You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by vg...@apache.org on 2018/10/15 03:33:50 UTC
[2/3] hive git commit: HIVE-17043: Remove non unique columns from
group by keys if not referenced later (Vineet Garg,
reviewed by Jesus Camacho Rodriguez)
http://git-wip-us.apache.org/repos/asf/hive/blob/1db3debc/ql/src/test/results/clientpositive/llap/constraints_optimization.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/constraints_optimization.q.out b/ql/src/test/results/clientpositive/llap/constraints_optimization.q.out
new file mode 100644
index 0000000..b45b7c4
--- /dev/null
+++ b/ql/src/test/results/clientpositive/llap/constraints_optimization.q.out
@@ -0,0 +1,2010 @@
+PREHOOK: query: CREATE TABLE `customer_removal_n0`(
+ `c_custkey` bigint,
+ `c_name` string,
+ `c_address` string,
+ `c_city` string,
+ `c_nation` string,
+ `c_region` string,
+ `c_phone` string,
+ `c_mktsegment` string,
+ primary key (`c_custkey`) disable rely)
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@customer_removal_n0
+POSTHOOK: query: CREATE TABLE `customer_removal_n0`(
+ `c_custkey` bigint,
+ `c_name` string,
+ `c_address` string,
+ `c_city` string,
+ `c_nation` string,
+ `c_region` string,
+ `c_phone` string,
+ `c_mktsegment` string,
+ primary key (`c_custkey`) disable rely)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@customer_removal_n0
+PREHOOK: query: CREATE TABLE `dates_removal_n0`(
+ `d_datekey` bigint,
+ `d_id` bigint,
+ `d_date` string,
+ `d_dayofweek` string,
+ `d_month` string,
+ `d_year` int,
+ `d_yearmonthnum` int,
+ `d_yearmonth` string,
+ `d_daynuminweek` int,
+ `d_daynuminmonth` int,
+ `d_daynuminyear` int,
+ `d_monthnuminyear` int,
+ `d_weeknuminyear` int,
+ `d_sellingseason` string,
+ `d_lastdayinweekfl` int,
+ `d_lastdayinmonthfl` int,
+ `d_holidayfl` int ,
+ `d_weekdayfl`int,
+ primary key (`d_datekey`, `d_id`) disable rely)
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@dates_removal_n0
+POSTHOOK: query: CREATE TABLE `dates_removal_n0`(
+ `d_datekey` bigint,
+ `d_id` bigint,
+ `d_date` string,
+ `d_dayofweek` string,
+ `d_month` string,
+ `d_year` int,
+ `d_yearmonthnum` int,
+ `d_yearmonth` string,
+ `d_daynuminweek` int,
+ `d_daynuminmonth` int,
+ `d_daynuminyear` int,
+ `d_monthnuminyear` int,
+ `d_weeknuminyear` int,
+ `d_sellingseason` string,
+ `d_lastdayinweekfl` int,
+ `d_lastdayinmonthfl` int,
+ `d_holidayfl` int ,
+ `d_weekdayfl`int,
+ primary key (`d_datekey`, `d_id`) disable rely)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@dates_removal_n0
+PREHOOK: query: -- group by key has single primary key
+ EXPLAIN SELECT c_custkey from customer_removal_n0 where c_nation IN ('USA', 'INDIA') group by c_custkey
+PREHOOK: type: QUERY
+PREHOOK: Input: default@customer_removal_n0
+#### A masked pattern was here ####
+POSTHOOK: query: -- group by key has single primary key
+ EXPLAIN SELECT c_custkey from customer_removal_n0 where c_nation IN ('USA', 'INDIA') group by c_custkey
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@customer_removal_n0
+#### A masked pattern was here ####
+STAGE DEPENDENCIES:
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ TableScan
+ alias: customer_removal_n0
+ filterExpr: (c_nation) IN ('USA', 'INDIA') (type: boolean)
+ Filter Operator
+ predicate: (c_nation) IN ('USA', 'INDIA') (type: boolean)
+ Select Operator
+ expressions: c_custkey (type: bigint)
+ outputColumnNames: _col0
+ ListSink
+
+PREHOOK: query: -- mix of primary + non-primary keys
+ EXPLAIN SELECT c_custkey from customer_removal_n0 where c_nation IN ('USA', 'INDIA') group by c_custkey, c_nation
+PREHOOK: type: QUERY
+PREHOOK: Input: default@customer_removal_n0
+#### A masked pattern was here ####
+POSTHOOK: query: -- mix of primary + non-primary keys
+ EXPLAIN SELECT c_custkey from customer_removal_n0 where c_nation IN ('USA', 'INDIA') group by c_custkey, c_nation
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@customer_removal_n0
+#### A masked pattern was here ####
+STAGE DEPENDENCIES:
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ TableScan
+ alias: customer_removal_n0
+ filterExpr: (c_nation) IN ('USA', 'INDIA') (type: boolean)
+ Filter Operator
+ predicate: (c_nation) IN ('USA', 'INDIA') (type: boolean)
+ Select Operator
+ expressions: c_custkey (type: bigint)
+ outputColumnNames: _col0
+ ListSink
+
+PREHOOK: query: -- multiple keys
+ EXPLAIN SELECT d_datekey from dates_removal_n0 where d_year IN (1985, 2004) group by d_datekey, d_id
+PREHOOK: type: QUERY
+PREHOOK: Input: default@dates_removal_n0
+#### A masked pattern was here ####
+POSTHOOK: query: -- multiple keys
+ EXPLAIN SELECT d_datekey from dates_removal_n0 where d_year IN (1985, 2004) group by d_datekey, d_id
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dates_removal_n0
+#### A masked pattern was here ####
+STAGE DEPENDENCIES:
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ TableScan
+ alias: dates_removal_n0
+ filterExpr: (d_year) IN (1985, 2004) (type: boolean)
+ Filter Operator
+ predicate: (d_year) IN (1985, 2004) (type: boolean)
+ Select Operator
+ expressions: d_datekey (type: bigint)
+ outputColumnNames: _col0
+ ListSink
+
+PREHOOK: query: -- multiple keys + non-keys + different order
+ EXPLAIN SELECT d_datekey from dates_removal_n0 where d_year IN (1985, 2004) group by d_id, d_datekey, d_sellingseason
+ order by d_datekey limit 10
+PREHOOK: type: QUERY
+PREHOOK: Input: default@dates_removal_n0
+#### A masked pattern was here ####
+POSTHOOK: query: -- multiple keys + non-keys + different order
+ EXPLAIN SELECT d_datekey from dates_removal_n0 where d_year IN (1985, 2004) group by d_id, d_datekey, d_sellingseason
+ order by d_datekey limit 10
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dates_removal_n0
+#### A masked pattern was here ####
+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:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: dates_removal_n0
+ filterExpr: (d_year) IN (1985, 2004) (type: boolean)
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (d_year) IN (1985, 2004) (type: boolean)
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: d_datekey (type: bigint)
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: bigint)
+ sort order: +
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ TopN Hash Memory Usage: 0.1
+ Execution mode: vectorized, llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: vectorized, llap
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey0 (type: bigint)
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Limit
+ Number of rows: 10
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 12 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: 10
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: -- multiple keys in different order and mixed with non-keys
+ EXPLAIN SELECT d_datekey from dates_removal_n0 where d_year IN (1985, 2004) group by d_id, d_daynuminmonth, d_datekey,
+ d_sellingseason order by d_datekey limit 10
+PREHOOK: type: QUERY
+PREHOOK: Input: default@dates_removal_n0
+#### A masked pattern was here ####
+POSTHOOK: query: -- multiple keys in different order and mixed with non-keys
+ EXPLAIN SELECT d_datekey from dates_removal_n0 where d_year IN (1985, 2004) group by d_id, d_daynuminmonth, d_datekey,
+ d_sellingseason order by d_datekey limit 10
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dates_removal_n0
+#### A masked pattern was here ####
+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:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: dates_removal_n0
+ filterExpr: (d_year) IN (1985, 2004) (type: boolean)
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (d_year) IN (1985, 2004) (type: boolean)
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: d_datekey (type: bigint)
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: bigint)
+ sort order: +
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ TopN Hash Memory Usage: 0.1
+ Execution mode: vectorized, llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: vectorized, llap
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey0 (type: bigint)
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Limit
+ Number of rows: 10
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 12 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: 10
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: -- same as above but with aggregate
+ EXPLAIN SELECT count(d_datekey) from dates_removal_n0 where d_year IN (1985, 2004) group by d_id, d_daynuminmonth, d_datekey,
+ d_sellingseason order by d_datekey limit 10
+PREHOOK: type: QUERY
+PREHOOK: Input: default@dates_removal_n0
+#### A masked pattern was here ####
+POSTHOOK: query: -- same as above but with aggregate
+ EXPLAIN SELECT count(d_datekey) from dates_removal_n0 where d_year IN (1985, 2004) group by d_id, d_daynuminmonth, d_datekey,
+ d_sellingseason order by d_datekey limit 10
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dates_removal_n0
+#### A masked pattern was here ####
+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:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: dates_removal_n0
+ filterExpr: (d_year) IN (1985, 2004) (type: boolean)
+ Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (d_year) IN (1985, 2004) (type: boolean)
+ Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: d_datekey (type: bigint), d_id (type: bigint)
+ outputColumnNames: d_datekey, d_id
+ Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: NONE
+ Top N Key Operator
+ sort order: ++
+ keys: d_datekey (type: bigint), d_id (type: bigint)
+ Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: NONE
+ top n: 10
+ Group By Operator
+ aggregations: count()
+ keys: d_datekey (type: bigint), d_id (type: bigint)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: bigint), _col1 (type: bigint)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: bigint), _col1 (type: bigint)
+ Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: NONE
+ TopN Hash Memory Usage: 0.1
+ value expressions: _col2 (type: bigint)
+ Execution mode: vectorized, llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: vectorized, llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ keys: KEY._col0 (type: bigint), KEY._col1 (type: bigint)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col2 (type: bigint), _col0 (type: bigint)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col1 (type: bigint)
+ sort order: +
+ Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: NONE
+ TopN Hash Memory Usage: 0.1
+ value expressions: _col0 (type: bigint)
+ Reducer 3
+ Execution mode: vectorized, llap
+ Reduce Operator Tree:
+ Select Operator
+ expressions: VALUE._col0 (type: bigint)
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: NONE
+ Limit
+ Number of rows: 10
+ Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 20 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
+
+PREHOOK: query: -- join
+ insert into dates_removal_n0(d_datekey, d_id) values(3, 0)
+PREHOOK: type: QUERY
+PREHOOK: Input: _dummy_database@_dummy_table
+PREHOOK: Output: default@dates_removal_n0
+POSTHOOK: query: -- join
+ insert into dates_removal_n0(d_datekey, d_id) values(3, 0)
+POSTHOOK: type: QUERY
+POSTHOOK: Input: _dummy_database@_dummy_table
+POSTHOOK: Output: default@dates_removal_n0
+POSTHOOK: Lineage: dates_removal_n0.d_date SIMPLE []
+POSTHOOK: Lineage: dates_removal_n0.d_datekey SCRIPT []
+POSTHOOK: Lineage: dates_removal_n0.d_daynuminmonth SIMPLE []
+POSTHOOK: Lineage: dates_removal_n0.d_daynuminweek SIMPLE []
+POSTHOOK: Lineage: dates_removal_n0.d_daynuminyear SIMPLE []
+POSTHOOK: Lineage: dates_removal_n0.d_dayofweek SIMPLE []
+POSTHOOK: Lineage: dates_removal_n0.d_holidayfl SIMPLE []
+POSTHOOK: Lineage: dates_removal_n0.d_id SCRIPT []
+POSTHOOK: Lineage: dates_removal_n0.d_lastdayinmonthfl SIMPLE []
+POSTHOOK: Lineage: dates_removal_n0.d_lastdayinweekfl SIMPLE []
+POSTHOOK: Lineage: dates_removal_n0.d_month SIMPLE []
+POSTHOOK: Lineage: dates_removal_n0.d_monthnuminyear SIMPLE []
+POSTHOOK: Lineage: dates_removal_n0.d_sellingseason SIMPLE []
+POSTHOOK: Lineage: dates_removal_n0.d_weekdayfl SIMPLE []
+POSTHOOK: Lineage: dates_removal_n0.d_weeknuminyear SIMPLE []
+POSTHOOK: Lineage: dates_removal_n0.d_year SIMPLE []
+POSTHOOK: Lineage: dates_removal_n0.d_yearmonth SIMPLE []
+POSTHOOK: Lineage: dates_removal_n0.d_yearmonthnum SIMPLE []
+PREHOOK: query: insert into dates_removal_n0(d_datekey, d_id) values(3, 1)
+PREHOOK: type: QUERY
+PREHOOK: Input: _dummy_database@_dummy_table
+PREHOOK: Output: default@dates_removal_n0
+POSTHOOK: query: insert into dates_removal_n0(d_datekey, d_id) values(3, 1)
+POSTHOOK: type: QUERY
+POSTHOOK: Input: _dummy_database@_dummy_table
+POSTHOOK: Output: default@dates_removal_n0
+POSTHOOK: Lineage: dates_removal_n0.d_date SIMPLE []
+POSTHOOK: Lineage: dates_removal_n0.d_datekey SCRIPT []
+POSTHOOK: Lineage: dates_removal_n0.d_daynuminmonth SIMPLE []
+POSTHOOK: Lineage: dates_removal_n0.d_daynuminweek SIMPLE []
+POSTHOOK: Lineage: dates_removal_n0.d_daynuminyear SIMPLE []
+POSTHOOK: Lineage: dates_removal_n0.d_dayofweek SIMPLE []
+POSTHOOK: Lineage: dates_removal_n0.d_holidayfl SIMPLE []
+POSTHOOK: Lineage: dates_removal_n0.d_id SCRIPT []
+POSTHOOK: Lineage: dates_removal_n0.d_lastdayinmonthfl SIMPLE []
+POSTHOOK: Lineage: dates_removal_n0.d_lastdayinweekfl SIMPLE []
+POSTHOOK: Lineage: dates_removal_n0.d_month SIMPLE []
+POSTHOOK: Lineage: dates_removal_n0.d_monthnuminyear SIMPLE []
+POSTHOOK: Lineage: dates_removal_n0.d_sellingseason SIMPLE []
+POSTHOOK: Lineage: dates_removal_n0.d_weekdayfl SIMPLE []
+POSTHOOK: Lineage: dates_removal_n0.d_weeknuminyear SIMPLE []
+POSTHOOK: Lineage: dates_removal_n0.d_year SIMPLE []
+POSTHOOK: Lineage: dates_removal_n0.d_yearmonth SIMPLE []
+POSTHOOK: Lineage: dates_removal_n0.d_yearmonthnum SIMPLE []
+PREHOOK: query: insert into customer_removal_n0 (c_custkey) values(3)
+PREHOOK: type: QUERY
+PREHOOK: Input: _dummy_database@_dummy_table
+PREHOOK: Output: default@customer_removal_n0
+POSTHOOK: query: insert into customer_removal_n0 (c_custkey) values(3)
+POSTHOOK: type: QUERY
+POSTHOOK: Input: _dummy_database@_dummy_table
+POSTHOOK: Output: default@customer_removal_n0
+POSTHOOK: Lineage: customer_removal_n0.c_address SIMPLE []
+POSTHOOK: Lineage: customer_removal_n0.c_city SIMPLE []
+POSTHOOK: Lineage: customer_removal_n0.c_custkey SCRIPT []
+POSTHOOK: Lineage: customer_removal_n0.c_mktsegment SIMPLE []
+POSTHOOK: Lineage: customer_removal_n0.c_name SIMPLE []
+POSTHOOK: Lineage: customer_removal_n0.c_nation SIMPLE []
+POSTHOOK: Lineage: customer_removal_n0.c_phone SIMPLE []
+POSTHOOK: Lineage: customer_removal_n0.c_region SIMPLE []
+PREHOOK: query: EXPLAIN SELECT d_datekey from dates_removal_n0 join customer_removal_n0 on d_datekey = c_custkey group by d_datekey, d_id
+PREHOOK: type: QUERY
+PREHOOK: Input: default@customer_removal_n0
+PREHOOK: Input: default@dates_removal_n0
+#### A masked pattern was here ####
+POSTHOOK: query: EXPLAIN SELECT d_datekey from dates_removal_n0 join customer_removal_n0 on d_datekey = c_custkey group by d_datekey, d_id
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@customer_removal_n0
+POSTHOOK: Input: default@dates_removal_n0
+#### A masked pattern was here ####
+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:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: dates_removal_n0
+ Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: d_datekey (type: bigint)
+ outputColumnNames: _col0
+ Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: bigint)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: bigint)
+ Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: vectorized, llap
+ LLAP IO: no inputs
+ Map 3
+ Map Operator Tree:
+ TableScan
+ alias: customer_removal_n0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: c_custkey (type: bigint)
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: bigint)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: bigint)
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: vectorized, llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Merge Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: bigint)
+ 1 _col0 (type: bigint)
+ outputColumnNames: _col0
+ Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
+ 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
+
+PREHOOK: query: SELECT d_datekey from dates_removal_n0 join customer_removal_n0 on d_datekey = c_custkey group by d_datekey, d_id
+PREHOOK: type: QUERY
+PREHOOK: Input: default@customer_removal_n0
+PREHOOK: Input: default@dates_removal_n0
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT d_datekey from dates_removal_n0 join customer_removal_n0 on d_datekey = c_custkey group by d_datekey, d_id
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@customer_removal_n0
+POSTHOOK: Input: default@dates_removal_n0
+#### A masked pattern was here ####
+3
+3
+PREHOOK: query: -- group by keys are not primary keys
+ EXPLAIN SELECT d_datekey from dates_removal_n0 where d_year IN (1985, 2004) group by d_datekey, d_sellingseason
+ order by d_datekey limit 10
+PREHOOK: type: QUERY
+PREHOOK: Input: default@dates_removal_n0
+#### A masked pattern was here ####
+POSTHOOK: query: -- group by keys are not primary keys
+ EXPLAIN SELECT d_datekey from dates_removal_n0 where d_year IN (1985, 2004) group by d_datekey, d_sellingseason
+ order by d_datekey limit 10
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dates_removal_n0
+#### A masked pattern was here ####
+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:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: dates_removal_n0
+ filterExpr: (d_year) IN (1985, 2004) (type: boolean)
+ Statistics: Num rows: 2 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: (d_year) IN (1985, 2004) (type: boolean)
+ Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: d_datekey (type: bigint), d_sellingseason (type: string)
+ outputColumnNames: d_datekey, d_sellingseason
+ Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
+ Top N Key Operator
+ sort order: ++
+ keys: d_datekey (type: bigint), d_sellingseason (type: string)
+ Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
+ top n: 10
+ Group By Operator
+ keys: d_datekey (type: bigint), d_sellingseason (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: bigint), _col1 (type: string)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: bigint), _col1 (type: string)
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ TopN Hash Memory Usage: 0.1
+ Execution mode: vectorized, llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: vectorized, llap
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: bigint), KEY._col1 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: bigint)
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: bigint)
+ sort order: +
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ TopN Hash Memory Usage: 0.1
+ Reducer 3
+ Execution mode: vectorized, llap
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey0 (type: bigint)
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Limit
+ Number of rows: 10
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ 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: 10
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: -- negative
+ -- with aggregate function
+ EXPLAIN SELECT count(c_custkey) from customer_removal_n0 where c_nation IN ('USA', 'INDIA')
+ group by c_custkey, c_nation
+PREHOOK: type: QUERY
+PREHOOK: Input: default@customer_removal_n0
+#### A masked pattern was here ####
+POSTHOOK: query: -- negative
+ -- with aggregate function
+ EXPLAIN SELECT count(c_custkey) from customer_removal_n0 where c_nation IN ('USA', 'INDIA')
+ group by c_custkey, c_nation
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@customer_removal_n0
+#### A masked pattern was here ####
+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:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: customer_removal_n0
+ filterExpr: (c_nation) IN ('USA', 'INDIA') (type: boolean)
+ Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: (c_nation) IN ('USA', 'INDIA') (type: boolean)
+ Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: c_custkey (type: bigint)
+ outputColumnNames: c_custkey
+ Statistics: Num rows: 1 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: count()
+ keys: c_custkey (type: bigint)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: bigint)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: bigint)
+ Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: bigint)
+ Execution mode: vectorized, llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: vectorized, llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ keys: KEY._col0 (type: bigint)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col1 (type: bigint)
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ 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
+
+PREHOOK: query: DROP TABLE customer_removal_n0
+PREHOOK: type: DROPTABLE
+PREHOOK: Input: default@customer_removal_n0
+PREHOOK: Output: default@customer_removal_n0
+POSTHOOK: query: DROP TABLE customer_removal_n0
+POSTHOOK: type: DROPTABLE
+POSTHOOK: Input: default@customer_removal_n0
+POSTHOOK: Output: default@customer_removal_n0
+PREHOOK: query: DROP TABLE dates_removal_n0
+PREHOOK: type: DROPTABLE
+PREHOOK: Input: default@dates_removal_n0
+PREHOOK: Output: default@dates_removal_n0
+POSTHOOK: query: DROP TABLE dates_removal_n0
+POSTHOOK: type: DROPTABLE
+POSTHOOK: Input: default@dates_removal_n0
+POSTHOOK: Output: default@dates_removal_n0
+PREHOOK: query: -- group by reduction optimization
+ create table dest_g21 (key1 int, value1 double, primary key(key1) disable rely)
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@dest_g21
+POSTHOOK: query: -- group by reduction optimization
+ create table dest_g21 (key1 int, value1 double, primary key(key1) disable rely)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@dest_g21
+PREHOOK: query: insert into dest_g21 values(1, 2), (2,2), (3, 1), (4,4), (5, null), (6, null)
+PREHOOK: type: QUERY
+PREHOOK: Input: _dummy_database@_dummy_table
+PREHOOK: Output: default@dest_g21
+POSTHOOK: query: insert into dest_g21 values(1, 2), (2,2), (3, 1), (4,4), (5, null), (6, null)
+POSTHOOK: type: QUERY
+POSTHOOK: Input: _dummy_database@_dummy_table
+POSTHOOK: Output: default@dest_g21
+POSTHOOK: Lineage: dest_g21.key1 SCRIPT []
+POSTHOOK: Lineage: dest_g21.value1 SCRIPT []
+PREHOOK: query: -- value1 will removed because it is unused, then whole group by will be removed because key1 is unique
+ explain select key1 from dest_g21 group by key1, value1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@dest_g21
+#### A masked pattern was here ####
+POSTHOOK: query: -- value1 will removed because it is unused, then whole group by will be removed because key1 is unique
+ explain select key1 from dest_g21 group by key1, value1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dest_g21
+#### A masked pattern was here ####
+STAGE DEPENDENCIES:
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ TableScan
+ alias: dest_g21
+ Select Operator
+ expressions: key1 (type: int)
+ outputColumnNames: _col0
+ ListSink
+
+PREHOOK: query: select key1 from dest_g21 group by key1, value1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@dest_g21
+#### A masked pattern was here ####
+POSTHOOK: query: select key1 from dest_g21 group by key1, value1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dest_g21
+#### A masked pattern was here ####
+1
+2
+3
+4
+5
+6
+PREHOOK: query: -- same query but with filter
+ explain select key1 from dest_g21 where value1 > 1 group by key1, value1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@dest_g21
+#### A masked pattern was here ####
+POSTHOOK: query: -- same query but with filter
+ explain select key1 from dest_g21 where value1 > 1 group by key1, value1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dest_g21
+#### A masked pattern was here ####
+STAGE DEPENDENCIES:
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ TableScan
+ alias: dest_g21
+ filterExpr: (value1 > 1.0D) (type: boolean)
+ Filter Operator
+ predicate: (value1 > 1.0D) (type: boolean)
+ Select Operator
+ expressions: key1 (type: int)
+ outputColumnNames: _col0
+ ListSink
+
+PREHOOK: query: select key1 from dest_g21 where value1 > 1 group by key1, value1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@dest_g21
+#### A masked pattern was here ####
+POSTHOOK: query: select key1 from dest_g21 where value1 > 1 group by key1, value1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dest_g21
+#### A masked pattern was here ####
+1
+2
+4
+PREHOOK: query: explain select key1 from dest_g21 where key1 > 1 group by key1, value1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@dest_g21
+#### A masked pattern was here ####
+POSTHOOK: query: explain select key1 from dest_g21 where key1 > 1 group by key1, value1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dest_g21
+#### A masked pattern was here ####
+STAGE DEPENDENCIES:
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ TableScan
+ alias: dest_g21
+ filterExpr: (key1 > 1) (type: boolean)
+ Filter Operator
+ predicate: (key1 > 1) (type: boolean)
+ Select Operator
+ expressions: key1 (type: int)
+ outputColumnNames: _col0
+ ListSink
+
+PREHOOK: query: select key1 from dest_g21 where key1 > 1 group by key1, value1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@dest_g21
+#### A masked pattern was here ####
+POSTHOOK: query: select key1 from dest_g21 where key1 > 1 group by key1, value1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dest_g21
+#### A masked pattern was here ####
+2
+3
+4
+5
+6
+PREHOOK: query: -- only value1 will be removed because there is aggregate call
+ explain select count(key1) from dest_g21 group by key1, value1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@dest_g21
+#### A masked pattern was here ####
+POSTHOOK: query: -- only value1 will be removed because there is aggregate call
+ explain select count(key1) from dest_g21 group by key1, value1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dest_g21
+#### A masked pattern was here ####
+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:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: dest_g21
+ Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key1 (type: int)
+ outputColumnNames: key1
+ Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: count()
+ keys: key1 (type: int)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: bigint)
+ Execution mode: vectorized, llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: vectorized, llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ keys: KEY._col0 (type: int)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col1 (type: bigint)
+ outputColumnNames: _col0
+ Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ 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
+
+PREHOOK: query: select count(key1) from dest_g21 group by key1, value1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@dest_g21
+#### A masked pattern was here ####
+POSTHOOK: query: select count(key1) from dest_g21 group by key1, value1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dest_g21
+#### A masked pattern was here ####
+1
+1
+1
+1
+1
+1
+PREHOOK: query: explain select count(key1) from dest_g21 where value1 > 1 group by key1, value1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@dest_g21
+#### A masked pattern was here ####
+POSTHOOK: query: explain select count(key1) from dest_g21 where value1 > 1 group by key1, value1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dest_g21
+#### A masked pattern was here ####
+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:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: dest_g21
+ filterExpr: (value1 > 1.0D) (type: boolean)
+ Statistics: Num rows: 6 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: (value1 > 1.0D) (type: boolean)
+ Statistics: Num rows: 6 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key1 (type: int)
+ outputColumnNames: key1
+ Statistics: Num rows: 6 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: count()
+ keys: key1 (type: int)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: bigint)
+ Execution mode: vectorized, llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: vectorized, llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ keys: KEY._col0 (type: int)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col1 (type: bigint)
+ outputColumnNames: _col0
+ Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ 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
+
+PREHOOK: query: select count(key1) from dest_g21 where value1 > 1 group by key1, value1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@dest_g21
+#### A masked pattern was here ####
+POSTHOOK: query: select count(key1) from dest_g21 where value1 > 1 group by key1, value1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dest_g21
+#### A masked pattern was here ####
+1
+1
+1
+PREHOOK: query: -- t1.key is unique even after join therefore group by = group by (t1.key)
+ explain select t1.key1 from dest_g21 t1 join dest_g21 t2 on t1.key1 = t2.key1 where t2.value1 > 2 group by t1.key1, t1.value1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@dest_g21
+#### A masked pattern was here ####
+POSTHOOK: query: -- t1.key is unique even after join therefore group by = group by (t1.key)
+ explain select t1.key1 from dest_g21 t1 join dest_g21 t2 on t1.key1 = t2.key1 where t2.value1 > 2 group by t1.key1, t1.value1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dest_g21
+#### A masked pattern was here ####
+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:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: t1
+ Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key1 (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: vectorized, llap
+ LLAP IO: no inputs
+ Map 3
+ Map Operator Tree:
+ TableScan
+ alias: t2
+ filterExpr: (value1 > 2.0D) (type: boolean)
+ Statistics: Num rows: 6 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: (value1 > 2.0D) (type: boolean)
+ Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key1 (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: vectorized, llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Merge Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ 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
+
+PREHOOK: query: select t1.key1 from dest_g21 t1 join dest_g21 t2 on t1.key1 = t2.key1 where t2.value1 > 2 group by t1.key1, t1.value1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@dest_g21
+#### A masked pattern was here ####
+POSTHOOK: query: select t1.key1 from dest_g21 t1 join dest_g21 t2 on t1.key1 = t2.key1 where t2.value1 > 2 group by t1.key1, t1.value1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dest_g21
+#### A masked pattern was here ####
+4
+PREHOOK: query: explain select count(t1.key1) from dest_g21 t1 join dest_g21 t2 on t1.key1 = t2.key1 where t2.value1 > 2 group by t1.key1, t1.value1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@dest_g21
+#### A masked pattern was here ####
+POSTHOOK: query: explain select count(t1.key1) from dest_g21 t1 join dest_g21 t2 on t1.key1 = t2.key1 where t2.value1 > 2 group by t1.key1, t1.value1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dest_g21
+#### A masked pattern was here ####
+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:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: t1
+ Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key1 (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: vectorized, llap
+ LLAP IO: no inputs
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: t2
+ filterExpr: (value1 > 2.0D) (type: boolean)
+ Statistics: Num rows: 6 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: (value1 > 2.0D) (type: boolean)
+ Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key1 (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: vectorized, llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Merge Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: count()
+ keys: _col0 (type: int)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: bigint)
+ Reducer 3
+ Execution mode: vectorized, llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ keys: KEY._col0 (type: int)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col1 (type: bigint)
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ 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
+
+PREHOOK: query: select count(t1.key1) from dest_g21 t1 join dest_g21 t2 on t1.key1 = t2.key1 where t2.value1 > 2 group by t1.key1, t1.value1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@dest_g21
+#### A masked pattern was here ####
+POSTHOOK: query: select count(t1.key1) from dest_g21 t1 join dest_g21 t2 on t1.key1 = t2.key1 where t2.value1 > 2 group by t1.key1, t1.value1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dest_g21
+#### A masked pattern was here ####
+1
+PREHOOK: query: -- both aggregate and one of the key1 should be removed
+ explain select key1 from (select key1, count(key1) from dest_g21 where value1 < 4.5 group by key1, value1) sub
+PREHOOK: type: QUERY
+PREHOOK: Input: default@dest_g21
+#### A masked pattern was here ####
+POSTHOOK: query: -- both aggregate and one of the key1 should be removed
+ explain select key1 from (select key1, count(key1) from dest_g21 where value1 < 4.5 group by key1, value1) sub
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dest_g21
+#### A masked pattern was here ####
+STAGE DEPENDENCIES:
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ TableScan
+ alias: dest_g21
+ filterExpr: (value1 < 4.5D) (type: boolean)
+ Filter Operator
+ predicate: (value1 < 4.5D) (type: boolean)
+ Select Operator
+ expressions: key1 (type: int)
+ outputColumnNames: _col0
+ ListSink
+
+PREHOOK: query: select key1 from (select key1, count(key1) from dest_g21 where value1 < 4.5 group by key1, value1) sub
+PREHOOK: type: QUERY
+PREHOOK: Input: default@dest_g21
+#### A masked pattern was here ####
+POSTHOOK: query: select key1 from (select key1, count(key1) from dest_g21 where value1 < 4.5 group by key1, value1) sub
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dest_g21
+#### A masked pattern was here ####
+1
+2
+3
+4
+PREHOOK: query: -- one of the aggregate will be removed and one of the key1 will be removed
+ explain select key1, sm from (select key1, count(key1), sum(key1) as sm from dest_g21 where value1 < 4.5 group by key1, value1) sub
+PREHOOK: type: QUERY
+PREHOOK: Input: default@dest_g21
+#### A masked pattern was here ####
+POSTHOOK: query: -- one of the aggregate will be removed and one of the key1 will be removed
+ explain select key1, sm from (select key1, count(key1), sum(key1) as sm from dest_g21 where value1 < 4.5 group by key1, value1) sub
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dest_g21
+#### A masked pattern was here ####
+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:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: dest_g21
+ filterExpr: (value1 < 4.5D) (type: boolean)
+ Statistics: Num rows: 6 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: (value1 < 4.5D) (type: boolean)
+ Statistics: Num rows: 6 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key1 (type: int)
+ outputColumnNames: key1
+ Statistics: Num rows: 6 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: sum(key1)
+ keys: key1 (type: int)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: bigint)
+ Execution mode: vectorized, llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: vectorized, llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0)
+ keys: KEY._col0 (type: int)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE
+ 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
+
+PREHOOK: query: select key1, sm from (select key1, count(key1), sum(key1) as sm from dest_g21 where value1 < 4.5 group by key1, value1) sub
+PREHOOK: type: QUERY
+PREHOOK: Input: default@dest_g21
+#### A masked pattern was here ####
+POSTHOOK: query: select key1, sm from (select key1, count(key1), sum(key1) as sm from dest_g21 where value1 < 4.5 group by key1, value1) sub
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dest_g21
+#### A masked pattern was here ####
+1 1
+3 3
+4 4
+2 2
+PREHOOK: query: DROP table dest_g21
+PREHOOK: type: DROPTABLE
+PREHOOK: Input: default@dest_g21
+PREHOOK: Output: default@dest_g21
+POSTHOOK: query: DROP table dest_g21
+POSTHOOK: type: DROPTABLE
+POSTHOOK: Input: default@dest_g21
+POSTHOOK: Output: default@dest_g21
+PREHOOK: query: CREATE TABLE tconst(i int NOT NULL disable rely, j INT NOT NULL disable norely, d_year string)
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@tconst
+POSTHOOK: query: CREATE TABLE tconst(i int NOT NULL disable rely, j INT NOT NULL disable norely, d_year string)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@tconst
+PREHOOK: query: INSERT INTO tconst values(1, 1, '2001'), (2, null, '2002'), (3, 3, '2010')
+PREHOOK: type: QUERY
+PREHOOK: Input: _dummy_database@_dummy_table
+PREHOOK: Output: default@tconst
+POSTHOOK: query: INSERT INTO tconst values(1, 1, '2001'), (2, null, '2002'), (3, 3, '2010')
+POSTHOOK: type: QUERY
+POSTHOOK: Input: _dummy_database@_dummy_table
+POSTHOOK: Output: default@tconst
+POSTHOOK: Lineage: tconst.d_year SCRIPT []
+POSTHOOK: Lineage: tconst.i SCRIPT []
+POSTHOOK: Lineage: tconst.j SCRIPT []
+PREHOOK: query: explain select i, j from tconst where i is not null group by i,j, d_year
+PREHOOK: type: QUERY
+PREHOOK: Input: default@tconst
+#### A masked pattern was here ####
+POSTHOOK: query: explain select i, j from tconst where i is not null group by i,j, d_year
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@tconst
+#### A masked pattern was here ####
+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:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: tconst
+ Statistics: Num rows: 3 Data size: 288 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: i (type: int), j (type: int), d_year (type: string)
+ outputColumnNames: i, j, d_year
+ Statistics: Num rows: 3 Data size: 288 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ keys: i (type: int), j (type: int), d_year (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string)
+ sort order: +++
+ Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: string)
+ Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: vectorized, llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: vectorized, llap
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: int)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ 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
+
+PREHOOK: query: select i, j from tconst where i is not null group by i,j, d_year
+PREHOOK: type: QUERY
+PREHOOK: Input: default@tconst
+#### A masked pattern was here ####
+POSTHOOK: query: select i, j from tconst where i is not null group by i,j, d_year
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@tconst
+#### A masked pattern was here ####
+3 3
+2 NULL
+1 1
+PREHOOK: query: explain select i, j from tconst where i IS NOT NULL and j IS NOT NULL group by i,j, d_year
+PREHOOK: type: QUERY
+PREHOOK: Input: default@tconst
+#### A masked pattern was here ####
+POSTHOOK: query: explain select i, j from tconst where i IS NOT NULL and j IS NOT NULL group by i,j, d_year
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@tconst
+#### A masked pattern was here ####
+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:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: tconst
+ filterExpr: j is not null (type: boolean)
+ Statistics: Num rows: 3 Data size: 288 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: j is not null (type: boolean)
+ Statistics: Num rows: 2 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ keys: i (type: int), j (type: int), d_year (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string)
+ sort order: +++
+ Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: string)
+ Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: vectorized, llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: vectorized, llap
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: int)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ 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
+
+PREHOOK: query: select i, j from tconst where i IS NOT NULL and j IS NOT NULL group by i,j, d_year
+PREHOOK: type: QUERY
+PREHOOK: Input: default@tconst
+#### A masked pattern was here ####
+POSTHOOK: query: select i, j from tconst where i IS NOT NULL and j IS NOT NULL group by i,j, d_year
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@tconst
+#### A masked pattern was here ####
+3 3
+1 1
+PREHOOK: query: explain select i,j from tconst where i is not null OR j IS NOT NULL group by i, j, d_year
+PREHOOK: type: QUERY
+PREHOOK: Input: default@tconst
+#### A masked pattern was here ####
+POSTHOOK: query: explain select i,j from tconst where i is not null OR j IS NOT NULL group by i, j, d_year
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@tconst
+#### A masked pattern was here ####
+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:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: tconst
+ Statistics: Num rows: 3 Data size: 288 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: i (type: int), j (type: int), d_year (type: string)
+ outputColumnNames: i, j, d_year
+ Statistics: Num rows: 3 Data size: 288 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ keys: i (type: int), j (type: int), d_year (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string)
+ sort order: +++
+ Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: string)
+ Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: vectorized, llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: vectorized, llap
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: int)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ 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
+
+PREHOOK: query: select i,j from tconst where i is not null OR j IS NOT NULL group by i, j, d_year
+PREHOOK: type: QUERY
+PREHOOK: Input: default@tconst
+#### A masked pattern was here ####
+POSTHOOK: query: select i,j from tconst where i is not null OR j IS NOT NULL group by i, j, d_year
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@tconst
+#### A masked pattern was here ####
+3 3
+2 NULL
+1 1
+PREHOOK: query: explain select sum(t1.i) from tconst t1 join tconst t2 on t1.i=t2.j group by t1.i, t1.d_year
+PREHOOK: type: QUERY
+PREHOOK: Input: default@tconst
+#### A masked pattern was here ####
+POSTHOOK: query: explain select sum(t1.i) from tconst t1 join tconst t2 on t1.i=t2.j group by t1.i, t1.d_year
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@tconst
+#### A masked pattern was here ####
+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:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: t1
+ Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: i (type: int), d_year (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: string)
+ Execution mode: vectorized, llap
+ LLAP IO: no inputs
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: t2
+ filterExpr: j is not null (type: boolean)
+ Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: j is not null (type: boolean)
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: j (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: vectorized, llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Merge Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 2 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: sum(_col0)
+ keys: _col0 (type: int), _col1 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: int), _col1 (type: string)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: int), _col1 (type: string)
+ Statistics: Num rows: 1 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col2 (type: bigint)
+ Reducer 3
+ Execution mode: vectorized, llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0)
+ keys: KEY._col0 (type: int), KEY._col1 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col2 (type: bigint)
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ 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
+
+PREHOOK: query: select sum(t1.i) from tconst t1 join tconst t2 on t1.i=t2.j group by t1.i, t1.d_year
+PREHOOK: type: QUERY
+PREHOOK: Input: default@tconst
+#### A masked pattern was here ####
+POSTHOOK: query: select sum(t1.i) from tconst t1 join tconst t2 on t1.i=t2.j group by t1.i, t1.d_year
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@tconst
+#### A masked pattern was here ####
+1
+3
+PREHOOK: query: explain select sum(t1.i) from tconst t1 join tconst t2 on t1.i=t2.i group by t1.i, t1.d_year
+PREHOOK: type: QUERY
+PREHOOK: Input: default@tconst
+#### A masked pattern was here ####
+POSTHOOK: query: explain select sum(t1.i) from tconst t1 join tconst t2 on t1.i=t2.i group by t1.i, t1.d_year
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@tconst
+#### A masked pattern was here ####
+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:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: t1
+ Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: i (type: int), d_year (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: string)
+ Execution mode: vectorized, llap
+ LLAP IO: no inputs
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: t2
+ Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: i (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: vectorized, llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Merge Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: sum(_col0)
+ keys: _col0 (type: int), _col1 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: int), _col1 (type: string)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: int), _col1 (type: string)
+ Statistics: Num rows: 1 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col2 (type: bigint)
+ Reducer 3
+ Execution mode: vectorized, llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0)
+ keys: KEY._col0 (type: int), KEY._col1 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col2 (type: bigint)
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ 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
+
+PREHOOK: query: select sum(t1.i) from tconst t1 join tconst t2 on t1.i=t2.i group by t1.i, t1.d_year
+PREHOOK: type: QUERY
+PREHOOK: Input: default@tconst
+#### A masked pattern was here ####
+POSTHOOK: query: select sum(t1.i) from tconst t1 join tconst t2 on t1.i=t2.i group by t1.i, t1.d_year
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@tconst
+#### A masked pattern was here ####
+1
+2
+3
+PREHOOK: query: DROP TABLE tconst
+PREHOOK: type: DROPTABLE
+PREHOOK: Input: default@tconst
+PREHOOK: Output: default@tconst
+POSTHOOK: query: DROP TABLE tconst
+POSTHOOK: type: DROPTABLE
+POSTHOOK: Input: default@tconst
+POSTHOOK: Output: default@tconst
+PREHOOK: query: create table dest_g21 (key1 int NOT NULL disable rely, value1 double, UNIQUE(key1) disable rely)
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@dest_g21
+POSTHOOK: query: create table dest_g21 (key1 int NOT NULL disable rely, value1 double, UNIQUE(key1) disable rely)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@dest_g21
+PREHOOK: query: explain select key1 from dest_g21 group by key1, value1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@dest_g21
+#### A masked pattern was here ####
+POSTHOOK: query: explain select key1 from dest_g21 group by key1, value1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dest_g21
+#### A masked pattern was here ####
+STAGE DEPENDENCIES:
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ TableScan
+ alias: dest_g21
+ Select Operator
+ expressions: key1 (type: int)
+ outputColumnNames: _col0
+ ListSink
+
+PREHOOK: query: create table dest_g24 (key1 int , value1 double, UNIQUE(key1) disable rely)
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@dest_g24
+POSTHOOK: query: create table dest_g24 (key1 int , value1 double, UNIQUE(key1) disable rely)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@dest_g24
+PREHOOK: query: explain select key1 from dest_g24 group by key1, value1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@dest_g24
+#### A masked pattern was here ####
+POSTHOOK: query: explain select key1 from dest_g24 group by key1, value1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dest_g24
+#### A masked pattern was here ####
+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:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: dest_g24
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key1 (type: int), value1 (type: double)
+ outputColumnNames: key1, value1
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ keys: key1 (type: int), value1 (type: double)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int), _col1 (type: double)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: int), _col1 (type: double)
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Execution mode: vectorized, llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: vectorized, llap
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: int), KEY._col1 (type: double)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 12 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
+
+PREHOOK: query: DROP TABLE dest_g21
+PREHOOK: type: DROPTABLE
+PREHOOK: Input: default@dest_g21
+PREHOOK: Output:
<TRUNCATED>