HIVE-9644 : CASE comparison operator rotation optimization (Ashutosh Chauhan via Gopal V)
Signed-off-by: Ashutosh Chauhan <hashut...@apache.org> Project: http://git-wip-us.apache.org/repos/asf/hive/repo Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/48a243ef Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/48a243ef Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/48a243ef Branch: refs/heads/beeline-cli Commit: 48a243efdf91a7f5334b28810b30fc8d82925d51 Parents: d434f64 Author: Ashutosh Chauhan <hashut...@apache.org> Authored: Sat May 2 13:17:47 2015 -0700 Committer: Ashutosh Chauhan <hashut...@apache.org> Committed: Thu May 7 10:27:35 2015 -0700 ---------------------------------------------------------------------- .../optimizer/ConstantPropagateProcFactory.java | 83 +++- ql/src/test/queries/clientpositive/fold_case.q | 12 + ql/src/test/queries/clientpositive/fold_when.q | 31 ++ .../test/results/clientpositive/fold_case.q.out | 301 ++++++++++++ .../test/results/clientpositive/fold_when.q.out | 480 +++++++++++++++++++ .../ql_rewrite_gbtoidx_cbo_2.q.out | 14 +- 6 files changed, 912 insertions(+), 9 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/hive/blob/48a243ef/ql/src/java/org/apache/hadoop/hive/ql/optimizer/ConstantPropagateProcFactory.java ---------------------------------------------------------------------- diff --git a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/ConstantPropagateProcFactory.java b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/ConstantPropagateProcFactory.java index e9436e5..f536ef6 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/ConstantPropagateProcFactory.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/ConstantPropagateProcFactory.java @@ -42,6 +42,7 @@ import org.apache.hadoop.hive.ql.exec.RowSchema; import org.apache.hadoop.hive.ql.exec.SelectOperator; import org.apache.hadoop.hive.ql.exec.TableScanOperator; import org.apache.hadoop.hive.ql.exec.UDF; +import org.apache.hadoop.hive.ql.exec.UDFArgumentException; import org.apache.hadoop.hive.ql.exec.Utilities; import org.apache.hadoop.hive.ql.lib.Node; import org.apache.hadoop.hive.ql.lib.NodeProcessor; @@ -65,11 +66,15 @@ import org.apache.hadoop.hive.ql.udf.generic.GenericUDF; import org.apache.hadoop.hive.ql.udf.generic.GenericUDF.DeferredJavaObject; import org.apache.hadoop.hive.ql.udf.generic.GenericUDFBaseCompare; import org.apache.hadoop.hive.ql.udf.generic.GenericUDFBridge; +import org.apache.hadoop.hive.ql.udf.generic.GenericUDFCase; import org.apache.hadoop.hive.ql.udf.generic.GenericUDFOPAnd; import org.apache.hadoop.hive.ql.udf.generic.GenericUDFOPEqual; +import org.apache.hadoop.hive.ql.udf.generic.GenericUDFOPNot; +import org.apache.hadoop.hive.ql.udf.generic.GenericUDFOPNotEqual; import org.apache.hadoop.hive.ql.udf.generic.GenericUDFOPNotNull; import org.apache.hadoop.hive.ql.udf.generic.GenericUDFOPNull; import org.apache.hadoop.hive.ql.udf.generic.GenericUDFOPOr; +import org.apache.hadoop.hive.ql.udf.generic.GenericUDFWhen; import org.apache.hadoop.hive.serde.serdeConstants; import org.apache.hadoop.hive.serde2.objectinspector.ObjectInspector; import org.apache.hadoop.hive.serde2.objectinspector.ObjectInspectorConverters; @@ -79,9 +84,11 @@ import org.apache.hadoop.hive.serde2.objectinspector.PrimitiveObjectInspector; import org.apache.hadoop.hive.serde2.objectinspector.PrimitiveObjectInspector.PrimitiveCategory; import org.apache.hadoop.hive.serde2.objectinspector.primitive.PrimitiveObjectInspectorFactory; import org.apache.hadoop.hive.serde2.objectinspector.primitive.PrimitiveObjectInspectorUtils; +import org.apache.hadoop.hive.serde2.objectinspector.primitive.WritableConstantBooleanObjectInspector; import org.apache.hadoop.hive.serde2.typeinfo.PrimitiveTypeInfo; import org.apache.hadoop.hive.serde2.typeinfo.TypeInfo; import org.apache.hadoop.hive.serde2.typeinfo.TypeInfoUtils; +import org.apache.hadoop.io.BooleanWritable; import com.google.common.collect.ImmutableSet; @@ -199,10 +206,11 @@ public final class ConstantPropagateProcFactory { * @param op processing operator * @param propagate if true, assignment expressions will be added to constants. * @return fold expression + * @throws UDFArgumentException */ private static ExprNodeDesc foldExpr(ExprNodeDesc desc, Map<ColumnInfo, ExprNodeDesc> constants, ConstantPropagateProcCtx cppCtx, Operator<? extends Serializable> op, int tag, - boolean propagate) { + boolean propagate) throws UDFArgumentException { if (desc instanceof ExprNodeGenericFuncDesc) { ExprNodeGenericFuncDesc funcDesc = (ExprNodeGenericFuncDesc) desc; @@ -356,7 +364,7 @@ public final class ConstantPropagateProcFactory { return (expr instanceof ExprNodeColumnDesc) ? (ExprNodeColumnDesc)expr : null; } - private static ExprNodeDesc shortcutFunction(GenericUDF udf, List<ExprNodeDesc> newExprs) { + private static ExprNodeDesc shortcutFunction(GenericUDF udf, List<ExprNodeDesc> newExprs) throws UDFArgumentException { if (udf instanceof GenericUDFOPAnd) { for (int i = 0; i < 2; i++) { ExprNodeDesc childExpr = newExprs.get(i); @@ -407,6 +415,77 @@ public final class ConstantPropagateProcFactory { } } + if (udf instanceof GenericUDFWhen) { + if (!(newExprs.size() == 2 || newExprs.size() == 3)) { + // In general, when can have unlimited # of branches, + // we currently only handle either 1 or 2 branch. + return null; + } + ExprNodeDesc thenExpr = newExprs.get(1); + if (thenExpr instanceof ExprNodeNullDesc && (newExprs.size() == 2 || newExprs.get(2) instanceof ExprNodeNullDesc)) { + return thenExpr; + } + ExprNodeDesc elseExpr = newExprs.size() == 3 ? newExprs.get(2) : + new ExprNodeConstantDesc(newExprs.get(2).getTypeInfo(),null); + + ExprNodeDesc whenExpr = newExprs.get(0); + if (whenExpr instanceof ExprNodeConstantDesc) { + Boolean whenVal = (Boolean)((ExprNodeConstantDesc) whenExpr).getValue(); + return (whenVal == null || Boolean.FALSE.equals(whenVal)) ? elseExpr : thenExpr; + } + + if (thenExpr instanceof ExprNodeConstantDesc && elseExpr instanceof ExprNodeConstantDesc) { + ExprNodeConstantDesc constThen = (ExprNodeConstantDesc) thenExpr; + ExprNodeConstantDesc constElse = (ExprNodeConstantDesc) elseExpr; + Object thenVal = constThen.getValue(); + Object elseVal = constElse.getValue(); + if (thenVal == null) { + return elseVal == null ? thenExpr : null; + } else if(thenVal.equals(elseVal)){ + return thenExpr; + } else if (thenVal instanceof Boolean && elseVal instanceof Boolean) { + return Boolean.TRUE.equals(thenVal) ? newExprs.get(0) : + ExprNodeGenericFuncDesc.newInstance(new GenericUDFOPNot(), newExprs.subList(0, 1)); + } else { + return null; + } + } + } + if (udf instanceof GenericUDFCase) { + // HIVE-9644 Attempt to fold expression like : + // where (case ss_sold_date when '1998-01-01' then 1=1 else null=1 end); + // where ss_sold_date= '1998-01-01' ; + if (!(newExprs.size() == 3 || newExprs.size() == 4)) { + // In general case can have unlimited # of branches, + // we currently only handle either 1 or 2 branch. + return null; + } + ExprNodeDesc thenExpr = newExprs.get(2); + if (thenExpr instanceof ExprNodeNullDesc && (newExprs.size() == 3 || newExprs.get(3) instanceof ExprNodeNullDesc)) { + return thenExpr; + } + + ExprNodeDesc elseExpr = newExprs.size() == 4 ? newExprs.get(3) : + new ExprNodeConstantDesc(newExprs.get(2).getTypeInfo(),null); + + if (thenExpr instanceof ExprNodeConstantDesc && elseExpr instanceof ExprNodeConstantDesc) { + ExprNodeConstantDesc constThen = (ExprNodeConstantDesc) thenExpr; + ExprNodeConstantDesc constElse = (ExprNodeConstantDesc) elseExpr; + Object thenVal = constThen.getValue(); + Object elseVal = constElse.getValue(); + if (thenVal == null) { + return elseVal == null ? thenExpr : null; + } else if(thenVal.equals(elseVal)){ + return thenExpr; + } else if (thenVal instanceof Boolean && elseVal instanceof Boolean) { + return Boolean.TRUE.equals(thenVal) ? ExprNodeGenericFuncDesc.newInstance(new GenericUDFOPEqual(), newExprs.subList(0, 2)) : + ExprNodeGenericFuncDesc.newInstance(new GenericUDFOPNotEqual(), newExprs.subList(0, 2)); + } else { + return null; + } + } + } + return null; } http://git-wip-us.apache.org/repos/asf/hive/blob/48a243ef/ql/src/test/queries/clientpositive/fold_case.q ---------------------------------------------------------------------- diff --git a/ql/src/test/queries/clientpositive/fold_case.q b/ql/src/test/queries/clientpositive/fold_case.q new file mode 100644 index 0000000..3f9e3a3 --- /dev/null +++ b/ql/src/test/queries/clientpositive/fold_case.q @@ -0,0 +1,12 @@ +explain +select count(1) from src where (case key when '238' then true else false end); +explain +select count(1) from src where (case key when '238' then 1=2 else 1=1 end); +explain +select count(1) from src where (case key when '238' then 1=2 else 1=31 end); +explain +select count(1) from src where (case key when '238' then true else 1=1 end); +explain +select count(1) from src where (case key when '238' then 1=1 else 1=null end); +explain +select count(1) from src where (case key when '238' then null else 1=1 end); http://git-wip-us.apache.org/repos/asf/hive/blob/48a243ef/ql/src/test/queries/clientpositive/fold_when.q ---------------------------------------------------------------------- diff --git a/ql/src/test/queries/clientpositive/fold_when.q b/ql/src/test/queries/clientpositive/fold_when.q new file mode 100644 index 0000000..e827a5c --- /dev/null +++ b/ql/src/test/queries/clientpositive/fold_when.q @@ -0,0 +1,31 @@ +explain +select key from src where ((case when (key = '238') then null end) = 1); +explain +select key from src where ((case when (key = '238') then null else null end) = 1); +explain +select key from src where ((case when (key = '238') then 1 else 1 end) = 1); +explain +select key from src where ((case when (key = '238') then 1 else 1 end) = 2); +explain +select key from src where ((case when (key = '238') then 1 else null end) = 1); +explain +select key from src where ((case when (key = '238') then 1=1 else null=1 end)); +explain +select key from src where ((case when (key = '238') then 1=1 else 2=2 end)); +explain +select key from src where ((case when (key = '238') then 1=3 else 2=1 end)); +explain +select key from src where ((case when (key = '238') then 1=1 else 2=1 end)); +explain +select key from src where ((case when (key = '238') then 1=3 else 1=1 end)); +explain +select key from src where ((case when ('23' = '23') then 1 else 1 end) = 1); +explain +select key from src where ((case when ('2' = '238') then 1 else 2 end) = 2); +explain +select key from src where ((case when (true=null) then 1 else 1 end) = 1); +explain +select key from src where ((case when (key = (case when (key = '238') then '11' else '11' end)) then false else true end)); +explain +select key from src where ((case when (key = (case when (key = '238') then '12' else '11' end)) then 2=2 else true end)); + http://git-wip-us.apache.org/repos/asf/hive/blob/48a243ef/ql/src/test/results/clientpositive/fold_case.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/fold_case.q.out b/ql/src/test/results/clientpositive/fold_case.q.out new file mode 100644 index 0000000..de6c43e --- /dev/null +++ b/ql/src/test/results/clientpositive/fold_case.q.out @@ -0,0 +1,301 @@ +PREHOOK: query: explain +select count(1) from src where (case key when '238' then true else false end) +PREHOOK: type: QUERY +POSTHOOK: query: explain +select count(1) from src where (case key when '238' then true else false end) +POSTHOOK: 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: src + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (key = '238') (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Select Operator + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(1) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 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 + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain +select count(1) from src where (case key when '238' then 1=2 else 1=1 end) +PREHOOK: type: QUERY +POSTHOOK: query: explain +select count(1) from src where (case key when '238' then 1=2 else 1=1 end) +POSTHOOK: 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: src + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (key <> '238') (type: boolean) + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Select Operator + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(1) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 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 + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain +select count(1) from src where (case key when '238' then 1=2 else 1=31 end) +PREHOOK: type: QUERY +POSTHOOK: query: explain +select count(1) from src where (case key when '238' then 1=2 else 1=31 end) +POSTHOOK: 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: src + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: false (type: boolean) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE + Group By Operator + aggregations: count(1) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + 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 + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain +select count(1) from src where (case key when '238' then true else 1=1 end) +PREHOOK: type: QUERY +POSTHOOK: query: explain +select count(1) from src where (case key when '238' then true else 1=1 end) +POSTHOOK: 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: src + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(1) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + 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 + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain +select count(1) from src where (case key when '238' then 1=1 else 1=null end) +PREHOOK: type: QUERY +POSTHOOK: query: explain +select count(1) from src where (case key when '238' then 1=1 else 1=null end) +POSTHOOK: 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: src + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: CASE (key) WHEN ('238') THEN (true) ELSE (null) END (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Select Operator + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(1) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 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 + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain +select count(1) from src where (case key when '238' then null else 1=1 end) +PREHOOK: type: QUERY +POSTHOOK: query: explain +select count(1) from src where (case key when '238' then null else 1=1 end) +POSTHOOK: 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: src + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: CASE (key) WHEN ('238') THEN (null) ELSE (true) END (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Select Operator + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(1) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 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 + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + http://git-wip-us.apache.org/repos/asf/hive/blob/48a243ef/ql/src/test/results/clientpositive/fold_when.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/fold_when.q.out b/ql/src/test/results/clientpositive/fold_when.q.out new file mode 100644 index 0000000..37803e0 --- /dev/null +++ b/ql/src/test/results/clientpositive/fold_when.q.out @@ -0,0 +1,480 @@ +PREHOOK: query: explain +select key from src where ((case when (key = '238') then null end) = 1) +PREHOOK: type: QUERY +POSTHOOK: query: explain +select key from src where ((case when (key = '238') then null end) = 1) +POSTHOOK: 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: src + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: false (type: boolean) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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 + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain +select key from src where ((case when (key = '238') then null else null end) = 1) +PREHOOK: type: QUERY +POSTHOOK: query: explain +select key from src where ((case when (key = '238') then null else null end) = 1) +POSTHOOK: 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: src + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: false (type: boolean) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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 + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain +select key from src where ((case when (key = '238') then 1 else 1 end) = 1) +PREHOOK: type: QUERY +POSTHOOK: query: explain +select key from src where ((case when (key = '238') then 1 else 1 end) = 1) +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + ListSink + +PREHOOK: query: explain +select key from src where ((case when (key = '238') then 1 else 1 end) = 2) +PREHOOK: type: QUERY +POSTHOOK: query: explain +select key from src where ((case when (key = '238') then 1 else 1 end) = 2) +POSTHOOK: 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: src + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: false (type: boolean) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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 + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain +select key from src where ((case when (key = '238') then 1 else null end) = 1) +PREHOOK: type: QUERY +POSTHOOK: query: explain +select key from src where ((case when (key = '238') then 1 else null end) = 1) +POSTHOOK: 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: src + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (CASE WHEN ((key = '238')) THEN (1) ELSE (null) END = 1) (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 2656 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 + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain +select key from src where ((case when (key = '238') then 1=1 else null=1 end)) +PREHOOK: type: QUERY +POSTHOOK: query: explain +select key from src where ((case when (key = '238') then 1=1 else null=1 end)) +POSTHOOK: 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: src + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: CASE WHEN ((key = '238')) THEN (true) ELSE (null) END (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 2656 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 + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain +select key from src where ((case when (key = '238') then 1=1 else 2=2 end)) +PREHOOK: type: QUERY +POSTHOOK: query: explain +select key from src where ((case when (key = '238') then 1=1 else 2=2 end)) +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + ListSink + +PREHOOK: query: explain +select key from src where ((case when (key = '238') then 1=3 else 2=1 end)) +PREHOOK: type: QUERY +POSTHOOK: query: explain +select key from src where ((case when (key = '238') then 1=3 else 2=1 end)) +POSTHOOK: 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: src + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: false (type: boolean) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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 + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain +select key from src where ((case when (key = '238') then 1=1 else 2=1 end)) +PREHOOK: type: QUERY +POSTHOOK: query: explain +select key from src where ((case when (key = '238') then 1=1 else 2=1 end)) +POSTHOOK: 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: src + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (key = '238') (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: '238' (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 2656 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 + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain +select key from src where ((case when (key = '238') then 1=3 else 1=1 end)) +PREHOOK: type: QUERY +POSTHOOK: query: explain +select key from src where ((case when (key = '238') then 1=3 else 1=1 end)) +POSTHOOK: 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: src + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (not (key = '238')) (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 2656 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 + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain +select key from src where ((case when ('23' = '23') then 1 else 1 end) = 1) +PREHOOK: type: QUERY +POSTHOOK: query: explain +select key from src where ((case when ('23' = '23') then 1 else 1 end) = 1) +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + ListSink + +PREHOOK: query: explain +select key from src where ((case when ('2' = '238') then 1 else 2 end) = 2) +PREHOOK: type: QUERY +POSTHOOK: query: explain +select key from src where ((case when ('2' = '238') then 1 else 2 end) = 2) +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + ListSink + +PREHOOK: query: explain +select key from src where ((case when (true=null) then 1 else 1 end) = 1) +PREHOOK: type: QUERY +POSTHOOK: query: explain +select key from src where ((case when (true=null) then 1 else 1 end) = 1) +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + ListSink + +PREHOOK: query: explain +select key from src where ((case when (key = (case when (key = '238') then '11' else '11' end)) then false else true end)) +PREHOOK: type: QUERY +POSTHOOK: query: explain +select key from src where ((case when (key = (case when (key = '238') then '11' else '11' end)) then false else true end)) +POSTHOOK: 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: src + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (not (key = '11')) (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 2656 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 + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain +select key from src where ((case when (key = (case when (key = '238') then '12' else '11' end)) then 2=2 else true end)) +PREHOOK: type: QUERY +POSTHOOK: query: explain +select key from src where ((case when (key = (case when (key = '238') then '12' else '11' end)) then 2=2 else true end)) +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + ListSink + http://git-wip-us.apache.org/repos/asf/hive/blob/48a243ef/ql/src/test/results/clientpositive/ql_rewrite_gbtoidx_cbo_2.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/ql_rewrite_gbtoidx_cbo_2.q.out b/ql/src/test/results/clientpositive/ql_rewrite_gbtoidx_cbo_2.q.out index 6340a75..381e58f 100644 --- a/ql/src/test/results/clientpositive/ql_rewrite_gbtoidx_cbo_2.q.out +++ b/ql/src/test/results/clientpositive/ql_rewrite_gbtoidx_cbo_2.q.out @@ -3814,22 +3814,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: lineitem_ix - Statistics: Num rows: 3024 Data size: 12099 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 0 Data size: 12099 Basic stats: PARTIAL Column stats: COMPLETE Select Operator - expressions: CASE (l_orderkey) WHEN (null) THEN (1) ELSE (1) END (type: int) + expressions: 1 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3024 Data size: 12099 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 0 Data size: 12099 Basic stats: PARTIAL Column stats: COMPLETE Group By Operator aggregations: count(_col0) keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 3024 Data size: 12099 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 3024 Data size: 12099 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator @@ -3837,10 +3837,10 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1512 Data size: 6049 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1512 Data size: 6049 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
