You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by jv...@apache.org on 2010/07/30 08:40:11 UTC
svn commit: r980659 [10/34] - in /hadoop/hive/trunk: ./
common/src/java/org/apache/hadoop/hive/common/
contrib/src/test/results/clientpositive/ metastore/if/ metastore/src/gen-cpp/
metastore/src/gen-javabean/org/apache/hadoop/hive/metastore/api/ metast...
Modified: hadoop/hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/plan/DDLWork.java
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/plan/DDLWork.java?rev=980659&r1=980658&r2=980659&view=diff
==============================================================================
--- hadoop/hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/plan/DDLWork.java (original)
+++ hadoop/hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/plan/DDLWork.java Fri Jul 30 06:40:04 2010
@@ -30,7 +30,8 @@ import org.apache.hadoop.hive.ql.hooks.W
*/
public class DDLWork implements Serializable {
private static final long serialVersionUID = 1L;
-
+ private CreateIndexDesc createIndexDesc;
+ private DropIndexDesc dropIdxDesc;
private CreateTableDesc createTblDesc;
private CreateTableLikeDesc createTblLikeDesc;
private CreateViewDesc createVwDesc;
@@ -63,6 +64,10 @@ public class DDLWork implements Serializ
this.outputs = outputs;
}
+ public DDLWork(CreateIndexDesc createIndex) {
+ this.createIndexDesc = createIndex;
+ }
+
/**
* @param alterTblDesc
* alter table descriptor
@@ -207,6 +212,12 @@ public class DDLWork implements Serializ
this.showTblStatusDesc = showTblStatusDesc;
}
+ public DDLWork(HashSet<ReadEntity> inputs, HashSet<WriteEntity> outputs,
+ DropIndexDesc dropIndexDesc) {
+ this(inputs, outputs);
+ this.dropIdxDesc = dropIndexDesc;
+ }
+
/**
* @return the createTblDesc
*/
@@ -222,6 +233,14 @@ public class DDLWork implements Serializ
public void setCreateTblDesc(CreateTableDesc createTblDesc) {
this.createTblDesc = createTblDesc;
}
+
+ public CreateIndexDesc getCreateIndexDesc() {
+ return createIndexDesc;
+ }
+
+ public void setCreateIndexDesc(CreateIndexDesc createIndexDesc) {
+ this.createIndexDesc = createIndexDesc;
+ }
/**
* @return the createTblDesc
@@ -454,5 +473,13 @@ public class DDLWork implements Serializ
public void setOutputs(HashSet<WriteEntity> outputs) {
this.outputs = outputs;
}
+
+ public DropIndexDesc getDropIdxDesc() {
+ return dropIdxDesc;
+ }
+
+ public void setDropIdxDesc(DropIndexDesc dropIdxDesc) {
+ this.dropIdxDesc = dropIdxDesc;
+ }
}
Added: hadoop/hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/plan/DropIndexDesc.java
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/plan/DropIndexDesc.java?rev=980659&view=auto
==============================================================================
--- hadoop/hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/plan/DropIndexDesc.java (added)
+++ hadoop/hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/plan/DropIndexDesc.java Fri Jul 30 06:40:04 2010
@@ -0,0 +1,66 @@
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements. See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership. The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package org.apache.hadoop.hive.ql.plan;
+
+public class DropIndexDesc {
+
+ private static final long serialVersionUID = 1L;
+
+ private String indexName;
+
+ private String tableName;
+
+ /**
+ * @param indexName
+ * @param tableName
+ */
+ public DropIndexDesc(String indexName, String tableName) {
+ super();
+ this.indexName = indexName;
+ this.tableName = tableName;
+ }
+
+ /**
+ * @return index name
+ */
+ public String getIndexName() {
+ return indexName;
+ }
+
+ /**
+ * @param indexName index name
+ */
+ public void setIndexName(String indexName) {
+ this.indexName = indexName;
+ }
+
+ /**
+ * @return table name
+ */
+ public String getTableName() {
+ return tableName;
+ }
+
+ /**
+ * @param tableName table name
+ */
+ public void setTableName(String tableName) {
+ this.tableName = tableName;
+ }
+
+}
Modified: hadoop/hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/plan/ExprNodeColumnDesc.java
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/plan/ExprNodeColumnDesc.java?rev=980659&r1=980658&r2=980659&view=diff
==============================================================================
--- hadoop/hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/plan/ExprNodeColumnDesc.java (original)
+++ hadoop/hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/plan/ExprNodeColumnDesc.java Fri Jul 30 06:40:04 2010
@@ -45,25 +45,25 @@ public class ExprNodeColumnDesc extends
/**
* Is the column a partitioned column.
*/
- private boolean isPartitionCol;
+ private boolean isPartitionColOrVirtualCol;
public ExprNodeColumnDesc() {
}
public ExprNodeColumnDesc(TypeInfo typeInfo, String column, String tabAlias,
- boolean isPartitionCol) {
+ boolean isPartitionColOrVirtualCol) {
super(typeInfo);
this.column = column;
this.tabAlias = tabAlias;
- this.isPartitionCol = isPartitionCol;
+ this.isPartitionColOrVirtualCol = isPartitionColOrVirtualCol;
}
public ExprNodeColumnDesc(Class<?> c, String column, String tabAlias,
- boolean isPartitionCol) {
+ boolean isPartitionColOrVirtualCol) {
super(TypeInfoFactory.getPrimitiveTypeInfoFromJavaPrimitive(c));
this.column = column;
this.tabAlias = tabAlias;
- this.isPartitionCol = isPartitionCol;
+ this.isPartitionColOrVirtualCol = isPartitionColOrVirtualCol;
}
public String getColumn() {
@@ -82,12 +82,12 @@ public class ExprNodeColumnDesc extends
this.tabAlias = tabAlias;
}
- public boolean getIsParititonCol() {
- return isPartitionCol;
+ public boolean getIsPartitionColOrVirtualCol() {
+ return isPartitionColOrVirtualCol;
}
- public void setIsPartitionCol(boolean isPartitionCol) {
- this.isPartitionCol = isPartitionCol;
+ public void setIsPartitionColOrVirtualCol(boolean isPartitionCol) {
+ this.isPartitionColOrVirtualCol = isPartitionCol;
}
@Override
@@ -110,7 +110,7 @@ public class ExprNodeColumnDesc extends
@Override
public ExprNodeDesc clone() {
- return new ExprNodeColumnDesc(typeInfo, column, tabAlias, isPartitionCol);
+ return new ExprNodeColumnDesc(typeInfo, column, tabAlias, isPartitionColOrVirtualCol);
}
@Override
Modified: hadoop/hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/plan/PartitionDesc.java
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/plan/PartitionDesc.java?rev=980659&r1=980658&r2=980659&view=diff
==============================================================================
--- hadoop/hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/plan/PartitionDesc.java (original)
+++ hadoop/hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/plan/PartitionDesc.java Fri Jul 30 06:40:04 2010
@@ -25,9 +25,9 @@ import java.util.Enumeration;
import java.util.Properties;
import org.apache.hadoop.hive.ql.exec.Utilities;
-import org.apache.hadoop.hive.ql.metadata.HiveException;
import org.apache.hadoop.hive.ql.io.HiveFileFormatUtils;
import org.apache.hadoop.hive.ql.io.HiveOutputFormat;
+import org.apache.hadoop.hive.ql.metadata.HiveException;
import org.apache.hadoop.hive.serde2.Deserializer;
import org.apache.hadoop.mapred.InputFormat;
import org.apache.hadoop.fs.Path;
Modified: hadoop/hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/plan/TableScanDesc.java
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/plan/TableScanDesc.java?rev=980659&r1=980658&r2=980659&view=diff
==============================================================================
--- hadoop/hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/plan/TableScanDesc.java (original)
+++ hadoop/hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/plan/TableScanDesc.java Fri Jul 30 06:40:04 2010
@@ -19,6 +19,9 @@
package org.apache.hadoop.hive.ql.plan;
import java.io.Serializable;
+import java.util.List;
+
+import org.apache.hadoop.hive.ql.metadata.VirtualColumn;
/**
* Table Scan Descriptor Currently, data is only read from a base source as part
@@ -30,6 +33,8 @@ public class TableScanDesc implements Se
private static final long serialVersionUID = 1L;
private String alias;
+
+ private List<VirtualColumn> virtualCols;
@SuppressWarnings("nls")
public TableScanDesc() {
@@ -38,6 +43,11 @@ public class TableScanDesc implements Se
public TableScanDesc(final String alias) {
this.alias = alias;
}
+
+ public TableScanDesc(final String alias, List<VirtualColumn> vcs) {
+ this.alias = alias;
+ this.virtualCols = vcs;
+ }
@Explain(displayName = "alias")
public String getAlias() {
@@ -47,4 +57,13 @@ public class TableScanDesc implements Se
public void setAlias(String alias) {
this.alias = alias;
}
+
+ public List<VirtualColumn> getVirtualCols() {
+ return virtualCols;
+ }
+
+ public void setVirtualCols(List<VirtualColumn> virtualCols) {
+ this.virtualCols = virtualCols;
+ }
+
}
Added: hadoop/hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/udf/generic/GenericUDAFCollectSet.java
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/udf/generic/GenericUDAFCollectSet.java?rev=980659&view=auto
==============================================================================
--- hadoop/hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/udf/generic/GenericUDAFCollectSet.java (added)
+++ hadoop/hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/udf/generic/GenericUDAFCollectSet.java Fri Jul 30 06:40:04 2010
@@ -0,0 +1,156 @@
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements. See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership. The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package org.apache.hadoop.hive.ql.udf.generic;
+
+import java.util.ArrayList;
+import java.util.HashSet;
+import java.util.Set;
+
+import org.apache.commons.logging.Log;
+import org.apache.commons.logging.LogFactory;
+import org.apache.hadoop.hive.ql.exec.Description;
+import org.apache.hadoop.hive.ql.exec.UDFArgumentTypeException;
+import org.apache.hadoop.hive.ql.metadata.HiveException;
+import org.apache.hadoop.hive.ql.parse.SemanticException;
+import org.apache.hadoop.hive.serde2.objectinspector.ObjectInspector;
+import org.apache.hadoop.hive.serde2.objectinspector.ObjectInspectorFactory;
+import org.apache.hadoop.hive.serde2.objectinspector.ObjectInspectorUtils;
+import org.apache.hadoop.hive.serde2.objectinspector.PrimitiveObjectInspector;
+import org.apache.hadoop.hive.serde2.objectinspector.StandardListObjectInspector;
+import org.apache.hadoop.hive.serde2.typeinfo.TypeInfo;
+
+/**
+ * GenericUDAFCollectSet
+ */
+@Description(name = "collect_set", value = "_FUNC_(x) - Returns a set of objects with duplicate elements eliminated")
+public class GenericUDAFCollectSet extends AbstractGenericUDAFResolver {
+
+ static final Log LOG = LogFactory.getLog(GenericUDAFCollectSet.class.getName());
+
+ public GenericUDAFCollectSet() {
+ }
+
+ @Override
+ public GenericUDAFEvaluator getEvaluator(TypeInfo[] parameters)
+ throws SemanticException {
+
+ if (parameters.length != 1) {
+ throw new UDFArgumentTypeException(parameters.length - 1,
+ "Exactly one argument is expected.");
+ }
+
+ if (parameters[0].getCategory() != ObjectInspector.Category.PRIMITIVE) {
+ throw new UDFArgumentTypeException(0,
+ "Only primitive type arguments are accepted but "
+ + parameters[0].getTypeName() + " was passed as parameter 1.");
+ }
+
+ return new GenericUDAFMkSetEvaluator();
+ }
+
+ public static class GenericUDAFMkSetEvaluator extends GenericUDAFEvaluator {
+
+ // For PARTIAL1 and COMPLETE: ObjectInspectors for original data
+ private PrimitiveObjectInspector inputOI;
+ // For PARTIAL2 and FINAL: ObjectInspectors for partial aggregations (list
+ // of objs)
+ private StandardListObjectInspector loi;
+
+ private StandardListObjectInspector internalMergeOI;
+
+ public ObjectInspector init(Mode m, ObjectInspector[] parameters)
+ throws HiveException {
+ super.init(m, parameters);
+ // init output object inspectors
+ // The output of a partial aggregation is a list
+ if (m == Mode.PARTIAL1) {
+ inputOI = (PrimitiveObjectInspector) parameters[0];
+ return ObjectInspectorFactory.getStandardListObjectInspector(inputOI);
+ } else {
+ internalMergeOI = (StandardListObjectInspector) parameters[0];
+ loi = (StandardListObjectInspector) ObjectInspectorUtils.getStandardObjectInspector(internalMergeOI);
+ return loi;
+ }
+ }
+
+ static class MkArrayAggregationBuffer implements AggregationBuffer {
+ Set<Object> container;
+ }
+
+ @Override
+ public void reset(AggregationBuffer agg) throws HiveException {
+ ((MkArrayAggregationBuffer) agg).container = new HashSet<Object>();
+ }
+
+ @Override
+ public AggregationBuffer getNewAggregationBuffer() throws HiveException {
+ MkArrayAggregationBuffer ret = new MkArrayAggregationBuffer();
+ reset(ret);
+ return ret;
+ }
+
+ //mapside
+ @Override
+ public void iterate(AggregationBuffer agg, Object[] parameters)
+ throws HiveException {
+ assert (parameters.length == 1);
+ Object p = parameters[0];
+
+ if (p != null) {
+ MkArrayAggregationBuffer myagg = (MkArrayAggregationBuffer) agg;
+ putIntoSet(p, myagg);
+ }
+ }
+
+ //mapside
+ @Override
+ public Object terminatePartial(AggregationBuffer agg) throws HiveException {
+ MkArrayAggregationBuffer myagg = (MkArrayAggregationBuffer) agg;
+ ArrayList<Object> ret = new ArrayList<Object>(myagg.container.size());
+ ret.addAll(myagg.container);
+ return ret;
+ }
+
+ @Override
+ public void merge(AggregationBuffer agg, Object partial)
+ throws HiveException {
+ MkArrayAggregationBuffer myagg = (MkArrayAggregationBuffer) agg;
+ ArrayList<Object> partialResult = (ArrayList<Object>) internalMergeOI.getList(partial);
+ for(Object i : partialResult) {
+ putIntoSet(i, myagg);
+ }
+ }
+
+ @Override
+ public Object terminate(AggregationBuffer agg) throws HiveException {
+ MkArrayAggregationBuffer myagg = (MkArrayAggregationBuffer) agg;
+ ArrayList<Object> ret = new ArrayList<Object>(myagg.container.size());
+ ret.addAll(myagg.container);
+ return ret;
+ }
+
+ private void putIntoSet(Object p, MkArrayAggregationBuffer myagg) {
+ if (myagg.container.contains(p))
+ return;
+ Object pCopy = ObjectInspectorUtils.copyToStandardObject(p,
+ this.inputOI);
+ myagg.container.add(pCopy);
+ }
+ }
+
+}
Modified: hadoop/hive/trunk/ql/src/test/org/apache/hadoop/hive/ql/hooks/PostExecutePrinter.java
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/ql/src/test/org/apache/hadoop/hive/ql/hooks/PostExecutePrinter.java?rev=980659&r1=980658&r2=980659&view=diff
==============================================================================
--- hadoop/hive/trunk/ql/src/test/org/apache/hadoop/hive/ql/hooks/PostExecutePrinter.java (original)
+++ hadoop/hive/trunk/ql/src/test/org/apache/hadoop/hive/ql/hooks/PostExecutePrinter.java Fri Jul 30 06:40:04 2010
@@ -127,6 +127,10 @@ public class PostExecutePrinter implemen
Dependency dep = it.getValue();
DependencyKey depK = it.getKey();
+ if(dep == null) {
+ continue;
+ }
+
StringBuilder sb = new StringBuilder();
sb.append("POSTHOOK: Lineage: ");
if (depK.getDataContainer().isPartition()) {
Added: hadoop/hive/trunk/ql/src/test/queries/clientnegative/bad_indextype.q
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/ql/src/test/queries/clientnegative/bad_indextype.q?rev=980659&view=auto
==============================================================================
--- hadoop/hive/trunk/ql/src/test/queries/clientnegative/bad_indextype.q (added)
+++ hadoop/hive/trunk/ql/src/test/queries/clientnegative/bad_indextype.q Fri Jul 30 06:40:04 2010
@@ -0,0 +1 @@
+CREATE INDEX srcpart_index_proj ON TABLE srcpart(key) AS 'UNKNOWN' WITH DEFERRED REBUILD;
Added: hadoop/hive/trunk/ql/src/test/queries/clientpositive/index_compact.q
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/ql/src/test/queries/clientpositive/index_compact.q?rev=980659&view=auto
==============================================================================
--- hadoop/hive/trunk/ql/src/test/queries/clientpositive/index_compact.q (added)
+++ hadoop/hive/trunk/ql/src/test/queries/clientpositive/index_compact.q Fri Jul 30 06:40:04 2010
@@ -0,0 +1,41 @@
+DROP INDEX srcpart_index_proj on srcpart;
+
+EXPLAIN
+CREATE INDEX srcpart_index_proj ON TABLE srcpart(key) as 'COMPACT' WITH DEFERRED REBUILD;
+CREATE INDEX srcpart_index_proj ON TABLE srcpart(key) as 'COMPACT' WITH DEFERRED REBUILD;
+ALTER INDEX srcpart_index_proj ON srcpart REBUILD;
+SELECT x.* FROM default__srcpart_srcpart_index_proj__ x WHERE x.ds = '2008-04-08' and x.hr = 11 ORDER BY key;
+
+SET hive.input.format=org.apache.hadoop.hive.ql.io.HiveInputFormat;
+INSERT OVERWRITE DIRECTORY "/tmp/index_test_index_result" SELECT `_bucketname` , `_offsets` FROM default__srcpart_srcpart_index_proj__ x WHERE x.key=100 AND x.ds = '2008-04-08';
+SET hive.index.compact.file=/tmp/index_test_index_result;
+SET hive.input.format=org.apache.hadoop.hive.ql.index.compact.HiveCompactIndexInputFormat;
+SELECT key, value FROM srcpart WHERE key=100 AND ds = '2008-04-08' ORDER BY key;
+
+SET hive.input.format=org.apache.hadoop.hive.ql.io.HiveInputFormat;
+INSERT OVERWRITE DIRECTORY "/tmp/index_test_index_result" SELECT `_bucketname` , `_offsets` FROM default__srcpart_srcpart_index_proj__ x WHERE x.key=100 AND x.ds = '2008-04-08' and x.hr = 11;
+SET hive.index.compact.file=/tmp/index_test_index_result;
+SET hive.input.format=org.apache.hadoop.hive.ql.index.compact.HiveCompactIndexInputFormat;
+SELECT key, value FROM srcpart WHERE key=100 AND ds = '2008-04-08' and hr = 11 ORDER BY key;
+
+SET hive.input.format=org.apache.hadoop.hive.ql.io.HiveInputFormat;
+SELECT key, value FROM srcpart WHERE key=100 AND ds = '2008-04-08' and hr = 11 ORDER BY key;
+
+DROP INDEX srcpart_index_proj on srcpart;
+
+EXPLAIN
+CREATE INDEX srcpart_index_proj ON TABLE srcpart(key) as 'COMPACT' WITH DEFERRED REBUILD;
+CREATE INDEX srcpart_index_proj ON TABLE srcpart(key) as 'COMPACT' WITH DEFERRED REBUILD;
+ALTER INDEX srcpart_index_proj ON srcpart REBUILD;
+SELECT x.* FROM default__srcpart_srcpart_index_proj__ x;
+
+SET hive.input.format=org.apache.hadoop.hive.ql.io.HiveInputFormat;
+INSERT OVERWRITE DIRECTORY "/tmp/index_result" SELECT `_bucketname` , `_offsets` FROM default__srcpart_srcpart_index_proj__ WHERE key=100;
+SET hive.index.compact.file=/tmp/index_result;
+SET hive.input.format=org.apache.hadoop.hive.ql.index.compact.HiveCompactIndexInputFormat;
+SELECT key, value FROM srcpart WHERE key=100 ORDER BY key;
+
+SET hive.input.format=org.apache.hadoop.hive.ql.io.HiveInputFormat;
+SELECT key, value FROM srcpart WHERE key=100 ORDER BY key;
+
+DROP INDEX srcpart_index_proj on srcpart;
Added: hadoop/hive/trunk/ql/src/test/queries/clientpositive/index_compact_1.q
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/ql/src/test/queries/clientpositive/index_compact_1.q?rev=980659&view=auto
==============================================================================
--- hadoop/hive/trunk/ql/src/test/queries/clientpositive/index_compact_1.q (added)
+++ hadoop/hive/trunk/ql/src/test/queries/clientpositive/index_compact_1.q Fri Jul 30 06:40:04 2010
@@ -0,0 +1,16 @@
+EXPLAIN
+CREATE INDEX src_index ON TABLE src(key) as 'COMPACT' WITH DEFERRED REBUILD;
+CREATE INDEX src_index ON TABLE src(key) as 'COMPACT' WITH DEFERRED REBUILD;
+ALTER INDEX src_index ON src REBUILD;
+SELECT x.* FROM default__src_src_index__ x ORDER BY key;
+
+SET hive.input.format=org.apache.hadoop.hive.ql.io.HiveInputFormat;
+INSERT OVERWRITE DIRECTORY "/tmp/index_result" SELECT `_bucketname` , `_offsets` FROM default__src_src_index__ WHERE key=100;
+SET hive.index.compact.file=/tmp/index_result;
+SET hive.input.format=org.apache.hadoop.hive.ql.index.compact.HiveCompactIndexInputFormat;
+SELECT key, value FROM src WHERE key=100 ORDER BY key;
+
+SET hive.input.format=org.apache.hadoop.hive.ql.io.HiveInputFormat;
+SELECT key, value FROM src WHERE key=100 ORDER BY key;
+
+DROP INDEX src_index on src;
\ No newline at end of file
Added: hadoop/hive/trunk/ql/src/test/queries/clientpositive/index_compact_2.q
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/ql/src/test/queries/clientpositive/index_compact_2.q?rev=980659&view=auto
==============================================================================
--- hadoop/hive/trunk/ql/src/test/queries/clientpositive/index_compact_2.q (added)
+++ hadoop/hive/trunk/ql/src/test/queries/clientpositive/index_compact_2.q Fri Jul 30 06:40:04 2010
@@ -0,0 +1,45 @@
+CREATE TABLE srcpart_rc (key int, value string) PARTITIONED BY (ds string, hr int) STORED AS RCFILE;
+
+INSERT OVERWRITE TABLE srcpart_rc PARTITION (ds='2008-04-08', hr=11) SELECT key, value FROM srcpart WHERE ds = '2008-04-08' AND hr = 11;
+INSERT OVERWRITE TABLE srcpart_rc PARTITION (ds='2008-04-08', hr=12) SELECT key, value FROM srcpart WHERE ds = '2008-04-08' AND hr = 12;
+INSERT OVERWRITE TABLE srcpart_rc PARTITION (ds='2008-04-09', hr=11) SELECT key, value FROM srcpart WHERE ds = '2008-04-09' AND hr = 11;
+INSERT OVERWRITE TABLE srcpart_rc PARTITION (ds='2008-04-09', hr=12) SELECT key, value FROM srcpart WHERE ds = '2008-04-09' AND hr = 12;
+
+CREATE INDEX srcpart_rc_index ON TABLE srcpart_rc(key) as 'COMPACT' WITH DEFERRED REBUILD;
+ALTER INDEX srcpart_rc_index ON srcpart_rc REBUILD;
+SELECT x.* FROM default__srcpart_rc_srcpart_rc_index__ x WHERE x.ds = '2008-04-08' and x.hr = 11 ORDER BY key;
+
+SET hive.input.format=org.apache.hadoop.hive.ql.io.HiveInputFormat;
+INSERT OVERWRITE DIRECTORY "/tmp/index_test_index_result" SELECT `_bucketname` , `_offsets` FROM default__srcpart_rc_srcpart_rc_index__ x WHERE x.key=100 AND x.ds = '2008-04-08';
+SET hive.index.compact.file=/tmp/index_test_index_result;
+SET hive.input.format=org.apache.hadoop.hive.ql.index.compact.HiveCompactIndexInputFormat;
+SELECT key, value FROM srcpart_rc WHERE key=100 AND ds = '2008-04-08' ORDER BY key;
+
+SET hive.input.format=org.apache.hadoop.hive.ql.io.HiveInputFormat;
+INSERT OVERWRITE DIRECTORY "/tmp/index_test_index_result" SELECT `_bucketname` , `_offsets` FROM default__srcpart_rc_srcpart_rc_index__ x WHERE x.key=100 AND x.ds = '2008-04-08' and x.hr = 11;
+SET hive.index.compact.file=/tmp/index_test_index_result;
+SET hive.input.format=org.apache.hadoop.hive.ql.index.compact.HiveCompactIndexInputFormat;
+SELECT key, value FROM srcpart_rc WHERE key=100 AND ds = '2008-04-08' and hr = 11 ORDER BY key;
+
+SET hive.input.format=org.apache.hadoop.hive.ql.io.HiveInputFormat;
+SELECT key, value FROM srcpart_rc WHERE key=100 AND ds = '2008-04-08' and hr = 11 ORDER BY key;
+
+DROP INDEX srcpart_rc_index on srcpart_rc;
+
+EXPLAIN
+CREATE INDEX srcpart_rc_index ON TABLE srcpart_rc(key) as 'COMPACT' WITH DEFERRED REBUILD;
+CREATE INDEX srcpart_rc_index ON TABLE srcpart_rc(key) as 'COMPACT' WITH DEFERRED REBUILD;
+ALTER INDEX srcpart_rc_index ON srcpart_rc REBUILD;
+SELECT x.* FROM default__srcpart_rc_srcpart_rc_index__ x ORDER BY key;
+
+SET hive.input.format=org.apache.hadoop.hive.ql.io.HiveInputFormat;
+INSERT OVERWRITE DIRECTORY "/tmp/index_result" SELECT `_bucketname` , `_offsets` FROM default__srcpart_rc_srcpart_rc_index__ WHERE key=100;
+SET hive.index.compact.file=/tmp/index_result;
+SET hive.input.format=org.apache.hadoop.hive.ql.index.compact.HiveCompactIndexInputFormat;
+SELECT key, value FROM srcpart_rc WHERE key=100 ORDER BY key;
+
+SET hive.input.format=org.apache.hadoop.hive.ql.io.HiveInputFormat;
+SELECT key, value FROM srcpart_rc WHERE key=100 ORDER BY key;
+
+DROP INDEX srcpart_rc_index on srcpart_rc;
+DROP TABLE srcpart_rc;
\ No newline at end of file
Added: hadoop/hive/trunk/ql/src/test/queries/clientpositive/index_compact_3.q
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/ql/src/test/queries/clientpositive/index_compact_3.q?rev=980659&view=auto
==============================================================================
--- hadoop/hive/trunk/ql/src/test/queries/clientpositive/index_compact_3.q (added)
+++ hadoop/hive/trunk/ql/src/test/queries/clientpositive/index_compact_3.q Fri Jul 30 06:40:04 2010
@@ -0,0 +1,19 @@
+CREATE TABLE src_index_test_rc (key int, value string) STORED AS RCFILE;
+
+INSERT OVERWRITE TABLE src_index_test_rc SELECT * FROM src;
+
+CREATE INDEX src_index ON TABLE src_index_test_rc(key) as 'COMPACT' WITH DEFERRED REBUILD;
+ALTER INDEX src_index ON src_index_test_rc REBUILD;
+SELECT x.* FROM default__src_index_test_rc_src_index__ x ORDER BY key;
+
+SET hive.input.format=org.apache.hadoop.hive.ql.io.HiveInputFormat;
+INSERT OVERWRITE DIRECTORY "/tmp/index_result" SELECT `_bucketname` , `_offsets` FROM default__src_index_test_rc_src_index__ WHERE key=100;
+SET hive.index.compact.file=/tmp/index_result;
+SET hive.input.format=org.apache.hadoop.hive.ql.index.compact.HiveCompactIndexInputFormat;
+SELECT key, value FROM src_index_test_rc WHERE key=100 ORDER BY key;
+
+SET hive.input.format=org.apache.hadoop.hive.ql.io.HiveInputFormat;
+SELECT key, value FROM src_index_test_rc WHERE key=100 ORDER BY key;
+
+DROP INDEX src_index on src_index_test_rc;
+DROP TABLE src_index_test_rc;
\ No newline at end of file
Added: hadoop/hive/trunk/ql/src/test/queries/clientpositive/index_creation.q
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/ql/src/test/queries/clientpositive/index_creation.q?rev=980659&view=auto
==============================================================================
--- hadoop/hive/trunk/ql/src/test/queries/clientpositive/index_creation.q (added)
+++ hadoop/hive/trunk/ql/src/test/queries/clientpositive/index_creation.q Fri Jul 30 06:40:04 2010
@@ -0,0 +1,33 @@
+drop index src_index_2 on src;
+drop index src_index_3 on src;
+drop index src_index_4 on src;
+drop index src_index_5 on src;
+drop index src_index_6 on src;
+drop index src_index_7 on src;
+
+create index src_index_2 on table src(key) as 'compact' WITH DEFERRED REBUILD;
+desc extended default__src_src_index_2__;
+
+create index src_index_3 on table src(key) as 'compact' WITH DEFERRED REBUILD in table src_idx_src_index_3;
+desc extended src_idx_src_index_3;
+
+create index src_index_4 on table src(key) as 'compact' WITH DEFERRED REBUILD ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t' STORED AS TEXTFILE;
+desc extended default__src_src_index_4__;
+
+create index src_index_5 on table src(key) as 'compact' WITH DEFERRED REBUILD ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t' ESCAPED BY '\\';
+desc extended default__src_src_index_5__;
+
+create index src_index_6 on table src(key) as 'compact' WITH DEFERRED REBUILD STORED AS RCFILE;
+desc extended default__src_src_index_6__;
+
+create index src_index_7 on table src(key) as 'compact' WITH DEFERRED REBUILD in table src_idx_src_index_7 STORED AS RCFILE;
+desc extended src_idx_src_index_7;
+
+drop index src_index_2 on src;
+drop index src_index_3 on src;
+drop index src_index_4 on src;
+drop index src_index_5 on src;
+drop index src_index_6 on src;
+drop index src_index_7 on src;
+
+show tables;
Modified: hadoop/hive/trunk/ql/src/test/queries/clientpositive/udf_index.q
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/ql/src/test/queries/clientpositive/udf_index.q?rev=980659&r1=980658&r2=980659&view=diff
==============================================================================
--- hadoop/hive/trunk/ql/src/test/queries/clientpositive/udf_index.q (original)
+++ hadoop/hive/trunk/ql/src/test/queries/clientpositive/udf_index.q Fri Jul 30 06:40:04 2010
@@ -1,2 +1,2 @@
-DESCRIBE FUNCTION index;
-DESCRIBE FUNCTION EXTENDED index;
+DESCRIBE FUNCTION `index`;
+DESCRIBE FUNCTION EXTENDED `index`;
Added: hadoop/hive/trunk/ql/src/test/queries/clientpositive/virtual_column.q
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/ql/src/test/queries/clientpositive/virtual_column.q?rev=980659&view=auto
==============================================================================
--- hadoop/hive/trunk/ql/src/test/queries/clientpositive/virtual_column.q (added)
+++ hadoop/hive/trunk/ql/src/test/queries/clientpositive/virtual_column.q Fri Jul 30 06:40:04 2010
@@ -0,0 +1,19 @@
+select INPUT__FILE__NAME, key, BLOCK__OFFSET__INSIDE__FILE from src;
+
+select key, count(INPUT__FILE__NAME) from src group by key order by key;
+
+select INPUT__FILE__NAME, key, collect_set(BLOCK__OFFSET__INSIDE__FILE) from src group by INPUT__FILE__NAME, key order by key;
+
+select * from src where BLOCK__OFFSET__INSIDE__FILE > 12000 order by key;
+
+select * from src where BLOCK__OFFSET__INSIDE__FILE > 5800 order by key;
+
+
+CREATE TABLE src_index_test_rc (key int, value string) STORED AS RCFILE;
+
+set hive.io.rcfile.record.buffer.size = 1024;
+INSERT OVERWRITE TABLE src_index_test_rc SELECT * FROM src;
+select INPUT__FILE__NAME, key, BLOCK__OFFSET__INSIDE__FILE from src_index_test_rc order by key;
+
+DROP TABLE src_index_test_rc;
+DROP INDEX src_index on src_index_test_rc;
Added: hadoop/hive/trunk/ql/src/test/results/clientnegative/bad_indextype.q.out
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/ql/src/test/results/clientnegative/bad_indextype.q.out?rev=980659&view=auto
==============================================================================
--- hadoop/hive/trunk/ql/src/test/results/clientnegative/bad_indextype.q.out (added)
+++ hadoop/hive/trunk/ql/src/test/results/clientnegative/bad_indextype.q.out Fri Jul 30 06:40:04 2010
@@ -0,0 +1 @@
+FAILED: Error in semantic analysis: class name provided for index handler not found.
Modified: hadoop/hive/trunk/ql/src/test/results/clientpositive/bucketmapjoin1.q.out
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/ql/src/test/results/clientpositive/bucketmapjoin1.q.out?rev=980659&r1=980658&r2=980659&view=diff
==============================================================================
--- hadoop/hive/trunk/ql/src/test/results/clientpositive/bucketmapjoin1.q.out (original)
+++ hadoop/hive/trunk/ql/src/test/results/clientpositive/bucketmapjoin1.q.out Fri Jul 30 06:40:04 2010
@@ -107,7 +107,7 @@ STAGE PLANS:
keys:
0 [Column[key]]
1 [Column[key]]
- outputColumnNames: _col0, _col1, _col3, _col4
+ outputColumnNames: _col0, _col1, _col5, _col6
Position of Big Table: 0
Select Operator
expressions:
@@ -115,15 +115,15 @@ STAGE PLANS:
type: int
expr: _col1
type: string
- expr: _col3
+ expr: _col5
type: string
- expr: _col4
+ expr: _col6
type: string
- outputColumnNames: _col0, _col1, _col3, _col4
+ outputColumnNames: _col0, _col1, _col5, _col6
Filter Operator
isSamplingPred: false
predicate:
- expr: (_col4 = '2008-04-08')
+ expr: (_col6 = '2008-04-08')
type: boolean
Select Operator
expressions:
@@ -131,13 +131,13 @@ STAGE PLANS:
type: int
expr: _col1
type: string
- expr: _col3
+ expr: _col5
type: string
outputColumnNames: _col0, _col1, _col2
File Output Operator
compressed: false
GlobalTableId: 1
- directory: pfile:/data/users/jssarma/hive_trunk/build/ql/scratchdir/hive_2010-07-25_11-40-19_167_2673747164055048229/-ext-10002
+ directory: pfile:/Users/heyongqiang/Documents/workspace/Hive-2/build/ql/scratchdir/hive_2010-07-29_10-52-35_366_8749407810388390396/-ext-10002
NumFilesPerFileSink: 1
table:
input format: org.apache.hadoop.mapred.TextInputFormat
@@ -148,12 +148,12 @@ STAGE PLANS:
columns.types string:string:string
file.inputformat org.apache.hadoop.mapred.TextInputFormat
file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- location pfile:/data/users/jssarma/hive_trunk/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
+ location pfile:/Users/heyongqiang/Documents/workspace/Hive-2/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
name bucketmapjoin_tmp_result
serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- transient_lastDdlTime 1280083219
+ transient_lastDdlTime 1280425955
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: bucketmapjoin_tmp_result
TotalFiles: 1
@@ -183,7 +183,7 @@ STAGE PLANS:
keys:
0 [Column[key]]
1 [Column[key]]
- outputColumnNames: _col0, _col1, _col3, _col4
+ outputColumnNames: _col0, _col1, _col5, _col6
Position of Big Table: 0
Select Operator
expressions:
@@ -191,15 +191,15 @@ STAGE PLANS:
type: int
expr: _col1
type: string
- expr: _col3
+ expr: _col5
type: string
- expr: _col4
+ expr: _col6
type: string
- outputColumnNames: _col0, _col1, _col3, _col4
+ outputColumnNames: _col0, _col1, _col5, _col6
Filter Operator
isSamplingPred: false
predicate:
- expr: (_col4 = '2008-04-08')
+ expr: (_col6 = '2008-04-08')
type: boolean
Select Operator
expressions:
@@ -207,13 +207,13 @@ STAGE PLANS:
type: int
expr: _col1
type: string
- expr: _col3
+ expr: _col5
type: string
outputColumnNames: _col0, _col1, _col2
File Output Operator
compressed: false
GlobalTableId: 1
- directory: pfile:/data/users/jssarma/hive_trunk/build/ql/scratchdir/hive_2010-07-25_11-40-19_167_2673747164055048229/-ext-10002
+ directory: pfile:/Users/heyongqiang/Documents/workspace/Hive-2/build/ql/scratchdir/hive_2010-07-29_10-52-35_366_8749407810388390396/-ext-10002
NumFilesPerFileSink: 1
table:
input format: org.apache.hadoop.mapred.TextInputFormat
@@ -224,12 +224,12 @@ STAGE PLANS:
columns.types string:string:string
file.inputformat org.apache.hadoop.mapred.TextInputFormat
file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- location pfile:/data/users/jssarma/hive_trunk/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
+ location pfile:/Users/heyongqiang/Documents/workspace/Hive-2/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
name bucketmapjoin_tmp_result
serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- transient_lastDdlTime 1280083219
+ transient_lastDdlTime 1280425955
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: bucketmapjoin_tmp_result
TotalFiles: 1
@@ -238,15 +238,15 @@ STAGE PLANS:
Alias Bucket Base File Name Mapping:
b {srcbucket20.txt=[srcbucket20.txt, srcbucket22.txt], srcbucket21.txt=[srcbucket21.txt, srcbucket23.txt]}
Alias Bucket File Name Mapping:
- b {pfile:/data/users/jssarma/hive_trunk/build/ql/test/data/warehouse/srcbucket_mapjoin/srcbucket20.txt=[pfile:/data/users/jssarma/hive_trunk/build/ql/test/data/warehouse/srcbucket_mapjoin_part/ds=2008-04-08/srcbucket20.txt, pfile:/data/users/jssarma/hive_trunk/build/ql/test/data/warehouse/srcbucket_mapjoin_part/ds=2008-04-08/srcbucket22.txt], pfile:/data/users/jssarma/hive_trunk/build/ql/test/data/warehouse/srcbucket_mapjoin/srcbucket21.txt=[pfile:/data/users/jssarma/hive_trunk/build/ql/test/data/warehouse/srcbucket_mapjoin_part/ds=2008-04-08/srcbucket21.txt, pfile:/data/users/jssarma/hive_trunk/build/ql/test/data/warehouse/srcbucket_mapjoin_part/ds=2008-04-08/srcbucket23.txt]}
+ b {pfile:/Users/heyongqiang/Documents/workspace/Hive-2/build/ql/test/data/warehouse/srcbucket_mapjoin/srcbucket20.txt=[pfile:/Users/heyongqiang/Documents/workspace/Hive-2/build/ql/test/data/warehouse/srcbucket_mapjoin_part/ds=2008-04-08/srcbucket20.txt, pfile:/Users/heyongqiang/Documents/workspace/Hive-2/build/ql/test/data/warehouse/srcbucket_mapjoin_part/ds=2008-04-08/srcbucket22.txt], pfile:/Users/heyongqiang/Documents/workspace/Hive-2/build/ql/test/data/warehouse/srcbucket_mapjoin/srcbucket21.txt=[pfile:/Users/heyongqiang/Documents/workspace/Hive-2/build/ql/test/data/warehouse/srcbucket_mapjoin_part/ds=2008-04-08/srcbucket21.txt, pfile:/Users/heyongqiang/Documents/workspace/Hive-2/build/ql/test/data/warehouse/srcbucket_mapjoin_part/ds=2008-04-08/srcbucket23.txt]}
Alias Bucket Output File Name Mapping:
- pfile:/data/users/jssarma/hive_trunk/build/ql/test/data/warehouse/srcbucket_mapjoin/srcbucket20.txt 0
- pfile:/data/users/jssarma/hive_trunk/build/ql/test/data/warehouse/srcbucket_mapjoin/srcbucket21.txt 1
+ pfile:/Users/heyongqiang/Documents/workspace/Hive-2/build/ql/test/data/warehouse/srcbucket_mapjoin/srcbucket20.txt 0
+ pfile:/Users/heyongqiang/Documents/workspace/Hive-2/build/ql/test/data/warehouse/srcbucket_mapjoin/srcbucket21.txt 1
Needs Tagging: false
Path -> Alias:
- pfile:/data/users/jssarma/hive_trunk/build/ql/test/data/warehouse/srcbucket_mapjoin [a]
+ pfile:/Users/heyongqiang/Documents/workspace/Hive-2/build/ql/test/data/warehouse/srcbucket_mapjoin [a]
Path -> Partition:
- pfile:/data/users/jssarma/hive_trunk/build/ql/test/data/warehouse/srcbucket_mapjoin
+ pfile:/Users/heyongqiang/Documents/workspace/Hive-2/build/ql/test/data/warehouse/srcbucket_mapjoin
Partition
base file name: srcbucket_mapjoin
input format: org.apache.hadoop.mapred.TextInputFormat
@@ -258,12 +258,12 @@ STAGE PLANS:
columns.types int:string
file.inputformat org.apache.hadoop.mapred.TextInputFormat
file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- location pfile:/data/users/jssarma/hive_trunk/build/ql/test/data/warehouse/srcbucket_mapjoin
+ location pfile:/Users/heyongqiang/Documents/workspace/Hive-2/build/ql/test/data/warehouse/srcbucket_mapjoin
name srcbucket_mapjoin
serialization.ddl struct srcbucket_mapjoin { i32 key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- transient_lastDdlTime 1280083214
+ transient_lastDdlTime 1280425951
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
input format: org.apache.hadoop.mapred.TextInputFormat
@@ -275,12 +275,12 @@ STAGE PLANS:
columns.types int:string
file.inputformat org.apache.hadoop.mapred.TextInputFormat
file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- location pfile:/data/users/jssarma/hive_trunk/build/ql/test/data/warehouse/srcbucket_mapjoin
+ location pfile:/Users/heyongqiang/Documents/workspace/Hive-2/build/ql/test/data/warehouse/srcbucket_mapjoin
name srcbucket_mapjoin
serialization.ddl struct srcbucket_mapjoin { i32 key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- transient_lastDdlTime 1280083214
+ transient_lastDdlTime 1280425951
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: srcbucket_mapjoin
name: srcbucket_mapjoin
@@ -292,14 +292,14 @@ STAGE PLANS:
Move Operator
files:
hdfs directory: true
- source: pfile:/data/users/jssarma/hive_trunk/build/ql/scratchdir/hive_2010-07-25_11-40-19_167_2673747164055048229/-ext-10002
- destination: pfile:/data/users/jssarma/hive_trunk/build/ql/scratchdir/hive_2010-07-25_11-40-19_167_2673747164055048229/-ext-10000
+ source: pfile:/Users/heyongqiang/Documents/workspace/Hive-2/build/ql/scratchdir/hive_2010-07-29_10-52-35_366_8749407810388390396/-ext-10002
+ destination: pfile:/Users/heyongqiang/Documents/workspace/Hive-2/build/ql/scratchdir/hive_2010-07-29_10-52-35_366_8749407810388390396/-ext-10000
Stage: Stage-0
Move Operator
tables:
replace: true
- source: pfile:/data/users/jssarma/hive_trunk/build/ql/scratchdir/hive_2010-07-25_11-40-19_167_2673747164055048229/-ext-10000
+ source: pfile:/Users/heyongqiang/Documents/workspace/Hive-2/build/ql/scratchdir/hive_2010-07-29_10-52-35_366_8749407810388390396/-ext-10000
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -309,20 +309,20 @@ STAGE PLANS:
columns.types string:string:string
file.inputformat org.apache.hadoop.mapred.TextInputFormat
file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- location pfile:/data/users/jssarma/hive_trunk/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
+ location pfile:/Users/heyongqiang/Documents/workspace/Hive-2/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
name bucketmapjoin_tmp_result
serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- transient_lastDdlTime 1280083219
+ transient_lastDdlTime 1280425955
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: bucketmapjoin_tmp_result
- tmp directory: pfile:/data/users/jssarma/hive_trunk/build/ql/scratchdir/hive_2010-07-25_11-40-19_167_2673747164055048229/-ext-10001
+ tmp directory: pfile:/Users/heyongqiang/Documents/workspace/Hive-2/build/ql/scratchdir/hive_2010-07-29_10-52-35_366_8749407810388390396/-ext-10001
Stage: Stage-2
Map Reduce
Alias -> Map Operator Tree:
- pfile:/data/users/jssarma/hive_trunk/build/ql/scratchdir/hive_2010-07-25_11-40-19_167_2673747164055048229/-ext-10002
+ pfile:/Users/heyongqiang/Documents/workspace/Hive-2/build/ql/scratchdir/hive_2010-07-29_10-52-35_366_8749407810388390396/-ext-10002
Reduce Output Operator
sort order:
Map-reduce partition columns:
@@ -338,9 +338,9 @@ STAGE PLANS:
type: string
Needs Tagging: false
Path -> Alias:
- pfile:/data/users/jssarma/hive_trunk/build/ql/scratchdir/hive_2010-07-25_11-40-19_167_2673747164055048229/-ext-10002 [pfile:/data/users/jssarma/hive_trunk/build/ql/scratchdir/hive_2010-07-25_11-40-19_167_2673747164055048229/-ext-10002]
+ pfile:/Users/heyongqiang/Documents/workspace/Hive-2/build/ql/scratchdir/hive_2010-07-29_10-52-35_366_8749407810388390396/-ext-10002 [pfile:/Users/heyongqiang/Documents/workspace/Hive-2/build/ql/scratchdir/hive_2010-07-29_10-52-35_366_8749407810388390396/-ext-10002]
Path -> Partition:
- pfile:/data/users/jssarma/hive_trunk/build/ql/scratchdir/hive_2010-07-25_11-40-19_167_2673747164055048229/-ext-10002
+ pfile:/Users/heyongqiang/Documents/workspace/Hive-2/build/ql/scratchdir/hive_2010-07-29_10-52-35_366_8749407810388390396/-ext-10002
Partition
base file name: -ext-10002
input format: org.apache.hadoop.mapred.TextInputFormat
@@ -351,12 +351,12 @@ STAGE PLANS:
columns.types string:string:string
file.inputformat org.apache.hadoop.mapred.TextInputFormat
file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- location pfile:/data/users/jssarma/hive_trunk/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
+ location pfile:/Users/heyongqiang/Documents/workspace/Hive-2/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
name bucketmapjoin_tmp_result
serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- transient_lastDdlTime 1280083219
+ transient_lastDdlTime 1280425955
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
input format: org.apache.hadoop.mapred.TextInputFormat
@@ -367,12 +367,12 @@ STAGE PLANS:
columns.types string:string:string
file.inputformat org.apache.hadoop.mapred.TextInputFormat
file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- location pfile:/data/users/jssarma/hive_trunk/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
+ location pfile:/Users/heyongqiang/Documents/workspace/Hive-2/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
name bucketmapjoin_tmp_result
serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- transient_lastDdlTime 1280083219
+ transient_lastDdlTime 1280425955
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: bucketmapjoin_tmp_result
name: bucketmapjoin_tmp_result
@@ -381,7 +381,7 @@ STAGE PLANS:
File Output Operator
compressed: false
GlobalTableId: 0
- directory: pfile:/data/users/jssarma/hive_trunk/build/ql/scratchdir/hive_2010-07-25_11-40-19_167_2673747164055048229/-ext-10000
+ directory: pfile:/Users/heyongqiang/Documents/workspace/Hive-2/build/ql/scratchdir/hive_2010-07-29_10-52-35_366_8749407810388390396/-ext-10000
NumFilesPerFileSink: 1
table:
input format: org.apache.hadoop.mapred.TextInputFormat
@@ -392,12 +392,12 @@ STAGE PLANS:
columns.types string:string:string
file.inputformat org.apache.hadoop.mapred.TextInputFormat
file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- location pfile:/data/users/jssarma/hive_trunk/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
+ location pfile:/Users/heyongqiang/Documents/workspace/Hive-2/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
name bucketmapjoin_tmp_result
serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- transient_lastDdlTime 1280083219
+ transient_lastDdlTime 1280425955
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: bucketmapjoin_tmp_result
TotalFiles: 1
@@ -426,11 +426,11 @@ POSTHOOK: Lineage: bucketmapjoin_tmp_res
PREHOOK: query: select count(1) from bucketmapjoin_tmp_result
PREHOOK: type: QUERY
PREHOOK: Input: default@bucketmapjoin_tmp_result
-PREHOOK: Output: file:/tmp/jssarma/hive_2010-07-25_11-40-25_482_8863784295269010139/-mr-10000
+PREHOOK: Output: file:/var/folders/6g/6grtCwPMEf4sqHUPpy6xQG9ByHg/-Tmp-/heyongqiang/hive_2010-07-29_10-52-47_947_1373971970810832824/-mr-10000
POSTHOOK: query: select count(1) from bucketmapjoin_tmp_result
POSTHOOK: type: QUERY
POSTHOOK: Input: default@bucketmapjoin_tmp_result
-POSTHOOK: Output: file:/tmp/jssarma/hive_2010-07-25_11-40-25_482_8863784295269010139/-mr-10000
+POSTHOOK: Output: file:/var/folders/6g/6grtCwPMEf4sqHUPpy6xQG9ByHg/-Tmp-/heyongqiang/hive_2010-07-29_10-52-47_947_1373971970810832824/-mr-10000
POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:key, type:int, comment:null), ]
POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:value, type:string, comment:null), ]
POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin_part)b.FieldSchema(name:key, type:int, comment:null), ]
@@ -479,11 +479,11 @@ POSTHOOK: Lineage: bucketmapjoin_tmp_res
PREHOOK: query: select count(1) from bucketmapjoin_tmp_result
PREHOOK: type: QUERY
PREHOOK: Input: default@bucketmapjoin_tmp_result
-PREHOOK: Output: file:/tmp/jssarma/hive_2010-07-25_11-40-37_529_1833707518210532364/-mr-10000
+PREHOOK: Output: file:/var/folders/6g/6grtCwPMEf4sqHUPpy6xQG9ByHg/-Tmp-/heyongqiang/hive_2010-07-29_10-53-06_994_5152208779378490082/-mr-10000
POSTHOOK: query: select count(1) from bucketmapjoin_tmp_result
POSTHOOK: type: QUERY
POSTHOOK: Input: default@bucketmapjoin_tmp_result
-POSTHOOK: Output: file:/tmp/jssarma/hive_2010-07-25_11-40-37_529_1833707518210532364/-mr-10000
+POSTHOOK: Output: file:/var/folders/6g/6grtCwPMEf4sqHUPpy6xQG9ByHg/-Tmp-/heyongqiang/hive_2010-07-29_10-53-06_994_5152208779378490082/-mr-10000
POSTHOOK: Lineage: bucketmapjoin_hash_result_1.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ]
POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ]
POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ]
@@ -522,14 +522,14 @@ on a.key = b.key
PREHOOK: type: QUERY
PREHOOK: Input: default@bucketmapjoin_hash_result_2
PREHOOK: Input: default@bucketmapjoin_hash_result_1
-PREHOOK: Output: file:/tmp/jssarma/hive_2010-07-25_11-40-42_954_929355026598795712/-mr-10000
+PREHOOK: Output: file:/var/folders/6g/6grtCwPMEf4sqHUPpy6xQG9ByHg/-Tmp-/heyongqiang/hive_2010-07-29_10-53-15_481_7356264960905577318/-mr-10000
POSTHOOK: query: select a.key-b.key, a.value1-b.value1, a.value2-b.value2
from bucketmapjoin_hash_result_1 a left outer join bucketmapjoin_hash_result_2 b
on a.key = b.key
POSTHOOK: type: QUERY
POSTHOOK: Input: default@bucketmapjoin_hash_result_2
POSTHOOK: Input: default@bucketmapjoin_hash_result_1
-POSTHOOK: Output: file:/tmp/jssarma/hive_2010-07-25_11-40-42_954_929355026598795712/-mr-10000
+POSTHOOK: Output: file:/var/folders/6g/6grtCwPMEf4sqHUPpy6xQG9ByHg/-Tmp-/heyongqiang/hive_2010-07-29_10-53-15_481_7356264960905577318/-mr-10000
POSTHOOK: Lineage: bucketmapjoin_hash_result_1.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ]
POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ]
POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ]
@@ -599,7 +599,7 @@ STAGE PLANS:
keys:
0 [Column[key]]
1 [Column[key]]
- outputColumnNames: _col0, _col1, _col3, _col4
+ outputColumnNames: _col0, _col1, _col5, _col6
Position of Big Table: 1
Select Operator
expressions:
@@ -607,15 +607,15 @@ STAGE PLANS:
type: int
expr: _col1
type: string
- expr: _col3
+ expr: _col5
type: string
- expr: _col4
+ expr: _col6
type: string
- outputColumnNames: _col0, _col1, _col3, _col4
+ outputColumnNames: _col0, _col1, _col5, _col6
Filter Operator
isSamplingPred: false
predicate:
- expr: (_col4 = '2008-04-08')
+ expr: (_col6 = '2008-04-08')
type: boolean
Select Operator
expressions:
@@ -623,13 +623,13 @@ STAGE PLANS:
type: int
expr: _col1
type: string
- expr: _col3
+ expr: _col5
type: string
outputColumnNames: _col0, _col1, _col2
File Output Operator
compressed: false
GlobalTableId: 1
- directory: pfile:/data/users/jssarma/hive_trunk/build/ql/scratchdir/hive_2010-07-25_11-40-45_690_2669369780343064476/-ext-10002
+ directory: pfile:/Users/heyongqiang/Documents/workspace/Hive-2/build/ql/scratchdir/hive_2010-07-29_10-53-20_871_6244434778770465214/-ext-10002
NumFilesPerFileSink: 1
table:
input format: org.apache.hadoop.mapred.TextInputFormat
@@ -640,12 +640,12 @@ STAGE PLANS:
columns.types string:string:string
file.inputformat org.apache.hadoop.mapred.TextInputFormat
file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- location pfile:/data/users/jssarma/hive_trunk/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
+ location pfile:/Users/heyongqiang/Documents/workspace/Hive-2/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
name bucketmapjoin_tmp_result
serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- transient_lastDdlTime 1280083237
+ transient_lastDdlTime 1280425986
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: bucketmapjoin_tmp_result
TotalFiles: 1
@@ -670,7 +670,7 @@ STAGE PLANS:
keys:
0 [Column[key]]
1 [Column[key]]
- outputColumnNames: _col0, _col1, _col3, _col4
+ outputColumnNames: _col0, _col1, _col5, _col6
Position of Big Table: 1
Select Operator
expressions:
@@ -678,15 +678,15 @@ STAGE PLANS:
type: int
expr: _col1
type: string
- expr: _col3
+ expr: _col5
type: string
- expr: _col4
+ expr: _col6
type: string
- outputColumnNames: _col0, _col1, _col3, _col4
+ outputColumnNames: _col0, _col1, _col5, _col6
Filter Operator
isSamplingPred: false
predicate:
- expr: (_col4 = '2008-04-08')
+ expr: (_col6 = '2008-04-08')
type: boolean
Select Operator
expressions:
@@ -694,13 +694,13 @@ STAGE PLANS:
type: int
expr: _col1
type: string
- expr: _col3
+ expr: _col5
type: string
outputColumnNames: _col0, _col1, _col2
File Output Operator
compressed: false
GlobalTableId: 1
- directory: pfile:/data/users/jssarma/hive_trunk/build/ql/scratchdir/hive_2010-07-25_11-40-45_690_2669369780343064476/-ext-10002
+ directory: pfile:/Users/heyongqiang/Documents/workspace/Hive-2/build/ql/scratchdir/hive_2010-07-29_10-53-20_871_6244434778770465214/-ext-10002
NumFilesPerFileSink: 1
table:
input format: org.apache.hadoop.mapred.TextInputFormat
@@ -711,12 +711,12 @@ STAGE PLANS:
columns.types string:string:string
file.inputformat org.apache.hadoop.mapred.TextInputFormat
file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- location pfile:/data/users/jssarma/hive_trunk/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
+ location pfile:/Users/heyongqiang/Documents/workspace/Hive-2/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
name bucketmapjoin_tmp_result
serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- transient_lastDdlTime 1280083237
+ transient_lastDdlTime 1280425986
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: bucketmapjoin_tmp_result
TotalFiles: 1
@@ -725,17 +725,17 @@ STAGE PLANS:
Alias Bucket Base File Name Mapping:
a {srcbucket20.txt=[srcbucket20.txt], srcbucket21.txt=[srcbucket21.txt], srcbucket22.txt=[srcbucket20.txt], srcbucket23.txt=[srcbucket21.txt]}
Alias Bucket File Name Mapping:
- a {pfile:/data/users/jssarma/hive_trunk/build/ql/test/data/warehouse/srcbucket_mapjoin_part/ds=2008-04-08/srcbucket20.txt=[pfile:/data/users/jssarma/hive_trunk/build/ql/test/data/warehouse/srcbucket_mapjoin/srcbucket20.txt], pfile:/data/users/jssarma/hive_trunk/build/ql/test/data/warehouse/srcbucket_mapjoin_part/ds=2008-04-08/srcbucket21.txt=[pfile:/data/users/jssarma/hive_trunk/build/ql/test/data/warehouse/srcbucket_mapjoin/srcbucket21.txt], pfile:/data/users/jssarma/hive_trunk/build/ql/test/data/warehouse/srcbucket_mapjoin_part/ds=2008-04-08/srcbucket22.txt=[pfile:/data/users/jssarma/hive_trunk/build/ql/test/data/warehouse/srcbucket_mapjoin/srcbucket20.txt], pfile:/data/users/jssarma/hive_trunk/build/ql/test/data/warehouse/srcbucket_mapjoin_part/ds=2008-04-08/srcbucket23.txt=[pfile:/data/users/jssarma/hive_trunk/build/ql/test/data/warehouse/srcbucket_mapjoin/srcbucket21.txt]}
+ a {pfile:/Users/heyongqiang/Documents/workspace/Hive-2/build/ql/test/data/warehouse/srcbucket_mapjoin_part/ds=2008-04-08/srcbucket20.txt=[pfile:/Users/heyongqiang/Documents/workspace/Hive-2/build/ql/test/data/warehouse/srcbucket_mapjoin/srcbucket20.txt], pfile:/Users/heyongqiang/Documents/workspace/Hive-2/build/ql/test/data/warehouse/srcbucket_mapjoin_part/ds=2008-04-08/srcbucket21.txt=[pfile:/Users/heyongqiang/Documents/workspace/Hive-2/build/ql/test/data/warehouse/srcbucket_mapjoin/srcbucket21.txt], pfile:/Users/heyongqiang/Documents/workspace/Hive-2/build/ql/test/data/warehouse/srcbucket_mapjoin_part/ds=2008-04-08/srcbucket22.txt=[pfile:/Users/heyongqiang/Documents/workspace/Hive-2/build/ql/test/data/warehouse/srcbucket_mapjoin/srcbucket20.txt], pfile:/Users/heyongqiang/Documents/workspace/Hive-2/build/ql/test/data/warehouse/srcbucket_mapjoin_part/ds=2008-04-08/srcbucket23.txt=[pfile:/Users/heyongqiang/Documents/workspace/Hive-2/build/ql/test/data/warehous
e/srcbucket_mapjoin/srcbucket21.txt]}
Alias Bucket Output File Name Mapping:
- pfile:/data/users/jssarma/hive_trunk/build/ql/test/data/warehouse/srcbucket_mapjoin_part/ds=2008-04-08/srcbucket20.txt 0
- pfile:/data/users/jssarma/hive_trunk/build/ql/test/data/warehouse/srcbucket_mapjoin_part/ds=2008-04-08/srcbucket21.txt 1
- pfile:/data/users/jssarma/hive_trunk/build/ql/test/data/warehouse/srcbucket_mapjoin_part/ds=2008-04-08/srcbucket22.txt 2
- pfile:/data/users/jssarma/hive_trunk/build/ql/test/data/warehouse/srcbucket_mapjoin_part/ds=2008-04-08/srcbucket23.txt 3
+ pfile:/Users/heyongqiang/Documents/workspace/Hive-2/build/ql/test/data/warehouse/srcbucket_mapjoin_part/ds=2008-04-08/srcbucket20.txt 0
+ pfile:/Users/heyongqiang/Documents/workspace/Hive-2/build/ql/test/data/warehouse/srcbucket_mapjoin_part/ds=2008-04-08/srcbucket21.txt 1
+ pfile:/Users/heyongqiang/Documents/workspace/Hive-2/build/ql/test/data/warehouse/srcbucket_mapjoin_part/ds=2008-04-08/srcbucket22.txt 2
+ pfile:/Users/heyongqiang/Documents/workspace/Hive-2/build/ql/test/data/warehouse/srcbucket_mapjoin_part/ds=2008-04-08/srcbucket23.txt 3
Needs Tagging: false
Path -> Alias:
- pfile:/data/users/jssarma/hive_trunk/build/ql/test/data/warehouse/srcbucket_mapjoin_part/ds=2008-04-08 [b]
+ pfile:/Users/heyongqiang/Documents/workspace/Hive-2/build/ql/test/data/warehouse/srcbucket_mapjoin_part/ds=2008-04-08 [b]
Path -> Partition:
- pfile:/data/users/jssarma/hive_trunk/build/ql/test/data/warehouse/srcbucket_mapjoin_part/ds=2008-04-08
+ pfile:/Users/heyongqiang/Documents/workspace/Hive-2/build/ql/test/data/warehouse/srcbucket_mapjoin_part/ds=2008-04-08
Partition
base file name: ds=2008-04-08
input format: org.apache.hadoop.mapred.TextInputFormat
@@ -749,13 +749,13 @@ STAGE PLANS:
columns.types int:string
file.inputformat org.apache.hadoop.mapred.TextInputFormat
file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- location pfile:/data/users/jssarma/hive_trunk/build/ql/test/data/warehouse/srcbucket_mapjoin_part
+ location pfile:/Users/heyongqiang/Documents/workspace/Hive-2/build/ql/test/data/warehouse/srcbucket_mapjoin_part
name srcbucket_mapjoin_part
partition_columns ds
serialization.ddl struct srcbucket_mapjoin_part { i32 key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- transient_lastDdlTime 1280083214
+ transient_lastDdlTime 1280425951
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
input format: org.apache.hadoop.mapred.TextInputFormat
@@ -767,13 +767,13 @@ STAGE PLANS:
columns.types int:string
file.inputformat org.apache.hadoop.mapred.TextInputFormat
file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- location pfile:/data/users/jssarma/hive_trunk/build/ql/test/data/warehouse/srcbucket_mapjoin_part
+ location pfile:/Users/heyongqiang/Documents/workspace/Hive-2/build/ql/test/data/warehouse/srcbucket_mapjoin_part
name srcbucket_mapjoin_part
partition_columns ds
serialization.ddl struct srcbucket_mapjoin_part { i32 key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- transient_lastDdlTime 1280083214
+ transient_lastDdlTime 1280425951
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: srcbucket_mapjoin_part
name: srcbucket_mapjoin_part
@@ -785,14 +785,14 @@ STAGE PLANS:
Move Operator
files:
hdfs directory: true
- source: pfile:/data/users/jssarma/hive_trunk/build/ql/scratchdir/hive_2010-07-25_11-40-45_690_2669369780343064476/-ext-10002
- destination: pfile:/data/users/jssarma/hive_trunk/build/ql/scratchdir/hive_2010-07-25_11-40-45_690_2669369780343064476/-ext-10000
+ source: pfile:/Users/heyongqiang/Documents/workspace/Hive-2/build/ql/scratchdir/hive_2010-07-29_10-53-20_871_6244434778770465214/-ext-10002
+ destination: pfile:/Users/heyongqiang/Documents/workspace/Hive-2/build/ql/scratchdir/hive_2010-07-29_10-53-20_871_6244434778770465214/-ext-10000
Stage: Stage-0
Move Operator
tables:
replace: true
- source: pfile:/data/users/jssarma/hive_trunk/build/ql/scratchdir/hive_2010-07-25_11-40-45_690_2669369780343064476/-ext-10000
+ source: pfile:/Users/heyongqiang/Documents/workspace/Hive-2/build/ql/scratchdir/hive_2010-07-29_10-53-20_871_6244434778770465214/-ext-10000
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -802,20 +802,20 @@ STAGE PLANS:
columns.types string:string:string
file.inputformat org.apache.hadoop.mapred.TextInputFormat
file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- location pfile:/data/users/jssarma/hive_trunk/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
+ location pfile:/Users/heyongqiang/Documents/workspace/Hive-2/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
name bucketmapjoin_tmp_result
serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- transient_lastDdlTime 1280083237
+ transient_lastDdlTime 1280425986
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: bucketmapjoin_tmp_result
- tmp directory: pfile:/data/users/jssarma/hive_trunk/build/ql/scratchdir/hive_2010-07-25_11-40-45_690_2669369780343064476/-ext-10001
+ tmp directory: pfile:/Users/heyongqiang/Documents/workspace/Hive-2/build/ql/scratchdir/hive_2010-07-29_10-53-20_871_6244434778770465214/-ext-10001
Stage: Stage-2
Map Reduce
Alias -> Map Operator Tree:
- pfile:/data/users/jssarma/hive_trunk/build/ql/scratchdir/hive_2010-07-25_11-40-45_690_2669369780343064476/-ext-10002
+ pfile:/Users/heyongqiang/Documents/workspace/Hive-2/build/ql/scratchdir/hive_2010-07-29_10-53-20_871_6244434778770465214/-ext-10002
Reduce Output Operator
sort order:
Map-reduce partition columns:
@@ -831,9 +831,9 @@ STAGE PLANS:
type: string
Needs Tagging: false
Path -> Alias:
- pfile:/data/users/jssarma/hive_trunk/build/ql/scratchdir/hive_2010-07-25_11-40-45_690_2669369780343064476/-ext-10002 [pfile:/data/users/jssarma/hive_trunk/build/ql/scratchdir/hive_2010-07-25_11-40-45_690_2669369780343064476/-ext-10002]
+ pfile:/Users/heyongqiang/Documents/workspace/Hive-2/build/ql/scratchdir/hive_2010-07-29_10-53-20_871_6244434778770465214/-ext-10002 [pfile:/Users/heyongqiang/Documents/workspace/Hive-2/build/ql/scratchdir/hive_2010-07-29_10-53-20_871_6244434778770465214/-ext-10002]
Path -> Partition:
- pfile:/data/users/jssarma/hive_trunk/build/ql/scratchdir/hive_2010-07-25_11-40-45_690_2669369780343064476/-ext-10002
+ pfile:/Users/heyongqiang/Documents/workspace/Hive-2/build/ql/scratchdir/hive_2010-07-29_10-53-20_871_6244434778770465214/-ext-10002
Partition
base file name: -ext-10002
input format: org.apache.hadoop.mapred.TextInputFormat
@@ -844,12 +844,12 @@ STAGE PLANS:
columns.types string:string:string
file.inputformat org.apache.hadoop.mapred.TextInputFormat
file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- location pfile:/data/users/jssarma/hive_trunk/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
+ location pfile:/Users/heyongqiang/Documents/workspace/Hive-2/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
name bucketmapjoin_tmp_result
serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- transient_lastDdlTime 1280083237
+ transient_lastDdlTime 1280425986
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
input format: org.apache.hadoop.mapred.TextInputFormat
@@ -860,12 +860,12 @@ STAGE PLANS:
columns.types string:string:string
file.inputformat org.apache.hadoop.mapred.TextInputFormat
file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- location pfile:/data/users/jssarma/hive_trunk/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
+ location pfile:/Users/heyongqiang/Documents/workspace/Hive-2/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
name bucketmapjoin_tmp_result
serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- transient_lastDdlTime 1280083237
+ transient_lastDdlTime 1280425986
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: bucketmapjoin_tmp_result
name: bucketmapjoin_tmp_result
@@ -874,7 +874,7 @@ STAGE PLANS:
File Output Operator
compressed: false
GlobalTableId: 0
- directory: pfile:/data/users/jssarma/hive_trunk/build/ql/scratchdir/hive_2010-07-25_11-40-45_690_2669369780343064476/-ext-10000
+ directory: pfile:/Users/heyongqiang/Documents/workspace/Hive-2/build/ql/scratchdir/hive_2010-07-29_10-53-20_871_6244434778770465214/-ext-10000
NumFilesPerFileSink: 1
table:
input format: org.apache.hadoop.mapred.TextInputFormat
@@ -885,12 +885,12 @@ STAGE PLANS:
columns.types string:string:string
file.inputformat org.apache.hadoop.mapred.TextInputFormat
file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- location pfile:/data/users/jssarma/hive_trunk/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
+ location pfile:/Users/heyongqiang/Documents/workspace/Hive-2/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
name bucketmapjoin_tmp_result
serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- transient_lastDdlTime 1280083237
+ transient_lastDdlTime 1280425986
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: bucketmapjoin_tmp_result
TotalFiles: 1
@@ -931,11 +931,11 @@ POSTHOOK: Lineage: bucketmapjoin_tmp_res
PREHOOK: query: select count(1) from bucketmapjoin_tmp_result
PREHOOK: type: QUERY
PREHOOK: Input: default@bucketmapjoin_tmp_result
-PREHOOK: Output: file:/tmp/jssarma/hive_2010-07-25_11-40-54_256_3570445615662799799/-mr-10000
+PREHOOK: Output: file:/var/folders/6g/6grtCwPMEf4sqHUPpy6xQG9ByHg/-Tmp-/heyongqiang/hive_2010-07-29_10-53-34_025_6513734302202119872/-mr-10000
POSTHOOK: query: select count(1) from bucketmapjoin_tmp_result
POSTHOOK: type: QUERY
POSTHOOK: Input: default@bucketmapjoin_tmp_result
-POSTHOOK: Output: file:/tmp/jssarma/hive_2010-07-25_11-40-54_256_3570445615662799799/-mr-10000
+POSTHOOK: Output: file:/var/folders/6g/6grtCwPMEf4sqHUPpy6xQG9ByHg/-Tmp-/heyongqiang/hive_2010-07-29_10-53-34_025_6513734302202119872/-mr-10000
POSTHOOK: Lineage: bucketmapjoin_hash_result_1.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ]
POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ]
POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ]
@@ -1020,11 +1020,11 @@ POSTHOOK: Lineage: bucketmapjoin_tmp_res
PREHOOK: query: select count(1) from bucketmapjoin_tmp_result
PREHOOK: type: QUERY
PREHOOK: Input: default@bucketmapjoin_tmp_result
-PREHOOK: Output: file:/tmp/jssarma/hive_2010-07-25_11-41-07_639_6613037422321680239/-mr-10000
+PREHOOK: Output: file:/var/folders/6g/6grtCwPMEf4sqHUPpy6xQG9ByHg/-Tmp-/heyongqiang/hive_2010-07-29_10-53-55_525_3771579881834121899/-mr-10000
POSTHOOK: query: select count(1) from bucketmapjoin_tmp_result
POSTHOOK: type: QUERY
POSTHOOK: Input: default@bucketmapjoin_tmp_result
-POSTHOOK: Output: file:/tmp/jssarma/hive_2010-07-25_11-41-07_639_6613037422321680239/-mr-10000
+POSTHOOK: Output: file:/var/folders/6g/6grtCwPMEf4sqHUPpy6xQG9ByHg/-Tmp-/heyongqiang/hive_2010-07-29_10-53-55_525_3771579881834121899/-mr-10000
POSTHOOK: Lineage: bucketmapjoin_hash_result_1.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ]
POSTHOOK: Lineage: bucketmapjoin_hash_result_1.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ]
POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ]
@@ -1087,14 +1087,14 @@ on a.key = b.key
PREHOOK: type: QUERY
PREHOOK: Input: default@bucketmapjoin_hash_result_2
PREHOOK: Input: default@bucketmapjoin_hash_result_1
-PREHOOK: Output: file:/tmp/jssarma/hive_2010-07-25_11-41-13_010_6197022944447272166/-mr-10000
+PREHOOK: Output: file:/var/folders/6g/6grtCwPMEf4sqHUPpy6xQG9ByHg/-Tmp-/heyongqiang/hive_2010-07-29_10-54-04_745_7587716495922580484/-mr-10000
POSTHOOK: query: select a.key-b.key, a.value1-b.value1, a.value2-b.value2
from bucketmapjoin_hash_result_1 a left outer join bucketmapjoin_hash_result_2 b
on a.key = b.key
POSTHOOK: type: QUERY
POSTHOOK: Input: default@bucketmapjoin_hash_result_2
POSTHOOK: Input: default@bucketmapjoin_hash_result_1
-POSTHOOK: Output: file:/tmp/jssarma/hive_2010-07-25_11-41-13_010_6197022944447272166/-mr-10000
+POSTHOOK: Output: file:/var/folders/6g/6grtCwPMEf4sqHUPpy6xQG9ByHg/-Tmp-/heyongqiang/hive_2010-07-29_10-54-04_745_7587716495922580484/-mr-10000
POSTHOOK: Lineage: bucketmapjoin_hash_result_1.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ]
POSTHOOK: Lineage: bucketmapjoin_hash_result_1.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ]
POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ]