szehon-ho commented on code in PR #10288: URL: https://github.com/apache/iceberg/pull/10288#discussion_r1626761248
########## api/src/main/java/org/apache/iceberg/actions/AnalyzeTable.java: ########## @@ -0,0 +1,66 @@ +/* + * 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.actions; + +import java.util.List; +import java.util.Set; + +/** An action that collects statistics of an Iceberg table and writes to Puffin files. */ +public interface AnalyzeTable extends Action<AnalyzeTable, AnalyzeTable.Result> { + /** + * The set of columns to be analyzed + * + * @param columns a set of column names to be analyzed + * @return this for method chaining + */ + AnalyzeTable columns(Set<String> columns); + + /** + * A set of statistics to be collected on the given columns of the given table + * + * @param statsToBeCollected set of statistics to be collected + * @return this for method chaining + */ + AnalyzeTable stats(Set<String> statsToBeCollected); Review Comment: Let's call statistics? Like StatisticsFile. https://iceberg.apache.org/contribute/#java-style-guidelines I think it can interpreted differently but I think point 3 implies we should make it have the full spelling if possible, and we dont have abbreviations for API methods in most of code. ########## api/src/main/java/org/apache/iceberg/actions/AnalyzeTable.java: ########## @@ -0,0 +1,58 @@ +/* + * 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.actions; + +import java.util.List; +import java.util.Set; + +/** An action that collects statistics of an Iceberg table and writes to Puffin files. */ +public interface AnalyzeTable extends Action<AnalyzeTable, AnalyzeTable.Result> { + /** + * The set of columns to be analyzed + * + * @param columns a set of column names to be analyzed + * @return this for method chaining + */ + AnalyzeTable columns(Set<String> columns); Review Comment: Nit, how about String... columns (see RewriteDataFiles). same for the others ########## spark/v3.5/spark/src/main/java/org/apache/iceberg/spark/actions/AnalyzeTableSparkAction.java: ########## @@ -0,0 +1,157 @@ +/* + * 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.io.IOException; +import java.util.List; +import java.util.Set; +import java.util.stream.Collectors; +import org.apache.iceberg.StatisticsFile; +import org.apache.iceberg.Table; +import org.apache.iceberg.actions.AnalyzeTable; +import org.apache.iceberg.actions.ImmutableAnalyzeTable; +import org.apache.iceberg.exceptions.ValidationException; +import org.apache.iceberg.puffin.StandardBlobTypes; +import org.apache.iceberg.relocated.com.google.common.base.Preconditions; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableSet; +import org.apache.iceberg.relocated.com.google.common.collect.Lists; +import org.apache.iceberg.relocated.com.google.common.collect.Sets; +import org.apache.iceberg.spark.JobGroupInfo; +import org.apache.iceberg.types.Type; +import org.apache.iceberg.types.Types; +import org.apache.spark.sql.SparkSession; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +/** Computes the statistic of the given columns and stores it as Puffin files. */ +public class AnalyzeTableSparkAction extends BaseSparkAction<AnalyzeTableSparkAction> + implements AnalyzeTable { + + private static final Logger LOG = LoggerFactory.getLogger(AnalyzeTableSparkAction.class); + private final Table table; + private Set<String> columnsToBeAnalyzed = ImmutableSet.of(); + private Set<String> statsToBecollected = + Sets.newHashSet(StandardBlobTypes.APACHE_DATASKETCHES_THETA_V1); Review Comment: Why did we have the StandardBlobType static set and not use it here? ########## api/src/main/java/org/apache/iceberg/actions/AnalyzeTable.java: ########## @@ -0,0 +1,66 @@ +/* + * 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.actions; + +import java.util.List; +import java.util.Set; + +/** An action that collects statistics of an Iceberg table and writes to Puffin files. */ +public interface AnalyzeTable extends Action<AnalyzeTable, AnalyzeTable.Result> { + /** + * The set of columns to be analyzed + * + * @param columns a set of column names to be analyzed + * @return this for method chaining + */ + AnalyzeTable columns(Set<String> columns); + + /** + * A set of statistics to be collected on the given columns of the given table Review Comment: The set of statistics to be collected? (given columns, given tables is specified elsewhere) ########## spark/v3.5/spark/src/main/java/org/apache/iceberg/spark/actions/NDVSketchGenerator.java: ########## @@ -0,0 +1,184 @@ +/* + * 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.io.IOException; +import java.nio.ByteBuffer; +import java.util.Iterator; +import java.util.List; +import java.util.Map; +import java.util.UUID; +import java.util.stream.Collectors; +import org.apache.datasketches.theta.CompactSketch; +import org.apache.datasketches.theta.SetOperationBuilder; +import org.apache.datasketches.theta.UpdateSketch; +import org.apache.iceberg.GenericBlobMetadata; +import org.apache.iceberg.GenericStatisticsFile; +import org.apache.iceberg.HasTableOperations; +import org.apache.iceberg.StatisticsFile; +import org.apache.iceberg.Table; +import org.apache.iceberg.TableOperations; +import org.apache.iceberg.io.FileIO; +import org.apache.iceberg.io.OutputFile; +import org.apache.iceberg.puffin.Blob; +import org.apache.iceberg.puffin.Puffin; +import org.apache.iceberg.puffin.PuffinWriter; +import org.apache.iceberg.puffin.StandardBlobTypes; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableList; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableMap; +import org.apache.iceberg.relocated.com.google.common.collect.Lists; +import org.apache.iceberg.relocated.com.google.common.collect.Maps; +import org.apache.iceberg.types.Types; +import org.apache.spark.api.java.JavaPairRDD; +import org.apache.spark.api.java.function.Function2; +import org.apache.spark.api.java.function.PairFlatMapFunction; +import org.apache.spark.sql.Dataset; +import org.apache.spark.sql.Row; +import org.apache.spark.sql.SparkSession; +import scala.Tuple2; + +public class NDVSketchGenerator { + + private NDVSketchGenerator() {} + + static StatisticsFile generateNDV( + SparkSession spark, Table table, long snapshotId, String... columnsToBeAnalyzed) + throws IOException { + List<String> columnList; + if (columnsToBeAnalyzed == null || columnsToBeAnalyzed.length == 0) { + columnList = + table.schema().columns().stream() + .map(Types.NestedField::name) + .collect(Collectors.toList()); + } else { + columnList = Lists.newArrayList(columnsToBeAnalyzed); + } + Iterator<Tuple2<String, ThetaSketchJavaSerializable>> tuple2Iterator = + computeNDVSketches(spark, table.name(), snapshotId, columnList); + Map<String, ThetaSketchJavaSerializable> sketchMap = Maps.newHashMap(); + + tuple2Iterator.forEachRemaining(tuple -> sketchMap.put(tuple._1, tuple._2)); + return writeToPuffin(table, columnList, sketchMap); + } + + private static StatisticsFile writeToPuffin( + Table table, List<String> columns, Map<String, ThetaSketchJavaSerializable> sketchMap) + throws IOException { + int columnSizes = columns.size(); + TableOperations operations = ((HasTableOperations) table).operations(); + FileIO fileIO = ((HasTableOperations) table).operations().io(); + String path = operations.metadataFileLocation(String.format("%s.stats", UUID.randomUUID())); + OutputFile outputFile = fileIO.newOutputFile(path); + try (PuffinWriter writer = + Puffin.write(outputFile).createdBy("Spark DistinctCountProcedure").build()) { + for (int i = 0; i < columnSizes; i++) { Review Comment: Let's use the enhanced for loop ########## spark/v3.5/spark/src/main/java/org/apache/iceberg/spark/actions/NDVSketchGenerator.java: ########## @@ -0,0 +1,184 @@ +/* + * 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.io.IOException; +import java.nio.ByteBuffer; +import java.util.Iterator; +import java.util.List; +import java.util.Map; +import java.util.UUID; +import java.util.stream.Collectors; +import org.apache.datasketches.theta.CompactSketch; +import org.apache.datasketches.theta.SetOperationBuilder; +import org.apache.datasketches.theta.UpdateSketch; +import org.apache.iceberg.GenericBlobMetadata; +import org.apache.iceberg.GenericStatisticsFile; +import org.apache.iceberg.HasTableOperations; +import org.apache.iceberg.StatisticsFile; +import org.apache.iceberg.Table; +import org.apache.iceberg.TableOperations; +import org.apache.iceberg.io.FileIO; +import org.apache.iceberg.io.OutputFile; +import org.apache.iceberg.puffin.Blob; +import org.apache.iceberg.puffin.Puffin; +import org.apache.iceberg.puffin.PuffinWriter; +import org.apache.iceberg.puffin.StandardBlobTypes; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableList; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableMap; +import org.apache.iceberg.relocated.com.google.common.collect.Lists; +import org.apache.iceberg.relocated.com.google.common.collect.Maps; +import org.apache.iceberg.types.Types; +import org.apache.spark.api.java.JavaPairRDD; +import org.apache.spark.api.java.function.Function2; +import org.apache.spark.api.java.function.PairFlatMapFunction; +import org.apache.spark.sql.Dataset; +import org.apache.spark.sql.Row; +import org.apache.spark.sql.SparkSession; +import scala.Tuple2; + +public class NDVSketchGenerator { + + private NDVSketchGenerator() {} + + static StatisticsFile generateNDV( + SparkSession spark, Table table, long snapshotId, String... columnsToBeAnalyzed) + throws IOException { + List<String> columnList; + if (columnsToBeAnalyzed == null || columnsToBeAnalyzed.length == 0) { + columnList = + table.schema().columns().stream() + .map(Types.NestedField::name) + .collect(Collectors.toList()); + } else { + columnList = Lists.newArrayList(columnsToBeAnalyzed); + } + Iterator<Tuple2<String, ThetaSketchJavaSerializable>> tuple2Iterator = + computeNDVSketches(spark, table.name(), snapshotId, columnList); + Map<String, ThetaSketchJavaSerializable> sketchMap = Maps.newHashMap(); + + tuple2Iterator.forEachRemaining(tuple -> sketchMap.put(tuple._1, tuple._2)); + return writeToPuffin(table, columnList, sketchMap); + } + + private static StatisticsFile writeToPuffin( + Table table, List<String> columns, Map<String, ThetaSketchJavaSerializable> sketchMap) + throws IOException { + int columnSizes = columns.size(); + TableOperations operations = ((HasTableOperations) table).operations(); + FileIO fileIO = ((HasTableOperations) table).operations().io(); Review Comment: operations.io() ########## api/src/main/java/org/apache/iceberg/actions/AnalyzeTable.java: ########## @@ -0,0 +1,66 @@ +/* + * 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.actions; + +import java.util.List; +import java.util.Set; + +/** An action that collects statistics of an Iceberg table and writes to Puffin files. */ +public interface AnalyzeTable extends Action<AnalyzeTable, AnalyzeTable.Result> { + /** + * The set of columns to be analyzed + * + * @param columns a set of column names to be analyzed + * @return this for method chaining + */ + AnalyzeTable columns(Set<String> columns); + + /** + * A set of statistics to be collected on the given columns of the given table + * + * @param statsToBeCollected set of statistics to be collected + * @return this for method chaining + */ + AnalyzeTable stats(Set<String> statsToBeCollected); Review Comment: Also statsToBeCollected => types ? ########## api/src/main/java/org/apache/iceberg/actions/AnalyzeTable.java: ########## @@ -0,0 +1,66 @@ +/* + * 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.actions; + +import java.util.List; +import java.util.Set; + +/** An action that collects statistics of an Iceberg table and writes to Puffin files. */ +public interface AnalyzeTable extends Action<AnalyzeTable, AnalyzeTable.Result> { + /** + * The set of columns to be analyzed + * + * @param columns a set of column names to be analyzed + * @return this for method chaining + */ + AnalyzeTable columns(Set<String> columns); + + /** + * A set of statistics to be collected on the given columns of the given table + * + * @param statsToBeCollected set of statistics to be collected + * @return this for method chaining + */ + AnalyzeTable stats(Set<String> statsToBeCollected); + + /** + * id of the snapshot for which stats needs to be collected + * + * @param snapshotId long id of the snapshot for which stats needs to be collected + * @return this for method chaining + */ + AnalyzeTable snapshot(String snapshotId); + + /** The action result that contains a summary of the Analysis. */ Review Comment: plural? `contains summaries of the analysis`? Also if capital, it can be a a javadoc link. ########## spark/v3.5/spark/src/main/java/org/apache/iceberg/spark/actions/AnalyzeTableSparkAction.java: ########## @@ -0,0 +1,157 @@ +/* + * 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.io.IOException; +import java.util.List; +import java.util.Set; +import java.util.stream.Collectors; +import org.apache.iceberg.StatisticsFile; +import org.apache.iceberg.Table; +import org.apache.iceberg.actions.AnalyzeTable; +import org.apache.iceberg.actions.ImmutableAnalyzeTable; +import org.apache.iceberg.exceptions.ValidationException; +import org.apache.iceberg.puffin.StandardBlobTypes; +import org.apache.iceberg.relocated.com.google.common.base.Preconditions; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableSet; +import org.apache.iceberg.relocated.com.google.common.collect.Lists; +import org.apache.iceberg.relocated.com.google.common.collect.Sets; +import org.apache.iceberg.spark.JobGroupInfo; +import org.apache.iceberg.types.Type; +import org.apache.iceberg.types.Types; +import org.apache.spark.sql.SparkSession; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +/** Computes the statistic of the given columns and stores it as Puffin files. */ +public class AnalyzeTableSparkAction extends BaseSparkAction<AnalyzeTableSparkAction> + implements AnalyzeTable { + + private static final Logger LOG = LoggerFactory.getLogger(AnalyzeTableSparkAction.class); + private final Table table; + private Set<String> columnsToBeAnalyzed = ImmutableSet.of(); + private Set<String> statsToBecollected = + Sets.newHashSet(StandardBlobTypes.APACHE_DATASKETCHES_THETA_V1); + private Long snapshotId; + + AnalyzeTableSparkAction(SparkSession spark, Table table) { + super(spark); + this.table = table; + } + + @Override + protected AnalyzeTableSparkAction self() { + return this; + } + + @Override + public Result execute() { + String desc = String.format("Analyzing table %s", table.name()); Review Comment: Should we put snapshotId as well? ########## spark/v3.5/spark/src/main/java/org/apache/iceberg/spark/actions/AnalyzeTableSparkAction.java: ########## @@ -0,0 +1,157 @@ +/* + * 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.io.IOException; +import java.util.List; +import java.util.Set; +import java.util.stream.Collectors; +import org.apache.iceberg.StatisticsFile; +import org.apache.iceberg.Table; +import org.apache.iceberg.actions.AnalyzeTable; +import org.apache.iceberg.actions.ImmutableAnalyzeTable; +import org.apache.iceberg.exceptions.ValidationException; +import org.apache.iceberg.puffin.StandardBlobTypes; +import org.apache.iceberg.relocated.com.google.common.base.Preconditions; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableSet; +import org.apache.iceberg.relocated.com.google.common.collect.Lists; +import org.apache.iceberg.relocated.com.google.common.collect.Sets; +import org.apache.iceberg.spark.JobGroupInfo; +import org.apache.iceberg.types.Type; +import org.apache.iceberg.types.Types; +import org.apache.spark.sql.SparkSession; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +/** Computes the statistic of the given columns and stores it as Puffin files. */ +public class AnalyzeTableSparkAction extends BaseSparkAction<AnalyzeTableSparkAction> + implements AnalyzeTable { + + private static final Logger LOG = LoggerFactory.getLogger(AnalyzeTableSparkAction.class); + private final Table table; Review Comment: Nit: we should have a newline between the static and non-static imports ########## api/src/main/java/org/apache/iceberg/actions/AnalyzeTable.java: ########## @@ -0,0 +1,66 @@ +/* + * 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.actions; + +import java.util.List; +import java.util.Set; + +/** An action that collects statistics of an Iceberg table and writes to Puffin files. */ +public interface AnalyzeTable extends Action<AnalyzeTable, AnalyzeTable.Result> { + /** + * The set of columns to be analyzed + * + * @param columns a set of column names to be analyzed + * @return this for method chaining + */ + AnalyzeTable columns(Set<String> columns); + + /** + * A set of statistics to be collected on the given columns of the given table + * + * @param statsToBeCollected set of statistics to be collected + * @return this for method chaining + */ + AnalyzeTable stats(Set<String> statsToBeCollected); + + /** + * id of the snapshot for which stats needs to be collected Review Comment: needs => need ########## api/src/main/java/org/apache/iceberg/actions/AnalyzeTable.java: ########## @@ -0,0 +1,66 @@ +/* + * 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.actions; + +import java.util.List; +import java.util.Set; + +/** An action that collects statistics of an Iceberg table and writes to Puffin files. */ +public interface AnalyzeTable extends Action<AnalyzeTable, AnalyzeTable.Result> { + /** + * The set of columns to be analyzed + * + * @param columns a set of column names to be analyzed + * @return this for method chaining + */ + AnalyzeTable columns(Set<String> columns); + + /** + * A set of statistics to be collected on the given columns of the given table + * + * @param statsToBeCollected set of statistics to be collected + * @return this for method chaining + */ + AnalyzeTable stats(Set<String> statsToBeCollected); + + /** + * id of the snapshot for which stats needs to be collected + * + * @param snapshotId long id of the snapshot for which stats needs to be collected + * @return this for method chaining + */ + AnalyzeTable snapshot(String snapshotId); + + /** The action result that contains a summary of the Analysis. */ + interface Result { + /** Returns summary of analysis */ + List<AnalysisResult> analysisResults(); + } + + interface AnalysisResult { + /** Returns the name of statistic */ + String statsName(); + + /** Returns if the stats was collected successfully */ + boolean statsCollected(); Review Comment: Can we imply success by having no errors? Ie, is the success boolean redundant? ########## api/src/main/java/org/apache/iceberg/actions/AnalyzeTable.java: ########## @@ -0,0 +1,66 @@ +/* + * 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.actions; + +import java.util.List; +import java.util.Set; + +/** An action that collects statistics of an Iceberg table and writes to Puffin files. */ +public interface AnalyzeTable extends Action<AnalyzeTable, AnalyzeTable.Result> { + /** + * The set of columns to be analyzed + * + * @param columns a set of column names to be analyzed + * @return this for method chaining + */ + AnalyzeTable columns(Set<String> columns); + + /** + * A set of statistics to be collected on the given columns of the given table + * + * @param statsToBeCollected set of statistics to be collected + * @return this for method chaining + */ + AnalyzeTable stats(Set<String> statsToBeCollected); + + /** + * id of the snapshot for which stats needs to be collected + * + * @param snapshotId long id of the snapshot for which stats needs to be collected + * @return this for method chaining + */ + AnalyzeTable snapshot(String snapshotId); + + /** The action result that contains a summary of the Analysis. */ + interface Result { + /** Returns summary of analysis */ + List<AnalysisResult> analysisResults(); + } + + interface AnalysisResult { + /** Returns the name of statistic */ + String statsName(); Review Comment: name => type? wdyt? ########## spark/v3.5/spark/src/main/java/org/apache/iceberg/spark/actions/AnalyzeTableSparkAction.java: ########## @@ -0,0 +1,157 @@ +/* + * 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.io.IOException; +import java.util.List; +import java.util.Set; +import java.util.stream.Collectors; +import org.apache.iceberg.StatisticsFile; +import org.apache.iceberg.Table; +import org.apache.iceberg.actions.AnalyzeTable; +import org.apache.iceberg.actions.ImmutableAnalyzeTable; +import org.apache.iceberg.exceptions.ValidationException; +import org.apache.iceberg.puffin.StandardBlobTypes; +import org.apache.iceberg.relocated.com.google.common.base.Preconditions; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableSet; +import org.apache.iceberg.relocated.com.google.common.collect.Lists; +import org.apache.iceberg.relocated.com.google.common.collect.Sets; +import org.apache.iceberg.spark.JobGroupInfo; +import org.apache.iceberg.types.Type; +import org.apache.iceberg.types.Types; +import org.apache.spark.sql.SparkSession; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +/** Computes the statistic of the given columns and stores it as Puffin files. */ +public class AnalyzeTableSparkAction extends BaseSparkAction<AnalyzeTableSparkAction> + implements AnalyzeTable { + + private static final Logger LOG = LoggerFactory.getLogger(AnalyzeTableSparkAction.class); + private final Table table; + private Set<String> columnsToBeAnalyzed = ImmutableSet.of(); + private Set<String> statsToBecollected = + Sets.newHashSet(StandardBlobTypes.APACHE_DATASKETCHES_THETA_V1); + private Long snapshotId; + + AnalyzeTableSparkAction(SparkSession spark, Table table) { + super(spark); + this.table = table; + } + + @Override + protected AnalyzeTableSparkAction self() { + return this; + } + + @Override + public Result execute() { + String desc = String.format("Analyzing table %s", table.name()); + JobGroupInfo info = newJobGroupInfo("ANALYZE-TABLE", desc); + return withJobGroupInfo(info, this::doExecute); + } + + private Result doExecute() { + LOG.info("Starting the analysis of {}", table.name()); + List<AnalysisResult> analysisResults = + statsToBecollected.stream() + .map( + statsName -> { + switch (statsName) { + case StandardBlobTypes.APACHE_DATASKETCHES_THETA_V1: + return generateNDVAndCommit(); + default: + return ImmutableAnalyzeTable.AnalysisResult.builder() + .statsName(statsName) + .statsCollected(false) + .addAllErrors(Lists.newArrayList("Stats type not supported")) + .build(); + } + }) + .collect(Collectors.toList()); + return ImmutableAnalyzeTable.Result.builder().analysisResults(analysisResults).build(); + } + + private boolean analyzeableTypes(Set<String> columns) { Review Comment: According to intellij, there is a typo (analyzable) ########## spark/v3.5/spark/src/main/java/org/apache/iceberg/spark/actions/AnalyzeTableSparkAction.java: ########## @@ -0,0 +1,157 @@ +/* + * 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.io.IOException; +import java.util.List; +import java.util.Set; +import java.util.stream.Collectors; +import org.apache.iceberg.StatisticsFile; +import org.apache.iceberg.Table; +import org.apache.iceberg.actions.AnalyzeTable; +import org.apache.iceberg.actions.ImmutableAnalyzeTable; +import org.apache.iceberg.exceptions.ValidationException; +import org.apache.iceberg.puffin.StandardBlobTypes; +import org.apache.iceberg.relocated.com.google.common.base.Preconditions; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableSet; +import org.apache.iceberg.relocated.com.google.common.collect.Lists; +import org.apache.iceberg.relocated.com.google.common.collect.Sets; +import org.apache.iceberg.spark.JobGroupInfo; +import org.apache.iceberg.types.Type; +import org.apache.iceberg.types.Types; +import org.apache.spark.sql.SparkSession; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +/** Computes the statistic of the given columns and stores it as Puffin files. */ +public class AnalyzeTableSparkAction extends BaseSparkAction<AnalyzeTableSparkAction> + implements AnalyzeTable { + + private static final Logger LOG = LoggerFactory.getLogger(AnalyzeTableSparkAction.class); + private final Table table; + private Set<String> columnsToBeAnalyzed = ImmutableSet.of(); + private Set<String> statsToBecollected = + Sets.newHashSet(StandardBlobTypes.APACHE_DATASKETCHES_THETA_V1); + private Long snapshotId; + + AnalyzeTableSparkAction(SparkSession spark, Table table) { + super(spark); + this.table = table; + } + + @Override + protected AnalyzeTableSparkAction self() { + return this; + } + + @Override + public Result execute() { + String desc = String.format("Analyzing table %s", table.name()); + JobGroupInfo info = newJobGroupInfo("ANALYZE-TABLE", desc); + return withJobGroupInfo(info, this::doExecute); + } + + private Result doExecute() { + LOG.info("Starting the analysis of {}", table.name()); + List<AnalysisResult> analysisResults = + statsToBecollected.stream() + .map( + statsName -> { + switch (statsName) { + case StandardBlobTypes.APACHE_DATASKETCHES_THETA_V1: + return generateNDVAndCommit(); + default: + return ImmutableAnalyzeTable.AnalysisResult.builder() + .statsName(statsName) + .statsCollected(false) + .addAllErrors(Lists.newArrayList("Stats type not supported")) + .build(); + } + }) + .collect(Collectors.toList()); + return ImmutableAnalyzeTable.Result.builder().analysisResults(analysisResults).build(); + } + + private boolean analyzeableTypes(Set<String> columns) { + return columns.stream() + .anyMatch( + columnName -> { + Types.NestedField field = table.schema().findField(columnName); + if (field == null) { + throw new ValidationException("No column with %s name in the table", columnName); + } + Type type = field.type(); + return type.isListType() + || type.isMapType() + || type.isNestedType() + || type.isStructType(); + }); + } + + private AnalysisResult generateNDVAndCommit() { + try { + Review Comment: Feel free to disagree, but I think removing the newline here is better, as its already the beginning ########## spark/v3.5/spark/src/main/java/org/apache/iceberg/spark/actions/AnalyzeTableSparkAction.java: ########## @@ -0,0 +1,157 @@ +/* + * 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.io.IOException; +import java.util.List; +import java.util.Set; +import java.util.stream.Collectors; +import org.apache.iceberg.StatisticsFile; +import org.apache.iceberg.Table; +import org.apache.iceberg.actions.AnalyzeTable; +import org.apache.iceberg.actions.ImmutableAnalyzeTable; +import org.apache.iceberg.exceptions.ValidationException; +import org.apache.iceberg.puffin.StandardBlobTypes; +import org.apache.iceberg.relocated.com.google.common.base.Preconditions; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableSet; +import org.apache.iceberg.relocated.com.google.common.collect.Lists; +import org.apache.iceberg.relocated.com.google.common.collect.Sets; +import org.apache.iceberg.spark.JobGroupInfo; +import org.apache.iceberg.types.Type; +import org.apache.iceberg.types.Types; +import org.apache.spark.sql.SparkSession; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +/** Computes the statistic of the given columns and stores it as Puffin files. */ +public class AnalyzeTableSparkAction extends BaseSparkAction<AnalyzeTableSparkAction> + implements AnalyzeTable { + + private static final Logger LOG = LoggerFactory.getLogger(AnalyzeTableSparkAction.class); + private final Table table; + private Set<String> columnsToBeAnalyzed = ImmutableSet.of(); Review Comment: Again, suggest variable names 'columns' and 'types' (below) to be more concise? ########## spark/v3.5/spark/src/main/java/org/apache/iceberg/spark/actions/AnalyzeTableSparkAction.java: ########## @@ -0,0 +1,157 @@ +/* + * 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.io.IOException; +import java.util.List; +import java.util.Set; +import java.util.stream.Collectors; +import org.apache.iceberg.StatisticsFile; +import org.apache.iceberg.Table; +import org.apache.iceberg.actions.AnalyzeTable; +import org.apache.iceberg.actions.ImmutableAnalyzeTable; +import org.apache.iceberg.exceptions.ValidationException; +import org.apache.iceberg.puffin.StandardBlobTypes; +import org.apache.iceberg.relocated.com.google.common.base.Preconditions; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableSet; +import org.apache.iceberg.relocated.com.google.common.collect.Lists; +import org.apache.iceberg.relocated.com.google.common.collect.Sets; +import org.apache.iceberg.spark.JobGroupInfo; +import org.apache.iceberg.types.Type; +import org.apache.iceberg.types.Types; +import org.apache.spark.sql.SparkSession; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +/** Computes the statistic of the given columns and stores it as Puffin files. */ +public class AnalyzeTableSparkAction extends BaseSparkAction<AnalyzeTableSparkAction> + implements AnalyzeTable { + + private static final Logger LOG = LoggerFactory.getLogger(AnalyzeTableSparkAction.class); + private final Table table; + private Set<String> columnsToBeAnalyzed = ImmutableSet.of(); + private Set<String> statsToBecollected = + Sets.newHashSet(StandardBlobTypes.APACHE_DATASKETCHES_THETA_V1); + private Long snapshotId; + + AnalyzeTableSparkAction(SparkSession spark, Table table) { + super(spark); + this.table = table; + } + + @Override + protected AnalyzeTableSparkAction self() { + return this; + } + + @Override + public Result execute() { + String desc = String.format("Analyzing table %s", table.name()); + JobGroupInfo info = newJobGroupInfo("ANALYZE-TABLE", desc); + return withJobGroupInfo(info, this::doExecute); + } + + private Result doExecute() { + LOG.info("Starting the analysis of {}", table.name()); + List<AnalysisResult> analysisResults = + statsToBecollected.stream() + .map( + statsName -> { + switch (statsName) { + case StandardBlobTypes.APACHE_DATASKETCHES_THETA_V1: + return generateNDVAndCommit(); + default: + return ImmutableAnalyzeTable.AnalysisResult.builder() + .statsName(statsName) + .statsCollected(false) + .addAllErrors(Lists.newArrayList("Stats type not supported")) + .build(); + } + }) + .collect(Collectors.toList()); + return ImmutableAnalyzeTable.Result.builder().analysisResults(analysisResults).build(); + } + + private boolean analyzeableTypes(Set<String> columns) { + return columns.stream() + .anyMatch( + columnName -> { + Types.NestedField field = table.schema().findField(columnName); + if (field == null) { + throw new ValidationException("No column with %s name in the table", columnName); + } + Type type = field.type(); + return type.isListType() + || type.isMapType() + || type.isNestedType() + || type.isStructType(); + }); + } + + private AnalysisResult generateNDVAndCommit() { + try { + + if (snapshotId == null) { + snapshotId = table.currentSnapshot().snapshotId(); Review Comment: Nit: let's move this logic to the constructor? I think default values are usually handled in the spark action constructors, as it helps to keep the business logic more concise. ########## spark/v3.5/spark/src/main/java/org/apache/iceberg/spark/actions/NDVSketchGenerator.java: ########## @@ -0,0 +1,184 @@ +/* + * 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.io.IOException; +import java.nio.ByteBuffer; +import java.util.Iterator; +import java.util.List; +import java.util.Map; +import java.util.UUID; +import java.util.stream.Collectors; +import org.apache.datasketches.theta.CompactSketch; +import org.apache.datasketches.theta.SetOperationBuilder; +import org.apache.datasketches.theta.UpdateSketch; +import org.apache.iceberg.GenericBlobMetadata; +import org.apache.iceberg.GenericStatisticsFile; +import org.apache.iceberg.HasTableOperations; +import org.apache.iceberg.StatisticsFile; +import org.apache.iceberg.Table; +import org.apache.iceberg.TableOperations; +import org.apache.iceberg.io.FileIO; +import org.apache.iceberg.io.OutputFile; +import org.apache.iceberg.puffin.Blob; +import org.apache.iceberg.puffin.Puffin; +import org.apache.iceberg.puffin.PuffinWriter; +import org.apache.iceberg.puffin.StandardBlobTypes; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableList; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableMap; +import org.apache.iceberg.relocated.com.google.common.collect.Lists; +import org.apache.iceberg.relocated.com.google.common.collect.Maps; +import org.apache.iceberg.types.Types; +import org.apache.spark.api.java.JavaPairRDD; +import org.apache.spark.api.java.function.Function2; +import org.apache.spark.api.java.function.PairFlatMapFunction; +import org.apache.spark.sql.Dataset; +import org.apache.spark.sql.Row; +import org.apache.spark.sql.SparkSession; +import scala.Tuple2; + +public class NDVSketchGenerator { + + private NDVSketchGenerator() {} + + static StatisticsFile generateNDV( + SparkSession spark, Table table, long snapshotId, String... columnsToBeAnalyzed) + throws IOException { + List<String> columnList; + if (columnsToBeAnalyzed == null || columnsToBeAnalyzed.length == 0) { + columnList = + table.schema().columns().stream() + .map(Types.NestedField::name) + .collect(Collectors.toList()); + } else { + columnList = Lists.newArrayList(columnsToBeAnalyzed); + } + Iterator<Tuple2<String, ThetaSketchJavaSerializable>> tuple2Iterator = + computeNDVSketches(spark, table.name(), snapshotId, columnList); + Map<String, ThetaSketchJavaSerializable> sketchMap = Maps.newHashMap(); + + tuple2Iterator.forEachRemaining(tuple -> sketchMap.put(tuple._1, tuple._2)); + return writeToPuffin(table, columnList, sketchMap); + } + + private static StatisticsFile writeToPuffin( + Table table, List<String> columns, Map<String, ThetaSketchJavaSerializable> sketchMap) + throws IOException { + int columnSizes = columns.size(); + TableOperations operations = ((HasTableOperations) table).operations(); + FileIO fileIO = ((HasTableOperations) table).operations().io(); + String path = operations.metadataFileLocation(String.format("%s.stats", UUID.randomUUID())); + OutputFile outputFile = fileIO.newOutputFile(path); + try (PuffinWriter writer = + Puffin.write(outputFile).createdBy("Spark DistinctCountProcedure").build()) { + for (int i = 0; i < columnSizes; i++) { + writer.add( + new Blob( + StandardBlobTypes.APACHE_DATASKETCHES_THETA_V1, + ImmutableList.of(table.schema().findField(columns.get(i)).fieldId()), + table.currentSnapshot().snapshotId(), + table.currentSnapshot().sequenceNumber(), + ByteBuffer.wrap(sketchMap.get(columns.get(i)).getSketch().toByteArray()), + null, + ImmutableMap.of())); + } + writer.finish(); + + return new GenericStatisticsFile( + table.currentSnapshot().snapshotId(), + path, + writer.fileSize(), + writer.footerSize(), + writer.writtenBlobsMetadata().stream() + .map(GenericBlobMetadata::from) + .collect(ImmutableList.toImmutableList())); + + } catch (IOException e) { + throw e; + } + } + + static Iterator<Tuple2<String, ThetaSketchJavaSerializable>> computeNDVSketches( + SparkSession spark, String tableName, long snapshotId, List<String> columns) { + String sql = + String.format( + "select %s from %s VERSION AS OF %d", String.join(",", columns), tableName, snapshotId); + Dataset<Row> data = spark.sql(sql); + final JavaPairRDD<String, String> pairs = + data.javaRDD() + .mapPartitionsToPair( + (PairFlatMapFunction<Iterator<Row>, String, String>) + input -> { + final List<Tuple2<String, String>> list = Lists.newArrayList(); Review Comment: We usually dont put finals in the code, as compilers mostly do this now. (this was from @aokolnychyi ) ########## api/src/main/java/org/apache/iceberg/actions/AnalyzeTable.java: ########## @@ -0,0 +1,58 @@ +/* + * 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.actions; + +import java.util.List; +import java.util.Set; + +/** An action that collects statistics of an Iceberg table and writes to Puffin files. */ +public interface AnalyzeTable extends Action<AnalyzeTable, AnalyzeTable.Result> { + /** + * The set of columns to be analyzed + * + * @param columns a set of column names to be analyzed + * @return this for method chaining + */ + AnalyzeTable columns(Set<String> columns); + + /** + * A set of statistics to be collected on the given columns of the given table + * + * @param statsToBeCollected set of statistics to be collected + * @return this for method chaining + */ + AnalyzeTable stats(Set<String> statsToBeCollected); + Review Comment: Should we support branch/tag as well? (I guess in subsequent pr) ########## spark/v3.5/spark/src/main/java/org/apache/iceberg/spark/actions/NDVSketchGenerator.java: ########## @@ -0,0 +1,184 @@ +/* + * 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.io.IOException; +import java.nio.ByteBuffer; +import java.util.Iterator; +import java.util.List; +import java.util.Map; +import java.util.UUID; +import java.util.stream.Collectors; +import org.apache.datasketches.theta.CompactSketch; +import org.apache.datasketches.theta.SetOperationBuilder; +import org.apache.datasketches.theta.UpdateSketch; +import org.apache.iceberg.GenericBlobMetadata; +import org.apache.iceberg.GenericStatisticsFile; +import org.apache.iceberg.HasTableOperations; +import org.apache.iceberg.StatisticsFile; +import org.apache.iceberg.Table; +import org.apache.iceberg.TableOperations; +import org.apache.iceberg.io.FileIO; +import org.apache.iceberg.io.OutputFile; +import org.apache.iceberg.puffin.Blob; +import org.apache.iceberg.puffin.Puffin; +import org.apache.iceberg.puffin.PuffinWriter; +import org.apache.iceberg.puffin.StandardBlobTypes; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableList; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableMap; +import org.apache.iceberg.relocated.com.google.common.collect.Lists; +import org.apache.iceberg.relocated.com.google.common.collect.Maps; +import org.apache.iceberg.types.Types; +import org.apache.spark.api.java.JavaPairRDD; +import org.apache.spark.api.java.function.Function2; +import org.apache.spark.api.java.function.PairFlatMapFunction; +import org.apache.spark.sql.Dataset; +import org.apache.spark.sql.Row; +import org.apache.spark.sql.SparkSession; +import scala.Tuple2; + +public class NDVSketchGenerator { + + private NDVSketchGenerator() {} + + static StatisticsFile generateNDV( + SparkSession spark, Table table, long snapshotId, String... columnsToBeAnalyzed) + throws IOException { + List<String> columnList; + if (columnsToBeAnalyzed == null || columnsToBeAnalyzed.length == 0) { + columnList = + table.schema().columns().stream() + .map(Types.NestedField::name) + .collect(Collectors.toList()); + } else { + columnList = Lists.newArrayList(columnsToBeAnalyzed); + } + Iterator<Tuple2<String, ThetaSketchJavaSerializable>> tuple2Iterator = + computeNDVSketches(spark, table.name(), snapshotId, columnList); + Map<String, ThetaSketchJavaSerializable> sketchMap = Maps.newHashMap(); + + tuple2Iterator.forEachRemaining(tuple -> sketchMap.put(tuple._1, tuple._2)); + return writeToPuffin(table, columnList, sketchMap); + } + + private static StatisticsFile writeToPuffin( + Table table, List<String> columns, Map<String, ThetaSketchJavaSerializable> sketchMap) + throws IOException { + int columnSizes = columns.size(); + TableOperations operations = ((HasTableOperations) table).operations(); + FileIO fileIO = ((HasTableOperations) table).operations().io(); + String path = operations.metadataFileLocation(String.format("%s.stats", UUID.randomUUID())); Review Comment: Question, is it valuable to prefix it with 'ndv' or something like that? ########## spark/v3.5/spark/src/main/java/org/apache/iceberg/spark/actions/NDVSketchGenerator.java: ########## @@ -0,0 +1,184 @@ +/* + * 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.io.IOException; +import java.nio.ByteBuffer; +import java.util.Iterator; +import java.util.List; +import java.util.Map; +import java.util.UUID; +import java.util.stream.Collectors; +import org.apache.datasketches.theta.CompactSketch; +import org.apache.datasketches.theta.SetOperationBuilder; +import org.apache.datasketches.theta.UpdateSketch; +import org.apache.iceberg.GenericBlobMetadata; +import org.apache.iceberg.GenericStatisticsFile; +import org.apache.iceberg.HasTableOperations; +import org.apache.iceberg.StatisticsFile; +import org.apache.iceberg.Table; +import org.apache.iceberg.TableOperations; +import org.apache.iceberg.io.FileIO; +import org.apache.iceberg.io.OutputFile; +import org.apache.iceberg.puffin.Blob; +import org.apache.iceberg.puffin.Puffin; +import org.apache.iceberg.puffin.PuffinWriter; +import org.apache.iceberg.puffin.StandardBlobTypes; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableList; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableMap; +import org.apache.iceberg.relocated.com.google.common.collect.Lists; +import org.apache.iceberg.relocated.com.google.common.collect.Maps; +import org.apache.iceberg.types.Types; +import org.apache.spark.api.java.JavaPairRDD; +import org.apache.spark.api.java.function.Function2; +import org.apache.spark.api.java.function.PairFlatMapFunction; +import org.apache.spark.sql.Dataset; +import org.apache.spark.sql.Row; +import org.apache.spark.sql.SparkSession; +import scala.Tuple2; + +public class NDVSketchGenerator { + + private NDVSketchGenerator() {} + + static StatisticsFile generateNDV( + SparkSession spark, Table table, long snapshotId, String... columnsToBeAnalyzed) + throws IOException { + List<String> columnList; + if (columnsToBeAnalyzed == null || columnsToBeAnalyzed.length == 0) { + columnList = + table.schema().columns().stream() + .map(Types.NestedField::name) + .collect(Collectors.toList()); + } else { + columnList = Lists.newArrayList(columnsToBeAnalyzed); + } + Iterator<Tuple2<String, ThetaSketchJavaSerializable>> tuple2Iterator = + computeNDVSketches(spark, table.name(), snapshotId, columnList); + Map<String, ThetaSketchJavaSerializable> sketchMap = Maps.newHashMap(); + + tuple2Iterator.forEachRemaining(tuple -> sketchMap.put(tuple._1, tuple._2)); + return writeToPuffin(table, columnList, sketchMap); + } + + private static StatisticsFile writeToPuffin( + Table table, List<String> columns, Map<String, ThetaSketchJavaSerializable> sketchMap) + throws IOException { + int columnSizes = columns.size(); + TableOperations operations = ((HasTableOperations) table).operations(); + FileIO fileIO = ((HasTableOperations) table).operations().io(); + String path = operations.metadataFileLocation(String.format("%s.stats", UUID.randomUUID())); + OutputFile outputFile = fileIO.newOutputFile(path); + try (PuffinWriter writer = + Puffin.write(outputFile).createdBy("Spark DistinctCountProcedure").build()) { + for (int i = 0; i < columnSizes; i++) { + writer.add( + new Blob( + StandardBlobTypes.APACHE_DATASKETCHES_THETA_V1, + ImmutableList.of(table.schema().findField(columns.get(i)).fieldId()), + table.currentSnapshot().snapshotId(), + table.currentSnapshot().sequenceNumber(), + ByteBuffer.wrap(sketchMap.get(columns.get(i)).getSketch().toByteArray()), + null, + ImmutableMap.of())); + } + writer.finish(); + + return new GenericStatisticsFile( + table.currentSnapshot().snapshotId(), + path, + writer.fileSize(), + writer.footerSize(), + writer.writtenBlobsMetadata().stream() + .map(GenericBlobMetadata::from) + .collect(ImmutableList.toImmutableList())); + + } catch (IOException e) { + throw e; + } + } + + static Iterator<Tuple2<String, ThetaSketchJavaSerializable>> computeNDVSketches( + SparkSession spark, String tableName, long snapshotId, List<String> columns) { + String sql = Review Comment: Let's use the dataframe API instead of SQL? As anyway we use the API further down ########## spark/v3.5/spark/src/main/java/org/apache/iceberg/spark/actions/NDVSketchGenerator.java: ########## @@ -0,0 +1,184 @@ +/* + * 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.io.IOException; +import java.nio.ByteBuffer; +import java.util.Iterator; +import java.util.List; +import java.util.Map; +import java.util.UUID; +import java.util.stream.Collectors; +import org.apache.datasketches.theta.CompactSketch; +import org.apache.datasketches.theta.SetOperationBuilder; +import org.apache.datasketches.theta.UpdateSketch; +import org.apache.iceberg.GenericBlobMetadata; +import org.apache.iceberg.GenericStatisticsFile; +import org.apache.iceberg.HasTableOperations; +import org.apache.iceberg.StatisticsFile; +import org.apache.iceberg.Table; +import org.apache.iceberg.TableOperations; +import org.apache.iceberg.io.FileIO; +import org.apache.iceberg.io.OutputFile; +import org.apache.iceberg.puffin.Blob; +import org.apache.iceberg.puffin.Puffin; +import org.apache.iceberg.puffin.PuffinWriter; +import org.apache.iceberg.puffin.StandardBlobTypes; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableList; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableMap; +import org.apache.iceberg.relocated.com.google.common.collect.Lists; +import org.apache.iceberg.relocated.com.google.common.collect.Maps; +import org.apache.iceberg.types.Types; +import org.apache.spark.api.java.JavaPairRDD; +import org.apache.spark.api.java.function.Function2; +import org.apache.spark.api.java.function.PairFlatMapFunction; +import org.apache.spark.sql.Dataset; +import org.apache.spark.sql.Row; +import org.apache.spark.sql.SparkSession; +import scala.Tuple2; + +public class NDVSketchGenerator { + + private NDVSketchGenerator() {} + + static StatisticsFile generateNDV( + SparkSession spark, Table table, long snapshotId, String... columnsToBeAnalyzed) + throws IOException { + List<String> columnList; + if (columnsToBeAnalyzed == null || columnsToBeAnalyzed.length == 0) { + columnList = + table.schema().columns().stream() + .map(Types.NestedField::name) + .collect(Collectors.toList()); + } else { + columnList = Lists.newArrayList(columnsToBeAnalyzed); + } + Iterator<Tuple2<String, ThetaSketchJavaSerializable>> tuple2Iterator = + computeNDVSketches(spark, table.name(), snapshotId, columnList); + Map<String, ThetaSketchJavaSerializable> sketchMap = Maps.newHashMap(); + + tuple2Iterator.forEachRemaining(tuple -> sketchMap.put(tuple._1, tuple._2)); + return writeToPuffin(table, columnList, sketchMap); + } + + private static StatisticsFile writeToPuffin( + Table table, List<String> columns, Map<String, ThetaSketchJavaSerializable> sketchMap) + throws IOException { + int columnSizes = columns.size(); + TableOperations operations = ((HasTableOperations) table).operations(); + FileIO fileIO = ((HasTableOperations) table).operations().io(); + String path = operations.metadataFileLocation(String.format("%s.stats", UUID.randomUUID())); + OutputFile outputFile = fileIO.newOutputFile(path); + try (PuffinWriter writer = + Puffin.write(outputFile).createdBy("Spark DistinctCountProcedure").build()) { + for (int i = 0; i < columnSizes; i++) { + writer.add( + new Blob( + StandardBlobTypes.APACHE_DATASKETCHES_THETA_V1, + ImmutableList.of(table.schema().findField(columns.get(i)).fieldId()), + table.currentSnapshot().snapshotId(), + table.currentSnapshot().sequenceNumber(), + ByteBuffer.wrap(sketchMap.get(columns.get(i)).getSketch().toByteArray()), + null, + ImmutableMap.of())); + } + writer.finish(); + + return new GenericStatisticsFile( + table.currentSnapshot().snapshotId(), + path, + writer.fileSize(), + writer.footerSize(), + writer.writtenBlobsMetadata().stream() + .map(GenericBlobMetadata::from) + .collect(ImmutableList.toImmutableList())); + + } catch (IOException e) { + throw e; + } + } + + static Iterator<Tuple2<String, ThetaSketchJavaSerializable>> computeNDVSketches( + SparkSession spark, String tableName, long snapshotId, List<String> columns) { + String sql = + String.format( + "select %s from %s VERSION AS OF %d", String.join(",", columns), tableName, snapshotId); + Dataset<Row> data = spark.sql(sql); + final JavaPairRDD<String, String> pairs = + data.javaRDD() + .mapPartitionsToPair( + (PairFlatMapFunction<Iterator<Row>, String, String>) + input -> { + final List<Tuple2<String, String>> list = Lists.newArrayList(); + while (input.hasNext()) { + final Row row = input.next(); + int size = row.size(); + for (int i = 0; i < size; i++) { + list.add(new Tuple2<>(columns.get(i), row.get(i).toString())); + } + } + return list.iterator(); + }); + + final JavaPairRDD<String, ThetaSketchJavaSerializable> sketches = + pairs.aggregateByKey( + new ThetaSketchJavaSerializable(), + 1, // number of partitions Review Comment: Why limit to 1 ? ########## spark/v3.5/spark/src/main/java/org/apache/iceberg/spark/actions/NDVSketchGenerator.java: ########## @@ -0,0 +1,184 @@ +/* + * 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.io.IOException; +import java.nio.ByteBuffer; +import java.util.Iterator; +import java.util.List; +import java.util.Map; +import java.util.UUID; +import java.util.stream.Collectors; +import org.apache.datasketches.theta.CompactSketch; +import org.apache.datasketches.theta.SetOperationBuilder; +import org.apache.datasketches.theta.UpdateSketch; +import org.apache.iceberg.GenericBlobMetadata; +import org.apache.iceberg.GenericStatisticsFile; +import org.apache.iceberg.HasTableOperations; +import org.apache.iceberg.StatisticsFile; +import org.apache.iceberg.Table; +import org.apache.iceberg.TableOperations; +import org.apache.iceberg.io.FileIO; +import org.apache.iceberg.io.OutputFile; +import org.apache.iceberg.puffin.Blob; +import org.apache.iceberg.puffin.Puffin; +import org.apache.iceberg.puffin.PuffinWriter; +import org.apache.iceberg.puffin.StandardBlobTypes; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableList; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableMap; +import org.apache.iceberg.relocated.com.google.common.collect.Lists; +import org.apache.iceberg.relocated.com.google.common.collect.Maps; +import org.apache.iceberg.types.Types; +import org.apache.spark.api.java.JavaPairRDD; +import org.apache.spark.api.java.function.Function2; +import org.apache.spark.api.java.function.PairFlatMapFunction; +import org.apache.spark.sql.Dataset; +import org.apache.spark.sql.Row; +import org.apache.spark.sql.SparkSession; +import scala.Tuple2; + +public class NDVSketchGenerator { + + private NDVSketchGenerator() {} + + static StatisticsFile generateNDV( + SparkSession spark, Table table, long snapshotId, String... columnsToBeAnalyzed) + throws IOException { + List<String> columnList; + if (columnsToBeAnalyzed == null || columnsToBeAnalyzed.length == 0) { + columnList = + table.schema().columns().stream() + .map(Types.NestedField::name) + .collect(Collectors.toList()); + } else { + columnList = Lists.newArrayList(columnsToBeAnalyzed); + } + Iterator<Tuple2<String, ThetaSketchJavaSerializable>> tuple2Iterator = + computeNDVSketches(spark, table.name(), snapshotId, columnList); + Map<String, ThetaSketchJavaSerializable> sketchMap = Maps.newHashMap(); + + tuple2Iterator.forEachRemaining(tuple -> sketchMap.put(tuple._1, tuple._2)); + return writeToPuffin(table, columnList, sketchMap); + } + + private static StatisticsFile writeToPuffin( + Table table, List<String> columns, Map<String, ThetaSketchJavaSerializable> sketchMap) + throws IOException { + int columnSizes = columns.size(); + TableOperations operations = ((HasTableOperations) table).operations(); + FileIO fileIO = ((HasTableOperations) table).operations().io(); + String path = operations.metadataFileLocation(String.format("%s.stats", UUID.randomUUID())); + OutputFile outputFile = fileIO.newOutputFile(path); + try (PuffinWriter writer = + Puffin.write(outputFile).createdBy("Spark DistinctCountProcedure").build()) { + for (int i = 0; i < columnSizes; i++) { + writer.add( + new Blob( + StandardBlobTypes.APACHE_DATASKETCHES_THETA_V1, + ImmutableList.of(table.schema().findField(columns.get(i)).fieldId()), + table.currentSnapshot().snapshotId(), + table.currentSnapshot().sequenceNumber(), + ByteBuffer.wrap(sketchMap.get(columns.get(i)).getSketch().toByteArray()), + null, + ImmutableMap.of())); + } + writer.finish(); + + return new GenericStatisticsFile( + table.currentSnapshot().snapshotId(), + path, + writer.fileSize(), + writer.footerSize(), + writer.writtenBlobsMetadata().stream() + .map(GenericBlobMetadata::from) + .collect(ImmutableList.toImmutableList())); + + } catch (IOException e) { + throw e; + } + } + + static Iterator<Tuple2<String, ThetaSketchJavaSerializable>> computeNDVSketches( + SparkSession spark, String tableName, long snapshotId, List<String> columns) { + String sql = + String.format( + "select %s from %s VERSION AS OF %d", String.join(",", columns), tableName, snapshotId); + Dataset<Row> data = spark.sql(sql); + final JavaPairRDD<String, String> pairs = + data.javaRDD() + .mapPartitionsToPair( + (PairFlatMapFunction<Iterator<Row>, String, String>) + input -> { + final List<Tuple2<String, String>> list = Lists.newArrayList(); + while (input.hasNext()) { + final Row row = input.next(); + int size = row.size(); + for (int i = 0; i < size; i++) { + list.add(new Tuple2<>(columns.get(i), row.get(i).toString())); + } + } + return list.iterator(); + }); + + final JavaPairRDD<String, ThetaSketchJavaSerializable> sketches = Review Comment: same comment with this final here. ########## spark/v3.5/spark/src/main/java/org/apache/iceberg/spark/actions/NDVSketchGenerator.java: ########## @@ -0,0 +1,184 @@ +/* + * 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.io.IOException; +import java.nio.ByteBuffer; +import java.util.Iterator; +import java.util.List; +import java.util.Map; +import java.util.UUID; +import java.util.stream.Collectors; +import org.apache.datasketches.theta.CompactSketch; +import org.apache.datasketches.theta.SetOperationBuilder; +import org.apache.datasketches.theta.UpdateSketch; +import org.apache.iceberg.GenericBlobMetadata; +import org.apache.iceberg.GenericStatisticsFile; +import org.apache.iceberg.HasTableOperations; +import org.apache.iceberg.StatisticsFile; +import org.apache.iceberg.Table; +import org.apache.iceberg.TableOperations; +import org.apache.iceberg.io.FileIO; +import org.apache.iceberg.io.OutputFile; +import org.apache.iceberg.puffin.Blob; +import org.apache.iceberg.puffin.Puffin; +import org.apache.iceberg.puffin.PuffinWriter; +import org.apache.iceberg.puffin.StandardBlobTypes; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableList; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableMap; +import org.apache.iceberg.relocated.com.google.common.collect.Lists; +import org.apache.iceberg.relocated.com.google.common.collect.Maps; +import org.apache.iceberg.types.Types; +import org.apache.spark.api.java.JavaPairRDD; +import org.apache.spark.api.java.function.Function2; +import org.apache.spark.api.java.function.PairFlatMapFunction; +import org.apache.spark.sql.Dataset; +import org.apache.spark.sql.Row; +import org.apache.spark.sql.SparkSession; +import scala.Tuple2; + +public class NDVSketchGenerator { + + private NDVSketchGenerator() {} + + static StatisticsFile generateNDV( + SparkSession spark, Table table, long snapshotId, String... columnsToBeAnalyzed) + throws IOException { + List<String> columnList; + if (columnsToBeAnalyzed == null || columnsToBeAnalyzed.length == 0) { + columnList = + table.schema().columns().stream() + .map(Types.NestedField::name) + .collect(Collectors.toList()); + } else { + columnList = Lists.newArrayList(columnsToBeAnalyzed); + } + Iterator<Tuple2<String, ThetaSketchJavaSerializable>> tuple2Iterator = + computeNDVSketches(spark, table.name(), snapshotId, columnList); + Map<String, ThetaSketchJavaSerializable> sketchMap = Maps.newHashMap(); + + tuple2Iterator.forEachRemaining(tuple -> sketchMap.put(tuple._1, tuple._2)); + return writeToPuffin(table, columnList, sketchMap); + } + + private static StatisticsFile writeToPuffin( + Table table, List<String> columns, Map<String, ThetaSketchJavaSerializable> sketchMap) + throws IOException { + int columnSizes = columns.size(); + TableOperations operations = ((HasTableOperations) table).operations(); + FileIO fileIO = ((HasTableOperations) table).operations().io(); + String path = operations.metadataFileLocation(String.format("%s.stats", UUID.randomUUID())); + OutputFile outputFile = fileIO.newOutputFile(path); + try (PuffinWriter writer = + Puffin.write(outputFile).createdBy("Spark DistinctCountProcedure").build()) { + for (int i = 0; i < columnSizes; i++) { + writer.add( + new Blob( + StandardBlobTypes.APACHE_DATASKETCHES_THETA_V1, + ImmutableList.of(table.schema().findField(columns.get(i)).fieldId()), + table.currentSnapshot().snapshotId(), + table.currentSnapshot().sequenceNumber(), + ByteBuffer.wrap(sketchMap.get(columns.get(i)).getSketch().toByteArray()), + null, + ImmutableMap.of())); + } + writer.finish(); + + return new GenericStatisticsFile( + table.currentSnapshot().snapshotId(), + path, + writer.fileSize(), + writer.footerSize(), + writer.writtenBlobsMetadata().stream() + .map(GenericBlobMetadata::from) + .collect(ImmutableList.toImmutableList())); + + } catch (IOException e) { + throw e; + } + } + + static Iterator<Tuple2<String, ThetaSketchJavaSerializable>> computeNDVSketches( + SparkSession spark, String tableName, long snapshotId, List<String> columns) { + String sql = + String.format( + "select %s from %s VERSION AS OF %d", String.join(",", columns), tableName, snapshotId); + Dataset<Row> data = spark.sql(sql); + final JavaPairRDD<String, String> pairs = + data.javaRDD() + .mapPartitionsToPair( + (PairFlatMapFunction<Iterator<Row>, String, String>) + input -> { + final List<Tuple2<String, String>> list = Lists.newArrayList(); + while (input.hasNext()) { Review Comment: Can we use flatmap and mapToPair to make this more concise? ``` data.javaRDD().flatMap(r -> { List<Tuple2<String, String>> list = Lists.newArrayListWithExpectedSize(columns.size()); for (int i = 0; i < r.size(); i++) { list.add(new Tuple2<>(columns.get(i), r.get(i).toString()); } return list.iterator(); }).mapToPair(t -> t); ``` ########## spark/v3.5/spark/src/main/java/org/apache/iceberg/spark/actions/NDVSketchGenerator.java: ########## @@ -0,0 +1,184 @@ +/* + * 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.io.IOException; +import java.nio.ByteBuffer; +import java.util.Iterator; +import java.util.List; +import java.util.Map; +import java.util.UUID; +import java.util.stream.Collectors; +import org.apache.datasketches.theta.CompactSketch; +import org.apache.datasketches.theta.SetOperationBuilder; +import org.apache.datasketches.theta.UpdateSketch; +import org.apache.iceberg.GenericBlobMetadata; +import org.apache.iceberg.GenericStatisticsFile; +import org.apache.iceberg.HasTableOperations; +import org.apache.iceberg.StatisticsFile; +import org.apache.iceberg.Table; +import org.apache.iceberg.TableOperations; +import org.apache.iceberg.io.FileIO; +import org.apache.iceberg.io.OutputFile; +import org.apache.iceberg.puffin.Blob; +import org.apache.iceberg.puffin.Puffin; +import org.apache.iceberg.puffin.PuffinWriter; +import org.apache.iceberg.puffin.StandardBlobTypes; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableList; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableMap; +import org.apache.iceberg.relocated.com.google.common.collect.Lists; +import org.apache.iceberg.relocated.com.google.common.collect.Maps; +import org.apache.iceberg.types.Types; +import org.apache.spark.api.java.JavaPairRDD; +import org.apache.spark.api.java.function.Function2; +import org.apache.spark.api.java.function.PairFlatMapFunction; +import org.apache.spark.sql.Dataset; +import org.apache.spark.sql.Row; +import org.apache.spark.sql.SparkSession; +import scala.Tuple2; + +public class NDVSketchGenerator { + + private NDVSketchGenerator() {} + + static StatisticsFile generateNDV( + SparkSession spark, Table table, long snapshotId, String... columnsToBeAnalyzed) + throws IOException { + List<String> columnList; + if (columnsToBeAnalyzed == null || columnsToBeAnalyzed.length == 0) { + columnList = + table.schema().columns().stream() + .map(Types.NestedField::name) + .collect(Collectors.toList()); + } else { + columnList = Lists.newArrayList(columnsToBeAnalyzed); + } + Iterator<Tuple2<String, ThetaSketchJavaSerializable>> tuple2Iterator = + computeNDVSketches(spark, table.name(), snapshotId, columnList); + Map<String, ThetaSketchJavaSerializable> sketchMap = Maps.newHashMap(); + + tuple2Iterator.forEachRemaining(tuple -> sketchMap.put(tuple._1, tuple._2)); + return writeToPuffin(table, columnList, sketchMap); + } + + private static StatisticsFile writeToPuffin( + Table table, List<String> columns, Map<String, ThetaSketchJavaSerializable> sketchMap) + throws IOException { + int columnSizes = columns.size(); + TableOperations operations = ((HasTableOperations) table).operations(); + FileIO fileIO = ((HasTableOperations) table).operations().io(); + String path = operations.metadataFileLocation(String.format("%s.stats", UUID.randomUUID())); + OutputFile outputFile = fileIO.newOutputFile(path); + try (PuffinWriter writer = + Puffin.write(outputFile).createdBy("Spark DistinctCountProcedure").build()) { + for (int i = 0; i < columnSizes; i++) { + writer.add( + new Blob( + StandardBlobTypes.APACHE_DATASKETCHES_THETA_V1, + ImmutableList.of(table.schema().findField(columns.get(i)).fieldId()), + table.currentSnapshot().snapshotId(), + table.currentSnapshot().sequenceNumber(), + ByteBuffer.wrap(sketchMap.get(columns.get(i)).getSketch().toByteArray()), + null, + ImmutableMap.of())); + } + writer.finish(); + + return new GenericStatisticsFile( + table.currentSnapshot().snapshotId(), + path, + writer.fileSize(), + writer.footerSize(), + writer.writtenBlobsMetadata().stream() + .map(GenericBlobMetadata::from) + .collect(ImmutableList.toImmutableList())); + + } catch (IOException e) { + throw e; + } + } + + static Iterator<Tuple2<String, ThetaSketchJavaSerializable>> computeNDVSketches( + SparkSession spark, String tableName, long snapshotId, List<String> columns) { + String sql = + String.format( + "select %s from %s VERSION AS OF %d", String.join(",", columns), tableName, snapshotId); + Dataset<Row> data = spark.sql(sql); + final JavaPairRDD<String, String> pairs = + data.javaRDD() + .mapPartitionsToPair( + (PairFlatMapFunction<Iterator<Row>, String, String>) + input -> { + final List<Tuple2<String, String>> list = Lists.newArrayList(); + while (input.hasNext()) { + final Row row = input.next(); + int size = row.size(); + for (int i = 0; i < size; i++) { + list.add(new Tuple2<>(columns.get(i), row.get(i).toString())); Review Comment: Question, does return from string affect anything? I see the sketch library takes in other types. ########## spark/v3.5/spark/src/main/java/org/apache/iceberg/spark/actions/NDVSketchGenerator.java: ########## @@ -0,0 +1,184 @@ +/* + * 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.io.IOException; +import java.nio.ByteBuffer; +import java.util.Iterator; +import java.util.List; +import java.util.Map; +import java.util.UUID; +import java.util.stream.Collectors; +import org.apache.datasketches.theta.CompactSketch; +import org.apache.datasketches.theta.SetOperationBuilder; +import org.apache.datasketches.theta.UpdateSketch; +import org.apache.iceberg.GenericBlobMetadata; +import org.apache.iceberg.GenericStatisticsFile; +import org.apache.iceberg.HasTableOperations; +import org.apache.iceberg.StatisticsFile; +import org.apache.iceberg.Table; +import org.apache.iceberg.TableOperations; +import org.apache.iceberg.io.FileIO; +import org.apache.iceberg.io.OutputFile; +import org.apache.iceberg.puffin.Blob; +import org.apache.iceberg.puffin.Puffin; +import org.apache.iceberg.puffin.PuffinWriter; +import org.apache.iceberg.puffin.StandardBlobTypes; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableList; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableMap; +import org.apache.iceberg.relocated.com.google.common.collect.Lists; +import org.apache.iceberg.relocated.com.google.common.collect.Maps; +import org.apache.iceberg.types.Types; +import org.apache.spark.api.java.JavaPairRDD; +import org.apache.spark.api.java.function.Function2; +import org.apache.spark.api.java.function.PairFlatMapFunction; +import org.apache.spark.sql.Dataset; +import org.apache.spark.sql.Row; +import org.apache.spark.sql.SparkSession; +import scala.Tuple2; + +public class NDVSketchGenerator { + + private NDVSketchGenerator() {} + + static StatisticsFile generateNDV( + SparkSession spark, Table table, long snapshotId, String... columnsToBeAnalyzed) + throws IOException { + List<String> columnList; + if (columnsToBeAnalyzed == null || columnsToBeAnalyzed.length == 0) { + columnList = + table.schema().columns().stream() + .map(Types.NestedField::name) + .collect(Collectors.toList()); + } else { + columnList = Lists.newArrayList(columnsToBeAnalyzed); + } + Iterator<Tuple2<String, ThetaSketchJavaSerializable>> tuple2Iterator = + computeNDVSketches(spark, table.name(), snapshotId, columnList); + Map<String, ThetaSketchJavaSerializable> sketchMap = Maps.newHashMap(); + + tuple2Iterator.forEachRemaining(tuple -> sketchMap.put(tuple._1, tuple._2)); + return writeToPuffin(table, columnList, sketchMap); + } + + private static StatisticsFile writeToPuffin( + Table table, List<String> columns, Map<String, ThetaSketchJavaSerializable> sketchMap) + throws IOException { + int columnSizes = columns.size(); + TableOperations operations = ((HasTableOperations) table).operations(); + FileIO fileIO = ((HasTableOperations) table).operations().io(); + String path = operations.metadataFileLocation(String.format("%s.stats", UUID.randomUUID())); + OutputFile outputFile = fileIO.newOutputFile(path); + try (PuffinWriter writer = + Puffin.write(outputFile).createdBy("Spark DistinctCountProcedure").build()) { + for (int i = 0; i < columnSizes; i++) { + writer.add( + new Blob( + StandardBlobTypes.APACHE_DATASKETCHES_THETA_V1, + ImmutableList.of(table.schema().findField(columns.get(i)).fieldId()), + table.currentSnapshot().snapshotId(), + table.currentSnapshot().sequenceNumber(), + ByteBuffer.wrap(sketchMap.get(columns.get(i)).getSketch().toByteArray()), + null, + ImmutableMap.of())); + } + writer.finish(); + + return new GenericStatisticsFile( + table.currentSnapshot().snapshotId(), + path, + writer.fileSize(), + writer.footerSize(), + writer.writtenBlobsMetadata().stream() + .map(GenericBlobMetadata::from) + .collect(ImmutableList.toImmutableList())); + + } catch (IOException e) { + throw e; + } + } + + static Iterator<Tuple2<String, ThetaSketchJavaSerializable>> computeNDVSketches( + SparkSession spark, String tableName, long snapshotId, List<String> columns) { + String sql = + String.format( + "select %s from %s VERSION AS OF %d", String.join(",", columns), tableName, snapshotId); + Dataset<Row> data = spark.sql(sql); + final JavaPairRDD<String, String> pairs = + data.javaRDD() + .mapPartitionsToPair( + (PairFlatMapFunction<Iterator<Row>, String, String>) + input -> { + final List<Tuple2<String, String>> list = Lists.newArrayList(); + while (input.hasNext()) { + final Row row = input.next(); + int size = row.size(); + for (int i = 0; i < size; i++) { + list.add(new Tuple2<>(columns.get(i), row.get(i).toString())); + } + } + return list.iterator(); + }); + + final JavaPairRDD<String, ThetaSketchJavaSerializable> sketches = + pairs.aggregateByKey( + new ThetaSketchJavaSerializable(), + 1, // number of partitions + new Add(), + new Combine()); + + return sketches.toLocalIterator(); + } + + static class Add Review Comment: can we use lambdas here for cleaner code? like ``` (sketch, val) -> { sketch.update(val;); return sketch; }, ``` The next one may be too complex to inline but maybe we can reduce the ugly java boilerplate ########## spark/v3.5/spark/src/main/java/org/apache/iceberg/spark/actions/NDVSketchGenerator.java: ########## @@ -0,0 +1,172 @@ +/* + * 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.io.IOException; +import java.nio.ByteBuffer; +import java.util.Iterator; +import java.util.List; +import java.util.Map; +import java.util.UUID; +import org.apache.datasketches.theta.CompactSketch; +import org.apache.datasketches.theta.SetOperationBuilder; +import org.apache.datasketches.theta.UpdateSketch; +import org.apache.iceberg.GenericBlobMetadata; +import org.apache.iceberg.GenericStatisticsFile; +import org.apache.iceberg.HasTableOperations; +import org.apache.iceberg.StatisticsFile; +import org.apache.iceberg.Table; +import org.apache.iceberg.TableOperations; +import org.apache.iceberg.io.FileIO; +import org.apache.iceberg.io.OutputFile; +import org.apache.iceberg.puffin.Blob; +import org.apache.iceberg.puffin.Puffin; +import org.apache.iceberg.puffin.PuffinWriter; +import org.apache.iceberg.puffin.StandardBlobTypes; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableList; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableMap; +import org.apache.iceberg.relocated.com.google.common.collect.Lists; +import org.apache.iceberg.relocated.com.google.common.collect.Maps; +import org.apache.spark.api.java.JavaPairRDD; +import org.apache.spark.api.java.function.Function2; +import org.apache.spark.api.java.function.PairFlatMapFunction; +import org.apache.spark.sql.Dataset; +import org.apache.spark.sql.Row; +import org.apache.spark.sql.SparkSession; +import scala.Tuple2; + +public class NDVSketchGenerator { + + private NDVSketchGenerator() {} + + public static StatisticsFile generateNDV( + SparkSession spark, Table table, long snapshotId, String... columnsToBeAnalyzed) + throws IOException { + Iterator<Tuple2<String, ThetaSketchJavaSerializable>> tuple2Iterator = + NDVSketchGenerator.computeNDVSketches(spark, table.name(), snapshotId, columnsToBeAnalyzed); + Map<String, ThetaSketchJavaSerializable> sketchMap = Maps.newHashMap(); + + tuple2Iterator.forEachRemaining(tuple -> sketchMap.put(tuple._1, tuple._2)); + return writeToPuffin(table, Lists.newArrayList(columnsToBeAnalyzed), sketchMap); + } + + private static StatisticsFile writeToPuffin( + Table table, List<String> columns, Map<String, ThetaSketchJavaSerializable> sketchMap) + throws IOException { + int columnSizes = columns.size(); + TableOperations operations = ((HasTableOperations) table).operations(); + FileIO fileIO = ((HasTableOperations) table).operations().io(); + String path = operations.metadataFileLocation(String.format("%s.stats", UUID.randomUUID())); + OutputFile outputFile = fileIO.newOutputFile(path); + try (PuffinWriter writer = + Puffin.write(outputFile).createdBy("Spark DistinctCountProcedure").build()) { + for (int i = 0; i < columnSizes; i++) { + writer.add( + new Blob( + StandardBlobTypes.APACHE_DATASKETCHES_THETA_V1, + ImmutableList.of(table.schema().findField(columns.get(i)).fieldId()), + table.currentSnapshot().snapshotId(), + table.currentSnapshot().sequenceNumber(), + ByteBuffer.wrap(sketchMap.get(columns.get(i)).getSketch().toByteArray()), + null, + ImmutableMap.of())); + } + writer.finish(); + + return new GenericStatisticsFile( + table.currentSnapshot().snapshotId(), + path, + writer.fileSize(), + writer.footerSize(), + writer.writtenBlobsMetadata().stream() + .map(GenericBlobMetadata::from) + .collect(ImmutableList.toImmutableList())); + + } catch (IOException e) { + throw e; + } Review Comment: +1 to remove this -- 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: issues-unsubscr...@iceberg.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org For additional commands, e-mail: issues-h...@iceberg.apache.org
