karuppayya commented on code in PR #10288: URL: https://github.com/apache/iceberg/pull/10288#discussion_r1606968313
########## spark/v3.5/spark/src/main/java/org/apache/iceberg/spark/actions/NDVSketchGenerator.java: ########## @@ -0,0 +1,169 @@ +/* + * 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, String... columnsToBeAnalyzed) throws IOException { + Iterator<Tuple2<String, ThetaSketchJavaSerializable>> tuple2Iterator = + NDVSketchGenerator.computeNDVSketches(spark, table.name(), 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, String... columns) { + String sql = String.format("select %s from %s", String.join(",", columns), tableName); Review Comment: Yes, incremental need to be wired into the ends of write paths. This procedure could exist in parallel, which could get stats of the whole table on demand. -- 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
