szehon-ho commented on code in PR #3983: URL: https://github.com/apache/iceberg/pull/3983#discussion_r851520519
########## spark/v3.2/spark/src/main/java/org/apache/iceberg/spark/actions/Spark3ZOrderStrategy.java: ########## @@ -0,0 +1,215 @@ +/* + * 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.spark.actions; + +import java.util.Arrays; +import java.util.List; +import java.util.Map; +import java.util.Set; +import java.util.UUID; +import java.util.stream.Collectors; +import java.util.stream.Stream; +import org.apache.iceberg.DataFile; +import org.apache.iceberg.FileScanTask; +import org.apache.iceberg.NullOrder; +import org.apache.iceberg.PartitionField; +import org.apache.iceberg.Schema; +import org.apache.iceberg.SortDirection; +import org.apache.iceberg.Table; +import org.apache.iceberg.actions.RewriteStrategy; +import org.apache.iceberg.relocated.com.google.common.base.Preconditions; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableSet; +import org.apache.iceberg.spark.SparkDistributionAndOrderingUtil; +import org.apache.iceberg.spark.SparkReadOptions; +import org.apache.iceberg.spark.SparkWriteOptions; +import org.apache.iceberg.types.Types; +import org.apache.iceberg.types.Types.NestedField; +import org.apache.iceberg.util.PropertyUtil; +import org.apache.iceberg.util.SortOrderUtil; +import org.apache.iceberg.util.ZOrderByteUtils; +import org.apache.spark.sql.Column; +import org.apache.spark.sql.Dataset; +import org.apache.spark.sql.Row; +import org.apache.spark.sql.SparkSession; +import org.apache.spark.sql.catalyst.plans.logical.LogicalPlan; +import org.apache.spark.sql.connector.distributions.Distribution; +import org.apache.spark.sql.connector.distributions.Distributions; +import org.apache.spark.sql.connector.expressions.SortOrder; +import org.apache.spark.sql.functions; +import org.apache.spark.sql.internal.SQLConf; +import org.apache.spark.sql.types.StructField; + +public class Spark3ZOrderStrategy extends Spark3SortStrategy { + + private static final String Z_COLUMN = "ICEZVALUE"; + private static final Schema Z_SCHEMA = new Schema(NestedField.required(0, Z_COLUMN, Types.BinaryType.get())); + private static final org.apache.iceberg.SortOrder Z_SORT_ORDER = org.apache.iceberg.SortOrder.builderFor(Z_SCHEMA) + .sortBy(Z_COLUMN, SortDirection.ASC, NullOrder.NULLS_LAST) + .build(); + + /** + * Controls the amount of bytes interleaved in the ZOrder Algorithm. Default is all bytes being interleaved. + */ + private static final String MAX_OUTPUT_SIZE_KEY = "max-output-size"; + private static final int DEFAULT_MAX_OUTPUT_SIZE = Integer.MAX_VALUE; + + /** + * Controls the number of bytes considered from an input column of a type with variable length (String, Binary). + * Default is to use the same size as primitives {@link ZOrderByteUtils#PRIMITIVE_BUFFER_SIZE} + */ + private static final String VAR_LENGTH_CONTRIBUTION_KEY = "var-length-contribution"; + private static final int DEFAULT_VAR_LENGTH_CONTRIBUTION = ZOrderByteUtils.PRIMITIVE_BUFFER_SIZE; + + private final List<String> zOrderColNames; + private final Spark3ZOrderUDF zOrderUDF; + + private int maxOutputSize; + private int varLengthContribution; + + @Override + public Set<String> validOptions() { + return ImmutableSet.<String>builder() + .addAll(super.validOptions()) + .add(VAR_LENGTH_CONTRIBUTION_KEY) + .add(MAX_OUTPUT_SIZE_KEY) + .build(); + } + + @Override + public RewriteStrategy options(Map<String, String> options) { + super.options(options); + + varLengthContribution = PropertyUtil.propertyAsInt(options, VAR_LENGTH_CONTRIBUTION_KEY, + DEFAULT_VAR_LENGTH_CONTRIBUTION); + Preconditions.checkArgument(varLengthContribution > 0, + "Cannot use less than 1 byte for variable length types with zOrder, %s was set to %s", + VAR_LENGTH_CONTRIBUTION_KEY, varLengthContribution); + + + maxOutputSize = PropertyUtil.propertyAsInt(options, MAX_OUTPUT_SIZE_KEY, DEFAULT_MAX_OUTPUT_SIZE); Review Comment: Yea I mean, its not used inside the UDF :) -- 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] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
