http://git-wip-us.apache.org/repos/asf/hive/blob/6f5c1135/ql/src/test/results/clientpositive/column_access_stats.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/column_access_stats.q.out b/ql/src/test/results/clientpositive/column_access_stats.q.out deleted file mode 100644 index dd8ade2..0000000 --- a/ql/src/test/results/clientpositive/column_access_stats.q.out +++ /dev/null @@ -1,869 +0,0 @@ -PREHOOK: query: -- SORT_QUERY_RESULTS --- This test is used for testing the ColumnAccessAnalyzer - -CREATE TABLE T1(key STRING, val STRING) STORED AS TEXTFILE -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@T1 -PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1 -PREHOOK: type: LOAD -#### A masked pattern was here #### -PREHOOK: Output: default@t1 -PREHOOK: query: CREATE TABLE T2(key STRING, val STRING) STORED AS TEXTFILE -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@T2 -PREHOOK: query: CREATE TABLE T3(key STRING, val STRING) STORED AS TEXTFILE -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@T3 -PREHOOK: query: CREATE TABLE T4(key STRING, val STRING) PARTITIONED BY (p STRING) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@T4 -PREHOOK: query: -- Simple select queries -SELECT key FROM T1 -PREHOOK: type: QUERY -PREHOOK: Input: default@t1 -#### A masked pattern was here #### -Table:default@t1 -Columns:key - -1 -2 -3 -7 -8 -8 -PREHOOK: query: SELECT key, val FROM T1 -PREHOOK: type: QUERY -PREHOOK: Input: default@t1 -#### A masked pattern was here #### -Table:default@t1 -Columns:key,val - -1 11 -2 12 -3 13 -7 17 -8 18 -8 28 -PREHOOK: query: SELECT 1 FROM T1 -PREHOOK: type: QUERY -PREHOOK: Input: default@t1 -#### A masked pattern was here #### -1 -1 -1 -1 -1 -1 -PREHOOK: query: SELECT key, val from T4 where p=1 -PREHOOK: type: QUERY -PREHOOK: Input: default@t4 -#### A masked pattern was here #### -Table:default@t4 -Columns:key,p,val - -PREHOOK: query: SELECT val FROM T4 where p=1 -PREHOOK: type: QUERY -PREHOOK: Input: default@t4 -#### A masked pattern was here #### -Table:default@t4 -Columns:p,val - -PREHOOK: query: SELECT p, val FROM T4 where p=1 -PREHOOK: type: QUERY -PREHOOK: Input: default@t4 -#### A masked pattern was here #### -Table:default@t4 -Columns:p,val - -PREHOOK: query: -- More complicated select queries -EXPLAIN SELECT key FROM (SELECT key, val FROM T1) subq1 -PREHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-0 is a root stage - -STAGE PLANS: - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - TableScan - alias: t1 - Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - ListSink - -PREHOOK: query: SELECT key FROM (SELECT key, val FROM T1) subq1 -PREHOOK: type: QUERY -PREHOOK: Input: default@t1 -#### A masked pattern was here #### -Table:default@t1 -Columns:key - -1 -2 -3 -7 -8 -8 -PREHOOK: query: EXPLAIN SELECT k FROM (SELECT key as k, val as v FROM T1) subq1 -PREHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-0 is a root stage - -STAGE PLANS: - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - TableScan - alias: t1 - Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - ListSink - -PREHOOK: query: SELECT k FROM (SELECT key as k, val as v FROM T1) subq1 -PREHOOK: type: QUERY -PREHOOK: Input: default@t1 -#### A masked pattern was here #### -Table:default@t1 -Columns:key - -1 -2 -3 -7 -8 -8 -PREHOOK: query: SELECT key + 1 as k FROM T1 -PREHOOK: type: QUERY -PREHOOK: Input: default@t1 -#### A masked pattern was here #### -Table:default@t1 -Columns:key - -2.0 -3.0 -4.0 -8.0 -9.0 -9.0 -PREHOOK: query: SELECT key + val as k FROM T1 -PREHOOK: type: QUERY -PREHOOK: Input: default@t1 -#### A masked pattern was here #### -Table:default@t1 -Columns:key,val - -12.0 -14.0 -16.0 -24.0 -26.0 -36.0 -PREHOOK: query: -- Work with union -EXPLAIN -SELECT * FROM ( -SELECT key as c FROM T1 - UNION ALL -SELECT val as c FROM T1 -) subq1 -PREHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t1 - Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Union - Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 60 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 - TableScan - alias: t1 - Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: val (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Union - Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 60 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 - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT * FROM ( -SELECT key as c FROM T1 - UNION ALL -SELECT val as c FROM T1 -) subq1 -PREHOOK: type: QUERY -PREHOOK: Input: default@t1 -#### A masked pattern was here #### -Table:default@t1 -Columns:key,val - -1 -11 -12 -13 -17 -18 -2 -28 -3 -7 -8 -8 -PREHOOK: query: EXPLAIN -SELECT * FROM ( -SELECT key as c FROM T1 - UNION ALL -SELECT key as c FROM T1 -) subq1 -PREHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t1 - Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Union - Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 60 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 - TableScan - alias: t1 - Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Union - Statistics: Num rows: 2 Data size: 60 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 60 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 - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT * FROM ( -SELECT key as c FROM T1 - UNION ALL -SELECT key as c FROM T1 -) subq1 -PREHOOK: type: QUERY -PREHOOK: Input: default@t1 -#### A masked pattern was here #### -Table:default@t1 -Columns:key - -1 -1 -2 -2 -3 -3 -7 -7 -8 -8 -8 -8 -PREHOOK: query: -- Work with insert overwrite -FROM T1 -INSERT OVERWRITE TABLE T2 SELECT key, count(1) GROUP BY key -INSERT OVERWRITE TABLE T3 SELECT key, sum(val) GROUP BY key -PREHOOK: type: QUERY -PREHOOK: Input: default@t1 -PREHOOK: Output: default@t2 -PREHOOK: Output: default@t3 -Table:default@t1 -Columns:key,val - -PREHOOK: query: -- Simple joins -SELECT * -FROM T1 JOIN T2 -ON T1.key = T2.key -PREHOOK: type: QUERY -PREHOOK: Input: default@t1 -PREHOOK: Input: default@t2 -#### A masked pattern was here #### -Table:default@t1 -Columns:key,val - -Table:default@t2 -Columns:key,val - -1 11 1 1 -2 12 2 1 -3 13 3 1 -7 17 7 1 -8 18 8 2 -8 28 8 2 -PREHOOK: query: EXPLAIN -SELECT T1.key -FROM T1 JOIN T2 -ON T1.key = T2.key -PREHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t1 - Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 30 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: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - TableScan - alias: t2 - Statistics: Num rows: 5 Data size: 15 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 5 Data size: 15 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 15 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: 5 Data size: 15 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) - outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 5 Data size: 16 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 - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT T1.key -FROM T1 JOIN T2 -ON T1.key = T2.key -PREHOOK: type: QUERY -PREHOOK: Input: default@t1 -PREHOOK: Input: default@t2 -#### A masked pattern was here #### -Table:default@t1 -Columns:key - -Table:default@t2 -Columns:key - -1 -2 -3 -7 -8 -8 -PREHOOK: query: SELECT * -FROM T1 JOIN T2 -ON T1.key = T2.key AND T1.val = T2.val -PREHOOK: type: QUERY -PREHOOK: Input: default@t1 -PREHOOK: Input: default@t2 -#### A masked pattern was here #### -Table:default@t1 -Columns:key,val - -Table:default@t2 -Columns:key,val - -PREHOOK: query: -- Map join -SELECT /*+ MAPJOIN(a) */ * -FROM T1 a JOIN T2 b -ON a.key = b.key -PREHOOK: type: QUERY -PREHOOK: Input: default@t1 -PREHOOK: Input: default@t2 -#### A masked pattern was here #### -Table:default@t1 -Columns:key,val - -Table:default@t2 -Columns:key,val - -1 11 1 1 -2 12 2 1 -3 13 3 1 -7 17 7 1 -8 18 8 2 -8 28 8 2 -PREHOOK: query: -- More joins -EXPLAIN -SELECT * -FROM T1 JOIN T2 -ON T1.key = T2.key AND T1.val = 3 and T2.val = 3 -PREHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t1 - Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((UDFToDouble(val) = 3.0) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 30 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: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - TableScan - alias: t2 - Statistics: Num rows: 5 Data size: 15 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((UDFToDouble(val) = 3.0) and key is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 6 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: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 6 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 - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT * -FROM T1 JOIN T2 -ON T1.key = T2.key AND T1.val = 3 and T2.val = 3 -PREHOOK: type: QUERY -PREHOOK: Input: default@t1 -PREHOOK: Input: default@t2 -#### A masked pattern was here #### -Table:default@t1 -Columns:key,val - -Table:default@t2 -Columns:key,val - -PREHOOK: query: EXPLAIN -SELECT subq1.val -FROM -( - SELECT val FROM T1 WHERE key = 5 -) subq1 -JOIN -( - SELECT val FROM T2 WHERE key = 6 -) subq2 -ON subq1.val = subq2.val -PREHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t1 - Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((UDFToDouble(key) = 5.0) and val is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: val (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 30 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: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - TableScan - alias: t2 - Statistics: Num rows: 5 Data size: 15 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((UDFToDouble(key) = 6.0) and val is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: val (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 6 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: 2 Data size: 6 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) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 6 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 - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT subq1.val -FROM -( - SELECT val FROM T1 WHERE key = 5 -) subq1 -JOIN -( - SELECT val FROM T2 WHERE key = 6 -) subq2 -ON subq1.val = subq2.val -PREHOOK: type: QUERY -PREHOOK: Input: default@t1 -PREHOOK: Input: default@t2 -#### A masked pattern was here #### -Table:default@t1 -Columns:key,val - -Table:default@t2 -Columns:key,val - -PREHOOK: query: -- Join followed by join -EXPLAIN -SELECT * -FROM -( - SELECT subq1.key as key - FROM - ( - SELECT key, val FROM T1 - ) subq1 - JOIN - ( - SELECT key, 'teststring' as val FROM T2 - ) subq2 - ON subq1.key = subq2.key -) T4 -JOIN T3 -ON T3.key = T4.key -PREHOOK: 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 PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: t1 - Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 30 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: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - TableScan - alias: t2 - Statistics: Num rows: 5 Data size: 15 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 5 Data size: 15 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 15 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: 5 Data size: 15 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) - outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 16 Basic stats: COMPLETE 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: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 5 Data size: 16 Basic stats: COMPLETE Column stats: NONE - TableScan - alias: t3 - Statistics: Num rows: 5 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 5 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 30 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: 5 Data size: 30 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 5 Data size: 17 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 5 Data size: 17 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 - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: SELECT * -FROM -( - SELECT subq1.key as key - FROM - ( - SELECT key, val FROM T1 - ) subq1 - JOIN - ( - SELECT key, 'teststring' as val FROM T2 - ) subq2 - ON subq1.key = subq2.key -) T4 -JOIN T3 -ON T3.key = T4.key -PREHOOK: type: QUERY -PREHOOK: Input: default@t1 -PREHOOK: Input: default@t2 -PREHOOK: Input: default@t3 -#### A masked pattern was here #### -Table:default@t1 -Columns:key - -Table:default@t2 -Columns:key - -Table:default@t3 -Columns:key,val - -1 1 11.0 -2 2 12.0 -3 3 13.0 -7 7 17.0 -8 8 46.0 -8 8 46.0 -PREHOOK: query: -- for partitioned table -SELECT * FROM srcpart TABLESAMPLE (10 ROWS) -PREHOOK: type: QUERY -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -Table:default@srcpart -Columns:ds,hr,key,value - -165 val_165 2008-04-08 11 -238 val_238 2008-04-08 11 -255 val_255 2008-04-08 11 -27 val_27 2008-04-08 11 -278 val_278 2008-04-08 11 -311 val_311 2008-04-08 11 -409 val_409 2008-04-08 11 -484 val_484 2008-04-08 11 -86 val_86 2008-04-08 11 -98 val_98 2008-04-08 11 -PREHOOK: query: SELECT key,ds FROM srcpart TABLESAMPLE (10 ROWS) WHERE hr='11' -PREHOOK: type: QUERY -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -#### A masked pattern was here #### -Table:default@srcpart -Columns:ds,hr,key - -165 2008-04-08 -238 2008-04-08 -255 2008-04-08 -27 2008-04-08 -278 2008-04-08 -311 2008-04-08 -409 2008-04-08 -484 2008-04-08 -86 2008-04-08 -98 2008-04-08 -PREHOOK: query: SELECT value FROM srcpart TABLESAMPLE (10 ROWS) WHERE ds='2008-04-08' -PREHOOK: type: QUERY -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -#### A masked pattern was here #### -Table:default@srcpart -Columns:ds,value - -val_165 -val_238 -val_255 -val_27 -val_278 -val_311 -val_409 -val_484 -val_86 -val_98
http://git-wip-us.apache.org/repos/asf/hive/blob/6f5c1135/ql/src/test/results/clientpositive/columnstats_part_coltype.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/columnstats_part_coltype.q.out b/ql/src/test/results/clientpositive/columnstats_part_coltype.q.out deleted file mode 100644 index d52f020..0000000 --- a/ql/src/test/results/clientpositive/columnstats_part_coltype.q.out +++ /dev/null @@ -1,441 +0,0 @@ -PREHOOK: query: -- Test type date, int, and string in partition column -drop table if exists partcolstats -PREHOOK: type: DROPTABLE -POSTHOOK: query: -- Test type date, int, and string in partition column -drop table if exists partcolstats -POSTHOOK: type: DROPTABLE -PREHOOK: query: create table partcolstats (key int, value string) partitioned by (ds date, hr int, part string) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@partcolstats -POSTHOOK: query: create table partcolstats (key int, value string) partitioned by (ds date, hr int, part string) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@partcolstats -PREHOOK: query: insert into partcolstats partition (ds=date '2015-04-02', hr=2, part='partA') select key, value from src limit 20 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@partcolstats@ds=2015-04-02/hr=2/part=partA -POSTHOOK: query: insert into partcolstats partition (ds=date '2015-04-02', hr=2, part='partA') select key, value from src limit 20 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@partcolstats@ds=2015-04-02/hr=2/part=partA -POSTHOOK: Lineage: partcolstats PARTITION(ds=2015-04-02,hr=2,part=partA).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: partcolstats PARTITION(ds=2015-04-02,hr=2,part=partA).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: insert into partcolstats partition (ds=date '2015-04-02', hr=2, part='partB') select key, value from src limit 20 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@partcolstats@ds=2015-04-02/hr=2/part=partB -POSTHOOK: query: insert into partcolstats partition (ds=date '2015-04-02', hr=2, part='partB') select key, value from src limit 20 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@partcolstats@ds=2015-04-02/hr=2/part=partB -POSTHOOK: Lineage: partcolstats PARTITION(ds=2015-04-02,hr=2,part=partB).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: partcolstats PARTITION(ds=2015-04-02,hr=2,part=partB).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: insert into partcolstats partition (ds=date '2015-04-02', hr=3, part='partA') select key, value from src limit 30 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@partcolstats@ds=2015-04-02/hr=3/part=partA -POSTHOOK: query: insert into partcolstats partition (ds=date '2015-04-02', hr=3, part='partA') select key, value from src limit 30 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@partcolstats@ds=2015-04-02/hr=3/part=partA -POSTHOOK: Lineage: partcolstats PARTITION(ds=2015-04-02,hr=3,part=partA).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: partcolstats PARTITION(ds=2015-04-02,hr=3,part=partA).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: insert into partcolstats partition (ds=date '2015-04-03', hr=3, part='partA') select key, value from src limit 40 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@partcolstats@ds=2015-04-03/hr=3/part=partA -POSTHOOK: query: insert into partcolstats partition (ds=date '2015-04-03', hr=3, part='partA') select key, value from src limit 40 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@partcolstats@ds=2015-04-03/hr=3/part=partA -POSTHOOK: Lineage: partcolstats PARTITION(ds=2015-04-03,hr=3,part=partA).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: partcolstats PARTITION(ds=2015-04-03,hr=3,part=partA).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: insert into partcolstats partition (ds=date '2015-04-03', hr=3, part='partB') select key, value from src limit 60 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@partcolstats@ds=2015-04-03/hr=3/part=partB -POSTHOOK: query: insert into partcolstats partition (ds=date '2015-04-03', hr=3, part='partB') select key, value from src limit 60 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@partcolstats@ds=2015-04-03/hr=3/part=partB -POSTHOOK: Lineage: partcolstats PARTITION(ds=2015-04-03,hr=3,part=partB).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: partcolstats PARTITION(ds=2015-04-03,hr=3,part=partB).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: analyze table partcolstats partition (ds=date '2015-04-02', hr=2, part='partA') compute statistics for columns -PREHOOK: type: QUERY -PREHOOK: Input: default@partcolstats -PREHOOK: Input: default@partcolstats@ds=2015-04-02/hr=2/part=partA -#### A masked pattern was here #### -POSTHOOK: query: analyze table partcolstats partition (ds=date '2015-04-02', hr=2, part='partA') compute statistics for columns -POSTHOOK: type: QUERY -POSTHOOK: Input: default@partcolstats -POSTHOOK: Input: default@partcolstats@ds=2015-04-02/hr=2/part=partA -#### A masked pattern was here #### -PREHOOK: query: describe formatted partcolstats partition (ds=date '2015-04-02', hr=2, part='partA') key -PREHOOK: type: DESCTABLE -PREHOOK: Input: default@partcolstats -POSTHOOK: query: describe formatted partcolstats partition (ds=date '2015-04-02', hr=2, part='partA') key -POSTHOOK: type: DESCTABLE -POSTHOOK: Input: default@partcolstats -# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment - -key int 27 484 0 18 from deserializer -PREHOOK: query: describe formatted partcolstats partition (ds=date '2015-04-02', hr=2, part='partA') value -PREHOOK: type: DESCTABLE -PREHOOK: Input: default@partcolstats -POSTHOOK: query: describe formatted partcolstats partition (ds=date '2015-04-02', hr=2, part='partA') value -POSTHOOK: type: DESCTABLE -POSTHOOK: Input: default@partcolstats -# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment - -value string 0 18 6.8 7 from deserializer -PREHOOK: query: describe formatted partcolstats partition (ds=date '2015-04-02', hr=2, part='partB') key -PREHOOK: type: DESCTABLE -PREHOOK: Input: default@partcolstats -POSTHOOK: query: describe formatted partcolstats partition (ds=date '2015-04-02', hr=2, part='partB') key -POSTHOOK: type: DESCTABLE -POSTHOOK: Input: default@partcolstats -# col_name data_type comment - -key int from deserializer -PREHOOK: query: describe formatted partcolstats partition (ds=date '2015-04-02', hr=2, part='partB') value -PREHOOK: type: DESCTABLE -PREHOOK: Input: default@partcolstats -POSTHOOK: query: describe formatted partcolstats partition (ds=date '2015-04-02', hr=2, part='partB') value -POSTHOOK: type: DESCTABLE -POSTHOOK: Input: default@partcolstats -# col_name data_type comment - -value string from deserializer -PREHOOK: query: analyze table partcolstats partition (ds=date '2015-04-02', hr=2, part) compute statistics for columns -PREHOOK: type: QUERY -PREHOOK: Input: default@partcolstats -PREHOOK: Input: default@partcolstats@ds=2015-04-02/hr=2/part=partA -PREHOOK: Input: default@partcolstats@ds=2015-04-02/hr=2/part=partB -#### A masked pattern was here #### -POSTHOOK: query: analyze table partcolstats partition (ds=date '2015-04-02', hr=2, part) compute statistics for columns -POSTHOOK: type: QUERY -POSTHOOK: Input: default@partcolstats -POSTHOOK: Input: default@partcolstats@ds=2015-04-02/hr=2/part=partA -POSTHOOK: Input: default@partcolstats@ds=2015-04-02/hr=2/part=partB -#### A masked pattern was here #### -PREHOOK: query: describe formatted partcolstats partition (ds=date '2015-04-02', hr=2, part='partB') key -PREHOOK: type: DESCTABLE -PREHOOK: Input: default@partcolstats -POSTHOOK: query: describe formatted partcolstats partition (ds=date '2015-04-02', hr=2, part='partB') key -POSTHOOK: type: DESCTABLE -POSTHOOK: Input: default@partcolstats -# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment - -key int 27 484 0 18 from deserializer -PREHOOK: query: describe formatted partcolstats partition (ds=date '2015-04-02', hr=2, part='partB') value -PREHOOK: type: DESCTABLE -PREHOOK: Input: default@partcolstats -POSTHOOK: query: describe formatted partcolstats partition (ds=date '2015-04-02', hr=2, part='partB') value -POSTHOOK: type: DESCTABLE -POSTHOOK: Input: default@partcolstats -# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment - -value string 0 18 6.8 7 from deserializer -PREHOOK: query: describe formatted partcolstats partition (ds=date '2015-04-02', hr=3, part='partA') key -PREHOOK: type: DESCTABLE -PREHOOK: Input: default@partcolstats -POSTHOOK: query: describe formatted partcolstats partition (ds=date '2015-04-02', hr=3, part='partA') key -POSTHOOK: type: DESCTABLE -POSTHOOK: Input: default@partcolstats -# col_name data_type comment - -key int from deserializer -PREHOOK: query: describe formatted partcolstats partition (ds=date '2015-04-02', hr=3, part='partA') value -PREHOOK: type: DESCTABLE -PREHOOK: Input: default@partcolstats -POSTHOOK: query: describe formatted partcolstats partition (ds=date '2015-04-02', hr=3, part='partA') value -POSTHOOK: type: DESCTABLE -POSTHOOK: Input: default@partcolstats -# col_name data_type comment - -value string from deserializer -PREHOOK: query: analyze table partcolstats partition (ds=date '2015-04-02', hr, part) compute statistics for columns -PREHOOK: type: QUERY -PREHOOK: Input: default@partcolstats -PREHOOK: Input: default@partcolstats@ds=2015-04-02/hr=2/part=partA -PREHOOK: Input: default@partcolstats@ds=2015-04-02/hr=2/part=partB -PREHOOK: Input: default@partcolstats@ds=2015-04-02/hr=3/part=partA -#### A masked pattern was here #### -POSTHOOK: query: analyze table partcolstats partition (ds=date '2015-04-02', hr, part) compute statistics for columns -POSTHOOK: type: QUERY -POSTHOOK: Input: default@partcolstats -POSTHOOK: Input: default@partcolstats@ds=2015-04-02/hr=2/part=partA -POSTHOOK: Input: default@partcolstats@ds=2015-04-02/hr=2/part=partB -POSTHOOK: Input: default@partcolstats@ds=2015-04-02/hr=3/part=partA -#### A masked pattern was here #### -PREHOOK: query: describe formatted partcolstats partition (ds=date '2015-04-02', hr=3, part='partA') key -PREHOOK: type: DESCTABLE -PREHOOK: Input: default@partcolstats -POSTHOOK: query: describe formatted partcolstats partition (ds=date '2015-04-02', hr=3, part='partA') key -POSTHOOK: type: DESCTABLE -POSTHOOK: Input: default@partcolstats -# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment - -key int 27 495 0 28 from deserializer -PREHOOK: query: describe formatted partcolstats partition (ds=date '2015-04-02', hr=3, part='partA') value -PREHOOK: type: DESCTABLE -PREHOOK: Input: default@partcolstats -POSTHOOK: query: describe formatted partcolstats partition (ds=date '2015-04-02', hr=3, part='partA') value -POSTHOOK: type: DESCTABLE -POSTHOOK: Input: default@partcolstats -# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment - -value string 0 18 6.833333333333333 7 from deserializer -PREHOOK: query: describe formatted partcolstats partition (ds=date '2015-04-03', hr=3, part='partA') key -PREHOOK: type: DESCTABLE -PREHOOK: Input: default@partcolstats -POSTHOOK: query: describe formatted partcolstats partition (ds=date '2015-04-03', hr=3, part='partA') key -POSTHOOK: type: DESCTABLE -POSTHOOK: Input: default@partcolstats -# col_name data_type comment - -key int from deserializer -PREHOOK: query: describe formatted partcolstats partition (ds=date '2015-04-03', hr=3, part='partA') value -PREHOOK: type: DESCTABLE -PREHOOK: Input: default@partcolstats -POSTHOOK: query: describe formatted partcolstats partition (ds=date '2015-04-03', hr=3, part='partA') value -POSTHOOK: type: DESCTABLE -POSTHOOK: Input: default@partcolstats -# col_name data_type comment - -value string from deserializer -PREHOOK: query: describe formatted partcolstats partition (ds=date '2015-04-03', hr=3, part='partB') key -PREHOOK: type: DESCTABLE -PREHOOK: Input: default@partcolstats -POSTHOOK: query: describe formatted partcolstats partition (ds=date '2015-04-03', hr=3, part='partB') key -POSTHOOK: type: DESCTABLE -POSTHOOK: Input: default@partcolstats -# col_name data_type comment - -key int from deserializer -PREHOOK: query: describe formatted partcolstats partition (ds=date '2015-04-03', hr=3, part='partB') value -PREHOOK: type: DESCTABLE -PREHOOK: Input: default@partcolstats -POSTHOOK: query: describe formatted partcolstats partition (ds=date '2015-04-03', hr=3, part='partB') value -POSTHOOK: type: DESCTABLE -POSTHOOK: Input: default@partcolstats -# col_name data_type comment - -value string from deserializer -PREHOOK: query: analyze table partcolstats partition (ds, hr, part) compute statistics for columns -PREHOOK: type: QUERY -PREHOOK: Input: default@partcolstats -PREHOOK: Input: default@partcolstats@ds=2015-04-02/hr=2/part=partA -PREHOOK: Input: default@partcolstats@ds=2015-04-02/hr=2/part=partB -PREHOOK: Input: default@partcolstats@ds=2015-04-02/hr=3/part=partA -PREHOOK: Input: default@partcolstats@ds=2015-04-03/hr=3/part=partA -PREHOOK: Input: default@partcolstats@ds=2015-04-03/hr=3/part=partB -#### A masked pattern was here #### -POSTHOOK: query: analyze table partcolstats partition (ds, hr, part) compute statistics for columns -POSTHOOK: type: QUERY -POSTHOOK: Input: default@partcolstats -POSTHOOK: Input: default@partcolstats@ds=2015-04-02/hr=2/part=partA -POSTHOOK: Input: default@partcolstats@ds=2015-04-02/hr=2/part=partB -POSTHOOK: Input: default@partcolstats@ds=2015-04-02/hr=3/part=partA -POSTHOOK: Input: default@partcolstats@ds=2015-04-03/hr=3/part=partA -POSTHOOK: Input: default@partcolstats@ds=2015-04-03/hr=3/part=partB -#### A masked pattern was here #### -PREHOOK: query: describe formatted partcolstats partition (ds=date '2015-04-03', hr=3, part='partA') key -PREHOOK: type: DESCTABLE -PREHOOK: Input: default@partcolstats -POSTHOOK: query: describe formatted partcolstats partition (ds=date '2015-04-03', hr=3, part='partA') key -POSTHOOK: type: DESCTABLE -POSTHOOK: Input: default@partcolstats -# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment - -key int 15 495 0 43 from deserializer -PREHOOK: query: describe formatted partcolstats partition (ds=date '2015-04-03', hr=3, part='partA') value -PREHOOK: type: DESCTABLE -PREHOOK: Input: default@partcolstats -POSTHOOK: query: describe formatted partcolstats partition (ds=date '2015-04-03', hr=3, part='partA') value -POSTHOOK: type: DESCTABLE -POSTHOOK: Input: default@partcolstats -# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment - -value string 0 34 6.825 7 from deserializer -PREHOOK: query: describe formatted partcolstats partition (ds=date '2015-04-03', hr=3, part='partB') key -PREHOOK: type: DESCTABLE -PREHOOK: Input: default@partcolstats -POSTHOOK: query: describe formatted partcolstats partition (ds=date '2015-04-03', hr=3, part='partB') key -POSTHOOK: type: DESCTABLE -POSTHOOK: Input: default@partcolstats -# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment - -key int 15 495 0 51 from deserializer -PREHOOK: query: describe formatted partcolstats partition (ds=date '2015-04-03', hr=3, part='partB') value -PREHOOK: type: DESCTABLE -PREHOOK: Input: default@partcolstats -POSTHOOK: query: describe formatted partcolstats partition (ds=date '2015-04-03', hr=3, part='partB') value -POSTHOOK: type: DESCTABLE -POSTHOOK: Input: default@partcolstats -# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment - -value string 0 53 6.883333333333334 7 from deserializer -PREHOOK: query: drop table partcolstats -PREHOOK: type: DROPTABLE -PREHOOK: Input: default@partcolstats -PREHOOK: Output: default@partcolstats -POSTHOOK: query: drop table partcolstats -POSTHOOK: type: DROPTABLE -POSTHOOK: Input: default@partcolstats -POSTHOOK: Output: default@partcolstats -PREHOOK: query: -- Test type tinyint, smallint, and bigint in partition column -drop table if exists partcolstatsnum -PREHOOK: type: DROPTABLE -POSTHOOK: query: -- Test type tinyint, smallint, and bigint in partition column -drop table if exists partcolstatsnum -POSTHOOK: type: DROPTABLE -PREHOOK: query: create table partcolstatsnum (key int, value string) partitioned by (tint tinyint, sint smallint, bint bigint) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@partcolstatsnum -POSTHOOK: query: create table partcolstatsnum (key int, value string) partitioned by (tint tinyint, sint smallint, bint bigint) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@partcolstatsnum -PREHOOK: query: insert into partcolstatsnum partition (tint=100, sint=1000, bint=1000000) select key, value from src limit 30 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@partcolstatsnum@tint=100/sint=1000/bint=1000000 -POSTHOOK: query: insert into partcolstatsnum partition (tint=100, sint=1000, bint=1000000) select key, value from src limit 30 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@partcolstatsnum@tint=100/sint=1000/bint=1000000 -POSTHOOK: Lineage: partcolstatsnum PARTITION(tint=100,sint=1000,bint=1000000).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: partcolstatsnum PARTITION(tint=100,sint=1000,bint=1000000).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: analyze table partcolstatsnum partition (tint=100, sint=1000, bint=1000000) compute statistics for columns -PREHOOK: type: QUERY -PREHOOK: Input: default@partcolstatsnum -PREHOOK: Input: default@partcolstatsnum@tint=100/sint=1000/bint=1000000 -#### A masked pattern was here #### -POSTHOOK: query: analyze table partcolstatsnum partition (tint=100, sint=1000, bint=1000000) compute statistics for columns -POSTHOOK: type: QUERY -POSTHOOK: Input: default@partcolstatsnum -POSTHOOK: Input: default@partcolstatsnum@tint=100/sint=1000/bint=1000000 -#### A masked pattern was here #### -PREHOOK: query: describe formatted partcolstatsnum partition (tint=100, sint=1000, bint=1000000) value -PREHOOK: type: DESCTABLE -PREHOOK: Input: default@partcolstatsnum -POSTHOOK: query: describe formatted partcolstatsnum partition (tint=100, sint=1000, bint=1000000) value -POSTHOOK: type: DESCTABLE -POSTHOOK: Input: default@partcolstatsnum -# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment - -value string 0 18 6.833333333333333 7 from deserializer -PREHOOK: query: drop table partcolstatsnum -PREHOOK: type: DROPTABLE -PREHOOK: Input: default@partcolstatsnum -PREHOOK: Output: default@partcolstatsnum -POSTHOOK: query: drop table partcolstatsnum -POSTHOOK: type: DROPTABLE -POSTHOOK: Input: default@partcolstatsnum -POSTHOOK: Output: default@partcolstatsnum -PREHOOK: query: -- Test type decimal in partition column -drop table if exists partcolstatsdec -PREHOOK: type: DROPTABLE -POSTHOOK: query: -- Test type decimal in partition column -drop table if exists partcolstatsdec -POSTHOOK: type: DROPTABLE -PREHOOK: query: create table partcolstatsdec (key int, value string) partitioned by (decpart decimal(8,4)) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@partcolstatsdec -POSTHOOK: query: create table partcolstatsdec (key int, value string) partitioned by (decpart decimal(8,4)) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@partcolstatsdec -PREHOOK: query: insert into partcolstatsdec partition (decpart='1000.0001') select key, value from src limit 30 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@partcolstatsdec@decpart=1000.0001 -POSTHOOK: query: insert into partcolstatsdec partition (decpart='1000.0001') select key, value from src limit 30 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@partcolstatsdec@decpart=1000.0001 -POSTHOOK: Lineage: partcolstatsdec PARTITION(decpart=1000.0001).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: partcolstatsdec PARTITION(decpart=1000.0001).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: analyze table partcolstatsdec partition (decpart='1000.0001') compute statistics for columns -PREHOOK: type: QUERY -PREHOOK: Input: default@partcolstatsdec -PREHOOK: Input: default@partcolstatsdec@decpart=1000.0001 -#### A masked pattern was here #### -POSTHOOK: query: analyze table partcolstatsdec partition (decpart='1000.0001') compute statistics for columns -POSTHOOK: type: QUERY -POSTHOOK: Input: default@partcolstatsdec -POSTHOOK: Input: default@partcolstatsdec@decpart=1000.0001 -#### A masked pattern was here #### -PREHOOK: query: describe formatted partcolstatsdec partition (decpart='1000.0001') value -PREHOOK: type: DESCTABLE -PREHOOK: Input: default@partcolstatsdec -POSTHOOK: query: describe formatted partcolstatsdec partition (decpart='1000.0001') value -POSTHOOK: type: DESCTABLE -POSTHOOK: Input: default@partcolstatsdec -# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment - -value string 0 18 6.833333333333333 7 from deserializer -PREHOOK: query: drop table partcolstatsdec -PREHOOK: type: DROPTABLE -PREHOOK: Input: default@partcolstatsdec -PREHOOK: Output: default@partcolstatsdec -POSTHOOK: query: drop table partcolstatsdec -POSTHOOK: type: DROPTABLE -POSTHOOK: Input: default@partcolstatsdec -POSTHOOK: Output: default@partcolstatsdec -PREHOOK: query: -- Test type varchar and char in partition column -drop table if exists partcolstatschar -PREHOOK: type: DROPTABLE -POSTHOOK: query: -- Test type varchar and char in partition column -drop table if exists partcolstatschar -POSTHOOK: type: DROPTABLE -PREHOOK: query: create table partcolstatschar (key int, value string) partitioned by (varpart varchar(5), charpart char(3)) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@partcolstatschar -POSTHOOK: query: create table partcolstatschar (key int, value string) partitioned by (varpart varchar(5), charpart char(3)) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@partcolstatschar -PREHOOK: query: insert into partcolstatschar partition (varpart='part1', charpart='aaa') select key, value from src limit 30 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@partcolstatschar@varpart=part1/charpart=aaa -POSTHOOK: query: insert into partcolstatschar partition (varpart='part1', charpart='aaa') select key, value from src limit 30 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@partcolstatschar@varpart=part1/charpart=aaa -POSTHOOK: Lineage: partcolstatschar PARTITION(varpart=part1,charpart=aaa).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: partcolstatschar PARTITION(varpart=part1,charpart=aaa).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: analyze table partcolstatschar partition (varpart='part1', charpart='aaa') compute statistics for columns -PREHOOK: type: QUERY -PREHOOK: Input: default@partcolstatschar -PREHOOK: Input: default@partcolstatschar@varpart=part1/charpart=aaa -#### A masked pattern was here #### -POSTHOOK: query: analyze table partcolstatschar partition (varpart='part1', charpart='aaa') compute statistics for columns -POSTHOOK: type: QUERY -POSTHOOK: Input: default@partcolstatschar -POSTHOOK: Input: default@partcolstatschar@varpart=part1/charpart=aaa -#### A masked pattern was here #### -PREHOOK: query: describe formatted partcolstatschar partition (varpart='part1', charpart='aaa') value -PREHOOK: type: DESCTABLE -PREHOOK: Input: default@partcolstatschar -POSTHOOK: query: describe formatted partcolstatschar partition (varpart='part1', charpart='aaa') value -POSTHOOK: type: DESCTABLE -POSTHOOK: Input: default@partcolstatschar -# col_name data_type min max num_nulls distinct_count avg_col_len max_col_len num_trues num_falses comment - -value string 0 18 6.833333333333333 7 from deserializer -PREHOOK: query: drop table partcolstatschar -PREHOOK: type: DROPTABLE -PREHOOK: Input: default@partcolstatschar -PREHOOK: Output: default@partcolstatschar -POSTHOOK: query: drop table partcolstatschar -POSTHOOK: type: DROPTABLE -POSTHOOK: Input: default@partcolstatschar -POSTHOOK: Output: default@partcolstatschar
