amogh-jahagirdar commented on code in PR #10288: URL: https://github.com/apache/iceberg/pull/10288#discussion_r1619229462
########## 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 these stats be a `Set<StandardBlobType>` instead of arbitrary Strings? I feel like the API becomes more well defined in this case. ########## spark/v3.5/spark/src/main/java/org/apache/iceberg/spark/actions/AnalyzeTableSparkAction.java: ########## @@ -0,0 +1,149 @@ +/* + * 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.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; + private Set<String> statsToBecollected = + Sets.newHashSet(StandardBlobTypes.APACHE_DATASKETCHES_THETA_V1); + + 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()); + validateColumns(); + 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 void validateColumns() { + validateEmptyColumns(); + validateTypes(); + } + + private void validateEmptyColumns() { + if (columnsToBeAnalyzed == null || columnsToBeAnalyzed.isEmpty()) { + throw new ValidationException("No columns to analyze for the table", table.name()); + } + } Review Comment: Nit: I think this validation should just happen at the time of setting these on the action rather than at the execcution time. ########## spark/v3.5/spark/src/main/java/org/apache/iceberg/spark/actions/AnalyzeTableSparkAction.java: ########## @@ -0,0 +1,149 @@ +/* + * 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.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; + private Set<String> statsToBecollected = + Sets.newHashSet(StandardBlobTypes.APACHE_DATASKETCHES_THETA_V1); + + 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()); + validateColumns(); + 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 void validateColumns() { + validateEmptyColumns(); + validateTypes(); + } + + private void validateEmptyColumns() { + if (columnsToBeAnalyzed == null || columnsToBeAnalyzed.isEmpty()) { + throw new ValidationException("No columns to analyze for the table", table.name()); + } + } + + private void validateTypes() { + columnsToBeAnalyzed.forEach( + columnName -> { + Types.NestedField field = table.schema().findField(columnName); + if (field == null) { + throw new ValidationException("No column with %s name in the table", columnName); + } Review Comment: Style nit: new line after the if ########## 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: I also think this interface should have a `snapshot` API to allow users to pass in a snapshot to generate the statistics for. If it's not specified then we can generate the statistics for the latest snapshot. ########## spark/v3.5/spark/src/main/java/org/apache/iceberg/spark/actions/ThetaSketchJavaSerializable.java: ########## @@ -0,0 +1,92 @@ +/* + * 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.io.ObjectInputStream; +import java.io.ObjectOutputStream; +import java.io.Serializable; +import org.apache.datasketches.memory.Memory; +import org.apache.datasketches.theta.CompactSketch; +import org.apache.datasketches.theta.Sketch; +import org.apache.datasketches.theta.Sketches; +import org.apache.datasketches.theta.UpdateSketch; + +public class ThetaSketchJavaSerializable implements Serializable { Review Comment: Does this need to be public? ########## 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, Review Comment: null means that the file will be uncompressed. I think it makes sense not to compress these files by default since the sketch will be a single long per column, so it'll be quite small already and not worth paying the price of compression/decompression. ########## spark/v3.5/spark/src/main/java/org/apache/iceberg/spark/actions/ThetaSketchJavaSerializable.java: ########## @@ -0,0 +1,92 @@ +/* + * 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.io.ObjectInputStream; +import java.io.ObjectOutputStream; +import java.io.Serializable; +import org.apache.datasketches.memory.Memory; +import org.apache.datasketches.theta.CompactSketch; +import org.apache.datasketches.theta.Sketch; +import org.apache.datasketches.theta.Sketches; +import org.apache.datasketches.theta.UpdateSketch; + +public class ThetaSketchJavaSerializable implements Serializable { + + private Sketch sketch; + + public ThetaSketchJavaSerializable() {} + + public ThetaSketchJavaSerializable(final Sketch sketch) { + this.sketch = sketch; + } + + public Sketch getSketch() { + return sketch; + } + + public CompactSketch getCompactSketch() { + if (sketch == null) { + return null; + } + if (sketch instanceof UpdateSketch) { + return sketch.compact(); + } Review Comment: Style nit: new line after if ########## 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(); Review Comment: Nit: Don't think you need the `writer.finish()` because the try with resources will close, and close will already finish ########## 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); Review Comment: Does computeDVSketches need to be public? Seems like it can just be package private. Also nit, either way don't think you need the full qualified method name ########## 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: Is this catch/throw actually needed? ########## 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: Oh I see, StandardBlobType defines string constants not enums ########## 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; + } + } + + public static Iterator<Tuple2<String, ThetaSketchJavaSerializable>> computeNDVSketches( + SparkSession spark, String tableName, long snapshotId, 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[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 + implements Function2<ThetaSketchJavaSerializable, String, ThetaSketchJavaSerializable> { + @Override + public ThetaSketchJavaSerializable call( + final ThetaSketchJavaSerializable sketch, final String value) throws Exception { + sketch.update(value); + return sketch; + } + } + + static class Combine + implements Function2< + ThetaSketchJavaSerializable, ThetaSketchJavaSerializable, ThetaSketchJavaSerializable> { + static final ThetaSketchJavaSerializable emptySketchWrapped = + new ThetaSketchJavaSerializable(UpdateSketch.builder().build().compact()); + + public ThetaSketchJavaSerializable call( + final ThetaSketchJavaSerializable sketch1, final ThetaSketchJavaSerializable sketch2) + throws Exception { + if (sketch1.getSketch() == null && sketch2.getSketch() == null) { + return emptySketchWrapped; + } + if (sketch1.getSketch() == null) { + return sketch2; + } + if (sketch2.getSketch() == null) { + return sketch1; + } Review Comment: Style nit: new line after if -- 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