You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by px...@apache.org on 2017/07/15 08:06:56 UTC
[17/24] hive git commit: HIVE-16996: Add HLL as an alternative to FM
sketch to compute stats (Pengcheng Xiong, reviewed by Ashutosh Chauhan,
Prasanth Jayachandran)
http://git-wip-us.apache.org/repos/asf/hive/blob/b883d313/ql/src/test/results/clientpositive/columnstats_tbllvl.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/columnstats_tbllvl.q.out b/ql/src/test/results/clientpositive/columnstats_tbllvl.q.out
index 462d4c1..91c8f15 100644
--- a/ql/src/test/results/clientpositive/columnstats_tbllvl.q.out
+++ b/ql/src/test/results/clientpositive/columnstats_tbllvl.q.out
@@ -60,23 +60,23 @@ STAGE PLANS:
outputColumnNames: sourceip, adrevenue, avgtimeonsite
Statistics: Num rows: 65 Data size: 7060 Basic stats: COMPLETE Column stats: NONE
Group By Operator
- aggregations: compute_stats(sourceip, 16), compute_stats(avgtimeonsite, 16), compute_stats(adrevenue, 16)
+ aggregations: compute_stats(sourceip, 'hll'), compute_stats(avgtimeonsite, 'hll'), compute_stats(adrevenue, 'hll')
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 1444 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1408 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 1444 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col2 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:string,numbitvectors:int>)
+ Statistics: Num rows: 1 Data size: 1408 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string>), _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:string>), _col2 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:string>)
Reduce Operator Tree:
Group By Operator
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 1452 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1440 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 1452 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1440 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -112,16 +112,16 @@ STAGE PLANS:
outputColumnNames: sourceip, adrevenue, avgtimeonsite
Statistics: Num rows: 65 Data size: 7060 Basic stats: COMPLETE Column stats: NONE
Group By Operator
- aggregations: compute_stats(sourceip, 16), compute_stats(avgtimeonsite, 16), compute_stats(adrevenue, 16)
+ aggregations: compute_stats(sourceip, 'hll'), compute_stats(avgtimeonsite, 'hll'), compute_stats(adrevenue, 'hll')
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 1444 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1408 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
null sort order:
sort order:
- Statistics: Num rows: 1 Data size: 1444 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1408 Basic stats: COMPLETE Column stats: NONE
tag: -1
- value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col2 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:string,numbitvectors:int>)
+ value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string>), _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:string>), _col2 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:string>)
auto parallelism: false
Path -> Alias:
#### A masked pattern was here ####
@@ -180,13 +180,13 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 1452 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1440 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
GlobalTableId: 0
#### A masked pattern was here ####
NumFilesPerFileSink: 1
- Statistics: Num rows: 1 Data size: 1452 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1440 Basic stats: COMPLETE Column stats: NONE
#### A masked pattern was here ####
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
@@ -242,23 +242,23 @@ STAGE PLANS:
outputColumnNames: sourceip, desturl, visitdate, adrevenue, useragent, ccode, lcode, skeyword, avgtimeonsite
Statistics: Num rows: 9 Data size: 7060 Basic stats: COMPLETE Column stats: NONE
Group By Operator
- aggregations: compute_stats(sourceip, 16), compute_stats(desturl, 16), compute_stats(visitdate, 16), compute_stats(adrevenue, 16), compute_stats(useragent, 16), compute_stats(ccode, 16), compute_stats(lcode, 16), compute_stats(skeyword, 16), compute_stats(avgtimeonsite, 16)
+ aggregations: compute_stats(sourceip, 'hll'), compute_stats(desturl, 'hll'), compute_stats(visitdate, 'hll'), compute_stats(adrevenue, 'hll'), compute_stats(useragent, 'hll'), compute_stats(ccode, 'hll'), compute_stats(lcode, 'hll'), compute_stats(skeyword, 'hll'), compute_stats(avgtimeonsite, 'hll')
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
- Statistics: Num rows: 1 Data size: 4396 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 4288 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 4396 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col3 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:string,numbitvectors:int>), _col4 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col5 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col6 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>)
, _col7 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col8 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>)
+ Statistics: Num rows: 1 Data size: 4288 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string>), _col3 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:string>), _col4 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string>), _col5 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string>), _col6 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string>), _col7 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string>), _
col8 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:string>)
Reduce Operator Tree:
Group By Operator
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3), compute_stats(VALUE._col4), compute_stats(VALUE._col5), compute_stats(VALUE._col6), compute_stats(VALUE._col7), compute_stats(VALUE._col8)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
- Statistics: Num rows: 1 Data size: 4404 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 4320 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 4404 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 4320 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -287,7 +287,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@uservisits_web_text_none
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-destURL string 0 56 48.945454545454545 96 from deserializer
+destURL string 0 55 48.945454545454545 96 from deserializer
COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"adrevenue\":\"true\",\"avgtimeonsite\":\"true\",\"ccode\":\"true\",\"desturl\":\"true\",\"lcode\":\"true\",\"skeyword\":\"true\",\"sourceip\":\"true\",\"useragent\":\"true\",\"visitdate\":\"true\"}}
PREHOOK: query: describe formatted UserVisits_web_text_none adRevenue
PREHOOK: type: DESCTABLE
@@ -297,7 +297,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@uservisits_web_text_none
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-adRevenue float 13.099044799804688 492.98870849609375 0 58 from deserializer
+adRevenue float 13.099044799804688 492.98870849609375 0 55 from deserializer
COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"adrevenue\":\"true\",\"avgtimeonsite\":\"true\",\"ccode\":\"true\",\"desturl\":\"true\",\"lcode\":\"true\",\"skeyword\":\"true\",\"sourceip\":\"true\",\"useragent\":\"true\",\"visitdate\":\"true\"}}
PREHOOK: query: describe formatted UserVisits_web_text_none avgTimeOnSite
PREHOOK: type: DESCTABLE
@@ -307,7 +307,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@uservisits_web_text_none
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-avgTimeOnSite int 1 9 0 11 from deserializer
+avgTimeOnSite int 1 9 0 9 from deserializer
COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"adrevenue\":\"true\",\"avgtimeonsite\":\"true\",\"ccode\":\"true\",\"desturl\":\"true\",\"lcode\":\"true\",\"skeyword\":\"true\",\"sourceip\":\"true\",\"useragent\":\"true\",\"visitdate\":\"true\"}}
PREHOOK: query: CREATE TABLE empty_tab(
a int,
@@ -351,23 +351,23 @@ STAGE PLANS:
outputColumnNames: a, b, c, d, e
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
Group By Operator
- aggregations: compute_stats(a, 16), compute_stats(b, 16), compute_stats(c, 16), compute_stats(d, 16), compute_stats(e, 16)
+ aggregations: compute_stats(a, 'hll'), compute_stats(b, 'hll'), compute_stats(c, 'hll'), compute_stats(d, 'hll'), compute_stats(e, 'hll')
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 1 Data size: 2004 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1968 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 2004 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col1 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:string,numbitvectors:int>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col3 (type: struct<columntype:string,counttrues:bigint,countfalses:bigint,countnulls:bigint>), _col4 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint>)
+ Statistics: Num rows: 1 Data size: 1968 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:string>), _col1 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:string>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string>), _col3 (type: struct<columntype:string,counttrues:bigint,countfalses:bigint,countnulls:bigint>), _col4 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint>)
Reduce Operator Tree:
Group By Operator
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3), compute_stats(VALUE._col4)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 2000 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 2000 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -416,7 +416,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@uservisits_web_text_none
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-destURL string 0 56 48.945454545454545 96 from deserializer
+destURL string 0 55 48.945454545454545 96 from deserializer
COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"adrevenue\":\"true\",\"avgtimeonsite\":\"true\",\"ccode\":\"true\",\"desturl\":\"true\",\"lcode\":\"true\",\"skeyword\":\"true\",\"sourceip\":\"true\",\"useragent\":\"true\",\"visitdate\":\"true\"}}
PREHOOK: query: CREATE TABLE UserVisits_in_dummy_db (
sourceIP string,
@@ -482,23 +482,23 @@ STAGE PLANS:
outputColumnNames: sourceip, adrevenue, avgtimeonsite
Statistics: Num rows: 65 Data size: 7060 Basic stats: COMPLETE Column stats: NONE
Group By Operator
- aggregations: compute_stats(sourceip, 16), compute_stats(avgtimeonsite, 16), compute_stats(adrevenue, 16)
+ aggregations: compute_stats(sourceip, 'hll'), compute_stats(avgtimeonsite, 'hll'), compute_stats(adrevenue, 'hll')
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 1444 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1408 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 1444 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col2 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:string,numbitvectors:int>)
+ Statistics: Num rows: 1 Data size: 1408 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string>), _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:string>), _col2 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:string>)
Reduce Operator Tree:
Group By Operator
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 1452 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1440 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 1452 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1440 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -534,16 +534,16 @@ STAGE PLANS:
outputColumnNames: sourceip, adrevenue, avgtimeonsite
Statistics: Num rows: 65 Data size: 7060 Basic stats: COMPLETE Column stats: NONE
Group By Operator
- aggregations: compute_stats(sourceip, 16), compute_stats(avgtimeonsite, 16), compute_stats(adrevenue, 16)
+ aggregations: compute_stats(sourceip, 'hll'), compute_stats(avgtimeonsite, 'hll'), compute_stats(adrevenue, 'hll')
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 1444 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1408 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
null sort order:
sort order:
- Statistics: Num rows: 1 Data size: 1444 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1408 Basic stats: COMPLETE Column stats: NONE
tag: -1
- value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col2 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:string,numbitvectors:int>)
+ value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string>), _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:string>), _col2 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:string>)
auto parallelism: false
Path -> Alias:
#### A masked pattern was here ####
@@ -602,13 +602,13 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 1452 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1440 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
GlobalTableId: 0
#### A masked pattern was here ####
NumFilesPerFileSink: 1
- Statistics: Num rows: 1 Data size: 1452 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1440 Basic stats: COMPLETE Column stats: NONE
#### A masked pattern was here ####
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
@@ -664,23 +664,23 @@ STAGE PLANS:
outputColumnNames: sourceip, desturl, visitdate, adrevenue, useragent, ccode, lcode, skeyword, avgtimeonsite
Statistics: Num rows: 9 Data size: 7060 Basic stats: COMPLETE Column stats: NONE
Group By Operator
- aggregations: compute_stats(sourceip, 16), compute_stats(desturl, 16), compute_stats(visitdate, 16), compute_stats(adrevenue, 16), compute_stats(useragent, 16), compute_stats(ccode, 16), compute_stats(lcode, 16), compute_stats(skeyword, 16), compute_stats(avgtimeonsite, 16)
+ aggregations: compute_stats(sourceip, 'hll'), compute_stats(desturl, 'hll'), compute_stats(visitdate, 'hll'), compute_stats(adrevenue, 'hll'), compute_stats(useragent, 'hll'), compute_stats(ccode, 'hll'), compute_stats(lcode, 'hll'), compute_stats(skeyword, 'hll'), compute_stats(avgtimeonsite, 'hll')
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
- Statistics: Num rows: 1 Data size: 4396 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 4288 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 4396 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col3 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:string,numbitvectors:int>), _col4 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col5 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col6 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>)
, _col7 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col8 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>)
+ Statistics: Num rows: 1 Data size: 4288 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string>), _col3 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:string>), _col4 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string>), _col5 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string>), _col6 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string>), _col7 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string>), _
col8 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:string>)
Reduce Operator Tree:
Group By Operator
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3), compute_stats(VALUE._col4), compute_stats(VALUE._col5), compute_stats(VALUE._col6), compute_stats(VALUE._col7), compute_stats(VALUE._col8)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
- Statistics: Num rows: 1 Data size: 4404 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 4320 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 4404 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 4320 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -709,7 +709,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: dummydb@uservisits_in_dummy_db
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-destURL string 0 56 48.945454545454545 96 from deserializer
+destURL string 0 55 48.945454545454545 96 from deserializer
COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"adrevenue\":\"true\",\"avgtimeonsite\":\"true\",\"ccode\":\"true\",\"desturl\":\"true\",\"lcode\":\"true\",\"skeyword\":\"true\",\"sourceip\":\"true\",\"useragent\":\"true\",\"visitdate\":\"true\"}}
PREHOOK: query: describe formatted dummydb.UserVisits_in_dummy_db adRevenue
PREHOOK: type: DESCTABLE
@@ -719,7 +719,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: dummydb@uservisits_in_dummy_db
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-adRevenue float 13.099044799804688 492.98870849609375 0 58 from deserializer
+adRevenue float 13.099044799804688 492.98870849609375 0 55 from deserializer
COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"adrevenue\":\"true\",\"avgtimeonsite\":\"true\",\"ccode\":\"true\",\"desturl\":\"true\",\"lcode\":\"true\",\"skeyword\":\"true\",\"sourceip\":\"true\",\"useragent\":\"true\",\"visitdate\":\"true\"}}
PREHOOK: query: describe formatted dummydb.UserVisits_in_dummy_db avgTimeOnSite
PREHOOK: type: DESCTABLE
@@ -729,7 +729,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: dummydb@uservisits_in_dummy_db
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-avgTimeOnSite int 1 9 0 11 from deserializer
+avgTimeOnSite int 1 9 0 9 from deserializer
COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"adrevenue\":\"true\",\"avgtimeonsite\":\"true\",\"ccode\":\"true\",\"desturl\":\"true\",\"lcode\":\"true\",\"skeyword\":\"true\",\"sourceip\":\"true\",\"useragent\":\"true\",\"visitdate\":\"true\"}}
PREHOOK: query: drop table dummydb.UserVisits_in_dummy_db
PREHOOK: type: DROPTABLE
http://git-wip-us.apache.org/repos/asf/hive/blob/b883d313/ql/src/test/results/clientpositive/compute_stats_date.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/compute_stats_date.q.out b/ql/src/test/results/clientpositive/compute_stats_date.q.out
index c247237..5cd2180 100644
--- a/ql/src/test/results/clientpositive/compute_stats_date.q.out
+++ b/ql/src/test/results/clientpositive/compute_stats_date.q.out
@@ -35,15 +35,15 @@ POSTHOOK: type: QUERY
POSTHOOK: Input: default@tab_date
#### A masked pattern was here ####
20
-PREHOOK: query: select compute_stats(fl_date, 16) from tab_date
+PREHOOK: query: select compute_stats(fl_date, 'hll') from tab_date
PREHOOK: type: QUERY
PREHOOK: Input: default@tab_date
#### A masked pattern was here ####
-POSTHOOK: query: select compute_stats(fl_date, 16) from tab_date
+POSTHOOK: query: select compute_stats(fl_date, 'hll') from tab_date
POSTHOOK: type: QUERY
POSTHOOK: Input: default@tab_date
#### A masked pattern was here ####
-{"columntype":"Date","min":"2000-11-20","max":"2010-10-29","countnulls":0,"numdistinctvalues":18,"ndvbitvector":"{0, 1, 2, 3, 4, 5}{0, 1, 2, 3}{0}{0, 1, 2, 6}{0, 1, 2, 3}{0, 1, 2, 3}{0, 1, 2}{0, 1, 2, 3}{0, 1, 2, 3}{0, 2}{0, 1, 2, 3, 4}{0, 1, 2, 4, 5}{0, 1, 2, 3}{0, 1, 2, 3, 5}{0, 1, 2, 3, 4, 5}{0, 1, 2, 3, 4}"}
+{"columntype":"Date","min":"2000-11-20","max":"2010-10-29","countnulls":0,"numdistinctvalues":19,"ndvbitvector":"SExM4BMTw6qAFv+ogCGC/7ZdgMDTH73K3+4Bgq+jE766tgWAh/xZgIqTVIDhgVDA655SwfXHA4Dy\r\n/Ve//Z0LwMSIToCZ6QOAhZ8Gg8jOEb38rBw=\r\n"}
PREHOOK: query: explain
analyze table tab_date compute statistics for columns fl_date
PREHOOK: type: QUERY
@@ -66,14 +66,14 @@ STAGE PLANS:
outputColumnNames: fl_date
Statistics: Num rows: 13 Data size: 778 Basic stats: COMPLETE Column stats: NONE
Group By Operator
- aggregations: compute_stats(fl_date, 16)
+ aggregations: compute_stats(fl_date, 'hll')
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 572 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 560 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 572 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: struct<columntype:string,min:date,max:date,countnulls:bigint,bitvector:string,numbitvectors:int>)
+ Statistics: Num rows: 1 Data size: 560 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<columntype:string,min:date,max:date,countnulls:bigint,bitvector:string>)
Reduce Operator Tree:
Group By Operator
aggregations: compute_stats(VALUE._col0)
@@ -111,7 +111,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@tab_date
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-fl_date date 2000-11-20 2010-10-29 0 18 from deserializer
+fl_date date 2000-11-20 2010-10-29 0 19 from deserializer
COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"fl_date\":\"true\"}}
PREHOOK: query: alter table tab_date update statistics for column fl_date set ('numDVs'='19', 'highValue'='2015-01-01', 'lowValue'='0')
PREHOOK: type: ALTERTABLE_UPDATETABLESTATS
http://git-wip-us.apache.org/repos/asf/hive/blob/b883d313/ql/src/test/results/clientpositive/compute_stats_decimal.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/compute_stats_decimal.q.out b/ql/src/test/results/clientpositive/compute_stats_decimal.q.out
index e0584c5..fcfce78 100644
--- a/ql/src/test/results/clientpositive/compute_stats_decimal.q.out
+++ b/ql/src/test/results/clientpositive/compute_stats_decimal.q.out
@@ -23,11 +23,11 @@ POSTHOOK: type: QUERY
POSTHOOK: Input: default@tab_decimal
#### A masked pattern was here ####
19
-PREHOOK: query: select compute_stats(a, 18) from tab_decimal
+PREHOOK: query: select compute_stats(a, 'fm', 18) from tab_decimal
PREHOOK: type: QUERY
PREHOOK: Input: default@tab_decimal
#### A masked pattern was here ####
-POSTHOOK: query: select compute_stats(a, 18) from tab_decimal
+POSTHOOK: query: select compute_stats(a, 'fm', 18) from tab_decimal
POSTHOOK: type: QUERY
POSTHOOK: Input: default@tab_decimal
#### A masked pattern was here ####
http://git-wip-us.apache.org/repos/asf/hive/blob/b883d313/ql/src/test/results/clientpositive/compute_stats_double.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/compute_stats_double.q.out b/ql/src/test/results/clientpositive/compute_stats_double.q.out
index 5b92173..e6a087d 100644
--- a/ql/src/test/results/clientpositive/compute_stats_double.q.out
+++ b/ql/src/test/results/clientpositive/compute_stats_double.q.out
@@ -23,11 +23,11 @@ POSTHOOK: type: QUERY
POSTHOOK: Input: default@tab_double
#### A masked pattern was here ####
16
-PREHOOK: query: select compute_stats(a, 16) from tab_double
+PREHOOK: query: select compute_stats(a, 'fm', 16) from tab_double
PREHOOK: type: QUERY
PREHOOK: Input: default@tab_double
#### A masked pattern was here ####
-POSTHOOK: query: select compute_stats(a, 16) from tab_double
+POSTHOOK: query: select compute_stats(a, 'fm', 16) from tab_double
POSTHOOK: type: QUERY
POSTHOOK: Input: default@tab_double
#### A masked pattern was here ####
http://git-wip-us.apache.org/repos/asf/hive/blob/b883d313/ql/src/test/results/clientpositive/compute_stats_long.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/compute_stats_long.q.out b/ql/src/test/results/clientpositive/compute_stats_long.q.out
index 119d1731..fb985d8 100644
--- a/ql/src/test/results/clientpositive/compute_stats_long.q.out
+++ b/ql/src/test/results/clientpositive/compute_stats_long.q.out
@@ -23,11 +23,11 @@ POSTHOOK: type: QUERY
POSTHOOK: Input: default@tab_int
#### A masked pattern was here ####
12
-PREHOOK: query: select compute_stats(a, 16) from tab_int
+PREHOOK: query: select compute_stats(a, 'fm', 16) from tab_int
PREHOOK: type: QUERY
PREHOOK: Input: default@tab_int
#### A masked pattern was here ####
-POSTHOOK: query: select compute_stats(a, 16) from tab_int
+POSTHOOK: query: select compute_stats(a, 'fm', 16) from tab_int
POSTHOOK: type: QUERY
POSTHOOK: Input: default@tab_int
#### A masked pattern was here ####
http://git-wip-us.apache.org/repos/asf/hive/blob/b883d313/ql/src/test/results/clientpositive/compute_stats_string.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/compute_stats_string.q.out b/ql/src/test/results/clientpositive/compute_stats_string.q.out
index 8c40490..a5d66eb 100644
--- a/ql/src/test/results/clientpositive/compute_stats_string.q.out
+++ b/ql/src/test/results/clientpositive/compute_stats_string.q.out
@@ -23,11 +23,11 @@ POSTHOOK: type: QUERY
POSTHOOK: Input: default@tab_string
#### A masked pattern was here ####
10
-PREHOOK: query: select compute_stats(a, 16) from tab_string
+PREHOOK: query: select compute_stats(a, 'fm', 16) from tab_string
PREHOOK: type: QUERY
PREHOOK: Input: default@tab_string
#### A masked pattern was here ####
-POSTHOOK: query: select compute_stats(a, 16) from tab_string
+POSTHOOK: query: select compute_stats(a, 'fm', 16) from tab_string
POSTHOOK: type: QUERY
POSTHOOK: Input: default@tab_string
#### A masked pattern was here ####
http://git-wip-us.apache.org/repos/asf/hive/blob/b883d313/ql/src/test/results/clientpositive/confirm_initial_tbl_stats.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/confirm_initial_tbl_stats.q.out b/ql/src/test/results/clientpositive/confirm_initial_tbl_stats.q.out
index faa14ba..5593e42 100644
--- a/ql/src/test/results/clientpositive/confirm_initial_tbl_stats.q.out
+++ b/ql/src/test/results/clientpositive/confirm_initial_tbl_stats.q.out
@@ -16,7 +16,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@src
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-key string 0 205 2.812 3 from deserializer
+key string 0 309 2.812 3 from deserializer
COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
PREHOOK: query: describe extended src1
PREHOOK: type: DESCTABLE
@@ -36,7 +36,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@src1
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-value string 0 14 4.92 7 from deserializer
+value string 0 19 4.92 7 from deserializer
COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
PREHOOK: query: describe extended src_json
PREHOOK: type: DESCTABLE
@@ -75,7 +75,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@src_sequencefile
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-value string 0 214 6.812 7 from deserializer
+value string 0 309 6.812 7 from deserializer
COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
PREHOOK: query: describe extended srcbucket
PREHOOK: type: DESCTABLE
@@ -95,7 +95,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@srcbucket
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-value string 0 234 6.802 7 from deserializer
+value string 0 430 6.802 7 from deserializer
COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
PREHOOK: query: describe extended srcbucket2
PREHOOK: type: DESCTABLE
@@ -115,7 +115,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@srcbucket2
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-value string 0 214 6.812 7 from deserializer
+value string 0 309 6.812 7 from deserializer
COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
PREHOOK: query: describe extended srcpart
PREHOOK: type: DESCTABLE
@@ -143,7 +143,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@srcpart
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-key string 0 205 2.812 3 from deserializer
+key string 0 309 2.812 3 from deserializer
PREHOOK: query: describe extended alltypesorc
PREHOOK: type: DESCTABLE
PREHOOK: Input: default@alltypesorc
@@ -172,7 +172,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@alltypesorc
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-ctinyint tinyint -64 62 3115 94 from deserializer
+ctinyint tinyint -64 62 3115 127 from deserializer
COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"cbigint\":\"true\",\"cboolean1\":\"true\",\"cboolean2\":\"true\",\"cdouble\":\"true\",\"cfloat\":\"true\",\"cint\":\"true\",\"csmallint\":\"true\",\"cstring1\":\"true\",\"cstring2\":\"true\",\"ctimestamp1\":\"true\",\"ctimestamp2\":\"true\",\"ctinyint\":\"true\"}}
PREHOOK: query: describe formatted alltypesorc cfloat
PREHOOK: type: DESCTABLE
@@ -182,7 +182,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@alltypesorc
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-cfloat float -64.0 79.5530014038086 3115 117 from deserializer
+cfloat float -64.0 79.5530014038086 3115 131 from deserializer
COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"cbigint\":\"true\",\"cboolean1\":\"true\",\"cboolean2\":\"true\",\"cdouble\":\"true\",\"cfloat\":\"true\",\"cint\":\"true\",\"csmallint\":\"true\",\"cstring1\":\"true\",\"cstring2\":\"true\",\"ctimestamp1\":\"true\",\"ctimestamp2\":\"true\",\"ctinyint\":\"true\"}}
PREHOOK: query: describe formatted alltypesorc ctimestamp1
PREHOOK: type: DESCTABLE
@@ -192,7 +192,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@alltypesorc
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-ctimestamp1 timestamp -30 31 3115 31 from deserializer
+ctimestamp1 timestamp -30 31 3115 35 from deserializer
COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"cbigint\":\"true\",\"cboolean1\":\"true\",\"cboolean2\":\"true\",\"cdouble\":\"true\",\"cfloat\":\"true\",\"cint\":\"true\",\"csmallint\":\"true\",\"cstring1\":\"true\",\"cstring2\":\"true\",\"ctimestamp1\":\"true\",\"ctimestamp2\":\"true\",\"ctinyint\":\"true\"}}
PREHOOK: query: describe formatted alltypesorc cboolean2
PREHOOK: type: DESCTABLE
http://git-wip-us.apache.org/repos/asf/hive/blob/b883d313/ql/src/test/results/clientpositive/constant_prop_2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/constant_prop_2.q.out b/ql/src/test/results/clientpositive/constant_prop_2.q.out
index 24be518..9305041 100644
--- a/ql/src/test/results/clientpositive/constant_prop_2.q.out
+++ b/ql/src/test/results/clientpositive/constant_prop_2.q.out
@@ -43,7 +43,7 @@ STAGE PLANS:
outputColumnNames: key, value
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Group By Operator
- aggregations: compute_stats(key, 16), compute_stats(value, 16)
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
keys: '2008-04-08' (type: string), '11' (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3
@@ -53,7 +53,7 @@ STAGE PLANS:
sort order: ++
Map-reduce partition columns: '2008-04-08' (type: string), '11' (type: string)
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>)
+ value expressions: _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string>)
Reduce Operator Tree:
Group By Operator
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
http://git-wip-us.apache.org/repos/asf/hive/blob/b883d313/ql/src/test/results/clientpositive/correlated_join_keys.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/correlated_join_keys.q.out b/ql/src/test/results/clientpositive/correlated_join_keys.q.out
index ec5d008..b81a561 100644
--- a/ql/src/test/results/clientpositive/correlated_join_keys.q.out
+++ b/ql/src/test/results/clientpositive/correlated_join_keys.q.out
@@ -207,7 +207,7 @@ STAGE PLANS:
keys:
0 _col0 (type: string), _col1 (type: string)
1 _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 16 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
mode: hash
http://git-wip-us.apache.org/repos/asf/hive/blob/b883d313/ql/src/test/results/clientpositive/cross_join_merge.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/cross_join_merge.q.out b/ql/src/test/results/clientpositive/cross_join_merge.q.out
index f4956de..7241dfe 100644
--- a/ql/src/test/results/clientpositive/cross_join_merge.q.out
+++ b/ql/src/test/results/clientpositive/cross_join_merge.q.out
@@ -233,7 +233,7 @@ STAGE PLANS:
Processor Tree:
ListSink
-Warning: Shuffle Join JOIN[14][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-2:MAPRED' is a cross product
+Warning: Shuffle Join JOIN[11][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product
PREHOOK: query: explain
select src1.key from src src1 join src src2 on 5 = src2.key join src src3 on src1.key=src3.key
PREHOOK: type: QUERY
@@ -250,7 +250,7 @@ STAGE PLANS:
Map Reduce
Map Operator Tree:
TableScan
- alias: src1
+ alias: src3
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: key is not null (type: boolean)
@@ -260,34 +260,29 @@ STAGE PLANS:
outputColumnNames: _col0
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
+ sort order:
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: string)
TableScan
- alias: src3
+ alias: src2
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: key is not null (type: boolean)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ predicate: (5.0 = UDFToDouble(key)) (type: boolean)
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: key (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ sort order:
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Reduce Operator Tree:
Join Operator
condition map:
Inner Join 0 to 1
keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
+ 0
+ 1
outputColumnNames: _col0
- Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 125000 Data size: 2781000 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
table:
@@ -300,36 +295,45 @@ STAGE PLANS:
Map Operator Tree:
TableScan
Reduce Output Operator
- sort order:
- Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: string)
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 125000 Data size: 2781000 Basic stats: COMPLETE Column stats: NONE
TableScan
- alias: src2
+ alias: src1
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (5.0 = UDFToDouble(key)) (type: boolean)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Select Operator
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
- sort order:
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Reduce Operator Tree:
Join Operator
condition map:
Inner Join 0 to 1
keys:
- 0
- 1
- outputColumnNames: _col0
- Statistics: Num rows: 137500 Data size: 3059050 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 137500 Data size: 3059050 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col2
+ Statistics: Num rows: 137500 Data size: 3059100 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col2 (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 137500 Data size: 3059100 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 137500 Data size: 3059100 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-0
Fetch Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/b883d313/ql/src/test/results/clientpositive/decimal_stats.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/decimal_stats.q.out b/ql/src/test/results/clientpositive/decimal_stats.q.out
index 5d86866..f58a7cc 100644
--- a/ql/src/test/results/clientpositive/decimal_stats.q.out
+++ b/ql/src/test/results/clientpositive/decimal_stats.q.out
@@ -48,7 +48,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@decimal_1
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-v decimal(10,0) 500 1 from deserializer
+v decimal(10,0) 500 0 from deserializer
COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"t\":\"true\",\"u\":\"true\",\"v\":\"true\"}}
PREHOOK: query: explain select * from decimal_1 order by t limit 100
PREHOOK: type: QUERY
http://git-wip-us.apache.org/repos/asf/hive/blob/b883d313/ql/src/test/results/clientpositive/describe_table.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/describe_table.q.out b/ql/src/test/results/clientpositive/describe_table.q.out
index 7869494..3ba9a7b 100644
--- a/ql/src/test/results/clientpositive/describe_table.q.out
+++ b/ql/src/test/results/clientpositive/describe_table.q.out
@@ -212,7 +212,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@srcpart
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-key string 0 205 2.812 3 from deserializer
+key string 0 309 2.812 3 from deserializer
COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"key\":\"true\"}}
PREHOOK: query: describe formatted srcpart PARTITION(ds='2008-04-08', hr='12')
PREHOOK: type: DESCTABLE
@@ -304,7 +304,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@srcpart
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-key string 0 205 2.812 3 from deserializer
+key string 0 309 2.812 3 from deserializer
COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"key\":\"true\"}}
PREHOOK: query: describe formatted `srcpart` PARTITION(ds='2008-04-08', hr='12')
PREHOOK: type: DESCTABLE
http://git-wip-us.apache.org/repos/asf/hive/blob/b883d313/ql/src/test/results/clientpositive/display_colstats_tbllvl.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/display_colstats_tbllvl.q.out b/ql/src/test/results/clientpositive/display_colstats_tbllvl.q.out
index a4b18d7..73d4cd7 100644
--- a/ql/src/test/results/clientpositive/display_colstats_tbllvl.q.out
+++ b/ql/src/test/results/clientpositive/display_colstats_tbllvl.q.out
@@ -76,23 +76,23 @@ STAGE PLANS:
outputColumnNames: sourceip, adrevenue, avgtimeonsite
Statistics: Num rows: 65 Data size: 7060 Basic stats: COMPLETE Column stats: NONE
Group By Operator
- aggregations: compute_stats(sourceip, 16), compute_stats(avgtimeonsite, 16), compute_stats(adrevenue, 16)
+ aggregations: compute_stats(sourceip, 'hll'), compute_stats(avgtimeonsite, 'hll'), compute_stats(adrevenue, 'hll')
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 1444 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1408 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 1444 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col2 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:string,numbitvectors:int>)
+ Statistics: Num rows: 1 Data size: 1408 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string>), _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:string>), _col2 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:string>)
Reduce Operator Tree:
Group By Operator
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 1452 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1440 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 1452 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1440 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -128,16 +128,16 @@ STAGE PLANS:
outputColumnNames: sourceip, adrevenue, avgtimeonsite
Statistics: Num rows: 65 Data size: 7060 Basic stats: COMPLETE Column stats: NONE
Group By Operator
- aggregations: compute_stats(sourceip, 16), compute_stats(avgtimeonsite, 16), compute_stats(adrevenue, 16)
+ aggregations: compute_stats(sourceip, 'hll'), compute_stats(avgtimeonsite, 'hll'), compute_stats(adrevenue, 'hll')
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 1444 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1408 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
null sort order:
sort order:
- Statistics: Num rows: 1 Data size: 1444 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1408 Basic stats: COMPLETE Column stats: NONE
tag: -1
- value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col2 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:string,numbitvectors:int>)
+ value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string>), _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:string>), _col2 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:string>)
auto parallelism: false
Path -> Alias:
#### A masked pattern was here ####
@@ -196,13 +196,13 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 1452 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1440 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
GlobalTableId: 0
#### A masked pattern was here ####
NumFilesPerFileSink: 1
- Statistics: Num rows: 1 Data size: 1452 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1440 Basic stats: COMPLETE Column stats: NONE
#### A masked pattern was here ####
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
@@ -244,7 +244,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@uservisits_web_text_none
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-sourceIP string 0 69 12.763636363636364 13 from deserializer
+sourceIP string 0 55 12.763636363636364 13 from deserializer
COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"adrevenue\":\"true\",\"avgtimeonsite\":\"true\",\"sourceip\":\"true\"}}
PREHOOK: query: desc formatted UserVisits_web_text_none avgTimeOnSite
PREHOOK: type: DESCTABLE
@@ -254,7 +254,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@uservisits_web_text_none
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-avgTimeOnSite int 1 9 0 11 from deserializer
+avgTimeOnSite int 1 9 0 9 from deserializer
COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"adrevenue\":\"true\",\"avgtimeonsite\":\"true\",\"sourceip\":\"true\"}}
PREHOOK: query: desc formatted UserVisits_web_text_none adRevenue
PREHOOK: type: DESCTABLE
@@ -264,7 +264,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@uservisits_web_text_none
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-adRevenue float 13.099044799804688 492.98870849609375 0 58 from deserializer
+adRevenue float 13.099044799804688 492.98870849609375 0 55 from deserializer
COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"adrevenue\":\"true\",\"avgtimeonsite\":\"true\",\"sourceip\":\"true\"}}
PREHOOK: query: CREATE TABLE empty_tab(
a int,
@@ -318,23 +318,23 @@ STAGE PLANS:
outputColumnNames: a, b, c, d, e
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
Group By Operator
- aggregations: compute_stats(a, 16), compute_stats(b, 16), compute_stats(c, 16), compute_stats(d, 16), compute_stats(e, 16)
+ aggregations: compute_stats(a, 'hll'), compute_stats(b, 'hll'), compute_stats(c, 'hll'), compute_stats(d, 'hll'), compute_stats(e, 'hll')
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 1 Data size: 2004 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1968 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 2004 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col1 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:string,numbitvectors:int>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col3 (type: struct<columntype:string,counttrues:bigint,countfalses:bigint,countnulls:bigint>), _col4 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint>)
+ Statistics: Num rows: 1 Data size: 1968 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:string>), _col1 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:string>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string>), _col3 (type: struct<columntype:string,counttrues:bigint,countfalses:bigint,countnulls:bigint>), _col4 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint>)
Reduce Operator Tree:
Group By Operator
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3), compute_stats(VALUE._col4)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 2000 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 2000 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -471,7 +471,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@uservisits_web_text_none
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-sourceIP string 0 69 12.763636363636364 13 from deserializer
+sourceIP string 0 55 12.763636363636364 13 from deserializer
COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"adrevenue\":\"true\",\"avgtimeonsite\":\"true\",\"sourceip\":\"true\"}}
PREHOOK: query: analyze table UserVisits_web_text_none compute statistics for columns sKeyword
PREHOOK: type: QUERY
@@ -497,7 +497,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: test@uservisits_web_text_none
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-sKeyword string 0 49 7.872727272727273 19 from deserializer
+sKeyword string 0 54 7.872727272727273 19 from deserializer
COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"skeyword\":\"true\"}}
PREHOOK: query: desc formatted test.UserVisits_web_text_none sKeyword
PREHOOK: type: DESCTABLE
@@ -507,5 +507,5 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: test@uservisits_web_text_none
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-sKeyword string 0 49 7.872727272727273 19 from deserializer
+sKeyword string 0 54 7.872727272727273 19 from deserializer
COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"skeyword\":\"true\"}}
http://git-wip-us.apache.org/repos/asf/hive/blob/b883d313/ql/src/test/results/clientpositive/encrypted/encryption_move_tbl.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/encrypted/encryption_move_tbl.q.out b/ql/src/test/results/clientpositive/encrypted/encryption_move_tbl.q.out
index 06f8408..1096e9f 100644
--- a/ql/src/test/results/clientpositive/encrypted/encryption_move_tbl.q.out
+++ b/ql/src/test/results/clientpositive/encrypted/encryption_move_tbl.q.out
@@ -61,7 +61,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@encrypted_table
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-key int 0 498 0 196 from deserializer
+key int 0 498 0 309 from deserializer
COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
PREHOOK: query: DESCRIBE FORMATTED encrypted_table value
PREHOOK: type: DESCTABLE
@@ -71,7 +71,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@encrypted_table
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-value string 0 214 6.812 7 from deserializer
+value string 0 309 6.812 7 from deserializer
COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
PREHOOK: query: ALTER TABLE default.encrypted_table RENAME TO encrypted_db.encrypted_table_2
PREHOOK: type: ALTERTABLE_RENAME
@@ -94,7 +94,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@encrypted_table
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-key int 0 498 0 196 from deserializer
+key int 0 498 0 309 from deserializer
COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
PREHOOK: query: DESCRIBE FORMATTED encrypted_table value
PREHOOK: type: DESCTABLE
@@ -104,7 +104,7 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@encrypted_table
# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment
-value string 0 214 6.812 7 from deserializer
+value string 0 309 6.812 7 from deserializer
COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
PREHOOK: query: ALTER TABLE default.encrypted_table RENAME TO default.plain_table
PREHOOK: type: ALTERTABLE_RENAME
http://git-wip-us.apache.org/repos/asf/hive/blob/b883d313/ql/src/test/results/clientpositive/exec_parallel_column_stats.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/exec_parallel_column_stats.q.out b/ql/src/test/results/clientpositive/exec_parallel_column_stats.q.out
index f256ec1..f6c4237 100644
--- a/ql/src/test/results/clientpositive/exec_parallel_column_stats.q.out
+++ b/ql/src/test/results/clientpositive/exec_parallel_column_stats.q.out
@@ -18,23 +18,23 @@ STAGE PLANS:
outputColumnNames: key, value
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Group By Operator
- aggregations: compute_stats(key, 16), compute_stats(value, 16)
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 984 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 960 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 984 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>)
+ Statistics: Num rows: 1 Data size: 960 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string>)
Reduce Operator Tree:
Group By Operator
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 984 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 960 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 984 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 960 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat