PREHOOK: query: -- INCLUDE_HADOOP_MAJOR_VERSIONS(0.20,0.20S)
-- This test uses mapred.max.split.size/mapred.max.split.size for controlling
-- number of input splits, which is not effective in hive 0.20.
-- stats_partscan_1_23.q is the same test with this but has different result.

-- test analyze table ... compute statistics partialscan

-- 1. prepare data
CREATE table analyze_srcpart_partial_scan (key STRING, value STRING)
partitioned by (ds string, hr string)
stored as rcfile
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
POSTHOOK: query: -- INCLUDE_HADOOP_MAJOR_VERSIONS(0.20,0.20S)
-- This test uses mapred.max.split.size/mapred.max.split.size for controlling
-- number of input splits, which is not effective in hive 0.20.
-- stats_partscan_1_23.q is the same test with this but has different result.

-- test analyze table ... compute statistics partialscan

-- 1. prepare data
CREATE table analyze_srcpart_partial_scan (key STRING, value STRING)
partitioned by (ds string, hr string)
stored as rcfile
POSTHOOK: type: CREATETABLE
POSTHOOK: Output: database:default
POSTHOOK: Output: default@analyze_srcpart_partial_scan
PREHOOK: query: insert overwrite table analyze_srcpart_partial_scan partition (ds, hr) select * from srcpart where ds is not null
PREHOOK: type: QUERY
PREHOOK: Input: default@srcpart
PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11
PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
PREHOOK: Output: default@analyze_srcpart_partial_scan
POSTHOOK: query: insert overwrite table analyze_srcpart_partial_scan partition (ds, hr) select * from srcpart where ds is not null
POSTHOOK: type: QUERY
POSTHOOK: Input: default@srcpart
POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11
POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
POSTHOOK: Output: default@analyze_srcpart_partial_scan@ds=2008-04-08/hr=11
POSTHOOK: Output: default@analyze_srcpart_partial_scan@ds=2008-04-08/hr=12
POSTHOOK: Output: default@analyze_srcpart_partial_scan@ds=2008-04-09/hr=11
POSTHOOK: Output: default@analyze_srcpart_partial_scan@ds=2008-04-09/hr=12
POSTHOOK: Lineage: analyze_srcpart_partial_scan PARTITION(ds=2008-04-08,hr=11).key SIMPLE [(srcpart)srcpart.FieldSchema(name:key, type:string, comment:default), ]
POSTHOOK: Lineage: analyze_srcpart_partial_scan PARTITION(ds=2008-04-08,hr=11).value SIMPLE [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ]
POSTHOOK: Lineage: analyze_srcpart_partial_scan PARTITION(ds=2008-04-08,hr=12).key SIMPLE [(srcpart)srcpart.FieldSchema(name:key, type:string, comment:default), ]
POSTHOOK: Lineage: analyze_srcpart_partial_scan PARTITION(ds=2008-04-08,hr=12).value SIMPLE [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ]
POSTHOOK: Lineage: analyze_srcpart_partial_scan PARTITION(ds=2008-04-09,hr=11).key SIMPLE [(srcpart)srcpart.FieldSchema(name:key, type:string, comment:default), ]
POSTHOOK: Lineage: analyze_srcpart_partial_scan PARTITION(ds=2008-04-09,hr=11).value SIMPLE [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ]
POSTHOOK: Lineage: analyze_srcpart_partial_scan PARTITION(ds=2008-04-09,hr=12).key SIMPLE [(srcpart)srcpart.FieldSchema(name:key, type:string, comment:default), ]
POSTHOOK: Lineage: analyze_srcpart_partial_scan PARTITION(ds=2008-04-09,hr=12).value SIMPLE [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ]
PREHOOK: query: describe formatted analyze_srcpart_partial_scan PARTITION(ds='2008-04-08',hr=11)
PREHOOK: type: DESCTABLE
PREHOOK: Input: default@analyze_srcpart_partial_scan
POSTHOOK: query: describe formatted analyze_srcpart_partial_scan PARTITION(ds='2008-04-08',hr=11)
POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@analyze_srcpart_partial_scan
# col_name            	data_type           	comment             
	 	 
key                 	string              	                    
value               	string              	                    
	 	 
# Partition Information	 	 
# col_name            	data_type           	comment             
	 	 
ds                  	string              	                    
hr                  	string              	                    
	 	 
# Detailed Partition Information	 	 
Partition Value:    	[2008-04-08, 11]    	 
Database:           	default             	 
Table:              	analyze_srcpart_partial_scan	 
#### A masked pattern was here ####
Protect Mode:       	None                	 
#### A masked pattern was here ####
Partition Parameters:	 	 
	COLUMN_STATS_ACCURATE	false               
	numFiles            	1                   
	numRows             	-1                  
	rawDataSize         	-1                  
	totalSize           	5293                
#### A masked pattern was here ####
	 	 
# Storage Information	 	 
SerDe Library:      	org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe	 
InputFormat:        	org.apache.hadoop.hive.ql.io.RCFileInputFormat	 
OutputFormat:       	org.apache.hadoop.hive.ql.io.RCFileOutputFormat	 
Compressed:         	No                  	 
Num Buckets:        	-1                  	 
Bucket Columns:     	[]                  	 
Sort Columns:       	[]                  	 
Storage Desc Params:	 	 
	serialization.format	1                   
PREHOOK: query: -- 2. partialscan
explain
analyze table analyze_srcpart_partial_scan PARTITION(ds='2008-04-08',hr=11) compute statistics partialscan
PREHOOK: type: QUERY
POSTHOOK: query: -- 2. partialscan
explain
analyze table analyze_srcpart_partial_scan PARTITION(ds='2008-04-08',hr=11) compute statistics partialscan
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
  Stage-2 is a root stage
  Stage-1 depends on stages: Stage-2

STAGE PLANS:
  Stage: Stage-2
    Partial Scan Statistics

  Stage: Stage-1
    Stats-Aggr Operator

PREHOOK: query: analyze table analyze_srcpart_partial_scan PARTITION(ds='2008-04-08',hr=11) compute statistics partialscan
PREHOOK: type: QUERY
PREHOOK: Input: default@analyze_srcpart_partial_scan
PREHOOK: Input: default@analyze_srcpart_partial_scan@ds=2008-04-08/hr=11
PREHOOK: Output: default@analyze_srcpart_partial_scan
PREHOOK: Output: default@analyze_srcpart_partial_scan@ds=2008-04-08/hr=11
POSTHOOK: query: analyze table analyze_srcpart_partial_scan PARTITION(ds='2008-04-08',hr=11) compute statistics partialscan
POSTHOOK: type: QUERY
POSTHOOK: Input: default@analyze_srcpart_partial_scan
POSTHOOK: Input: default@analyze_srcpart_partial_scan@ds=2008-04-08/hr=11
POSTHOOK: Output: default@analyze_srcpart_partial_scan
POSTHOOK: Output: default@analyze_srcpart_partial_scan@ds=2008-04-08/hr=11
PREHOOK: query: -- 3. confirm result
describe formatted analyze_srcpart_partial_scan PARTITION(ds='2008-04-08',hr=11)
PREHOOK: type: DESCTABLE
PREHOOK: Input: default@analyze_srcpart_partial_scan
POSTHOOK: query: -- 3. confirm result
describe formatted analyze_srcpart_partial_scan PARTITION(ds='2008-04-08',hr=11)
POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@analyze_srcpart_partial_scan
# col_name            	data_type           	comment             
	 	 
key                 	string              	                    
value               	string              	                    
	 	 
# Partition Information	 	 
# col_name            	data_type           	comment             
	 	 
ds                  	string              	                    
hr                  	string              	                    
	 	 
# Detailed Partition Information	 	 
Partition Value:    	[2008-04-08, 11]    	 
Database:           	default             	 
Table:              	analyze_srcpart_partial_scan	 
#### A masked pattern was here ####
Protect Mode:       	None                	 
#### A masked pattern was here ####
Partition Parameters:	 	 
	COLUMN_STATS_ACCURATE	true                
	numFiles            	1                   
	numRows             	500                 
	rawDataSize         	4812                
	totalSize           	5293                
#### A masked pattern was here ####
	 	 
# Storage Information	 	 
SerDe Library:      	org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe	 
InputFormat:        	org.apache.hadoop.hive.ql.io.RCFileInputFormat	 
OutputFormat:       	org.apache.hadoop.hive.ql.io.RCFileOutputFormat	 
Compressed:         	No                  	 
Num Buckets:        	-1                  	 
Bucket Columns:     	[]                  	 
Sort Columns:       	[]                  	 
Storage Desc Params:	 	 
	serialization.format	1                   
PREHOOK: query: describe formatted analyze_srcpart_partial_scan PARTITION(ds='2008-04-09',hr=11)
PREHOOK: type: DESCTABLE
PREHOOK: Input: default@analyze_srcpart_partial_scan
POSTHOOK: query: describe formatted analyze_srcpart_partial_scan PARTITION(ds='2008-04-09',hr=11)
POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@analyze_srcpart_partial_scan
# col_name            	data_type           	comment             
	 	 
key                 	string              	                    
value               	string              	                    
	 	 
# Partition Information	 	 
# col_name            	data_type           	comment             
	 	 
ds                  	string              	                    
hr                  	string              	                    
	 	 
# Detailed Partition Information	 	 
Partition Value:    	[2008-04-09, 11]    	 
Database:           	default             	 
Table:              	analyze_srcpart_partial_scan	 
#### A masked pattern was here ####
Protect Mode:       	None                	 
#### A masked pattern was here ####
Partition Parameters:	 	 
	COLUMN_STATS_ACCURATE	false               
	numFiles            	1                   
	numRows             	-1                  
	rawDataSize         	-1                  
	totalSize           	5293                
#### A masked pattern was here ####
	 	 
# Storage Information	 	 
SerDe Library:      	org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe	 
InputFormat:        	org.apache.hadoop.hive.ql.io.RCFileInputFormat	 
OutputFormat:       	org.apache.hadoop.hive.ql.io.RCFileOutputFormat	 
Compressed:         	No                  	 
Num Buckets:        	-1                  	 
Bucket Columns:     	[]                  	 
Sort Columns:       	[]                  	 
Storage Desc Params:	 	 
	serialization.format	1                   
PREHOOK: query: drop table analyze_srcpart_partial_scan
PREHOOK: type: DROPTABLE
PREHOOK: Input: default@analyze_srcpart_partial_scan
PREHOOK: Output: default@analyze_srcpart_partial_scan
POSTHOOK: query: drop table analyze_srcpart_partial_scan
POSTHOOK: type: DROPTABLE
POSTHOOK: Input: default@analyze_srcpart_partial_scan
POSTHOOK: Output: default@analyze_srcpart_partial_scan