mirror of
https://github.com/apache/impala.git
synced 2026-01-27 15:03:20 -05:00
a93f2c2675
This change compute the real number of true and false statistics information for boolean columns. Before this, impala used to set numTrues and numFalses to hardcoded -1 to indicate that its statistics is missing. Test Done: Append the numTrue and numFalse test for all the statistics-related test cases including the non-incremental, incremental and other test cases. Change-Id: I991bee8e7fdc644d908289f5fe2ee8032cc2c431 Reviewed-on: http://gerrit.cloudera.org:8080/14666 Reviewed-by: Impala Public Jenkins <impala-public-jenkins@cloudera.com> Tested-by: Impala Public Jenkins <impala-public-jenkins@cloudera.com>
84 lines
2.7 KiB
Plaintext
84 lines
2.7 KiB
Plaintext
====
|
|
---- QUERY
|
|
# test compute stats on a partitioned date text table
|
|
create table date_tbl_copy like functional.date_tbl;
|
|
insert into date_tbl_copy partition(date_part)
|
|
select * from functional.date_tbl;
|
|
alter table date_tbl_copy add column d DATE;
|
|
====
|
|
---- QUERY
|
|
compute stats date_tbl_copy;
|
|
---- RESULTS
|
|
'Updated 4 partition(s) and 3 column(s).'
|
|
====
|
|
---- QUERY
|
|
show table stats date_tbl_copy;
|
|
---- LABELS
|
|
date_part, #Rows, #Files, Size, Bytes Cached, Cache Replication, Format, Incremental Stats, Location
|
|
---- RESULTS
|
|
'0001-01-01',7,1,'83B','NOT CACHED','NOT CACHED','TEXT','false',regex:.*
|
|
'1399-06-27',3,1,'34B','NOT CACHED','NOT CACHED','TEXT','false',regex:.*
|
|
'2017-11-27',10,1,'140B','NOT CACHED','NOT CACHED','TEXT','false',regex:.*
|
|
'9999-12-31',2,1,'28B','NOT CACHED','NOT CACHED','TEXT','false',regex:.*
|
|
'Total',22,4,'285B','0B','','','',''
|
|
---- TYPES
|
|
STRING, BIGINT, BIGINT, STRING, STRING, STRING, STRING, STRING, STRING
|
|
====
|
|
---- QUERY
|
|
show column stats date_tbl_copy;
|
|
---- LABELS
|
|
COLUMN, TYPE, #DISTINCT VALUES, #NULLS, MAX SIZE, AVG SIZE, #TRUES, #FALSES
|
|
---- RESULTS
|
|
'd','DATE',0,22,4,4,-1,-1
|
|
'date_part','DATE',4,0,4,4,-1,-1
|
|
'date_col','DATE',16,2,4,4,-1,-1
|
|
'id_col','INT',22,0,4,4,-1,-1
|
|
---- TYPES
|
|
STRING, STRING, BIGINT, BIGINT, BIGINT, DOUBLE, BIGINT, BIGINT
|
|
====
|
|
---- QUERY
|
|
# Removing a column shouldn't cause the stats to be dropped.
|
|
alter table date_tbl_copy drop column date_col;
|
|
---- RESULTS
|
|
'Column has been dropped.'
|
|
====
|
|
---- QUERY
|
|
show column stats date_tbl_copy;
|
|
---- LABELS
|
|
COLUMN, TYPE, #DISTINCT VALUES, #NULLS, MAX SIZE, AVG SIZE, #TRUES, #FALSES
|
|
---- RESULTS
|
|
'd','DATE',0,22,4,4,-1,-1
|
|
'id_col','INT',22,0,4,4,-1,-1
|
|
'date_part','DATE',4,0,4,4,-1,-1
|
|
---- TYPES
|
|
STRING, STRING, BIGINT, BIGINT, BIGINT, DOUBLE, BIGINT, BIGINT
|
|
====
|
|
---- QUERY
|
|
# drop stats from this table
|
|
drop stats date_tbl_copy;
|
|
====
|
|
---- QUERY
|
|
show table stats date_tbl_copy;
|
|
---- LABELS
|
|
date_part, #Rows, #Files, Size, Bytes Cached, Cache Replication, Format, Incremental Stats, Location
|
|
---- RESULTS
|
|
'0001-01-01',-1,1,'83B','NOT CACHED','NOT CACHED','TEXT','false',regex:.*
|
|
'1399-06-27',-1,1,'34B','NOT CACHED','NOT CACHED','TEXT','false',regex:.*
|
|
'2017-11-27',-1,1,'140B','NOT CACHED','NOT CACHED','TEXT','false',regex:.*
|
|
'9999-12-31',-1,1,'28B','NOT CACHED','NOT CACHED','TEXT','false',regex:.*
|
|
'Total',-1,4,'285B','0B','','','',''
|
|
---- TYPES
|
|
STRING, BIGINT, BIGINT, STRING, STRING, STRING, STRING, STRING, STRING
|
|
====
|
|
---- QUERY
|
|
show column stats date_tbl_copy;
|
|
---- LABELS
|
|
COLUMN, TYPE, #DISTINCT VALUES, #NULLS, MAX SIZE, AVG SIZE, #TRUES, #FALSES
|
|
---- RESULTS
|
|
'd','DATE',-1,-1,4,4,-1,-1
|
|
'id_col','INT',-1,-1,4,4,-1,-1
|
|
'date_part','DATE',4,0,4,4,-1,-1
|
|
---- TYPES
|
|
STRING, STRING, BIGINT, BIGINT, BIGINT, DOUBLE, BIGINT, BIGINT
|
|
====
|