You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by ha...@apache.org on 2018/03/24 17:32:42 UTC
[5/9] hive git commit: HIVE-18780 : Improve schema discovery For
Druid Storage Handler (Slim Bouguerra via Ashutosh Chauhan) HIVE-18993 : Use
Druid Expressions HIVE-14518 : Support 'having' translation for Druid GroupBy
queries HIVE-18957 : Upgrade Calci
http://git-wip-us.apache.org/repos/asf/hive/blob/696affa2/ql/src/test/results/clientpositive/druid/druidmini_test1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/druid/druidmini_test1.q.out b/ql/src/test/results/clientpositive/druid/druidmini_test1.q.out
index aa68f48..34cccef 100644
--- a/ql/src/test/results/clientpositive/druid/druidmini_test1.q.out
+++ b/ql/src/test/results/clientpositive/druid/druidmini_test1.q.out
@@ -64,7 +64,9 @@ STAGE PLANS:
TableScan
alias: druid_table
properties:
- druid.query.json {"queryType":"timeseries","dataSource":"default.druid_table","descending":false,"granularity":"all","aggregations":[{"type":"count","name":"$f0"}],"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"context":{"skipEmptyBuckets":true}}
+ druid.fieldNames $f0
+ druid.fieldTypes bigint
+ druid.query.json {"queryType":"timeseries","dataSource":"default.druid_table","descending":false,"granularity":"all","aggregations":[{"type":"count","name":"$f0"}],"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"context":{"skipEmptyBuckets":false}}
druid.query.type timeseries
Select Operator
expressions: $f0 (type: bigint)
@@ -97,10 +99,12 @@ STAGE PLANS:
TableScan
alias: druid_table
properties:
- druid.query.json {"queryType":"timeseries","dataSource":"default.druid_table","descending":false,"granularity":"year","aggregations":[{"type":"doubleSum","name":"$f1","fieldName":"cfloat"},{"type":"doubleSum","name":"$f2","fieldName":"cdouble"},{"type":"longSum","name":"$f3","fieldName":"ctinyint"},{"type":"longSum","name":"$f4","fieldName":"csmallint"},{"type":"longSum","name":"$f5","fieldName":"cint"},{"type":"longSum","name":"$f6","fieldName":"cbigint"}],"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"context":{"skipEmptyBuckets":true}}
+ druid.fieldNames timestamp,$f1,$f2,$f3,$f4,$f5,$f6
+ druid.fieldTypes timestamp with local time zone,double,double,bigint,bigint,bigint,bigint
+ druid.query.json {"queryType":"timeseries","dataSource":"default.druid_table","descending":false,"granularity":{"type":"period","period":"P1Y","timeZone":"US/Pacific"},"aggregations":[{"type":"doubleSum","name":"$f1","fieldName":"cfloat"},{"type":"doubleSum","name":"$f2","fieldName":"cdouble"},{"type":"longSum","name":"$f3","fieldName":"ctinyint"},{"type":"longSum","name":"$f4","fieldName":"csmallint"},{"type":"longSum","name":"$f5","fieldName":"cint"},{"type":"longSum","name":"$f6","fieldName":"cbigint"}],"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"context":{"skipEmptyBuckets":true}}
druid.query.type timeseries
Select Operator
- expressions: __time (type: timestamp with local time zone), $f1 (type: float), $f2 (type: float), $f3 (type: bigint), $f4 (type: bigint), $f5 (type: bigint), $f6 (type: bigint)
+ expressions: timestamp (type: timestamp with local time zone), $f1 (type: double), $f2 (type: double), $f3 (type: bigint), $f4 (type: bigint), $f5 (type: bigint), $f6 (type: bigint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
ListSink
@@ -114,8 +118,7 @@ FROM druid_table GROUP BY floor_year(`__time`)
POSTHOOK: type: QUERY
POSTHOOK: Input: default@druid_table
POSTHOOK: Output: hdfs://### HDFS PATH ###
-1968-12-31 16:00:00.0 US/Pacific -4532.57 3660538.8 -4611 3658030 688783835691 8060200254
-1969-12-31 16:00:00.0 US/Pacific -35057.676 2.3648124E7 -35356 4123059 719285966109 2932345033
+1969-01-01 00:00:00.0 US/Pacific -39590.24694168568 2.7308662809692383E7 -39967 7781089 1408069801800 10992545287
PREHOOK: query: EXPLAIN SELECT floor_year(`__time`), MIN(cfloat), MIN(cdouble), MIN(ctinyint), MIN(csmallint),MIN(cint), MIN(cbigint)
FROM druid_table GROUP BY floor_year(`__time`)
PREHOOK: type: QUERY
@@ -133,10 +136,12 @@ STAGE PLANS:
TableScan
alias: druid_table
properties:
- druid.query.json {"queryType":"timeseries","dataSource":"default.druid_table","descending":false,"granularity":"year","aggregations":[{"type":"doubleMin","name":"$f1","fieldName":"cfloat"},{"type":"doubleMin","name":"$f2","fieldName":"cdouble"},{"type":"longMin","name":"$f3","fieldName":"ctinyint"},{"type":"longMin","name":"$f4","fieldName":"csmallint"},{"type":"longMin","name":"$f5","fieldName":"cint"},{"type":"longMin","name":"$f6","fieldName":"cbigint"}],"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"context":{"skipEmptyBuckets":true}}
+ druid.fieldNames timestamp,$f1,$f2,$f3,$f4,$f5,$f6
+ druid.fieldTypes timestamp with local time zone,float,double,tinyint,smallint,int,bigint
+ druid.query.json {"queryType":"timeseries","dataSource":"default.druid_table","descending":false,"granularity":{"type":"period","period":"P1Y","timeZone":"US/Pacific"},"aggregations":[{"type":"doubleMin","name":"$f1","fieldName":"cfloat"},{"type":"doubleMin","name":"$f2","fieldName":"cdouble"},{"type":"longMin","name":"$f3","fieldName":"ctinyint"},{"type":"longMin","name":"$f4","fieldName":"csmallint"},{"type":"longMin","name":"$f5","fieldName":"cint"},{"type":"longMin","name":"$f6","fieldName":"cbigint"}],"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"context":{"skipEmptyBuckets":true}}
druid.query.type timeseries
Select Operator
- expressions: __time (type: timestamp with local time zone), $f1 (type: float), $f2 (type: float), $f3 (type: bigint), $f4 (type: bigint), $f5 (type: bigint), $f6 (type: bigint)
+ expressions: timestamp (type: timestamp with local time zone), $f1 (type: float), $f2 (type: double), $f3 (type: tinyint), $f4 (type: smallint), $f5 (type: int), $f6 (type: bigint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
ListSink
@@ -150,8 +155,7 @@ FROM druid_table GROUP BY floor_year(`__time`)
POSTHOOK: type: QUERY
POSTHOOK: Input: default@druid_table
POSTHOOK: Output: hdfs://### HDFS PATH ###
-1968-12-31 16:00:00.0 US/Pacific -1790.778 -308691.84 -1790 -313425 0 -8577981133
-1969-12-31 16:00:00.0 US/Pacific -964.719 -287404.84 -1051 -292138 -1073279343 -2147311592
+1969-01-01 00:00:00.0 US/Pacific -1790.778 -308691.84375 2 14255 -1073279343 -8577981133
PREHOOK: query: EXPLAIN SELECT floor_year(`__time`), MAX(cfloat), MAX(cdouble), MAX(ctinyint), MAX(csmallint),MAX(cint), MAX(cbigint)
FROM druid_table GROUP BY floor_year(`__time`)
PREHOOK: type: QUERY
@@ -169,10 +173,12 @@ STAGE PLANS:
TableScan
alias: druid_table
properties:
- druid.query.json {"queryType":"timeseries","dataSource":"default.druid_table","descending":false,"granularity":"year","aggregations":[{"type":"doubleMax","name":"$f1","fieldName":"cfloat"},{"type":"doubleMax","name":"$f2","fieldName":"cdouble"},{"type":"longMax","name":"$f3","fieldName":"ctinyint"},{"type":"longMax","name":"$f4","fieldName":"csmallint"},{"type":"longMax","name":"$f5","fieldName":"cint"},{"type":"longMax","name":"$f6","fieldName":"cbigint"}],"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"context":{"skipEmptyBuckets":true}}
+ druid.fieldNames timestamp,$f1,$f2,$f3,$f4,$f5,$f6
+ druid.fieldTypes timestamp with local time zone,float,double,tinyint,smallint,int,bigint
+ druid.query.json {"queryType":"timeseries","dataSource":"default.druid_table","descending":false,"granularity":{"type":"period","period":"P1Y","timeZone":"US/Pacific"},"aggregations":[{"type":"doubleMax","name":"$f1","fieldName":"cfloat"},{"type":"doubleMax","name":"$f2","fieldName":"cdouble"},{"type":"longMax","name":"$f3","fieldName":"ctinyint"},{"type":"longMax","name":"$f4","fieldName":"csmallint"},{"type":"longMax","name":"$f5","fieldName":"cint"},{"type":"longMax","name":"$f6","fieldName":"cbigint"}],"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"context":{"skipEmptyBuckets":true}}
druid.query.type timeseries
Select Operator
- expressions: __time (type: timestamp with local time zone), $f1 (type: float), $f2 (type: float), $f3 (type: bigint), $f4 (type: bigint), $f5 (type: bigint), $f6 (type: bigint)
+ expressions: timestamp (type: timestamp with local time zone), $f1 (type: float), $f2 (type: double), $f3 (type: tinyint), $f4 (type: smallint), $f5 (type: int), $f6 (type: bigint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
ListSink
@@ -186,8 +192,7 @@ FROM druid_table GROUP BY floor_year(`__time`)
POSTHOOK: type: QUERY
POSTHOOK: Input: default@druid_table
POSTHOOK: Output: hdfs://### HDFS PATH ###
-1968-12-31 16:00:00.0 US/Pacific 62.0 57235.0 62 57235 314088763179 2144274348
-1969-12-31 16:00:00.0 US/Pacific 769.164 1.9565518E7 723 57435 319104152611 4923772860
+1969-01-01 00:00:00.0 US/Pacific 769.164 1.9565518E7 -45 -8101 1276572707 4923772860
PREHOOK: query: EXPLAIN SELECT cstring1, SUM(cdouble) as s FROM druid_table GROUP BY cstring1 ORDER BY s ASC LIMIT 10
PREHOOK: type: QUERY
POSTHOOK: query: EXPLAIN SELECT cstring1, SUM(cdouble) as s FROM druid_table GROUP BY cstring1 ORDER BY s ASC LIMIT 10
@@ -203,10 +208,12 @@ STAGE PLANS:
TableScan
alias: druid_table
properties:
- druid.query.json {"queryType":"groupBy","dataSource":"default.druid_table","granularity":"all","dimensions":[{"type":"default","dimension":"cstring1"}],"limitSpec":{"type":"default","limit":10,"columns":[{"dimension":"$f1","direction":"ascending","dimensionOrder":"numeric"}]},"aggregations":[{"type":"doubleSum","name":"$f1","fieldName":"cdouble"}],"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"]}
+ druid.fieldNames cstring1,$f1
+ druid.fieldTypes string,double
+ druid.query.json {"queryType":"groupBy","dataSource":"default.druid_table","granularity":"all","dimensions":[{"type":"default","dimension":"cstring1","outputName":"cstring1","outputType":"STRING"}],"limitSpec":{"type":"default","limit":10,"columns":[{"dimension":"$f1","direction":"ascending","dimensionOrder":"numeric"}]},"aggregations":[{"type":"doubleSum","name":"$f1","fieldName":"cdouble"}],"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"]}
druid.query.type groupBy
Select Operator
- expressions: cstring1 (type: string), $f1 (type: float)
+ expressions: cstring1 (type: string), $f1 (type: double)
outputColumnNames: _col0, _col1
ListSink
@@ -218,8 +225,8 @@ POSTHOOK: query: SELECT cstring1, SUM(cdouble) as s FROM druid_table GROUP BY cs
POSTHOOK: type: QUERY
POSTHOOK: Input: default@druid_table
POSTHOOK: Output: hdfs://### HDFS PATH ###
-1cGVWH7n1QU -596096.7
-821UdmGbkEf4j -14161.827
+1cGVWH7n1QU -596096.6875
+821UdmGbkEf4j -14161.827026367188
00iT08 0.0
02v8WnLuYDos3Cq 0.0
yv1js 0.0
@@ -243,10 +250,12 @@ STAGE PLANS:
TableScan
alias: druid_table
properties:
- druid.query.json {"queryType":"groupBy","dataSource":"default.druid_table","granularity":"all","dimensions":[{"type":"default","dimension":"cstring2"}],"limitSpec":{"type":"default","limit":10,"columns":[{"dimension":"cstring2","direction":"ascending","dimensionOrder":"alphanumeric"}]},"aggregations":[{"type":"doubleMax","name":"$f1","fieldName":"cdouble"}],"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"]}
+ druid.fieldNames cstring2,$f1
+ druid.fieldTypes string,double
+ druid.query.json {"queryType":"groupBy","dataSource":"default.druid_table","granularity":"all","dimensions":[{"type":"default","dimension":"cstring2","outputName":"cstring2","outputType":"STRING"}],"limitSpec":{"type":"default","limit":10,"columns":[{"dimension":"cstring2","direction":"ascending","dimensionOrder":"lexicographic"}]},"aggregations":[{"type":"doubleMax","name":"$f1","fieldName":"cdouble"}],"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"]}
druid.query.type groupBy
Select Operator
- expressions: cstring2 (type: string), $f1 (type: float)
+ expressions: cstring2 (type: string), $f1 (type: double)
outputColumnNames: _col0, _col1
ListSink
@@ -259,15 +268,15 @@ POSTHOOK: type: QUERY
POSTHOOK: Input: default@druid_table
POSTHOOK: Output: hdfs://### HDFS PATH ###
NULL 1.9565518E7
-0AAE3daA78MISbsRsHJrp2PI 0.0
-0amu3m60U20Xa3 -200.0
-0aO3Lwer 0.0
-0aQBRP67JY0gpi 15601.0
-0b1WvXy 0.0
-0b03cuG3B4ASx4es1411336I -7196.0
-0B5S310g 0.0
-0bffMd8KSbW32A8A5 0.0
-0bke07kBhD1s33AV3R1X7j7j 0.0
+0034fkcXMQI3 15601.0
+004J8y 0.0
+00GNm -200.0
+00GW4dnb6Wgj52 -200.0
+00PBhB1Iefgk 0.0
+00d5kr1wEB7evExG 15601.0
+00qccwt8n 0.0
+017fFeQ3Gcsa83Xj2Vo0 0.0
+01EfkvNk6mjG44uxs 0.0
PREHOOK: query: EXPLAIN
SELECT `__time`
FROM druid_table ORDER BY `__time` ASC LIMIT 10
@@ -293,11 +302,13 @@ STAGE PLANS:
TableScan
alias: druid_table
properties:
- druid.query.json {"queryType":"select","dataSource":"default.druid_table","descending":false,"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"dimensions":[],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}}
- druid.query.type select
+ druid.fieldNames vc
+ druid.fieldTypes timestamp with local time zone
+ druid.query.json {"queryType":"scan","dataSource":"default.druid_table","intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"virtualColumns":[{"type":"expression","name":"vc","expression":"\"__time\"","outputType":"LONG"}],"columns":["vc"],"resultFormat":"compactedList"}
+ druid.query.type scan
Statistics: Num rows: 9173 Data size: 348640 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: __time (type: timestamp with local time zone)
+ expressions: vc (type: timestamp with local time zone)
outputColumnNames: _col0
Statistics: Num rows: 9173 Data size: 348640 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
@@ -375,11 +386,13 @@ STAGE PLANS:
TableScan
alias: druid_table
properties:
- druid.query.json {"queryType":"select","dataSource":"default.druid_table","descending":false,"intervals":["1900-01-01T00:00:00.000Z/1970-03-01T08:00:00.000Z"],"dimensions":[],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}}
- druid.query.type select
+ druid.fieldNames vc
+ druid.fieldTypes timestamp with local time zone
+ druid.query.json {"queryType":"scan","dataSource":"default.druid_table","intervals":["1900-01-01T00:00:00.000Z/1970-03-01T08:00:00.000Z"],"virtualColumns":[{"type":"expression","name":"vc","expression":"\"__time\"","outputType":"LONG"}],"columns":["vc"],"resultFormat":"compactedList"}
+ druid.query.type scan
Statistics: Num rows: 9173 Data size: 348640 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: __time (type: timestamp with local time zone)
+ expressions: vc (type: timestamp with local time zone)
outputColumnNames: _col0
Statistics: Num rows: 9173 Data size: 348640 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
@@ -459,11 +472,13 @@ STAGE PLANS:
TableScan
alias: druid_table
properties:
- druid.query.json {"queryType":"select","dataSource":"default.druid_table","descending":false,"intervals":["1968-01-01T08:00:00.000Z/1970-03-01T08:00:00.001Z"],"dimensions":[],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}}
- druid.query.type select
+ druid.fieldNames vc
+ druid.fieldTypes timestamp with local time zone
+ druid.query.json {"queryType":"scan","dataSource":"default.druid_table","intervals":["1968-01-01T08:00:00.000Z/1970-03-01T08:00:00.001Z"],"virtualColumns":[{"type":"expression","name":"vc","expression":"\"__time\"","outputType":"LONG"}],"columns":["vc"],"resultFormat":"compactedList"}
+ druid.query.type scan
Statistics: Num rows: 9173 Data size: 348640 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: __time (type: timestamp with local time zone)
+ expressions: vc (type: timestamp with local time zone)
outputColumnNames: _col0
Statistics: Num rows: 9173 Data size: 348640 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
@@ -545,11 +560,13 @@ STAGE PLANS:
TableScan
alias: druid_table
properties:
- druid.query.json {"queryType":"select","dataSource":"default.druid_table","descending":false,"intervals":["1968-01-01T08:00:00.000Z/1970-03-01T08:00:00.001Z"],"dimensions":[],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}}
- druid.query.type select
+ druid.fieldNames vc
+ druid.fieldTypes timestamp with local time zone
+ druid.query.json {"queryType":"scan","dataSource":"default.druid_table","intervals":["1968-01-01T08:00:00.000Z/1970-03-01T08:00:00.001Z"],"virtualColumns":[{"type":"expression","name":"vc","expression":"\"__time\"","outputType":"LONG"}],"columns":["vc"],"resultFormat":"compactedList"}
+ druid.query.type scan
Statistics: Num rows: 9173 Data size: 348640 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: __time (type: timestamp with local time zone)
+ expressions: vc (type: timestamp with local time zone)
outputColumnNames: _col0
Statistics: Num rows: 9173 Data size: 348640 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
@@ -631,11 +648,13 @@ STAGE PLANS:
TableScan
alias: druid_table
properties:
- druid.query.json {"queryType":"select","dataSource":"default.druid_table","descending":false,"intervals":["1968-01-01T08:00:00.000Z/1970-01-01T08:00:00.001Z"],"dimensions":[],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}}
- druid.query.type select
+ druid.fieldNames vc
+ druid.fieldTypes timestamp with local time zone
+ druid.query.json {"queryType":"scan","dataSource":"default.druid_table","intervals":["1968-01-01T08:00:00.000Z/1970-01-01T08:00:00.001Z"],"virtualColumns":[{"type":"expression","name":"vc","expression":"\"__time\"","outputType":"LONG"}],"columns":["vc"],"resultFormat":"compactedList"}
+ druid.query.type scan
Statistics: Num rows: 9173 Data size: 348640 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: __time (type: timestamp with local time zone)
+ expressions: vc (type: timestamp with local time zone)
outputColumnNames: _col0
Statistics: Num rows: 9173 Data size: 348640 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
@@ -717,11 +736,13 @@ STAGE PLANS:
TableScan
alias: druid_table
properties:
- druid.query.json {"queryType":"select","dataSource":"default.druid_table","descending":false,"intervals":["1968-01-01T08:00:00.000Z/1970-04-01T08:00:00.001Z"],"dimensions":[],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}}
- druid.query.type select
+ druid.fieldNames vc
+ druid.fieldTypes timestamp with local time zone
+ druid.query.json {"queryType":"scan","dataSource":"default.druid_table","intervals":["1968-01-01T08:00:00.000Z/1970-04-01T08:00:00.001Z"],"virtualColumns":[{"type":"expression","name":"vc","expression":"\"__time\"","outputType":"LONG"}],"columns":["vc"],"resultFormat":"compactedList"}
+ druid.query.type scan
Statistics: Num rows: 9173 Data size: 348640 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: __time (type: timestamp with local time zone)
+ expressions: vc (type: timestamp with local time zone)
outputColumnNames: _col0
Statistics: Num rows: 9173 Data size: 348640 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/696affa2/ql/src/test/results/clientpositive/druid_basic2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/druid_basic2.q.out b/ql/src/test/results/clientpositive/druid_basic2.q.out
index eb2b83f..5ed039b 100644
--- a/ql/src/test/results/clientpositive/druid_basic2.q.out
+++ b/ql/src/test/results/clientpositive/druid_basic2.q.out
@@ -76,8 +76,10 @@ STAGE PLANS:
TableScan
alias: druid_table_1
properties:
- druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"dimensions":["robot"],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}}
- druid.query.type select
+ druid.fieldNames robot
+ druid.fieldTypes string
+ druid.query.json {"queryType":"scan","dataSource":"wikipedia","intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"columns":["robot"],"resultFormat":"compactedList"}
+ druid.query.type scan
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
GatherStats: false
Select Operator
@@ -103,8 +105,10 @@ STAGE PLANS:
TableScan
alias: druid_table_1
properties:
- druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"dimensions":[],"metrics":["delta"],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}}
- druid.query.type select
+ druid.fieldNames delta
+ druid.fieldTypes float
+ druid.query.json {"queryType":"scan","dataSource":"wikipedia","intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"columns":["delta"],"resultFormat":"compactedList"}
+ druid.query.type scan
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
GatherStats: false
Select Operator
@@ -134,8 +138,10 @@ STAGE PLANS:
TableScan
alias: druid_table_1
properties:
- druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"filter":{"type":"selector","dimension":"language","value":"en"},"dimensions":["robot"],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}}
- druid.query.type select
+ druid.fieldNames robot
+ druid.fieldTypes string
+ druid.query.json {"queryType":"scan","dataSource":"wikipedia","intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"filter":{"type":"selector","dimension":"language","value":"en"},"columns":["robot"],"resultFormat":"compactedList"}
+ druid.query.type scan
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
GatherStats: false
Select Operator
@@ -165,7 +171,9 @@ STAGE PLANS:
TableScan
alias: druid_table_1
properties:
- druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"all","dimensions":[{"type":"default","dimension":"robot"}],"limitSpec":{"type":"default"},"filter":{"type":"selector","dimension":"language","value":"en"},"aggregations":[{"type":"longSum","name":"dummy_agg","fieldName":"dummy_agg"}],"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"]}
+ druid.fieldNames robot
+ druid.fieldTypes string
+ druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"all","dimensions":[{"type":"default","dimension":"robot","outputName":"robot","outputType":"STRING"}],"limitSpec":{"type":"default"},"filter":{"type":"selector","dimension":"language","value":"en"},"aggregations":[],"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"]}
druid.query.type groupBy
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
GatherStats: false
@@ -210,8 +218,10 @@ STAGE PLANS:
TableScan
alias: druid_table_1
properties:
- druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"filter":{"type":"not","field":{"type":"selector","dimension":"language","value":null}},"dimensions":["robot","language"],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}}
- druid.query.type select
+ druid.fieldNames robot,language
+ druid.fieldTypes string,string
+ druid.query.json {"queryType":"scan","dataSource":"wikipedia","intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"filter":{"type":"not","field":{"type":"selector","dimension":"language","value":null}},"columns":["robot","language"],"resultFormat":"compactedList"}
+ druid.query.type scan
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
GatherStats: false
Select Operator
@@ -230,8 +240,10 @@ STAGE PLANS:
TableScan
alias: druid_table_1
properties:
- druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"filter":{"type":"not","field":{"type":"selector","dimension":"language","value":null}},"dimensions":["language"],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}}
- druid.query.type select
+ druid.fieldNames language
+ druid.fieldTypes string
+ druid.query.json {"queryType":"scan","dataSource":"wikipedia","intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"filter":{"type":"not","field":{"type":"selector","dimension":"language","value":null}},"columns":["language"],"resultFormat":"compactedList"}
+ druid.query.type scan
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
GatherStats: false
Reduce Output Operator
@@ -259,8 +271,10 @@ STAGE PLANS:
columns.comments 'from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer'
columns.types timestamp with local time zone:string:string:string:string:string:string:string:string:float:float:float:float:float
druid.datasource wikipedia
- druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"filter":{"type":"not","field":{"type":"selector","dimension":"language","value":null}},"dimensions":["robot","language"],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}}
- druid.query.type select
+ druid.fieldNames robot,language
+ druid.fieldTypes string,string
+ druid.query.json {"queryType":"scan","dataSource":"wikipedia","intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"filter":{"type":"not","field":{"type":"selector","dimension":"language","value":null}},"columns":["robot","language"],"resultFormat":"compactedList"}
+ druid.query.type scan
#### A masked pattern was here ####
name default.druid_table_1
numFiles 0
@@ -285,8 +299,10 @@ STAGE PLANS:
columns.comments 'from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer'
columns.types timestamp with local time zone:string:string:string:string:string:string:string:string:float:float:float:float:float
druid.datasource wikipedia
- druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"filter":{"type":"not","field":{"type":"selector","dimension":"language","value":null}},"dimensions":["language"],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}}
- druid.query.type select
+ druid.fieldNames language
+ druid.fieldTypes string
+ druid.query.json {"queryType":"scan","dataSource":"wikipedia","intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"filter":{"type":"not","field":{"type":"selector","dimension":"language","value":null}},"columns":["language"],"resultFormat":"compactedList"}
+ druid.query.type scan
#### A masked pattern was here ####
name default.druid_table_1
numFiles 0
@@ -311,10 +327,10 @@ STAGE PLANS:
keys:
0 _col1 (type: string)
1 language (type: string)
- outputColumnNames: _col0, _col3
+ outputColumnNames: _col0, _col2
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
Select Operator
- expressions: _col0 (type: string), _col3 (type: string)
+ expressions: _col0 (type: string), _col2 (type: string)
outputColumnNames: _col0, _col1
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
File Output Operator
@@ -346,7 +362,7 @@ STAGE PLANS:
Processor Tree:
ListSink
-Warning: Shuffle Join JOIN[5][tables = [druid_table_1, $hdt$_0]] in Stage 'Stage-1:MAPRED' is a cross product
+Warning: Shuffle Join JOIN[5][tables = [$hdt$_0, druid_table_1]] in Stage 'Stage-1:MAPRED' is a cross product
PREHOOK: query: EXPLAIN EXTENDED
SELECT a.robot, b.language
FROM
@@ -384,31 +400,37 @@ STAGE PLANS:
TableScan
alias: druid_table_1
properties:
- druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"filter":{"type":"selector","dimension":"language","value":"en"},"dimensions":[],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}}
- druid.query.type select
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE
+ druid.fieldNames robot
+ druid.fieldTypes string
+ druid.query.json {"queryType":"scan","dataSource":"wikipedia","intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"filter":{"type":"selector","dimension":"language","value":"en"},"columns":["robot"],"resultFormat":"compactedList"}
+ druid.query.type scan
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
GatherStats: false
Select Operator
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE
+ expressions: robot (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
Reduce Output Operator
null sort order:
sort order:
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE
- tag: 1
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ tag: 0
+ value expressions: _col0 (type: string)
auto parallelism: false
TableScan
alias: druid_table_1
properties:
- druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"filter":{"type":"selector","dimension":"language","value":"en"},"dimensions":["robot"],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}}
- druid.query.type select
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ druid.fieldNames vc
+ druid.fieldTypes string
+ druid.query.json {"queryType":"scan","dataSource":"wikipedia","intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"filter":{"type":"selector","dimension":"language","value":"en"},"virtualColumns":[{"type":"expression","name":"vc","expression":"'en'","outputType":"STRING"}],"columns":["vc"],"resultFormat":"compactedList"}
+ druid.query.type scan
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE
GatherStats: false
Reduce Output Operator
null sort order:
sort order:
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- tag: 0
- value expressions: robot (type: string)
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE
+ tag: 1
auto parallelism: false
Path -> Alias:
#### A masked pattern was here ####
@@ -427,8 +449,10 @@ STAGE PLANS:
columns.comments 'from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer'
columns.types timestamp with local time zone:string:string:string:string:string:string:string:string:float:float:float:float:float
druid.datasource wikipedia
- druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"filter":{"type":"selector","dimension":"language","value":"en"},"dimensions":[],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}}
- druid.query.type select
+ druid.fieldNames robot
+ druid.fieldTypes string
+ druid.query.json {"queryType":"scan","dataSource":"wikipedia","intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"filter":{"type":"selector","dimension":"language","value":"en"},"columns":["robot"],"resultFormat":"compactedList"}
+ druid.query.type scan
#### A masked pattern was here ####
name default.druid_table_1
numFiles 0
@@ -453,8 +477,10 @@ STAGE PLANS:
columns.comments 'from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer'
columns.types timestamp with local time zone:string:string:string:string:string:string:string:string:float:float:float:float:float
druid.datasource wikipedia
- druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"filter":{"type":"selector","dimension":"language","value":"en"},"dimensions":["robot"],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}}
- druid.query.type select
+ druid.fieldNames vc
+ druid.fieldTypes string
+ druid.query.json {"queryType":"scan","dataSource":"wikipedia","intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"filter":{"type":"selector","dimension":"language","value":"en"},"virtualColumns":[{"type":"expression","name":"vc","expression":"'en'","outputType":"STRING"}],"columns":["vc"],"resultFormat":"compactedList"}
+ druid.query.type scan
#### A masked pattern was here ####
name default.druid_table_1
numFiles 0
@@ -479,10 +505,10 @@ STAGE PLANS:
keys:
0
1
- outputColumnNames: _col1
+ outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 1 Basic stats: PARTIAL Column stats: NONE
Select Operator
- expressions: _col1 (type: string), 'en' (type: string)
+ expressions: _col0 (type: string), 'en' (type: string)
outputColumnNames: _col0, _col1
Statistics: Num rows: 1 Data size: 1 Basic stats: PARTIAL Column stats: NONE
File Output Operator
@@ -529,132 +555,27 @@ ORDER BY CAST(robot AS INTEGER) ASC, m DESC
LIMIT 10
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
+ Stage-0 is a root stage
STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: druid_table_1
- properties:
- druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"all","dimensions":[{"type":"default","dimension":"robot"},{"type":"default","dimension":"language"},{"type":"extraction","dimension":"__time","outputName":"floor_day","extractionFn":{"type":"timeFormat","format":"yyyy-MM-dd'T'HH:mm:ss.SSS'Z'","granularity":"day","timeZone":"US/Pacific","locale":"en-US"}}],"limitSpec":{"type":"default"},"aggregations":[{"type":"doubleMax","name":"$f3","fieldName":"added"},{"type":"doubleSum","name":"$f4","fieldName":"delta"}],"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"]}
- druid.query.type groupBy
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- GatherStats: false
- Select Operator
- expressions: robot (type: string), floor_day (type: timestamp with local time zone), $f3 (type: float), $f4 (type: float), UDFToInteger(robot) (type: int)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Reduce Output Operator
- key expressions: _col4 (type: int), _col2 (type: float)
- null sort order: az
- sort order: +-
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- tag: -1
- TopN: 10
- TopN Hash Memory Usage: 0.1
- value expressions: _col0 (type: string), _col1 (type: timestamp with local time zone), _col3 (type: float)
- auto parallelism: false
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- base file name: druid_table_1
- input format: org.apache.hadoop.hive.druid.io.DruidQueryBasedInputFormat
- output format: org.apache.hadoop.hive.druid.io.DruidOutputFormat
- properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"__time":"true","added":"true","anonymous":"true","count":"true","deleted":"true","delta":"true","language":"true","namespace":"true","newpage":"true","page":"true","robot":"true","unpatrolled":"true","user":"true","variation":"true"}}
- EXTERNAL TRUE
- bucket_count -1
- column.name.delimiter ,
- columns __time,robot,namespace,anonymous,unpatrolled,page,language,newpage,user,count,added,delta,variation,deleted
- columns.comments 'from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer'
- columns.types timestamp with local time zone:string:string:string:string:string:string:string:string:float:float:float:float:float
- druid.datasource wikipedia
- druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"all","dimensions":[{"type":"default","dimension":"robot"},{"type":"default","dimension":"language"},{"type":"extraction","dimension":"__time","outputName":"floor_day","extractionFn":{"type":"timeFormat","format":"yyyy-MM-dd'T'HH:mm:ss.SSS'Z'","granularity":"day","timeZone":"US/Pacific","locale":"en-US"}}],"limitSpec":{"type":"default"},"aggregations":[{"type":"doubleMax","name":"$f3","fieldName":"added"},{"type":"doubleSum","name":"$f4","fieldName":"delta"}],"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"]}
- druid.query.type groupBy
-#### A masked pattern was here ####
- name default.druid_table_1
- numFiles 0
- numRows 0
- rawDataSize 0
- serialization.ddl struct druid_table_1 { timestamp with local time zone __time, string robot, string namespace, string anonymous, string unpatrolled, string page, string language, string newpage, string user, float count, float added, float delta, float variation, float deleted}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.druid.QTestDruidSerDe
- storage_handler org.apache.hadoop.hive.druid.QTestDruidStorageHandler
- totalSize 0
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.druid.QTestDruidSerDe
-
- input format: org.apache.hadoop.hive.druid.io.DruidQueryBasedInputFormat
- output format: org.apache.hadoop.hive.druid.io.DruidOutputFormat
- properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"__time":"true","added":"true","anonymous":"true","count":"true","deleted":"true","delta":"true","language":"true","namespace":"true","newpage":"true","page":"true","robot":"true","unpatrolled":"true","user":"true","variation":"true"}}
- EXTERNAL TRUE
- bucket_count -1
- column.name.delimiter ,
- columns __time,robot,namespace,anonymous,unpatrolled,page,language,newpage,user,count,added,delta,variation,deleted
- columns.comments 'from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer','from deserializer'
- columns.types timestamp with local time zone:string:string:string:string:string:string:string:string:float:float:float:float:float
- druid.datasource wikipedia
- druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"all","dimensions":[{"type":"default","dimension":"robot"},{"type":"default","dimension":"language"},{"type":"extraction","dimension":"__time","outputName":"floor_day","extractionFn":{"type":"timeFormat","format":"yyyy-MM-dd'T'HH:mm:ss.SSS'Z'","granularity":"day","timeZone":"US/Pacific","locale":"en-US"}}],"limitSpec":{"type":"default"},"aggregations":[{"type":"doubleMax","name":"$f3","fieldName":"added"},{"type":"doubleSum","name":"$f4","fieldName":"delta"}],"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"]}
- druid.query.type groupBy
-#### A masked pattern was here ####
- name default.druid_table_1
- numFiles 0
- numRows 0
- rawDataSize 0
- serialization.ddl struct druid_table_1 { timestamp with local time zone __time, string robot, string namespace, string anonymous, string unpatrolled, string page, string language, string newpage, string user, float count, float added, float delta, float variation, float deleted}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.druid.QTestDruidSerDe
- storage_handler org.apache.hadoop.hive.druid.QTestDruidStorageHandler
- totalSize 0
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.druid.QTestDruidSerDe
- name: default.druid_table_1
- name: default.druid_table_1
- Truncated Path -> Alias:
- /druid_table_1 [$hdt$_0:druid_table_1]
- Needs Tagging: false
- Reduce Operator Tree:
- Select Operator
- expressions: VALUE._col0 (type: string), VALUE._col1 (type: timestamp with local time zone), KEY.reducesinkkey1 (type: float), VALUE._col2 (type: float)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Limit
- Number of rows: 10
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 0
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- properties:
- columns _col0,_col1,_col2,_col3
- columns.types string:timestamp with local time zone:float:float
- escape.delim \
- hive.serialization.extend.additional.nesting.levels true
- serialization.escape.crlf true
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- TotalFiles: 1
- GatherStats: false
- MultiFileSpray: false
-
Stage: Stage-0
Fetch Operator
limit: -1
Processor Tree:
- ListSink
+ TableScan
+ alias: druid_table_1
+ properties:
+ druid.fieldNames robot,floor_day,$f3,$f4,(tok_function tok_int (tok_table_or_col robot))
+ druid.fieldTypes string,timestamp with local time zone,float,double,int
+ druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"all","dimensions":[{"type":"default","dimension":"robot","outputName":"robot","outputType":"STRING"},{"type":"default","dimension":"language","outputName":"language","outputType":"STRING"},{"type":"extraction","dimension":"__time","outputName":"floor_day","extractionFn":{"type":"timeFormat","format":"yyyy-MM-dd'T'HH:mm:ss.SSS'Z'","granularity":{"type":"period","period":"P1D","timeZone":"US/Pacific"},"timeZone":"US/Pacific","locale":"und"}}],"limitSpec":{"type":"default","limit":10,"columns":[{"dimension":"(tok_function tok_int (tok_table_or_col robot))","direction":"ascending","dimensionOrder":"numeric"},{"dimension":"$f3","direction":"descending","dimensionOrder":"numeric"}]},"aggregations":[{"type":"doubleMax","name":"$f3","fieldName":"added"},{"type":"doubleSum","name":"$f4","fieldName":"delta"}],"postAggregations":[{"type":"expression","name":"(tok_function tok_int (tok_table_or_col robot
))","expression":"CAST(\"robot\", 'LONG')"}],"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"]}
+ druid.query.type groupBy
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ GatherStats: false
+ Select Operator
+ expressions: robot (type: string), floor_day (type: timestamp with local time zone), $f3 (type: float), $f4 (type: double)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ ListSink
PREHOOK: query: EXPLAIN
SELECT substring(namespace, CAST(deleted AS INT), 4)
@@ -665,36 +586,26 @@ SELECT substring(namespace, CAST(deleted AS INT), 4)
FROM druid_table_1
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
+ Stage-0 is a root stage
STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: druid_table_1
- properties:
- druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"dimensions":["namespace"],"metrics":["deleted"],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}}
- druid.query.type select
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Select Operator
- expressions: substring(namespace, UDFToInteger(deleted), 4) (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL 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
limit: -1
Processor Tree:
- ListSink
+ TableScan
+ alias: druid_table_1
+ properties:
+ druid.fieldNames vc
+ druid.fieldTypes string
+ druid.query.json {"queryType":"scan","dataSource":"wikipedia","intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"virtualColumns":[{"type":"expression","name":"vc","expression":"substring(\"namespace\", (CAST(\"deleted\", 'LONG') - 1), 4)","outputType":"STRING"}],"columns":["vc"],"resultFormat":"compactedList"}
+ druid.query.type scan
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Select Operator
+ expressions: vc (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ ListSink
PREHOOK: query: EXPLAIN
SELECT robot, floor_day(`__time`)
@@ -713,83 +624,26 @@ ORDER BY robot
LIMIT 10
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-2 depends on stages: Stage-1
- Stage-0 depends on stages: Stage-2
+ Stage-0 is a root stage
STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: druid_table_1
- filterExpr: floor_day(__time) BETWEEN TIMESTAMPLOCALTZ'1999-11-01 00:00:00.0 US/Pacific' AND TIMESTAMPLOCALTZ'1999-11-10 00:00:00.0 US/Pacific' (type: boolean)
- properties:
- druid.query.json {"queryType":"select","dataSource":"wikipedia","descending":false,"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"],"dimensions":["robot"],"metrics":[],"granularity":"all","pagingSpec":{"threshold":16384,"fromNext":true},"context":{"druid.query.fetch":false}}
- druid.query.type select
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Filter Operator
- predicate: floor_day(__time) BETWEEN TIMESTAMPLOCALTZ'1999-11-01 00:00:00.0 US/Pacific' AND TIMESTAMPLOCALTZ'1999-11-10 00:00:00.0 US/Pacific' (type: boolean)
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Select Operator
- expressions: robot (type: string), floor_day(__time) (type: timestamp with local time zone)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Group By Operator
- keys: _col0 (type: string), _col1 (type: timestamp with local time zone)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: timestamp with local time zone)
- sort order: ++
- Map-reduce partition columns: _col0 (type: string), _col1 (type: timestamp with local time zone)
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- TopN Hash Memory Usage: 0.1
- Reduce Operator Tree:
- Group By Operator
- keys: KEY._col0 (type: string), KEY._col1 (type: timestamp with local time zone)
- mode: mergepartial
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-2
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- TopN Hash Memory Usage: 0.1
- value expressions: _col1 (type: timestamp with local time zone)
- Reduce Operator Tree:
- Select Operator
- expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: timestamp with local time zone)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Limit
- Number of rows: 10
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL 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
- limit: 10
+ limit: -1
Processor Tree:
- ListSink
+ TableScan
+ alias: druid_table_1
+ properties:
+ druid.fieldNames robot,floor_day
+ druid.fieldTypes string,timestamp with local time zone
+ druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"all","dimensions":[{"type":"default","dimension":"robot","outputName":"robot","outputType":"STRING"},{"type":"extraction","dimension":"__time","outputName":"floor_day","extractionFn":{"type":"timeFormat","format":"yyyy-MM-dd'T'HH:mm:ss.SSS'Z'","granularity":{"type":"period","period":"P1D","timeZone":"US/Pacific"},"timeZone":"US/Pacific","locale":"und"}}],"limitSpec":{"type":"default","limit":10,"columns":[{"dimension":"robot","direction":"ascending","dimensionOrder":"lexicographic"}]},"aggregations":[],"intervals":["1999-11-01T08:00:00.000Z/1999-11-10T08:00:00.001Z"]}
+ druid.query.type groupBy
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Select Operator
+ expressions: robot (type: string), floor_day (type: timestamp with local time zone)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ ListSink
PREHOOK: query: EXPLAIN
SELECT robot, `__time`
@@ -808,54 +662,26 @@ ORDER BY robot
LIMIT 10
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
+ Stage-0 is a root stage
STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: druid_table_1
- filterExpr: floor_day(extract) BETWEEN TIMESTAMPLOCALTZ'1999-11-01 00:00:00.0 US/Pacific' AND TIMESTAMPLOCALTZ'1999-11-10 00:00:00.0 US/Pacific' (type: boolean)
- properties:
- druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"all","dimensions":[{"type":"extraction","dimension":"__time","outputName":"extract","extractionFn":{"type":"timeFormat","format":"yyyy-MM-dd'T'HH:mm:ss.SSS'Z'","timeZone":"US/Pacific"}},{"type":"default","dimension":"robot"}],"limitSpec":{"type":"default"},"aggregations":[{"type":"longSum","name":"dummy_agg","fieldName":"dummy_agg"}],"intervals":["1900-01-01T00:00:00.000Z/3000-01-01T00:00:00.000Z"]}
- druid.query.type groupBy
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Filter Operator
- predicate: floor_day(extract) BETWEEN TIMESTAMPLOCALTZ'1999-11-01 00:00:00.0 US/Pacific' AND TIMESTAMPLOCALTZ'1999-11-10 00:00:00.0 US/Pacific' (type: boolean)
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Select Operator
- expressions: robot (type: string), extract (type: timestamp with local time zone)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- TopN Hash Memory Usage: 0.1
- value expressions: _col1 (type: timestamp with local time zone)
- Reduce Operator Tree:
- Select Operator
- expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: timestamp with local time zone)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Limit
- Number of rows: 10
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL 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
- limit: 10
+ limit: -1
Processor Tree:
- ListSink
+ TableScan
+ alias: druid_table_1
+ properties:
+ druid.fieldNames extract,robot
+ druid.fieldTypes timestamp with local time zone,string
+ druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"all","dimensions":[{"type":"extraction","dimension":"__time","outputName":"extract","extractionFn":{"type":"timeFormat","format":"yyyy-MM-dd'T'HH:mm:ss.SSS'Z'","timeZone":"US/Pacific"}},{"type":"default","dimension":"robot","outputName":"robot","outputType":"STRING"}],"limitSpec":{"type":"default","limit":10,"columns":[{"dimension":"robot","direction":"ascending","dimensionOrder":"lexicographic"}]},"aggregations":[],"intervals":["1999-11-01T08:00:00.000Z/1999-11-10T08:00:00.001Z"]}
+ druid.query.type groupBy
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Select Operator
+ expressions: robot (type: string), extract (type: timestamp with local time zone)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ ListSink
PREHOOK: query: EXPLAIN
SELECT robot, floor_day(`__time`)
@@ -884,7 +710,9 @@ STAGE PLANS:
TableScan
alias: druid_table_1
properties:
- druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"all","dimensions":[{"type":"default","dimension":"robot"},{"type":"extraction","dimension":"__time","outputName":"floor_day","extractionFn":{"type":"timeFormat","format":"yyyy-MM-dd'T'HH:mm:ss.SSS'Z'","granularity":"day","timeZone":"US/Pacific","locale":"en-US"}}],"limitSpec":{"type":"default","limit":10,"columns":[{"dimension":"robot","direction":"ascending","dimensionOrder":"alphanumeric"}]},"aggregations":[{"type":"longSum","name":"dummy_agg","fieldName":"dummy_agg"}],"intervals":["1999-11-01T08:00:00.000Z/1999-11-10T08:00:00.001Z"]}
+ druid.fieldNames robot,floor_day
+ druid.fieldTypes string,timestamp with local time zone
+ druid.query.json {"queryType":"groupBy","dataSource":"wikipedia","granularity":"all","dimensions":[{"type":"default","dimension":"robot","outputName":"robot","outputType":"STRING"},{"type":"extraction","dimension":"__time","outputName":"floor_day","extractionFn":{"type":"timeFormat","format":"yyyy-MM-dd'T'HH:mm:ss.SSS'Z'","granularity":{"type":"period","period":"P1D","timeZone":"US/Pacific"},"timeZone":"US/Pacific","locale":"und"}}],"limitSpec":{"type":"default","limit":10,"columns":[{"dimension":"robot","direction":"ascending","dimensionOrder":"lexicographic"}]},"aggregations":[],"intervals":["1999-11-01T08:00:00.000Z/1999-11-10T08:00:00.001Z"]}
druid.query.type groupBy
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
Select Operator