[
https://issues.apache.org/jira/browse/HIVE-25975?focusedWorklogId=735820&page=com.atlassian.jira.plugin.system.issuetabpanels:worklog-tabpanel#worklog-735820
]
ASF GitHub Bot logged work on HIVE-25975:
-----------------------------------------
Author: ASF GitHub Bot
Created on: 03/Mar/22 09:24
Start Date: 03/Mar/22 09:24
Worklog Time Spent: 10m
Work Description: szlta commented on a change in pull request #3060:
URL: https://github.com/apache/hive/pull/3060#discussion_r818463694
##########
File path:
iceberg/iceberg-handler/src/main/java/org/apache/iceberg/mr/hive/GenericUDFIcebergBucket.java
##########
@@ -0,0 +1,198 @@
+/*
+ * 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.iceberg.mr.hive;
+
+import java.nio.ByteBuffer;
+import org.apache.hadoop.hive.ql.exec.Description;
+import org.apache.hadoop.hive.ql.exec.UDFArgumentException;
+import org.apache.hadoop.hive.ql.exec.UDFArgumentLengthException;
+import org.apache.hadoop.hive.ql.metadata.HiveException;
+import org.apache.hadoop.hive.ql.udf.generic.GenericUDF;
+import org.apache.hadoop.hive.serde2.io.HiveDecimalWritable;
+import org.apache.hadoop.hive.serde2.objectinspector.ObjectInspector;
+import org.apache.hadoop.hive.serde2.objectinspector.ObjectInspectorConverters;
+import org.apache.hadoop.hive.serde2.objectinspector.PrimitiveObjectInspector;
+import
org.apache.hadoop.hive.serde2.objectinspector.primitive.PrimitiveObjectInspectorConverter;
+import
org.apache.hadoop.hive.serde2.objectinspector.primitive.PrimitiveObjectInspectorFactory;
+import
org.apache.hadoop.hive.serde2.objectinspector.primitive.WritableConstantIntObjectInspector;
+import org.apache.hadoop.hive.serde2.typeinfo.DecimalTypeInfo;
+import org.apache.hadoop.hive.serde2.typeinfo.TypeInfoUtils;
+import org.apache.hadoop.io.BytesWritable;
+import org.apache.hadoop.io.DoubleWritable;
+import org.apache.hadoop.io.FloatWritable;
+import org.apache.hadoop.io.IntWritable;
+import org.apache.hadoop.io.LongWritable;
+import org.apache.iceberg.transforms.Transform;
+import org.apache.iceberg.transforms.Transforms;
+import org.apache.iceberg.types.Type;
+import org.apache.iceberg.types.Types;
+
+/**
+ * GenericUDFIcebergBucket - UDF that wraps around Iceberg's bucket transform
function
+ */
+@Description(name = "iceberg_bucket",
+ value = "_FUNC_(value, bucketCount) - " +
+ "Returns the bucket value calculated by Iceberg bucket transform
function ",
+ extended = "Example:\n > SELECT _FUNC_('A bucket full of ice!', 5);\n 4")
+public class GenericUDFIcebergBucket extends GenericUDF {
+ private final IntWritable result = new IntWritable();
+ private int numBuckets = -1;
+ private transient PrimitiveObjectInspector argumentOI;
+ private transient ObjectInspectorConverters.Converter converter;
+
+ @FunctionalInterface
+ private interface UDFEvalFunction<T> {
+ void apply(T argument) throws HiveException;
+ }
+
+ private transient UDFEvalFunction<DeferredObject> evaluator;
+
+ @Override
+ public ObjectInspector initialize(ObjectInspector[] arguments) throws
UDFArgumentException {
+ if (arguments.length != 2) {
+ throw new UDFArgumentLengthException(
+ "ICEBERG_BUCKET requires 2 arguments (value, bucketCount), but got "
+ arguments.length);
+ }
+
+ if (arguments[0].getCategory() != ObjectInspector.Category.PRIMITIVE) {
+ throw new UDFArgumentException(
+ "ICEBERG_BUCKET first argument takes primitive types, got " +
argumentOI.getTypeName());
+ }
+ argumentOI = (PrimitiveObjectInspector) arguments[0];
+
+ PrimitiveObjectInspector.PrimitiveCategory inputType =
argumentOI.getPrimitiveCategory();
+ ObjectInspector outputOI = null;
+ switch (inputType) {
+ case CHAR:
+ case VARCHAR:
+ case STRING:
+ converter = new
PrimitiveObjectInspectorConverter.StringConverter(argumentOI);
+ evaluator = arg -> {
+ String val = (String) converter.convert(arg.get());
+ applyBucketTransform(val, Types.StringType.get());
+ };
+ break;
+
+ case BINARY:
+ converter = new
PrimitiveObjectInspectorConverter.BinaryConverter(argumentOI,
+ PrimitiveObjectInspectorFactory.writableBinaryObjectInspector);
+ evaluator = arg -> {
+ BytesWritable val = (BytesWritable) converter.convert(arg.get());
+ ByteBuffer byteBuffer = ByteBuffer.wrap(val.getBytes(), 0,
val.getLength());
+ applyBucketTransform(byteBuffer, Types.BinaryType.get());
+ };
+ break;
+
+ case INT:
+ converter = new
PrimitiveObjectInspectorConverter.IntConverter(argumentOI,
+ PrimitiveObjectInspectorFactory.writableIntObjectInspector);
+ evaluator = arg -> {
+ IntWritable val = (IntWritable) converter.convert(arg.get());
+ applyBucketTransform(val.get(), Types.IntegerType.get());
+ };
+ break;
+
+ case LONG:
+ converter = new
PrimitiveObjectInspectorConverter.LongConverter(argumentOI,
+ PrimitiveObjectInspectorFactory.writableLongObjectInspector);
+ evaluator = arg -> {
+ LongWritable val = (LongWritable) converter.convert(arg.get());
+ applyBucketTransform(val.get(), Types.LongType.get());
+ };
+ break;
+
+ case DECIMAL:
+ DecimalTypeInfo decimalTypeInfo = (DecimalTypeInfo)
TypeInfoUtils.getTypeInfoFromObjectInspector(argumentOI);
+ Type.PrimitiveType decimalIcebergType =
Types.DecimalType.of(decimalTypeInfo.getPrecision(),
+ decimalTypeInfo.getScale());
+
+ converter = new
PrimitiveObjectInspectorConverter.HiveDecimalConverter(argumentOI,
+
PrimitiveObjectInspectorFactory.writableHiveDecimalObjectInspector);
+ evaluator = arg -> {
+ HiveDecimalWritable val = (HiveDecimalWritable)
converter.convert(arg.get());
+ applyBucketTransform(val.getHiveDecimal().bigDecimalValue(),
decimalIcebergType);
+ };
+ break;
+
+ case FLOAT:
+ converter = new
PrimitiveObjectInspectorConverter.FloatConverter(argumentOI,
+ PrimitiveObjectInspectorFactory.writableFloatObjectInspector);
+ evaluator = arg -> {
+ FloatWritable val = (FloatWritable) converter.convert(arg.get());
+ applyBucketTransform(val.get(), Types.FloatType.get());
+ };
+ break;
+
+ case DOUBLE:
+ converter = new
PrimitiveObjectInspectorConverter.DoubleConverter(argumentOI,
+ PrimitiveObjectInspectorFactory.writableDoubleObjectInspector);
+ evaluator = arg -> {
+ DoubleWritable val = (DoubleWritable) converter.convert(arg.get());
+ applyBucketTransform(val.get(), Types.DoubleType.get());
+ };
+ break;
+
+ default:
+ throw new UDFArgumentException(
+ " ICEBERG_BUCKET() only takes
STRING/CHAR/VARCHAR/BINARY/INT/LONG/DECIMAL/FLOAT/DOUBLE" +
+ " types as first argument, got " + inputType);
+ }
+
+ numBuckets = getNumBuckets(arguments[1]);
+
+ outputOI = PrimitiveObjectInspectorFactory.writableIntObjectInspector;
+ return outputOI;
+ }
+
+ private static int getNumBuckets(ObjectInspector arg) throws
UDFArgumentException {
+ UDFArgumentException udfArgumentException = new
UDFArgumentException("ICEBERG_BUCKET() second argument can only " +
+ "take an int type, but got " + arg.getTypeName());
+ if (arg.getCategory() != ObjectInspector.Category.PRIMITIVE) {
+ throw udfArgumentException;
+ }
+ PrimitiveObjectInspector.PrimitiveCategory inputType =
((PrimitiveObjectInspector) arg).getPrimitiveCategory();
+ if (inputType != PrimitiveObjectInspector.PrimitiveCategory.INT) {
+ throw udfArgumentException;
+ }
+ return ((WritableConstantIntObjectInspector)
arg).getWritableConstantValue().get();
+ }
+
+ @Override
+ public Object evaluate(DeferredObject[] arguments) throws HiveException {
+
+ DeferredObject argument = arguments[0];
+ if (argument == null) {
+ return null;
+ } else {
+ evaluator.apply(argument);
+ }
+
+ return result;
+ }
+
+ private <T> void applyBucketTransform(T value, Type.PrimitiveType
icebergType) {
+ Transform<T, Integer> transform = Transforms.bucket(icebergType,
numBuckets);
Review comment:
Yes it would, I just refactored this. I must say I really liked my
generic method though :/
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: gitbox-unsubscr...@hive.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
Issue Time Tracking
-------------------
Worklog Id: (was: 735820)
Time Spent: 5h 50m (was: 5h 40m)
> Optimize ClusteredWriter for bucketed Iceberg tables
> ----------------------------------------------------
>
> Key: HIVE-25975
> URL: https://issues.apache.org/jira/browse/HIVE-25975
> Project: Hive
> Issue Type: Improvement
> Reporter: Ádám Szita
> Assignee: Ádám Szita
> Priority: Major
> Labels: pull-request-available
> Time Spent: 5h 50m
> Remaining Estimate: 0h
>
> The first version of the ClusteredWriter in Hive-Iceberg will be lenient for
> bucketed tables: i.e. the records do not need to be ordered by the bucket
> values, the writer will just close its current file and open a new one for
> out-of-order records.
> This is suboptimal for the long-term due to creating many small files. Spark
> uses a UDF to compute the bucket value for each record and therefore it is
> able to order the records by bucket values, achieving optimal clustering.
--
This message was sent by Atlassian Jira
(v8.20.1#820001)
