mirror of
https://github.com/apache/impala.git
synced 2026-01-27 06:10:53 -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>
171 lines
5.1 KiB
Plaintext
171 lines
5.1 KiB
Plaintext
====
|
|
---- QUERY
|
|
# test computing stats on an HBase table
|
|
create table alltypessmall_hbase like functional_hbase.alltypessmall
|
|
====
|
|
---- QUERY
|
|
compute stats alltypessmall_hbase
|
|
---- RESULTS
|
|
'Updated 1 partition(s) and 13 column(s).'
|
|
---- TYPES
|
|
STRING
|
|
====
|
|
---- QUERY
|
|
show table stats alltypessmall_hbase
|
|
---- LABELS
|
|
REGION LOCATION, START ROWKEY, EST. #ROWS, SIZE
|
|
---- RESULTS: VERIFY_IS_EQUAL
|
|
regex:.+,'',regex:.+,regex:.+B
|
|
regex:.+,'1',regex:.+,regex:.+B
|
|
regex:.+,'3',regex:.+,regex:.+B
|
|
regex:.+,'5',regex:.+,regex:.+B
|
|
regex:.+,'7',regex:.+,regex:.+B
|
|
regex:.+,'9',regex:.+,regex:.+B
|
|
'Total','',regex:.+,regex:.+B
|
|
---- TYPES
|
|
STRING, STRING, BIGINT, STRING
|
|
====
|
|
---- QUERY
|
|
show column stats alltypessmall_hbase
|
|
---- LABELS
|
|
COLUMN, TYPE, #DISTINCT VALUES, #NULLS, MAX SIZE, AVG SIZE, #TRUES, #FALSES
|
|
---- RESULTS
|
|
'id','INT',99,0,4,4,-1,-1
|
|
'bigint_col','BIGINT',10,0,8,8,-1,-1
|
|
'bool_col','BOOLEAN',2,0,1,1,50,50
|
|
'date_string_col','STRING',12,0,8,8,-1,-1
|
|
'double_col','DOUBLE',10,0,8,8,-1,-1
|
|
'float_col','FLOAT',10,0,4,4,-1,-1
|
|
'int_col','INT',10,0,4,4,-1,-1
|
|
'month','INT',4,0,4,4,-1,-1
|
|
'smallint_col','SMALLINT',10,0,2,2,-1,-1
|
|
'string_col','STRING',10,0,1,1,-1,-1
|
|
'timestamp_col','TIMESTAMP',100,0,16,16,-1,-1
|
|
'tinyint_col','TINYINT',10,0,1,1,-1,-1
|
|
'year','INT',1,0,4,4,-1,-1
|
|
---- TYPES
|
|
STRING, STRING, BIGINT, BIGINT, BIGINT, DOUBLE, BIGINT, BIGINT
|
|
====
|
|
---- QUERY
|
|
# test computing stats on an binary HBase table
|
|
create table alltypessmall_hbase_bin like functional_hbase.alltypessmallbinary
|
|
====
|
|
---- QUERY
|
|
compute stats alltypessmall_hbase_bin
|
|
---- RESULTS
|
|
'Updated 1 partition(s) and 13 column(s).'
|
|
---- TYPES
|
|
STRING
|
|
====
|
|
---- QUERY: VERIFY_IS_EQUAL
|
|
show table stats alltypessmall_hbase_bin
|
|
---- LABELS
|
|
REGION LOCATION, START ROWKEY, EST. #ROWS, SIZE
|
|
---- RESULTS
|
|
regex:.+,'',regex:.+,regex:.+
|
|
---- TYPES
|
|
STRING, STRING, BIGINT, STRING
|
|
====
|
|
---- QUERY
|
|
show column stats alltypessmall_hbase_bin
|
|
---- LABELS
|
|
COLUMN, TYPE, #DISTINCT VALUES, #NULLS, MAX SIZE, AVG SIZE, #TRUES, #FALSES
|
|
---- RESULTS
|
|
'id','INT',99,0,4,4,-1,-1
|
|
'bigint_col','BIGINT',10,0,8,8,-1,-1
|
|
'bool_col','BOOLEAN',2,0,1,1,50,50
|
|
'date_string_col','STRING',12,0,8,8,-1,-1
|
|
'double_col','DOUBLE',10,0,8,8,-1,-1
|
|
'float_col','FLOAT',10,0,4,4,-1,-1
|
|
'int_col','INT',10,0,4,4,-1,-1
|
|
'month','INT',4,0,4,4,-1,-1
|
|
'smallint_col','SMALLINT',10,0,2,2,-1,-1
|
|
'string_col','STRING',10,0,1,1,-1,-1
|
|
'timestamp_col','TIMESTAMP',100,0,16,16,-1,-1
|
|
'tinyint_col','TINYINT',10,0,1,1,-1,-1
|
|
'year','INT',1,0,4,4,-1,-1
|
|
---- TYPES
|
|
STRING, STRING, BIGINT, BIGINT, BIGINT, DOUBLE, BIGINT, BIGINT
|
|
====
|
|
---- QUERY
|
|
# IMP-1227: Test computing stats on an HBase table that has a
|
|
# complex-typed column that Impala does not yet support.
|
|
create table allcomplextypes_hbase like functional_hbase.allcomplextypes
|
|
====
|
|
---- QUERY
|
|
compute stats allcomplextypes_hbase
|
|
---- RESULTS
|
|
'Updated 1 partition(s) and 3 column(s).'
|
|
---- TYPES
|
|
STRING
|
|
====
|
|
---- QUERY: VERIFY_IS_EQUAL
|
|
show table stats allcomplextypes_hbase
|
|
---- LABELS
|
|
REGION LOCATION, START ROWKEY, EST. #ROWS, SIZE
|
|
---- RESULTS
|
|
regex:.+,'',regex:.+,regex:.+
|
|
---- TYPES
|
|
STRING, STRING, BIGINT, STRING
|
|
====
|
|
---- QUERY
|
|
show column stats allcomplextypes_hbase
|
|
---- LABELS
|
|
COLUMN, TYPE, #DISTINCT VALUES, #NULLS, MAX SIZE, AVG SIZE, #TRUES, #FALSES
|
|
---- RESULTS
|
|
'id','INT',0,0,4,4,-1,-1
|
|
'array_array_col','ARRAY<ARRAY<INT>>',-1,-1,-1,-1,-1,-1
|
|
'array_map_col','MAP<STRING,ARRAY<INT>>',-1,-1,-1,-1,-1,-1
|
|
'complex_nested_struct_col','STRUCT<f1:INT,f2:ARRAY<STRUCT<f11:BIGINT,f12:MAP<STRING,STRUCT<f21:BIGINT>>>>>',-1,-1,-1,-1,-1,-1
|
|
'complex_struct_col','STRUCT<f1:INT,f2:ARRAY<INT>,f3:MAP<STRING,INT>>',-1,-1,-1,-1,-1,-1
|
|
'int_array_col','ARRAY<INT>',-1,-1,-1,-1,-1,-1
|
|
'int_map_col','MAP<STRING,INT>',-1,-1,-1,-1,-1,-1
|
|
'int_struct_col','STRUCT<f1:INT,f2:INT>',-1,-1,-1,-1,-1,-1
|
|
'map_array_col','ARRAY<MAP<STRING,INT>>',-1,-1,-1,-1,-1,-1
|
|
'map_map_col','MAP<STRING,MAP<STRING,INT>>',-1,-1,-1,-1,-1,-1
|
|
'month','INT',0,0,4,4,-1,-1
|
|
'nested_struct_col','STRUCT<f1:INT,f2:STRUCT<f11:BIGINT,f12:STRUCT<f21:BIGINT>>>',-1,-1,-1,-1,-1,-1
|
|
'struct_array_col','ARRAY<STRUCT<f1:BIGINT,f2:STRING>>',-1,-1,-1,-1,-1,-1
|
|
'struct_map_col','MAP<STRING,STRUCT<f1:BIGINT,f2:STRING>>',-1,-1,-1,-1,-1,-1
|
|
'year','INT',0,0,4,4,-1,-1
|
|
---- TYPES
|
|
STRING, STRING, BIGINT, BIGINT, BIGINT, DOUBLE, BIGINT, BIGINT
|
|
====
|
|
---- QUERY
|
|
# test computing stats on an HBase table
|
|
create table date_tbl_hbase like functional_hbase.date_tbl
|
|
====
|
|
---- QUERY
|
|
compute stats date_tbl_hbase
|
|
---- RESULTS
|
|
'Updated 1 partition(s) and 3 column(s).'
|
|
---- TYPES
|
|
STRING
|
|
====
|
|
---- QUERY
|
|
show table stats date_tbl_hbase
|
|
---- LABELS
|
|
REGION LOCATION, START ROWKEY, EST. #ROWS, SIZE
|
|
---- RESULTS: VERIFY_IS_EQUAL
|
|
regex:.+,'',regex:.+,regex:.+B
|
|
regex:.+,'1',regex:.+,regex:.+B
|
|
regex:.+,'3',regex:.+,regex:.+B
|
|
regex:.+,'5',regex:.+,regex:.+B
|
|
regex:.+,'7',regex:.+,regex:.+B
|
|
regex:.+,'9',regex:.+,regex:.+B
|
|
'Total','',regex:.+,regex:.+B
|
|
---- TYPES
|
|
STRING, STRING, BIGINT, STRING
|
|
====
|
|
---- QUERY
|
|
show column stats date_tbl_hbase
|
|
---- LABELS
|
|
COLUMN, TYPE, #DISTINCT VALUES, #NULLS, MAX SIZE, AVG SIZE, #TRUES, #FALSES
|
|
---- RESULTS
|
|
'id_col','INT',22,0,4,4,-1,-1
|
|
'date_col','DATE',16,2,4,4,-1,-1
|
|
'date_part','DATE',4,0,4,4,-1,-1
|
|
---- TYPES
|
|
STRING, STRING, BIGINT, BIGINT, BIGINT, DOUBLE, BIGINT, BIGINT
|
|
====
|