[
https://issues.apache.org/jira/browse/HIVE-12719?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Surbhit updated HIVE-12719:
---------------------------
Release Note:
I am facing an issues while calling custom generic UDAF's in HIVE (1.2.1).
Below is my implementation for GenericUDAF : -
/**
*
*/
package com.practice.hive.udaf.test;
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.ql.udf.generic.GenericUDAFEvaluator;
import org.apache.hadoop.hive.ql.udf.generic.GenericUDAFParameterInfo;
import org.apache.hadoop.hive.ql.udf.generic.GenericUDAFResolver2;
import org.apache.hadoop.hive.ql.util.JavaDataModel;
import org.apache.hadoop.hive.serde2.objectinspector.ObjectInspector;
import
org.apache.hadoop.hive.serde2.objectinspector.primitive.LongObjectInspector;
import
org.apache.hadoop.hive.serde2.objectinspector.primitive.PrimitiveObjectInspectorFactory;
import org.apache.hadoop.hive.serde2.typeinfo.TypeInfo;
import org.apache.hadoop.io.LongWritable;
/**
* @author surbhit.shrivastava
*
*/
public class GenericUDAFRegrCount implements GenericUDAFResolver2 {
// This is deprecated will not be called .. but is present for backward
compatibility purpose
@Override
public GenericUDAFEvaluator getEvaluator(TypeInfo[] parameters)
throws SemanticException {
if (parameters.length != 2) {
throw new UDFArgumentTypeException(parameters.length -
1,
"Exactly two arguments are expected.");
}
return new GenericUDAFRegrCountEvaluator();
}
@Override
public GenericUDAFEvaluator getEvaluator(GenericUDAFParameterInfo
paramInfo)
throws SemanticException {
TypeInfo[] parameters = paramInfo.getParameters();
if (parameters.length != 2) {
throw new UDFArgumentTypeException(parameters.length -
1,
"Exactly two arguments are expected.");
}
if (paramInfo.isAllColumns()) {
throw new UDFArgumentTypeException(parameters.length -
1,
"* is not supported");
}
if (paramInfo.isDistinct()) {
throw new UDFArgumentTypeException(parameters.length -
1,
"DISTINCT keyword is not allowed");
}
return new GenericUDAFRegrCountEvaluator();
}
public static class GenericUDAFRegrCountEvaluator extends
GenericUDAFEvaluator {
private LongObjectInspector partialCountAggOI;
private LongWritable result;
@Override
public ObjectInspector init(Mode m, ObjectInspector[]
parameters)
throws HiveException {
super.init(m, parameters);
if (m == Mode.PARTIAL2 || m == Mode.FINAL) {
partialCountAggOI = (LongObjectInspector)
parameters[0];
}
result = new LongWritable(0);
return
PrimitiveObjectInspectorFactory.writableLongObjectInspector;
}
/** class for storing count value. */
@AggregationType(estimable = true)
static class CountAgg extends AbstractAggregationBuffer {
long value;
@Override
public int estimate() {
return JavaDataModel.PRIMITIVES2;
}
}
@Override
public AggregationBuffer getNewAggregationBuffer() throws
HiveException {
CountAgg buffer = new CountAgg();
reset(buffer);
return buffer;
}
@Override
public void reset(AggregationBuffer agg) throws HiveException {
((CountAgg) agg).value = 0;
}
@Override
public void iterate(AggregationBuffer agg, Object[] parameters)
throws HiveException {
if (parameters == null) {
return;
}
if (null != parameters[0] && null != parameters[1]) {
((CountAgg) agg).value++;
}
}
@Override
public void merge(AggregationBuffer agg, Object partial) throws
HiveException {
if (partial != null) {
long p = partialCountAggOI.get(partial);
((CountAgg) agg).value += p;
}
}
@Override
public Object terminate(AggregationBuffer agg) throws
HiveException {
result.set(((CountAgg) agg).value);
return result;
}
@Override
public Object terminatePartial(AggregationBuffer agg)
throws HiveException {
return terminate(agg);
}
}
}
I have registered the function using -
CREATE FUNCTION REGR_COUNT AS
'com.practice.hive.udaf.test.GenericUDAFRegrCount' USING JAR
'hdfs:///data/test/hadoop-sample-0.1-SNAPSHOT.jar';
I get the below errors while trying to execute query -
select regr_count(empid,depid) over() from EMPLOYEE;
FAILED: SemanticException Failed to breakup Windowing invocations into Groups.
At least 1 group must only depend on input columns. Also check for circular
dependencies. Underlying error: Invalid function regr_count
Although the same function works fine when registered as temporary function
using .
CREATE TEMPORARY FUNCTION REGR_COUNT AS
'com.practice.hive.udaf.test.GenericUDAFRegrCount' USING JAR
'hdfs:///data/test/hadoop-sample-0.1-SNAPSHOT.jar';
Any help would be highly appreciated :)
was:
I am facing an issues while calling custom generic UDAF's in HIVE (1.2.1).
Below is my implementation for GenericUDAF : -
{code}
/**
*
*/
package com.practice.hive.udaf.test;
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.ql.udf.generic.GenericUDAFEvaluator;
import org.apache.hadoop.hive.ql.udf.generic.GenericUDAFParameterInfo;
import org.apache.hadoop.hive.ql.udf.generic.GenericUDAFResolver2;
import org.apache.hadoop.hive.ql.util.JavaDataModel;
import org.apache.hadoop.hive.serde2.objectinspector.ObjectInspector;
import
org.apache.hadoop.hive.serde2.objectinspector.primitive.LongObjectInspector;
import
org.apache.hadoop.hive.serde2.objectinspector.primitive.PrimitiveObjectInspectorFactory;
import org.apache.hadoop.hive.serde2.typeinfo.TypeInfo;
import org.apache.hadoop.io.LongWritable;
/**
* @author surbhit.shrivastava
*
*/
public class GenericUDAFRegrCount implements GenericUDAFResolver2 {
// This is deprecated will not be called .. but is present for backward
compatibility purpose
@Override
public GenericUDAFEvaluator getEvaluator(TypeInfo[] parameters)
throws SemanticException {
if (parameters.length != 2) {
throw new UDFArgumentTypeException(parameters.length -
1,
"Exactly two arguments are expected.");
}
return new GenericUDAFRegrCountEvaluator();
}
@Override
public GenericUDAFEvaluator getEvaluator(GenericUDAFParameterInfo
paramInfo)
throws SemanticException {
TypeInfo[] parameters = paramInfo.getParameters();
if (parameters.length != 2) {
throw new UDFArgumentTypeException(parameters.length -
1,
"Exactly two arguments are expected.");
}
if (paramInfo.isAllColumns()) {
throw new UDFArgumentTypeException(parameters.length -
1,
"* is not supported");
}
if (paramInfo.isDistinct()) {
throw new UDFArgumentTypeException(parameters.length -
1,
"DISTINCT keyword is not allowed");
}
return new GenericUDAFRegrCountEvaluator();
}
public static class GenericUDAFRegrCountEvaluator extends
GenericUDAFEvaluator {
private LongObjectInspector partialCountAggOI;
private LongWritable result;
@Override
public ObjectInspector init(Mode m, ObjectInspector[]
parameters)
throws HiveException {
super.init(m, parameters);
if (m == Mode.PARTIAL2 || m == Mode.FINAL) {
partialCountAggOI = (LongObjectInspector)
parameters[0];
}
result = new LongWritable(0);
return
PrimitiveObjectInspectorFactory.writableLongObjectInspector;
}
/** class for storing count value. */
@AggregationType(estimable = true)
static class CountAgg extends AbstractAggregationBuffer {
long value;
@Override
public int estimate() {
return JavaDataModel.PRIMITIVES2;
}
}
@Override
public AggregationBuffer getNewAggregationBuffer() throws
HiveException {
CountAgg buffer = new CountAgg();
reset(buffer);
return buffer;
}
@Override
public void reset(AggregationBuffer agg) throws HiveException {
((CountAgg) agg).value = 0;
}
@Override
public void iterate(AggregationBuffer agg, Object[] parameters)
throws HiveException {
if (parameters == null) {
return;
}
if (null != parameters[0] && null != parameters[1]) {
((CountAgg) agg).value++;
}
}
@Override
public void merge(AggregationBuffer agg, Object partial) throws
HiveException {
if (partial != null) {
long p = partialCountAggOI.get(partial);
((CountAgg) agg).value += p;
}
}
@Override
public Object terminate(AggregationBuffer agg) throws
HiveException {
result.set(((CountAgg) agg).value);
return result;
}
@Override
public Object terminatePartial(AggregationBuffer agg)
throws HiveException {
return terminate(agg);
}
}
}
{code}
I have registered the function using -
CREATE FUNCTION REGR_COUNT AS
'com.practice.hive.udaf.test.GenericUDAFRegrCount' USING JAR
'hdfs:///data/test/hadoop-sample-0.1-SNAPSHOT.jar';
I get the below errors while trying to execute query -
select regr_count(empid,depid) over() from EMPLOYEE;
FAILED: SemanticException Failed to breakup Windowing invocations into Groups.
At least 1 group must only depend on input columns. Also check for circular
dependencies. Underlying error: Invalid function regr_count
Although the same function works fine when registered as temporary function
using .
CREATE TEMPORARY FUNCTION REGR_COUNT AS
'com.practice.hive.udaf.test.GenericUDAFRegrCount' USING JAR
'hdfs:///data/test/hadoop-sample-0.1-SNAPSHOT.jar';
Any help would be highly appreciated :)
> As a hive user, I am facing issues using permanent UDAF's.
> ----------------------------------------------------------
>
> Key: HIVE-12719
> URL: https://issues.apache.org/jira/browse/HIVE-12719
> Project: Hive
> Issue Type: Bug
> Components: Hive
> Affects Versions: 1.2.1
> Reporter: Surbhit
>
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
