rows between unbounded preceding and current row) as s1 from noop(on part_orc partition by p_mfgr order by p_name) PREHOOK: type: QUERY POSTHOOK: query: -- 11. testHavingWithWindowingPTFNoGBY explain extended select p_mfgr, p_name, p_size, rank() over (partition by p_mfgr order by p_name) as r, dense_rank() over (partition by p_mfgr order by p_name) as dr, sum(p_retailprice) over (partition by p_mfgr order by p_name rows between unbounded preceding and current row) as s1 from noop(on part_orc partition by p_mfgr order by p_name) POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: TOK_QUERY TOK_FROM TOK_PTBLFUNCTION noop TOK_TABREF TOK_TABNAME part_orc TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name TOK_INSERT TOK_DESTINATION TOK_DIR TOK_TMP_FILE TOK_SELECT TOK_SELEXPR TOK_TABLE_OR_COL p_mfgr TOK_SELEXPR TOK_TABLE_OR_COL p_name TOK_SELEXPR TOK_TABLE_OR_COL p_size TOK_SELEXPR TOK_FUNCTION rank TOK_WINDOWSPEC TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name r TOK_SELEXPR TOK_FUNCTION dense_rank TOK_WINDOWSPEC TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name dr TOK_SELEXPR TOK_FUNCTION sum TOK_TABLE_OR_COL p_retailprice TOK_WINDOWSPEC TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name TOK_WINDOWRANGE preceding unbounded current s1 STAGE DEPENDENCIES: Stage-1 is a root stage Stage-2 depends on stages: Stage-1 Stage-0 depends on stages: Stage-2 STAGE PLANS: Stage: Stage-1 Map Reduce Map Operator Tree: TableScan alias: part_orc Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE GatherStats: false Reduce Output Operator key expressions: p_mfgr (type: string), p_name (type: string) sort order: ++ Map-reduce partition columns: p_mfgr (type: string) Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: p_size (type: int), p_retailprice (type: double) auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: part_orc input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat properties: COLUMN_STATS_ACCURATE true bucket_count -1 columns p_partkey,p_name,p_mfgr,p_brand,p_type,p_size,p_container,p_retailprice,p_comment columns.comments columns.types int:string:string:string:string:int:string:double:string #### A masked pattern was here #### name default.part_orc numFiles 1 numRows 26 rawDataSize 16042 serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde totalSize 2655 #### 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: COLUMN_STATS_ACCURATE true bucket_count -1 columns p_partkey,p_name,p_mfgr,p_brand,p_type,p_size,p_container,p_retailprice,p_comment columns.comments columns.types int:string:string:string:string:int:string:double:string #### A masked pattern was here #### name default.part_orc numFiles 1 numRows 26 rawDataSize 16042 serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde totalSize 2655 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.part_orc name: default.part_orc Truncated Path -> Alias: /part_orc [part_orc] Execution mode: vectorized Needs Tagging: false Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int), VALUE._col5 (type: double) outputColumnNames: _col1, _col2, _col5, _col7 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: part_orc output shape: _col1: string, _col2: string, _col5: int, _col7: double type: TABLE Partition table definition input alias: ptf_1 name: noop order by: _col1 output shape: _col1: string, _col2: string, _col5: int, _col7: double partition by: _col2 raw input shape: Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5,_col7 columns.types string,string,int,double escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe TotalFiles: 1 GatherStats: false MultiFileSpray: false Stage: Stage-2 Map Reduce Map Operator Tree: TableScan GatherStats: false Reduce Output Operator key expressions: _col2 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col2 (type: string) Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col5 (type: int), _col7 (type: double) auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: -mr-10002 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5,_col7 columns.types string,string,int,double escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5,_col7 columns.types string,string,int,double escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Truncated Path -> Alias: #### A masked pattern was here #### Needs Tagging: false Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int), VALUE._col5 (type: double) outputColumnNames: _col1, _col2, _col5, _col7 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: ptf_0 output shape: _col1: string, _col2: string, _col5: int, _col7: double type: WINDOWING Windowing table definition input alias: ptf_1 name: windowingtablefunction order by: _col1 partition by: _col2 raw input shape: window functions: window function definition alias: rank_window_0 arguments: _col1 name: rank window function: GenericUDAFRankEvaluator window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true window function definition alias: dense_rank_window_1 arguments: _col1 name: dense_rank window function: GenericUDAFDenseRankEvaluator window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true window function definition alias: sum_window_2 arguments: _col7 name: sum window function: GenericUDAFSumDouble window frame: PRECEDING(MAX)~ Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col2 (type: string), _col1 (type: string), _col5 (type: int), rank_window_0 (type: int), dense_rank_window_1 (type: int), sum_window_2 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE #### 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,_col2,_col3,_col4,_col5 columns.types string:string:int:int:int:double escape.delim \ hive.serialization.extend.additional.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-0 Fetch Operator limit: -1 Processor Tree: ListSink PREHOOK: query: select p_mfgr, p_name, p_size, rank() over (partition by p_mfgr order by p_name) as r, dense_rank() over (partition by p_mfgr order by p_name) as dr, sum(p_retailprice) over (partition by p_mfgr order by p_name rows between unbounded preceding and current row) as s1 from noop(on part_orc partition by p_mfgr order by p_name) PREHOOK: type: QUERY PREHOOK: Input: default@part_orc #### A masked pattern was here #### POSTHOOK: query: select p_mfgr, p_name, p_size, rank() over (partition by p_mfgr order by p_name) as r, dense_rank() over (partition by p_mfgr order by p_name) as dr, sum(p_retailprice) over (partition by p_mfgr order by p_name rows between unbounded preceding and current row) as s1 from noop(on part_orc partition by p_mfgr order by p_name) POSTHOOK: type: QUERY POSTHOOK: Input: default@part_orc #### A masked pattern was here #### Manufacturer#1 almond antique burnished rose metallic 2 1 1 1173.15 Manufacturer#1 almond antique burnished rose metallic 2 1 1 2346.3 Manufacturer#1 almond antique chartreuse lavender yellow 34 3 2 4100.06 Manufacturer#1 almond antique salmon chartreuse burlywood 6 4 3 5702.650000000001 Manufacturer#1 almond aquamarine burnished black steel 28 5 4 7117.070000000001 Manufacturer#1 almond aquamarine pink moccasin thistle 42 6 5 8749.730000000001 Manufacturer#2 almond antique violet chocolate turquoise 14 1 1 1690.68 Manufacturer#2 almond antique violet turquoise frosted 40 2 2 3491.38 Manufacturer#2 almond aquamarine midnight light salmon 2 3 3 5523.360000000001 Manufacturer#2 almond aquamarine rose maroon antique 25 4 4 7222.02 Manufacturer#2 almond aquamarine sandy cyan gainsboro 18 5 5 8923.62 Manufacturer#3 almond antique chartreuse khaki white 17 1 1 1671.68 Manufacturer#3 almond antique forest lavender goldenrod 14 2 2 2861.95 Manufacturer#3 almond antique metallic orange dim 19 3 3 4272.34 Manufacturer#3 almond antique misty red olive 1 4 4 6195.32 Manufacturer#3 almond antique olive coral navajo 45 5 5 7532.61 Manufacturer#4 almond antique gainsboro frosted violet 10 1 1 1620.67 Manufacturer#4 almond antique violet mint lemon 39 2 2 2996.09 Manufacturer#4 almond aquamarine floral ivory bisque 27 3 3 4202.35 Manufacturer#4 almond aquamarine yellow dodger mint 7 4 4 6047.27 Manufacturer#4 almond azure aquamarine papaya violet 12 5 5 7337.620000000001 Manufacturer#5 almond antique blue firebrick mint 31 1 1 1789.69 Manufacturer#5 almond antique medium spring khaki 6 2 2 3401.3500000000004 Manufacturer#5 almond antique sky peru orange 2 3 3 5190.08 Manufacturer#5 almond aquamarine dodger light gainsboro 46 4 4 6208.18 Manufacturer#5 almond azure blanched chiffon midnight 23 5 5 7672.66 PREHOOK: query: -- 12. testFunctionChain explain extended select p_mfgr, p_name, p_size, rank() over (partition by p_mfgr order by p_name) as r, dense_rank() over (partition by p_mfgr order by p_name) as dr, sum(p_retailprice) over (partition by p_mfgr order by p_name rows between unbounded preceding and current row) as s1 from noop(on noopwithmap(on noop(on part_orc partition by p_mfgr order by p_mfgr, p_name ))) PREHOOK: type: QUERY POSTHOOK: query: -- 12. testFunctionChain explain extended select p_mfgr, p_name, p_size, rank() over (partition by p_mfgr order by p_name) as r, dense_rank() over (partition by p_mfgr order by p_name) as dr, sum(p_retailprice) over (partition by p_mfgr order by p_name rows between unbounded preceding and current row) as s1 from noop(on noopwithmap(on noop(on part_orc partition by p_mfgr order by p_mfgr, p_name ))) POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: TOK_QUERY TOK_FROM TOK_PTBLFUNCTION noop TOK_PTBLFUNCTION noopwithmap TOK_PTBLFUNCTION noop TOK_TABREF TOK_TABNAME part_orc TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_mfgr TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name TOK_INSERT TOK_DESTINATION TOK_DIR TOK_TMP_FILE TOK_SELECT TOK_SELEXPR TOK_TABLE_OR_COL p_mfgr TOK_SELEXPR TOK_TABLE_OR_COL p_name TOK_SELEXPR TOK_TABLE_OR_COL p_size TOK_SELEXPR TOK_FUNCTION rank TOK_WINDOWSPEC TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name r TOK_SELEXPR TOK_FUNCTION dense_rank TOK_WINDOWSPEC TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name dr TOK_SELEXPR TOK_FUNCTION sum TOK_TABLE_OR_COL p_retailprice TOK_WINDOWSPEC TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name TOK_WINDOWRANGE preceding unbounded current s1 STAGE DEPENDENCIES: Stage-1 is a root stage Stage-2 depends on stages: Stage-1 Stage-3 depends on stages: Stage-2 Stage-0 depends on stages: Stage-3 STAGE PLANS: Stage: Stage-1 Map Reduce Map Operator Tree: TableScan alias: part_orc Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE GatherStats: false Reduce Output Operator key expressions: p_mfgr (type: string), p_name (type: string) sort order: ++ Map-reduce partition columns: p_mfgr (type: string) Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: p_size (type: int), p_retailprice (type: double) auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: part_orc input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat properties: COLUMN_STATS_ACCURATE true bucket_count -1 columns p_partkey,p_name,p_mfgr,p_brand,p_type,p_size,p_container,p_retailprice,p_comment columns.comments columns.types int:string:string:string:string:int:string:double:string #### A masked pattern was here #### name default.part_orc numFiles 1 numRows 26 rawDataSize 16042 serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde totalSize 2655 #### 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: COLUMN_STATS_ACCURATE true bucket_count -1 columns p_partkey,p_name,p_mfgr,p_brand,p_type,p_size,p_container,p_retailprice,p_comment columns.comments columns.types int:string:string:string:string:int:string:double:string #### A masked pattern was here #### name default.part_orc numFiles 1 numRows 26 rawDataSize 16042 serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde totalSize 2655 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.part_orc name: default.part_orc Truncated Path -> Alias: /part_orc [part_orc] Execution mode: vectorized Needs Tagging: false Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int), VALUE._col5 (type: double) outputColumnNames: _col1, _col2, _col5, _col7 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: part_orc output shape: _col1: string, _col2: string, _col5: int, _col7: double type: TABLE Partition table definition input alias: ptf_1 name: noop order by: _col2, _col1 output shape: _col1: string, _col2: string, _col5: int, _col7: double partition by: _col2 raw input shape: Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: ptf_0 output shape: _col1: string, _col2: string, _col5: int, _col7: double type: PTFCOMPONENT Partition table definition input alias: ptf_1 name: noopwithmap order by: _col2, _col1 output shape: _col1: string, _col2: string, _col5: int, _col7: double partition by: _col2 raw input shape: transforms raw input: true Partition table definition input alias: ptf_2 name: noop order by: _col2, _col1 output shape: _col1: string, _col2: string, _col5: int, _col7: double partition by: _col2 raw input shape: Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE Map-side function: true File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5,_col7 columns.types string,string,int,double escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe TotalFiles: 1 GatherStats: false MultiFileSpray: false Stage: Stage-2 Map Reduce Map Operator Tree: TableScan GatherStats: false Reduce Output Operator key expressions: _col2 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col2 (type: string) Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col5 (type: int), _col7 (type: double) auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: -mr-10002 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5,_col7 columns.types string,string,int,double escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5,_col7 columns.types string,string,int,double escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Truncated Path -> Alias: #### A masked pattern was here #### Needs Tagging: false Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int), VALUE._col5 (type: double) outputColumnNames: _col1, _col2, _col5, _col7 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: ptf_0 output shape: _col1: string, _col2: string, _col5: int, _col7: double type: PTFCOMPONENT Partition table definition input alias: ptf_1 name: noopwithmap order by: _col2, _col1 output shape: _col1: string, _col2: string, _col5: int, _col7: double partition by: _col2 raw input shape: transforms raw input: true Partition table definition input alias: ptf_2 name: noop order by: _col2, _col1 output shape: _col1: string, _col2: string, _col5: int, _col7: double partition by: _col2 raw input shape: Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5,_col7 columns.types string,string,int,double escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe TotalFiles: 1 GatherStats: false MultiFileSpray: false Stage: Stage-3 Map Reduce Map Operator Tree: TableScan GatherStats: false Reduce Output Operator key expressions: _col2 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col2 (type: string) Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col5 (type: int), _col7 (type: double) auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: -mr-10003 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5,_col7 columns.types string,string,int,double escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5,_col7 columns.types string,string,int,double escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Truncated Path -> Alias: #### A masked pattern was here #### Needs Tagging: false Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int), VALUE._col5 (type: double) outputColumnNames: _col1, _col2, _col5, _col7 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: ptf_0 output shape: _col1: string, _col2: string, _col5: int, _col7: double type: WINDOWING Windowing table definition input alias: ptf_1 name: windowingtablefunction order by: _col1 partition by: _col2 raw input shape: window functions: window function definition alias: rank_window_0 arguments: _col1 name: rank window function: GenericUDAFRankEvaluator window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true window function definition alias: dense_rank_window_1 arguments: _col1 name: dense_rank window function: GenericUDAFDenseRankEvaluator window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true window function definition alias: sum_window_2 arguments: _col7 name: sum window function: GenericUDAFSumDouble window frame: PRECEDING(MAX)~ Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col2 (type: string), _col1 (type: string), _col5 (type: int), rank_window_0 (type: int), dense_rank_window_1 (type: int), sum_window_2 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE #### 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,_col2,_col3,_col4,_col5 columns.types string:string:int:int:int:double escape.delim \ hive.serialization.extend.additional.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-0 Fetch Operator limit: -1 Processor Tree: ListSink PREHOOK: query: select p_mfgr, p_name, p_size, rank() over (partition by p_mfgr order by p_name) as r, dense_rank() over (partition by p_mfgr order by p_name) as dr, sum(p_retailprice) over (partition by p_mfgr order by p_name rows between unbounded preceding and current row) as s1 from noop(on noopwithmap(on noop(on part_orc partition by p_mfgr order by p_mfgr, p_name ))) PREHOOK: type: QUERY PREHOOK: Input: default@part_orc #### A masked pattern was here #### POSTHOOK: query: select p_mfgr, p_name, p_size, rank() over (partition by p_mfgr order by p_name) as r, dense_rank() over (partition by p_mfgr order by p_name) as dr, sum(p_retailprice) over (partition by p_mfgr order by p_name rows between unbounded preceding and current row) as s1 from noop(on noopwithmap(on noop(on part_orc partition by p_mfgr order by p_mfgr, p_name ))) POSTHOOK: type: QUERY POSTHOOK: Input: default@part_orc #### A masked pattern was here #### Manufacturer#1 almond antique burnished rose metallic 2 1 1 1173.15 Manufacturer#1 almond antique burnished rose metallic 2 1 1 2346.3 Manufacturer#1 almond antique chartreuse lavender yellow 34 3 2 4100.06 Manufacturer#1 almond antique salmon chartreuse burlywood 6 4 3 5702.650000000001 Manufacturer#1 almond aquamarine burnished black steel 28 5 4 7117.070000000001 Manufacturer#1 almond aquamarine pink moccasin thistle 42 6 5 8749.730000000001 Manufacturer#2 almond antique violet chocolate turquoise 14 1 1 1690.68 Manufacturer#2 almond antique violet turquoise frosted 40 2 2 3491.38 Manufacturer#2 almond aquamarine midnight light salmon 2 3 3 5523.360000000001 Manufacturer#2 almond aquamarine rose maroon antique 25 4 4 7222.02 Manufacturer#2 almond aquamarine sandy cyan gainsboro 18 5 5 8923.62 Manufacturer#3 almond antique chartreuse khaki white 17 1 1 1671.68 Manufacturer#3 almond antique forest lavender goldenrod 14 2 2 2861.95 Manufacturer#3 almond antique metallic orange dim 19 3 3 4272.34 Manufacturer#3 almond antique misty red olive 1 4 4 6195.32 Manufacturer#3 almond antique olive coral navajo 45 5 5 7532.61 Manufacturer#4 almond antique gainsboro frosted violet 10 1 1 1620.67 Manufacturer#4 almond antique violet mint lemon 39 2 2 2996.09 Manufacturer#4 almond aquamarine floral ivory bisque 27 3 3 4202.35 Manufacturer#4 almond aquamarine yellow dodger mint 7 4 4 6047.27 Manufacturer#4 almond azure aquamarine papaya violet 12 5 5 7337.620000000001 Manufacturer#5 almond antique blue firebrick mint 31 1 1 1789.69 Manufacturer#5 almond antique medium spring khaki 6 2 2 3401.3500000000004 Manufacturer#5 almond antique sky peru orange 2 3 3 5190.08 Manufacturer#5 almond aquamarine dodger light gainsboro 46 4 4 6208.18 Manufacturer#5 almond azure blanched chiffon midnight 23 5 5 7672.66 PREHOOK: query: -- 13. testPTFAndWindowingInSubQ explain extended select p_mfgr, p_name, sub1.cd, sub1.s1 from (select p_mfgr, p_name, count(p_size) over (partition by p_mfgr order by p_name) as cd, p_retailprice, sum(p_retailprice) over w1 as s1 from noop(on part_orc partition by p_mfgr order by p_name) window w1 as (partition by p_mfgr order by p_name rows between 2 preceding and 2 following) ) sub1 PREHOOK: type: QUERY POSTHOOK: query: -- 13. testPTFAndWindowingInSubQ explain extended select p_mfgr, p_name, sub1.cd, sub1.s1 from (select p_mfgr, p_name, count(p_size) over (partition by p_mfgr order by p_name) as cd, p_retailprice, sum(p_retailprice) over w1 as s1 from noop(on part_orc partition by p_mfgr order by p_name) window w1 as (partition by p_mfgr order by p_name rows between 2 preceding and 2 following) ) sub1 POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: TOK_QUERY TOK_FROM TOK_SUBQUERY TOK_QUERY TOK_FROM TOK_PTBLFUNCTION noop TOK_TABREF TOK_TABNAME part_orc TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name TOK_INSERT TOK_DESTINATION TOK_DIR TOK_TMP_FILE TOK_SELECT TOK_SELEXPR TOK_TABLE_OR_COL p_mfgr TOK_SELEXPR TOK_TABLE_OR_COL p_name TOK_SELEXPR TOK_FUNCTION count TOK_TABLE_OR_COL p_size TOK_WINDOWSPEC TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name cd TOK_SELEXPR TOK_TABLE_OR_COL p_retailprice TOK_SELEXPR TOK_FUNCTION sum TOK_TABLE_OR_COL p_retailprice TOK_WINDOWSPEC w1 s1 window TOK_WINDOWDEF w1 TOK_WINDOWSPEC TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name TOK_WINDOWRANGE preceding 2 following 2 sub1 TOK_INSERT TOK_DESTINATION TOK_DIR TOK_TMP_FILE TOK_SELECT TOK_SELEXPR TOK_TABLE_OR_COL p_mfgr TOK_SELEXPR TOK_TABLE_OR_COL p_name TOK_SELEXPR . TOK_TABLE_OR_COL sub1 cd TOK_SELEXPR . TOK_TABLE_OR_COL sub1 s1 STAGE DEPENDENCIES: Stage-1 is a root stage Stage-2 depends on stages: Stage-1 Stage-0 depends on stages: Stage-2 STAGE PLANS: Stage: Stage-1 Map Reduce Map Operator Tree: TableScan alias: part_orc Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE GatherStats: false Reduce Output Operator key expressions: p_mfgr (type: string), p_name (type: string) sort order: ++ Map-reduce partition columns: p_mfgr (type: string) Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: p_size (type: int), p_retailprice (type: double) auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: part_orc input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat properties: COLUMN_STATS_ACCURATE true bucket_count -1 columns p_partkey,p_name,p_mfgr,p_brand,p_type,p_size,p_container,p_retailprice,p_comment columns.comments columns.types int:string:string:string:string:int:string:double:string #### A masked pattern was here #### name default.part_orc numFiles 1 numRows 26 rawDataSize 16042 serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde totalSize 2655 #### 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: COLUMN_STATS_ACCURATE true bucket_count -1 columns p_partkey,p_name,p_mfgr,p_brand,p_type,p_size,p_container,p_retailprice,p_comment columns.comments columns.types int:string:string:string:string:int:string:double:string #### A masked pattern was here #### name default.part_orc numFiles 1 numRows 26 rawDataSize 16042 serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde totalSize 2655 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.part_orc name: default.part_orc Truncated Path -> Alias: /part_orc [sub1:part_orc] Execution mode: vectorized Needs Tagging: false Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int), VALUE._col5 (type: double) outputColumnNames: _col1, _col2, _col5, _col7 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: part_orc output shape: _col1: string, _col2: string, _col5: int, _col7: double type: TABLE Partition table definition input alias: ptf_1 name: noop order by: _col1 output shape: _col1: string, _col2: string, _col5: int, _col7: double partition by: _col2 raw input shape: Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5,_col7 columns.types string,string,int,double escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe TotalFiles: 1 GatherStats: false MultiFileSpray: false Stage: Stage-2 Map Reduce Map Operator Tree: TableScan GatherStats: false Reduce Output Operator key expressions: _col2 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col2 (type: string) Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col5 (type: int), _col7 (type: double) auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: -mr-10002 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5,_col7 columns.types string,string,int,double escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5,_col7 columns.types string,string,int,double escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Truncated Path -> Alias: #### A masked pattern was here #### Needs Tagging: false Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int), VALUE._col5 (type: double) outputColumnNames: _col1, _col2, _col5, _col7 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: ptf_0 output shape: _col1: string, _col2: string, _col5: int, _col7: double type: WINDOWING Windowing table definition input alias: ptf_1 name: windowingtablefunction order by: _col1 partition by: _col2 raw input shape: window functions: window function definition alias: count_window_0 arguments: _col5 name: count window function: GenericUDAFCountEvaluator window frame: PRECEDING(MAX)~ window function definition alias: sum_window_1 arguments: _col7 name: sum window function: GenericUDAFSumDouble window frame: PRECEDING(2)~FOLLOWING(2) Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col2 (type: string), _col1 (type: string), count_window_0 (type: bigint), sum_window_1 (type: double) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE #### 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,_col2,_col3 columns.types string:string:bigint:double escape.delim \ hive.serialization.extend.additional.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-0 Fetch Operator limit: -1 Processor Tree: ListSink PREHOOK: query: select p_mfgr, p_name, sub1.cd, sub1.s1 from (select p_mfgr, p_name, count(p_size) over (partition by p_mfgr order by p_name) as cd, p_retailprice, sum(p_retailprice) over w1 as s1 from noop(on part_orc partition by p_mfgr order by p_name) window w1 as (partition by p_mfgr order by p_name rows between 2 preceding and 2 following) ) sub1 PREHOOK: type: QUERY PREHOOK: Input: default@part_orc #### A masked pattern was here #### POSTHOOK: query: select p_mfgr, p_name, sub1.cd, sub1.s1 from (select p_mfgr, p_name, count(p_size) over (partition by p_mfgr order by p_name) as cd, p_retailprice, sum(p_retailprice) over w1 as s1 from noop(on part_orc partition by p_mfgr order by p_name) window w1 as (partition by p_mfgr order by p_name rows between 2 preceding and 2 following) ) sub1 POSTHOOK: type: QUERY POSTHOOK: Input: default@part_orc #### A masked pattern was here #### Manufacturer#1 almond antique burnished rose metallic 2 4100.06 Manufacturer#1 almond antique burnished rose metallic 2 5702.650000000001 Manufacturer#1 almond antique chartreuse lavender yellow 3 7117.070000000001 Manufacturer#1 almond antique salmon chartreuse burlywood 4 7576.58 Manufacturer#1 almond aquamarine burnished black steel 5 6403.43 Manufacturer#1 almond aquamarine pink moccasin thistle 6 4649.67 Manufacturer#2 almond antique violet chocolate turquoise 1 5523.360000000001 Manufacturer#2 almond antique violet turquoise frosted 2 7222.02 Manufacturer#2 almond aquamarine midnight light salmon 3 8923.62 Manufacturer#2 almond aquamarine rose maroon antique 4 7232.9400000000005 Manufacturer#2 almond aquamarine sandy cyan gainsboro 5 5432.24 Manufacturer#3 almond antique chartreuse khaki white 1 4272.34 Manufacturer#3 almond antique forest lavender goldenrod 2 6195.32 Manufacturer#3 almond antique metallic orange dim 3 7532.61 Manufacturer#3 almond antique misty red olive 4 5860.929999999999 Manufacturer#3 almond antique olive coral navajo 5 4670.66 Manufacturer#4 almond antique gainsboro frosted violet 1 4202.35 Manufacturer#4 almond antique violet mint lemon 2 6047.27 Manufacturer#4 almond aquamarine floral ivory bisque 3 7337.620000000001 Manufacturer#4 almond aquamarine yellow dodger mint 4 5716.950000000001 Manufacturer#4 almond azure aquamarine papaya violet 5 4341.530000000001 Manufacturer#5 almond antique blue firebrick mint 1 5190.08 Manufacturer#5 almond antique medium spring khaki 2 6208.18 Manufacturer#5 almond antique sky peru orange 3 7672.66 Manufacturer#5 almond aquamarine dodger light gainsboro 4 5882.970000000001 Manufacturer#5 almond azure blanched chiffon midnight 5 4271.3099999999995 PREHOOK: query: -- 14. testPTFJoinWithWindowingWithCount explain extended select abc.p_mfgr, abc.p_name, rank() over (distribute by abc.p_mfgr sort by abc.p_name) as r, dense_rank() over (distribute by abc.p_mfgr sort by abc.p_name) as dr, count(abc.p_name) over (distribute by abc.p_mfgr sort by abc.p_name) as cd, abc.p_retailprice, sum(abc.p_retailprice) over (distribute by abc.p_mfgr sort by abc.p_name rows between unbounded preceding and current row) as s1, abc.p_size, abc.p_size - lag(abc.p_size,1,abc.p_size) over (distribute by abc.p_mfgr sort by abc.p_name) as deltaSz from noop(on part_orc partition by p_mfgr order by p_name ) abc join part_orc p1 on abc.p_partkey = p1.p_partkey PREHOOK: type: QUERY POSTHOOK: query: -- 14. testPTFJoinWithWindowingWithCount explain extended select abc.p_mfgr, abc.p_name, rank() over (distribute by abc.p_mfgr sort by abc.p_name) as r, dense_rank() over (distribute by abc.p_mfgr sort by abc.p_name) as dr, count(abc.p_name) over (distribute by abc.p_mfgr sort by abc.p_name) as cd, abc.p_retailprice, sum(abc.p_retailprice) over (distribute by abc.p_mfgr sort by abc.p_name rows between unbounded preceding and current row) as s1, abc.p_size, abc.p_size - lag(abc.p_size,1,abc.p_size) over (distribute by abc.p_mfgr sort by abc.p_name) as deltaSz from noop(on part_orc partition by p_mfgr order by p_name ) abc join part_orc p1 on abc.p_partkey = p1.p_partkey POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: TOK_QUERY TOK_FROM TOK_JOIN TOK_PTBLFUNCTION noop abc TOK_TABREF TOK_TABNAME part_orc TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name TOK_TABREF TOK_TABNAME part_orc p1 = . TOK_TABLE_OR_COL abc p_partkey . TOK_TABLE_OR_COL p1 p_partkey TOK_INSERT TOK_DESTINATION TOK_DIR TOK_TMP_FILE TOK_SELECT TOK_SELEXPR . TOK_TABLE_OR_COL abc p_mfgr TOK_SELEXPR . TOK_TABLE_OR_COL abc p_name TOK_SELEXPR TOK_FUNCTION rank TOK_WINDOWSPEC TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY . TOK_TABLE_OR_COL abc p_mfgr TOK_SORTBY TOK_TABSORTCOLNAMEASC . TOK_TABLE_OR_COL abc p_name r TOK_SELEXPR TOK_FUNCTION dense_rank TOK_WINDOWSPEC TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY . TOK_TABLE_OR_COL abc p_mfgr TOK_SORTBY TOK_TABSORTCOLNAMEASC . TOK_TABLE_OR_COL abc p_name dr TOK_SELEXPR TOK_FUNCTION count . TOK_TABLE_OR_COL abc p_name TOK_WINDOWSPEC TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY . TOK_TABLE_OR_COL abc p_mfgr TOK_SORTBY TOK_TABSORTCOLNAMEASC . TOK_TABLE_OR_COL abc p_name cd TOK_SELEXPR . TOK_TABLE_OR_COL abc p_retailprice TOK_SELEXPR TOK_FUNCTION sum . TOK_TABLE_OR_COL abc p_retailprice TOK_WINDOWSPEC TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY . TOK_TABLE_OR_COL abc p_mfgr TOK_SORTBY TOK_TABSORTCOLNAMEASC . TOK_TABLE_OR_COL abc p_name TOK_WINDOWRANGE preceding unbounded current s1 TOK_SELEXPR . TOK_TABLE_OR_COL abc p_size TOK_SELEXPR - . TOK_TABLE_OR_COL abc p_size TOK_FUNCTION lag . TOK_TABLE_OR_COL abc p_size 1 . TOK_TABLE_OR_COL abc p_size TOK_WINDOWSPEC TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY . TOK_TABLE_OR_COL abc p_mfgr TOK_SORTBY TOK_TABSORTCOLNAMEASC . TOK_TABLE_OR_COL abc p_name deltaSz STAGE DEPENDENCIES: Stage-1 is a root stage Stage-2 depends on stages: Stage-1 Stage-3 depends on stages: Stage-2 Stage-0 depends on stages: Stage-3 STAGE PLANS: Stage: Stage-1 Map Reduce Map Operator Tree: TableScan alias: part_orc Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE GatherStats: false Reduce Output Operator key expressions: p_mfgr (type: string), p_name (type: string) sort order: ++ Map-reduce partition columns: p_mfgr (type: string) Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: p_partkey (type: int), p_size (type: int), p_retailprice (type: double) auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: part_orc input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat properties: COLUMN_STATS_ACCURATE true bucket_count -1 columns p_partkey,p_name,p_mfgr,p_brand,p_type,p_size,p_container,p_retailprice,p_comment columns.comments columns.types int:string:string:string:string:int:string:double:string #### A masked pattern was here #### name default.part_orc numFiles 1 numRows 26 rawDataSize 16042 serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde totalSize 2655 #### 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: COLUMN_STATS_ACCURATE true bucket_count -1 columns p_partkey,p_name,p_mfgr,p_brand,p_type,p_size,p_container,p_retailprice,p_comment columns.comments columns.types int:string:string:string:string:int:string:double:string #### A masked pattern was here #### name default.part_orc numFiles 1 numRows 26 rawDataSize 16042 serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde totalSize 2655 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.part_orc name: default.part_orc Truncated Path -> Alias: /part_orc [part_orc] Execution mode: vectorized Needs Tagging: false Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int), VALUE._col5 (type: double) outputColumnNames: _col0, _col1, _col2, _col5, _col7 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: part_orc output shape: _col0: int, _col1: string, _col2: string, _col5: int, _col7: double type: TABLE Partition table definition input alias: abc name: noop order by: _col1 output shape: _col0: int, _col1: string, _col2: string, _col5: int, _col7: double partition by: _col2 raw input shape: Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE Filter Operator isSamplingPred: false predicate: _col0 is not null (type: boolean) Statistics: Num rows: 13 Data size: 8021 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col0,_col1,_col2,_col5,_col7 columns.types int,string,string,int,double escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe TotalFiles: 1 GatherStats: false MultiFileSpray: false Stage: Stage-2 Map Reduce Map Operator Tree: TableScan GatherStats: false Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 13 Data size: 8021 Basic stats: COMPLETE Column stats: NONE tag: 0 value expressions: _col1 (type: string), _col2 (type: string), _col5 (type: int), _col7 (type: double) auto parallelism: false TableScan alias: p1 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: p_partkey is not null (type: boolean) Statistics: Num rows: 13 Data size: 8021 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: p_partkey (type: int) sort order: + Map-reduce partition columns: p_partkey (type: int) Statistics: Num rows: 13 Data size: 8021 Basic stats: COMPLETE Column stats: NONE tag: 1 auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: -mr-10002 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col0,_col1,_col2,_col5,_col7 columns.types int,string,string,int,double escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col0,_col1,_col2,_col5,_col7 columns.types int,string,string,int,double escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe #### A masked pattern was here #### Partition base file name: part_orc input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat properties: COLUMN_STATS_ACCURATE true bucket_count -1 columns p_partkey,p_name,p_mfgr,p_brand,p_type,p_size,p_container,p_retailprice,p_comment columns.comments columns.types int:string:string:string:string:int:string:double:string #### A masked pattern was here #### name default.part_orc numFiles 1 numRows 26 rawDataSize 16042 serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde totalSize 2655 #### 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: COLUMN_STATS_ACCURATE true bucket_count -1 columns p_partkey,p_name,p_mfgr,p_brand,p_type,p_size,p_container,p_retailprice,p_comment columns.comments columns.types int:string:string:string:string:int:string:double:string #### A masked pattern was here #### name default.part_orc numFiles 1 numRows 26 rawDataSize 16042 serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde totalSize 2655 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.part_orc name: default.part_orc Truncated Path -> Alias: /part_orc [p1] #### A masked pattern was here #### Needs Tagging: true Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 p_partkey (type: int) outputColumnNames: _col1, _col2, _col5, _col7 Statistics: Num rows: 14 Data size: 8823 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5,_col7 columns.types string,string,int,double escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe TotalFiles: 1 GatherStats: false MultiFileSpray: false Stage: Stage-3 Map Reduce Map Operator Tree: TableScan GatherStats: false Reduce Output Operator key expressions: _col2 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col2 (type: string) Statistics: Num rows: 14 Data size: 8823 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col5 (type: int), _col7 (type: double) auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: -mr-10003 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5,_col7 columns.types string,string,int,double escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5,_col7 columns.types string,string,int,double escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Truncated Path -> Alias: #### A masked pattern was here #### Needs Tagging: false Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int), VALUE._col5 (type: double) outputColumnNames: _col1, _col2, _col5, _col7 Statistics: Num rows: 14 Data size: 8823 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: ptf_0 output shape: _col1: string, _col2: string, _col5: int, _col7: double type: WINDOWING Windowing table definition input alias: ptf_1 name: windowingtablefunction order by: _col1 partition by: _col2 raw input shape: window functions: window function definition alias: rank_window_0 arguments: _col1 name: rank window function: GenericUDAFRankEvaluator window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true window function definition alias: dense_rank_window_1 arguments: _col1 name: dense_rank window function: GenericUDAFDenseRankEvaluator window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true window function definition alias: count_window_2 arguments: _col1 name: count window function: GenericUDAFCountEvaluator window frame: PRECEDING(MAX)~ window function definition alias: sum_window_3 arguments: _col7 name: sum window function: GenericUDAFSumDouble window frame: PRECEDING(MAX)~ window function definition alias: lag_window_4 arguments: _col5, 1, _col5 name: lag window function: GenericUDAFLagEvaluator window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true Statistics: Num rows: 14 Data size: 8823 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col2 (type: string), _col1 (type: string), rank_window_0 (type: int), dense_rank_window_1 (type: int), count_window_2 (type: bigint), _col7 (type: double), sum_window_3 (type: double), _col5 (type: int), (_col5 - lag_window_4) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 14 Data size: 8823 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 Statistics: Num rows: 14 Data size: 8823 Basic stats: COMPLETE Column stats: NONE #### 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,_col2,_col3,_col4,_col5,_col6,_col7,_col8 columns.types string:string:int:int:bigint:double:double:int:int escape.delim \ hive.serialization.extend.additional.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-0 Fetch Operator limit: -1 Processor Tree: ListSink PREHOOK: query: select abc.p_mfgr, abc.p_name, rank() over (distribute by abc.p_mfgr sort by abc.p_name) as r, dense_rank() over (distribute by abc.p_mfgr sort by abc.p_name) as dr, count(abc.p_name) over (distribute by abc.p_mfgr sort by abc.p_name) as cd, abc.p_retailprice, sum(abc.p_retailprice) over (distribute by abc.p_mfgr sort by abc.p_name rows between unbounded preceding and current row) as s1, abc.p_size, abc.p_size - lag(abc.p_size,1,abc.p_size) over (distribute by abc.p_mfgr sort by abc.p_name) as deltaSz from noop(on part_orc partition by p_mfgr order by p_name ) abc join part_orc p1 on abc.p_partkey = p1.p_partkey PREHOOK: type: QUERY PREHOOK: Input: default@part_orc #### A masked pattern was here #### POSTHOOK: query: select abc.p_mfgr, abc.p_name, rank() over (distribute by abc.p_mfgr sort by abc.p_name) as r, dense_rank() over (distribute by abc.p_mfgr sort by abc.p_name) as dr, count(abc.p_name) over (distribute by abc.p_mfgr sort by abc.p_name) as cd, abc.p_retailprice, sum(abc.p_retailprice) over (distribute by abc.p_mfgr sort by abc.p_name rows between unbounded preceding and current row) as s1, abc.p_size, abc.p_size - lag(abc.p_size,1,abc.p_size) over (distribute by abc.p_mfgr sort by abc.p_name) as deltaSz from noop(on part_orc partition by p_mfgr order by p_name ) abc join part_orc p1 on abc.p_partkey = p1.p_partkey POSTHOOK: type: QUERY POSTHOOK: Input: default@part_orc #### A masked pattern was here #### Manufacturer#1 almond antique burnished rose metallic 1 1 4 1173.15 1173.15 2 0 Manufacturer#1 almond antique burnished rose metallic 1 1 4 1173.15 2346.3 2 0 Manufacturer#1 almond antique burnished rose metallic 1 1 4 1173.15 3519.4500000000003 2 0 Manufacturer#1 almond antique burnished rose metallic 1 1 4 1173.15 4692.6 2 0 Manufacturer#1 almond antique chartreuse lavender yellow 5 2 5 1753.76 6446.360000000001 34 32 Manufacturer#1 almond antique salmon chartreuse burlywood 6 3 6 1602.59 8048.950000000001 6 -28 Manufacturer#1 almond aquamarine burnished black steel 7 4 7 1414.42 9463.37 28 22 Manufacturer#1 almond aquamarine pink moccasin thistle 8 5 8 1632.66 11096.03 42 14 Manufacturer#2 almond antique violet chocolate turquoise 1 1 1 1690.68 1690.68 14 0 Manufacturer#2 almond antique violet turquoise frosted 2 2 2 1800.7 3491.38 40 26 Manufacturer#2 almond aquamarine midnight light salmon 3 3 3 2031.98 5523.360000000001 2 -38 Manufacturer#2 almond aquamarine rose maroon antique 4 4 4 1698.66 7222.02 25 23 Manufacturer#2 almond aquamarine sandy cyan gainsboro 5 5 5 1701.6 8923.62 18 -7 Manufacturer#3 almond antique chartreuse khaki white 1 1 1 1671.68 1671.68 17 0 Manufacturer#3 almond antique forest lavender goldenrod 2 2 2 1190.27 2861.95 14 -3 Manufacturer#3 almond antique metallic orange dim 3 3 3 1410.39 4272.34 19 5 Manufacturer#3 almond antique misty red olive 4 4 4 1922.98 6195.32 1 -18 Manufacturer#3 almond antique olive coral navajo 5 5 5 1337.29 7532.61 45 44 Manufacturer#4 almond antique gainsboro frosted violet 1 1 1 1620.67 1620.67 10 0 Manufacturer#4 almond antique violet mint lemon 2 2 2 1375.42 2996.09 39 29 Manufacturer#4 almond aquamarine floral ivory bisque 3 3 3 1206.26 4202.35 27 -12 Manufacturer#4 almond aquamarine yellow dodger mint 4 4 4 1844.92 6047.27 7 -20 Manufacturer#4 almond azure aquamarine papaya violet 5 5 5 1290.35 7337.620000000001 12 5 Manufacturer#5 almond antique blue firebrick mint 1 1 1 1789.69 1789.69 31 0 Manufacturer#5 almond antique medium spring khaki 2 2 2 1611.66 3401.3500000000004 6 -25 Manufacturer#5 almond antique sky peru orange 3 3 3 1788.73 5190.08 2 -4 Manufacturer#5 almond aquamarine dodger light gainsboro 4 4 4 1018.1 6208.18 46 44 Manufacturer#5 almond azure blanched chiffon midnight 5 5 5 1464.48 7672.66 23 -23 PREHOOK: query: -- 15. testDistinctInSelectWithPTF explain extended select DISTINCT p_mfgr, p_name, p_size from noop(on part_orc partition by p_mfgr order by p_name) PREHOOK: type: QUERY POSTHOOK: query: -- 15. testDistinctInSelectWithPTF explain extended select DISTINCT p_mfgr, p_name, p_size from noop(on part_orc partition by p_mfgr order by p_name) POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: TOK_QUERY TOK_FROM TOK_PTBLFUNCTION noop TOK_TABREF TOK_TABNAME part_orc TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name TOK_INSERT TOK_DESTINATION TOK_DIR TOK_TMP_FILE TOK_SELECTDI TOK_SELEXPR TOK_TABLE_OR_COL p_mfgr TOK_SELEXPR TOK_TABLE_OR_COL p_name TOK_SELEXPR TOK_TABLE_OR_COL p_size STAGE DEPENDENCIES: Stage-1 is a root stage Stage-2 depends on stages: Stage-1 Stage-0 depends on stages: Stage-2 STAGE PLANS: Stage: Stage-1 Map Reduce Map Operator Tree: TableScan alias: part_orc Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE GatherStats: false Reduce Output Operator key expressions: p_mfgr (type: string), p_name (type: string) sort order: ++ Map-reduce partition columns: p_mfgr (type: string) Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: p_size (type: int) auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: part_orc input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat properties: COLUMN_STATS_ACCURATE true bucket_count -1 columns p_partkey,p_name,p_mfgr,p_brand,p_type,p_size,p_container,p_retailprice,p_comment columns.comments columns.types int:string:string:string:string:int:string:double:string #### A masked pattern was here #### name default.part_orc numFiles 1 numRows 26 rawDataSize 16042 serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde totalSize 2655 #### 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: COLUMN_STATS_ACCURATE true bucket_count -1 columns p_partkey,p_name,p_mfgr,p_brand,p_type,p_size,p_container,p_retailprice,p_comment columns.comments columns.types int:string:string:string:string:int:string:double:string #### A masked pattern was here #### name default.part_orc numFiles 1 numRows 26 rawDataSize 16042 serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde totalSize 2655 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.part_orc name: default.part_orc Truncated Path -> Alias: /part_orc [part_orc] Execution mode: vectorized Needs Tagging: false Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int) outputColumnNames: _col1, _col2, _col5 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: part_orc output shape: _col1: string, _col2: string, _col5: int type: TABLE Partition table definition input alias: ptf_1 name: noop order by: _col1 output shape: _col1: string, _col2: string, _col5: int partition by: _col2 raw input shape: Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col2 (type: string), _col1 (type: string), _col5 (type: int) outputColumnNames: _col2, _col1, _col5 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: _col2 (type: string), _col1 (type: string), _col5 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col0,_col1,_col2 columns.types string,string,int escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe TotalFiles: 1 GatherStats: false MultiFileSpray: false Stage: Stage-2 Map Reduce Map Operator Tree: TableScan GatherStats: false Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: int) Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE tag: -1 auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: -mr-10002 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col0,_col1,_col2 columns.types string,string,int escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col0,_col1,_col2 columns.types string,string,int escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Truncated Path -> Alias: #### A masked pattern was here #### Needs Tagging: false Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 13 Data size: 8021 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 Statistics: Num rows: 13 Data size: 8021 Basic stats: COMPLETE Column stats: NONE #### 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,_col2 columns.types string:string:int escape.delim \ hive.serialization.extend.additional.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-0 Fetch Operator limit: -1 Processor Tree: ListSink PREHOOK: query: select DISTINCT p_mfgr, p_name, p_size from noop(on part_orc partition by p_mfgr order by p_name) PREHOOK: type: QUERY PREHOOK: Input: default@part_orc #### A masked pattern was here #### POSTHOOK: query: select DISTINCT p_mfgr, p_name, p_size from noop(on part_orc partition by p_mfgr order by p_name) POSTHOOK: type: QUERY POSTHOOK: Input: default@part_orc #### A masked pattern was here #### Manufacturer#1 almond antique burnished rose metallic 2 Manufacturer#1 almond antique chartreuse lavender yellow 34 Manufacturer#1 almond antique salmon chartreuse burlywood 6 Manufacturer#1 almond aquamarine burnished black steel 28 Manufacturer#1 almond aquamarine pink moccasin thistle 42 Manufacturer#2 almond antique violet chocolate turquoise 14 Manufacturer#2 almond antique violet turquoise frosted 40 Manufacturer#2 almond aquamarine midnight light salmon 2 Manufacturer#2 almond aquamarine rose maroon antique 25 Manufacturer#2 almond aquamarine sandy cyan gainsboro 18 Manufacturer#3 almond antique chartreuse khaki white 17 Manufacturer#3 almond antique forest lavender goldenrod 14 Manufacturer#3 almond antique metallic orange dim 19 Manufacturer#3 almond antique misty red olive 1 Manufacturer#3 almond antique olive coral navajo 45 Manufacturer#4 almond antique gainsboro frosted violet 10 Manufacturer#4 almond antique violet mint lemon 39 Manufacturer#4 almond aquamarine floral ivory bisque 27 Manufacturer#4 almond aquamarine yellow dodger mint 7 Manufacturer#4 almond azure aquamarine papaya violet 12 Manufacturer#5 almond antique blue firebrick mint 31 Manufacturer#5 almond antique medium spring khaki 6 Manufacturer#5 almond antique sky peru orange 2 Manufacturer#5 almond aquamarine dodger light gainsboro 46 Manufacturer#5 almond azure blanched chiffon midnight 23 PREHOOK: query: -- 16. testViewAsTableInputToPTF create view IF NOT EXISTS mfgr_price_view as select p_mfgr, p_brand, sum(p_retailprice) as s from part_orc group by p_mfgr, p_brand PREHOOK: type: CREATEVIEW PREHOOK: Input: default@part_orc PREHOOK: Output: database:default PREHOOK: Output: default@mfgr_price_view POSTHOOK: query: -- 16. testViewAsTableInputToPTF create view IF NOT EXISTS mfgr_price_view as select p_mfgr, p_brand, sum(p_retailprice) as s from part_orc group by p_mfgr, p_brand POSTHOOK: type: CREATEVIEW POSTHOOK: Input: default@part_orc POSTHOOK: Output: database:default POSTHOOK: Output: default@mfgr_price_view PREHOOK: query: explain extended select p_mfgr, p_brand, s, sum(s) over w1 as s1 from noop(on mfgr_price_view partition by p_mfgr order by p_mfgr) window w1 as ( partition by p_mfgr order by p_brand rows between 2 preceding and current row) PREHOOK: type: QUERY POSTHOOK: query: explain extended select p_mfgr, p_brand, s, sum(s) over w1 as s1 from noop(on mfgr_price_view partition by p_mfgr order by p_mfgr) window w1 as ( partition by p_mfgr order by p_brand rows between 2 preceding and current row) POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: TOK_QUERY TOK_FROM TOK_PTBLFUNCTION noop TOK_TABREF TOK_TABNAME mfgr_price_view TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_mfgr TOK_INSERT TOK_DESTINATION TOK_DIR TOK_TMP_FILE TOK_SELECT TOK_SELEXPR TOK_TABLE_OR_COL p_mfgr TOK_SELEXPR TOK_TABLE_OR_COL p_brand TOK_SELEXPR TOK_TABLE_OR_COL s TOK_SELEXPR TOK_FUNCTION sum TOK_TABLE_OR_COL s TOK_WINDOWSPEC w1 s1 window TOK_WINDOWDEF w1 TOK_WINDOWSPEC TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_brand TOK_WINDOWRANGE preceding 2 current STAGE DEPENDENCIES: Stage-1 is a root stage Stage-2 depends on stages: Stage-1 Stage-0 depends on stages: Stage-2 STAGE PLANS: Stage: Stage-1 Map Reduce Map Operator Tree: TableScan alias: part_orc Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator expressions: p_mfgr (type: string), p_brand (type: string), p_retailprice (type: double) outputColumnNames: p_mfgr, p_brand, p_retailprice Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(p_retailprice) keys: p_mfgr (type: string), p_brand (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col2 (type: double) auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: part_orc input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat properties: COLUMN_STATS_ACCURATE true bucket_count -1 columns p_partkey,p_name,p_mfgr,p_brand,p_type,p_size,p_container,p_retailprice,p_comment columns.comments columns.types int:string:string:string:string:int:string:double:string #### A masked pattern was here #### name default.part_orc numFiles 1 numRows 26 rawDataSize 16042 serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde totalSize 2655 #### 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: COLUMN_STATS_ACCURATE true bucket_count -1 columns p_partkey,p_name,p_mfgr,p_brand,p_type,p_size,p_container,p_retailprice,p_comment columns.comments columns.types int:string:string:string:string:int:string:double:string #### A masked pattern was here #### name default.part_orc numFiles 1 numRows 26 rawDataSize 16042 serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde totalSize 2655 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.part_orc name: default.part_orc Truncated Path -> Alias: /part_orc [mfgr_price_view:part_orc] Execution mode: vectorized Needs Tagging: false Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0) keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 13 Data size: 8021 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: mfgr_price_view output shape: _col0: string, _col1: string, _col2: double type: TABLE Partition table definition input alias: ptf_1 name: noop order by: _col0 output shape: _col0: string, _col1: string, _col2: double partition by: _col0 raw input shape: Statistics: Num rows: 13 Data size: 8021 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col0,_col1,_col2 columns.types string,string,double escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe TotalFiles: 1 GatherStats: false MultiFileSpray: false Stage: Stage-2 Map Reduce Map Operator Tree: TableScan GatherStats: false Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 13 Data size: 8021 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col2 (type: double) auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: -mr-10002 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col0,_col1,_col2 columns.types string,string,double escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col0,_col1,_col2 columns.types string,string,double escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Truncated Path -> Alias: #### A masked pattern was here #### Needs Tagging: false Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), VALUE._col0 (type: double) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 13 Data size: 8021 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: ptf_0 output shape: _col0: string, _col1: string, _col2: double type: WINDOWING Windowing table definition input alias: ptf_1 name: windowingtablefunction order by: _col1 partition by: _col0 raw input shape: window functions: window function definition alias: sum_window_0 arguments: _col2 name: sum window function: GenericUDAFSumDouble window frame: PRECEDING(2)~ Statistics: Num rows: 13 Data size: 8021 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: double), sum_window_0 (type: double) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 13 Data size: 8021 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 Statistics: Num rows: 13 Data size: 8021 Basic stats: COMPLETE Column stats: NONE #### 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,_col2,_col3 columns.types string:string:double:double escape.delim \ hive.serialization.extend.additional.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-0 Fetch Operator limit: -1 Processor Tree: ListSink PREHOOK: query: select p_mfgr, p_brand, s, sum(s) over w1 as s1 from noop(on mfgr_price_view partition by p_mfgr order by p_mfgr) window w1 as ( partition by p_mfgr order by p_brand rows between 2 preceding and current row) PREHOOK: type: QUERY PREHOOK: Input: default@mfgr_price_view PREHOOK: Input: default@part_orc #### A masked pattern was here #### POSTHOOK: query: select p_mfgr, p_brand, s, sum(s) over w1 as s1 from noop(on mfgr_price_view partition by p_mfgr order by p_mfgr) window w1 as ( partition by p_mfgr order by p_brand rows between 2 preceding and current row) POSTHOOK: type: QUERY POSTHOOK: Input: default@mfgr_price_view POSTHOOK: Input: default@part_orc #### A masked pattern was here #### Manufacturer#1 Brand#12 4800.84 4800.84 Manufacturer#1 Brand#14 2346.3 7147.14 Manufacturer#1 Brand#15 1602.59 8749.73 Manufacturer#2 Brand#22 3491.38 3491.38 Manufacturer#2 Brand#23 2031.98 5523.360000000001 Manufacturer#2 Brand#24 1698.66 7222.02 Manufacturer#2 Brand#25 1701.6 5432.240000000001 Manufacturer#3 Brand#31 1671.68 1671.68 Manufacturer#3 Brand#32 3333.37 5005.05 Manufacturer#3 Brand#34 1337.29 6342.34 Manufacturer#3 Brand#35 1190.27 5860.93 Manufacturer#4 Brand#41 4755.9400000000005 4755.9400000000005 Manufacturer#4 Brand#42 2581.6800000000003 7337.620000000001 Manufacturer#5 Brand#51 1611.66 1611.66 Manufacturer#5 Brand#52 3254.17 4865.83 Manufacturer#5 Brand#53 2806.83 7672.66 PREHOOK: query: -- 17. testMultipleInserts2SWQsWithPTF CREATE TABLE part_4( p_mfgr STRING, p_name STRING, p_size INT, r INT, dr INT, s DOUBLE) PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@part_4 POSTHOOK: query: -- 17. testMultipleInserts2SWQsWithPTF CREATE TABLE part_4( p_mfgr STRING, p_name STRING, p_size INT, r INT, dr INT, s DOUBLE) POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@part_4 PREHOOK: query: CREATE TABLE part_5( p_mfgr STRING, p_name STRING, p_size INT, s2 INT, r INT, dr INT, cud DOUBLE, fv1 INT) PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@part_5 POSTHOOK: query: CREATE TABLE part_5( p_mfgr STRING, p_name STRING, p_size INT, s2 INT, r INT, dr INT, cud DOUBLE, fv1 INT) POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@part_5 PREHOOK: query: explain extended from noop(on part_orc partition by p_mfgr order by p_name) INSERT OVERWRITE TABLE part_4 select p_mfgr, p_name, p_size, rank() over (distribute by p_mfgr sort by p_name) as r, dense_rank() over (distribute by p_mfgr sort by p_name) as dr, sum(p_retailprice) over (distribute by p_mfgr sort by p_name rows between unbounded preceding and current row) as s INSERT OVERWRITE TABLE part_5 select p_mfgr,p_name, p_size, round(sum(p_size) over (distribute by p_mfgr sort by p_size range between 5 preceding and current row),1) as s2, rank() over (distribute by p_mfgr sort by p_mfgr, p_name) as r, dense_rank() over (distribute by p_mfgr sort by p_mfgr, p_name) as dr, cume_dist() over (distribute by p_mfgr sort by p_mfgr, p_name) as cud, first_value(p_size, true) over w1 as fv1 window w1 as (distribute by p_mfgr sort by p_mfgr, p_name rows between 2 preceding and 2 following) PREHOOK: type: QUERY POSTHOOK: query: explain extended from noop(on part_orc partition by p_mfgr order by p_name) INSERT OVERWRITE TABLE part_4 select p_mfgr, p_name, p_size, rank() over (distribute by p_mfgr sort by p_name) as r, dense_rank() over (distribute by p_mfgr sort by p_name) as dr, sum(p_retailprice) over (distribute by p_mfgr sort by p_name rows between unbounded preceding and current row) as s INSERT OVERWRITE TABLE part_5 select p_mfgr,p_name, p_size, round(sum(p_size) over (distribute by p_mfgr sort by p_size range between 5 preceding and current row),1) as s2, rank() over (distribute by p_mfgr sort by p_mfgr, p_name) as r, dense_rank() over (distribute by p_mfgr sort by p_mfgr, p_name) as dr, cume_dist() over (distribute by p_mfgr sort by p_mfgr, p_name) as cud, first_value(p_size, true) over w1 as fv1 window w1 as (distribute by p_mfgr sort by p_mfgr, p_name rows between 2 preceding and 2 following) POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: TOK_QUERY TOK_FROM TOK_PTBLFUNCTION noop TOK_TABREF TOK_TABNAME part_orc TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name TOK_INSERT TOK_DESTINATION TOK_TAB TOK_TABNAME part_4 TOK_SELECT TOK_SELEXPR TOK_TABLE_OR_COL p_mfgr TOK_SELEXPR TOK_TABLE_OR_COL p_name TOK_SELEXPR TOK_TABLE_OR_COL p_size TOK_SELEXPR TOK_FUNCTION rank TOK_WINDOWSPEC TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_SORTBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name r TOK_SELEXPR TOK_FUNCTION dense_rank TOK_WINDOWSPEC TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_SORTBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name dr TOK_SELEXPR TOK_FUNCTION sum TOK_TABLE_OR_COL p_retailprice TOK_WINDOWSPEC TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_SORTBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name TOK_WINDOWRANGE preceding unbounded current s TOK_INSERT TOK_DESTINATION TOK_TAB TOK_TABNAME part_5 TOK_SELECT TOK_SELEXPR TOK_TABLE_OR_COL p_mfgr TOK_SELEXPR TOK_TABLE_OR_COL p_name TOK_SELEXPR TOK_TABLE_OR_COL p_size TOK_SELEXPR TOK_FUNCTION round TOK_FUNCTION sum TOK_TABLE_OR_COL p_size TOK_WINDOWSPEC TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_SORTBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_size TOK_WINDOWVALUES preceding 5 current 1 s2 TOK_SELEXPR TOK_FUNCTION rank TOK_WINDOWSPEC TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_SORTBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_mfgr TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name r TOK_SELEXPR TOK_FUNCTION dense_rank TOK_WINDOWSPEC TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_SORTBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_mfgr TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name dr TOK_SELEXPR TOK_FUNCTION cume_dist TOK_WINDOWSPEC TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_SORTBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_mfgr TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name cud TOK_SELEXPR TOK_FUNCTION first_value TOK_TABLE_OR_COL p_size true TOK_WINDOWSPEC w1 fv1 window TOK_WINDOWDEF w1 TOK_WINDOWSPEC TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_SORTBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_mfgr TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name TOK_WINDOWRANGE preceding 2 following 2 STAGE DEPENDENCIES: Stage-2 is a root stage Stage-3 depends on stages: Stage-2 Stage-0 depends on stages: Stage-3 Stage-4 depends on stages: Stage-0 Stage-5 depends on stages: Stage-2 Stage-6 depends on stages: Stage-5 Stage-1 depends on stages: Stage-6 Stage-7 depends on stages: Stage-1 STAGE PLANS: Stage: Stage-2 Map Reduce Map Operator Tree: TableScan alias: part_orc Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE GatherStats: false Reduce Output Operator key expressions: p_mfgr (type: string), p_name (type: string) sort order: ++ Map-reduce partition columns: p_mfgr (type: string) Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: p_size (type: int), p_retailprice (type: double) auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: part_orc input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat properties: COLUMN_STATS_ACCURATE true bucket_count -1 columns p_partkey,p_name,p_mfgr,p_brand,p_type,p_size,p_container,p_retailprice,p_comment columns.comments columns.types int:string:string:string:string:int:string:double:string #### A masked pattern was here #### name default.part_orc numFiles 1 numRows 26 rawDataSize 16042 serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde totalSize 2655 #### 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: COLUMN_STATS_ACCURATE true bucket_count -1 columns p_partkey,p_name,p_mfgr,p_brand,p_type,p_size,p_container,p_retailprice,p_comment columns.comments columns.types int:string:string:string:string:int:string:double:string #### A masked pattern was here #### name default.part_orc numFiles 1 numRows 26 rawDataSize 16042 serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde totalSize 2655 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.part_orc name: default.part_orc Truncated Path -> Alias: /part_orc [part_orc] Execution mode: vectorized Needs Tagging: false Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int), VALUE._col5 (type: double) outputColumnNames: _col1, _col2, _col5, _col7 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: part_orc output shape: _col1: string, _col2: string, _col5: int, _col7: double type: TABLE Partition table definition input alias: ptf_1 name: noop order by: _col1 output shape: _col1: string, _col2: string, _col5: int, _col7: double partition by: _col2 raw input shape: Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5,_col7 columns.types string,string,int,double escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe TotalFiles: 1 GatherStats: false MultiFileSpray: false File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5,_col7 columns.types string,string,int,double escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe TotalFiles: 1 GatherStats: false MultiFileSpray: false Stage: Stage-3 Map Reduce Map Operator Tree: TableScan GatherStats: false Reduce Output Operator key expressions: _col2 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col2 (type: string) Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col5 (type: int), _col7 (type: double) auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: -mr-10002 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5,_col7 columns.types string,string,int,double escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5,_col7 columns.types string,string,int,double escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Truncated Path -> Alias: #### A masked pattern was here #### Needs Tagging: false Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int), VALUE._col5 (type: double) outputColumnNames: _col1, _col2, _col5, _col7 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: ptf_0 output shape: _col1: string, _col2: string, _col5: int, _col7: double type: WINDOWING Windowing table definition input alias: ptf_1 name: windowingtablefunction order by: _col1 partition by: _col2 raw input shape: window functions: window function definition alias: rank_window_0 arguments: _col1 name: rank window function: GenericUDAFRankEvaluator window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true window function definition alias: dense_rank_window_1 arguments: _col1 name: dense_rank window function: GenericUDAFDenseRankEvaluator window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true window function definition alias: sum_window_2 arguments: _col7 name: sum window function: GenericUDAFSumDouble window frame: PRECEDING(MAX)~ Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col2 (type: string), _col1 (type: string), _col5 (type: int), rank_window_0 (type: int), dense_rank_window_1 (type: int), sum_window_2 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 columns p_mfgr,p_name,p_size,r,dr,s columns.comments columns.types string:string:int:int:int:double #### A masked pattern was here #### name default.part_4 serialization.ddl struct part_4 { string p_mfgr, string p_name, i32 p_size, i32 r, i32 dr, double s} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.part_4 TotalFiles: 1 GatherStats: true MultiFileSpray: false Stage: Stage-0 Move Operator tables: replace: true #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 columns p_mfgr,p_name,p_size,r,dr,s columns.comments columns.types string:string:int:int:int:double #### A masked pattern was here #### name default.part_4 serialization.ddl struct part_4 { string p_mfgr, string p_name, i32 p_size, i32 r, i32 dr, double s} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.part_4 Stage: Stage-4 Stats-Aggr Operator #### A masked pattern was here #### Stage: Stage-5 Map Reduce Map Operator Tree: TableScan GatherStats: false Reduce Output Operator key expressions: _col2 (type: string), _col5 (type: int) sort order: ++ Map-reduce partition columns: _col2 (type: string) Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col1 (type: string) auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: -mr-10003 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5,_col7 columns.types string,string,int,double escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5,_col7 columns.types string,string,int,double escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Truncated Path -> Alias: #### A masked pattern was here #### Needs Tagging: false Reduce Operator Tree: Select Operator expressions: VALUE._col1 (type: string), KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: int) outputColumnNames: _col1, _col2, _col5 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: ptf_0 output shape: _col1: string, _col2: string, _col5: int type: WINDOWING Windowing table definition input alias: ptf_1 name: windowingtablefunction order by: _col5 partition by: _col2 raw input shape: window functions: window function definition alias: sum_window_0 arguments: _col5 name: sum window function: GenericUDAFSumLong window frame: PRECEDING(5)~ Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: string), _col2 (type: string), _col5 (type: int), sum_window_0 (type: bigint) outputColumnNames: _col1, _col2, _col5, sum_window_0 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5,sum_window_0 columns.types string,string,int,bigint escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe TotalFiles: 1 GatherStats: false MultiFileSpray: false Stage: Stage-6 Map Reduce Map Operator Tree: TableScan GatherStats: false Reduce Output Operator key expressions: _col2 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col2 (type: string) Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: sum_window_0 (type: bigint), _col5 (type: int) auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: -mr-10004 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5,sum_window_0 columns.types string,string,int,bigint escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5,sum_window_0 columns.types string,string,int,bigint escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Truncated Path -> Alias: #### A masked pattern was here #### Needs Tagging: false Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: bigint), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col4 (type: int) outputColumnNames: _col0, _col2, _col3, _col6 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: ptf_0 output shape: _col0: bigint, _col2: string, _col3: string, _col6: int type: WINDOWING Windowing table definition input alias: ptf_1 name: windowingtablefunction order by: _col3, _col2 partition by: _col3 raw input shape: window functions: window function definition alias: rank_window_1 arguments: _col3, _col2 name: rank window function: GenericUDAFRankEvaluator window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true window function definition alias: dense_rank_window_2 arguments: _col3, _col2 name: dense_rank window function: GenericUDAFDenseRankEvaluator window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true window function definition alias: cume_dist_window_3 arguments: _col3, _col2 name: cume_dist window function: GenericUDAFCumeDistEvaluator window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true window function definition alias: first_value_window_4 arguments: _col6, true name: first_value window function: GenericUDAFFirstValueEvaluator window frame: PRECEDING(2)~FOLLOWING(2) Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col3 (type: string), _col2 (type: string), _col6 (type: int), UDFToInteger(round(_col0, 1)) (type: int), rank_window_1 (type: int), dense_rank_window_2 (type: int), cume_dist_window_3 (type: double), first_value_window_4 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 2 #### A masked pattern was here #### NumFilesPerFileSink: 1 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 columns p_mfgr,p_name,p_size,s2,r,dr,cud,fv1 columns.comments columns.types string:string:int:int:int:int:double:int #### A masked pattern was here #### name default.part_5 serialization.ddl struct part_5 { string p_mfgr, string p_name, i32 p_size, i32 s2, i32 r, i32 dr, double cud, i32 fv1} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.part_5 TotalFiles: 1 GatherStats: true MultiFileSpray: false Stage: Stage-1 Move Operator tables: replace: true #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 columns p_mfgr,p_name,p_size,s2,r,dr,cud,fv1 columns.comments columns.types string:string:int:int:int:int:double:int #### A masked pattern was here #### name default.part_5 serialization.ddl struct part_5 { string p_mfgr, string p_name, i32 p_size, i32 s2, i32 r, i32 dr, double cud, i32 fv1} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.part_5 Stage: Stage-7 Stats-Aggr Operator #### A masked pattern was here #### PREHOOK: query: from noop(on part_orc partition by p_mfgr order by p_name) INSERT OVERWRITE TABLE part_4 select p_mfgr, p_name, p_size, rank() over (distribute by p_mfgr sort by p_name) as r, dense_rank() over (distribute by p_mfgr sort by p_name) as dr, sum(p_retailprice) over (distribute by p_mfgr sort by p_name rows between unbounded preceding and current row) as s INSERT OVERWRITE TABLE part_5 select p_mfgr,p_name, p_size, round(sum(p_size) over (distribute by p_mfgr sort by p_size range between 5 preceding and current row),1) as s2, rank() over (distribute by p_mfgr sort by p_mfgr, p_name) as r, dense_rank() over (distribute by p_mfgr sort by p_mfgr, p_name) as dr, cume_dist() over (distribute by p_mfgr sort by p_mfgr, p_name) as cud, first_value(p_size, true) over w1 as fv1 window w1 as (distribute by p_mfgr sort by p_mfgr, p_name rows between 2 preceding and 2 following) PREHOOK: type: QUERY PREHOOK: Input: default@part_orc PREHOOK: Output: default@part_4 PREHOOK: Output: default@part_5 POSTHOOK: query: from noop(on part_orc partition by p_mfgr order by p_name) INSERT OVERWRITE TABLE part_4 select p_mfgr, p_name, p_size, rank() over (distribute by p_mfgr sort by p_name) as r, dense_rank() over (distribute by p_mfgr sort by p_name) as dr, sum(p_retailprice) over (distribute by p_mfgr sort by p_name rows between unbounded preceding and current row) as s INSERT OVERWRITE TABLE part_5 select p_mfgr,p_name, p_size, round(sum(p_size) over (distribute by p_mfgr sort by p_size range between 5 preceding and current row),1) as s2, rank() over (distribute by p_mfgr sort by p_mfgr, p_name) as r, dense_rank() over (distribute by p_mfgr sort by p_mfgr, p_name) as dr, cume_dist() over (distribute by p_mfgr sort by p_mfgr, p_name) as cud, first_value(p_size, true) over w1 as fv1 window w1 as (distribute by p_mfgr sort by p_mfgr, p_name rows between 2 preceding and 2 following) POSTHOOK: type: QUERY POSTHOOK: Input: default@part_orc POSTHOOK: Output: default@part_4 POSTHOOK: Output: default@part_5 POSTHOOK: Lineage: part_4.dr SCRIPT [(part_orc)part_orc.FieldSchema(name:p_partkey, type:int, comment:null), (part_orc)part_orc.FieldSchema(name:p_name, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_mfgr, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_brand, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_type, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_size, type:int, comment:null), (part_orc)part_orc.FieldSchema(name:p_container, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_retailprice, type:double, comment:null), (part_orc)part_orc.FieldSchema(name:p_comment, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:BLOCK__OFFSET__INSIDE__FILE, type:bigint, comment:), (part_orc)part_orc.FieldSchema(name:INPUT__FILE__NAME, type:string, comment:), (part_orc)part_orc.FieldSchema(name:ROW__ID, type:struct, comment:), ] POSTHOOK: Lineage: part_4.p_mfgr SCRIPT [(part_orc)part_orc.FieldSchema(name:p_partkey, type:int, comment:null), (part_orc)part_orc.FieldSchema(name:p_name, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_mfgr, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_brand, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_type, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_size, type:int, comment:null), (part_orc)part_orc.FieldSchema(name:p_container, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_retailprice, type:double, comment:null), (part_orc)part_orc.FieldSchema(name:p_comment, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:BLOCK__OFFSET__INSIDE__FILE, type:bigint, comment:), (part_orc)part_orc.FieldSchema(name:INPUT__FILE__NAME, type:string, comment:), (part_orc)part_orc.FieldSchema(name:ROW__ID, type:struct, comment:), ] POSTHOOK: Lineage: part_4.p_name SCRIPT [(part_orc)part_orc.FieldSchema(name:p_partkey, type:int, comment:null), (part_orc)part_orc.FieldSchema(name:p_name, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_mfgr, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_brand, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_type, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_size, type:int, comment:null), (part_orc)part_orc.FieldSchema(name:p_container, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_retailprice, type:double, comment:null), (part_orc)part_orc.FieldSchema(name:p_comment, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:BLOCK__OFFSET__INSIDE__FILE, type:bigint, comment:), (part_orc)part_orc.FieldSchema(name:INPUT__FILE__NAME, type:string, comment:), (part_orc)part_orc.FieldSchema(name:ROW__ID, type:struct, comment:), ] POSTHOOK: Lineage: part_4.p_size SCRIPT [(part_orc)part_orc.FieldSchema(name:p_partkey, type:int, comment:null), (part_orc)part_orc.FieldSchema(name:p_name, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_mfgr, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_brand, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_type, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_size, type:int, comment:null), (part_orc)part_orc.FieldSchema(name:p_container, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_retailprice, type:double, comment:null), (part_orc)part_orc.FieldSchema(name:p_comment, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:BLOCK__OFFSET__INSIDE__FILE, type:bigint, comment:), (part_orc)part_orc.FieldSchema(name:INPUT__FILE__NAME, type:string, comment:), (part_orc)part_orc.FieldSchema(name:ROW__ID, type:struct, comment:), ] POSTHOOK: Lineage: part_4.r SCRIPT [(part_orc)part_orc.FieldSchema(name:p_partkey, type:int, comment:null), (part_orc)part_orc.FieldSchema(name:p_name, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_mfgr, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_brand, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_type, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_size, type:int, comment:null), (part_orc)part_orc.FieldSchema(name:p_container, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_retailprice, type:double, comment:null), (part_orc)part_orc.FieldSchema(name:p_comment, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:BLOCK__OFFSET__INSIDE__FILE, type:bigint, comment:), (part_orc)part_orc.FieldSchema(name:INPUT__FILE__NAME, type:string, comment:), (part_orc)part_orc.FieldSchema(name:ROW__ID, type:struct, comment:), ] POSTHOOK: Lineage: part_4.s SCRIPT [(part_orc)part_orc.FieldSchema(name:p_partkey, type:int, comment:null), (part_orc)part_orc.FieldSchema(name:p_name, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_mfgr, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_brand, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_type, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_size, type:int, comment:null), (part_orc)part_orc.FieldSchema(name:p_container, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_retailprice, type:double, comment:null), (part_orc)part_orc.FieldSchema(name:p_comment, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:BLOCK__OFFSET__INSIDE__FILE, type:bigint, comment:), (part_orc)part_orc.FieldSchema(name:INPUT__FILE__NAME, type:string, comment:), (part_orc)part_orc.FieldSchema(name:ROW__ID, type:struct, comment:), ] POSTHOOK: Lineage: part_5.cud SCRIPT [(part_orc)part_orc.FieldSchema(name:p_partkey, type:int, comment:null), (part_orc)part_orc.FieldSchema(name:p_name, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_mfgr, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_brand, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_type, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_size, type:int, comment:null), (part_orc)part_orc.FieldSchema(name:p_container, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_retailprice, type:double, comment:null), (part_orc)part_orc.FieldSchema(name:p_comment, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:BLOCK__OFFSET__INSIDE__FILE, type:bigint, comment:), (part_orc)part_orc.FieldSchema(name:INPUT__FILE__NAME, type:string, comment:), (part_orc)part_orc.FieldSchema(name:ROW__ID, type:struct, comment:), ] POSTHOOK: Lineage: part_5.dr SCRIPT [(part_orc)part_orc.FieldSchema(name:p_partkey, type:int, comment:null), (part_orc)part_orc.FieldSchema(name:p_name, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_mfgr, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_brand, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_type, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_size, type:int, comment:null), (part_orc)part_orc.FieldSchema(name:p_container, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_retailprice, type:double, comment:null), (part_orc)part_orc.FieldSchema(name:p_comment, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:BLOCK__OFFSET__INSIDE__FILE, type:bigint, comment:), (part_orc)part_orc.FieldSchema(name:INPUT__FILE__NAME, type:string, comment:), (part_orc)part_orc.FieldSchema(name:ROW__ID, type:struct, comment:), ] POSTHOOK: Lineage: part_5.fv1 SCRIPT [(part_orc)part_orc.FieldSchema(name:p_partkey, type:int, comment:null), (part_orc)part_orc.FieldSchema(name:p_name, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_mfgr, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_brand, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_type, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_size, type:int, comment:null), (part_orc)part_orc.FieldSchema(name:p_container, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_retailprice, type:double, comment:null), (part_orc)part_orc.FieldSchema(name:p_comment, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:BLOCK__OFFSET__INSIDE__FILE, type:bigint, comment:), (part_orc)part_orc.FieldSchema(name:INPUT__FILE__NAME, type:string, comment:), (part_orc)part_orc.FieldSchema(name:ROW__ID, type:struct, comment:), ] POSTHOOK: Lineage: part_5.p_mfgr SCRIPT [(part_orc)part_orc.FieldSchema(name:p_partkey, type:int, comment:null), (part_orc)part_orc.FieldSchema(name:p_name, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_mfgr, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_brand, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_type, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_size, type:int, comment:null), (part_orc)part_orc.FieldSchema(name:p_container, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_retailprice, type:double, comment:null), (part_orc)part_orc.FieldSchema(name:p_comment, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:BLOCK__OFFSET__INSIDE__FILE, type:bigint, comment:), (part_orc)part_orc.FieldSchema(name:INPUT__FILE__NAME, type:string, comment:), (part_orc)part_orc.FieldSchema(name:ROW__ID, type:struct, comment:), ] POSTHOOK: Lineage: part_5.p_name SCRIPT [(part_orc)part_orc.FieldSchema(name:p_partkey, type:int, comment:null), (part_orc)part_orc.FieldSchema(name:p_name, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_mfgr, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_brand, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_type, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_size, type:int, comment:null), (part_orc)part_orc.FieldSchema(name:p_container, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_retailprice, type:double, comment:null), (part_orc)part_orc.FieldSchema(name:p_comment, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:BLOCK__OFFSET__INSIDE__FILE, type:bigint, comment:), (part_orc)part_orc.FieldSchema(name:INPUT__FILE__NAME, type:string, comment:), (part_orc)part_orc.FieldSchema(name:ROW__ID, type:struct, comment:), ] POSTHOOK: Lineage: part_5.p_size SCRIPT [(part_orc)part_orc.FieldSchema(name:p_partkey, type:int, comment:null), (part_orc)part_orc.FieldSchema(name:p_name, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_mfgr, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_brand, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_type, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_size, type:int, comment:null), (part_orc)part_orc.FieldSchema(name:p_container, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_retailprice, type:double, comment:null), (part_orc)part_orc.FieldSchema(name:p_comment, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:BLOCK__OFFSET__INSIDE__FILE, type:bigint, comment:), (part_orc)part_orc.FieldSchema(name:INPUT__FILE__NAME, type:string, comment:), (part_orc)part_orc.FieldSchema(name:ROW__ID, type:struct, comment:), ] POSTHOOK: Lineage: part_5.r SCRIPT [(part_orc)part_orc.FieldSchema(name:p_partkey, type:int, comment:null), (part_orc)part_orc.FieldSchema(name:p_name, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_mfgr, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_brand, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_type, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_size, type:int, comment:null), (part_orc)part_orc.FieldSchema(name:p_container, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_retailprice, type:double, comment:null), (part_orc)part_orc.FieldSchema(name:p_comment, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:BLOCK__OFFSET__INSIDE__FILE, type:bigint, comment:), (part_orc)part_orc.FieldSchema(name:INPUT__FILE__NAME, type:string, comment:), (part_orc)part_orc.FieldSchema(name:ROW__ID, type:struct, comment:), ] POSTHOOK: Lineage: part_5.s2 SCRIPT [(part_orc)part_orc.FieldSchema(name:p_partkey, type:int, comment:null), (part_orc)part_orc.FieldSchema(name:p_name, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_mfgr, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_brand, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_type, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_size, type:int, comment:null), (part_orc)part_orc.FieldSchema(name:p_container, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:p_retailprice, type:double, comment:null), (part_orc)part_orc.FieldSchema(name:p_comment, type:string, comment:null), (part_orc)part_orc.FieldSchema(name:BLOCK__OFFSET__INSIDE__FILE, type:bigint, comment:), (part_orc)part_orc.FieldSchema(name:INPUT__FILE__NAME, type:string, comment:), (part_orc)part_orc.FieldSchema(name:ROW__ID, type:struct, comment:), ] PREHOOK: query: select * from part_4 PREHOOK: type: QUERY PREHOOK: Input: default@part_4 #### A masked pattern was here #### POSTHOOK: query: select * from part_4 POSTHOOK: type: QUERY POSTHOOK: Input: default@part_4 #### A masked pattern was here #### Manufacturer#1 almond antique burnished rose metallic 2 1 1 1173.15 Manufacturer#1 almond antique burnished rose metallic 2 1 1 2346.3 Manufacturer#1 almond antique chartreuse lavender yellow 34 3 2 4100.06 Manufacturer#1 almond antique salmon chartreuse burlywood 6 4 3 5702.650000000001 Manufacturer#1 almond aquamarine burnished black steel 28 5 4 7117.070000000001 Manufacturer#1 almond aquamarine pink moccasin thistle 42 6 5 8749.730000000001 Manufacturer#2 almond antique violet chocolate turquoise 14 1 1 1690.68 Manufacturer#2 almond antique violet turquoise frosted 40 2 2 3491.38 Manufacturer#2 almond aquamarine midnight light salmon 2 3 3 5523.360000000001 Manufacturer#2 almond aquamarine rose maroon antique 25 4 4 7222.02 Manufacturer#2 almond aquamarine sandy cyan gainsboro 18 5 5 8923.62 Manufacturer#3 almond antique chartreuse khaki white 17 1 1 1671.68 Manufacturer#3 almond antique forest lavender goldenrod 14 2 2 2861.95 Manufacturer#3 almond antique metallic orange dim 19 3 3 4272.34 Manufacturer#3 almond antique misty red olive 1 4 4 6195.32 Manufacturer#3 almond antique olive coral navajo 45 5 5 7532.61 Manufacturer#4 almond antique gainsboro frosted violet 10 1 1 1620.67 Manufacturer#4 almond antique violet mint lemon 39 2 2 2996.09 Manufacturer#4 almond aquamarine floral ivory bisque 27 3 3 4202.35 Manufacturer#4 almond aquamarine yellow dodger mint 7 4 4 6047.27 Manufacturer#4 almond azure aquamarine papaya violet 12 5 5 7337.620000000001 Manufacturer#5 almond antique blue firebrick mint 31 1 1 1789.69 Manufacturer#5 almond antique medium spring khaki 6 2 2 3401.3500000000004 Manufacturer#5 almond antique sky peru orange 2 3 3 5190.08 Manufacturer#5 almond aquamarine dodger light gainsboro 46 4 4 6208.18 Manufacturer#5 almond azure blanched chiffon midnight 23 5 5 7672.66 PREHOOK: query: select * from part_5 PREHOOK: type: QUERY PREHOOK: Input: default@part_5 #### A masked pattern was here #### POSTHOOK: query: select * from part_5 POSTHOOK: type: QUERY POSTHOOK: Input: default@part_5 #### A masked pattern was here #### Manufacturer#1 almond antique burnished rose metallic 2 4 1 1 0.3333333333333333 2 Manufacturer#1 almond antique burnished rose metallic 2 4 1 1 0.3333333333333333 2 Manufacturer#1 almond antique chartreuse lavender yellow 34 34 3 2 0.5 2 Manufacturer#1 almond antique salmon chartreuse burlywood 6 10 4 3 0.6666666666666666 2 Manufacturer#1 almond aquamarine burnished black steel 28 28 5 4 0.8333333333333334 34 Manufacturer#1 almond aquamarine pink moccasin thistle 42 42 6 5 1.0 6 Manufacturer#2 almond antique violet chocolate turquoise 14 14 1 1 0.2 14 Manufacturer#2 almond antique violet turquoise frosted 40 40 2 2 0.4 14 Manufacturer#2 almond aquamarine midnight light salmon 2 2 3 3 0.6 14 Manufacturer#2 almond aquamarine rose maroon antique 25 25 4 4 0.8 40 Manufacturer#2 almond aquamarine sandy cyan gainsboro 18 32 5 5 1.0 2 Manufacturer#3 almond antique chartreuse khaki white 17 31 1 1 0.2 17 Manufacturer#3 almond antique forest lavender goldenrod 14 14 2 2 0.4 17 Manufacturer#3 almond antique metallic orange dim 19 50 3 3 0.6 17 Manufacturer#3 almond antique misty red olive 1 1 4 4 0.8 14 Manufacturer#3 almond antique olive coral navajo 45 45 5 5 1.0 19 Manufacturer#4 almond antique gainsboro frosted violet 10 17 1 1 0.2 10 Manufacturer#4 almond antique violet mint lemon 39 39 2 2 0.4 10 Manufacturer#4 almond aquamarine floral ivory bisque 27 27 3 3 0.6 10 Manufacturer#4 almond aquamarine yellow dodger mint 7 7 4 4 0.8 39 Manufacturer#4 almond azure aquamarine papaya violet 12 29 5 5 1.0 27 Manufacturer#5 almond antique blue firebrick mint 31 31 1 1 0.2 31 Manufacturer#5 almond antique medium spring khaki 6 8 2 2 0.4 31 Manufacturer#5 almond antique sky peru orange 2 2 3 3 0.6 31 Manufacturer#5 almond aquamarine dodger light gainsboro 46 46 4 4 0.8 6 Manufacturer#5 almond azure blanched chiffon midnight 23 23 5 5 1.0 2 PREHOOK: query: -- 18. testMulti2OperatorsFunctionChainWithMap explain extended select p_mfgr, p_name, rank() over (partition by p_mfgr,p_name) as r, dense_rank() over (partition by p_mfgr,p_name) as dr, p_size, sum(p_size) over (partition by p_mfgr,p_name rows between unbounded preceding and current row) as s1 from noop(on noopwithmap(on noop(on noop(on part_orc partition by p_mfgr order by p_mfgr) ) partition by p_mfgr,p_name order by p_mfgr,p_name) partition by p_mfgr,p_name order by p_mfgr,p_name) PREHOOK: type: QUERY POSTHOOK: query: -- 18. testMulti2OperatorsFunctionChainWithMap explain extended select p_mfgr, p_name, rank() over (partition by p_mfgr,p_name) as r, dense_rank() over (partition by p_mfgr,p_name) as dr, p_size, sum(p_size) over (partition by p_mfgr,p_name rows between unbounded preceding and current row) as s1 from noop(on noopwithmap(on noop(on noop(on part_orc partition by p_mfgr order by p_mfgr) ) partition by p_mfgr,p_name order by p_mfgr,p_name) partition by p_mfgr,p_name order by p_mfgr,p_name) POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: TOK_QUERY TOK_FROM TOK_PTBLFUNCTION noop TOK_PTBLFUNCTION noopwithmap TOK_PTBLFUNCTION noop TOK_PTBLFUNCTION noop TOK_TABREF TOK_TABNAME part_orc TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_mfgr TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_TABLE_OR_COL p_name TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_mfgr TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_TABLE_OR_COL p_name TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_mfgr TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name TOK_INSERT TOK_DESTINATION TOK_DIR TOK_TMP_FILE TOK_SELECT TOK_SELEXPR TOK_TABLE_OR_COL p_mfgr TOK_SELEXPR TOK_TABLE_OR_COL p_name TOK_SELEXPR TOK_FUNCTION rank TOK_WINDOWSPEC TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_TABLE_OR_COL p_name r TOK_SELEXPR TOK_FUNCTION dense_rank TOK_WINDOWSPEC TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_TABLE_OR_COL p_name dr TOK_SELEXPR TOK_TABLE_OR_COL p_size TOK_SELEXPR TOK_FUNCTION sum TOK_TABLE_OR_COL p_size TOK_WINDOWSPEC TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_TABLE_OR_COL p_name TOK_WINDOWRANGE preceding unbounded current s1 STAGE DEPENDENCIES: Stage-1 is a root stage Stage-2 depends on stages: Stage-1 Stage-3 depends on stages: Stage-2 Stage-0 depends on stages: Stage-3 STAGE PLANS: Stage: Stage-1 Map Reduce Map Operator Tree: TableScan alias: part_orc Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE GatherStats: false Reduce Output Operator key expressions: p_mfgr (type: string) sort order: + Map-reduce partition columns: p_mfgr (type: string) Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: p_name (type: string), p_size (type: int) auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: part_orc input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat properties: COLUMN_STATS_ACCURATE true bucket_count -1 columns p_partkey,p_name,p_mfgr,p_brand,p_type,p_size,p_container,p_retailprice,p_comment columns.comments columns.types int:string:string:string:string:int:string:double:string #### A masked pattern was here #### name default.part_orc numFiles 1 numRows 26 rawDataSize 16042 serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde totalSize 2655 #### 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: COLUMN_STATS_ACCURATE true bucket_count -1 columns p_partkey,p_name,p_mfgr,p_brand,p_type,p_size,p_container,p_retailprice,p_comment columns.comments columns.types int:string:string:string:string:int:string:double:string #### A masked pattern was here #### name default.part_orc numFiles 1 numRows 26 rawDataSize 16042 serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde totalSize 2655 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.part_orc name: default.part_orc Truncated Path -> Alias: /part_orc [part_orc] Execution mode: vectorized Needs Tagging: false Reduce Operator Tree: Select Operator expressions: VALUE._col1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col4 (type: int) outputColumnNames: _col1, _col2, _col5 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: part_orc output shape: _col1: string, _col2: string, _col5: int type: TABLE Partition table definition input alias: ptf_1 name: noop order by: _col2 output shape: _col1: string, _col2: string, _col5: int partition by: _col2 raw input shape: Partition table definition input alias: ptf_2 name: noop order by: _col2 output shape: _col1: string, _col2: string, _col5: int partition by: _col2 raw input shape: Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: ptf_0 output shape: _col1: string, _col2: string, _col5: int type: PTFCOMPONENT Partition table definition input alias: ptf_1 name: noopwithmap order by: _col2, _col1 output shape: _col1: string, _col2: string, _col5: int partition by: _col2, _col1 raw input shape: transforms raw input: true Partition table definition input alias: ptf_2 name: noop order by: _col2, _col1 output shape: _col1: string, _col2: string, _col5: int partition by: _col2, _col1 raw input shape: Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE Map-side function: true File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5 columns.types string,string,int escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe TotalFiles: 1 GatherStats: false MultiFileSpray: false Stage: Stage-2 Map Reduce Map Operator Tree: TableScan GatherStats: false Reduce Output Operator key expressions: _col2 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col2 (type: string), _col1 (type: string) Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col5 (type: int) auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: -mr-10002 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5 columns.types string,string,int escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5 columns.types string,string,int escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Truncated Path -> Alias: #### A masked pattern was here #### Needs Tagging: false Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int) outputColumnNames: _col1, _col2, _col5 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: ptf_0 output shape: _col1: string, _col2: string, _col5: int type: PTFCOMPONENT Partition table definition input alias: ptf_1 name: noopwithmap order by: _col2, _col1 output shape: _col1: string, _col2: string, _col5: int partition by: _col2, _col1 raw input shape: transforms raw input: true Partition table definition input alias: ptf_2 name: noop order by: _col2, _col1 output shape: _col1: string, _col2: string, _col5: int partition by: _col2, _col1 raw input shape: Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5 columns.types string,string,int escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe TotalFiles: 1 GatherStats: false MultiFileSpray: false Stage: Stage-3 Map Reduce Map Operator Tree: TableScan GatherStats: false Reduce Output Operator key expressions: _col2 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col2 (type: string), _col1 (type: string) Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col5 (type: int) auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: -mr-10003 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5 columns.types string,string,int escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5 columns.types string,string,int escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Truncated Path -> Alias: #### A masked pattern was here #### Needs Tagging: false Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int) outputColumnNames: _col1, _col2, _col5 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: ptf_0 output shape: _col1: string, _col2: string, _col5: int type: WINDOWING Windowing table definition input alias: ptf_1 name: windowingtablefunction order by: _col2, _col1 partition by: _col2, _col1 raw input shape: window functions: window function definition alias: rank_window_0 arguments: _col2, _col1 name: rank window function: GenericUDAFRankEvaluator window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true window function definition alias: dense_rank_window_1 arguments: _col2, _col1 name: dense_rank window function: GenericUDAFDenseRankEvaluator window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true window function definition alias: sum_window_2 arguments: _col5 name: sum window function: GenericUDAFSumLong window frame: PRECEDING(MAX)~ Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col2 (type: string), _col1 (type: string), rank_window_0 (type: int), dense_rank_window_1 (type: int), _col5 (type: int), sum_window_2 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE #### 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,_col2,_col3,_col4,_col5 columns.types string:string:int:int:int:bigint escape.delim \ hive.serialization.extend.additional.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-0 Fetch Operator limit: -1 Processor Tree: ListSink PREHOOK: query: select p_mfgr, p_name, rank() over (partition by p_mfgr,p_name) as r, dense_rank() over (partition by p_mfgr,p_name) as dr, p_size, sum(p_size) over (partition by p_mfgr,p_name rows between unbounded preceding and current row) as s1 from noop(on noopwithmap(on noop(on noop(on part_orc partition by p_mfgr order by p_mfgr) ) partition by p_mfgr,p_name order by p_mfgr,p_name) partition by p_mfgr,p_name order by p_mfgr,p_name) PREHOOK: type: QUERY PREHOOK: Input: default@part_orc #### A masked pattern was here #### POSTHOOK: query: select p_mfgr, p_name, rank() over (partition by p_mfgr,p_name) as r, dense_rank() over (partition by p_mfgr,p_name) as dr, p_size, sum(p_size) over (partition by p_mfgr,p_name rows between unbounded preceding and current row) as s1 from noop(on noopwithmap(on noop(on noop(on part_orc partition by p_mfgr order by p_mfgr) ) partition by p_mfgr,p_name order by p_mfgr,p_name) partition by p_mfgr,p_name order by p_mfgr,p_name) POSTHOOK: type: QUERY POSTHOOK: Input: default@part_orc #### A masked pattern was here #### Manufacturer#1 almond antique burnished rose metallic 1 1 2 2 Manufacturer#1 almond antique burnished rose metallic 1 1 2 4 Manufacturer#1 almond antique chartreuse lavender yellow 1 1 34 34 Manufacturer#1 almond antique salmon chartreuse burlywood 1 1 6 6 Manufacturer#1 almond aquamarine burnished black steel 1 1 28 28 Manufacturer#1 almond aquamarine pink moccasin thistle 1 1 42 42 Manufacturer#2 almond antique violet chocolate turquoise 1 1 14 14 Manufacturer#2 almond antique violet turquoise frosted 1 1 40 40 Manufacturer#2 almond aquamarine midnight light salmon 1 1 2 2 Manufacturer#2 almond aquamarine rose maroon antique 1 1 25 25 Manufacturer#2 almond aquamarine sandy cyan gainsboro 1 1 18 18 Manufacturer#3 almond antique chartreuse khaki white 1 1 17 17 Manufacturer#3 almond antique forest lavender goldenrod 1 1 14 14 Manufacturer#3 almond antique metallic orange dim 1 1 19 19 Manufacturer#3 almond antique misty red olive 1 1 1 1 Manufacturer#3 almond antique olive coral navajo 1 1 45 45 Manufacturer#4 almond antique gainsboro frosted violet 1 1 10 10 Manufacturer#4 almond antique violet mint lemon 1 1 39 39 Manufacturer#4 almond aquamarine floral ivory bisque 1 1 27 27 Manufacturer#4 almond aquamarine yellow dodger mint 1 1 7 7 Manufacturer#4 almond azure aquamarine papaya violet 1 1 12 12 Manufacturer#5 almond antique blue firebrick mint 1 1 31 31 Manufacturer#5 almond antique medium spring khaki 1 1 6 6 Manufacturer#5 almond antique sky peru orange 1 1 2 2 Manufacturer#5 almond aquamarine dodger light gainsboro 1 1 46 46 Manufacturer#5 almond azure blanched chiffon midnight 1 1 23 23 PREHOOK: query: -- 19. testMulti3OperatorsFunctionChain explain extended select p_mfgr, p_name, rank() over (partition by p_mfgr order by p_name) as r, dense_rank() over (partition by p_mfgr order by p_name) as dr, p_size, sum(p_size) over (partition by p_mfgr order by p_name rows between unbounded preceding and current row) as s1 from noop(on noop(on noop(on noop(on part_orc partition by p_mfgr order by p_mfgr) ) partition by p_mfgr,p_name order by p_mfgr,p_name) partition by p_mfgr order by p_mfgr ) PREHOOK: type: QUERY POSTHOOK: query: -- 19. testMulti3OperatorsFunctionChain explain extended select p_mfgr, p_name, rank() over (partition by p_mfgr order by p_name) as r, dense_rank() over (partition by p_mfgr order by p_name) as dr, p_size, sum(p_size) over (partition by p_mfgr order by p_name rows between unbounded preceding and current row) as s1 from noop(on noop(on noop(on noop(on part_orc partition by p_mfgr order by p_mfgr) ) partition by p_mfgr,p_name order by p_mfgr,p_name) partition by p_mfgr order by p_mfgr ) POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: TOK_QUERY TOK_FROM TOK_PTBLFUNCTION noop TOK_PTBLFUNCTION noop TOK_PTBLFUNCTION noop TOK_PTBLFUNCTION noop TOK_TABREF TOK_TABNAME part_orc TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_mfgr TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_TABLE_OR_COL p_name TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_mfgr TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_mfgr TOK_INSERT TOK_DESTINATION TOK_DIR TOK_TMP_FILE TOK_SELECT TOK_SELEXPR TOK_TABLE_OR_COL p_mfgr TOK_SELEXPR TOK_TABLE_OR_COL p_name TOK_SELEXPR TOK_FUNCTION rank TOK_WINDOWSPEC TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name r TOK_SELEXPR TOK_FUNCTION dense_rank TOK_WINDOWSPEC TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name dr TOK_SELEXPR TOK_TABLE_OR_COL p_size TOK_SELEXPR TOK_FUNCTION sum TOK_TABLE_OR_COL p_size TOK_WINDOWSPEC TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name TOK_WINDOWRANGE preceding unbounded current s1 STAGE DEPENDENCIES: Stage-1 is a root stage Stage-2 depends on stages: Stage-1 Stage-3 depends on stages: Stage-2 Stage-4 depends on stages: Stage-3 Stage-0 depends on stages: Stage-4 STAGE PLANS: Stage: Stage-1 Map Reduce Map Operator Tree: TableScan alias: part_orc Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE GatherStats: false Reduce Output Operator key expressions: p_mfgr (type: string) sort order: + Map-reduce partition columns: p_mfgr (type: string) Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: p_name (type: string), p_size (type: int) auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: part_orc input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat properties: COLUMN_STATS_ACCURATE true bucket_count -1 columns p_partkey,p_name,p_mfgr,p_brand,p_type,p_size,p_container,p_retailprice,p_comment columns.comments columns.types int:string:string:string:string:int:string:double:string #### A masked pattern was here #### name default.part_orc numFiles 1 numRows 26 rawDataSize 16042 serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde totalSize 2655 #### 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: COLUMN_STATS_ACCURATE true bucket_count -1 columns p_partkey,p_name,p_mfgr,p_brand,p_type,p_size,p_container,p_retailprice,p_comment columns.comments columns.types int:string:string:string:string:int:string:double:string #### A masked pattern was here #### name default.part_orc numFiles 1 numRows 26 rawDataSize 16042 serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde totalSize 2655 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.part_orc name: default.part_orc Truncated Path -> Alias: /part_orc [part_orc] Execution mode: vectorized Needs Tagging: false Reduce Operator Tree: Select Operator expressions: VALUE._col1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col4 (type: int) outputColumnNames: _col1, _col2, _col5 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: part_orc output shape: _col1: string, _col2: string, _col5: int type: TABLE Partition table definition input alias: ptf_1 name: noop order by: _col2 output shape: _col1: string, _col2: string, _col5: int partition by: _col2 raw input shape: Partition table definition input alias: ptf_2 name: noop order by: _col2 output shape: _col1: string, _col2: string, _col5: int partition by: _col2 raw input shape: Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5 columns.types string,string,int escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe TotalFiles: 1 GatherStats: false MultiFileSpray: false Stage: Stage-2 Map Reduce Map Operator Tree: TableScan GatherStats: false Reduce Output Operator key expressions: _col2 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col2 (type: string), _col1 (type: string) Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col5 (type: int) auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: -mr-10002 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5 columns.types string,string,int escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5 columns.types string,string,int escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Truncated Path -> Alias: #### A masked pattern was here #### Needs Tagging: false Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int) outputColumnNames: _col1, _col2, _col5 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: ptf_0 output shape: _col1: string, _col2: string, _col5: int type: PTFCOMPONENT Partition table definition input alias: ptf_1 name: noop order by: _col2, _col1 output shape: _col1: string, _col2: string, _col5: int partition by: _col2, _col1 raw input shape: Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5 columns.types string,string,int escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe TotalFiles: 1 GatherStats: false MultiFileSpray: false Stage: Stage-3 Map Reduce Map Operator Tree: TableScan GatherStats: false Reduce Output Operator key expressions: _col2 (type: string) sort order: + Map-reduce partition columns: _col2 (type: string) Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col1 (type: string), _col5 (type: int) auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: -mr-10003 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5 columns.types string,string,int escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5 columns.types string,string,int escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Truncated Path -> Alias: #### A masked pattern was here #### Needs Tagging: false Reduce Operator Tree: Select Operator expressions: VALUE._col1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col4 (type: int) outputColumnNames: _col1, _col2, _col5 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: ptf_0 output shape: _col1: string, _col2: string, _col5: int type: PTFCOMPONENT Partition table definition input alias: ptf_1 name: noop order by: _col2 output shape: _col1: string, _col2: string, _col5: int partition by: _col2 raw input shape: Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5 columns.types string,string,int escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe TotalFiles: 1 GatherStats: false MultiFileSpray: false Stage: Stage-4 Map Reduce Map Operator Tree: TableScan GatherStats: false Reduce Output Operator key expressions: _col2 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col2 (type: string) Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col5 (type: int) auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: -mr-10004 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5 columns.types string,string,int escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5 columns.types string,string,int escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Truncated Path -> Alias: #### A masked pattern was here #### Needs Tagging: false Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int) outputColumnNames: _col1, _col2, _col5 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: ptf_0 output shape: _col1: string, _col2: string, _col5: int type: WINDOWING Windowing table definition input alias: ptf_1 name: windowingtablefunction order by: _col1 partition by: _col2 raw input shape: window functions: window function definition alias: rank_window_0 arguments: _col1 name: rank window function: GenericUDAFRankEvaluator window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true window function definition alias: dense_rank_window_1 arguments: _col1 name: dense_rank window function: GenericUDAFDenseRankEvaluator window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true window function definition alias: sum_window_2 arguments: _col5 name: sum window function: GenericUDAFSumLong window frame: PRECEDING(MAX)~ Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col2 (type: string), _col1 (type: string), rank_window_0 (type: int), dense_rank_window_1 (type: int), _col5 (type: int), sum_window_2 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE #### 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,_col2,_col3,_col4,_col5 columns.types string:string:int:int:int:bigint escape.delim \ hive.serialization.extend.additional.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-0 Fetch Operator limit: -1 Processor Tree: ListSink PREHOOK: query: select p_mfgr, p_name, rank() over (partition by p_mfgr order by p_name) as r, dense_rank() over (partition by p_mfgr order by p_name) as dr, p_size, sum(p_size) over (partition by p_mfgr order by p_name rows between unbounded preceding and current row) as s1 from noop(on noop(on noop(on noop(on part_orc partition by p_mfgr order by p_mfgr) ) partition by p_mfgr,p_name order by p_mfgr,p_name) partition by p_mfgr order by p_mfgr ) PREHOOK: type: QUERY PREHOOK: Input: default@part_orc #### A masked pattern was here #### POSTHOOK: query: select p_mfgr, p_name, rank() over (partition by p_mfgr order by p_name) as r, dense_rank() over (partition by p_mfgr order by p_name) as dr, p_size, sum(p_size) over (partition by p_mfgr order by p_name rows between unbounded preceding and current row) as s1 from noop(on noop(on noop(on noop(on part_orc partition by p_mfgr order by p_mfgr) ) partition by p_mfgr,p_name order by p_mfgr,p_name) partition by p_mfgr order by p_mfgr ) POSTHOOK: type: QUERY POSTHOOK: Input: default@part_orc #### A masked pattern was here #### Manufacturer#1 almond antique burnished rose metallic 1 1 2 2 Manufacturer#1 almond antique burnished rose metallic 1 1 2 4 Manufacturer#1 almond antique chartreuse lavender yellow 3 2 34 38 Manufacturer#1 almond antique salmon chartreuse burlywood 4 3 6 44 Manufacturer#1 almond aquamarine burnished black steel 5 4 28 72 Manufacturer#1 almond aquamarine pink moccasin thistle 6 5 42 114 Manufacturer#2 almond antique violet chocolate turquoise 1 1 14 14 Manufacturer#2 almond antique violet turquoise frosted 2 2 40 54 Manufacturer#2 almond aquamarine midnight light salmon 3 3 2 56 Manufacturer#2 almond aquamarine rose maroon antique 4 4 25 81 Manufacturer#2 almond aquamarine sandy cyan gainsboro 5 5 18 99 Manufacturer#3 almond antique chartreuse khaki white 1 1 17 17 Manufacturer#3 almond antique forest lavender goldenrod 2 2 14 31 Manufacturer#3 almond antique metallic orange dim 3 3 19 50 Manufacturer#3 almond antique misty red olive 4 4 1 51 Manufacturer#3 almond antique olive coral navajo 5 5 45 96 Manufacturer#4 almond antique gainsboro frosted violet 1 1 10 10 Manufacturer#4 almond antique violet mint lemon 2 2 39 49 Manufacturer#4 almond aquamarine floral ivory bisque 3 3 27 76 Manufacturer#4 almond aquamarine yellow dodger mint 4 4 7 83 Manufacturer#4 almond azure aquamarine papaya violet 5 5 12 95 Manufacturer#5 almond antique blue firebrick mint 1 1 31 31 Manufacturer#5 almond antique medium spring khaki 2 2 6 37 Manufacturer#5 almond antique sky peru orange 3 3 2 39 Manufacturer#5 almond aquamarine dodger light gainsboro 4 4 46 85 Manufacturer#5 almond azure blanched chiffon midnight 5 5 23 108 PREHOOK: query: -- 20. testMultiOperatorChainWithNoWindowing explain extended select p_mfgr, p_name, rank() over (partition by p_mfgr order by p_name) as r, dense_rank() over (partition by p_mfgr order by p_name) as dr, p_size, sum(p_size) over (partition by p_mfgr order by p_name) as s1 from noop(on noop(on noop(on noop(on part_orc partition by p_mfgr,p_name order by p_mfgr,p_name) ) partition by p_mfgr order by p_mfgr)) PREHOOK: type: QUERY POSTHOOK: query: -- 20. testMultiOperatorChainWithNoWindowing explain extended select p_mfgr, p_name, rank() over (partition by p_mfgr order by p_name) as r, dense_rank() over (partition by p_mfgr order by p_name) as dr, p_size, sum(p_size) over (partition by p_mfgr order by p_name) as s1 from noop(on noop(on noop(on noop(on part_orc partition by p_mfgr,p_name order by p_mfgr,p_name) ) partition by p_mfgr order by p_mfgr)) POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: TOK_QUERY TOK_FROM TOK_PTBLFUNCTION noop TOK_PTBLFUNCTION noop TOK_PTBLFUNCTION noop TOK_PTBLFUNCTION noop TOK_TABREF TOK_TABNAME part_orc TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_TABLE_OR_COL p_name TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_mfgr TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_mfgr TOK_INSERT TOK_DESTINATION TOK_DIR TOK_TMP_FILE TOK_SELECT TOK_SELEXPR TOK_TABLE_OR_COL p_mfgr TOK_SELEXPR TOK_TABLE_OR_COL p_name TOK_SELEXPR TOK_FUNCTION rank TOK_WINDOWSPEC TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name r TOK_SELEXPR TOK_FUNCTION dense_rank TOK_WINDOWSPEC TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name dr TOK_SELEXPR TOK_TABLE_OR_COL p_size TOK_SELEXPR TOK_FUNCTION sum TOK_TABLE_OR_COL p_size TOK_WINDOWSPEC TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name s1 STAGE DEPENDENCIES: Stage-1 is a root stage Stage-2 depends on stages: Stage-1 Stage-3 depends on stages: Stage-2 Stage-0 depends on stages: Stage-3 STAGE PLANS: Stage: Stage-1 Map Reduce Map Operator Tree: TableScan alias: part_orc Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE GatherStats: false Reduce Output Operator key expressions: p_mfgr (type: string), p_name (type: string) sort order: ++ Map-reduce partition columns: p_mfgr (type: string), p_name (type: string) Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: p_size (type: int) auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: part_orc input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat properties: COLUMN_STATS_ACCURATE true bucket_count -1 columns p_partkey,p_name,p_mfgr,p_brand,p_type,p_size,p_container,p_retailprice,p_comment columns.comments columns.types int:string:string:string:string:int:string:double:string #### A masked pattern was here #### name default.part_orc numFiles 1 numRows 26 rawDataSize 16042 serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde totalSize 2655 #### 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: COLUMN_STATS_ACCURATE true bucket_count -1 columns p_partkey,p_name,p_mfgr,p_brand,p_type,p_size,p_container,p_retailprice,p_comment columns.comments columns.types int:string:string:string:string:int:string:double:string #### A masked pattern was here #### name default.part_orc numFiles 1 numRows 26 rawDataSize 16042 serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde totalSize 2655 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.part_orc name: default.part_orc Truncated Path -> Alias: /part_orc [part_orc] Execution mode: vectorized Needs Tagging: false Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int) outputColumnNames: _col1, _col2, _col5 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: part_orc output shape: _col1: string, _col2: string, _col5: int type: TABLE Partition table definition input alias: ptf_1 name: noop order by: _col2, _col1 output shape: _col1: string, _col2: string, _col5: int partition by: _col2, _col1 raw input shape: Partition table definition input alias: ptf_2 name: noop order by: _col2, _col1 output shape: _col1: string, _col2: string, _col5: int partition by: _col2, _col1 raw input shape: Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5 columns.types string,string,int escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe TotalFiles: 1 GatherStats: false MultiFileSpray: false Stage: Stage-2 Map Reduce Map Operator Tree: TableScan GatherStats: false Reduce Output Operator key expressions: _col2 (type: string) sort order: + Map-reduce partition columns: _col2 (type: string) Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col1 (type: string), _col5 (type: int) auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: -mr-10002 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5 columns.types string,string,int escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5 columns.types string,string,int escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Truncated Path -> Alias: #### A masked pattern was here #### Needs Tagging: false Reduce Operator Tree: Select Operator expressions: VALUE._col1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col4 (type: int) outputColumnNames: _col1, _col2, _col5 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: ptf_0 output shape: _col1: string, _col2: string, _col5: int type: PTFCOMPONENT Partition table definition input alias: ptf_1 name: noop order by: _col2 output shape: _col1: string, _col2: string, _col5: int partition by: _col2 raw input shape: Partition table definition input alias: ptf_2 name: noop order by: _col2 output shape: _col1: string, _col2: string, _col5: int partition by: _col2 raw input shape: Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5 columns.types string,string,int escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe TotalFiles: 1 GatherStats: false MultiFileSpray: false Stage: Stage-3 Map Reduce Map Operator Tree: TableScan GatherStats: false Reduce Output Operator key expressions: _col2 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col2 (type: string) Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col5 (type: int) auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: -mr-10003 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5 columns.types string,string,int escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5 columns.types string,string,int escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Truncated Path -> Alias: #### A masked pattern was here #### Needs Tagging: false Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int) outputColumnNames: _col1, _col2, _col5 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: ptf_0 output shape: _col1: string, _col2: string, _col5: int type: WINDOWING Windowing table definition input alias: ptf_1 name: windowingtablefunction order by: _col1 partition by: _col2 raw input shape: window functions: window function definition alias: rank_window_0 arguments: _col1 name: rank window function: GenericUDAFRankEvaluator window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true window function definition alias: dense_rank_window_1 arguments: _col1 name: dense_rank window function: GenericUDAFDenseRankEvaluator window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true window function definition alias: sum_window_2 arguments: _col5 name: sum window function: GenericUDAFSumLong window frame: PRECEDING(MAX)~ Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col2 (type: string), _col1 (type: string), rank_window_0 (type: int), dense_rank_window_1 (type: int), _col5 (type: int), sum_window_2 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE #### 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,_col2,_col3,_col4,_col5 columns.types string:string:int:int:int:bigint escape.delim \ hive.serialization.extend.additional.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-0 Fetch Operator limit: -1 Processor Tree: ListSink PREHOOK: query: select p_mfgr, p_name, rank() over (partition by p_mfgr order by p_name) as r, dense_rank() over (partition by p_mfgr order by p_name) as dr, p_size, sum(p_size) over (partition by p_mfgr order by p_name) as s1 from noop(on noop(on noop(on noop(on part_orc partition by p_mfgr,p_name order by p_mfgr,p_name) ) partition by p_mfgr order by p_mfgr)) PREHOOK: type: QUERY PREHOOK: Input: default@part_orc #### A masked pattern was here #### POSTHOOK: query: select p_mfgr, p_name, rank() over (partition by p_mfgr order by p_name) as r, dense_rank() over (partition by p_mfgr order by p_name) as dr, p_size, sum(p_size) over (partition by p_mfgr order by p_name) as s1 from noop(on noop(on noop(on noop(on part_orc partition by p_mfgr,p_name order by p_mfgr,p_name) ) partition by p_mfgr order by p_mfgr)) POSTHOOK: type: QUERY POSTHOOK: Input: default@part_orc #### A masked pattern was here #### Manufacturer#1 almond antique burnished rose metallic 1 1 2 4 Manufacturer#1 almond antique burnished rose metallic 1 1 2 4 Manufacturer#1 almond antique chartreuse lavender yellow 3 2 34 38 Manufacturer#1 almond antique salmon chartreuse burlywood 4 3 6 44 Manufacturer#1 almond aquamarine burnished black steel 5 4 28 72 Manufacturer#1 almond aquamarine pink moccasin thistle 6 5 42 114 Manufacturer#2 almond antique violet chocolate turquoise 1 1 14 14 Manufacturer#2 almond antique violet turquoise frosted 2 2 40 54 Manufacturer#2 almond aquamarine midnight light salmon 3 3 2 56 Manufacturer#2 almond aquamarine rose maroon antique 4 4 25 81 Manufacturer#2 almond aquamarine sandy cyan gainsboro 5 5 18 99 Manufacturer#3 almond antique chartreuse khaki white 1 1 17 17 Manufacturer#3 almond antique forest lavender goldenrod 2 2 14 31 Manufacturer#3 almond antique metallic orange dim 3 3 19 50 Manufacturer#3 almond antique misty red olive 4 4 1 51 Manufacturer#3 almond antique olive coral navajo 5 5 45 96 Manufacturer#4 almond antique gainsboro frosted violet 1 1 10 10 Manufacturer#4 almond antique violet mint lemon 2 2 39 49 Manufacturer#4 almond aquamarine floral ivory bisque 3 3 27 76 Manufacturer#4 almond aquamarine yellow dodger mint 4 4 7 83 Manufacturer#4 almond azure aquamarine papaya violet 5 5 12 95 Manufacturer#5 almond antique blue firebrick mint 1 1 31 31 Manufacturer#5 almond antique medium spring khaki 2 2 6 37 Manufacturer#5 almond antique sky peru orange 3 3 2 39 Manufacturer#5 almond aquamarine dodger light gainsboro 4 4 46 85 Manufacturer#5 almond azure blanched chiffon midnight 5 5 23 108 PREHOOK: query: -- 21. testMultiOperatorChainEndsWithNoopMap explain extended select p_mfgr, p_name, rank() over (partition by p_mfgr,p_name) as r, dense_rank() over (partition by p_mfgr,p_name) as dr, p_size, sum(p_size) over (partition by p_mfgr,p_name rows between unbounded preceding and current row) as s1 from noopwithmap(on noop(on noop(on noop(on part_orc partition by p_mfgr,p_name order by p_mfgr,p_name) ) partition by p_mfgr order by p_mfgr) partition by p_mfgr,p_name order by p_mfgr,p_name) PREHOOK: type: QUERY POSTHOOK: query: -- 21. testMultiOperatorChainEndsWithNoopMap explain extended select p_mfgr, p_name, rank() over (partition by p_mfgr,p_name) as r, dense_rank() over (partition by p_mfgr,p_name) as dr, p_size, sum(p_size) over (partition by p_mfgr,p_name rows between unbounded preceding and current row) as s1 from noopwithmap(on noop(on noop(on noop(on part_orc partition by p_mfgr,p_name order by p_mfgr,p_name) ) partition by p_mfgr order by p_mfgr) partition by p_mfgr,p_name order by p_mfgr,p_name) POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: TOK_QUERY TOK_FROM TOK_PTBLFUNCTION noopwithmap TOK_PTBLFUNCTION noop TOK_PTBLFUNCTION noop TOK_PTBLFUNCTION noop TOK_TABREF TOK_TABNAME part_orc TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_TABLE_OR_COL p_name TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_mfgr TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_mfgr TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_TABLE_OR_COL p_name TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_mfgr TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name TOK_INSERT TOK_DESTINATION TOK_DIR TOK_TMP_FILE TOK_SELECT TOK_SELEXPR TOK_TABLE_OR_COL p_mfgr TOK_SELEXPR TOK_TABLE_OR_COL p_name TOK_SELEXPR TOK_FUNCTION rank TOK_WINDOWSPEC TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_TABLE_OR_COL p_name r TOK_SELEXPR TOK_FUNCTION dense_rank TOK_WINDOWSPEC TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_TABLE_OR_COL p_name dr TOK_SELEXPR TOK_TABLE_OR_COL p_size TOK_SELEXPR TOK_FUNCTION sum TOK_TABLE_OR_COL p_size TOK_WINDOWSPEC TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_TABLE_OR_COL p_name TOK_WINDOWRANGE preceding unbounded current s1 STAGE DEPENDENCIES: Stage-1 is a root stage Stage-2 depends on stages: Stage-1 Stage-3 depends on stages: Stage-2 Stage-4 depends on stages: Stage-3 Stage-0 depends on stages: Stage-4 STAGE PLANS: Stage: Stage-1 Map Reduce Map Operator Tree: TableScan alias: part_orc Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE GatherStats: false Reduce Output Operator key expressions: p_mfgr (type: string), p_name (type: string) sort order: ++ Map-reduce partition columns: p_mfgr (type: string), p_name (type: string) Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: p_size (type: int) auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: part_orc input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat properties: COLUMN_STATS_ACCURATE true bucket_count -1 columns p_partkey,p_name,p_mfgr,p_brand,p_type,p_size,p_container,p_retailprice,p_comment columns.comments columns.types int:string:string:string:string:int:string:double:string #### A masked pattern was here #### name default.part_orc numFiles 1 numRows 26 rawDataSize 16042 serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde totalSize 2655 #### 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: COLUMN_STATS_ACCURATE true bucket_count -1 columns p_partkey,p_name,p_mfgr,p_brand,p_type,p_size,p_container,p_retailprice,p_comment columns.comments columns.types int:string:string:string:string:int:string:double:string #### A masked pattern was here #### name default.part_orc numFiles 1 numRows 26 rawDataSize 16042 serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde totalSize 2655 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.part_orc name: default.part_orc Truncated Path -> Alias: /part_orc [part_orc] Execution mode: vectorized Needs Tagging: false Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int) outputColumnNames: _col1, _col2, _col5 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: part_orc output shape: _col1: string, _col2: string, _col5: int type: TABLE Partition table definition input alias: ptf_1 name: noop order by: _col2, _col1 output shape: _col1: string, _col2: string, _col5: int partition by: _col2, _col1 raw input shape: Partition table definition input alias: ptf_2 name: noop order by: _col2, _col1 output shape: _col1: string, _col2: string, _col5: int partition by: _col2, _col1 raw input shape: Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5 columns.types string,string,int escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe TotalFiles: 1 GatherStats: false MultiFileSpray: false Stage: Stage-2 Map Reduce Map Operator Tree: TableScan GatherStats: false Reduce Output Operator key expressions: _col2 (type: string) sort order: + Map-reduce partition columns: _col2 (type: string) Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col1 (type: string), _col5 (type: int) auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: -mr-10002 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5 columns.types string,string,int escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5 columns.types string,string,int escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Truncated Path -> Alias: #### A masked pattern was here #### Needs Tagging: false Reduce Operator Tree: Select Operator expressions: VALUE._col1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col4 (type: int) outputColumnNames: _col1, _col2, _col5 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: ptf_0 output shape: _col1: string, _col2: string, _col5: int type: PTFCOMPONENT Partition table definition input alias: ptf_1 name: noop order by: _col2 output shape: _col1: string, _col2: string, _col5: int partition by: _col2 raw input shape: Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: ptf_0 output shape: _col1: string, _col2: string, _col5: int type: PTFCOMPONENT Partition table definition input alias: ptf_1 name: noopwithmap order by: _col2, _col1 output shape: _col1: string, _col2: string, _col5: int partition by: _col2, _col1 raw input shape: transforms raw input: true Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE Map-side function: true File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5 columns.types string,string,int escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe TotalFiles: 1 GatherStats: false MultiFileSpray: false Stage: Stage-3 Map Reduce Map Operator Tree: TableScan GatherStats: false Reduce Output Operator key expressions: _col2 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col2 (type: string), _col1 (type: string) Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col5 (type: int) auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: -mr-10003 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5 columns.types string,string,int escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5 columns.types string,string,int escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Truncated Path -> Alias: #### A masked pattern was here #### Needs Tagging: false Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int) outputColumnNames: _col1, _col2, _col5 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: ptf_0 output shape: _col1: string, _col2: string, _col5: int type: PTFCOMPONENT Partition table definition input alias: ptf_1 name: noopwithmap order by: _col2, _col1 output shape: _col1: string, _col2: string, _col5: int partition by: _col2, _col1 raw input shape: transforms raw input: true Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5 columns.types string,string,int escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe TotalFiles: 1 GatherStats: false MultiFileSpray: false Stage: Stage-4 Map Reduce Map Operator Tree: TableScan GatherStats: false Reduce Output Operator key expressions: _col2 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col2 (type: string), _col1 (type: string) Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col5 (type: int) auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: -mr-10004 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5 columns.types string,string,int escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5 columns.types string,string,int escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Truncated Path -> Alias: #### A masked pattern was here #### Needs Tagging: false Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int) outputColumnNames: _col1, _col2, _col5 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: ptf_0 output shape: _col1: string, _col2: string, _col5: int type: WINDOWING Windowing table definition input alias: ptf_1 name: windowingtablefunction order by: _col2, _col1 partition by: _col2, _col1 raw input shape: window functions: window function definition alias: rank_window_0 arguments: _col2, _col1 name: rank window function: GenericUDAFRankEvaluator window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true window function definition alias: dense_rank_window_1 arguments: _col2, _col1 name: dense_rank window function: GenericUDAFDenseRankEvaluator window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true window function definition alias: sum_window_2 arguments: _col5 name: sum window function: GenericUDAFSumLong window frame: PRECEDING(MAX)~ Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col2 (type: string), _col1 (type: string), rank_window_0 (type: int), dense_rank_window_1 (type: int), _col5 (type: int), sum_window_2 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE #### 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,_col2,_col3,_col4,_col5 columns.types string:string:int:int:int:bigint escape.delim \ hive.serialization.extend.additional.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-0 Fetch Operator limit: -1 Processor Tree: ListSink PREHOOK: query: select p_mfgr, p_name, rank() over (partition by p_mfgr,p_name) as r, dense_rank() over (partition by p_mfgr,p_name) as dr, p_size, sum(p_size) over (partition by p_mfgr,p_name rows between unbounded preceding and current row) as s1 from noopwithmap(on noop(on noop(on noop(on part_orc partition by p_mfgr,p_name order by p_mfgr,p_name) ) partition by p_mfgr order by p_mfgr) partition by p_mfgr,p_name order by p_mfgr,p_name) PREHOOK: type: QUERY PREHOOK: Input: default@part_orc #### A masked pattern was here #### POSTHOOK: query: select p_mfgr, p_name, rank() over (partition by p_mfgr,p_name) as r, dense_rank() over (partition by p_mfgr,p_name) as dr, p_size, sum(p_size) over (partition by p_mfgr,p_name rows between unbounded preceding and current row) as s1 from noopwithmap(on noop(on noop(on noop(on part_orc partition by p_mfgr,p_name order by p_mfgr,p_name) ) partition by p_mfgr order by p_mfgr) partition by p_mfgr,p_name order by p_mfgr,p_name) POSTHOOK: type: QUERY POSTHOOK: Input: default@part_orc #### A masked pattern was here #### Manufacturer#1 almond antique burnished rose metallic 1 1 2 2 Manufacturer#1 almond antique burnished rose metallic 1 1 2 4 Manufacturer#1 almond antique chartreuse lavender yellow 1 1 34 34 Manufacturer#1 almond antique salmon chartreuse burlywood 1 1 6 6 Manufacturer#1 almond aquamarine burnished black steel 1 1 28 28 Manufacturer#1 almond aquamarine pink moccasin thistle 1 1 42 42 Manufacturer#2 almond antique violet chocolate turquoise 1 1 14 14 Manufacturer#2 almond antique violet turquoise frosted 1 1 40 40 Manufacturer#2 almond aquamarine midnight light salmon 1 1 2 2 Manufacturer#2 almond aquamarine rose maroon antique 1 1 25 25 Manufacturer#2 almond aquamarine sandy cyan gainsboro 1 1 18 18 Manufacturer#3 almond antique chartreuse khaki white 1 1 17 17 Manufacturer#3 almond antique forest lavender goldenrod 1 1 14 14 Manufacturer#3 almond antique metallic orange dim 1 1 19 19 Manufacturer#3 almond antique misty red olive 1 1 1 1 Manufacturer#3 almond antique olive coral navajo 1 1 45 45 Manufacturer#4 almond antique gainsboro frosted violet 1 1 10 10 Manufacturer#4 almond antique violet mint lemon 1 1 39 39 Manufacturer#4 almond aquamarine floral ivory bisque 1 1 27 27 Manufacturer#4 almond aquamarine yellow dodger mint 1 1 7 7 Manufacturer#4 almond azure aquamarine papaya violet 1 1 12 12 Manufacturer#5 almond antique blue firebrick mint 1 1 31 31 Manufacturer#5 almond antique medium spring khaki 1 1 6 6 Manufacturer#5 almond antique sky peru orange 1 1 2 2 Manufacturer#5 almond aquamarine dodger light gainsboro 1 1 46 46 Manufacturer#5 almond azure blanched chiffon midnight 1 1 23 23 PREHOOK: query: -- 22. testMultiOperatorChainWithDiffPartitionForWindow1 explain extended select p_mfgr, p_name, rank() over (partition by p_mfgr,p_name order by p_mfgr,p_name) as r, dense_rank() over (partition by p_mfgr,p_name order by p_mfgr,p_name) as dr, p_size, sum(p_size) over (partition by p_mfgr,p_name order by p_mfgr,p_name rows between unbounded preceding and current row) as s1, sum(p_size) over (partition by p_mfgr,p_name order by p_mfgr,p_name rows between unbounded preceding and current row) as s2 from noop(on noopwithmap(on noop(on part_orc partition by p_mfgr, p_name order by p_mfgr, p_name) partition by p_mfgr order by p_mfgr )) PREHOOK: type: QUERY POSTHOOK: query: -- 22. testMultiOperatorChainWithDiffPartitionForWindow1 explain extended select p_mfgr, p_name, rank() over (partition by p_mfgr,p_name order by p_mfgr,p_name) as r, dense_rank() over (partition by p_mfgr,p_name order by p_mfgr,p_name) as dr, p_size, sum(p_size) over (partition by p_mfgr,p_name order by p_mfgr,p_name rows between unbounded preceding and current row) as s1, sum(p_size) over (partition by p_mfgr,p_name order by p_mfgr,p_name rows between unbounded preceding and current row) as s2 from noop(on noopwithmap(on noop(on part_orc partition by p_mfgr, p_name order by p_mfgr, p_name) partition by p_mfgr order by p_mfgr )) POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: TOK_QUERY TOK_FROM TOK_PTBLFUNCTION noop TOK_PTBLFUNCTION noopwithmap TOK_PTBLFUNCTION noop TOK_TABREF TOK_TABNAME part_orc TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_TABLE_OR_COL p_name TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_mfgr TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_mfgr TOK_INSERT TOK_DESTINATION TOK_DIR TOK_TMP_FILE TOK_SELECT TOK_SELEXPR TOK_TABLE_OR_COL p_mfgr TOK_SELEXPR TOK_TABLE_OR_COL p_name TOK_SELEXPR TOK_FUNCTION rank TOK_WINDOWSPEC TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_TABLE_OR_COL p_name TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_mfgr TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name r TOK_SELEXPR TOK_FUNCTION dense_rank TOK_WINDOWSPEC TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_TABLE_OR_COL p_name TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_mfgr TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name dr TOK_SELEXPR TOK_TABLE_OR_COL p_size TOK_SELEXPR TOK_FUNCTION sum TOK_TABLE_OR_COL p_size TOK_WINDOWSPEC TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_TABLE_OR_COL p_name TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_mfgr TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name TOK_WINDOWRANGE preceding unbounded current s1 TOK_SELEXPR TOK_FUNCTION sum TOK_TABLE_OR_COL p_size TOK_WINDOWSPEC TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_TABLE_OR_COL p_name TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_mfgr TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name TOK_WINDOWRANGE preceding unbounded current s2 STAGE DEPENDENCIES: Stage-1 is a root stage Stage-2 depends on stages: Stage-1 Stage-3 depends on stages: Stage-2 Stage-0 depends on stages: Stage-3 STAGE PLANS: Stage: Stage-1 Map Reduce Map Operator Tree: TableScan alias: part_orc Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE GatherStats: false Reduce Output Operator key expressions: p_mfgr (type: string), p_name (type: string) sort order: ++ Map-reduce partition columns: p_mfgr (type: string), p_name (type: string) Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: p_size (type: int) auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: part_orc input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat properties: COLUMN_STATS_ACCURATE true bucket_count -1 columns p_partkey,p_name,p_mfgr,p_brand,p_type,p_size,p_container,p_retailprice,p_comment columns.comments columns.types int:string:string:string:string:int:string:double:string #### A masked pattern was here #### name default.part_orc numFiles 1 numRows 26 rawDataSize 16042 serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde totalSize 2655 #### 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: COLUMN_STATS_ACCURATE true bucket_count -1 columns p_partkey,p_name,p_mfgr,p_brand,p_type,p_size,p_container,p_retailprice,p_comment columns.comments columns.types int:string:string:string:string:int:string:double:string #### A masked pattern was here #### name default.part_orc numFiles 1 numRows 26 rawDataSize 16042 serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde totalSize 2655 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.part_orc name: default.part_orc Truncated Path -> Alias: /part_orc [part_orc] Execution mode: vectorized Needs Tagging: false Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int) outputColumnNames: _col1, _col2, _col5 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: part_orc output shape: _col1: string, _col2: string, _col5: int type: TABLE Partition table definition input alias: ptf_1 name: noop order by: _col2, _col1 output shape: _col1: string, _col2: string, _col5: int partition by: _col2, _col1 raw input shape: Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: ptf_0 output shape: _col1: string, _col2: string, _col5: int type: PTFCOMPONENT Partition table definition input alias: ptf_1 name: noopwithmap order by: _col2 output shape: _col1: string, _col2: string, _col5: int partition by: _col2 raw input shape: transforms raw input: true Partition table definition input alias: ptf_2 name: noop order by: _col2 output shape: _col1: string, _col2: string, _col5: int partition by: _col2 raw input shape: Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE Map-side function: true File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5 columns.types string,string,int escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe TotalFiles: 1 GatherStats: false MultiFileSpray: false Stage: Stage-2 Map Reduce Map Operator Tree: TableScan GatherStats: false Reduce Output Operator key expressions: _col2 (type: string) sort order: + Map-reduce partition columns: _col2 (type: string) Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col1 (type: string), _col5 (type: int) auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: -mr-10002 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5 columns.types string,string,int escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5 columns.types string,string,int escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Truncated Path -> Alias: #### A masked pattern was here #### Needs Tagging: false Reduce Operator Tree: Select Operator expressions: VALUE._col1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col4 (type: int) outputColumnNames: _col1, _col2, _col5 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: ptf_0 output shape: _col1: string, _col2: string, _col5: int type: PTFCOMPONENT Partition table definition input alias: ptf_1 name: noopwithmap order by: _col2 output shape: _col1: string, _col2: string, _col5: int partition by: _col2 raw input shape: transforms raw input: true Partition table definition input alias: ptf_2 name: noop order by: _col2 output shape: _col1: string, _col2: string, _col5: int partition by: _col2 raw input shape: Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5 columns.types string,string,int escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe TotalFiles: 1 GatherStats: false MultiFileSpray: false Stage: Stage-3 Map Reduce Map Operator Tree: TableScan GatherStats: false Reduce Output Operator key expressions: _col2 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col2 (type: string), _col1 (type: string) Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col5 (type: int) auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: -mr-10003 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5 columns.types string,string,int escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5 columns.types string,string,int escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Truncated Path -> Alias: #### A masked pattern was here #### Needs Tagging: false Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int) outputColumnNames: _col1, _col2, _col5 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: ptf_0 output shape: _col1: string, _col2: string, _col5: int type: WINDOWING Windowing table definition input alias: ptf_1 name: windowingtablefunction order by: _col2, _col1 partition by: _col2, _col1 raw input shape: window functions: window function definition alias: rank_window_0 arguments: _col2, _col1 name: rank window function: GenericUDAFRankEvaluator window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true window function definition alias: dense_rank_window_1 arguments: _col2, _col1 name: dense_rank window function: GenericUDAFDenseRankEvaluator window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true window function definition alias: sum_window_2 arguments: _col5 name: sum window function: GenericUDAFSumLong window frame: PRECEDING(MAX)~ Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col2 (type: string), _col1 (type: string), rank_window_0 (type: int), dense_rank_window_1 (type: int), _col5 (type: int), sum_window_2 (type: bigint), sum_window_2 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE #### 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,_col2,_col3,_col4,_col5,_col6 columns.types string:string:int:int:int:bigint:bigint escape.delim \ hive.serialization.extend.additional.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-0 Fetch Operator limit: -1 Processor Tree: ListSink PREHOOK: query: select p_mfgr, p_name, rank() over (partition by p_mfgr,p_name order by p_mfgr,p_name) as r, dense_rank() over (partition by p_mfgr,p_name order by p_mfgr,p_name) as dr, p_size, sum(p_size) over (partition by p_mfgr,p_name order by p_mfgr,p_name rows between unbounded preceding and current row) as s1, sum(p_size) over (partition by p_mfgr,p_name order by p_mfgr,p_name rows between unbounded preceding and current row) as s2 from noop(on noopwithmap(on noop(on part_orc partition by p_mfgr, p_name order by p_mfgr, p_name) partition by p_mfgr order by p_mfgr )) PREHOOK: type: QUERY PREHOOK: Input: default@part_orc #### A masked pattern was here #### POSTHOOK: query: select p_mfgr, p_name, rank() over (partition by p_mfgr,p_name order by p_mfgr,p_name) as r, dense_rank() over (partition by p_mfgr,p_name order by p_mfgr,p_name) as dr, p_size, sum(p_size) over (partition by p_mfgr,p_name order by p_mfgr,p_name rows between unbounded preceding and current row) as s1, sum(p_size) over (partition by p_mfgr,p_name order by p_mfgr,p_name rows between unbounded preceding and current row) as s2 from noop(on noopwithmap(on noop(on part_orc partition by p_mfgr, p_name order by p_mfgr, p_name) partition by p_mfgr order by p_mfgr )) POSTHOOK: type: QUERY POSTHOOK: Input: default@part_orc #### A masked pattern was here #### Manufacturer#1 almond antique burnished rose metallic 1 1 2 2 2 Manufacturer#1 almond antique burnished rose metallic 1 1 2 4 4 Manufacturer#1 almond antique chartreuse lavender yellow 1 1 34 34 34 Manufacturer#1 almond antique salmon chartreuse burlywood 1 1 6 6 6 Manufacturer#1 almond aquamarine burnished black steel 1 1 28 28 28 Manufacturer#1 almond aquamarine pink moccasin thistle 1 1 42 42 42 Manufacturer#2 almond antique violet chocolate turquoise 1 1 14 14 14 Manufacturer#2 almond antique violet turquoise frosted 1 1 40 40 40 Manufacturer#2 almond aquamarine midnight light salmon 1 1 2 2 2 Manufacturer#2 almond aquamarine rose maroon antique 1 1 25 25 25 Manufacturer#2 almond aquamarine sandy cyan gainsboro 1 1 18 18 18 Manufacturer#3 almond antique chartreuse khaki white 1 1 17 17 17 Manufacturer#3 almond antique forest lavender goldenrod 1 1 14 14 14 Manufacturer#3 almond antique metallic orange dim 1 1 19 19 19 Manufacturer#3 almond antique misty red olive 1 1 1 1 1 Manufacturer#3 almond antique olive coral navajo 1 1 45 45 45 Manufacturer#4 almond antique gainsboro frosted violet 1 1 10 10 10 Manufacturer#4 almond antique violet mint lemon 1 1 39 39 39 Manufacturer#4 almond aquamarine floral ivory bisque 1 1 27 27 27 Manufacturer#4 almond aquamarine yellow dodger mint 1 1 7 7 7 Manufacturer#4 almond azure aquamarine papaya violet 1 1 12 12 12 Manufacturer#5 almond antique blue firebrick mint 1 1 31 31 31 Manufacturer#5 almond antique medium spring khaki 1 1 6 6 6 Manufacturer#5 almond antique sky peru orange 1 1 2 2 2 Manufacturer#5 almond aquamarine dodger light gainsboro 1 1 46 46 46 Manufacturer#5 almond azure blanched chiffon midnight 1 1 23 23 23 PREHOOK: query: -- 23. testMultiOperatorChainWithDiffPartitionForWindow2 explain extended select p_mfgr, p_name, rank() over (partition by p_mfgr order by p_name) as r, dense_rank() over (partition by p_mfgr order by p_name) as dr, p_size, sum(p_size) over (partition by p_mfgr order by p_name range between unbounded preceding and current row) as s1, sum(p_size) over (partition by p_mfgr order by p_name range between unbounded preceding and current row) as s2 from noopwithmap(on noop(on noop(on part_orc partition by p_mfgr, p_name order by p_mfgr, p_name) )) PREHOOK: type: QUERY POSTHOOK: query: -- 23. testMultiOperatorChainWithDiffPartitionForWindow2 explain extended select p_mfgr, p_name, rank() over (partition by p_mfgr order by p_name) as r, dense_rank() over (partition by p_mfgr order by p_name) as dr, p_size, sum(p_size) over (partition by p_mfgr order by p_name range between unbounded preceding and current row) as s1, sum(p_size) over (partition by p_mfgr order by p_name range between unbounded preceding and current row) as s2 from noopwithmap(on noop(on noop(on part_orc partition by p_mfgr, p_name order by p_mfgr, p_name) )) POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: TOK_QUERY TOK_FROM TOK_PTBLFUNCTION noopwithmap TOK_PTBLFUNCTION noop TOK_PTBLFUNCTION noop TOK_TABREF TOK_TABNAME part_orc TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_TABLE_OR_COL p_name TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_mfgr TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name TOK_INSERT TOK_DESTINATION TOK_DIR TOK_TMP_FILE TOK_SELECT TOK_SELEXPR TOK_TABLE_OR_COL p_mfgr TOK_SELEXPR TOK_TABLE_OR_COL p_name TOK_SELEXPR TOK_FUNCTION rank TOK_WINDOWSPEC TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name r TOK_SELEXPR TOK_FUNCTION dense_rank TOK_WINDOWSPEC TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name dr TOK_SELEXPR TOK_TABLE_OR_COL p_size TOK_SELEXPR TOK_FUNCTION sum TOK_TABLE_OR_COL p_size TOK_WINDOWSPEC TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name TOK_WINDOWVALUES preceding unbounded current s1 TOK_SELEXPR TOK_FUNCTION sum TOK_TABLE_OR_COL p_size TOK_WINDOWSPEC TOK_PARTITIONINGSPEC TOK_DISTRIBUTEBY TOK_TABLE_OR_COL p_mfgr TOK_ORDERBY TOK_TABSORTCOLNAMEASC TOK_TABLE_OR_COL p_name TOK_WINDOWVALUES preceding unbounded current s2 STAGE DEPENDENCIES: Stage-1 is a root stage Stage-2 depends on stages: Stage-1 Stage-3 depends on stages: Stage-2 Stage-0 depends on stages: Stage-3 STAGE PLANS: Stage: Stage-1 Map Reduce Map Operator Tree: TableScan alias: part_orc Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE GatherStats: false Reduce Output Operator key expressions: p_mfgr (type: string), p_name (type: string) sort order: ++ Map-reduce partition columns: p_mfgr (type: string), p_name (type: string) Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: p_size (type: int) auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: part_orc input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat properties: COLUMN_STATS_ACCURATE true bucket_count -1 columns p_partkey,p_name,p_mfgr,p_brand,p_type,p_size,p_container,p_retailprice,p_comment columns.comments columns.types int:string:string:string:string:int:string:double:string #### A masked pattern was here #### name default.part_orc numFiles 1 numRows 26 rawDataSize 16042 serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde totalSize 2655 #### 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: COLUMN_STATS_ACCURATE true bucket_count -1 columns p_partkey,p_name,p_mfgr,p_brand,p_type,p_size,p_container,p_retailprice,p_comment columns.comments columns.types int:string:string:string:string:int:string:double:string #### A masked pattern was here #### name default.part_orc numFiles 1 numRows 26 rawDataSize 16042 serialization.ddl struct part_orc { i32 p_partkey, string p_name, string p_mfgr, string p_brand, string p_type, i32 p_size, string p_container, double p_retailprice, string p_comment} serialization.format 1 serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde totalSize 2655 #### A masked pattern was here #### serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.part_orc name: default.part_orc Truncated Path -> Alias: /part_orc [part_orc] Execution mode: vectorized Needs Tagging: false Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int) outputColumnNames: _col1, _col2, _col5 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: part_orc output shape: _col1: string, _col2: string, _col5: int type: TABLE Partition table definition input alias: ptf_1 name: noop order by: _col2, _col1 output shape: _col1: string, _col2: string, _col5: int partition by: _col2, _col1 raw input shape: Partition table definition input alias: ptf_2 name: noop order by: _col2, _col1 output shape: _col1: string, _col2: string, _col5: int partition by: _col2, _col1 raw input shape: Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: ptf_0 output shape: _col1: string, _col2: string, _col5: int type: PTFCOMPONENT Partition table definition input alias: ptf_1 name: noopwithmap order by: _col2, _col1 output shape: _col1: string, _col2: string, _col5: int partition by: _col2, _col1 raw input shape: transforms raw input: true Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE Map-side function: true File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5 columns.types string,string,int escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe TotalFiles: 1 GatherStats: false MultiFileSpray: false Stage: Stage-2 Map Reduce Map Operator Tree: TableScan GatherStats: false Reduce Output Operator key expressions: _col2 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col2 (type: string), _col1 (type: string) Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col5 (type: int) auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: -mr-10002 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5 columns.types string,string,int escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5 columns.types string,string,int escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Truncated Path -> Alias: #### A masked pattern was here #### Needs Tagging: false Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int) outputColumnNames: _col1, _col2, _col5 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: ptf_0 output shape: _col1: string, _col2: string, _col5: int type: PTFCOMPONENT Partition table definition input alias: ptf_1 name: noopwithmap order by: _col2, _col1 output shape: _col1: string, _col2: string, _col5: int partition by: _col2, _col1 raw input shape: transforms raw input: true Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5 columns.types string,string,int escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe TotalFiles: 1 GatherStats: false MultiFileSpray: false Stage: Stage-3 Map Reduce Map Operator Tree: TableScan GatherStats: false Reduce Output Operator key expressions: _col2 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col2 (type: string) Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col5 (type: int) auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: -mr-10003 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5 columns.types string,string,int escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col1,_col2,_col5 columns.types string,string,int escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Truncated Path -> Alias: #### A masked pattern was here #### Needs Tagging: false Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int) outputColumnNames: _col1, _col2, _col5 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: ptf_0 output shape: _col1: string, _col2: string, _col5: int type: WINDOWING Windowing table definition input alias: ptf_1 name: windowingtablefunction order by: _col1 partition by: _col2 raw input shape: window functions: window function definition alias: rank_window_0 arguments: _col1 name: rank window function: GenericUDAFRankEvaluator window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true window function definition alias: dense_rank_window_1 arguments: _col1 name: dense_rank window function: GenericUDAFDenseRankEvaluator window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true window function definition alias: sum_window_2 arguments: _col5 name: sum window function: GenericUDAFSumLong window frame: PRECEDING(MAX)~ Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col2 (type: string), _col1 (type: string), rank_window_0 (type: int), dense_rank_window_1 (type: int), _col5 (type: int), sum_window_2 (type: bigint), sum_window_2 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 Statistics: Num rows: 26 Data size: 16042 Basic stats: COMPLETE Column stats: NONE #### 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,_col2,_col3,_col4,_col5,_col6 columns.types string:string:int:int:int:bigint:bigint escape.delim \ hive.serialization.extend.additional.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-0 Fetch Operator limit: -1 Processor Tree: ListSink PREHOOK: query: select p_mfgr, p_name, rank() over (partition by p_mfgr order by p_name) as r, dense_rank() over (partition by p_mfgr order by p_name) as dr, p_size, sum(p_size) over (partition by p_mfgr order by p_name range between unbounded preceding and current row) as s1, sum(p_size) over (partition by p_mfgr order by p_name range between unbounded preceding and current row) as s2 from noopwithmap(on noop(on noop(on part_orc partition by p_mfgr, p_name order by p_mfgr, p_name) )) PREHOOK: type: QUERY PREHOOK: Input: default@part_orc #### A masked pattern was here #### POSTHOOK: query: select p_mfgr, p_name, rank() over (partition by p_mfgr order by p_name) as r, dense_rank() over (partition by p_mfgr order by p_name) as dr, p_size, sum(p_size) over (partition by p_mfgr order by p_name range between unbounded preceding and current row) as s1, sum(p_size) over (partition by p_mfgr order by p_name range between unbounded preceding and current row) as s2 from noopwithmap(on noop(on noop(on part_orc partition by p_mfgr, p_name order by p_mfgr, p_name) )) POSTHOOK: type: QUERY POSTHOOK: Input: default@part_orc #### A masked pattern was here #### Manufacturer#1 almond antique burnished rose metallic 1 1 2 4 4 Manufacturer#1 almond antique burnished rose metallic 1 1 2 4 4 Manufacturer#1 almond antique chartreuse lavender yellow 3 2 34 38 38 Manufacturer#1 almond antique salmon chartreuse burlywood 4 3 6 44 44 Manufacturer#1 almond aquamarine burnished black steel 5 4 28 72 72 Manufacturer#1 almond aquamarine pink moccasin thistle 6 5 42 114 114 Manufacturer#2 almond antique violet chocolate turquoise 1 1 14 14 14 Manufacturer#2 almond antique violet turquoise frosted 2 2 40 54 54 Manufacturer#2 almond aquamarine midnight light salmon 3 3 2 56 56 Manufacturer#2 almond aquamarine rose maroon antique 4 4 25 81 81 Manufacturer#2 almond aquamarine sandy cyan gainsboro 5 5 18 99 99 Manufacturer#3 almond antique chartreuse khaki white 1 1 17 17 17 Manufacturer#3 almond antique forest lavender goldenrod 2 2 14 31 31 Manufacturer#3 almond antique metallic orange dim 3 3 19 50 50 Manufacturer#3 almond antique misty red olive 4 4 1 51 51 Manufacturer#3 almond antique olive coral navajo 5 5 45 96 96 Manufacturer#4 almond antique gainsboro frosted violet 1 1 10 10 10 Manufacturer#4 almond antique violet mint lemon 2 2 39 49 49 Manufacturer#4 almond aquamarine floral ivory bisque 3 3 27 76 76 Manufacturer#4 almond aquamarine yellow dodger mint 4 4 7 83 83 Manufacturer#4 almond azure aquamarine papaya violet 5 5 12 95 95 Manufacturer#5 almond antique blue firebrick mint 1 1 31 31 31 Manufacturer#5 almond antique medium spring khaki 2 2 6 37 37 Manufacturer#5 almond antique sky peru orange 3 3 2 39 39 Manufacturer#5 almond aquamarine dodger light gainsboro 4 4 46 85 85 Manufacturer#5 almond azure blanched chiffon midnight 5 5 23 108 108