yihua commented on a change in pull request #4106: URL: https://github.com/apache/hudi/pull/4106#discussion_r765407715
########## File path: hudi-client/hudi-spark-client/src/main/java/org/apache/hudi/sort/SpaceCurveSortingHelper.java ########## @@ -0,0 +1,260 @@ +/* + * 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.hudi.sort; + +import org.apache.hudi.common.util.CollectionUtils; +import org.apache.hudi.config.HoodieClusteringConfig; +import org.apache.hudi.optimize.HilbertCurveUtils; +import org.apache.hudi.optimize.ZOrderingUtil; +import org.apache.log4j.LogManager; +import org.apache.log4j.Logger; +import org.apache.spark.api.java.JavaRDD; +import org.apache.spark.sql.Column; +import org.apache.spark.sql.Dataset; +import org.apache.spark.sql.Row; +import org.apache.spark.sql.Row$; +import org.apache.spark.sql.hudi.execution.RangeSampleSort$; +import org.apache.spark.sql.hudi.execution.ZorderingBinarySort; +import org.apache.spark.sql.types.BinaryType; +import org.apache.spark.sql.types.BinaryType$; +import org.apache.spark.sql.types.BooleanType; +import org.apache.spark.sql.types.ByteType; +import org.apache.spark.sql.types.DataType; +import org.apache.spark.sql.types.DateType; +import org.apache.spark.sql.types.DecimalType; +import org.apache.spark.sql.types.DoubleType; +import org.apache.spark.sql.types.FloatType; +import org.apache.spark.sql.types.IntegerType; +import org.apache.spark.sql.types.LongType; +import org.apache.spark.sql.types.Metadata; +import org.apache.spark.sql.types.ShortType; +import org.apache.spark.sql.types.StringType; +import org.apache.spark.sql.types.StructField; +import org.apache.spark.sql.types.StructType; +import org.apache.spark.sql.types.StructType$; +import org.apache.spark.sql.types.TimestampType; +import org.davidmoten.hilbert.HilbertCurve; +import scala.collection.JavaConversions; + +import java.util.ArrayList; +import java.util.Arrays; +import java.util.Iterator; +import java.util.List; +import java.util.Map; +import java.util.function.Function; +import java.util.stream.Collectors; + +public class SpaceCurveSortingHelper { + + private static final Logger LOG = LogManager.getLogger(SpaceCurveSortingHelper.class); + + /** + * Orders provided {@link Dataset} by mapping values of the provided list of columns + * {@code orderByCols} onto a specified space curve (Z-curve, Hilbert, etc) + * + * <p/> + * NOTE: Only support base data-types: long,int,short,double,float,string,timestamp,decimal,date,byte. + * This method is more effective than {@link #orderDataFrameBySamplingValues} leveraging + * data sampling instead of direct mapping + * + * @param df Spark {@link Dataset} holding data to be ordered + * @param orderByCols list of columns to be ordered by + * @param targetPartitionCount target number of output partitions + * @param layoutOptStrategy target layout optimization strategy + * @return a {@link Dataset} holding data ordered by mapping tuple of values from provided columns + * onto a specified space-curve + */ + public static Dataset<Row> orderDataFrameByMappingValues( + Dataset<Row> df, + HoodieClusteringConfig.LayoutOptimizationStrategy layoutOptStrategy, + List<String> orderByCols, + int targetPartitionCount + ) { + Map<String, StructField> columnsMap = + Arrays.stream(df.schema().fields()) + .collect(Collectors.toMap(StructField::name, Function.identity())); + + List<String> checkCols = + orderByCols.stream() + .filter(columnsMap::containsKey) + .collect(Collectors.toList()); + + if (orderByCols.size() != checkCols.size()) { + LOG.error(String.format("Trying to ordering over a column(s) not present in the schema (%s); skipping", CollectionUtils.diff(orderByCols, checkCols))); + return df; + } Review comment: Got it. Sg. -- 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: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
