HIVE-13808: Use constant expressions to backtrack when we create ReduceSink (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
Project: http://git-wip-us.apache.org/repos/asf/hive/repo Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/c7c4ec4c Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/c7c4ec4c Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/c7c4ec4c Branch: refs/heads/master Commit: c7c4ec4ce384f64cf1721714e505e212832b7ac0 Parents: 58d8203 Author: Jesus Camacho Rodriguez <[email protected]> Authored: Mon May 30 14:48:05 2016 +0100 Committer: Jesus Camacho Rodriguez <[email protected]> Committed: Mon May 30 15:15:50 2016 +0100 ---------------------------------------------------------------------- .../hadoop/hive/ql/parse/SemanticAnalyzer.java | 65 +++++++--- .../results/clientpositive/bucket_groupby.q.out | 4 +- ql/src/test/results/clientpositive/cp_sel.q.out | 11 +- .../results/clientpositive/decimal_stats.q.out | 3 +- .../clientpositive/dynamic_rdd_cache.q.out | 6 +- .../dynpart_sort_optimization_acid.q.out | 16 +-- ql/src/test/results/clientpositive/pcr.q.out | 120 +++++++++---------- .../results/clientpositive/perf/query31.q.out | 2 +- .../results/clientpositive/perf/query64.q.out | 2 +- .../results/clientpositive/perf/query66.q.out | 2 +- .../results/clientpositive/perf/query75.q.out | 2 +- .../results/clientpositive/pointlookup2.q.out | 96 +++++++-------- .../results/clientpositive/pointlookup3.q.out | 104 ++++++++-------- .../results/clientpositive/ppd_udf_case.q.out | 12 +- .../clientpositive/reducesink_dedup.q.out | 48 ++++---- .../spark/dynamic_rdd_cache.q.out | 6 +- .../test/results/clientpositive/spark/pcr.q.out | 64 +++++----- .../clientpositive/spark/union_view.q.out | 20 ++-- .../clientpositive/tez/vector_coalesce.q.out | 22 ++-- .../clientpositive/tez/vector_date_1.q.out | 5 +- .../clientpositive/tez/vector_decimal_2.q.out | 85 ++++--------- .../tez/vector_decimal_round_2.q.out | 8 +- .../clientpositive/tez/vector_interval_1.q.out | 10 +- .../tez/vector_interval_arithmetic.q.out | 8 +- .../results/clientpositive/union_view.q.out | 20 ++-- .../clientpositive/vector_coalesce.q.out | 22 ++-- .../results/clientpositive/vector_date_1.q.out | 5 +- .../clientpositive/vector_decimal_2.q.out | 85 ++++--------- .../clientpositive/vector_decimal_round_2.q.out | 8 +- .../clientpositive/vector_interval_1.q.out | 10 +- .../vector_interval_arithmetic.q.out | 8 +- 31 files changed, 390 insertions(+), 489 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/hive/blob/c7c4ec4c/ql/src/java/org/apache/hadoop/hive/ql/parse/SemanticAnalyzer.java ---------------------------------------------------------------------- diff --git a/ql/src/java/org/apache/hadoop/hive/ql/parse/SemanticAnalyzer.java b/ql/src/java/org/apache/hadoop/hive/ql/parse/SemanticAnalyzer.java index 265dd7e..c3d903b 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/parse/SemanticAnalyzer.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/parse/SemanticAnalyzer.java @@ -78,7 +78,6 @@ import org.apache.hadoop.hive.ql.exec.AbstractMapJoinOperator; import org.apache.hadoop.hive.ql.exec.ArchiveUtils; import org.apache.hadoop.hive.ql.exec.ColumnInfo; import org.apache.hadoop.hive.ql.exec.ExprNodeEvaluatorFactory; -import org.apache.hadoop.hive.ql.exec.FetchOperator; import org.apache.hadoop.hive.ql.exec.FetchTask; import org.apache.hadoop.hive.ql.exec.FileSinkOperator; import org.apache.hadoop.hive.ql.exec.FilterOperator; @@ -129,7 +128,6 @@ import org.apache.hadoop.hive.ql.optimizer.calcite.CalciteSemanticException; import org.apache.hadoop.hive.ql.optimizer.calcite.CalciteSemanticException.UnsupportedFeature; import org.apache.hadoop.hive.ql.optimizer.calcite.translator.HiveOpConverterPostProc; import org.apache.hadoop.hive.ql.optimizer.lineage.Generator; -import org.apache.hadoop.hive.ql.optimizer.ppr.PartitionPruner; import org.apache.hadoop.hive.ql.optimizer.unionproc.UnionProcContext; import org.apache.hadoop.hive.ql.parse.BaseSemanticAnalyzer.TableSpec.SpecType; import org.apache.hadoop.hive.ql.parse.CalcitePlanner.ASTSearcher; @@ -183,7 +181,6 @@ import org.apache.hadoop.hive.ql.plan.LoadTableDesc; import org.apache.hadoop.hive.ql.plan.MapJoinDesc; import org.apache.hadoop.hive.ql.plan.OperatorDesc; import org.apache.hadoop.hive.ql.plan.PTFDesc; -import org.apache.hadoop.hive.ql.plan.PartitionDesc; import org.apache.hadoop.hive.ql.plan.PlanUtils; import org.apache.hadoop.hive.ql.plan.ReduceSinkDesc; import org.apache.hadoop.hive.ql.plan.ScriptDesc; @@ -7589,7 +7586,7 @@ public class SemanticAnalyzer extends BaseSemanticAnalyzer { } Operator result = genReduceSinkPlan( input, partCols, sortCols, order.toString(), nullOrder.toString(), - numReducers, Operation.NOT_ACID); + numReducers, Operation.NOT_ACID, true); if (result.getParentOperators().size() == 1 && result.getParentOperators().get(0) instanceof ReduceSinkOperator) { ((ReduceSinkOperator) result.getParentOperators().get(0)) @@ -7598,21 +7595,41 @@ public class SemanticAnalyzer extends BaseSemanticAnalyzer { return result; } + private Operator genReduceSinkPlan(Operator<?> input, + ArrayList<ExprNodeDesc> partitionCols, ArrayList<ExprNodeDesc> sortCols, + String sortOrder, String nullOrder, int numReducers, AcidUtils.Operation acidOp) + throws SemanticException { + return genReduceSinkPlan(input, partitionCols, sortCols, sortOrder, nullOrder, numReducers, + acidOp, false); + } + @SuppressWarnings("nls") private Operator genReduceSinkPlan(Operator<?> input, ArrayList<ExprNodeDesc> partitionCols, ArrayList<ExprNodeDesc> sortCols, - String sortOrder, String nullOrder, int numReducers, AcidUtils.Operation acidOp) - throws SemanticException { + String sortOrder, String nullOrder, int numReducers, AcidUtils.Operation acidOp, + boolean pullConstants) throws SemanticException { RowResolver inputRR = opParseCtx.get(input).getRowResolver(); Operator dummy = Operator.createDummy(); dummy.setParentOperators(Arrays.asList(input)); + ArrayList<ExprNodeDesc> newSortCols = new ArrayList<ExprNodeDesc>(); + StringBuilder newSortOrder = new StringBuilder(); + StringBuilder newNullOrder = new StringBuilder(); ArrayList<ExprNodeDesc> sortColsBack = new ArrayList<ExprNodeDesc>(); - for (ExprNodeDesc sortCol : sortCols) { - sortColsBack.add(ExprNodeDescUtils.backtrack(sortCol, dummy, input)); + for (int i = 0; i < sortCols.size(); i++) { + ExprNodeDesc sortCol = sortCols.get(i); + // If we are not pulling constants, OR + // we are pulling constants but this is not a constant + if (!pullConstants || !(sortCol instanceof ExprNodeConstantDesc)) { + newSortCols.add(sortCol); + newSortOrder.append(sortOrder.charAt(i)); + newNullOrder.append(nullOrder.charAt(i)); + sortColsBack.add(ExprNodeDescUtils.backtrack(sortCol, dummy, input)); + } } + // For the generation of the values expression just get the inputs // signature and generate field expressions for those RowResolver rsRR = new RowResolver(); @@ -7620,6 +7637,7 @@ public class SemanticAnalyzer extends BaseSemanticAnalyzer { ArrayList<ExprNodeDesc> valueCols = new ArrayList<ExprNodeDesc>(); ArrayList<ExprNodeDesc> valueColsBack = new ArrayList<ExprNodeDesc>(); Map<String, ExprNodeDesc> colExprMap = new HashMap<String, ExprNodeDesc>(); + ArrayList<ExprNodeDesc> constantCols = new ArrayList<ExprNodeDesc>(); ArrayList<ColumnInfo> columnInfos = inputRR.getColumnInfos(); @@ -7632,6 +7650,12 @@ public class SemanticAnalyzer extends BaseSemanticAnalyzer { // backtrack can be null when input is script operator ExprNodeDesc valueBack = ExprNodeDescUtils.backtrack(value, dummy, input); + if (pullConstants && valueBack instanceof ExprNodeConstantDesc) { + // ignore, it will be generated by SEL op + index[i] = Integer.MAX_VALUE; + constantCols.add(valueBack); + continue; + } int kindex = valueBack == null ? -1 : ExprNodeDescUtils.indexOf(valueBack, sortColsBack); if (kindex >= 0) { index[i] = kindex; @@ -7668,8 +7692,9 @@ public class SemanticAnalyzer extends BaseSemanticAnalyzer { dummy.setParentOperators(null); - ReduceSinkDesc rsdesc = PlanUtils.getReduceSinkDesc(sortCols, valueCols, outputColumns, - false, -1, partitionCols, sortOrder, nullOrder, numReducers, acidOp); + ReduceSinkDesc rsdesc = PlanUtils.getReduceSinkDesc(newSortCols, valueCols, outputColumns, + false, -1, partitionCols, newSortOrder.toString(), newNullOrder.toString(), + numReducers, acidOp); Operator interim = putOpInsertMap(OperatorFactory.getAndMakeChild(rsdesc, new RowSchema(rsRR.getColumnInfos()), input), rsRR); @@ -7688,23 +7713,29 @@ public class SemanticAnalyzer extends BaseSemanticAnalyzer { ArrayList<String> selOutputCols = new ArrayList<String>(); Map<String, ExprNodeDesc> selColExprMap = new HashMap<String, ExprNodeDesc>(); + Iterator<ExprNodeDesc> constants = constantCols.iterator(); for (int i = 0; i < index.length; i++) { ColumnInfo prev = columnInfos.get(i); String[] nm = inputRR.reverseLookup(prev.getInternalName()); String[] nm2 = inputRR.getAlternateMappings(prev.getInternalName()); ColumnInfo info = new ColumnInfo(prev); - String field; - if (index[i] >= 0) { - field = Utilities.ReduceField.KEY + "." + keyColNames.get(index[i]); + ExprNodeDesc desc; + if (index[i] == Integer.MAX_VALUE) { + desc = constants.next(); } else { - field = Utilities.ReduceField.VALUE + "." + valueColNames.get(-index[i] - 1); + String field; + if (index[i] >= 0) { + field = Utilities.ReduceField.KEY + "." + keyColNames.get(index[i]); + } else { + field = Utilities.ReduceField.VALUE + "." + valueColNames.get(-index[i] - 1); + } + desc = new ExprNodeColumnDesc(info.getType(), + field, info.getTabAlias(), info.getIsVirtualCol()); } - String internalName = getColumnInternalName(i); - ExprNodeColumnDesc desc = new ExprNodeColumnDesc(info.getType(), - field, info.getTabAlias(), info.getIsVirtualCol()); selCols.add(desc); + String internalName = getColumnInternalName(i); info.setInternalName(internalName); selectRR.put(nm[0], nm[1], info); if (nm2 != null) { http://git-wip-us.apache.org/repos/asf/hive/blob/c7c4ec4c/ql/src/test/results/clientpositive/bucket_groupby.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/bucket_groupby.q.out b/ql/src/test/results/clientpositive/bucket_groupby.q.out index 1afab38..e198617 100644 --- a/ql/src/test/results/clientpositive/bucket_groupby.q.out +++ b/ql/src/test/results/clientpositive/bucket_groupby.q.out @@ -467,8 +467,8 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: string), 3 (type: int) - sort order: ++ + key expressions: _col0 (type: string) + sort order: + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: bigint) http://git-wip-us.apache.org/repos/asf/hive/blob/c7c4ec4c/ql/src/test/results/clientpositive/cp_sel.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/cp_sel.q.out b/ql/src/test/results/clientpositive/cp_sel.q.out index 9ee9754..6300578 100644 --- a/ql/src/test/results/clientpositive/cp_sel.q.out +++ b/ql/src/test/results/clientpositive/cp_sel.q.out @@ -16,18 +16,17 @@ STAGE PLANS: alias: srcpart Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), value (type: string), 'hello' (type: string), 'world' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: 1 (type: int) - sort order: + + sort order: Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 - value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + value expressions: _col0 (type: string), _col1 (type: string) Reduce Operator Tree: Select Operator - expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string), VALUE._col3 (type: string) + expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), 'hello' (type: string), 'world' (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Limit http://git-wip-us.apache.org/repos/asf/hive/blob/c7c4ec4c/ql/src/test/results/clientpositive/decimal_stats.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/decimal_stats.q.out b/ql/src/test/results/clientpositive/decimal_stats.q.out index 72806f0..6bcf3fa 100644 --- a/ql/src/test/results/clientpositive/decimal_stats.q.out +++ b/ql/src/test/results/clientpositive/decimal_stats.q.out @@ -69,8 +69,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 112000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: 1 (type: int) - sort order: + + sort order: Statistics: Num rows: 500 Data size: 112000 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: decimal(4,2)), _col1 (type: decimal(5,0)), _col2 (type: decimal(10,0)) http://git-wip-us.apache.org/repos/asf/hive/blob/c7c4ec4c/ql/src/test/results/clientpositive/dynamic_rdd_cache.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/dynamic_rdd_cache.q.out b/ql/src/test/results/clientpositive/dynamic_rdd_cache.q.out index 86346b3..4088a39 100644 --- a/ql/src/test/results/clientpositive/dynamic_rdd_cache.q.out +++ b/ql/src/test/results/clientpositive/dynamic_rdd_cache.q.out @@ -1139,13 +1139,13 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: int), 3 (type: int), _col3 (type: double), _col4 (type: double), 4 (type: int), _col8 (type: double), _col9 (type: double) - sort order: ++++++++ + key expressions: _col0 (type: int), _col1 (type: int), _col3 (type: double), _col4 (type: double), _col8 (type: double), _col9 (type: double) + sort order: ++++++ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE value expressions: _col5 (type: int), _col6 (type: int) Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: int), KEY.reducesinkkey2 (type: int), KEY.reducesinkkey3 (type: double), KEY.reducesinkkey4 (type: double), VALUE._col0 (type: int), VALUE._col1 (type: int), KEY.reducesinkkey5 (type: int), KEY.reducesinkkey6 (type: double), KEY.reducesinkkey7 (type: double) + expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: int), 3 (type: int), KEY.reducesinkkey2 (type: double), KEY.reducesinkkey3 (type: double), VALUE._col0 (type: int), VALUE._col1 (type: int), 4 (type: int), KEY.reducesinkkey4 (type: double), KEY.reducesinkkey5 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE File Output Operator http://git-wip-us.apache.org/repos/asf/hive/blob/c7c4ec4c/ql/src/test/results/clientpositive/dynpart_sort_optimization_acid.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/dynpart_sort_optimization_acid.q.out b/ql/src/test/results/clientpositive/dynpart_sort_optimization_acid.q.out index ac95ec2..de08dc5 100644 --- a/ql/src/test/results/clientpositive/dynpart_sort_optimization_acid.q.out +++ b/ql/src/test/results/clientpositive/dynpart_sort_optimization_acid.q.out @@ -164,7 +164,7 @@ STAGE PLANS: value expressions: _col3 (type: string) Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>), 'foo' (type: string), 'bar' (type: string), VALUE._col2 (type: string) + expressions: KEY.reducesinkkey0 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>), 'foo' (type: string), 'bar' (type: string), VALUE._col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 File Output Operator compressed: false @@ -644,7 +644,7 @@ STAGE PLANS: value expressions: _col4 (type: int) Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>), 'foo' (type: string), 'bar' (type: string), '2008-04-08' (type: string), VALUE._col3 (type: int) + expressions: KEY.reducesinkkey0 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>), 'foo' (type: string), 'bar' (type: string), '2008-04-08' (type: string), VALUE._col2 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 File Output Operator compressed: false @@ -1063,13 +1063,13 @@ STAGE PLANS: Filter Operator predicate: (key = 'foo') (type: boolean) Select Operator - expressions: ROW__ID (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>), key (type: string), 'bar' (type: string), ds (type: string), hr (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + expressions: ROW__ID (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>), key (type: string), ds (type: string), hr (type: int) + outputColumnNames: _col0, _col1, _col3, _col4 Reduce Output Operator key expressions: _col3 (type: string), _col4 (type: int), '_bucket_number' (type: string), _col0 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>) sort order: ++++ Map-reduce partition columns: _col3 (type: string), _col4 (type: int) - value expressions: _col1 (type: string), _col2 (type: string) + value expressions: _col1 (type: string), 'bar' (type: string) Reduce Operator Tree: Select Operator expressions: KEY._col0 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>), VALUE._col1 (type: string), VALUE._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: int), KEY.'_bucket_number' (type: string) @@ -1137,13 +1137,13 @@ STAGE PLANS: Filter Operator predicate: (key = 'foo') (type: boolean) Select Operator - expressions: ROW__ID (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>), key (type: string), 'bar' (type: string), ds (type: string), hr (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + expressions: ROW__ID (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>), key (type: string), ds (type: string), hr (type: int) + outputColumnNames: _col0, _col1, _col3, _col4 Reduce Output Operator key expressions: _col3 (type: string), _col4 (type: int), '_bucket_number' (type: string), _col0 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>) sort order: ++++ Map-reduce partition columns: _col3 (type: string), _col4 (type: int) - value expressions: _col1 (type: string), _col2 (type: string) + value expressions: _col1 (type: string), 'bar' (type: string) Reduce Operator Tree: Select Operator expressions: KEY._col0 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>), VALUE._col1 (type: string), VALUE._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: int), KEY.'_bucket_number' (type: string) http://git-wip-us.apache.org/repos/asf/hive/blob/c7c4ec4c/ql/src/test/results/clientpositive/pcr.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/pcr.q.out b/ql/src/test/results/clientpositive/pcr.q.out index 9fb1481..2a5d579 100644 --- a/ql/src/test/results/clientpositive/pcr.q.out +++ b/ql/src/test/results/clientpositive/pcr.q.out @@ -1400,9 +1400,9 @@ STAGE PLANS: outputColumnNames: _col1 Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: 14 (type: int), _col1 (type: string) - null sort order: aa - sort order: ++ + key expressions: _col1 (type: string) + null sort order: a + sort order: + Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE tag: -1 auto parallelism: false @@ -1505,7 +1505,7 @@ STAGE PLANS: Needs Tagging: false Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string) + expressions: 14 (type: int), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -2327,27 +2327,23 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3, _col4 Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col1 (type: string), '2000-04-08' (type: string), _col3 (type: int), _col4 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - columns _col0,_col1,_col2,_col3,_col4 - columns.types int,string,string,int,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns _col0,_col1,_col3,_col4 + columns.types int,string,int,string + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-2 Map Reduce @@ -2360,7 +2356,7 @@ STAGE PLANS: sort order: + Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE tag: -1 - value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: int), _col4 (type: string) + value expressions: _col1 (type: string), _col3 (type: int), _col4 (type: string) auto parallelism: false Path -> Alias: #### A masked pattern was here #### @@ -2371,8 +2367,8 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: - columns _col0,_col1,_col2,_col3,_col4 - columns.types int,string,string,int,string + columns _col0,_col1,_col3,_col4 + columns.types int,string,int,string escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -2380,8 +2376,8 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: - columns _col0,_col1,_col2,_col3,_col4 - columns.types int,string,string,int,string + columns _col0,_col1,_col3,_col4 + columns.types int,string,int,string escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -2390,7 +2386,7 @@ STAGE PLANS: Needs Tagging: false Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: int), VALUE._col3 (type: string), VALUE._col1 (type: string) + expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), '2000-04-08' (type: string), VALUE._col1 (type: int), VALUE._col2 (type: string), '2000-04-08' (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -2631,27 +2627,23 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3, _col4 Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col1 (type: string), '2000-04-08' (type: string), _col3 (type: int), _col4 (type: string), '2000-04-09' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - columns _col0,_col1,_col2,_col3,_col4,_col5 - columns.types int,string,string,int,string,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns _col0,_col1,_col3,_col4 + columns.types int,string,int,string + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-2 Map Reduce @@ -2664,7 +2656,7 @@ STAGE PLANS: sort order: + Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE tag: -1 - value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: int), _col4 (type: string), _col5 (type: string) + value expressions: _col1 (type: string), _col3 (type: int), _col4 (type: string) auto parallelism: false Path -> Alias: #### A masked pattern was here #### @@ -2675,8 +2667,8 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: - columns _col0,_col1,_col2,_col3,_col4,_col5 - columns.types int,string,string,int,string,string + columns _col0,_col1,_col3,_col4 + columns.types int,string,int,string escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -2684,8 +2676,8 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: - columns _col0,_col1,_col2,_col3,_col4,_col5 - columns.types int,string,string,int,string,string + columns _col0,_col1,_col3,_col4 + columns.types int,string,int,string escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -2694,7 +2686,7 @@ STAGE PLANS: Needs Tagging: false Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: int), VALUE._col3 (type: string), VALUE._col4 (type: string) + expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), '2000-04-08' (type: string), VALUE._col1 (type: int), VALUE._col2 (type: string), '2000-04-09' (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -4745,9 +4737,9 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col3 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), '2008-04-08' (type: string), _col3 (type: string) - null sort order: aaa - sort order: +++ + key expressions: _col0 (type: string), _col3 (type: string) + null sort order: aa + sort order: ++ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col1 (type: string) @@ -4853,7 +4845,7 @@ STAGE PLANS: Needs Tagging: false Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string) + expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string), '2008-04-08' (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -4924,9 +4916,9 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col2 (type: string), '11' (type: string) - null sort order: aaa - sort order: +++ + key expressions: _col0 (type: string), _col2 (type: string) + null sort order: aa + sort order: ++ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col1 (type: string) @@ -5032,7 +5024,7 @@ STAGE PLANS: Needs Tagging: false Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string) + expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string), KEY.reducesinkkey1 (type: string), '11' (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator http://git-wip-us.apache.org/repos/asf/hive/blob/c7c4ec4c/ql/src/test/results/clientpositive/perf/query31.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/query31.q.out b/ql/src/test/results/clientpositive/perf/query31.q.out index 935631c..433d419 100644 --- a/ql/src/test/results/clientpositive/perf/query31.q.out +++ b/ql/src/test/results/clientpositive/perf/query31.q.out @@ -39,7 +39,7 @@ Stage-0 <-Reducer 6 [SIMPLE_EDGE] SHUFFLE [RS_138] Select Operator [SEL_137] (rows=316243230 width=88) - Output:["_col0","_col1","_col2","_col3","_col4","_col5"] + Output:["_col0","_col2","_col3","_col4","_col5"] Filter Operator [FIL_136] (rows=316243230 width=88) predicate:CASE WHEN ((_col3 > 0)) THEN (CASE WHEN ((_col9 > 0)) THEN (((_col11 / _col9) > (_col5 / _col3))) ELSE ((null > (_col5 / _col3))) END) ELSE (CASE WHEN ((_col9 > 0)) THEN (((_col11 / _col9) > null)) ELSE (null) END) END Merge Join Operator [MERGEJOIN_272] (rows=632486460 width=88) http://git-wip-us.apache.org/repos/asf/hive/blob/c7c4ec4c/ql/src/test/results/clientpositive/perf/query64.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/query64.q.out b/ql/src/test/results/clientpositive/perf/query64.q.out index 5a5ee74..5c931c0 100644 --- a/ql/src/test/results/clientpositive/perf/query64.q.out +++ b/ql/src/test/results/clientpositive/perf/query64.q.out @@ -59,7 +59,7 @@ Stage-0 <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_265] Select Operator [SEL_264] (rows=331415616 width=88) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20"] + Output:["_col0","_col1","_col10","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col2","_col20","_col3","_col4","_col5","_col6","_col7","_col8","_col9"] Filter Operator [FIL_263] (rows=331415616 width=88) predicate:(_col30 <= _col13) Merge Join Operator [MERGEJOIN_658] (rows=994246850 width=88) http://git-wip-us.apache.org/repos/asf/hive/blob/c7c4ec4c/ql/src/test/results/clientpositive/perf/query66.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/query66.q.out b/ql/src/test/results/clientpositive/perf/query66.q.out index 5eef7e7..8f62292 100644 --- a/ql/src/test/results/clientpositive/perf/query66.q.out +++ b/ql/src/test/results/clientpositive/perf/query66.q.out @@ -465,7 +465,7 @@ Stage-0 <-Reducer 8 [SIMPLE_EDGE] SHUFFLE [RS_73] Select Operator [SEL_72] (rows=158120068 width=135) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23","_col24","_col25","_col26","_col27","_col28","_col29","_col30","_col31","_col32","_col33","_col34","_col35","_col36","_col37","_col38","_col39","_col40","_col41","_col42","_col43"] + Output:["_col0","_col1","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col2","_col20","_col21","_col22","_col23","_col24","_col25","_col26","_col27","_col28","_col29","_col3","_col30","_col31","_col32","_col33","_col34","_col35","_col36","_col37","_col38","_col39","_col4","_col40","_col41","_col42","_col43","_col5","_col8","_col9"] Group By Operator [GBY_71] (rows=158120068 width=135) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23","_col24","_col25","_col26","_col27","_col28","_col29","_col30","_col31","_col32","_col33","_col34","_col35","_col36","_col37","_col38","_col39","_col40","_col41"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)","sum(VALUE._col3)","sum(VALUE._col4)","sum(VALUE._col5)","sum(VALUE._col6)","sum(VALUE._col7)","sum(VALUE._col8)","sum(VALUE._col9)","sum(VALUE._col10)","sum(VALUE._col11)","sum(VALUE._col12)","sum(VALUE._col13)","sum(VALUE._col14)","sum(VALUE._col15)","sum(VALUE._col16)","sum(VALUE._col17)","sum(VALUE._col18)","sum(VALUE._col19)","sum(VALUE._col20)","sum(VALUE._col21)","sum(VALUE._col22)","sum(VALUE._col23)","sum(VALUE._col24)","sum(VALUE._col25)","sum(VALUE._col26)","sum(VALUE._col27)","sum(VALUE._col28)","sum(VALUE._col29) ","sum(VALUE._col30)","sum(VALUE._col31)","sum(VALUE._col32)","sum(VALUE._col33)","sum(VALUE._col34)","sum(VALUE._col35)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5 <-Union 7 [SIMPLE_EDGE] http://git-wip-us.apache.org/repos/asf/hive/blob/c7c4ec4c/ql/src/test/results/clientpositive/perf/query75.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/query75.q.out b/ql/src/test/results/clientpositive/perf/query75.q.out index 802c1af..4279f54 100644 --- a/ql/src/test/results/clientpositive/perf/query75.q.out +++ b/ql/src/test/results/clientpositive/perf/query75.q.out @@ -41,7 +41,7 @@ Stage-0 <-Reducer 7 [SIMPLE_EDGE] SHUFFLE [RS_153] Select Operator [SEL_152] (rows=245965926 width=108) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"] + Output:["_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"] Filter Operator [FIL_151] (rows=245965926 width=108) predicate:(UDFToDouble((CAST( _col4 AS decimal(17,2)) / CAST( _col10 AS decimal(17,2)))) < 0.9) Merge Join Operator [MERGEJOIN_259] (rows=737897778 width=108) http://git-wip-us.apache.org/repos/asf/hive/blob/c7c4ec4c/ql/src/test/results/clientpositive/pointlookup2.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/pointlookup2.q.out b/ql/src/test/results/clientpositive/pointlookup2.q.out index 5facf9a..dfcf14e 100644 --- a/ql/src/test/results/clientpositive/pointlookup2.q.out +++ b/ql/src/test/results/clientpositive/pointlookup2.q.out @@ -379,27 +379,23 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3, _col4 Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col1 (type: string), '2000-04-08' (type: string), _col3 (type: int), _col4 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - columns _col0,_col1,_col2,_col3,_col4 - columns.types int,string,string,int,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns _col0,_col1,_col3,_col4 + columns.types int,string,int,string + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-2 Map Reduce @@ -412,7 +408,7 @@ STAGE PLANS: sort order: + Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE tag: -1 - value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: int), _col4 (type: string) + value expressions: _col1 (type: string), _col3 (type: int), _col4 (type: string) auto parallelism: false Path -> Alias: #### A masked pattern was here #### @@ -423,8 +419,8 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: - columns _col0,_col1,_col2,_col3,_col4 - columns.types int,string,string,int,string + columns _col0,_col1,_col3,_col4 + columns.types int,string,int,string escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -432,8 +428,8 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: - columns _col0,_col1,_col2,_col3,_col4 - columns.types int,string,string,int,string + columns _col0,_col1,_col3,_col4 + columns.types int,string,int,string escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -442,7 +438,7 @@ STAGE PLANS: Needs Tagging: false Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: int), VALUE._col3 (type: string), VALUE._col1 (type: string) + expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), '2000-04-08' (type: string), VALUE._col1 (type: int), VALUE._col2 (type: string), '2000-04-08' (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -643,27 +639,23 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3, _col4 Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col1 (type: string), '2000-04-08' (type: string), _col3 (type: int), _col4 (type: string), '2000-04-09' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - columns _col0,_col1,_col2,_col3,_col4,_col5 - columns.types int,string,string,int,string,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns _col0,_col1,_col3,_col4 + columns.types int,string,int,string + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-2 Map Reduce @@ -676,7 +668,7 @@ STAGE PLANS: sort order: + Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE tag: -1 - value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: int), _col4 (type: string), _col5 (type: string) + value expressions: _col1 (type: string), _col3 (type: int), _col4 (type: string) auto parallelism: false Path -> Alias: #### A masked pattern was here #### @@ -687,8 +679,8 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: - columns _col0,_col1,_col2,_col3,_col4,_col5 - columns.types int,string,string,int,string,string + columns _col0,_col1,_col3,_col4 + columns.types int,string,int,string escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -696,8 +688,8 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: - columns _col0,_col1,_col2,_col3,_col4,_col5 - columns.types int,string,string,int,string,string + columns _col0,_col1,_col3,_col4 + columns.types int,string,int,string escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -706,7 +698,7 @@ STAGE PLANS: Needs Tagging: false Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: int), VALUE._col3 (type: string), VALUE._col4 (type: string) + expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), '2000-04-08' (type: string), VALUE._col1 (type: int), VALUE._col2 (type: string), '2000-04-09' (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE File Output Operator http://git-wip-us.apache.org/repos/asf/hive/blob/c7c4ec4c/ql/src/test/results/clientpositive/pointlookup3.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/pointlookup3.q.out b/ql/src/test/results/clientpositive/pointlookup3.q.out index def1bc8..35c2094 100644 --- a/ql/src/test/results/clientpositive/pointlookup3.q.out +++ b/ql/src/test/results/clientpositive/pointlookup3.q.out @@ -245,9 +245,9 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), '2001-04-08' (type: string) - null sort order: aaaa - sort order: ++++ + key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) + null sort order: aaa + sort order: +++ Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE tag: -1 auto parallelism: false @@ -305,7 +305,7 @@ STAGE PLANS: Needs Tagging: false Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string) + expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), '2001-04-08' (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -461,27 +461,23 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3, _col4, _col5, _col6 Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col1 (type: string), '2000-04-08' (type: string), _col3 (type: string), _col4 (type: int), _col5 (type: string), _col6 (type: string), '2001-04-08' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - columns _col0,_col1,_col2,_col3,_col4,_col5,_col6,_col7 - columns.types int,string,string,string,int,string,string,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns _col0,_col1,_col3,_col4,_col5,_col6 + columns.types int,string,string,int,string,string + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-2 Map Reduce @@ -494,7 +490,7 @@ STAGE PLANS: sort order: + Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE tag: -1 - value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: int), _col5 (type: string), _col6 (type: string), _col7 (type: string) + value expressions: _col1 (type: string), _col3 (type: string), _col4 (type: int), _col5 (type: string), _col6 (type: string) auto parallelism: false Path -> Alias: #### A masked pattern was here #### @@ -505,8 +501,8 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: - columns _col0,_col1,_col2,_col3,_col4,_col5,_col6,_col7 - columns.types int,string,string,string,int,string,string,string + columns _col0,_col1,_col3,_col4,_col5,_col6 + columns.types int,string,string,int,string,string escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -514,8 +510,8 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: - columns _col0,_col1,_col2,_col3,_col4,_col5,_col6,_col7 - columns.types int,string,string,string,int,string,string,string + columns _col0,_col1,_col3,_col4,_col5,_col6 + columns.types int,string,string,int,string,string escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -524,7 +520,7 @@ STAGE PLANS: Needs Tagging: false Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string), VALUE._col3 (type: int), VALUE._col4 (type: string), VALUE._col5 (type: string), VALUE._col6 (type: string) + expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), '2000-04-08' (type: string), VALUE._col1 (type: string), VALUE._col2 (type: int), VALUE._col3 (type: string), VALUE._col4 (type: string), '2001-04-08' (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -727,27 +723,23 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3, _col4, _col5, _col7 Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col1 (type: string), '2000-04-08' (type: string), _col3 (type: string), _col4 (type: int), _col5 (type: string), '2000-04-09' (type: string), _col7 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - columns _col0,_col1,_col2,_col3,_col4,_col5,_col6,_col7 - columns.types int,string,string,string,int,string,string,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns _col0,_col1,_col3,_col4,_col5,_col7 + columns.types int,string,string,int,string,string + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-2 Map Reduce @@ -760,7 +752,7 @@ STAGE PLANS: sort order: + Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE tag: -1 - value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: int), _col5 (type: string), _col6 (type: string), _col7 (type: string) + value expressions: _col1 (type: string), _col3 (type: string), _col4 (type: int), _col5 (type: string), _col7 (type: string) auto parallelism: false Path -> Alias: #### A masked pattern was here #### @@ -771,8 +763,8 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: - columns _col0,_col1,_col2,_col3,_col4,_col5,_col6,_col7 - columns.types int,string,string,string,int,string,string,string + columns _col0,_col1,_col3,_col4,_col5,_col7 + columns.types int,string,string,int,string,string escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -780,8 +772,8 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: - columns _col0,_col1,_col2,_col3,_col4,_col5,_col6,_col7 - columns.types int,string,string,string,int,string,string,string + columns _col0,_col1,_col3,_col4,_col5,_col7 + columns.types int,string,string,int,string,string escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -790,7 +782,7 @@ STAGE PLANS: Needs Tagging: false Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string), VALUE._col3 (type: int), VALUE._col4 (type: string), VALUE._col5 (type: string), VALUE._col6 (type: string) + expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), '2000-04-08' (type: string), VALUE._col1 (type: string), VALUE._col2 (type: int), VALUE._col3 (type: string), '2000-04-09' (type: string), VALUE._col4 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE File Output Operator http://git-wip-us.apache.org/repos/asf/hive/blob/c7c4ec4c/ql/src/test/results/clientpositive/ppd_udf_case.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/ppd_udf_case.q.out b/ql/src/test/results/clientpositive/ppd_udf_case.q.out index 56941cd..e444ef7 100644 --- a/ql/src/test/results/clientpositive/ppd_udf_case.q.out +++ b/ql/src/test/results/clientpositive/ppd_udf_case.q.out @@ -83,12 +83,12 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: '27' (type: string), _col1 (type: string), '2008-04-08' (type: string), _col3 (type: string), '27' (type: string), _col5 (type: string), '2008-04-08' (type: string), _col7 (type: string) - sort order: ++++++++ + key expressions: _col1 (type: string), _col3 (type: string), _col5 (type: string), _col7 (type: string) + sort order: ++++ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey0 (type: string), KEY.reducesinkkey5 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey7 (type: string) + expressions: '27' (type: string), KEY.reducesinkkey0 (type: string), '2008-04-08' (type: string), KEY.reducesinkkey1 (type: string), '27' (type: string), KEY.reducesinkkey2 (type: string), '2008-04-08' (type: string), KEY.reducesinkkey3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -227,12 +227,12 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: '27' (type: string), _col1 (type: string), '2008-04-08' (type: string), _col3 (type: string), '27' (type: string), _col5 (type: string), '2008-04-08' (type: string), _col7 (type: string) - sort order: ++++++++ + key expressions: _col1 (type: string), _col3 (type: string), _col5 (type: string), _col7 (type: string) + sort order: ++++ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey0 (type: string), KEY.reducesinkkey5 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey7 (type: string) + expressions: '27' (type: string), KEY.reducesinkkey0 (type: string), '2008-04-08' (type: string), KEY.reducesinkkey1 (type: string), '27' (type: string), KEY.reducesinkkey2 (type: string), '2008-04-08' (type: string), KEY.reducesinkkey3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE File Output Operator http://git-wip-us.apache.org/repos/asf/hive/blob/c7c4ec4c/ql/src/test/results/clientpositive/reducesink_dedup.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/reducesink_dedup.q.out b/ql/src/test/results/clientpositive/reducesink_dedup.q.out index 77bffff..b89df52 100644 --- a/ql/src/test/results/clientpositive/reducesink_dedup.q.out +++ b/ql/src/test/results/clientpositive/reducesink_dedup.q.out @@ -10,29 +10,29 @@ distribute by 1 sort by 1 POSTHOOK: type: QUERY POSTHOOK: Input: default@part #### A masked pattern was here #### -almond azure blanched chiffon midnight -almond aquamarine dodger light gainsboro -almond antique sky peru orange -almond antique medium spring khaki -almond antique blue firebrick mint -almond azure aquamarine papaya violet -almond aquamarine yellow dodger mint -almond aquamarine floral ivory bisque -almond antique violet mint lemon -almond antique gainsboro frosted violet -almond antique olive coral navajo -almond antique misty red olive -almond antique metallic orange dim -almond antique forest lavender goldenrod -almond antique chartreuse khaki white -almond aquamarine sandy cyan gainsboro -almond aquamarine rose maroon antique -almond aquamarine midnight light salmon -almond antique violet turquoise frosted -almond antique violet chocolate turquoise -almond aquamarine pink moccasin thistle -almond aquamarine burnished black steel -almond antique salmon chartreuse burlywood -almond antique chartreuse lavender yellow almond antique burnished rose metallic almond antique burnished rose metallic +almond antique chartreuse lavender yellow +almond antique salmon chartreuse burlywood +almond aquamarine burnished black steel +almond aquamarine pink moccasin thistle +almond antique violet chocolate turquoise +almond antique violet turquoise frosted +almond aquamarine midnight light salmon +almond aquamarine rose maroon antique +almond aquamarine sandy cyan gainsboro +almond antique chartreuse khaki white +almond antique forest lavender goldenrod +almond antique metallic orange dim +almond antique misty red olive +almond antique olive coral navajo +almond antique gainsboro frosted violet +almond antique violet mint lemon +almond aquamarine floral ivory bisque +almond aquamarine yellow dodger mint +almond azure aquamarine papaya violet +almond antique blue firebrick mint +almond antique medium spring khaki +almond antique sky peru orange +almond aquamarine dodger light gainsboro +almond azure blanched chiffon midnight http://git-wip-us.apache.org/repos/asf/hive/blob/c7c4ec4c/ql/src/test/results/clientpositive/spark/dynamic_rdd_cache.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/dynamic_rdd_cache.q.out b/ql/src/test/results/clientpositive/spark/dynamic_rdd_cache.q.out index 86c5bd7..b290fa1 100644 --- a/ql/src/test/results/clientpositive/spark/dynamic_rdd_cache.q.out +++ b/ql/src/test/results/clientpositive/spark/dynamic_rdd_cache.q.out @@ -1046,14 +1046,14 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col3, _col4, _col5, _col6, _col8, _col9 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: int), 3 (type: int), _col3 (type: double), _col4 (type: double), 4 (type: int), _col8 (type: double), _col9 (type: double) - sort order: ++++++++ + key expressions: _col0 (type: int), _col1 (type: int), _col3 (type: double), _col4 (type: double), _col8 (type: double), _col9 (type: double) + sort order: ++++++ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE value expressions: _col5 (type: int), _col6 (type: int) Reducer 7 Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: int), KEY.reducesinkkey2 (type: int), KEY.reducesinkkey3 (type: double), KEY.reducesinkkey4 (type: double), VALUE._col0 (type: int), VALUE._col1 (type: int), KEY.reducesinkkey5 (type: int), KEY.reducesinkkey6 (type: double), KEY.reducesinkkey7 (type: double) + expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: int), 3 (type: int), KEY.reducesinkkey2 (type: double), KEY.reducesinkkey3 (type: double), VALUE._col0 (type: int), VALUE._col1 (type: int), 4 (type: int), KEY.reducesinkkey4 (type: double), KEY.reducesinkkey5 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE File Output Operator http://git-wip-us.apache.org/repos/asf/hive/blob/c7c4ec4c/ql/src/test/results/clientpositive/spark/pcr.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/pcr.q.out b/ql/src/test/results/clientpositive/spark/pcr.q.out index cbebbdd..cb3e288 100644 --- a/ql/src/test/results/clientpositive/spark/pcr.q.out +++ b/ql/src/test/results/clientpositive/spark/pcr.q.out @@ -1441,9 +1441,9 @@ STAGE PLANS: outputColumnNames: _col1 Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: 14 (type: int), _col1 (type: string) - null sort order: aa - sort order: ++ + key expressions: _col1 (type: string) + null sort order: a + sort order: + Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE tag: -1 auto parallelism: false @@ -1547,7 +1547,7 @@ STAGE PLANS: Needs Tagging: false Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string) + expressions: 14 (type: int), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -2445,23 +2445,19 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3, _col4 Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col1 (type: string), '2000-04-08' (type: string), _col3 (type: int), _col4 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Reduce Output Operator + key expressions: _col0 (type: int) + null sort order: a + sort order: + Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: a - sort order: + - Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: int), _col4 (type: string) - auto parallelism: false + tag: -1 + value expressions: _col1 (type: string), _col3 (type: int), _col4 (type: string) + auto parallelism: false Reducer 3 Needs Tagging: false Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: int), VALUE._col3 (type: string), VALUE._col1 (type: string) + expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), '2000-04-08' (type: string), VALUE._col1 (type: int), VALUE._col2 (type: string), '2000-04-08' (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -2714,23 +2710,19 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3, _col4 Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col1 (type: string), '2000-04-08' (type: string), _col3 (type: int), _col4 (type: string), '2000-04-09' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Reduce Output Operator + key expressions: _col0 (type: int) + null sort order: a + sort order: + Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - null sort order: a - sort order: + - Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: int), _col4 (type: string), _col5 (type: string) - auto parallelism: false + tag: -1 + value expressions: _col1 (type: string), _col3 (type: int), _col4 (type: string) + auto parallelism: false Reducer 3 Needs Tagging: false Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: int), VALUE._col3 (type: string), VALUE._col4 (type: string) + expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), '2000-04-08' (type: string), VALUE._col1 (type: int), VALUE._col2 (type: string), '2000-04-09' (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -4058,9 +4050,9 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col3 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), '2008-04-08' (type: string), _col3 (type: string) - null sort order: aaa - sort order: +++ + key expressions: _col0 (type: string), _col3 (type: string) + null sort order: aa + sort order: ++ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col1 (type: string) @@ -4167,7 +4159,7 @@ STAGE PLANS: Needs Tagging: false Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string) + expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string), '2008-04-08' (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -4243,9 +4235,9 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col2 (type: string), '11' (type: string) - null sort order: aaa - sort order: +++ + key expressions: _col0 (type: string), _col2 (type: string) + null sort order: aa + sort order: ++ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col1 (type: string) @@ -4352,7 +4344,7 @@ STAGE PLANS: Needs Tagging: false Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string) + expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string), KEY.reducesinkkey1 (type: string), '11' (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator http://git-wip-us.apache.org/repos/asf/hive/blob/c7c4ec4c/ql/src/test/results/clientpositive/spark/union_view.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/union_view.q.out b/ql/src/test/results/clientpositive/spark/union_view.q.out index 7ac641f..f06b080 100644 --- a/ql/src/test/results/clientpositive/spark/union_view.q.out +++ b/ql/src/test/results/clientpositive/spark/union_view.q.out @@ -541,14 +541,14 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: 86 (type: int), _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col1, _col2 Statistics: Num rows: 1250 Data size: 13280 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col2 (type: string) sort order: + Statistics: Num rows: 1250 Data size: 13280 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string) + value expressions: _col1 (type: string) Map 3 Map Operator Tree: TableScan @@ -563,14 +563,14 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: 86 (type: int), _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col1, _col2 Statistics: Num rows: 1250 Data size: 13280 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col2 (type: string) sort order: + Statistics: Num rows: 1250 Data size: 13280 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string) + value expressions: _col1 (type: string) Map 4 Map Operator Tree: TableScan @@ -585,18 +585,18 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: 86 (type: int), _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col1, _col2 Statistics: Num rows: 1250 Data size: 13280 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col2 (type: string) sort order: + Statistics: Num rows: 1250 Data size: 13280 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string) + value expressions: _col1 (type: string) Reducer 2 Reduce Operator Tree: Select Operator - expressions: VALUE._col0 (type: int), VALUE._col1 (type: string), KEY.reducesinkkey0 (type: string) + expressions: 86 (type: int), VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1250 Data size: 13280 Basic stats: COMPLETE Column stats: NONE File Output Operator
