http://git-wip-us.apache.org/repos/asf/hive/blob/7e64114d/ql/src/test/results/clientpositive/autoColumnStats_5.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/autoColumnStats_5.q.out b/ql/src/test/results/clientpositive/autoColumnStats_5.q.out index db5dd86..6b29dad 100644 --- a/ql/src/test/results/clientpositive/autoColumnStats_5.q.out +++ b/ql/src/test/results/clientpositive/autoColumnStats_5.q.out @@ -26,50 +26,58 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: values__tmp__table__1 - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + alias: _dummy_table + Row Limit Per Split: 1 + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: UDFToInteger(tmp_values_col1) (type: int), tmp_values_col2 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.partitioned1 - Select Operator - expressions: _col0 (type: int), _col1 (type: string), UDFToInteger('1') (type: int) - outputColumnNames: a, b, part - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: compute_stats(a, 'hll'), compute_stats(b, 'hll') - keys: part (type: int) - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) + expressions: array(const struct(1,'original'),const struct(2,'original'),const struct(3,'original'),const struct(4,'original')) (type: array<struct<col1:int,col2:string>>) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE + UDTF Operator + Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE + function name: inline + Select Operator + expressions: col1 (type: int), col2 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.partitioned1 + Select Operator + expressions: _col0 (type: int), _col1 (type: string), UDFToInteger('1') (type: int) + outputColumnNames: a, b, part + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(a, 'hll'), compute_stats(b, 'hll') + keys: part (type: int) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 868 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 1 Data size: 868 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 884 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 884 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 884 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -136,13 +144,15 @@ STAGE PLANS: PREHOOK: query: insert into table partitioned1 partition(part=1) values(1, 'original'),(2, 'original'), (3, 'original'),(4, 'original') PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table PREHOOK: Output: default@partitioned1@part=1 POSTHOOK: query: insert into table partitioned1 partition(part=1) values(1, 'original'),(2, 'original'), (3, 'original'),(4, 'original') POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table POSTHOOK: Output: default@partitioned1@part=1 -POSTHOOK: Lineage: partitioned1 PARTITION(part=1).a EXPRESSION [(values__tmp__table__2)values__tmp__table__2.FieldSchema(name:tmp_values_col1, type:string, comment:), ] -POSTHOOK: Lineage: partitioned1 PARTITION(part=1).b SIMPLE [(values__tmp__table__2)values__tmp__table__2.FieldSchema(name:tmp_values_col2, type:string, comment:), ] -_col0 _col1 +POSTHOOK: Lineage: partitioned1 PARTITION(part=1).a SCRIPT [] +POSTHOOK: Lineage: partitioned1 PARTITION(part=1).b SCRIPT [] +col1 col2 PREHOOK: query: desc formatted partitioned1 partition(part=1) PREHOOK: type: DESCTABLE PREHOOK: Input: default@partitioned1 @@ -266,50 +276,58 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: values__tmp__table__3 - Statistics: Num rows: 1 Data size: 600 Basic stats: COMPLETE Column stats: NONE + alias: _dummy_table + Row Limit Per Split: 1 + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: UDFToInteger(tmp_values_col1) (type: int), tmp_values_col2 (type: string), UDFToInteger(tmp_values_col3) (type: int), tmp_values_col4 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 600 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 600 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.partitioned1 - Select Operator - expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int), _col3 (type: string), UDFToInteger('2') (type: int) - outputColumnNames: a, b, c, d, part - Statistics: Num rows: 1 Data size: 600 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: compute_stats(a, 'hll'), compute_stats(b, 'hll'), compute_stats(c, 'hll'), compute_stats(d, 'hll') - keys: part (type: int) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 600 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 600 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col4 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) + expressions: array(const struct(1,'new',10,'ten'),const struct(2,'new',20,'twenty'),const struct(3,'new',30,'thirty'),const struct(4,'new',40,'forty')) (type: array<struct<col1:int,col2:string,col3:int,col4:string>>) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE + UDTF Operator + Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE + function name: inline + Select Operator + expressions: col1 (type: int), col2 (type: string), col3 (type: int), col4 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.partitioned1 + Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int), _col3 (type: string), UDFToInteger('2') (type: int) + outputColumnNames: a, b, c, d, part + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(a, 'hll'), compute_stats(b, 'hll'), compute_stats(c, 'hll'), compute_stats(d, 'hll') + keys: part (type: int) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 1 Data size: 1732 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 1 Data size: 1732 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col4 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1764 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col3 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col4 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1764 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1764 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -376,15 +394,17 @@ STAGE PLANS: PREHOOK: query: insert into table partitioned1 partition(part=2) values(1, 'new', 10, 'ten'),(2, 'new', 20, 'twenty'), (3, 'new', 30, 'thirty'),(4, 'new', 40, 'forty') PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table PREHOOK: Output: default@partitioned1@part=2 POSTHOOK: query: insert into table partitioned1 partition(part=2) values(1, 'new', 10, 'ten'),(2, 'new', 20, 'twenty'), (3, 'new', 30, 'thirty'),(4, 'new', 40, 'forty') POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table POSTHOOK: Output: default@partitioned1@part=2 -POSTHOOK: Lineage: partitioned1 PARTITION(part=2).a EXPRESSION [(values__tmp__table__4)values__tmp__table__4.FieldSchema(name:tmp_values_col1, type:string, comment:), ] -POSTHOOK: Lineage: partitioned1 PARTITION(part=2).b SIMPLE [(values__tmp__table__4)values__tmp__table__4.FieldSchema(name:tmp_values_col2, type:string, comment:), ] -POSTHOOK: Lineage: partitioned1 PARTITION(part=2).c EXPRESSION [(values__tmp__table__4)values__tmp__table__4.FieldSchema(name:tmp_values_col3, type:string, comment:), ] -POSTHOOK: Lineage: partitioned1 PARTITION(part=2).d SIMPLE [(values__tmp__table__4)values__tmp__table__4.FieldSchema(name:tmp_values_col4, type:string, comment:), ] -_col0 _col1 _col2 _col3 +POSTHOOK: Lineage: partitioned1 PARTITION(part=2).a SCRIPT [] +POSTHOOK: Lineage: partitioned1 PARTITION(part=2).b SCRIPT [] +POSTHOOK: Lineage: partitioned1 PARTITION(part=2).c SCRIPT [] +POSTHOOK: Lineage: partitioned1 PARTITION(part=2).d SCRIPT [] +col1 col2 col3 col4 PREHOOK: query: desc formatted partitioned1 partition(part=2) PREHOOK: type: DESCTABLE PREHOOK: Input: default@partitioned1 @@ -464,50 +484,58 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: values__tmp__table__5 - Statistics: Num rows: 1 Data size: 400 Basic stats: COMPLETE Column stats: NONE + alias: _dummy_table + Row Limit Per Split: 1 + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: UDFToInteger(tmp_values_col1) (type: int), tmp_values_col2 (type: string), UDFToInteger(tmp_values_col3) (type: int), tmp_values_col4 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 400 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 400 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.partitioned1 - Select Operator - expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int), _col3 (type: string), UDFToInteger('1') (type: int) - outputColumnNames: a, b, c, d, part - Statistics: Num rows: 1 Data size: 400 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: compute_stats(a, 'hll'), compute_stats(b, 'hll'), compute_stats(c, 'hll'), compute_stats(d, 'hll') - keys: part (type: int) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 400 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 400 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col4 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) + expressions: array(const struct(5,'new',100,'hundred'),const struct(6,'new',200,'two hundred')) (type: array<struct<col1:int,col2:string,col3:int,col4:string>>) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE + UDTF Operator + Statistics: Num rows: 1 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE + function name: inline + Select Operator + expressions: col1 (type: int), col2 (type: string), col3 (type: int), col4 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.partitioned1 + Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int), _col3 (type: string), UDFToInteger('1') (type: int) + outputColumnNames: a, b, c, d, part + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(a, 'hll'), compute_stats(b, 'hll'), compute_stats(c, 'hll'), compute_stats(d, 'hll') + keys: part (type: int) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 1 Data size: 1732 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 1 Data size: 1732 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col4 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3) keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1764 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col3 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col4 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1 Data size: 400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1764 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1764 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -574,15 +602,17 @@ STAGE PLANS: PREHOOK: query: insert into table partitioned1 partition(part=1) values(5, 'new', 100, 'hundred'),(6, 'new', 200, 'two hundred') PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table PREHOOK: Output: default@partitioned1@part=1 POSTHOOK: query: insert into table partitioned1 partition(part=1) values(5, 'new', 100, 'hundred'),(6, 'new', 200, 'two hundred') POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table POSTHOOK: Output: default@partitioned1@part=1 -POSTHOOK: Lineage: partitioned1 PARTITION(part=1).a EXPRESSION [(values__tmp__table__6)values__tmp__table__6.FieldSchema(name:tmp_values_col1, type:string, comment:), ] -POSTHOOK: Lineage: partitioned1 PARTITION(part=1).b SIMPLE [(values__tmp__table__6)values__tmp__table__6.FieldSchema(name:tmp_values_col2, type:string, comment:), ] -POSTHOOK: Lineage: partitioned1 PARTITION(part=1).c EXPRESSION [(values__tmp__table__6)values__tmp__table__6.FieldSchema(name:tmp_values_col3, type:string, comment:), ] -POSTHOOK: Lineage: partitioned1 PARTITION(part=1).d SIMPLE [(values__tmp__table__6)values__tmp__table__6.FieldSchema(name:tmp_values_col4, type:string, comment:), ] -_col0 _col1 _col2 _col3 +POSTHOOK: Lineage: partitioned1 PARTITION(part=1).a SCRIPT [] +POSTHOOK: Lineage: partitioned1 PARTITION(part=1).b SCRIPT [] +POSTHOOK: Lineage: partitioned1 PARTITION(part=1).c SCRIPT [] +POSTHOOK: Lineage: partitioned1 PARTITION(part=1).d SCRIPT [] +col1 col2 col3 col4 PREHOOK: query: desc formatted partitioned1 partition(part=1) PREHOOK: type: DESCTABLE PREHOOK: Input: default@partitioned1
http://git-wip-us.apache.org/repos/asf/hive/blob/7e64114d/ql/src/test/results/clientpositive/autoColumnStats_5a.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/autoColumnStats_5a.q.out b/ql/src/test/results/clientpositive/autoColumnStats_5a.q.out index 40548d0..44f4c71 100644 --- a/ql/src/test/results/clientpositive/autoColumnStats_5a.q.out +++ b/ql/src/test/results/clientpositive/autoColumnStats_5a.q.out @@ -28,98 +28,106 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: values__tmp__table__1 - Statistics: Num rows: 1 Data size: 110 Basic stats: COMPLETE Column stats: NONE + alias: _dummy_table + Row Limit Per Split: 1 + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator - expressions: UDFToInteger(tmp_values_col1) (type: int), tmp_values_col2 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 110 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 1 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Static Partition Specification: part=1/ - Statistics: Num rows: 1 Data size: 110 Basic stats: COMPLETE Column stats: NONE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - column.name.delimiter , - columns a,b - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.partitioned1 - partition_columns.types int - serialization.ddl struct partitioned1 { i32 a, string b} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.partitioned1 - TotalFiles: 1 - GatherStats: true - MultiFileSpray: false - Select Operator - expressions: _col0 (type: int), _col1 (type: string), UDFToInteger('1') (type: int) - outputColumnNames: a, b, part - Statistics: Num rows: 1 Data size: 110 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: compute_stats(a, 'hll'), compute_stats(b, 'hll') - keys: part (type: int) - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 110 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: a - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 110 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) - auto parallelism: false + expressions: array(const struct(1,'original')) (type: array<struct<col1:int,col2:string>>) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + UDTF Operator + Statistics: Num rows: 1 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + function name: inline + Select Operator + expressions: col1 (type: int), col2 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + GlobalTableId: 1 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Static Partition Specification: part=1/ + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + column.name.delimiter , + columns a,b + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.partitioned1 + partition_columns.types int + serialization.ddl struct partitioned1 { i32 a, string b} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.partitioned1 + TotalFiles: 1 + GatherStats: true + MultiFileSpray: false + Select Operator + expressions: _col0 (type: int), _col1 (type: string), UDFToInteger('1') (type: int) + outputColumnNames: a, b, part + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(a, 'hll'), compute_stats(b, 'hll') + keys: part (type: int) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 868 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + null sort order: a + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 1 Data size: 868 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + value expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition - base file name: Values__Tmp__Table__1 - input format: org.apache.hadoop.mapred.TextInputFormat + base file name: dummy_path + input format: org.apache.hadoop.hive.ql.io.NullRowsInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 column.name.delimiter , - columns tmp_values_col1,tmp_values_col2 + columns columns.comments - columns.types string:string + columns.types #### A masked pattern was here #### - name default.values__tmp__table__1 - serialization.ddl struct values__tmp__table__1 { string tmp_values_col1, string tmp_values_col2} + name _dummy_database._dummy_table + serialization.ddl struct _dummy_table { } serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serialization.lib org.apache.hadoop.hive.serde2.NullStructSerDe + serde: org.apache.hadoop.hive.serde2.NullStructSerDe - input format: org.apache.hadoop.mapred.TextInputFormat + input format: org.apache.hadoop.hive.ql.io.NullRowsInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 column.name.delimiter , - columns tmp_values_col1,tmp_values_col2 + columns columns.comments - columns.types string:string + columns.types #### A masked pattern was here #### - name default.values__tmp__table__1 - serialization.ddl struct values__tmp__table__1 { string tmp_values_col1, string tmp_values_col2} + name _dummy_database._dummy_table + serialization.ddl struct _dummy_table { } serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.values__tmp__table__1 - name: default.values__tmp__table__1 + serialization.lib org.apache.hadoop.hive.serde2.NullStructSerDe + serde: org.apache.hadoop.hive.serde2.NullStructSerDe + name: _dummy_database._dummy_table + name: _dummy_database._dummy_table Truncated Path -> Alias: #### A masked pattern was here #### Needs Tagging: false @@ -129,17 +137,17 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 110 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 884 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 110 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 884 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 110 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 884 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -362,13 +370,15 @@ STAGE PLANS: PREHOOK: query: insert into table partitioned1 partition(part=1) values(1, 'original') PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table PREHOOK: Output: default@partitioned1@part=1 POSTHOOK: query: insert into table partitioned1 partition(part=1) values(1, 'original') POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table POSTHOOK: Output: default@partitioned1@part=1 -POSTHOOK: Lineage: partitioned1 PARTITION(part=1).a EXPRESSION [(values__tmp__table__2)values__tmp__table__2.FieldSchema(name:tmp_values_col1, type:string, comment:), ] -POSTHOOK: Lineage: partitioned1 PARTITION(part=1).b SIMPLE [(values__tmp__table__2)values__tmp__table__2.FieldSchema(name:tmp_values_col2, type:string, comment:), ] -_col0 _col1 +POSTHOOK: Lineage: partitioned1 PARTITION(part=1).a SCRIPT [] +POSTHOOK: Lineage: partitioned1 PARTITION(part=1).b SCRIPT [] +col1 col2 PREHOOK: query: desc formatted partitioned1 partition(part=1) PREHOOK: type: DESCTABLE PREHOOK: Input: default@partitioned1 @@ -429,98 +439,106 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: values__tmp__table__3 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + alias: _dummy_table + Row Limit Per Split: 1 + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Select Operator - expressions: UDFToInteger(tmp_values_col1) (type: int), tmp_values_col2 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 1 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Static Partition Specification: part=1/ - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - column.name.delimiter , - columns a,b - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.partitioned1 - partition_columns.types int - serialization.ddl struct partitioned1 { i32 a, string b} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.partitioned1 - TotalFiles: 1 - GatherStats: true - MultiFileSpray: false - Select Operator - expressions: _col0 (type: int), _col1 (type: string), UDFToInteger('1') (type: int) - outputColumnNames: a, b, part - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: compute_stats(a, 'hll'), compute_stats(b, 'hll') - keys: part (type: int) - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: a - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) - auto parallelism: false + expressions: array(const struct(2,'original'),const struct(3,'original'),const struct(4,'original')) (type: array<struct<col1:int,col2:string>>) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE + UDTF Operator + Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE + function name: inline + Select Operator + expressions: col1 (type: int), col2 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + GlobalTableId: 1 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Static Partition Specification: part=1/ + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + column.name.delimiter , + columns a,b + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.partitioned1 + partition_columns.types int + serialization.ddl struct partitioned1 { i32 a, string b} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.partitioned1 + TotalFiles: 1 + GatherStats: true + MultiFileSpray: false + Select Operator + expressions: _col0 (type: int), _col1 (type: string), UDFToInteger('1') (type: int) + outputColumnNames: a, b, part + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(a, 'hll'), compute_stats(b, 'hll') + keys: part (type: int) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 868 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + null sort order: a + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 1 Data size: 868 Basic stats: COMPLETE Column stats: COMPLETE + tag: -1 + value expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition - base file name: Values__Tmp__Table__3 - input format: org.apache.hadoop.mapred.TextInputFormat + base file name: dummy_path + input format: org.apache.hadoop.hive.ql.io.NullRowsInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 column.name.delimiter , - columns tmp_values_col1,tmp_values_col2 + columns columns.comments - columns.types string:string + columns.types #### A masked pattern was here #### - name default.values__tmp__table__3 - serialization.ddl struct values__tmp__table__3 { string tmp_values_col1, string tmp_values_col2} + name _dummy_database._dummy_table + serialization.ddl struct _dummy_table { } serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serialization.lib org.apache.hadoop.hive.serde2.NullStructSerDe + serde: org.apache.hadoop.hive.serde2.NullStructSerDe - input format: org.apache.hadoop.mapred.TextInputFormat + input format: org.apache.hadoop.hive.ql.io.NullRowsInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 column.name.delimiter , - columns tmp_values_col1,tmp_values_col2 + columns columns.comments - columns.types string:string + columns.types #### A masked pattern was here #### - name default.values__tmp__table__3 - serialization.ddl struct values__tmp__table__3 { string tmp_values_col1, string tmp_values_col2} + name _dummy_database._dummy_table + serialization.ddl struct _dummy_table { } serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.values__tmp__table__3 - name: default.values__tmp__table__3 + serialization.lib org.apache.hadoop.hive.serde2.NullStructSerDe + serde: org.apache.hadoop.hive.serde2.NullStructSerDe + name: _dummy_database._dummy_table + name: _dummy_database._dummy_table Truncated Path -> Alias: #### A masked pattern was here #### Needs Tagging: false @@ -530,17 +548,17 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 884 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 884 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 884 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -763,13 +781,15 @@ STAGE PLANS: PREHOOK: query: insert into table partitioned1 partition(part=1) values(2, 'original'), (3, 'original'),(4, 'original') PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table PREHOOK: Output: default@partitioned1@part=1 POSTHOOK: query: insert into table partitioned1 partition(part=1) values(2, 'original'), (3, 'original'),(4, 'original') POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table POSTHOOK: Output: default@partitioned1@part=1 -POSTHOOK: Lineage: partitioned1 PARTITION(part=1).a EXPRESSION [(values__tmp__table__4)values__tmp__table__4.FieldSchema(name:tmp_values_col1, type:string, comment:), ] -POSTHOOK: Lineage: partitioned1 PARTITION(part=1).b SIMPLE [(values__tmp__table__4)values__tmp__table__4.FieldSchema(name:tmp_values_col2, type:string, comment:), ] -_col0 _col1 +POSTHOOK: Lineage: partitioned1 PARTITION(part=1).a SCRIPT [] +POSTHOOK: Lineage: partitioned1 PARTITION(part=1).b SCRIPT [] +col1 col2 PREHOOK: query: explain insert into table partitioned1 partition(part=1) values(1, 'original'),(2, 'original'), (3, 'original'),(4, 'original') PREHOOK: type: QUERY POSTHOOK: query: explain insert into table partitioned1 partition(part=1) values(1, 'original'),(2, 'original'), (3, 'original'),(4, 'original') @@ -790,50 +810,58 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: values__tmp__table__5 - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + alias: _dummy_table + Row Limit Per Split: 1 + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: UDFToInteger(tmp_values_col1) (type: int), tmp_values_col2 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.partitioned1 - Select Operator - expressions: _col0 (type: int), _col1 (type: string), UDFToInteger('1') (type: int) - outputColumnNames: a, b, part - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: compute_stats(a, 'hll'), compute_stats(b, 'hll') - keys: part (type: int) - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) + expressions: array(const struct(1,'original'),const struct(2,'original'),const struct(3,'original'),const struct(4,'original')) (type: array<struct<col1:int,col2:string>>) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE + UDTF Operator + Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE + function name: inline + Select Operator + expressions: col1 (type: int), col2 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.partitioned1 + Select Operator + expressions: _col0 (type: int), _col1 (type: string), UDFToInteger('1') (type: int) + outputColumnNames: a, b, part + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(a, 'hll'), compute_stats(b, 'hll') + keys: part (type: int) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 868 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 1 Data size: 868 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) Reduce Operator Tree: Group By Operator aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 884 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 884 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 884 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat http://git-wip-us.apache.org/repos/asf/hive/blob/7e64114d/ql/src/test/results/clientpositive/avrotblsjoin.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/avrotblsjoin.q.out b/ql/src/test/results/clientpositive/avrotblsjoin.q.out index d0170a3..a686235 100644 --- a/ql/src/test/results/clientpositive/avrotblsjoin.q.out +++ b/ql/src/test/results/clientpositive/avrotblsjoin.q.out @@ -52,21 +52,25 @@ POSTHOOK: Output: database:default POSTHOOK: Output: default@table1_1 PREHOOK: query: insert into table1 values ("1", "2", "3") PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table PREHOOK: Output: default@table1 POSTHOOK: query: insert into table1 values ("1", "2", "3") POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table POSTHOOK: Output: default@table1 -POSTHOOK: Lineage: table1.col1 SIMPLE [(values__tmp__table__1)values__tmp__table__1.FieldSchema(name:tmp_values_col1, type:string, comment:), ] -POSTHOOK: Lineage: table1.col2 EXPRESSION [(values__tmp__table__1)values__tmp__table__1.FieldSchema(name:tmp_values_col2, type:string, comment:), ] -POSTHOOK: Lineage: table1.col3 SIMPLE [(values__tmp__table__1)values__tmp__table__1.FieldSchema(name:tmp_values_col3, type:string, comment:), ] +POSTHOOK: Lineage: table1.col1 SCRIPT [] +POSTHOOK: Lineage: table1.col2 SCRIPT [] +POSTHOOK: Lineage: table1.col3 SCRIPT [] PREHOOK: query: insert into table1_1 values (1, "2") PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table PREHOOK: Output: default@table1_1 POSTHOOK: query: insert into table1_1 values (1, "2") POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table POSTHOOK: Output: default@table1_1 -POSTHOOK: Lineage: table1_1.col1 EXPRESSION [(values__tmp__table__2)values__tmp__table__2.FieldSchema(name:tmp_values_col1, type:string, comment:), ] -POSTHOOK: Lineage: table1_1.col2 SIMPLE [(values__tmp__table__2)values__tmp__table__2.FieldSchema(name:tmp_values_col2, type:string, comment:), ] +POSTHOOK: Lineage: table1_1.col1 SCRIPT [] +POSTHOOK: Lineage: table1_1.col2 SCRIPT [] WARNING: Comparing a bigint and a string may result in a loss of precision. Warning: Shuffle Join JOIN[8][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: select table1.col1, table1_1.* from table1 join table1_1 on table1.col1=table1_1.col1 where table1_1.col1="1" http://git-wip-us.apache.org/repos/asf/hive/blob/7e64114d/ql/src/test/results/clientpositive/basicstat_partval.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/basicstat_partval.q.out b/ql/src/test/results/clientpositive/basicstat_partval.q.out index 1e46d58..ac75365 100644 --- a/ql/src/test/results/clientpositive/basicstat_partval.q.out +++ b/ql/src/test/results/clientpositive/basicstat_partval.q.out @@ -8,18 +8,22 @@ POSTHOOK: Output: database:default POSTHOOK: Output: default@p1 PREHOOK: query: insert into p1 partition(p='a') values (1) PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table PREHOOK: Output: default@p1@p=a POSTHOOK: query: insert into p1 partition(p='a') values (1) POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table POSTHOOK: Output: default@p1@p=a -POSTHOOK: Lineage: p1 PARTITION(p=a).i EXPRESSION [(values__tmp__table__1)values__tmp__table__1.FieldSchema(name:tmp_values_col1, type:string, comment:), ] +POSTHOOK: Lineage: p1 PARTITION(p=a).i SCRIPT [] PREHOOK: query: insert into p1 partition(p='A') values (2),(3) PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table PREHOOK: Output: default@p1@p=A POSTHOOK: query: insert into p1 partition(p='A') values (2),(3) POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table POSTHOOK: Output: default@p1@p=A -POSTHOOK: Lineage: p1 PARTITION(p=A).i EXPRESSION [(values__tmp__table__2)values__tmp__table__2.FieldSchema(name:tmp_values_col1, type:string, comment:), ] +POSTHOOK: Lineage: p1 PARTITION(p=A).i SCRIPT [] PREHOOK: query: describe formatted p1 PREHOOK: type: DESCTABLE PREHOOK: Input: default@p1 http://git-wip-us.apache.org/repos/asf/hive/blob/7e64114d/ql/src/test/results/clientpositive/beeline/mapjoin2.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/beeline/mapjoin2.q.out b/ql/src/test/results/clientpositive/beeline/mapjoin2.q.out index 7e70841..f178742 100644 --- a/ql/src/test/results/clientpositive/beeline/mapjoin2.q.out +++ b/ql/src/test/results/clientpositive/beeline/mapjoin2.q.out @@ -8,20 +8,24 @@ POSTHOOK: Output: database:default POSTHOOK: Output: default@tbl PREHOOK: query: insert into tbl values (1, 'one') PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table PREHOOK: Output: default@tbl POSTHOOK: query: insert into tbl values (1, 'one') POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table POSTHOOK: Output: default@tbl -POSTHOOK: Lineage: tbl.n EXPRESSION [(values__tmp__table__1)values__tmp__table__1.FieldSchema(name:tmp_values_col1, type:string, comment:), ] -POSTHOOK: Lineage: tbl.t SIMPLE [(values__tmp__table__1)values__tmp__table__1.FieldSchema(name:tmp_values_col2, type:string, comment:), ] +POSTHOOK: Lineage: tbl.n SCRIPT [] +POSTHOOK: Lineage: tbl.t SCRIPT [] PREHOOK: query: insert into tbl values(2, 'two') PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table PREHOOK: Output: default@tbl POSTHOOK: query: insert into tbl values(2, 'two') POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table POSTHOOK: Output: default@tbl -POSTHOOK: Lineage: tbl.n EXPRESSION [(values__tmp__table__2)values__tmp__table__2.FieldSchema(name:tmp_values_col1, type:string, comment:), ] -POSTHOOK: Lineage: tbl.t SIMPLE [(values__tmp__table__2)values__tmp__table__2.FieldSchema(name:tmp_values_col2, type:string, comment:), ] +POSTHOOK: Lineage: tbl.n SCRIPT [] +POSTHOOK: Lineage: tbl.t SCRIPT [] Warning: Map Join MAPJOIN[13][bigTable=?] in task 'Stage-3:MAPRED' is a cross product PREHOOK: query: select a.n, a.t, isnull(b.n), isnull(b.t) from (select * from tbl where n = 1) a left outer join (select * from tbl where 1 = 2) b on a.n = b.n PREHOOK: type: QUERY http://git-wip-us.apache.org/repos/asf/hive/blob/7e64114d/ql/src/test/results/clientpositive/beeline/materialized_view_create_rewrite.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/beeline/materialized_view_create_rewrite.q.out b/ql/src/test/results/clientpositive/beeline/materialized_view_create_rewrite.q.out index 5541aeb..15c51e1 100644 --- a/ql/src/test/results/clientpositive/beeline/materialized_view_create_rewrite.q.out +++ b/ql/src/test/results/clientpositive/beeline/materialized_view_create_rewrite.q.out @@ -13,6 +13,7 @@ PREHOOK: query: insert into cmv_basetable values (3, 'calvin', 978.76, 3), (3, 'charlie', 9.8, 1) PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table PREHOOK: Output: default@cmv_basetable POSTHOOK: query: insert into cmv_basetable values (1, 'alfred', 10.30, 2), @@ -21,11 +22,12 @@ POSTHOOK: query: insert into cmv_basetable values (3, 'calvin', 978.76, 3), (3, 'charlie', 9.8, 1) POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table POSTHOOK: Output: default@cmv_basetable -POSTHOOK: Lineage: cmv_basetable.a EXPRESSION [(values__tmp__table__1)values__tmp__table__1.FieldSchema(name:tmp_values_col1, type:string, comment:), ] -POSTHOOK: Lineage: cmv_basetable.b EXPRESSION [(values__tmp__table__1)values__tmp__table__1.FieldSchema(name:tmp_values_col2, type:string, comment:), ] -POSTHOOK: Lineage: cmv_basetable.c EXPRESSION [(values__tmp__table__1)values__tmp__table__1.FieldSchema(name:tmp_values_col3, type:string, comment:), ] -POSTHOOK: Lineage: cmv_basetable.d EXPRESSION [(values__tmp__table__1)values__tmp__table__1.FieldSchema(name:tmp_values_col4, type:string, comment:), ] +POSTHOOK: Lineage: cmv_basetable.a SCRIPT [] +POSTHOOK: Lineage: cmv_basetable.b SCRIPT [] +POSTHOOK: Lineage: cmv_basetable.c SCRIPT [] +POSTHOOK: Lineage: cmv_basetable.d SCRIPT [] PREHOOK: query: analyze table cmv_basetable compute statistics for columns PREHOOK: type: QUERY PREHOOK: Input: default@cmv_basetable http://git-wip-us.apache.org/repos/asf/hive/blob/7e64114d/ql/src/test/results/clientpositive/bucket_num_reducers_acid.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/bucket_num_reducers_acid.q.out b/ql/src/test/results/clientpositive/bucket_num_reducers_acid.q.out index 8ea23d7..81ba5ae 100644 --- a/ql/src/test/results/clientpositive/bucket_num_reducers_acid.q.out +++ b/ql/src/test/results/clientpositive/bucket_num_reducers_acid.q.out @@ -12,9 +12,11 @@ POSTHOOK: Output: database:default POSTHOOK: Output: default@bucket_nr_acid PREHOOK: query: insert into bucket_nr_acid values(1,1) PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table PREHOOK: Output: default@bucket_nr_acid PREHOOK: query: insert into bucket_nr_acid values(0,0),(3,3) PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table PREHOOK: Output: default@bucket_nr_acid PREHOOK: query: update bucket_nr_acid set b = -1 PREHOOK: type: QUERY http://git-wip-us.apache.org/repos/asf/hive/blob/7e64114d/ql/src/test/results/clientpositive/bucket_num_reducers_acid2.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/bucket_num_reducers_acid2.q.out b/ql/src/test/results/clientpositive/bucket_num_reducers_acid2.q.out index cabb4f7..94a2884 100644 --- a/ql/src/test/results/clientpositive/bucket_num_reducers_acid2.q.out +++ b/ql/src/test/results/clientpositive/bucket_num_reducers_acid2.q.out @@ -12,15 +12,19 @@ POSTHOOK: Output: database:default POSTHOOK: Output: default@bucket_nr_acid2 PREHOOK: query: insert into bucket_nr_acid2 values(0,1),(1,1) PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table PREHOOK: Output: default@bucket_nr_acid2 PREHOOK: query: insert into bucket_nr_acid2 values(2,2),(3,2) PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table PREHOOK: Output: default@bucket_nr_acid2 PREHOOK: query: insert into bucket_nr_acid2 values(0,3),(1,3) PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table PREHOOK: Output: default@bucket_nr_acid2 PREHOOK: query: insert into bucket_nr_acid2 values(2,4),(3,4) PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table PREHOOK: Output: default@bucket_nr_acid2 PREHOOK: query: update bucket_nr_acid2 set b = -1 PREHOOK: type: QUERY http://git-wip-us.apache.org/repos/asf/hive/blob/7e64114d/ql/src/test/results/clientpositive/cbo_rp_insert.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/cbo_rp_insert.q.out b/ql/src/test/results/clientpositive/cbo_rp_insert.q.out deleted file mode 100644 index fde7915..0000000 --- a/ql/src/test/results/clientpositive/cbo_rp_insert.q.out +++ /dev/null @@ -1,83 +0,0 @@ -PREHOOK: query: drop database if exists x314 cascade -PREHOOK: type: DROPDATABASE -POSTHOOK: query: drop database if exists x314 cascade -POSTHOOK: type: DROPDATABASE -PREHOOK: query: create database x314 -PREHOOK: type: CREATEDATABASE -PREHOOK: Output: database:x314 -POSTHOOK: query: create database x314 -POSTHOOK: type: CREATEDATABASE -POSTHOOK: Output: database:x314 -PREHOOK: query: use x314 -PREHOOK: type: SWITCHDATABASE -PREHOOK: Input: database:x314 -POSTHOOK: query: use x314 -POSTHOOK: type: SWITCHDATABASE -POSTHOOK: Input: database:x314 -PREHOOK: query: create table source(s1 int, s2 int) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:x314 -PREHOOK: Output: x314@source -POSTHOOK: query: create table source(s1 int, s2 int) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:x314 -POSTHOOK: Output: x314@source -PREHOOK: query: create table target1(x int, y int, z int) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:x314 -PREHOOK: Output: x314@target1 -POSTHOOK: query: create table target1(x int, y int, z int) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:x314 -POSTHOOK: Output: x314@target1 -PREHOOK: query: insert into source(s2,s1) values(2,1) -PREHOOK: type: QUERY -PREHOOK: Output: x314@source -POSTHOOK: query: insert into source(s2,s1) values(2,1) -POSTHOOK: type: QUERY -POSTHOOK: Output: x314@source -POSTHOOK: Lineage: source.s1 EXPRESSION [(values__tmp__table__1)values__tmp__table__1.FieldSchema(name:tmp_values_col2, type:string, comment:), ] -POSTHOOK: Lineage: source.s2 EXPRESSION [(values__tmp__table__1)values__tmp__table__1.FieldSchema(name:tmp_values_col1, type:string, comment:), ] -PREHOOK: query: select * from source -PREHOOK: type: QUERY -PREHOOK: Input: x314@source -#### A masked pattern was here #### -POSTHOOK: query: select * from source -POSTHOOK: type: QUERY -POSTHOOK: Input: x314@source -#### A masked pattern was here #### -1 2 -PREHOOK: query: insert into target1(z,x) select * from source -PREHOOK: type: QUERY -PREHOOK: Input: x314@source -PREHOOK: Output: x314@target1 -POSTHOOK: query: insert into target1(z,x) select * from source -POSTHOOK: type: QUERY -POSTHOOK: Input: x314@source -POSTHOOK: Output: x314@target1 -POSTHOOK: Lineage: target1.x SIMPLE [(source)source.FieldSchema(name:s2, type:int, comment:null), ] -POSTHOOK: Lineage: target1.y SIMPLE [] -POSTHOOK: Lineage: target1.z SIMPLE [(source)source.FieldSchema(name:s1, type:int, comment:null), ] -PREHOOK: query: select * from target1 -PREHOOK: type: QUERY -PREHOOK: Input: x314@target1 -#### A masked pattern was here #### -POSTHOOK: query: select * from target1 -POSTHOOK: type: QUERY -POSTHOOK: Input: x314@target1 -#### A masked pattern was here #### -2 NULL 1 -PREHOOK: query: drop database if exists x314 cascade -PREHOOK: type: DROPDATABASE -PREHOOK: Input: database:x314 -PREHOOK: Output: database:x314 -PREHOOK: Output: x314@source -PREHOOK: Output: x314@target1 -PREHOOK: Output: x314@values__tmp__table__1 -POSTHOOK: query: drop database if exists x314 cascade -POSTHOOK: type: DROPDATABASE -POSTHOOK: Input: database:x314 -POSTHOOK: Output: database:x314 -POSTHOOK: Output: x314@source -POSTHOOK: Output: x314@target1 -POSTHOOK: Output: x314@values__tmp__table__1 http://git-wip-us.apache.org/repos/asf/hive/blob/7e64114d/ql/src/test/results/clientpositive/cmdwithcomments.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/cmdwithcomments.q.out b/ql/src/test/results/clientpositive/cmdwithcomments.q.out index 151a82c..a05522a 100644 --- a/ql/src/test/results/clientpositive/cmdwithcomments.q.out +++ b/ql/src/test/results/clientpositive/cmdwithcomments.q.out @@ -11,21 +11,25 @@ POSTHOOK: Output: default@numt PREHOOK: query: --comment2 insert into numt values(1) PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table PREHOOK: Output: default@numt POSTHOOK: query: --comment2 insert into numt values(1) POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table POSTHOOK: Output: default@numt -POSTHOOK: Lineage: numt.idx EXPRESSION [(values__tmp__table__1)values__tmp__table__1.FieldSchema(name:tmp_values_col1, type:string, comment:), ] +POSTHOOK: Lineage: numt.idx SCRIPT [] PREHOOK: query: --comment3 insert into numt values(2) PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table PREHOOK: Output: default@numt POSTHOOK: query: --comment3 insert into numt values(2) POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table POSTHOOK: Output: default@numt -POSTHOOK: Lineage: numt.idx EXPRESSION [(values__tmp__table__2)values__tmp__table__2.FieldSchema(name:tmp_values_col1, type:string, comment:), ] +POSTHOOK: Lineage: numt.idx SCRIPT [] PREHOOK: query: select idx from numt where --comment5 idx = 1 PREHOOK: type: QUERY http://git-wip-us.apache.org/repos/asf/hive/blob/7e64114d/ql/src/test/results/clientpositive/columnStatsUpdateForStatsOptimizer_2.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/columnStatsUpdateForStatsOptimizer_2.q.out b/ql/src/test/results/clientpositive/columnStatsUpdateForStatsOptimizer_2.q.out index ee0da96..1a4cf73 100644 --- a/ql/src/test/results/clientpositive/columnStatsUpdateForStatsOptimizer_2.q.out +++ b/ql/src/test/results/clientpositive/columnStatsUpdateForStatsOptimizer_2.q.out @@ -12,12 +12,14 @@ POSTHOOK: Output: database:default POSTHOOK: Output: default@calendar PREHOOK: query: insert into calendar values (2010, 10), (2011, 11), (2012, 12) PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table PREHOOK: Output: default@calendar POSTHOOK: query: insert into calendar values (2010, 10), (2011, 11), (2012, 12) POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table POSTHOOK: Output: default@calendar -POSTHOOK: Lineage: calendar.month EXPRESSION [(values__tmp__table__1)values__tmp__table__1.FieldSchema(name:tmp_values_col2, type:string, comment:), ] -POSTHOOK: Lineage: calendar.year EXPRESSION [(values__tmp__table__1)values__tmp__table__1.FieldSchema(name:tmp_values_col1, type:string, comment:), ] +POSTHOOK: Lineage: calendar.month SCRIPT [] +POSTHOOK: Lineage: calendar.year SCRIPT [] PREHOOK: query: desc formatted calendar PREHOOK: type: DESCTABLE PREHOOK: Input: default@calendar http://git-wip-us.apache.org/repos/asf/hive/blob/7e64114d/ql/src/test/results/clientpositive/column_names_with_leading_and_trailing_spaces.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/column_names_with_leading_and_trailing_spaces.q.out b/ql/src/test/results/clientpositive/column_names_with_leading_and_trailing_spaces.q.out index 2b87d50..b327bf8 100644 --- a/ql/src/test/results/clientpositive/column_names_with_leading_and_trailing_spaces.q.out +++ b/ql/src/test/results/clientpositive/column_names_with_leading_and_trailing_spaces.q.out @@ -62,13 +62,15 @@ comment from deserializer COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\" left\":\"true\",\" middle \":\"true\",\"right \":\"true\"}} PREHOOK: query: insert into space values ("1", "2", "3") PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table PREHOOK: Output: default@space POSTHOOK: query: insert into space values ("1", "2", "3") POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table POSTHOOK: Output: default@space -POSTHOOK: Lineage: space. left SIMPLE [(values__tmp__table__1)values__tmp__table__1.FieldSchema(name:tmp_values_col1, type:string, comment:), ] -POSTHOOK: Lineage: space. middle SIMPLE [(values__tmp__table__1)values__tmp__table__1.FieldSchema(name:tmp_values_col2, type:string, comment:), ] -POSTHOOK: Lineage: space.right SIMPLE [(values__tmp__table__1)values__tmp__table__1.FieldSchema(name:tmp_values_col3, type:string, comment:), ] +POSTHOOK: Lineage: space. left SCRIPT [] +POSTHOOK: Lineage: space. middle SCRIPT [] +POSTHOOK: Lineage: space.right SCRIPT [] PREHOOK: query: desc formatted space ` left` PREHOOK: type: DESCTABLE PREHOOK: Input: default@space @@ -99,12 +101,14 @@ POSTHOOK: Input: default@space 1 2 3 PREHOOK: query: insert into space (` middle `) values("2") PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table PREHOOK: Output: default@space POSTHOOK: query: insert into space (` middle `) values("2") POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table POSTHOOK: Output: default@space POSTHOOK: Lineage: space. left SIMPLE [] -POSTHOOK: Lineage: space. middle SIMPLE [(values__tmp__table__2)values__tmp__table__2.FieldSchema(name:tmp_values_col1, type:string, comment:), ] +POSTHOOK: Lineage: space. middle SCRIPT [] POSTHOOK: Lineage: space.right SIMPLE [] PREHOOK: query: select * from space order by ` left` PREHOOK: type: QUERY http://git-wip-us.apache.org/repos/asf/hive/blob/7e64114d/ql/src/test/results/clientpositive/comma_in_column_name.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/comma_in_column_name.q.out b/ql/src/test/results/clientpositive/comma_in_column_name.q.out index f8e319d..43357c0 100644 --- a/ql/src/test/results/clientpositive/comma_in_column_name.q.out +++ b/ql/src/test/results/clientpositive/comma_in_column_name.q.out @@ -8,11 +8,13 @@ POSTHOOK: Output: database:default POSTHOOK: Output: default@test PREHOOK: query: insert into test values (1),(2) PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table PREHOOK: Output: default@test POSTHOOK: query: insert into test values (1),(2) POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table POSTHOOK: Output: default@test -POSTHOOK: Lineage: test.x,y EXPRESSION [(values__tmp__table__1)values__tmp__table__1.FieldSchema(name:tmp_values_col1, type:string, comment:), ] +POSTHOOK: Lineage: test.x,y SCRIPT [] PREHOOK: query: select `x,y` from test where `x,y` >=2 PREHOOK: type: QUERY PREHOOK: Input: default@test @@ -40,11 +42,13 @@ POSTHOOK: Output: database:default POSTHOOK: Output: default@test PREHOOK: query: insert into test values (1),(2) PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table PREHOOK: Output: default@test POSTHOOK: query: insert into test values (1),(2) POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table POSTHOOK: Output: default@test -POSTHOOK: Lineage: test.x,y EXPRESSION [(values__tmp__table__2)values__tmp__table__2.FieldSchema(name:tmp_values_col1, type:string, comment:), ] +POSTHOOK: Lineage: test.x,y SCRIPT [] PREHOOK: query: select `x,y` from test where `x,y` <2 PREHOOK: type: QUERY PREHOOK: Input: default@test http://git-wip-us.apache.org/repos/asf/hive/blob/7e64114d/ql/src/test/results/clientpositive/concat_op.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/concat_op.q.out b/ql/src/test/results/clientpositive/concat_op.q.out index 33c84f9..e260518 100644 --- a/ql/src/test/results/clientpositive/concat_op.q.out +++ b/ql/src/test/results/clientpositive/concat_op.q.out @@ -148,18 +148,22 @@ POSTHOOK: Output: database:default POSTHOOK: Output: default@ct2 PREHOOK: query: insert into ct1 values (7),(5),(3),(1) PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table PREHOOK: Output: default@ct1 POSTHOOK: query: insert into ct1 values (7),(5),(3),(1) POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table POSTHOOK: Output: default@ct1 -POSTHOOK: Lineage: ct1.c EXPRESSION [(values__tmp__table__1)values__tmp__table__1.FieldSchema(name:tmp_values_col1, type:string, comment:), ] +POSTHOOK: Lineage: ct1.c SCRIPT [] PREHOOK: query: insert into ct2 values (8),(6),(4),(2) PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table PREHOOK: Output: default@ct2 POSTHOOK: query: insert into ct2 values (8),(6),(4),(2) POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table POSTHOOK: Output: default@ct2 -POSTHOOK: Lineage: ct2.c EXPRESSION [(values__tmp__table__2)values__tmp__table__2.FieldSchema(name:tmp_values_col1, type:string, comment:), ] +POSTHOOK: Lineage: ct2.c SCRIPT [] PREHOOK: query: create view ct_v1 as select * from ct1 union all select * from ct2 PREHOOK: type: CREATEVIEW PREHOOK: Input: default@ct1 http://git-wip-us.apache.org/repos/asf/hive/blob/7e64114d/ql/src/test/results/clientpositive/constantPropWhen.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/constantPropWhen.q.out b/ql/src/test/results/clientpositive/constantPropWhen.q.out index 4f4bf80..c03a824 100644 --- a/ql/src/test/results/clientpositive/constantPropWhen.q.out +++ b/ql/src/test/results/clientpositive/constantPropWhen.q.out @@ -12,12 +12,14 @@ POSTHOOK: Output: database:default POSTHOOK: Output: default@test_1 PREHOOK: query: insert into table test_1 values (123, NULL), (NULL, NULL), (NULL, 123), (123, 123) PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table PREHOOK: Output: default@test_1 POSTHOOK: query: insert into table test_1 values (123, NULL), (NULL, NULL), (NULL, 123), (123, 123) POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table POSTHOOK: Output: default@test_1 -POSTHOOK: Lineage: test_1.id EXPRESSION [(values__tmp__table__1)values__tmp__table__1.FieldSchema(name:tmp_values_col1, type:string, comment:), ] -POSTHOOK: Lineage: test_1.id2 EXPRESSION [(values__tmp__table__1)values__tmp__table__1.FieldSchema(name:tmp_values_col2, type:string, comment:), ] +POSTHOOK: Lineage: test_1.id SCRIPT [] +POSTHOOK: Lineage: test_1.id2 SCRIPT [] PREHOOK: query: explain SELECT cast(CASE WHEN id = id2 THEN FALSE ELSE TRUE END AS BOOLEAN) AS b FROM test_1 PREHOOK: type: QUERY POSTHOOK: query: explain SELECT cast(CASE WHEN id = id2 THEN FALSE ELSE TRUE END AS BOOLEAN) AS b FROM test_1 http://git-wip-us.apache.org/repos/asf/hive/blob/7e64114d/ql/src/test/results/clientpositive/constantfolding.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/constantfolding.q.out b/ql/src/test/results/clientpositive/constantfolding.q.out index f9a9d24..c4fce25 100644 --- a/ql/src/test/results/clientpositive/constantfolding.q.out +++ b/ql/src/test/results/clientpositive/constantfolding.q.out @@ -60,34 +60,42 @@ POSTHOOK: Output: database:default POSTHOOK: Output: default@union_all_bug_test_2 PREHOOK: query: insert into table union_all_bug_test_1 values (1,1) PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table PREHOOK: Output: default@union_all_bug_test_1 POSTHOOK: query: insert into table union_all_bug_test_1 values (1,1) POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table POSTHOOK: Output: default@union_all_bug_test_1 -POSTHOOK: Lineage: union_all_bug_test_1.f1 EXPRESSION [(values__tmp__table__1)values__tmp__table__1.FieldSchema(name:tmp_values_col1, type:string, comment:), ] -POSTHOOK: Lineage: union_all_bug_test_1.f2 EXPRESSION [(values__tmp__table__1)values__tmp__table__1.FieldSchema(name:tmp_values_col2, type:string, comment:), ] +POSTHOOK: Lineage: union_all_bug_test_1.f1 SCRIPT [] +POSTHOOK: Lineage: union_all_bug_test_1.f2 SCRIPT [] PREHOOK: query: insert into table union_all_bug_test_2 values (1) PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table PREHOOK: Output: default@union_all_bug_test_2 POSTHOOK: query: insert into table union_all_bug_test_2 values (1) POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table POSTHOOK: Output: default@union_all_bug_test_2 -POSTHOOK: Lineage: union_all_bug_test_2.f1 EXPRESSION [(values__tmp__table__2)values__tmp__table__2.FieldSchema(name:tmp_values_col1, type:string, comment:), ] +POSTHOOK: Lineage: union_all_bug_test_2.f1 SCRIPT [] PREHOOK: query: insert into table union_all_bug_test_1 values (0,0) PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table PREHOOK: Output: default@union_all_bug_test_1 POSTHOOK: query: insert into table union_all_bug_test_1 values (0,0) POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table POSTHOOK: Output: default@union_all_bug_test_1 -POSTHOOK: Lineage: union_all_bug_test_1.f1 EXPRESSION [(values__tmp__table__3)values__tmp__table__3.FieldSchema(name:tmp_values_col1, type:string, comment:), ] -POSTHOOK: Lineage: union_all_bug_test_1.f2 EXPRESSION [(values__tmp__table__3)values__tmp__table__3.FieldSchema(name:tmp_values_col2, type:string, comment:), ] +POSTHOOK: Lineage: union_all_bug_test_1.f1 SCRIPT [] +POSTHOOK: Lineage: union_all_bug_test_1.f2 SCRIPT [] PREHOOK: query: insert into table union_all_bug_test_2 values (0) PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table PREHOOK: Output: default@union_all_bug_test_2 POSTHOOK: query: insert into table union_all_bug_test_2 values (0) POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table POSTHOOK: Output: default@union_all_bug_test_2 -POSTHOOK: Lineage: union_all_bug_test_2.f1 EXPRESSION [(values__tmp__table__4)values__tmp__table__4.FieldSchema(name:tmp_values_col1, type:string, comment:), ] +POSTHOOK: Lineage: union_all_bug_test_2.f1 SCRIPT [] PREHOOK: query: SELECT f1 FROM ( http://git-wip-us.apache.org/repos/asf/hive/blob/7e64114d/ql/src/test/results/clientpositive/cte_5.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/cte_5.q.out b/ql/src/test/results/clientpositive/cte_5.q.out index 3d7b324..1c7812e 100644 --- a/ql/src/test/results/clientpositive/cte_5.q.out +++ b/ql/src/test/results/clientpositive/cte_5.q.out @@ -20,12 +20,14 @@ POSTHOOK: Output: database:mydb POSTHOOK: Output: mydb@q1 PREHOOK: query: insert into q1 values (5, 'A') PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table PREHOOK: Output: mydb@q1 POSTHOOK: query: insert into q1 values (5, 'A') POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table POSTHOOK: Output: mydb@q1 -POSTHOOK: Lineage: q1.colnum EXPRESSION [(values__tmp__table__1)values__tmp__table__1.FieldSchema(name:tmp_values_col1, type:string, comment:), ] -POSTHOOK: Lineage: q1.colstring SIMPLE [(values__tmp__table__1)values__tmp__table__1.FieldSchema(name:tmp_values_col2, type:string, comment:), ] +POSTHOOK: Lineage: q1.colnum SCRIPT [] +POSTHOOK: Lineage: q1.colstring SCRIPT [] PREHOOK: query: use default PREHOOK: type: SWITCHDATABASE PREHOOK: Input: database:default @@ -39,7 +41,6 @@ POSTHOOK: query: show tables in mydb POSTHOOK: type: SHOWTABLES POSTHOOK: Input: database:mydb q1 -values__tmp__table__1 PREHOOK: query: show tables PREHOOK: type: SHOWTABLES PREHOOK: Input: database:default http://git-wip-us.apache.org/repos/asf/hive/blob/7e64114d/ql/src/test/results/clientpositive/cte_7.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/cte_7.q.out b/ql/src/test/results/clientpositive/cte_7.q.out index 54b6841..6f82dd4 100644 --- a/ql/src/test/results/clientpositive/cte_7.q.out +++ b/ql/src/test/results/clientpositive/cte_7.q.out @@ -8,13 +8,15 @@ POSTHOOK: Output: database:default POSTHOOK: Output: default@t PREHOOK: query: insert into t values (1,'hello','world'),(2,'bye',null) PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table PREHOOK: Output: default@t POSTHOOK: query: insert into t values (1,'hello','world'),(2,'bye',null) POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table POSTHOOK: Output: default@t -POSTHOOK: Lineage: t.a SIMPLE [(values__tmp__table__1)values__tmp__table__1.FieldSchema(name:tmp_values_col2, type:string, comment:), ] -POSTHOOK: Lineage: t.b SIMPLE [(values__tmp__table__1)values__tmp__table__1.FieldSchema(name:tmp_values_col3, type:string, comment:), ] -POSTHOOK: Lineage: t.i EXPRESSION [(values__tmp__table__1)values__tmp__table__1.FieldSchema(name:tmp_values_col1, type:string, comment:), ] +POSTHOOK: Lineage: t.a SCRIPT [] +POSTHOOK: Lineage: t.b SCRIPT [] +POSTHOOK: Lineage: t.i SCRIPT [] PREHOOK: query: select * from t where t.b is null PREHOOK: type: QUERY PREHOOK: Input: default@t