jprdonnelly/impala
1
0
Fork 0
mirror of https://github.com/apache/impala.git synced 2026-02-03 00:00:40 -05:00
Code Issues Projects Releases Wiki Activity
Files
13bbff4e4e5fc5d459cc6f7a5512f84ceba897cd
impala/testdata/workloads/functional-planner/queries/PlannerTest/multiple-distinct-predicates.test
Tim Armstrong 983e3a66de IMPALA-2138: part 1: initial cleanup 
This is a mixed bag of simplifications, debugging improvements
and test fixes that came up in the projection work.

I had to update some planner tests because some expressions
now include their arguments. Various things in the planner
tests were stale, so there are spurious changes in the
expected output that are ignored by the plan verification.

Change-Id: I75d2c8cab79988300c1a9c6c23d6ccea53da7d23
Reviewed-on: http://gerrit.cloudera.org:8080/14265
Reviewed-by: Impala Public Jenkins <impala-public-jenkins@cloudera.com>
Tested-by: Impala Public Jenkins <impala-public-jenkins@cloudera.com>
2019-09-20 22:15:41 +00:00

559 lines
21 KiB
Plaintext
Raw Blame History

# HAVING predicate assignment. No group by.
select count(distinct tinyint_col), count(distinct smallint_col), max(string_col)
from functional.alltypes
having count(distinct tinyint_col) < 10
and count(distinct smallint_col) between 20 and 30
and max(string_col) = 'test'
---- PLAN
PLAN-ROOT SINK
|
03:AGGREGATE [FINALIZE]
| output: aggif(valid_tid(2,4,5) = 2, count(tinyint_col)), aggif(valid_tid(2,4,5) = 4, count(smallint_col)), aggif(valid_tid(2,4,5) = 5, max(string_col))
| having: aggif(valid_tid(2,4,5) = 2, count(tinyint_col)) < 10, aggif(valid_tid(2,4,5) = 4, count(smallint_col)) <= 30, aggif(valid_tid(2,4,5) = 4, count(smallint_col)) >= 20, aggif(valid_tid(2,4,5) = 5, max(string_col)) = 'test'
| row-size=28B cardinality=0
|
02:AGGREGATE [FINALIZE]
| Class 0
| output: count(tinyint_col)
| Class 1
| output: count(smallint_col)
| Class 2
| output: max:merge(string_col)
| row-size=28B cardinality=3
|
01:AGGREGATE
| Class 0
| group by: tinyint_col
| Class 1
| group by: smallint_col
| Class 2
| output: max(string_col)
| row-size=15B cardinality=21
|
00:SCAN HDFS [functional.alltypes]
HDFS partitions=24/24 files=24 size=478.45KB
row-size=16B cardinality=7.30K
---- DISTRIBUTEDPLAN
PLAN-ROOT SINK
|
03:AGGREGATE [FINALIZE]
| output: aggif(valid_tid(2,4,5) = 2, count(tinyint_col)), aggif(valid_tid(2,4,5) = 4, count(smallint_col)), aggif(valid_tid(2,4,5) = 5, max(string_col))
| having: aggif(valid_tid(2,4,5) = 2, count(tinyint_col)) < 10, aggif(valid_tid(2,4,5) = 4, count(smallint_col)) <= 30, aggif(valid_tid(2,4,5) = 4, count(smallint_col)) >= 20, aggif(valid_tid(2,4,5) = 5, max(string_col)) = 'test'
| row-size=28B cardinality=0
|
07:AGGREGATE [FINALIZE]
| Class 0
| output: count:merge(tinyint_col)
| Class 1
| output: count:merge(smallint_col)
| Class 2
| output: max:merge(string_col)
| row-size=28B cardinality=3
|
06:EXCHANGE [UNPARTITIONED]
|
02:AGGREGATE
| Class 0
| output: count(tinyint_col)
| Class 1
| output: count(smallint_col)
| Class 2
| output: max:merge(string_col)
| row-size=28B cardinality=3
|
05:AGGREGATE
| Class 0
| group by: tinyint_col
| Class 1
| group by: smallint_col
| Class 2
| output: max:merge(string_col)
| row-size=15B cardinality=21
|
04:EXCHANGE [HASH(CASE valid_tid(1,3,5) WHEN 1 THEN murmur_hash(tinyint_col) WHEN 3 THEN murmur_hash(smallint_col) WHEN 5 THEN 0 END)]
|
01:AGGREGATE [STREAMING]
| Class 0
| group by: tinyint_col
| Class 1
| group by: smallint_col
| Class 2
| output: max(string_col)
| row-size=15B cardinality=21
|
00:SCAN HDFS [functional.alltypes]
HDFS partitions=24/24 files=24 size=478.45KB
row-size=16B cardinality=7.30K
====
# HAVING predicate references multiple aggregates. No group by.
select count(distinct tinyint_col), count(distinct smallint_col), max(string_col)
from functional.alltypes
having count(distinct tinyint_col) < count(distinct smallint_col)
---- PLAN
PLAN-ROOT SINK
|
03:AGGREGATE [FINALIZE]
| output: aggif(valid_tid(2,4,5) = 2, count(tinyint_col)), aggif(valid_tid(2,4,5) = 4, count(smallint_col)), aggif(valid_tid(2,4,5) = 5, max(string_col))
| having: aggif(valid_tid(2,4,5) = 2, count(tinyint_col)) < aggif(valid_tid(2,4,5) = 4, count(smallint_col))
| row-size=28B cardinality=0
|
02:AGGREGATE [FINALIZE]
| Class 0
| output: count(tinyint_col)
| Class 1
| output: count(smallint_col)
| Class 2
| output: max:merge(string_col)
| row-size=28B cardinality=3
|
01:AGGREGATE
| Class 0
| group by: tinyint_col
| Class 1
| group by: smallint_col
| Class 2
| output: max(string_col)
| row-size=15B cardinality=21
|
00:SCAN HDFS [functional.alltypes]
HDFS partitions=24/24 files=24 size=478.45KB
row-size=16B cardinality=7.30K
---- DISTRIBUTEDPLAN
PLAN-ROOT SINK
|
03:AGGREGATE [FINALIZE]
| output: aggif(valid_tid(2,4,5) = 2, count(tinyint_col)), aggif(valid_tid(2,4,5) = 4, count(smallint_col)), aggif(valid_tid(2,4,5) = 5, max(string_col))
| having: aggif(valid_tid(2,4,5) = 2, count(tinyint_col)) < aggif(valid_tid(2,4,5) = 4, count(smallint_col))
| row-size=28B cardinality=0
|
07:AGGREGATE [FINALIZE]
| Class 0
| output: count:merge(tinyint_col)
| Class 1
| output: count:merge(smallint_col)
| Class 2
| output: max:merge(string_col)
| row-size=28B cardinality=3
|
06:EXCHANGE [UNPARTITIONED]
|
02:AGGREGATE
| Class 0
| output: count(tinyint_col)
| Class 1
| output: count(smallint_col)
| Class 2
| output: max:merge(string_col)
| row-size=28B cardinality=3
|
05:AGGREGATE
| Class 0
| group by: tinyint_col
| Class 1
| group by: smallint_col
| Class 2
| output: max:merge(string_col)
| row-size=15B cardinality=21
|
04:EXCHANGE [HASH(CASE valid_tid(1,3,5) WHEN 1 THEN murmur_hash(tinyint_col) WHEN 3 THEN murmur_hash(smallint_col) WHEN 5 THEN 0 END)]
|
01:AGGREGATE [STREAMING]
| Class 0
| group by: tinyint_col
| Class 1
| group by: smallint_col
| Class 2
| output: max(string_col)
| row-size=15B cardinality=21
|
00:SCAN HDFS [functional.alltypes]
HDFS partitions=24/24 files=24 size=478.45KB
row-size=16B cardinality=7.30K
====
# Predicates assigned through inline view. No group by.
select a, b, c from
(select count(distinct tinyint_col) a, count(distinct smallint_col) b, max(string_col) c
from functional.alltypes) v
where a < b and b between 20 and 30 and c = 'test'
---- PLAN
PLAN-ROOT SINK
|
03:AGGREGATE [FINALIZE]
| output: aggif(valid_tid(2,4,5) = 2, count(tinyint_col)), aggif(valid_tid(2,4,5) = 4, count(smallint_col)), aggif(valid_tid(2,4,5) = 5, max(string_col))
| having: aggif(valid_tid(2,4,5) = 2, count(tinyint_col)) < aggif(valid_tid(2,4,5) = 4, count(smallint_col)), aggif(valid_tid(2,4,5) = 4, count(smallint_col)) <= 30, aggif(valid_tid(2,4,5) = 4, count(smallint_col)) >= 20, aggif(valid_tid(2,4,5) = 5, max(string_col)) = 'test'
| row-size=28B cardinality=0
|
02:AGGREGATE [FINALIZE]
| Class 0
| output: count(tinyint_col)
| Class 1
| output: count(smallint_col)
| Class 2
| output: max:merge(string_col)
| row-size=28B cardinality=3
|
01:AGGREGATE
| Class 0
| group by: tinyint_col
| Class 1
| group by: smallint_col
| Class 2
| output: max(string_col)
| row-size=15B cardinality=21
|
00:SCAN HDFS [functional.alltypes]
HDFS partitions=24/24 files=24 size=478.45KB
row-size=16B cardinality=7.30K
---- DISTRIBUTEDPLAN
PLAN-ROOT SINK
|
03:AGGREGATE [FINALIZE]
| output: aggif(valid_tid(2,4,5) = 2, count(tinyint_col)), aggif(valid_tid(2,4,5) = 4, count(smallint_col)), aggif(valid_tid(2,4,5) = 5, max(string_col))
| having: aggif(valid_tid(2,4,5) = 2, count(tinyint_col)) < aggif(valid_tid(2,4,5) = 4, count(smallint_col)), aggif(valid_tid(2,4,5) = 4, count(smallint_col)) <= 30, aggif(valid_tid(2,4,5) = 4, count(smallint_col)) >= 20, aggif(valid_tid(2,4,5) = 5, max(string_col)) = 'test'
| row-size=28B cardinality=0
|
07:AGGREGATE [FINALIZE]
| Class 0
| output: count:merge(tinyint_col)
| Class 1
| output: count:merge(smallint_col)
| Class 2
| output: max:merge(string_col)
| row-size=28B cardinality=3
|
06:EXCHANGE [UNPARTITIONED]
|
02:AGGREGATE
| Class 0
| output: count(tinyint_col)
| Class 1
| output: count(smallint_col)
| Class 2
| output: max:merge(string_col)
| row-size=28B cardinality=3
|
05:AGGREGATE
| Class 0
| group by: tinyint_col
| Class 1
| group by: smallint_col
| Class 2
| output: max:merge(string_col)
| row-size=15B cardinality=21
|
04:EXCHANGE [HASH(CASE valid_tid(1,3,5) WHEN 1 THEN murmur_hash(tinyint_col) WHEN 3 THEN murmur_hash(smallint_col) WHEN 5 THEN 0 END)]
|
01:AGGREGATE [STREAMING]
| Class 0
| group by: tinyint_col
| Class 1
| group by: smallint_col
| Class 2
| output: max(string_col)
| row-size=15B cardinality=21
|
00:SCAN HDFS [functional.alltypes]
HDFS partitions=24/24 files=24 size=478.45KB
row-size=16B cardinality=7.30K
====
# Predicates assigned through inline view. No group by.
select a, b, c from
(select count(distinct tinyint_col) a, count(distinct smallint_col) b, max(string_col) c
from functional.alltypes) v
where a < b and b between 20 and 30 and c = 'test'
---- PLAN
PLAN-ROOT SINK
|
03:AGGREGATE [FINALIZE]
| output: aggif(valid_tid(2,4,5) = 2, count(tinyint_col)), aggif(valid_tid(2,4,5) = 4, count(smallint_col)), aggif(valid_tid(2,4,5) = 5, max(string_col))
| having: aggif(valid_tid(2,4,5) = 2, count(tinyint_col)) < aggif(valid_tid(2,4,5) = 4, count(smallint_col)), aggif(valid_tid(2,4,5) = 4, count(smallint_col)) <= 30, aggif(valid_tid(2,4,5) = 4, count(smallint_col)) >= 20, aggif(valid_tid(2,4,5) = 5, max(string_col)) = 'test'
| row-size=28B cardinality=0
|
02:AGGREGATE [FINALIZE]
| Class 0
| output: count(tinyint_col)
| Class 1
| output: count(smallint_col)
| Class 2
| output: max:merge(string_col)
| row-size=28B cardinality=3
|
01:AGGREGATE
| Class 0
| group by: tinyint_col
| Class 1
| group by: smallint_col
| Class 2
| output: max(string_col)
| row-size=15B cardinality=21
|
00:SCAN HDFS [functional.alltypes]
HDFS partitions=24/24 files=24 size=478.45KB
row-size=16B cardinality=7.30K
---- DISTRIBUTEDPLAN
PLAN-ROOT SINK
|
03:AGGREGATE [FINALIZE]
| output: aggif(valid_tid(2,4,5) = 2, count(tinyint_col)), aggif(valid_tid(2,4,5) = 4, count(smallint_col)), aggif(valid_tid(2,4,5) = 5, max(string_col))
| having: aggif(valid_tid(2,4,5) = 2, count(tinyint_col)) < aggif(valid_tid(2,4,5) = 4, count(smallint_col)), aggif(valid_tid(2,4,5) = 4, count(smallint_col)) <= 30, aggif(valid_tid(2,4,5) = 4, count(smallint_col)) >= 20, aggif(valid_tid(2,4,5) = 5, max(string_col)) = 'test'
| row-size=28B cardinality=0
|
07:AGGREGATE [FINALIZE]
| Class 0
| output: count:merge(tinyint_col)
| Class 1
| output: count:merge(smallint_col)
| Class 2
| output: max:merge(string_col)
| row-size=28B cardinality=3
|
06:EXCHANGE [UNPARTITIONED]
|
02:AGGREGATE
| Class 0
| output: count(tinyint_col)
| Class 1
| output: count(smallint_col)
| Class 2
| output: max:merge(string_col)
| row-size=28B cardinality=3
|
05:AGGREGATE
| Class 0
| group by: tinyint_col
| Class 1
| group by: smallint_col
| Class 2
| output: max:merge(string_col)
| row-size=15B cardinality=21
|
04:EXCHANGE [HASH(CASE valid_tid(1,3,5) WHEN 1 THEN murmur_hash(tinyint_col) WHEN 3 THEN murmur_hash(smallint_col) WHEN 5 THEN 0 END)]
|
01:AGGREGATE [STREAMING]
| Class 0
| group by: tinyint_col
| Class 1
| group by: smallint_col
| Class 2
| output: max(string_col)
| row-size=15B cardinality=21
|
00:SCAN HDFS [functional.alltypes]
HDFS partitions=24/24 files=24 size=478.45KB
row-size=16B cardinality=7.30K
====
# HAVING predicate assignment. With group by.
select count(distinct tinyint_col), count(distinct smallint_col), max(string_col)
from functional.alltypes
group by date_string_col, timestamp_col
having count(distinct tinyint_col) < 10
and date_string_col between 'test1' and 'test2'
and cast(timestamp_col as string) < date_string_col
and cast(timestamp_col as bigint) = count(distinct tinyint_col)
---- PLAN
PLAN-ROOT SINK
|
03:AGGREGATE [FINALIZE]
| output: aggif(valid_tid(2,4,5) = 2, count(tinyint_col)), aggif(valid_tid(2,4,5) = 4, count(smallint_col)), aggif(valid_tid(2,4,5) = 5, max(string_col))
| group by: CASE valid_tid(2,4,5) WHEN 2 THEN date_string_col WHEN 4 THEN date_string_col WHEN 5 THEN date_string_col END, CASE valid_tid(2,4,5) WHEN 2 THEN timestamp_col WHEN 4 THEN timestamp_col WHEN 5 THEN timestamp_col END
| having: aggif(valid_tid(2,4,5) = 2, count(tinyint_col)) < 10, CAST(CASE valid_tid(2,4,5) WHEN 2 THEN timestamp_col WHEN 4 THEN timestamp_col WHEN 5 THEN timestamp_col END AS BIGINT) = aggif(valid_tid(2,4,5) = 2, count(tinyint_col)), CAST(CASE valid_tid(2,4,5) WHEN 2 THEN timestamp_col WHEN 4 THEN timestamp_col WHEN 5 THEN timestamp_col END AS STRING) < CASE valid_tid(2,4,5) WHEN 2 THEN date_string_col WHEN 4 THEN date_string_col WHEN 5 THEN date_string_col END
| row-size=56B cardinality=657
|
02:AGGREGATE [FINALIZE]
| Class 0
| output: count(tinyint_col)
| group by: date_string_col, timestamp_col
| Class 1
| output: count(smallint_col)
| group by: date_string_col, timestamp_col
| Class 2
| output: max:merge(string_col)
| group by: date_string_col, timestamp_col
| row-size=136B cardinality=6.57K
|
01:AGGREGATE
| Class 0
| group by: date_string_col, timestamp_col, tinyint_col
| Class 1
| group by: date_string_col, timestamp_col, smallint_col
| Class 2
| output: max(string_col)
| group by: date_string_col, timestamp_col
| row-size=123B cardinality=2.19K
|
00:SCAN HDFS [functional.alltypes]
HDFS partitions=24/24 files=24 size=478.45KB
predicates: functional.alltypes.date_string_col <= 'test2', functional.alltypes.date_string_col >= 'test1', CAST(functional.alltypes.timestamp_col AS STRING) < functional.alltypes.date_string_col
row-size=52B cardinality=730
---- DISTRIBUTEDPLAN
PLAN-ROOT SINK
|
08:EXCHANGE [UNPARTITIONED]
|
03:AGGREGATE [FINALIZE]
| output: aggif(valid_tid(2,4,5) = 2, count(tinyint_col)), aggif(valid_tid(2,4,5) = 4, count(smallint_col)), aggif(valid_tid(2,4,5) = 5, max(string_col))
| group by: CASE valid_tid(2,4,5) WHEN 2 THEN date_string_col WHEN 4 THEN date_string_col WHEN 5 THEN date_string_col END, CASE valid_tid(2,4,5) WHEN 2 THEN timestamp_col WHEN 4 THEN timestamp_col WHEN 5 THEN timestamp_col END
| having: aggif(valid_tid(2,4,5) = 2, count(tinyint_col)) < 10, CAST(CASE valid_tid(2,4,5) WHEN 2 THEN timestamp_col WHEN 4 THEN timestamp_col WHEN 5 THEN timestamp_col END AS BIGINT) = aggif(valid_tid(2,4,5) = 2, count(tinyint_col)), CAST(CASE valid_tid(2,4,5) WHEN 2 THEN timestamp_col WHEN 4 THEN timestamp_col WHEN 5 THEN timestamp_col END AS STRING) < CASE valid_tid(2,4,5) WHEN 2 THEN date_string_col WHEN 4 THEN date_string_col WHEN 5 THEN date_string_col END
| row-size=56B cardinality=657
|
07:AGGREGATE [FINALIZE]
| Class 0
| output: count:merge(tinyint_col)
| group by: date_string_col, timestamp_col
| Class 1
| output: count:merge(smallint_col)
| group by: date_string_col, timestamp_col
| Class 2
| output: max:merge(string_col)
| group by: date_string_col, timestamp_col
| row-size=136B cardinality=6.57K
|
06:EXCHANGE [HASH(CASE valid_tid(2,4,5) WHEN 2 THEN murmur_hash(date_string_col) WHEN 4 THEN murmur_hash(date_string_col) WHEN 5 THEN murmur_hash(date_string_col) END,CASE valid_tid(2,4,5) WHEN 2 THEN murmur_hash(timestamp_col) WHEN 4 THEN murmur_hash(timestamp_col) WHEN 5 THEN murmur_hash(timestamp_col) END)]
|
02:AGGREGATE [STREAMING]
| Class 0
| output: count(tinyint_col)
| group by: date_string_col, timestamp_col
| Class 1
| output: count(smallint_col)
| group by: date_string_col, timestamp_col
| Class 2
| output: max:merge(string_col)
| group by: date_string_col, timestamp_col
| row-size=136B cardinality=6.57K
|
05:AGGREGATE
| Class 0
| group by: date_string_col, timestamp_col, tinyint_col
| Class 1
| group by: date_string_col, timestamp_col, smallint_col
| Class 2
| output: max:merge(string_col)
| group by: date_string_col, timestamp_col
| row-size=123B cardinality=2.19K
|
04:EXCHANGE [HASH(CASE valid_tid(1,3,5) WHEN 1 THEN murmur_hash(date_string_col) WHEN 3 THEN murmur_hash(date_string_col) WHEN 5 THEN murmur_hash(date_string_col) END,CASE valid_tid(1,3,5) WHEN 1 THEN murmur_hash(timestamp_col) WHEN 3 THEN murmur_hash(timestamp_col) WHEN 5 THEN murmur_hash(timestamp_col) END,CASE valid_tid(1,3,5) WHEN 1 THEN murmur_hash(tinyint_col) WHEN 3 THEN murmur_hash(smallint_col) WHEN 5 THEN 0 END)]
|
01:AGGREGATE [STREAMING]
| Class 0
| group by: date_string_col, timestamp_col, tinyint_col
| Class 1
| group by: date_string_col, timestamp_col, smallint_col
| Class 2
| output: max(string_col)
| group by: date_string_col, timestamp_col
| row-size=123B cardinality=2.19K
|
00:SCAN HDFS [functional.alltypes]
HDFS partitions=24/24 files=24 size=478.45KB
predicates: functional.alltypes.date_string_col <= 'test2', functional.alltypes.date_string_col >= 'test1', CAST(functional.alltypes.timestamp_col AS STRING) < functional.alltypes.date_string_col
row-size=52B cardinality=730
====
# Predicate assignment through an inline view. With group by.
select a, b, c from
(select count(distinct tinyint_col) a, count(distinct smallint_col) b, max(string_col) c,
date_string_col gby1, timestamp_col gby2
from functional.alltypes
group by gby1, gby2) v
where a < 10 and gby1 between 'test1' and 'test2' and cast(gby2 as string) < gby1
and cast(gby2 as bigint) = a
---- PLAN
PLAN-ROOT SINK
|
03:AGGREGATE [FINALIZE]
| output: aggif(valid_tid(2,4,5) = 2, count(tinyint_col)), aggif(valid_tid(2,4,5) = 4, count(smallint_col)), aggif(valid_tid(2,4,5) = 5, max(string_col))
| group by: CASE valid_tid(2,4,5) WHEN 2 THEN date_string_col WHEN 4 THEN date_string_col WHEN 5 THEN date_string_col END, CASE valid_tid(2,4,5) WHEN 2 THEN timestamp_col WHEN 4 THEN timestamp_col WHEN 5 THEN timestamp_col END
| having: aggif(valid_tid(2,4,5) = 2, count(tinyint_col)) < 10, CAST(CASE valid_tid(2,4,5) WHEN 2 THEN timestamp_col WHEN 4 THEN timestamp_col WHEN 5 THEN timestamp_col END AS BIGINT) = aggif(valid_tid(2,4,5) = 2, count(tinyint_col)), CAST(CASE valid_tid(2,4,5) WHEN 2 THEN timestamp_col WHEN 4 THEN timestamp_col WHEN 5 THEN timestamp_col END AS STRING) < CASE valid_tid(2,4,5) WHEN 2 THEN date_string_col WHEN 4 THEN date_string_col WHEN 5 THEN date_string_col END
| row-size=56B cardinality=657
|
02:AGGREGATE [FINALIZE]
| Class 0
| output: count(tinyint_col)
| group by: date_string_col, timestamp_col
| Class 1
| output: count(smallint_col)
| group by: date_string_col, timestamp_col
| Class 2
| output: max:merge(string_col)
| group by: date_string_col, timestamp_col
| row-size=136B cardinality=6.57K
|
01:AGGREGATE
| Class 0
| group by: date_string_col, timestamp_col, tinyint_col
| Class 1
| group by: date_string_col, timestamp_col, smallint_col
| Class 2
| output: max(string_col)
| group by: date_string_col, timestamp_col
| row-size=123B cardinality=2.19K
|
00:SCAN HDFS [functional.alltypes]
HDFS partitions=24/24 files=24 size=478.45KB
predicates: functional.alltypes.date_string_col <= 'test2', functional.alltypes.date_string_col >= 'test1', CAST(functional.alltypes.timestamp_col AS STRING) < functional.alltypes.date_string_col
row-size=52B cardinality=730
---- DISTRIBUTEDPLAN
PLAN-ROOT SINK
|
08:EXCHANGE [UNPARTITIONED]
|
03:AGGREGATE [FINALIZE]
| output: aggif(valid_tid(2,4,5) = 2, count(tinyint_col)), aggif(valid_tid(2,4,5) = 4, count(smallint_col)), aggif(valid_tid(2,4,5) = 5, max(string_col))
| group by: CASE valid_tid(2,4,5) WHEN 2 THEN date_string_col WHEN 4 THEN date_string_col WHEN 5 THEN date_string_col END, CASE valid_tid(2,4,5) WHEN 2 THEN timestamp_col WHEN 4 THEN timestamp_col WHEN 5 THEN timestamp_col END
| having: aggif(valid_tid(2,4,5) = 2, count(tinyint_col)) < 10, CAST(CASE valid_tid(2,4,5) WHEN 2 THEN timestamp_col WHEN 4 THEN timestamp_col WHEN 5 THEN timestamp_col END AS BIGINT) = aggif(valid_tid(2,4,5) = 2, count(tinyint_col)), CAST(CASE valid_tid(2,4,5) WHEN 2 THEN timestamp_col WHEN 4 THEN timestamp_col WHEN 5 THEN timestamp_col END AS STRING) < CASE valid_tid(2,4,5) WHEN 2 THEN date_string_col WHEN 4 THEN date_string_col WHEN 5 THEN date_string_col END
| row-size=56B cardinality=657
|
07:AGGREGATE [FINALIZE]
| Class 0
| output: count:merge(tinyint_col)
| group by: date_string_col, timestamp_col
| Class 1
| output: count:merge(smallint_col)
| group by: date_string_col, timestamp_col
| Class 2
| output: max:merge(string_col)
| group by: date_string_col, timestamp_col
| row-size=136B cardinality=6.57K
|
06:EXCHANGE [HASH(CASE valid_tid(2,4,5) WHEN 2 THEN murmur_hash(date_string_col) WHEN 4 THEN murmur_hash(date_string_col) WHEN 5 THEN murmur_hash(date_string_col) END,CASE valid_tid(2,4,5) WHEN 2 THEN murmur_hash(timestamp_col) WHEN 4 THEN murmur_hash(timestamp_col) WHEN 5 THEN murmur_hash(timestamp_col) END)]
|
02:AGGREGATE [STREAMING]
| Class 0
| output: count(tinyint_col)
| group by: date_string_col, timestamp_col
| Class 1
| output: count(smallint_col)
| group by: date_string_col, timestamp_col
| Class 2
| output: max:merge(string_col)
| group by: date_string_col, timestamp_col
| row-size=136B cardinality=6.57K
|
05:AGGREGATE
| Class 0
| group by: date_string_col, timestamp_col, tinyint_col
| Class 1
| group by: date_string_col, timestamp_col, smallint_col
| Class 2
| output: max:merge(string_col)
| group by: date_string_col, timestamp_col
| row-size=123B cardinality=2.19K
|
04:EXCHANGE [HASH(CASE valid_tid(1,3,5) WHEN 1 THEN murmur_hash(date_string_col) WHEN 3 THEN murmur_hash(date_string_col) WHEN 5 THEN murmur_hash(date_string_col) END,CASE valid_tid(1,3,5) WHEN 1 THEN murmur_hash(timestamp_col) WHEN 3 THEN murmur_hash(timestamp_col) WHEN 5 THEN murmur_hash(timestamp_col) END,CASE valid_tid(1,3,5) WHEN 1 THEN murmur_hash(tinyint_col) WHEN 3 THEN murmur_hash(smallint_col) WHEN 5 THEN 0 END)]
|
01:AGGREGATE [STREAMING]
| Class 0
| group by: date_string_col, timestamp_col, tinyint_col
| Class 1
| group by: date_string_col, timestamp_col, smallint_col
| Class 2
| output: max(string_col)
| group by: date_string_col, timestamp_col
| row-size=123B cardinality=2.19K
|
00:SCAN HDFS [functional.alltypes]
HDFS partitions=24/24 files=24 size=478.45KB
predicates: functional.alltypes.date_string_col <= 'test2', functional.alltypes.date_string_col >= 'test1', CAST(functional.alltypes.timestamp_col AS STRING) < functional.alltypes.date_string_col
row-size=52B cardinality=730
====
Reference in New Issue View Git Blame Copy Permalink