PREHOOK: query: -- create table with 1000 rows
create table srcorc(key string, value string) stored as textfile
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
PREHOOK: Output: default@srcorc
POSTHOOK: query: -- create table with 1000 rows
create table srcorc(key string, value string) stored as textfile
POSTHOOK: type: CREATETABLE
POSTHOOK: Output: database:default
POSTHOOK: Output: default@srcorc
PREHOOK: query: insert overwrite table srcorc select * from src
PREHOOK: type: QUERY
PREHOOK: Input: default@src
PREHOOK: Output: default@srcorc
POSTHOOK: query: insert overwrite table srcorc select * from src
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
POSTHOOK: Output: default@srcorc
POSTHOOK: Lineage: srcorc.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
POSTHOOK: Lineage: srcorc.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
PREHOOK: query: insert into table srcorc select * from src
PREHOOK: type: QUERY
PREHOOK: Input: default@src
PREHOOK: Output: default@srcorc
POSTHOOK: query: insert into table srcorc select * from src
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
POSTHOOK: Output: default@srcorc
POSTHOOK: Lineage: srcorc.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
POSTHOOK: Lineage: srcorc.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
PREHOOK: query: -- load table with each row group having 1000 rows and stripe 1 & 2 having 5000 & 2000 rows respectively
create table if not exists vectororc
(s1 string,
s2 string,
d double,
s3 string)
stored as ORC tblproperties("orc.row.index.stride"="1000", "orc.stripe.size"="100000", "orc.compress.size"="10000")
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
PREHOOK: Output: default@vectororc
POSTHOOK: query: -- load table with each row group having 1000 rows and stripe 1 & 2 having 5000 & 2000 rows respectively
create table if not exists vectororc
(s1 string,
s2 string,
d double,
s3 string)
stored as ORC tblproperties("orc.row.index.stride"="1000", "orc.stripe.size"="100000", "orc.compress.size"="10000")
POSTHOOK: type: CREATETABLE
POSTHOOK: Output: database:default
POSTHOOK: Output: default@vectororc
PREHOOK: query: -- insert creates separate orc files
insert overwrite table vectororc select "apple", "a", rand(1), "zoo" from srcorc
PREHOOK: type: QUERY
PREHOOK: Input: default@srcorc
PREHOOK: Output: default@vectororc
POSTHOOK: query: -- insert creates separate orc files
insert overwrite table vectororc select "apple", "a", rand(1), "zoo" from srcorc
POSTHOOK: type: QUERY
POSTHOOK: Input: default@srcorc
POSTHOOK: Output: default@vectororc
POSTHOOK: Lineage: vectororc.d EXPRESSION []
POSTHOOK: Lineage: vectororc.s1 SIMPLE []
POSTHOOK: Lineage: vectororc.s2 SIMPLE []
POSTHOOK: Lineage: vectororc.s3 SIMPLE []
PREHOOK: query: insert into table vectororc select null, "b", rand(2), "zoo" from srcorc
PREHOOK: type: QUERY
PREHOOK: Input: default@srcorc
PREHOOK: Output: default@vectororc
POSTHOOK: query: insert into table vectororc select null, "b", rand(2), "zoo" from srcorc
POSTHOOK: type: QUERY
POSTHOOK: Input: default@srcorc
POSTHOOK: Output: default@vectororc
POSTHOOK: Lineage: vectororc.d EXPRESSION []
POSTHOOK: Lineage: vectororc.s1 EXPRESSION []
POSTHOOK: Lineage: vectororc.s2 SIMPLE []
POSTHOOK: Lineage: vectororc.s3 SIMPLE []
PREHOOK: query: insert into table vectororc select null, "c", rand(3), "zoo" from srcorc
PREHOOK: type: QUERY
PREHOOK: Input: default@srcorc
PREHOOK: Output: default@vectororc
POSTHOOK: query: insert into table vectororc select null, "c", rand(3), "zoo" from srcorc
POSTHOOK: type: QUERY
POSTHOOK: Input: default@srcorc
POSTHOOK: Output: default@vectororc
POSTHOOK: Lineage: vectororc.d EXPRESSION []
POSTHOOK: Lineage: vectororc.s1 EXPRESSION []
POSTHOOK: Lineage: vectororc.s2 SIMPLE []
POSTHOOK: Lineage: vectororc.s3 SIMPLE []
PREHOOK: query: insert into table vectororc select "apple", "d", rand(4), "zoo" from srcorc
PREHOOK: type: QUERY
PREHOOK: Input: default@srcorc
PREHOOK: Output: default@vectororc
POSTHOOK: query: insert into table vectororc select "apple", "d", rand(4), "zoo" from srcorc
POSTHOOK: type: QUERY
POSTHOOK: Input: default@srcorc
POSTHOOK: Output: default@vectororc
POSTHOOK: Lineage: vectororc.d EXPRESSION []
POSTHOOK: Lineage: vectororc.s1 SIMPLE []
POSTHOOK: Lineage: vectororc.s2 SIMPLE []
POSTHOOK: Lineage: vectororc.s3 SIMPLE []
PREHOOK: query: insert into table vectororc select null, "e", rand(5), "z" from srcorc
PREHOOK: type: QUERY
PREHOOK: Input: default@srcorc
PREHOOK: Output: default@vectororc
POSTHOOK: query: insert into table vectororc select null, "e", rand(5), "z" from srcorc
POSTHOOK: type: QUERY
POSTHOOK: Input: default@srcorc
POSTHOOK: Output: default@vectororc
POSTHOOK: Lineage: vectororc.d EXPRESSION []
POSTHOOK: Lineage: vectororc.s1 EXPRESSION []
POSTHOOK: Lineage: vectororc.s2 SIMPLE []
POSTHOOK: Lineage: vectororc.s3 SIMPLE []
PREHOOK: query: insert into table vectororc select "apple", "f", rand(6), "z" from srcorc
PREHOOK: type: QUERY
PREHOOK: Input: default@srcorc
PREHOOK: Output: default@vectororc
POSTHOOK: query: insert into table vectororc select "apple", "f", rand(6), "z" from srcorc
POSTHOOK: type: QUERY
POSTHOOK: Input: default@srcorc
POSTHOOK: Output: default@vectororc
POSTHOOK: Lineage: vectororc.d EXPRESSION []
POSTHOOK: Lineage: vectororc.s1 SIMPLE []
POSTHOOK: Lineage: vectororc.s2 SIMPLE []
POSTHOOK: Lineage: vectororc.s3 SIMPLE []
PREHOOK: query: insert into table vectororc select null, "g", rand(7), "zoo" from srcorc
PREHOOK: type: QUERY
PREHOOK: Input: default@srcorc
PREHOOK: Output: default@vectororc
POSTHOOK: query: insert into table vectororc select null, "g", rand(7), "zoo" from srcorc
POSTHOOK: type: QUERY
POSTHOOK: Input: default@srcorc
POSTHOOK: Output: default@vectororc
POSTHOOK: Lineage: vectororc.d EXPRESSION []
POSTHOOK: Lineage: vectororc.s1 EXPRESSION []
POSTHOOK: Lineage: vectororc.s2 SIMPLE []
POSTHOOK: Lineage: vectororc.s3 SIMPLE []
PREHOOK: query: -- since vectororc table has multiple orc file we will load them into a single file using another table
create table if not exists testorc
(s1 string,
s2 string,
d double,
s3 string)
stored as ORC tblproperties("orc.row.index.stride"="1000", "orc.stripe.size"="100000", "orc.compress.size"="10000")
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
PREHOOK: Output: default@testorc
POSTHOOK: query: -- since vectororc table has multiple orc file we will load them into a single file using another table
create table if not exists testorc
(s1 string,
s2 string,
d double,
s3 string)
stored as ORC tblproperties("orc.row.index.stride"="1000", "orc.stripe.size"="100000", "orc.compress.size"="10000")
POSTHOOK: type: CREATETABLE
POSTHOOK: Output: database:default
POSTHOOK: Output: default@testorc
PREHOOK: query: insert overwrite table testorc select * from vectororc order by s2
PREHOOK: type: QUERY
PREHOOK: Input: default@vectororc
PREHOOK: Output: default@testorc
POSTHOOK: query: insert overwrite table testorc select * from vectororc order by s2
POSTHOOK: type: QUERY
POSTHOOK: Input: default@vectororc
POSTHOOK: Output: default@testorc
POSTHOOK: Lineage: testorc.d SIMPLE [(vectororc)vectororc.FieldSchema(name:d, type:double, comment:null), ]
POSTHOOK: Lineage: testorc.s1 SIMPLE [(vectororc)vectororc.FieldSchema(name:s1, type:string, comment:null), ]
POSTHOOK: Lineage: testorc.s2 SIMPLE [(vectororc)vectororc.FieldSchema(name:s2, type:string, comment:null), ]
POSTHOOK: Lineage: testorc.s3 SIMPLE [(vectororc)vectororc.FieldSchema(name:s3, type:string, comment:null), ]
PREHOOK: query: -- row group (1,4) from stripe 1 and row group (1) from stripe 2
-- PPD ONLY
select count(*),int(sum(d)) from testorc where s1 is not null
PREHOOK: type: QUERY
PREHOOK: Input: default@testorc
#### A masked pattern was here ####
POSTHOOK: query: -- row group (1,4) from stripe 1 and row group (1) from stripe 2
-- PPD ONLY
select count(*),int(sum(d)) from testorc where s1 is not null
POSTHOOK: type: QUERY
POSTHOOK: Input: default@testorc
#### A masked pattern was here ####
3000	1505
PREHOOK: query: -- VECTORIZATION + PPD
select count(*),int(sum(d)) from testorc where s1 is not null
PREHOOK: type: QUERY
PREHOOK: Input: default@testorc
#### A masked pattern was here ####
POSTHOOK: query: -- VECTORIZATION + PPD
select count(*),int(sum(d)) from testorc where s1 is not null
POSTHOOK: type: QUERY
POSTHOOK: Input: default@testorc
#### A masked pattern was here ####
3000	1505
PREHOOK: query: -- row group (2,3,5) from stripe 1 and row group (2) from stripe 2
-- PPD ONLY
select count(*),int(sum(d)) from testorc where s2 in ("b", "c", "e", "g")
PREHOOK: type: QUERY
PREHOOK: Input: default@testorc
#### A masked pattern was here ####
POSTHOOK: query: -- row group (2,3,5) from stripe 1 and row group (2) from stripe 2
-- PPD ONLY
select count(*),int(sum(d)) from testorc where s2 in ("b", "c", "e", "g")
POSTHOOK: type: QUERY
POSTHOOK: Input: default@testorc
#### A masked pattern was here ####
4000	2006
PREHOOK: query: -- VECTORIZATION + PPD
select count(*),int(sum(d)) from testorc where s2 in ("b", "c", "e", "g")
PREHOOK: type: QUERY
PREHOOK: Input: default@testorc
#### A masked pattern was here ####
POSTHOOK: query: -- VECTORIZATION + PPD
select count(*),int(sum(d)) from testorc where s2 in ("b", "c", "e", "g")
POSTHOOK: type: QUERY
POSTHOOK: Input: default@testorc
#### A masked pattern was here ####
4000	2006
PREHOOK: query: -- last row group of stripe 1 and first row group of stripe 2
-- PPD ONLY
select count(*),int(sum(d)) from testorc where s3="z"
PREHOOK: type: QUERY
PREHOOK: Input: default@testorc
#### A masked pattern was here ####
POSTHOOK: query: -- last row group of stripe 1 and first row group of stripe 2
-- PPD ONLY
select count(*),int(sum(d)) from testorc where s3="z"
POSTHOOK: type: QUERY
POSTHOOK: Input: default@testorc
#### A masked pattern was here ####
2000	1011
PREHOOK: query: -- VECTORIZATION + PPD
select count(*),int(sum(d)) from testorc where s3="z"
PREHOOK: type: QUERY
PREHOOK: Input: default@testorc
#### A masked pattern was here ####
POSTHOOK: query: -- VECTORIZATION + PPD
select count(*),int(sum(d)) from testorc where s3="z"
POSTHOOK: type: QUERY
POSTHOOK: Input: default@testorc
#### A masked pattern was here ####
2000	1011
PREHOOK: query: -- first row group of stripe 1 and last row group of stripe 2
-- PPD ONLY
select count(*),int(sum(d)) from testorc where s2="a" or s2="g"
PREHOOK: type: QUERY
PREHOOK: Input: default@testorc
#### A masked pattern was here ####
POSTHOOK: query: -- first row group of stripe 1 and last row group of stripe 2
-- PPD ONLY
select count(*),int(sum(d)) from testorc where s2="a" or s2="g"
POSTHOOK: type: QUERY
POSTHOOK: Input: default@testorc
#### A masked pattern was here ####
2000	1006
PREHOOK: query: -- VECTORIZATION + PPD
select count(*),int(sum(d)) from testorc where s2="a" or s2="g"
PREHOOK: type: QUERY
PREHOOK: Input: default@testorc
#### A masked pattern was here ####
POSTHOOK: query: -- VECTORIZATION + PPD
select count(*),int(sum(d)) from testorc where s2="a" or s2="g"
POSTHOOK: type: QUERY
POSTHOOK: Input: default@testorc
#### A masked pattern was here ####
2000	1006
PREHOOK: query: drop table srcorc
PREHOOK: type: DROPTABLE
PREHOOK: Input: default@srcorc
PREHOOK: Output: default@srcorc
POSTHOOK: query: drop table srcorc
POSTHOOK: type: DROPTABLE
POSTHOOK: Input: default@srcorc
POSTHOOK: Output: default@srcorc
PREHOOK: query: drop table vectororc
PREHOOK: type: DROPTABLE
PREHOOK: Input: default@vectororc
PREHOOK: Output: default@vectororc
POSTHOOK: query: drop table vectororc
POSTHOOK: type: DROPTABLE
POSTHOOK: Input: default@vectororc
POSTHOOK: Output: default@vectororc
PREHOOK: query: drop table testorc
PREHOOK: type: DROPTABLE
PREHOOK: Input: default@testorc
PREHOOK: Output: default@testorc
POSTHOOK: query: drop table testorc
POSTHOOK: type: DROPTABLE
POSTHOOK: Input: default@testorc
POSTHOOK: Output: default@testorc