szehon-ho commented on code in PR #10288: URL: https://github.com/apache/iceberg/pull/10288#discussion_r1637308620
########## 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: Hm, I was initially thinking it will be cleaner to make it static default the constructor itself like: ``` AnalyzeTableSparkAction(SparkSession spark, Table table) { super(spark); this.table = table; this.snapshotId = table.currentSnapshot().snapshotId(); } ``` Are you thinking to make it dynamic where the user calls table.refresh() between creating the action and execute? But I see a problem, if you call execute again, it wont update as snapshotId is set already. I think what bothers me is that it non-determisticallly sets the state by calling execute(), and also in generateNDVAndCommit(). How about making the snapshot a Long and keeping it null. Then just have a method private long snapshotId() { return snapshotId != null ? snapshotId : table.currentSnapshot().snapshotId(); } that we use everywhere. This is inspired from DataTableScan::snapshot() -- 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
