huaxingao commented on code in PR #6582: URL: https://github.com/apache/iceberg/pull/6582#discussion_r1070182092
########## spark/v3.3/spark/src/main/java/org/apache/iceberg/spark/procedures/DistinctCountProcedure.java: ########## @@ -0,0 +1,188 @@ +/* + * 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.procedures; + +import java.io.IOException; +import java.io.UncheckedIOException; +import java.nio.ByteBuffer; +import java.util.UUID; +import org.apache.iceberg.GenericBlobMetadata; +import org.apache.iceberg.GenericStatisticsFile; +import org.apache.iceberg.HasTableOperations; +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.spark.source.SparkTable; +import org.apache.spark.sql.Dataset; +import org.apache.spark.sql.Row; +import org.apache.spark.sql.catalyst.InternalRow; +import org.apache.spark.sql.catalyst.util.ArrayData; +import org.apache.spark.sql.connector.catalog.Identifier; +import org.apache.spark.sql.connector.catalog.TableCatalog; +import org.apache.spark.sql.connector.iceberg.catalog.ProcedureParameter; +import org.apache.spark.sql.types.DataTypes; +import org.apache.spark.sql.types.Metadata; +import org.apache.spark.sql.types.StructField; +import org.apache.spark.sql.types.StructType; +import org.apache.spark.unsafe.types.UTF8String; +import org.jetbrains.annotations.NotNull; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +/** + * A procedure that gets approximate NDV (number of distinct value) for the requested columns and + * sets this to the table's StatisticsFile. + */ +public class DistinctCountProcedure extends BaseProcedure { + private static final Logger LOG = LoggerFactory.getLogger(DistinctCountProcedure.class); + + private static final ProcedureParameter[] PARAMETERS = + new ProcedureParameter[] { + ProcedureParameter.required("table", DataTypes.StringType), + ProcedureParameter.optional("distinct_count_view", DataTypes.StringType), + ProcedureParameter.optional("columns", STRING_ARRAY), + }; + + private static final StructType OUTPUT_TYPE = + new StructType( + new StructField[] { + new StructField("view_name", DataTypes.StringType, false, Metadata.empty()) + }); + + public static SparkProcedures.ProcedureBuilder builder() { + return new Builder<DistinctCountProcedure>() { + @Override + protected DistinctCountProcedure doBuild() { + return new DistinctCountProcedure(tableCatalog()); + } + }; + } + + private DistinctCountProcedure(TableCatalog tableCatalog) { + super(tableCatalog); + } + + @Override + public ProcedureParameter[] parameters() { + return PARAMETERS; + } + + @Override + public StructType outputType() { + return OUTPUT_TYPE; + } + + @Override + public InternalRow[] call(InternalRow args) { + String tableName = args.getString(0); + Identifier tableIdent = toIdentifier(tableName, PARAMETERS[0].name()); + SparkTable sparkTable = loadSparkTable(tableIdent); + StructType schema = sparkTable.schema(); + Table table = sparkTable.table(); + ArrayData columns = args.getArray(2); + int columnSizes = columns.numElements(); + + long[] ndvs = new long[columnSizes]; + int[] fieldId = new int[columnSizes]; + String query = "SELECT "; + for (int i = 0; i < columnSizes; i++) { + String colName = columns.getUTF8String(i).toString(); + query += "APPROX_COUNT_DISTINCT(" + colName + "), "; + fieldId[i] = schema.fieldIndex(colName); + } + + query = query.substring(0, query.length() - 2) + " FROM " + tableName; + Dataset<Row> df = spark().sql(query); + + for (int i = 0; i < columnSizes; i++) { + ndvs[i] = df.head().getLong(i); + } + + 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.NDV_BLOB, + ImmutableList.of(fieldId[i]), + table.currentSnapshot().snapshotId(), + table.currentSnapshot().sequenceNumber(), + ByteBuffer.allocate(0), + null, + ImmutableMap.of("ndv", Long.toString(ndvs[i])))); + } + writer.finish(); + + GenericStatisticsFile statisticsFile = + new GenericStatisticsFile( + table.currentSnapshot().snapshotId(), + path, + writer.fileSize(), + writer.footerSize(), + writer.writtenBlobsMetadata().stream() + .map(GenericBlobMetadata::from) + .collect(ImmutableList.toImmutableList())); + + table + .updateStatistics() + .setStatistics(table.currentSnapshot().snapshotId(), statisticsFile) + .commit(); + } catch (IOException exception) { + throw new UncheckedIOException(exception); + } + + String viewName = viewName(args, tableName); + // Create a view for users to query + df.createOrReplaceTempView(viewName); Review Comment: I kept this as a view so users will have an easy way to query the statistics information after calling the stored procedure. The main reason I am adding this store procedure is because I can't get an agreement to implement `ANALYZE TABLE` for data source V2 in Spark. This stored procedure is doing something similar to `ANALYZE TABLE`. Normally after users analyze table, they will `DESCRIBE` to get the statistics information. I create a view so users can query the statistics. -- 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
