mirror of
https://github.com/apache/impala.git
synced 2026-01-05 12:01:11 -05:00
fd09294b74
This is preparation for fixing IMPALA-97. These changes are mostly non-functional to bring the code closer to styling standards. The biggest functional changes should be: 1) IMPALA-1623 was caused by a misuse of a constructor and that code didn't compile after the refactor so the bug was fixed. 2) TimestampValue.Hash() seems to have been hashing the time twice instead of the time and date. 3) Timings using TimestampValue.time() would not be accurate when crossing midnight (time and date are separate fields). 4) Timings using local time should use UTC to avoid daylight savings problems. 5) Use system monotonic clock in util/time.h. Some timings may still be affected by #3 & 4 above but fixing those isn't the purpose of this change. Change-Id: I26056c876c4361e898acc3656aa98abf6f153a6b Reviewed-on: http://gerrit.sjc.cloudera.com:8080/5779 Reviewed-by: Casey Ching <casey@cloudera.com> Tested-by: jenkins
142 lines
3.7 KiB
Plaintext
142 lines
3.7 KiB
Plaintext
# These computations take a while so we do not want to add too many test cases
|
|
# They also require a non-trivial amount of data to get reasonable results.
|
|
====
|
|
---- QUERY
|
|
select count(distinct id), distinctpc(id), distinctpcsa(id) from alltypesagg
|
|
---- TYPES
|
|
bigint, bigint, bigint
|
|
---- RESULTS
|
|
10000,10590,17429
|
|
====
|
|
---- QUERY
|
|
# Test the distinctpcsa aggregate function on all col types with group by
|
|
select
|
|
tinyint_col,
|
|
distinctpcsa(id),
|
|
distinctpcsa(bool_col),
|
|
distinctpcsa(smallint_col),
|
|
distinctpcsa(int_col),
|
|
distinctpcsa(bigint_col),
|
|
distinctpcsa(float_col),
|
|
distinctpcsa(double_col),
|
|
distinctpcsa(string_col),
|
|
distinctpcsa(timestamp_col)
|
|
from alltypesagg
|
|
group by tinyint_col
|
|
---- TYPES
|
|
tinyint, bigint, bigint, bigint, bigint, bigint, bigint, bigint, bigint, bigint
|
|
---- RESULTS
|
|
1,1066,82,87,148,128,146,139,163,956
|
|
2,906,83,86,151,136,140,160,158,1054
|
|
3,1200,82,86,140,131,146,139,163,896
|
|
4,1043,83,87,128,126,140,139,161,926
|
|
5,1149,82,87,137,130,148,140,163,916
|
|
6,998,83,87,137,128,146,142,161,1187
|
|
7,1125,82,87,140,140,145,140,163,830
|
|
8,977,83,88,139,124,139,142,163,804
|
|
9,867,82,88,130,131,139,136,161,840
|
|
NULL,1101,83,87,142,131,133,142,158,813
|
|
====
|
|
---- QUERY
|
|
# Test the distinctpcsa aggregate function on all col types without group by
|
|
select
|
|
distinctpcsa(id),
|
|
distinctpcsa(bool_col),
|
|
distinctpcsa(tinyint_col),
|
|
distinctpcsa(smallint_col),
|
|
distinctpcsa(int_col),
|
|
distinctpcsa(bigint_col),
|
|
distinctpcsa(float_col),
|
|
distinctpcsa(double_col),
|
|
distinctpcsa(string_col),
|
|
distinctpcsa(timestamp_col)
|
|
from alltypesagg
|
|
---- TYPES
|
|
bigint, bigint, bigint, bigint, bigint, bigint, bigint, bigint, bigint, bigint
|
|
---- RESULTS
|
|
17429,83,87,109,544,1213,867,1043,252,10476
|
|
====
|
|
---- QUERY
|
|
# Test the distinctpc aggregate function on all col types with group by
|
|
select
|
|
tinyint_col,
|
|
distinctpc(id),
|
|
distinctpc(bool_col),
|
|
distinctpc(smallint_col),
|
|
distinctpc(int_col),
|
|
distinctpc(bigint_col),
|
|
distinctpc(float_col),
|
|
distinctpc(double_col),
|
|
distinctpc(string_col),
|
|
distinctpc(timestamp_col)
|
|
from alltypesagg
|
|
group by tinyint_col
|
|
---- TYPES
|
|
tinyint, bigint, bigint, bigint, bigint, bigint, bigint, bigint, bigint, bigint
|
|
---- RESULTS
|
|
1,896,1,11,20,89,112,88,151,977
|
|
2,936,1,11,20,100,153,94,180,1043
|
|
3,936,1,11,20,109,118,90,182,896
|
|
4,977,1,14,20,81,84,83,190,946
|
|
5,977,1,14,20,96,97,100,151,840
|
|
6,998,1,13,20,97,128,101,178,1077
|
|
7,998,1,13,20,86,117,105,158,858
|
|
8,896,1,13,20,88,96,101,155,745
|
|
9,896,1,13,20,109,142,109,182,926
|
|
NULL,896,1,11,20,91,97,85,176,753
|
|
====
|
|
---- QUERY
|
|
# Test the distinctpc aggregate function on all col types without group by
|
|
select
|
|
distinctpc(id),
|
|
distinctpc(bool_col),
|
|
distinctpc(tinyint_col),
|
|
distinctpc(smallint_col),
|
|
distinctpc(int_col),
|
|
distinctpc(bigint_col),
|
|
distinctpc(float_col),
|
|
distinctpc(double_col),
|
|
distinctpc(string_col),
|
|
distinctpc(timestamp_col)
|
|
from alltypesagg
|
|
---- TYPES
|
|
bigint, bigint, bigint, bigint, bigint, bigint, bigint, bigint, bigint, bigint
|
|
---- RESULTS
|
|
10590,3,7,63,20,1295,936,1020,330,9711
|
|
====
|
|
---- QUERY
|
|
# Test the hll aggregate function on all col types without group by
|
|
select
|
|
ndv(id),
|
|
ndv(bool_col),
|
|
ndv(tinyint_col),
|
|
ndv(smallint_col),
|
|
ndv(int_col),
|
|
ndv(bigint_col),
|
|
ndv(float_col),
|
|
ndv(double_col),
|
|
ndv(string_col),
|
|
ndv(timestamp_col)
|
|
from alltypesagg
|
|
---- TYPES
|
|
bigint, bigint, bigint, bigint, bigint, bigint, bigint, bigint, bigint, bigint
|
|
---- RESULTS
|
|
10549,2,9,104,1881,1342,944,991,1178,9880
|
|
====
|
|
---- QUERY
|
|
# Test the distinctpc aggregate function on empty table
|
|
select distinctpc(field) from EmptyTable
|
|
---- TYPES
|
|
bigint
|
|
---- RESULTS
|
|
0
|
|
====
|
|
---- QUERY
|
|
# Test the hll aggregate function on empty table
|
|
select ndv(field) from EmptyTable
|
|
---- TYPES
|
|
bigint
|
|
---- RESULTS
|
|
0
|
|
====
|