Repository: hive Updated Branches: refs/heads/master 5783ab858 -> b7e8d0c9c
http://git-wip-us.apache.org/repos/asf/hive/blob/b7e8d0c9/ql/src/test/results/clientpositive/tez/vector_include_no_sel.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/tez/vector_include_no_sel.q.out b/ql/src/test/results/clientpositive/tez/vector_include_no_sel.q.out new file mode 100644 index 0000000..be991b2 --- /dev/null +++ b/ql/src/test/results/clientpositive/tez/vector_include_no_sel.q.out @@ -0,0 +1,284 @@ +PREHOOK: query: -- HIVE-13872 +-- Looking for TableScan immediately followed by ReduceSink (no intervening SEL operator). +-- This caused problems for Vectorizer not eliminating columns which are not included. +-- The input file format didn't fill in those vectorized columns and thus caused NPE in +-- ReduceSink. +-- Only a problem when NOT CBO because of CBO rule-based transforms. +-- +-- Using a cross-product. + +create table store_sales_txt +( + ss_sold_date_sk int, + ss_sold_time_sk int, + ss_item_sk int, + ss_customer_sk int, + ss_cdemo_sk int, + ss_hdemo_sk int, + ss_addr_sk int, + ss_store_sk int, + ss_promo_sk int, + ss_ticket_number int, + ss_quantity int, + ss_wholesale_cost float, + ss_list_price float, + ss_sales_price float, + ss_ext_discount_amt float, + ss_ext_sales_price float, + ss_ext_wholesale_cost float, + ss_ext_list_price float, + ss_ext_tax float, + ss_coupon_amt float, + ss_net_paid float, + ss_net_paid_inc_tax float, + ss_net_profit float +) +row format delimited fields terminated by '|' +stored as textfile +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@store_sales_txt +POSTHOOK: query: -- HIVE-13872 +-- Looking for TableScan immediately followed by ReduceSink (no intervening SEL operator). +-- This caused problems for Vectorizer not eliminating columns which are not included. +-- The input file format didn't fill in those vectorized columns and thus caused NPE in +-- ReduceSink. +-- Only a problem when NOT CBO because of CBO rule-based transforms. +-- +-- Using a cross-product. + +create table store_sales_txt +( + ss_sold_date_sk int, + ss_sold_time_sk int, + ss_item_sk int, + ss_customer_sk int, + ss_cdemo_sk int, + ss_hdemo_sk int, + ss_addr_sk int, + ss_store_sk int, + ss_promo_sk int, + ss_ticket_number int, + ss_quantity int, + ss_wholesale_cost float, + ss_list_price float, + ss_sales_price float, + ss_ext_discount_amt float, + ss_ext_sales_price float, + ss_ext_wholesale_cost float, + ss_ext_list_price float, + ss_ext_tax float, + ss_coupon_amt float, + ss_net_paid float, + ss_net_paid_inc_tax float, + ss_net_profit float +) +row format delimited fields terminated by '|' +stored as textfile +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@store_sales_txt +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/store_sales.txt' OVERWRITE INTO TABLE store_sales_txt +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@store_sales_txt +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/store_sales.txt' OVERWRITE INTO TABLE store_sales_txt +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@store_sales_txt +PREHOOK: query: create table store_sales stored as orc as select * from store_sales_txt +PREHOOK: type: CREATETABLE_AS_SELECT +PREHOOK: Input: default@store_sales_txt +PREHOOK: Output: database:default +PREHOOK: Output: default@store_sales +POSTHOOK: query: create table store_sales stored as orc as select * from store_sales_txt +POSTHOOK: type: CREATETABLE_AS_SELECT +POSTHOOK: Input: default@store_sales_txt +POSTHOOK: Output: database:default +POSTHOOK: Output: default@store_sales +POSTHOOK: Lineage: store_sales.ss_addr_sk SIMPLE [(store_sales_txt)store_sales_txt.FieldSchema(name:ss_addr_sk, type:int, comment:null), ] +POSTHOOK: Lineage: store_sales.ss_cdemo_sk SIMPLE [(store_sales_txt)store_sales_txt.FieldSchema(name:ss_cdemo_sk, type:int, comment:null), ] +POSTHOOK: Lineage: store_sales.ss_coupon_amt SIMPLE [(store_sales_txt)store_sales_txt.FieldSchema(name:ss_coupon_amt, type:float, comment:null), ] +POSTHOOK: Lineage: store_sales.ss_customer_sk SIMPLE [(store_sales_txt)store_sales_txt.FieldSchema(name:ss_customer_sk, type:int, comment:null), ] +POSTHOOK: Lineage: store_sales.ss_ext_discount_amt SIMPLE [(store_sales_txt)store_sales_txt.FieldSchema(name:ss_ext_discount_amt, type:float, comment:null), ] +POSTHOOK: Lineage: store_sales.ss_ext_list_price SIMPLE [(store_sales_txt)store_sales_txt.FieldSchema(name:ss_ext_list_price, type:float, comment:null), ] +POSTHOOK: Lineage: store_sales.ss_ext_sales_price SIMPLE [(store_sales_txt)store_sales_txt.FieldSchema(name:ss_ext_sales_price, type:float, comment:null), ] +POSTHOOK: Lineage: store_sales.ss_ext_tax SIMPLE [(store_sales_txt)store_sales_txt.FieldSchema(name:ss_ext_tax, type:float, comment:null), ] +POSTHOOK: Lineage: store_sales.ss_ext_wholesale_cost SIMPLE [(store_sales_txt)store_sales_txt.FieldSchema(name:ss_ext_wholesale_cost, type:float, comment:null), ] +POSTHOOK: Lineage: store_sales.ss_hdemo_sk SIMPLE [(store_sales_txt)store_sales_txt.FieldSchema(name:ss_hdemo_sk, type:int, comment:null), ] +POSTHOOK: Lineage: store_sales.ss_item_sk SIMPLE [(store_sales_txt)store_sales_txt.FieldSchema(name:ss_item_sk, type:int, comment:null), ] +POSTHOOK: Lineage: store_sales.ss_list_price SIMPLE [(store_sales_txt)store_sales_txt.FieldSchema(name:ss_list_price, type:float, comment:null), ] +POSTHOOK: Lineage: store_sales.ss_net_paid SIMPLE [(store_sales_txt)store_sales_txt.FieldSchema(name:ss_net_paid, type:float, comment:null), ] +POSTHOOK: Lineage: store_sales.ss_net_paid_inc_tax SIMPLE [(store_sales_txt)store_sales_txt.FieldSchema(name:ss_net_paid_inc_tax, type:float, comment:null), ] +POSTHOOK: Lineage: store_sales.ss_net_profit SIMPLE [(store_sales_txt)store_sales_txt.FieldSchema(name:ss_net_profit, type:float, comment:null), ] +POSTHOOK: Lineage: store_sales.ss_promo_sk SIMPLE [(store_sales_txt)store_sales_txt.FieldSchema(name:ss_promo_sk, type:int, comment:null), ] +POSTHOOK: Lineage: store_sales.ss_quantity SIMPLE [(store_sales_txt)store_sales_txt.FieldSchema(name:ss_quantity, type:int, comment:null), ] +POSTHOOK: Lineage: store_sales.ss_sales_price SIMPLE [(store_sales_txt)store_sales_txt.FieldSchema(name:ss_sales_price, type:float, comment:null), ] +POSTHOOK: Lineage: store_sales.ss_sold_date_sk SIMPLE [(store_sales_txt)store_sales_txt.FieldSchema(name:ss_sold_date_sk, type:int, comment:null), ] +POSTHOOK: Lineage: store_sales.ss_sold_time_sk SIMPLE [(store_sales_txt)store_sales_txt.FieldSchema(name:ss_sold_time_sk, type:int, comment:null), ] +POSTHOOK: Lineage: store_sales.ss_store_sk SIMPLE [(store_sales_txt)store_sales_txt.FieldSchema(name:ss_store_sk, type:int, comment:null), ] +POSTHOOK: Lineage: store_sales.ss_ticket_number SIMPLE [(store_sales_txt)store_sales_txt.FieldSchema(name:ss_ticket_number, type:int, comment:null), ] +POSTHOOK: Lineage: store_sales.ss_wholesale_cost SIMPLE [(store_sales_txt)store_sales_txt.FieldSchema(name:ss_wholesale_cost, type:float, comment:null), ] +PREHOOK: query: create table customer_demographics_txt +( + cd_demo_sk int, + cd_gender string, + cd_marital_status string, + cd_education_status string, + cd_purchase_estimate int, + cd_credit_rating string, + cd_dep_count int, + cd_dep_employed_count int, + cd_dep_college_count int +) +row format delimited fields terminated by '|' +stored as textfile +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@customer_demographics_txt +POSTHOOK: query: create table customer_demographics_txt +( + cd_demo_sk int, + cd_gender string, + cd_marital_status string, + cd_education_status string, + cd_purchase_estimate int, + cd_credit_rating string, + cd_dep_count int, + cd_dep_employed_count int, + cd_dep_college_count int +) +row format delimited fields terminated by '|' +stored as textfile +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@customer_demographics_txt +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/customer_demographics.txt' OVERWRITE INTO TABLE customer_demographics_txt +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@customer_demographics_txt +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/customer_demographics.txt' OVERWRITE INTO TABLE customer_demographics_txt +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@customer_demographics_txt +PREHOOK: query: create table customer_demographics stored as orc as select * from customer_demographics_txt +PREHOOK: type: CREATETABLE_AS_SELECT +PREHOOK: Input: default@customer_demographics_txt +PREHOOK: Output: database:default +PREHOOK: Output: default@customer_demographics +POSTHOOK: query: create table customer_demographics stored as orc as select * from customer_demographics_txt +POSTHOOK: type: CREATETABLE_AS_SELECT +POSTHOOK: Input: default@customer_demographics_txt +POSTHOOK: Output: database:default +POSTHOOK: Output: default@customer_demographics +POSTHOOK: Lineage: customer_demographics.cd_credit_rating SIMPLE [(customer_demographics_txt)customer_demographics_txt.FieldSchema(name:cd_credit_rating, type:string, comment:null), ] +POSTHOOK: Lineage: customer_demographics.cd_demo_sk SIMPLE [(customer_demographics_txt)customer_demographics_txt.FieldSchema(name:cd_demo_sk, type:int, comment:null), ] +POSTHOOK: Lineage: customer_demographics.cd_dep_college_count SIMPLE [(customer_demographics_txt)customer_demographics_txt.FieldSchema(name:cd_dep_college_count, type:int, comment:null), ] +POSTHOOK: Lineage: customer_demographics.cd_dep_count SIMPLE [(customer_demographics_txt)customer_demographics_txt.FieldSchema(name:cd_dep_count, type:int, comment:null), ] +POSTHOOK: Lineage: customer_demographics.cd_dep_employed_count SIMPLE [(customer_demographics_txt)customer_demographics_txt.FieldSchema(name:cd_dep_employed_count, type:int, comment:null), ] +POSTHOOK: Lineage: customer_demographics.cd_education_status SIMPLE [(customer_demographics_txt)customer_demographics_txt.FieldSchema(name:cd_education_status, type:string, comment:null), ] +POSTHOOK: Lineage: customer_demographics.cd_gender SIMPLE [(customer_demographics_txt)customer_demographics_txt.FieldSchema(name:cd_gender, type:string, comment:null), ] +POSTHOOK: Lineage: customer_demographics.cd_marital_status SIMPLE [(customer_demographics_txt)customer_demographics_txt.FieldSchema(name:cd_marital_status, type:string, comment:null), ] +POSTHOOK: Lineage: customer_demographics.cd_purchase_estimate SIMPLE [(customer_demographics_txt)customer_demographics_txt.FieldSchema(name:cd_purchase_estimate, type:int, comment:null), ] +Warning: Map Join MAPJOIN[13][bigTable=store_sales] in task 'Map 2' is a cross product +PREHOOK: query: explain +select count(1) from customer_demographics,store_sales +where ((customer_demographics.cd_demo_sk = store_sales.ss_cdemo_sk and customer_demographics.cd_marital_status = 'M') or + (customer_demographics.cd_demo_sk = store_sales.ss_cdemo_sk and customer_demographics.cd_marital_status = 'U')) +PREHOOK: type: QUERY +POSTHOOK: query: explain +select count(1) from customer_demographics,store_sales +where ((customer_demographics.cd_demo_sk = store_sales.ss_cdemo_sk and customer_demographics.cd_marital_status = 'M') or + (customer_demographics.cd_demo_sk = store_sales.ss_cdemo_sk and customer_demographics.cd_marital_status = 'U')) +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Map 2 <- Map 1 (BROADCAST_EDGE) + Reducer 3 <- Map 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: customer_demographics + Statistics: Num rows: 200 Data size: 74200 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 200 Data size: 74200 Basic stats: COMPLETE Column stats: NONE + value expressions: cd_demo_sk (type: int), cd_marital_status (type: string) + Execution mode: vectorized + Map 2 + Map Operator Tree: + TableScan + alias: store_sales + Statistics: Num rows: 1000 Data size: 88276 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col0, _col2, _col16 + input vertices: + 0 Map 1 + Statistics: Num rows: 200000 Data size: 92055200 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (((_col0 = _col16) and (_col2 = 'M')) or ((_col0 = _col16) and (_col2 = 'U'))) (type: boolean) + Statistics: Num rows: 100000 Data size: 46027600 Basic stats: COMPLETE Column stats: NONE + Select Operator + Statistics: Num rows: 100000 Data size: 46027600 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(1) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) + Execution mode: vectorized + Reducer 3 + Execution mode: vectorized + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +Warning: Map Join MAPJOIN[13][bigTable=store_sales] in task 'Map 2' is a cross product +PREHOOK: query: select count(1) from customer_demographics,store_sales +where ((customer_demographics.cd_demo_sk = store_sales.ss_cdemo_sk and customer_demographics.cd_marital_status = 'M') or + (customer_demographics.cd_demo_sk = store_sales.ss_cdemo_sk and customer_demographics.cd_marital_status = 'U')) +PREHOOK: type: QUERY +PREHOOK: Input: default@customer_demographics +PREHOOK: Input: default@store_sales +#### A masked pattern was here #### +POSTHOOK: query: select count(1) from customer_demographics,store_sales +where ((customer_demographics.cd_demo_sk = store_sales.ss_cdemo_sk and customer_demographics.cd_marital_status = 'M') or + (customer_demographics.cd_demo_sk = store_sales.ss_cdemo_sk and customer_demographics.cd_marital_status = 'U')) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@customer_demographics +POSTHOOK: Input: default@store_sales +#### A masked pattern was here #### +0 http://git-wip-us.apache.org/repos/asf/hive/blob/b7e8d0c9/ql/src/test/results/clientpositive/vector_include_no_sel.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/vector_include_no_sel.q.out b/ql/src/test/results/clientpositive/vector_include_no_sel.q.out new file mode 100644 index 0000000..697d422 --- /dev/null +++ b/ql/src/test/results/clientpositive/vector_include_no_sel.q.out @@ -0,0 +1,282 @@ +PREHOOK: query: -- HIVE-13872 +-- Looking for TableScan immediately followed by ReduceSink (no intervening SEL operator). +-- This caused problems for Vectorizer not eliminating columns which are not included. +-- The input file format didn't fill in those vectorized columns and thus caused NPE in +-- ReduceSink. +-- Only a problem when NOT CBO because of CBO rule-based transforms. +-- +-- Using a cross-product. + +create table store_sales_txt +( + ss_sold_date_sk int, + ss_sold_time_sk int, + ss_item_sk int, + ss_customer_sk int, + ss_cdemo_sk int, + ss_hdemo_sk int, + ss_addr_sk int, + ss_store_sk int, + ss_promo_sk int, + ss_ticket_number int, + ss_quantity int, + ss_wholesale_cost float, + ss_list_price float, + ss_sales_price float, + ss_ext_discount_amt float, + ss_ext_sales_price float, + ss_ext_wholesale_cost float, + ss_ext_list_price float, + ss_ext_tax float, + ss_coupon_amt float, + ss_net_paid float, + ss_net_paid_inc_tax float, + ss_net_profit float +) +row format delimited fields terminated by '|' +stored as textfile +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@store_sales_txt +POSTHOOK: query: -- HIVE-13872 +-- Looking for TableScan immediately followed by ReduceSink (no intervening SEL operator). +-- This caused problems for Vectorizer not eliminating columns which are not included. +-- The input file format didn't fill in those vectorized columns and thus caused NPE in +-- ReduceSink. +-- Only a problem when NOT CBO because of CBO rule-based transforms. +-- +-- Using a cross-product. + +create table store_sales_txt +( + ss_sold_date_sk int, + ss_sold_time_sk int, + ss_item_sk int, + ss_customer_sk int, + ss_cdemo_sk int, + ss_hdemo_sk int, + ss_addr_sk int, + ss_store_sk int, + ss_promo_sk int, + ss_ticket_number int, + ss_quantity int, + ss_wholesale_cost float, + ss_list_price float, + ss_sales_price float, + ss_ext_discount_amt float, + ss_ext_sales_price float, + ss_ext_wholesale_cost float, + ss_ext_list_price float, + ss_ext_tax float, + ss_coupon_amt float, + ss_net_paid float, + ss_net_paid_inc_tax float, + ss_net_profit float +) +row format delimited fields terminated by '|' +stored as textfile +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@store_sales_txt +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/store_sales.txt' OVERWRITE INTO TABLE store_sales_txt +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@store_sales_txt +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/store_sales.txt' OVERWRITE INTO TABLE store_sales_txt +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@store_sales_txt +PREHOOK: query: create table store_sales stored as orc as select * from store_sales_txt +PREHOOK: type: CREATETABLE_AS_SELECT +PREHOOK: Input: default@store_sales_txt +PREHOOK: Output: database:default +PREHOOK: Output: default@store_sales +POSTHOOK: query: create table store_sales stored as orc as select * from store_sales_txt +POSTHOOK: type: CREATETABLE_AS_SELECT +POSTHOOK: Input: default@store_sales_txt +POSTHOOK: Output: database:default +POSTHOOK: Output: default@store_sales +POSTHOOK: Lineage: store_sales.ss_addr_sk SIMPLE [(store_sales_txt)store_sales_txt.FieldSchema(name:ss_addr_sk, type:int, comment:null), ] +POSTHOOK: Lineage: store_sales.ss_cdemo_sk SIMPLE [(store_sales_txt)store_sales_txt.FieldSchema(name:ss_cdemo_sk, type:int, comment:null), ] +POSTHOOK: Lineage: store_sales.ss_coupon_amt SIMPLE [(store_sales_txt)store_sales_txt.FieldSchema(name:ss_coupon_amt, type:float, comment:null), ] +POSTHOOK: Lineage: store_sales.ss_customer_sk SIMPLE [(store_sales_txt)store_sales_txt.FieldSchema(name:ss_customer_sk, type:int, comment:null), ] +POSTHOOK: Lineage: store_sales.ss_ext_discount_amt SIMPLE [(store_sales_txt)store_sales_txt.FieldSchema(name:ss_ext_discount_amt, type:float, comment:null), ] +POSTHOOK: Lineage: store_sales.ss_ext_list_price SIMPLE [(store_sales_txt)store_sales_txt.FieldSchema(name:ss_ext_list_price, type:float, comment:null), ] +POSTHOOK: Lineage: store_sales.ss_ext_sales_price SIMPLE [(store_sales_txt)store_sales_txt.FieldSchema(name:ss_ext_sales_price, type:float, comment:null), ] +POSTHOOK: Lineage: store_sales.ss_ext_tax SIMPLE [(store_sales_txt)store_sales_txt.FieldSchema(name:ss_ext_tax, type:float, comment:null), ] +POSTHOOK: Lineage: store_sales.ss_ext_wholesale_cost SIMPLE [(store_sales_txt)store_sales_txt.FieldSchema(name:ss_ext_wholesale_cost, type:float, comment:null), ] +POSTHOOK: Lineage: store_sales.ss_hdemo_sk SIMPLE [(store_sales_txt)store_sales_txt.FieldSchema(name:ss_hdemo_sk, type:int, comment:null), ] +POSTHOOK: Lineage: store_sales.ss_item_sk SIMPLE [(store_sales_txt)store_sales_txt.FieldSchema(name:ss_item_sk, type:int, comment:null), ] +POSTHOOK: Lineage: store_sales.ss_list_price SIMPLE [(store_sales_txt)store_sales_txt.FieldSchema(name:ss_list_price, type:float, comment:null), ] +POSTHOOK: Lineage: store_sales.ss_net_paid SIMPLE [(store_sales_txt)store_sales_txt.FieldSchema(name:ss_net_paid, type:float, comment:null), ] +POSTHOOK: Lineage: store_sales.ss_net_paid_inc_tax SIMPLE [(store_sales_txt)store_sales_txt.FieldSchema(name:ss_net_paid_inc_tax, type:float, comment:null), ] +POSTHOOK: Lineage: store_sales.ss_net_profit SIMPLE [(store_sales_txt)store_sales_txt.FieldSchema(name:ss_net_profit, type:float, comment:null), ] +POSTHOOK: Lineage: store_sales.ss_promo_sk SIMPLE [(store_sales_txt)store_sales_txt.FieldSchema(name:ss_promo_sk, type:int, comment:null), ] +POSTHOOK: Lineage: store_sales.ss_quantity SIMPLE [(store_sales_txt)store_sales_txt.FieldSchema(name:ss_quantity, type:int, comment:null), ] +POSTHOOK: Lineage: store_sales.ss_sales_price SIMPLE [(store_sales_txt)store_sales_txt.FieldSchema(name:ss_sales_price, type:float, comment:null), ] +POSTHOOK: Lineage: store_sales.ss_sold_date_sk SIMPLE [(store_sales_txt)store_sales_txt.FieldSchema(name:ss_sold_date_sk, type:int, comment:null), ] +POSTHOOK: Lineage: store_sales.ss_sold_time_sk SIMPLE [(store_sales_txt)store_sales_txt.FieldSchema(name:ss_sold_time_sk, type:int, comment:null), ] +POSTHOOK: Lineage: store_sales.ss_store_sk SIMPLE [(store_sales_txt)store_sales_txt.FieldSchema(name:ss_store_sk, type:int, comment:null), ] +POSTHOOK: Lineage: store_sales.ss_ticket_number SIMPLE [(store_sales_txt)store_sales_txt.FieldSchema(name:ss_ticket_number, type:int, comment:null), ] +POSTHOOK: Lineage: store_sales.ss_wholesale_cost SIMPLE [(store_sales_txt)store_sales_txt.FieldSchema(name:ss_wholesale_cost, type:float, comment:null), ] +PREHOOK: query: create table customer_demographics_txt +( + cd_demo_sk int, + cd_gender string, + cd_marital_status string, + cd_education_status string, + cd_purchase_estimate int, + cd_credit_rating string, + cd_dep_count int, + cd_dep_employed_count int, + cd_dep_college_count int +) +row format delimited fields terminated by '|' +stored as textfile +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@customer_demographics_txt +POSTHOOK: query: create table customer_demographics_txt +( + cd_demo_sk int, + cd_gender string, + cd_marital_status string, + cd_education_status string, + cd_purchase_estimate int, + cd_credit_rating string, + cd_dep_count int, + cd_dep_employed_count int, + cd_dep_college_count int +) +row format delimited fields terminated by '|' +stored as textfile +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@customer_demographics_txt +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/customer_demographics.txt' OVERWRITE INTO TABLE customer_demographics_txt +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@customer_demographics_txt +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/customer_demographics.txt' OVERWRITE INTO TABLE customer_demographics_txt +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@customer_demographics_txt +PREHOOK: query: create table customer_demographics stored as orc as select * from customer_demographics_txt +PREHOOK: type: CREATETABLE_AS_SELECT +PREHOOK: Input: default@customer_demographics_txt +PREHOOK: Output: database:default +PREHOOK: Output: default@customer_demographics +POSTHOOK: query: create table customer_demographics stored as orc as select * from customer_demographics_txt +POSTHOOK: type: CREATETABLE_AS_SELECT +POSTHOOK: Input: default@customer_demographics_txt +POSTHOOK: Output: database:default +POSTHOOK: Output: default@customer_demographics +POSTHOOK: Lineage: customer_demographics.cd_credit_rating SIMPLE [(customer_demographics_txt)customer_demographics_txt.FieldSchema(name:cd_credit_rating, type:string, comment:null), ] +POSTHOOK: Lineage: customer_demographics.cd_demo_sk SIMPLE [(customer_demographics_txt)customer_demographics_txt.FieldSchema(name:cd_demo_sk, type:int, comment:null), ] +POSTHOOK: Lineage: customer_demographics.cd_dep_college_count SIMPLE [(customer_demographics_txt)customer_demographics_txt.FieldSchema(name:cd_dep_college_count, type:int, comment:null), ] +POSTHOOK: Lineage: customer_demographics.cd_dep_count SIMPLE [(customer_demographics_txt)customer_demographics_txt.FieldSchema(name:cd_dep_count, type:int, comment:null), ] +POSTHOOK: Lineage: customer_demographics.cd_dep_employed_count SIMPLE [(customer_demographics_txt)customer_demographics_txt.FieldSchema(name:cd_dep_employed_count, type:int, comment:null), ] +POSTHOOK: Lineage: customer_demographics.cd_education_status SIMPLE [(customer_demographics_txt)customer_demographics_txt.FieldSchema(name:cd_education_status, type:string, comment:null), ] +POSTHOOK: Lineage: customer_demographics.cd_gender SIMPLE [(customer_demographics_txt)customer_demographics_txt.FieldSchema(name:cd_gender, type:string, comment:null), ] +POSTHOOK: Lineage: customer_demographics.cd_marital_status SIMPLE [(customer_demographics_txt)customer_demographics_txt.FieldSchema(name:cd_marital_status, type:string, comment:null), ] +POSTHOOK: Lineage: customer_demographics.cd_purchase_estimate SIMPLE [(customer_demographics_txt)customer_demographics_txt.FieldSchema(name:cd_purchase_estimate, type:int, comment:null), ] +Warning: Map Join MAPJOIN[15][bigTable=store_sales] in task 'Stage-2:MAPRED' is a cross product +PREHOOK: query: explain +select count(1) from customer_demographics,store_sales +where ((customer_demographics.cd_demo_sk = store_sales.ss_cdemo_sk and customer_demographics.cd_marital_status = 'M') or + (customer_demographics.cd_demo_sk = store_sales.ss_cdemo_sk and customer_demographics.cd_marital_status = 'U')) +PREHOOK: type: QUERY +POSTHOOK: query: explain +select count(1) from customer_demographics,store_sales +where ((customer_demographics.cd_demo_sk = store_sales.ss_cdemo_sk and customer_demographics.cd_marital_status = 'M') or + (customer_demographics.cd_demo_sk = store_sales.ss_cdemo_sk and customer_demographics.cd_marital_status = 'U')) +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-5 is a root stage + Stage-2 depends on stages: Stage-5 + Stage-0 depends on stages: Stage-2 + +STAGE PLANS: + Stage: Stage-5 + Map Reduce Local Work + Alias -> Map Local Tables: + customer_demographics + Fetch Operator + limit: -1 + Alias -> Map Local Operator Tree: + customer_demographics + TableScan + alias: customer_demographics + Statistics: Num rows: 200 Data size: 74200 Basic stats: COMPLETE Column stats: NONE + HashTable Sink Operator + keys: + 0 + 1 + + Stage: Stage-2 + Map Reduce + Map Operator Tree: + TableScan + alias: store_sales + Statistics: Num rows: 1000 Data size: 88276 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col0, _col2, _col16 + Statistics: Num rows: 200000 Data size: 92055200 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (((_col0 = _col16) and (_col2 = 'M')) or ((_col0 = _col16) and (_col2 = 'U'))) (type: boolean) + Statistics: Num rows: 100000 Data size: 46027600 Basic stats: COMPLETE Column stats: NONE + Select Operator + Statistics: Num rows: 100000 Data size: 46027600 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(1) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) + Execution mode: vectorized + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +Warning: Map Join MAPJOIN[15][bigTable=store_sales] in task 'Stage-2:MAPRED' is a cross product +PREHOOK: query: select count(1) from customer_demographics,store_sales +where ((customer_demographics.cd_demo_sk = store_sales.ss_cdemo_sk and customer_demographics.cd_marital_status = 'M') or + (customer_demographics.cd_demo_sk = store_sales.ss_cdemo_sk and customer_demographics.cd_marital_status = 'U')) +PREHOOK: type: QUERY +PREHOOK: Input: default@customer_demographics +PREHOOK: Input: default@store_sales +#### A masked pattern was here #### +POSTHOOK: query: select count(1) from customer_demographics,store_sales +where ((customer_demographics.cd_demo_sk = store_sales.ss_cdemo_sk and customer_demographics.cd_marital_status = 'M') or + (customer_demographics.cd_demo_sk = store_sales.ss_cdemo_sk and customer_demographics.cd_marital_status = 'U')) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@customer_demographics +POSTHOOK: Input: default@store_sales +#### A masked pattern was here #### +0