You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by na...@apache.org on 2012/12/05 12:59:26 UTC
svn commit: r1417374 [9/11] - in /hive/trunk:
common/src/java/org/apache/hadoop/hive/common/
common/src/java/org/apache/hadoop/hive/conf/ conf/
ql/src/java/org/apache/hadoop/hive/ql/
ql/src/java/org/apache/hadoop/hive/ql/exec/ ql/src/java/org/apache/ha...
Modified: hive/trunk/ql/src/test/results/clientpositive/list_bucket_query_multiskew_1.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/list_bucket_query_multiskew_1.q.out?rev=1417374&r1=1417373&r2=1417374&view=diff
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/list_bucket_query_multiskew_1.q.out (original)
+++ hive/trunk/ql/src/test/results/clientpositive/list_bucket_query_multiskew_1.q.out Wed Dec 5 11:59:15 2012
@@ -11,16 +11,11 @@ PREHOOK: query: -- INCLUDE_HADOOP_MAJOR_
-- 1. pruner only pick up right directory
-- 2. query result is right
--- create 1 table: fact_daily
--- 1. create a few partitions
--- 2. dfs move partition according to list bucketing structure (simulate DML)
--- $/fact_daily/ds=1/hr=4/x=../y=..
--- notes: waste all partitions except ds=1 and hr=4 for list bucketing query test
--- 3. alter it to skewed table and set up location map
--- 4. list bucketing query
--- fact_daily (ds=1 and hr=4) will be used for list bucketing query
-CREATE TABLE fact_daily(x int, y STRING) PARTITIONED BY (ds STRING, hr STRING)
-#### A masked pattern was here ####
+-- create a skewed table
+create table fact_daily (key String, value String)
+partitioned by (ds String, hr String)
+skewed by (key, value) on (('484','val_484'),('238','val_238'))
+stored as DIRECTORIES
PREHOOK: type: CREATETABLE
POSTHOOK: query: -- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
@@ -35,127 +30,35 @@ POSTHOOK: query: -- INCLUDE_HADOOP_MAJOR
-- 1. pruner only pick up right directory
-- 2. query result is right
--- create 1 table: fact_daily
--- 1. create a few partitions
--- 2. dfs move partition according to list bucketing structure (simulate DML)
--- $/fact_daily/ds=1/hr=4/x=../y=..
--- notes: waste all partitions except ds=1 and hr=4 for list bucketing query test
--- 3. alter it to skewed table and set up location map
--- 4. list bucketing query
--- fact_daily (ds=1 and hr=4) will be used for list bucketing query
-CREATE TABLE fact_daily(x int, y STRING) PARTITIONED BY (ds STRING, hr STRING)
-#### A masked pattern was here ####
+-- create a skewed table
+create table fact_daily (key String, value String)
+partitioned by (ds String, hr String)
+skewed by (key, value) on (('484','val_484'),('238','val_238'))
+stored as DIRECTORIES
POSTHOOK: type: CREATETABLE
POSTHOOK: Output: default@fact_daily
-PREHOOK: query: -- create /fact_daily/ds=1/hr=1 directory
-INSERT OVERWRITE TABLE fact_daily PARTITION (ds='1', hr='1')
-SELECT key, value FROM src WHERE key=484
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Output: default@fact_daily@ds=1/hr=1
-POSTHOOK: query: -- create /fact_daily/ds=1/hr=1 directory
-INSERT OVERWRITE TABLE fact_daily PARTITION (ds='1', hr='1')
-SELECT key, value FROM src WHERE key=484
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Output: default@fact_daily@ds=1/hr=1
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=1).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=1).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-PREHOOK: query: -- create /fact_daily/ds=1/hr=2 directory
-INSERT OVERWRITE TABLE fact_daily PARTITION (ds='1', hr='2')
-SELECT key, value FROM src WHERE key=369 or key=406
+PREHOOK: query: insert overwrite table fact_daily partition (ds = '1', hr = '4')
+select key, value from src
PREHOOK: type: QUERY
PREHOOK: Input: default@src
-PREHOOK: Output: default@fact_daily@ds=1/hr=2
-POSTHOOK: query: -- create /fact_daily/ds=1/hr=2 directory
-INSERT OVERWRITE TABLE fact_daily PARTITION (ds='1', hr='2')
-SELECT key, value FROM src WHERE key=369 or key=406
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Output: default@fact_daily@ds=1/hr=2
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=1).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=1).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=2).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=2).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-PREHOOK: query: -- create /fact_daily/ds=1/hr=3 directory
-INSERT OVERWRITE TABLE fact_daily PARTITION (ds='1', hr='3')
-SELECT key, value FROM src WHERE key=238
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Output: default@fact_daily@ds=1/hr=3
-POSTHOOK: query: -- create /fact_daily/ds=1/hr=3 directory
-INSERT OVERWRITE TABLE fact_daily PARTITION (ds='1', hr='3')
-SELECT key, value FROM src WHERE key=238
+PREHOOK: Output: default@fact_daily@ds=1/hr=4
+POSTHOOK: query: insert overwrite table fact_daily partition (ds = '1', hr = '4')
+select key, value from src
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
-POSTHOOK: Output: default@fact_daily@ds=1/hr=3
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=1).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=1).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=2).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=2).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=3).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=3).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-#### A masked pattern was here ####
-PREHOOK: query: -- switch fact_daily to skewed table and point its location to /fact_daily/ds=1
-alter table fact_daily skewed by (x,y) on ((484,'val_484'),(238,'val_238'))
-PREHOOK: type: ALTERTABLE_SKEWED
-PREHOOK: Input: default@fact_daily
-PREHOOK: Output: default@fact_daily
-POSTHOOK: query: -- switch fact_daily to skewed table and point its location to /fact_daily/ds=1
-alter table fact_daily skewed by (x,y) on ((484,'val_484'),(238,'val_238'))
-POSTHOOK: type: ALTERTABLE_SKEWED
-POSTHOOK: Input: default@fact_daily
-POSTHOOK: Output: default@fact_daily
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=1).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=1).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=2).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=2).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=3).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=3).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-PREHOOK: query: ALTER TABLE fact_daily ADD PARTITION (ds='1', hr='4')
-PREHOOK: type: ALTERTABLE_ADDPARTS
-PREHOOK: Input: default@fact_daily
-POSTHOOK: query: ALTER TABLE fact_daily ADD PARTITION (ds='1', hr='4')
-POSTHOOK: type: ALTERTABLE_ADDPARTS
-POSTHOOK: Input: default@fact_daily
-POSTHOOK: Output: default@fact_daily@ds=1/hr=4
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=1).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=1).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=2).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=2).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=3).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=3).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-PREHOOK: query: -- set List Bucketing location map
-#### A masked pattern was here ####
-PREHOOK: type: ALTERTBLPART_SKEWED_LOCATION
-PREHOOK: Input: default@fact_daily
-PREHOOK: Output: default@fact_daily@ds=1/hr=4
-POSTHOOK: query: -- set List Bucketing location map
-#### A masked pattern was here ####
-POSTHOOK: type: ALTERTBLPART_SKEWED_LOCATION
-POSTHOOK: Input: default@fact_daily
-POSTHOOK: Input: default@fact_daily@ds=1/hr=4
POSTHOOK: Output: default@fact_daily@ds=1/hr=4
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=1).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=1).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=2).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=2).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=3).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=3).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=4).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=4).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
PREHOOK: query: describe formatted fact_daily PARTITION (ds = '1', hr='4')
PREHOOK: type: DESCTABLE
POSTHOOK: query: describe formatted fact_daily PARTITION (ds = '1', hr='4')
POSTHOOK: type: DESCTABLE
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=1).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=1).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=2).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=2).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=3).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=3).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=4).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=4).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
# col_name data_type comment
-x int None
-y string None
+key string None
+value string None
# Partition Information
# col_name data_type comment
@@ -171,6 +74,10 @@ Table: fact_daily
Protect Mode: None
#### A masked pattern was here ####
Partition Parameters:
+ numFiles 3
+ numRows 500
+ rawDataSize 5312
+ totalSize 5812
#### A masked pattern was here ####
# Storage Information
@@ -181,51 +88,36 @@ Compressed: No
Num Buckets: -1
Bucket Columns: []
Sort Columns: []
-Skewed Columns: [x, y]
+Stored As SubDirectories: Yes
+Skewed Columns: [key, value]
Skewed Values: [[484, val_484], [238, val_238]]
#### A masked pattern was here ####
+Skewed Value to Truncated Path: {[484, val_484]=/fact_daily/ds=1/hr=4/key=484/value=val_484, [238, val_238]=/fact_daily/ds=1/hr=4/key=238/value=val_238}
Storage Desc Params:
serialization.format 1
-PREHOOK: query: SELECT * FROM fact_daily WHERE ds='1' and hr='4'
+PREHOOK: query: SELECT count(1) FROM fact_daily WHERE ds='1' and hr='4'
PREHOOK: type: QUERY
PREHOOK: Input: default@fact_daily@ds=1/hr=4
#### A masked pattern was here ####
-POSTHOOK: query: SELECT * FROM fact_daily WHERE ds='1' and hr='4'
+POSTHOOK: query: SELECT count(1) FROM fact_daily WHERE ds='1' and hr='4'
POSTHOOK: type: QUERY
POSTHOOK: Input: default@fact_daily@ds=1/hr=4
#### A masked pattern was here ####
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=1).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=1).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=2).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=2).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=3).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=3).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-369 val_369 1 4
-406 val_406 1 4
-369 val_369 1 4
-369 val_369 1 4
-406 val_406 1 4
-406 val_406 1 4
-406 val_406 1 4
-238 val_238 1 4
-238 val_238 1 4
-484 val_484 1 4
+POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=4).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=4).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+500
PREHOOK: query: -- pruner only pick up skewed-value directory
-- explain plan shows which directory selected: Truncated Path -> Alias
-explain extended SELECT x FROM fact_daily WHERE ( ds='1' and hr='4') and (x=484 and y= 'val_484')
+explain extended SELECT key FROM fact_daily WHERE ( ds='1' and hr='4') and (key='484' and value= 'val_484')
PREHOOK: type: QUERY
POSTHOOK: query: -- pruner only pick up skewed-value directory
-- explain plan shows which directory selected: Truncated Path -> Alias
-explain extended SELECT x FROM fact_daily WHERE ( ds='1' and hr='4') and (x=484 and y= 'val_484')
+explain extended SELECT key FROM fact_daily WHERE ( ds='1' and hr='4') and (key='484' and value= 'val_484')
POSTHOOK: type: QUERY
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=1).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=1).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=2).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=2).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=3).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=3).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=4).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=4).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
ABSTRACT SYNTAX TREE:
- (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME fact_daily))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL x))) (TOK_WHERE (and (and (= (TOK_TABLE_OR_COL ds) '1') (= (TOK_TABLE_OR_COL hr) '4')) (and (= (TOK_TABLE_OR_COL x) 484) (= (TOK_TABLE_OR_COL y) 'val_484'))))))
+ (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME fact_daily))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key))) (TOK_WHERE (and (and (= (TOK_TABLE_OR_COL ds) '1') (= (TOK_TABLE_OR_COL hr) '4')) (and (= (TOK_TABLE_OR_COL key) '484') (= (TOK_TABLE_OR_COL value) 'val_484'))))))
STAGE DEPENDENCIES:
Stage-1 is a root stage
@@ -242,12 +134,12 @@ STAGE PLANS:
Filter Operator
isSamplingPred: false
predicate:
- expr: ((x = 484) and (y = 'val_484'))
+ expr: ((key = '484') and (value = 'val_484'))
type: boolean
Select Operator
expressions:
- expr: x
- type: int
+ expr: key
+ type: string
outputColumnNames: _col0
File Output Operator
compressed: false
@@ -260,7 +152,7 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
columns _col0
- columns.types int
+ columns.types string
escape.delim \
serialization.format 1
TotalFiles: 1
@@ -272,7 +164,7 @@ STAGE PLANS:
Path -> Partition:
#### A masked pattern was here ####
Partition
- base file name: y=val_484
+ base file name: value=val_484
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
partition values:
@@ -280,19 +172,19 @@ STAGE PLANS:
hr 4
properties:
bucket_count -1
- columns x,y
- columns.types int:string
+ columns key,value
+ columns.types string:string
#### A masked pattern was here ####
name default.fact_daily
numFiles 3
- numPartitions 3
- numRows 10
+ numPartitions 1
+ numRows 500
partition_columns ds/hr
- rawDataSize 110
- serialization.ddl struct fact_daily { i32 x, string y}
+ rawDataSize 5312
+ serialization.ddl struct fact_daily { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 120
+ totalSize 5812
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
@@ -300,25 +192,25 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
bucket_count -1
- columns x,y
- columns.types int:string
+ columns key,value
+ columns.types string:string
#### A masked pattern was here ####
name default.fact_daily
numFiles 3
- numPartitions 3
- numRows 10
+ numPartitions 1
+ numRows 500
partition_columns ds/hr
- rawDataSize 110
- serialization.ddl struct fact_daily { i32 x, string y}
+ rawDataSize 5312
+ serialization.ddl struct fact_daily { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 120
+ totalSize 5812
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.fact_daily
name: default.fact_daily
Truncated Path -> Alias:
- /fact_daily/ds=1/hr=4/x=484/y=val_484 [fact_daily]
+ /fact_daily/ds=1/hr=4/key=484/value=val_484 [fact_daily]
Stage: Stage-0
Fetch Operator
@@ -326,38 +218,30 @@ STAGE PLANS:
PREHOOK: query: -- List Bucketing Query
-SELECT x FROM fact_daily WHERE ( ds='1' and hr='4') and (x=484 and y= 'val_484')
+SELECT key FROM fact_daily WHERE ( ds='1' and hr='4') and (key='484' and value= 'val_484')
PREHOOK: type: QUERY
PREHOOK: Input: default@fact_daily@ds=1/hr=4
#### A masked pattern was here ####
POSTHOOK: query: -- List Bucketing Query
-SELECT x FROM fact_daily WHERE ( ds='1' and hr='4') and (x=484 and y= 'val_484')
+SELECT key FROM fact_daily WHERE ( ds='1' and hr='4') and (key='484' and value= 'val_484')
POSTHOOK: type: QUERY
POSTHOOK: Input: default@fact_daily@ds=1/hr=4
#### A masked pattern was here ####
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=1).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=1).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=2).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=2).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=3).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=3).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=4).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=4).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
484
PREHOOK: query: -- pruner only pick up skewed-value directory
-- explain plan shows which directory selected: Truncated Path -> Alias
-explain extended SELECT x,y FROM fact_daily WHERE ( ds='1' and hr='4') and (x=238 and y= 'val_238')
+explain extended SELECT key,value FROM fact_daily WHERE ( ds='1' and hr='4') and (key='238' and value= 'val_238')
PREHOOK: type: QUERY
POSTHOOK: query: -- pruner only pick up skewed-value directory
-- explain plan shows which directory selected: Truncated Path -> Alias
-explain extended SELECT x,y FROM fact_daily WHERE ( ds='1' and hr='4') and (x=238 and y= 'val_238')
+explain extended SELECT key,value FROM fact_daily WHERE ( ds='1' and hr='4') and (key='238' and value= 'val_238')
POSTHOOK: type: QUERY
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=1).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=1).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=2).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=2).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=3).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=3).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=4).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=4).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
ABSTRACT SYNTAX TREE:
- (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME fact_daily))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL x)) (TOK_SELEXPR (TOK_TABLE_OR_COL y))) (TOK_WHERE (and (and (= (TOK_TABLE_OR_COL ds) '1') (= (TOK_TABLE_OR_COL hr) '4')) (and (= (TOK_TABLE_OR_COL x) 238) (= (TOK_TABLE_OR_COL y) 'val_238'))))))
+ (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME fact_daily))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_TABLE_OR_COL value))) (TOK_WHERE (and (and (= (TOK_TABLE_OR_COL ds) '1') (= (TOK_TABLE_OR_COL hr) '4')) (and (= (TOK_TABLE_OR_COL key) '238') (= (TOK_TABLE_OR_COL value) 'val_238'))))))
STAGE DEPENDENCIES:
Stage-1 is a root stage
@@ -374,13 +258,13 @@ STAGE PLANS:
Filter Operator
isSamplingPred: false
predicate:
- expr: ((x = 238) and (y = 'val_238'))
+ expr: ((key = '238') and (value = 'val_238'))
type: boolean
Select Operator
expressions:
- expr: x
- type: int
- expr: y
+ expr: key
+ type: string
+ expr: value
type: string
outputColumnNames: _col0, _col1
File Output Operator
@@ -394,7 +278,7 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
columns _col0,_col1
- columns.types int:string
+ columns.types string:string
escape.delim \
serialization.format 1
TotalFiles: 1
@@ -406,7 +290,7 @@ STAGE PLANS:
Path -> Partition:
#### A masked pattern was here ####
Partition
- base file name: y=val_238
+ base file name: value=val_238
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
partition values:
@@ -414,19 +298,19 @@ STAGE PLANS:
hr 4
properties:
bucket_count -1
- columns x,y
- columns.types int:string
+ columns key,value
+ columns.types string:string
#### A masked pattern was here ####
name default.fact_daily
numFiles 3
- numPartitions 3
- numRows 10
+ numPartitions 1
+ numRows 500
partition_columns ds/hr
- rawDataSize 110
- serialization.ddl struct fact_daily { i32 x, string y}
+ rawDataSize 5312
+ serialization.ddl struct fact_daily { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 120
+ totalSize 5812
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
@@ -434,25 +318,25 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
bucket_count -1
- columns x,y
- columns.types int:string
+ columns key,value
+ columns.types string:string
#### A masked pattern was here ####
name default.fact_daily
numFiles 3
- numPartitions 3
- numRows 10
+ numPartitions 1
+ numRows 500
partition_columns ds/hr
- rawDataSize 110
- serialization.ddl struct fact_daily { i32 x, string y}
+ rawDataSize 5312
+ serialization.ddl struct fact_daily { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 120
+ totalSize 5812
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.fact_daily
name: default.fact_daily
Truncated Path -> Alias:
- /fact_daily/ds=1/hr=4/x=238/y=val_238 [fact_daily]
+ /fact_daily/ds=1/hr=4/key=238/value=val_238 [fact_daily]
Stage: Stage-0
Fetch Operator
@@ -460,39 +344,31 @@ STAGE PLANS:
PREHOOK: query: -- List Bucketing Query
-SELECT x,y FROM fact_daily WHERE ( ds='1' and hr='4') and (x=238 and y= 'val_238')
+SELECT key,value FROM fact_daily WHERE ( ds='1' and hr='4') and (key='238' and value= 'val_238')
PREHOOK: type: QUERY
PREHOOK: Input: default@fact_daily@ds=1/hr=4
#### A masked pattern was here ####
POSTHOOK: query: -- List Bucketing Query
-SELECT x,y FROM fact_daily WHERE ( ds='1' and hr='4') and (x=238 and y= 'val_238')
+SELECT key,value FROM fact_daily WHERE ( ds='1' and hr='4') and (key='238' and value= 'val_238')
POSTHOOK: type: QUERY
POSTHOOK: Input: default@fact_daily@ds=1/hr=4
#### A masked pattern was here ####
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=1).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=1).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=2).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=2).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=3).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=3).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=4).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=4).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
238 val_238
238 val_238
PREHOOK: query: -- pruner only pick up default directory
-- explain plan shows which directory selected: Truncated Path -> Alias
-explain extended SELECT x FROM fact_daily WHERE ( ds='1' and hr='4') and (y = "3")
+explain extended SELECT key FROM fact_daily WHERE ( ds='1' and hr='4') and (value = "3")
PREHOOK: type: QUERY
POSTHOOK: query: -- pruner only pick up default directory
-- explain plan shows which directory selected: Truncated Path -> Alias
-explain extended SELECT x FROM fact_daily WHERE ( ds='1' and hr='4') and (y = "3")
+explain extended SELECT key FROM fact_daily WHERE ( ds='1' and hr='4') and (value = "3")
POSTHOOK: type: QUERY
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=1).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=1).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=2).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=2).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=3).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=3).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=4).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=4).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
ABSTRACT SYNTAX TREE:
- (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME fact_daily))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL x))) (TOK_WHERE (and (and (= (TOK_TABLE_OR_COL ds) '1') (= (TOK_TABLE_OR_COL hr) '4')) (= (TOK_TABLE_OR_COL y) "3")))))
+ (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME fact_daily))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key))) (TOK_WHERE (and (and (= (TOK_TABLE_OR_COL ds) '1') (= (TOK_TABLE_OR_COL hr) '4')) (= (TOK_TABLE_OR_COL value) "3")))))
STAGE DEPENDENCIES:
Stage-1 is a root stage
@@ -509,12 +385,12 @@ STAGE PLANS:
Filter Operator
isSamplingPred: false
predicate:
- expr: (y = '3')
+ expr: (value = '3')
type: boolean
Select Operator
expressions:
- expr: x
- type: int
+ expr: key
+ type: string
outputColumnNames: _col0
File Output Operator
compressed: false
@@ -527,7 +403,7 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
columns _col0
- columns.types int
+ columns.types string
escape.delim \
serialization.format 1
TotalFiles: 1
@@ -547,19 +423,19 @@ STAGE PLANS:
hr 4
properties:
bucket_count -1
- columns x,y
- columns.types int:string
+ columns key,value
+ columns.types string:string
#### A masked pattern was here ####
name default.fact_daily
numFiles 3
- numPartitions 3
- numRows 10
+ numPartitions 1
+ numRows 500
partition_columns ds/hr
- rawDataSize 110
- serialization.ddl struct fact_daily { i32 x, string y}
+ rawDataSize 5312
+ serialization.ddl struct fact_daily { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 120
+ totalSize 5812
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
@@ -567,19 +443,19 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
bucket_count -1
- columns x,y
- columns.types int:string
+ columns key,value
+ columns.types string:string
#### A masked pattern was here ####
name default.fact_daily
numFiles 3
- numPartitions 3
- numRows 10
+ numPartitions 1
+ numRows 500
partition_columns ds/hr
- rawDataSize 110
- serialization.ddl struct fact_daily { i32 x, string y}
+ rawDataSize 5312
+ serialization.ddl struct fact_daily { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 120
+ totalSize 5812
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.fact_daily
@@ -593,37 +469,29 @@ STAGE PLANS:
PREHOOK: query: -- List Bucketing Query
-SELECT x FROM fact_daily WHERE ( ds='1' and hr='4') and (y = "3")
+SELECT key FROM fact_daily WHERE ( ds='1' and hr='4') and (value = "3")
PREHOOK: type: QUERY
PREHOOK: Input: default@fact_daily@ds=1/hr=4
#### A masked pattern was here ####
POSTHOOK: query: -- List Bucketing Query
-SELECT x FROM fact_daily WHERE ( ds='1' and hr='4') and (y = "3")
+SELECT key FROM fact_daily WHERE ( ds='1' and hr='4') and (value = "3")
POSTHOOK: type: QUERY
POSTHOOK: Input: default@fact_daily@ds=1/hr=4
#### A masked pattern was here ####
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=1).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=1).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=2).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=2).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=3).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=3).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=4).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=4).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
PREHOOK: query: -- pruner only pick up default directory
-- explain plan shows which directory selected: Truncated Path -> Alias
-explain extended SELECT x,y FROM fact_daily WHERE ( ds='1' and hr='4') and x = 495
+explain extended SELECT key,value FROM fact_daily WHERE ( ds='1' and hr='4') and key = '495'
PREHOOK: type: QUERY
POSTHOOK: query: -- pruner only pick up default directory
-- explain plan shows which directory selected: Truncated Path -> Alias
-explain extended SELECT x,y FROM fact_daily WHERE ( ds='1' and hr='4') and x = 495
+explain extended SELECT key,value FROM fact_daily WHERE ( ds='1' and hr='4') and key = '495'
POSTHOOK: type: QUERY
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=1).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=1).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=2).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=2).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=3).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=3).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=4).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=4).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
ABSTRACT SYNTAX TREE:
- (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME fact_daily))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL x)) (TOK_SELEXPR (TOK_TABLE_OR_COL y))) (TOK_WHERE (and (and (= (TOK_TABLE_OR_COL ds) '1') (= (TOK_TABLE_OR_COL hr) '4')) (= (TOK_TABLE_OR_COL x) 495)))))
+ (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME fact_daily))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_TABLE_OR_COL value))) (TOK_WHERE (and (and (= (TOK_TABLE_OR_COL ds) '1') (= (TOK_TABLE_OR_COL hr) '4')) (= (TOK_TABLE_OR_COL key) '495')))))
STAGE DEPENDENCIES:
Stage-1 is a root stage
@@ -640,13 +508,13 @@ STAGE PLANS:
Filter Operator
isSamplingPred: false
predicate:
- expr: (x = 495)
+ expr: (key = '495')
type: boolean
Select Operator
expressions:
- expr: x
- type: int
- expr: y
+ expr: key
+ type: string
+ expr: value
type: string
outputColumnNames: _col0, _col1
File Output Operator
@@ -660,7 +528,7 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
columns _col0,_col1
- columns.types int:string
+ columns.types string:string
escape.delim \
serialization.format 1
TotalFiles: 1
@@ -680,19 +548,19 @@ STAGE PLANS:
hr 4
properties:
bucket_count -1
- columns x,y
- columns.types int:string
+ columns key,value
+ columns.types string:string
#### A masked pattern was here ####
name default.fact_daily
numFiles 3
- numPartitions 3
- numRows 10
+ numPartitions 1
+ numRows 500
partition_columns ds/hr
- rawDataSize 110
- serialization.ddl struct fact_daily { i32 x, string y}
+ rawDataSize 5312
+ serialization.ddl struct fact_daily { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 120
+ totalSize 5812
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
@@ -700,19 +568,19 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
bucket_count -1
- columns x,y
- columns.types int:string
+ columns key,value
+ columns.types string:string
#### A masked pattern was here ####
name default.fact_daily
numFiles 3
- numPartitions 3
- numRows 10
+ numPartitions 1
+ numRows 500
partition_columns ds/hr
- rawDataSize 110
- serialization.ddl struct fact_daily { i32 x, string y}
+ rawDataSize 5312
+ serialization.ddl struct fact_daily { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 120
+ totalSize 5812
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.fact_daily
@@ -726,21 +594,17 @@ STAGE PLANS:
PREHOOK: query: -- List Bucketing Query
-SELECT x,y FROM fact_daily WHERE ( ds='1' and hr='4') and x = 369
+SELECT key,value FROM fact_daily WHERE ( ds='1' and hr='4') and key = '369'
PREHOOK: type: QUERY
PREHOOK: Input: default@fact_daily@ds=1/hr=4
#### A masked pattern was here ####
POSTHOOK: query: -- List Bucketing Query
-SELECT x,y FROM fact_daily WHERE ( ds='1' and hr='4') and x = 369
+SELECT key,value FROM fact_daily WHERE ( ds='1' and hr='4') and key = '369'
POSTHOOK: type: QUERY
POSTHOOK: Input: default@fact_daily@ds=1/hr=4
#### A masked pattern was here ####
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=1).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=1).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=2).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=2).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=3).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=3).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=4).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=4).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
369 val_369
369 val_369
369 val_369
Modified: hive/trunk/ql/src/test/results/clientpositive/list_bucket_query_multiskew_2.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/list_bucket_query_multiskew_2.q.out?rev=1417374&r1=1417373&r2=1417374&view=diff
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/list_bucket_query_multiskew_2.q.out (original)
+++ hive/trunk/ql/src/test/results/clientpositive/list_bucket_query_multiskew_2.q.out Wed Dec 5 11:59:15 2012
@@ -10,17 +10,11 @@ PREHOOK: query: -- INCLUDE_HADOOP_MAJOR_
-- 1. pruner only pick up right directory
-- 2. query result is right
-
--- create 1 table: fact_daily
--- 1. create a few partitions
--- 2. dfs move partition according to list bucketing structure (simulate DML)
--- $/fact_daily/ds=1/hr=4/x=../y=..
--- notes: waste all partitions except ds=1 and hr=4 for list bucketing query test
--- 3. alter it to skewed table and set up location map
--- 4. list bucketing query
--- fact_daily (ds=1 and hr=4) will be used for list bucketing query
-CREATE TABLE fact_daily(x int, y STRING) PARTITIONED BY (ds STRING, hr STRING)
-#### A masked pattern was here ####
+-- create a skewed table
+create table fact_daily (key String, value String)
+partitioned by (ds String, hr String)
+skewed by (key, value) on (('484','val_484'),('238','val_238'))
+stored as DIRECTORIES
PREHOOK: type: CREATETABLE
POSTHOOK: query: -- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
@@ -34,128 +28,35 @@ POSTHOOK: query: -- INCLUDE_HADOOP_MAJOR
-- 1. pruner only pick up right directory
-- 2. query result is right
-
--- create 1 table: fact_daily
--- 1. create a few partitions
--- 2. dfs move partition according to list bucketing structure (simulate DML)
--- $/fact_daily/ds=1/hr=4/x=../y=..
--- notes: waste all partitions except ds=1 and hr=4 for list bucketing query test
--- 3. alter it to skewed table and set up location map
--- 4. list bucketing query
--- fact_daily (ds=1 and hr=4) will be used for list bucketing query
-CREATE TABLE fact_daily(x int, y STRING) PARTITIONED BY (ds STRING, hr STRING)
-#### A masked pattern was here ####
+-- create a skewed table
+create table fact_daily (key String, value String)
+partitioned by (ds String, hr String)
+skewed by (key, value) on (('484','val_484'),('238','val_238'))
+stored as DIRECTORIES
POSTHOOK: type: CREATETABLE
POSTHOOK: Output: default@fact_daily
-PREHOOK: query: -- create /fact_daily/ds=1/hr=1 directory
-INSERT OVERWRITE TABLE fact_daily PARTITION (ds='1', hr='1')
-SELECT key, value FROM src WHERE key=484
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Output: default@fact_daily@ds=1/hr=1
-POSTHOOK: query: -- create /fact_daily/ds=1/hr=1 directory
-INSERT OVERWRITE TABLE fact_daily PARTITION (ds='1', hr='1')
-SELECT key, value FROM src WHERE key=484
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Output: default@fact_daily@ds=1/hr=1
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=1).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=1).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-PREHOOK: query: -- create /fact_daily/ds=1/hr=2 directory
-INSERT OVERWRITE TABLE fact_daily PARTITION (ds='1', hr='2')
-SELECT key, value FROM src WHERE key=369 or key=406
+PREHOOK: query: insert overwrite table fact_daily partition (ds = '1', hr = '4')
+select key, value from src
PREHOOK: type: QUERY
PREHOOK: Input: default@src
-PREHOOK: Output: default@fact_daily@ds=1/hr=2
-POSTHOOK: query: -- create /fact_daily/ds=1/hr=2 directory
-INSERT OVERWRITE TABLE fact_daily PARTITION (ds='1', hr='2')
-SELECT key, value FROM src WHERE key=369 or key=406
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Output: default@fact_daily@ds=1/hr=2
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=1).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=1).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=2).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=2).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-PREHOOK: query: -- create /fact_daily/ds=1/hr=3 directory
-INSERT OVERWRITE TABLE fact_daily PARTITION (ds='1', hr='3')
-SELECT key, value FROM src WHERE key=238
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Output: default@fact_daily@ds=1/hr=3
-POSTHOOK: query: -- create /fact_daily/ds=1/hr=3 directory
-INSERT OVERWRITE TABLE fact_daily PARTITION (ds='1', hr='3')
-SELECT key, value FROM src WHERE key=238
+PREHOOK: Output: default@fact_daily@ds=1/hr=4
+POSTHOOK: query: insert overwrite table fact_daily partition (ds = '1', hr = '4')
+select key, value from src
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
-POSTHOOK: Output: default@fact_daily@ds=1/hr=3
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=1).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=1).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=2).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=2).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=3).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=3).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-#### A masked pattern was here ####
-PREHOOK: query: -- switch fact_daily to skewed table and point its location to /fact_daily/ds=1
-alter table fact_daily skewed by (x,y) on ((484,'val_484'),(238,'val_238'))
-PREHOOK: type: ALTERTABLE_SKEWED
-PREHOOK: Input: default@fact_daily
-PREHOOK: Output: default@fact_daily
-POSTHOOK: query: -- switch fact_daily to skewed table and point its location to /fact_daily/ds=1
-alter table fact_daily skewed by (x,y) on ((484,'val_484'),(238,'val_238'))
-POSTHOOK: type: ALTERTABLE_SKEWED
-POSTHOOK: Input: default@fact_daily
-POSTHOOK: Output: default@fact_daily
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=1).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=1).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=2).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=2).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=3).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=3).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-PREHOOK: query: ALTER TABLE fact_daily ADD PARTITION (ds='1', hr='4')
-PREHOOK: type: ALTERTABLE_ADDPARTS
-PREHOOK: Input: default@fact_daily
-POSTHOOK: query: ALTER TABLE fact_daily ADD PARTITION (ds='1', hr='4')
-POSTHOOK: type: ALTERTABLE_ADDPARTS
-POSTHOOK: Input: default@fact_daily
-POSTHOOK: Output: default@fact_daily@ds=1/hr=4
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=1).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=1).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=2).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=2).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=3).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=3).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-PREHOOK: query: -- set List Bucketing location map
-#### A masked pattern was here ####
-PREHOOK: type: ALTERTBLPART_SKEWED_LOCATION
-PREHOOK: Input: default@fact_daily
-PREHOOK: Output: default@fact_daily@ds=1/hr=4
-POSTHOOK: query: -- set List Bucketing location map
-#### A masked pattern was here ####
-POSTHOOK: type: ALTERTBLPART_SKEWED_LOCATION
-POSTHOOK: Input: default@fact_daily
-POSTHOOK: Input: default@fact_daily@ds=1/hr=4
POSTHOOK: Output: default@fact_daily@ds=1/hr=4
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=1).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=1).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=2).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=2).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=3).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=3).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=4).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=4).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
PREHOOK: query: describe formatted fact_daily PARTITION (ds = '1', hr='4')
PREHOOK: type: DESCTABLE
POSTHOOK: query: describe formatted fact_daily PARTITION (ds = '1', hr='4')
POSTHOOK: type: DESCTABLE
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=1).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=1).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=2).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=2).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=3).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=3).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=4).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=4).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
# col_name data_type comment
-x int None
-y string None
+key string None
+value string None
# Partition Information
# col_name data_type comment
@@ -171,6 +72,10 @@ Table: fact_daily
Protect Mode: None
#### A masked pattern was here ####
Partition Parameters:
+ numFiles 3
+ numRows 500
+ rawDataSize 5312
+ totalSize 5812
#### A masked pattern was here ####
# Storage Information
@@ -181,51 +86,36 @@ Compressed: No
Num Buckets: -1
Bucket Columns: []
Sort Columns: []
-Skewed Columns: [x, y]
+Stored As SubDirectories: Yes
+Skewed Columns: [key, value]
Skewed Values: [[484, val_484], [238, val_238]]
#### A masked pattern was here ####
+Skewed Value to Truncated Path: {[484, val_484]=/fact_daily/ds=1/hr=4/key=484/value=val_484, [238, val_238]=/fact_daily/ds=1/hr=4/key=238/value=val_238}
Storage Desc Params:
serialization.format 1
-PREHOOK: query: SELECT * FROM fact_daily WHERE ds='1' and hr='4'
+PREHOOK: query: SELECT count(1) FROM fact_daily WHERE ds='1' and hr='4'
PREHOOK: type: QUERY
PREHOOK: Input: default@fact_daily@ds=1/hr=4
#### A masked pattern was here ####
-POSTHOOK: query: SELECT * FROM fact_daily WHERE ds='1' and hr='4'
+POSTHOOK: query: SELECT count(1) FROM fact_daily WHERE ds='1' and hr='4'
POSTHOOK: type: QUERY
POSTHOOK: Input: default@fact_daily@ds=1/hr=4
#### A masked pattern was here ####
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=1).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=1).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=2).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=2).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=3).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=3).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-369 val_369 1 4
-406 val_406 1 4
-369 val_369 1 4
-369 val_369 1 4
-406 val_406 1 4
-406 val_406 1 4
-406 val_406 1 4
-238 val_238 1 4
-238 val_238 1 4
-484 val_484 1 4
+POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=4).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=4).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+500
PREHOOK: query: -- pruner only pick up default directory
-- explain plan shows which directory selected: Truncated Path -> Alias
-explain extended SELECT x,y FROM fact_daily WHERE ds='1' and hr='4' and y= 'val_484'
+explain extended SELECT key, value FROM fact_daily WHERE ds='1' and hr='4' and value= 'val_484'
PREHOOK: type: QUERY
POSTHOOK: query: -- pruner only pick up default directory
-- explain plan shows which directory selected: Truncated Path -> Alias
-explain extended SELECT x,y FROM fact_daily WHERE ds='1' and hr='4' and y= 'val_484'
+explain extended SELECT key, value FROM fact_daily WHERE ds='1' and hr='4' and value= 'val_484'
POSTHOOK: type: QUERY
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=1).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=1).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=2).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=2).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=3).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=3).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=4).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=4).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
ABSTRACT SYNTAX TREE:
- (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME fact_daily))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL x)) (TOK_SELEXPR (TOK_TABLE_OR_COL y))) (TOK_WHERE (and (and (= (TOK_TABLE_OR_COL ds) '1') (= (TOK_TABLE_OR_COL hr) '4')) (= (TOK_TABLE_OR_COL y) 'val_484')))))
+ (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME fact_daily))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_TABLE_OR_COL value))) (TOK_WHERE (and (and (= (TOK_TABLE_OR_COL ds) '1') (= (TOK_TABLE_OR_COL hr) '4')) (= (TOK_TABLE_OR_COL value) 'val_484')))))
STAGE DEPENDENCIES:
Stage-1 is a root stage
@@ -242,13 +132,13 @@ STAGE PLANS:
Filter Operator
isSamplingPred: false
predicate:
- expr: (y = 'val_484')
+ expr: (value = 'val_484')
type: boolean
Select Operator
expressions:
- expr: x
- type: int
- expr: y
+ expr: key
+ type: string
+ expr: value
type: string
outputColumnNames: _col0, _col1
File Output Operator
@@ -262,7 +152,7 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
columns _col0,_col1
- columns.types int:string
+ columns.types string:string
escape.delim \
serialization.format 1
TotalFiles: 1
@@ -282,19 +172,19 @@ STAGE PLANS:
hr 4
properties:
bucket_count -1
- columns x,y
- columns.types int:string
+ columns key,value
+ columns.types string:string
#### A masked pattern was here ####
name default.fact_daily
numFiles 3
- numPartitions 3
- numRows 10
+ numPartitions 1
+ numRows 500
partition_columns ds/hr
- rawDataSize 110
- serialization.ddl struct fact_daily { i32 x, string y}
+ rawDataSize 5312
+ serialization.ddl struct fact_daily { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 120
+ totalSize 5812
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
@@ -302,26 +192,26 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
bucket_count -1
- columns x,y
- columns.types int:string
+ columns key,value
+ columns.types string:string
#### A masked pattern was here ####
name default.fact_daily
numFiles 3
- numPartitions 3
- numRows 10
+ numPartitions 1
+ numRows 500
partition_columns ds/hr
- rawDataSize 110
- serialization.ddl struct fact_daily { i32 x, string y}
+ rawDataSize 5312
+ serialization.ddl struct fact_daily { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 120
+ totalSize 5812
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.fact_daily
name: default.fact_daily
#### A masked pattern was here ####
Partition
- base file name: y=val_484
+ base file name: value=val_484
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
partition values:
@@ -329,19 +219,19 @@ STAGE PLANS:
hr 4
properties:
bucket_count -1
- columns x,y
- columns.types int:string
+ columns key,value
+ columns.types string:string
#### A masked pattern was here ####
name default.fact_daily
numFiles 3
- numPartitions 3
- numRows 10
+ numPartitions 1
+ numRows 500
partition_columns ds/hr
- rawDataSize 110
- serialization.ddl struct fact_daily { i32 x, string y}
+ rawDataSize 5312
+ serialization.ddl struct fact_daily { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 120
+ totalSize 5812
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
@@ -349,26 +239,26 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
bucket_count -1
- columns x,y
- columns.types int:string
+ columns key,value
+ columns.types string:string
#### A masked pattern was here ####
name default.fact_daily
numFiles 3
- numPartitions 3
- numRows 10
+ numPartitions 1
+ numRows 500
partition_columns ds/hr
- rawDataSize 110
- serialization.ddl struct fact_daily { i32 x, string y}
+ rawDataSize 5312
+ serialization.ddl struct fact_daily { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 120
+ totalSize 5812
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.fact_daily
name: default.fact_daily
Truncated Path -> Alias:
/fact_daily/ds=1/hr=4/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME [fact_daily]
- /fact_daily/ds=1/hr=4/x=484/y=val_484 [fact_daily]
+ /fact_daily/ds=1/hr=4/key=484/value=val_484 [fact_daily]
Stage: Stage-0
Fetch Operator
@@ -376,38 +266,30 @@ STAGE PLANS:
PREHOOK: query: -- List Bucketing Query
-SELECT x,y FROM fact_daily WHERE ds='1' and hr='4' and y= 'val_484'
+SELECT key, value FROM fact_daily WHERE ds='1' and hr='4' and value= 'val_484'
PREHOOK: type: QUERY
PREHOOK: Input: default@fact_daily@ds=1/hr=4
#### A masked pattern was here ####
POSTHOOK: query: -- List Bucketing Query
-SELECT x,y FROM fact_daily WHERE ds='1' and hr='4' and y= 'val_484'
+SELECT key, value FROM fact_daily WHERE ds='1' and hr='4' and value= 'val_484'
POSTHOOK: type: QUERY
POSTHOOK: Input: default@fact_daily@ds=1/hr=4
#### A masked pattern was here ####
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=1).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=1).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=2).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=2).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=3).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=3).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=4).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=4).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
484 val_484
PREHOOK: query: -- pruner only pick up default directory
-- explain plan shows which directory selected: Truncated Path -> Alias
-explain extended SELECT x FROM fact_daily WHERE ds='1' and hr='4' and x= 406
+explain extended SELECT key FROM fact_daily WHERE ds='1' and hr='4' and key= '406'
PREHOOK: type: QUERY
POSTHOOK: query: -- pruner only pick up default directory
-- explain plan shows which directory selected: Truncated Path -> Alias
-explain extended SELECT x FROM fact_daily WHERE ds='1' and hr='4' and x= 406
+explain extended SELECT key FROM fact_daily WHERE ds='1' and hr='4' and key= '406'
POSTHOOK: type: QUERY
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=1).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=1).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=2).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=2).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=3).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=3).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=4).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=4).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
ABSTRACT SYNTAX TREE:
- (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME fact_daily))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL x))) (TOK_WHERE (and (and (= (TOK_TABLE_OR_COL ds) '1') (= (TOK_TABLE_OR_COL hr) '4')) (= (TOK_TABLE_OR_COL x) 406)))))
+ (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME fact_daily))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key))) (TOK_WHERE (and (and (= (TOK_TABLE_OR_COL ds) '1') (= (TOK_TABLE_OR_COL hr) '4')) (= (TOK_TABLE_OR_COL key) '406')))))
STAGE DEPENDENCIES:
Stage-1 is a root stage
@@ -424,12 +306,12 @@ STAGE PLANS:
Filter Operator
isSamplingPred: false
predicate:
- expr: (x = 406)
+ expr: (key = '406')
type: boolean
Select Operator
expressions:
- expr: x
- type: int
+ expr: key
+ type: string
outputColumnNames: _col0
File Output Operator
compressed: false
@@ -442,7 +324,7 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
columns _col0
- columns.types int
+ columns.types string
escape.delim \
serialization.format 1
TotalFiles: 1
@@ -462,19 +344,19 @@ STAGE PLANS:
hr 4
properties:
bucket_count -1
- columns x,y
- columns.types int:string
+ columns key,value
+ columns.types string:string
#### A masked pattern was here ####
name default.fact_daily
numFiles 3
- numPartitions 3
- numRows 10
+ numPartitions 1
+ numRows 500
partition_columns ds/hr
- rawDataSize 110
- serialization.ddl struct fact_daily { i32 x, string y}
+ rawDataSize 5312
+ serialization.ddl struct fact_daily { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 120
+ totalSize 5812
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
@@ -482,19 +364,19 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
bucket_count -1
- columns x,y
- columns.types int:string
+ columns key,value
+ columns.types string:string
#### A masked pattern was here ####
name default.fact_daily
numFiles 3
- numPartitions 3
- numRows 10
+ numPartitions 1
+ numRows 500
partition_columns ds/hr
- rawDataSize 110
- serialization.ddl struct fact_daily { i32 x, string y}
+ rawDataSize 5312
+ serialization.ddl struct fact_daily { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 120
+ totalSize 5812
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.fact_daily
@@ -508,41 +390,33 @@ STAGE PLANS:
PREHOOK: query: -- List Bucketing Query
-SELECT x,y FROM fact_daily WHERE ds='1' and hr='4' and x= 406
+SELECT key, value FROM fact_daily WHERE ds='1' and hr='4' and key= '406'
PREHOOK: type: QUERY
PREHOOK: Input: default@fact_daily@ds=1/hr=4
#### A masked pattern was here ####
POSTHOOK: query: -- List Bucketing Query
-SELECT x,y FROM fact_daily WHERE ds='1' and hr='4' and x= 406
+SELECT key, value FROM fact_daily WHERE ds='1' and hr='4' and key= '406'
POSTHOOK: type: QUERY
POSTHOOK: Input: default@fact_daily@ds=1/hr=4
#### A masked pattern was here ####
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=1).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=1).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=2).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=2).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=3).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=3).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=4).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=4).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
406 val_406
406 val_406
406 val_406
406 val_406
PREHOOK: query: -- pruner only pick up skewed-value directory
-- explain plan shows which directory selected: Truncated Path -> Alias
-explain extended SELECT x,y FROM fact_daily WHERE ds='1' and hr='4' and ( (x=484 and y ='val_484') or (x=238 and y= 'val_238'))
+explain extended SELECT key, value FROM fact_daily WHERE ds='1' and hr='4' and ( (key='484' and value ='val_484') or (key='238' and value= 'val_238'))
PREHOOK: type: QUERY
POSTHOOK: query: -- pruner only pick up skewed-value directory
-- explain plan shows which directory selected: Truncated Path -> Alias
-explain extended SELECT x,y FROM fact_daily WHERE ds='1' and hr='4' and ( (x=484 and y ='val_484') or (x=238 and y= 'val_238'))
+explain extended SELECT key, value FROM fact_daily WHERE ds='1' and hr='4' and ( (key='484' and value ='val_484') or (key='238' and value= 'val_238'))
POSTHOOK: type: QUERY
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=1).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=1).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=2).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=2).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=3).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=3).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=4).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=4).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
ABSTRACT SYNTAX TREE:
- (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME fact_daily))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL x)) (TOK_SELEXPR (TOK_TABLE_OR_COL y))) (TOK_WHERE (and (and (= (TOK_TABLE_OR_COL ds) '1') (= (TOK_TABLE_OR_COL hr) '4')) (or (and (= (TOK_TABLE_OR_COL x) 484) (= (TOK_TABLE_OR_COL y) 'val_484')) (and (= (TOK_TABLE_OR_COL x) 238) (= (TOK_TABLE_OR_COL y) 'val_238')))))))
+ (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME fact_daily))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_TABLE_OR_COL value))) (TOK_WHERE (and (and (= (TOK_TABLE_OR_COL ds) '1') (= (TOK_TABLE_OR_COL hr) '4')) (or (and (= (TOK_TABLE_OR_COL key) '484') (= (TOK_TABLE_OR_COL value) 'val_484')) (and (= (TOK_TABLE_OR_COL key) '238') (= (TOK_TABLE_OR_COL value) 'val_238')))))))
STAGE DEPENDENCIES:
Stage-1 is a root stage
@@ -559,13 +433,13 @@ STAGE PLANS:
Filter Operator
isSamplingPred: false
predicate:
- expr: (((x = 484) and (y = 'val_484')) or ((x = 238) and (y = 'val_238')))
+ expr: (((key = '484') and (value = 'val_484')) or ((key = '238') and (value = 'val_238')))
type: boolean
Select Operator
expressions:
- expr: x
- type: int
- expr: y
+ expr: key
+ type: string
+ expr: value
type: string
outputColumnNames: _col0, _col1
File Output Operator
@@ -579,7 +453,7 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
columns _col0,_col1
- columns.types int:string
+ columns.types string:string
escape.delim \
serialization.format 1
TotalFiles: 1
@@ -591,7 +465,7 @@ STAGE PLANS:
Path -> Partition:
#### A masked pattern was here ####
Partition
- base file name: y=val_238
+ base file name: value=val_238
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
partition values:
@@ -599,19 +473,19 @@ STAGE PLANS:
hr 4
properties:
bucket_count -1
- columns x,y
- columns.types int:string
+ columns key,value
+ columns.types string:string
#### A masked pattern was here ####
name default.fact_daily
numFiles 3
- numPartitions 3
- numRows 10
+ numPartitions 1
+ numRows 500
partition_columns ds/hr
- rawDataSize 110
- serialization.ddl struct fact_daily { i32 x, string y}
+ rawDataSize 5312
+ serialization.ddl struct fact_daily { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 120
+ totalSize 5812
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
@@ -619,26 +493,26 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
bucket_count -1
- columns x,y
- columns.types int:string
+ columns key,value
+ columns.types string:string
#### A masked pattern was here ####
name default.fact_daily
numFiles 3
- numPartitions 3
- numRows 10
+ numPartitions 1
+ numRows 500
partition_columns ds/hr
- rawDataSize 110
- serialization.ddl struct fact_daily { i32 x, string y}
+ rawDataSize 5312
+ serialization.ddl struct fact_daily { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 120
+ totalSize 5812
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.fact_daily
name: default.fact_daily
#### A masked pattern was here ####
Partition
- base file name: y=val_484
+ base file name: value=val_484
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
partition values:
@@ -646,19 +520,19 @@ STAGE PLANS:
hr 4
properties:
bucket_count -1
- columns x,y
- columns.types int:string
+ columns key,value
+ columns.types string:string
#### A masked pattern was here ####
name default.fact_daily
numFiles 3
- numPartitions 3
- numRows 10
+ numPartitions 1
+ numRows 500
partition_columns ds/hr
- rawDataSize 110
- serialization.ddl struct fact_daily { i32 x, string y}
+ rawDataSize 5312
+ serialization.ddl struct fact_daily { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 120
+ totalSize 5812
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
@@ -666,26 +540,26 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
bucket_count -1
- columns x,y
- columns.types int:string
+ columns key,value
+ columns.types string:string
#### A masked pattern was here ####
name default.fact_daily
numFiles 3
- numPartitions 3
- numRows 10
+ numPartitions 1
+ numRows 500
partition_columns ds/hr
- rawDataSize 110
- serialization.ddl struct fact_daily { i32 x, string y}
+ rawDataSize 5312
+ serialization.ddl struct fact_daily { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 120
+ totalSize 5812
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.fact_daily
name: default.fact_daily
Truncated Path -> Alias:
- /fact_daily/ds=1/hr=4/x=238/y=val_238 [fact_daily]
- /fact_daily/ds=1/hr=4/x=484/y=val_484 [fact_daily]
+ /fact_daily/ds=1/hr=4/key=238/value=val_238 [fact_daily]
+ /fact_daily/ds=1/hr=4/key=484/value=val_484 [fact_daily]
Stage: Stage-0
Fetch Operator
@@ -693,21 +567,17 @@ STAGE PLANS:
PREHOOK: query: -- List Bucketing Query
-SELECT x,y FROM fact_daily WHERE ds='1' and hr='4' and ( (x=484 and y ='val_484') or (x=238 and y= 'val_238'))
+SELECT key, value FROM fact_daily WHERE ds='1' and hr='4' and ( (key='484' and value ='val_484') or (key='238' and value= 'val_238'))
PREHOOK: type: QUERY
PREHOOK: Input: default@fact_daily@ds=1/hr=4
#### A masked pattern was here ####
POSTHOOK: query: -- List Bucketing Query
-SELECT x,y FROM fact_daily WHERE ds='1' and hr='4' and ( (x=484 and y ='val_484') or (x=238 and y= 'val_238'))
+SELECT key, value FROM fact_daily WHERE ds='1' and hr='4' and ( (key='484' and value ='val_484') or (key='238' and value= 'val_238'))
POSTHOOK: type: QUERY
POSTHOOK: Input: default@fact_daily@ds=1/hr=4
#### A masked pattern was here ####
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=1).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=1).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=2).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=2).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=3).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=3).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=4).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=4).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
238 val_238
238 val_238
484 val_484
@@ -721,9 +591,5 @@ drop table fact_daily
POSTHOOK: type: DROPTABLE
POSTHOOK: Input: default@fact_daily
POSTHOOK: Output: default@fact_daily
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=1).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=1).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=2).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=2).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=3).x EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=3).y SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=4).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=4).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]