Spark: Add DistributionAndOrderingUtils #2141
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,69 @@ | ||
| /* | ||
| * 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.util; | ||
|
|
||
| import java.util.Collection; | ||
| import org.apache.iceberg.PartitionField; | ||
| import org.apache.iceberg.PartitionSpec; | ||
| import org.apache.iceberg.Schema; | ||
| import org.apache.iceberg.SortField; | ||
| import org.apache.iceberg.SortOrder; | ||
| import org.apache.iceberg.Table; | ||
| import org.apache.iceberg.expressions.Expressions; | ||
| import org.apache.iceberg.relocated.com.google.common.collect.Multimap; | ||
| import org.apache.iceberg.relocated.com.google.common.collect.Multimaps; | ||
| import org.apache.iceberg.transforms.SortOrderVisitor; | ||
|
|
||
| public class SortOrderUtil { | ||
|
|
||
| private SortOrderUtil() { | ||
| } | ||
|
|
||
| public static SortOrder buildSortOrder(Table table) { | ||
| return buildSortOrder(table.spec(), table.sortOrder()); | ||
| } | ||
|
|
||
| public static SortOrder buildSortOrder(PartitionSpec spec, SortOrder sortOrder) { | ||
| if (sortOrder.isUnsorted() && spec.isUnpartitioned()) { | ||
| return SortOrder.unsorted(); | ||
| } | ||
|
|
||
| Schema schema = spec.schema(); | ||
|
|
||
| Multimap<Integer, SortField> sortFieldIndex = Multimaps.index(sortOrder.fields(), SortField::sourceId); | ||
|
|
||
| // build a sort prefix of partition fields that are not already in the sort order | ||
| SortOrder.Builder builder = SortOrder.builderFor(schema); | ||
rdblue marked this conversation as resolved.
Show resolved
Hide resolved
|
||
| for (PartitionField field : spec.fields()) { | ||
| Collection<SortField> sortFields = sortFieldIndex.get(field.sourceId()); | ||
| boolean isSorted = sortFields.stream().anyMatch(sortField -> | ||
| field.transform().equals(sortField.transform()) || sortField.transform().satisfiesOrderOf(field.transform())); | ||
| if (!isSorted) { | ||
| String sourceName = schema.findColumnName(field.sourceId()); | ||
| builder.asc(Expressions.transform(sourceName, field.transform())); | ||
| } | ||
| } | ||
|
|
||
| // add the configured sort to the partition spec prefix sort | ||
| SortOrderVisitor.visit(sortOrder, new CopySortOrderFields(builder)); | ||
|
Contributor
Author
There was a problem hiding this comment. I removed another |
||
|
|
||
| return builder.build(); | ||
| } | ||
| } | ||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,162 @@ | ||
| /* | ||
| * 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.spark.sql.catalyst.utils | ||
|
|
||
| import org.apache.spark.sql.AnalysisException | ||
| import org.apache.spark.sql.catalyst | ||
| import org.apache.spark.sql.catalyst.analysis.Resolver | ||
| import org.apache.spark.sql.catalyst.expressions.IcebergBucketTransform | ||
| import org.apache.spark.sql.catalyst.expressions.IcebergDayTransform | ||
| import org.apache.spark.sql.catalyst.expressions.IcebergHourTransform | ||
| import org.apache.spark.sql.catalyst.expressions.IcebergMonthTransform | ||
| import org.apache.spark.sql.catalyst.expressions.IcebergYearTransform | ||
| import org.apache.spark.sql.catalyst.expressions.NamedExpression | ||
| import org.apache.spark.sql.catalyst.plans.logical.LogicalPlan | ||
| import org.apache.spark.sql.catalyst.plans.logical.RepartitionByExpression | ||
| import org.apache.spark.sql.catalyst.plans.logical.Sort | ||
| import org.apache.spark.sql.connector.catalog.CatalogV2Implicits | ||
| import org.apache.spark.sql.connector.expressions.BucketTransform | ||
| import org.apache.spark.sql.connector.expressions.DaysTransform | ||
| import org.apache.spark.sql.connector.expressions.Expression | ||
| import org.apache.spark.sql.connector.expressions.FieldReference | ||
| import org.apache.spark.sql.connector.expressions.HoursTransform | ||
| import org.apache.spark.sql.connector.expressions.IdentityTransform | ||
| import org.apache.spark.sql.connector.expressions.MonthsTransform | ||
| import org.apache.spark.sql.connector.expressions.NamedReference | ||
| import org.apache.spark.sql.connector.expressions.Transform | ||
| import org.apache.spark.sql.connector.expressions.YearsTransform | ||
| import org.apache.spark.sql.connector.iceberg.distributions.ClusteredDistribution | ||
| import org.apache.spark.sql.connector.iceberg.distributions.Distribution | ||
| import org.apache.spark.sql.connector.iceberg.distributions.OrderedDistribution | ||
| import org.apache.spark.sql.connector.iceberg.distributions.UnspecifiedDistribution | ||
| import org.apache.spark.sql.connector.iceberg.expressions.NullOrdering | ||
| import org.apache.spark.sql.connector.iceberg.expressions.SortDirection | ||
| import org.apache.spark.sql.connector.iceberg.expressions.SortOrder | ||
| import org.apache.spark.sql.internal.SQLConf | ||
aokolnychyi marked this conversation as resolved.
Show resolved
Hide resolved
|
||
|
|
||
| object DistributionAndOrderingUtils { | ||
|
|
||
| def prepareQuery( | ||
| requiredDistribution: Distribution, | ||
| requiredOrdering: Seq[SortOrder], | ||
| query: LogicalPlan, | ||
| conf: SQLConf): LogicalPlan = { | ||
|
|
||
| val resolver = conf.resolver | ||
|
|
||
| val distribution = requiredDistribution match { | ||
| case d: OrderedDistribution => | ||
| d.ordering.map(e => toCatalyst(e, query, resolver)) | ||
| case d: ClusteredDistribution => | ||
| d.clustering.map(e => toCatalyst(e, query, resolver)) | ||
| case _: UnspecifiedDistribution => | ||
| Array.empty[catalyst.expressions.Expression] | ||
| } | ||
|
|
||
| val queryWithDistribution = if (distribution.nonEmpty) { | ||
| val numShufflePartitions = conf.numShufflePartitions | ||
| // the conversion to catalyst expressions above produces SortOrder expressions | ||
| // for OrderedDistribution and generic expressions for ClusteredDistribution | ||
| // this allows RepartitionByExpression to pick either range or hash partitioning | ||
| RepartitionByExpression(distribution, query, numShufflePartitions) | ||
|
Contributor
There was a problem hiding this comment. When After this PR, Logical Plan is In my opinion, the conversion of Please take a look here, thanks @aokolnychyi @rdblue |
||
| } else { | ||
| query | ||
| } | ||
|
|
||
| val ordering = requiredOrdering | ||
| .map(e => toCatalyst(e, query, resolver)) | ||
| .asInstanceOf[Seq[catalyst.expressions.SortOrder]] | ||
|
|
||
| val queryWithDistributionAndOrdering = if (ordering.nonEmpty) { | ||
| Sort(ordering, global = false, queryWithDistribution) | ||
| } else { | ||
| queryWithDistribution | ||
| } | ||
|
|
||
| queryWithDistributionAndOrdering | ||
| } | ||
|
|
||
| private def toCatalyst( | ||
| expr: Expression, | ||
| query: LogicalPlan, | ||
| resolver: Resolver): catalyst.expressions.Expression = { | ||
|
|
||
| // we cannot perform the resolution in the analyzer since we need to optimize expressions | ||
| // in nodes like OverwriteByExpression before constructing a logical write | ||
| def resolve(parts: Seq[String]): NamedExpression = { | ||
| query.resolve(parts, resolver) match { | ||
| case Some(attr) => | ||
| attr | ||
| case None => | ||
| val ref = parts.map(CatalogV2Implicits.quoteIfNeeded).mkString(".") | ||
| throw new AnalysisException(s"Cannot resolve '$ref' using ${query.output}") | ||
| } | ||
| } | ||
|
|
||
| expr match { | ||
| case s: SortOrder => | ||
| val catalystChild = toCatalyst(s.expression(), query, resolver) | ||
| catalyst.expressions.SortOrder(catalystChild, toCatalyst(s.direction), toCatalyst(s.nullOrdering), Set.empty) | ||
| case it: IdentityTransform => | ||
| resolve(it.ref.fieldNames) | ||
| case BucketTransform(numBuckets, ref) => | ||
| IcebergBucketTransform(numBuckets, resolve(ref.fieldNames)) | ||
| case yt: YearsTransform => | ||
| IcebergYearTransform(resolve(yt.ref.fieldNames)) | ||
| case mt: MonthsTransform => | ||
| IcebergMonthTransform(resolve(mt.ref.fieldNames)) | ||
| case dt: DaysTransform => | ||
| IcebergDayTransform(resolve(dt.ref.fieldNames)) | ||
| case ht: HoursTransform => | ||
| IcebergHourTransform(resolve(ht.ref.fieldNames)) | ||
| case ref: FieldReference => | ||
| resolve(ref.fieldNames) | ||
| case _ => | ||
| throw new RuntimeException(s"$expr is not currently supported") | ||
|
|
||
| } | ||
| } | ||
|
|
||
| private def toCatalyst(direction: SortDirection): catalyst.expressions.SortDirection = { | ||
| direction match { | ||
| case SortDirection.ASCENDING => catalyst.expressions.Ascending | ||
| case SortDirection.DESCENDING => catalyst.expressions.Descending | ||
| } | ||
| } | ||
|
|
||
| private def toCatalyst(nullOrdering: NullOrdering): catalyst.expressions.NullOrdering = { | ||
| nullOrdering match { | ||
| case NullOrdering.NULLS_FIRST => catalyst.expressions.NullsFirst | ||
| case NullOrdering.NULLS_LAST => catalyst.expressions.NullsLast | ||
| } | ||
| } | ||
|
|
||
| private object BucketTransform { | ||
| def unapply(transform: Transform): Option[(Int, FieldReference)] = transform match { | ||
| case bt: BucketTransform => bt.columns match { | ||
| case Seq(nf: NamedReference) => | ||
| Some(bt.numBuckets.value(), FieldReference(nf.fieldNames())) | ||
| case _ => | ||
| None | ||
| } | ||
| case _ => None | ||
| } | ||
| } | ||
| } | ||
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Uh oh!
There was an error while loading. Please reload this page.