Github user cloud-fan commented on a diff in the pull request: https://github.com/apache/spark/pull/20647#discussion_r171332408 --- Diff: sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/DataSourceV2StringFormat.scala --- @@ -0,0 +1,94 @@ +/* + * 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.spark.sql.execution.datasources.v2 + +import org.apache.commons.lang3.StringUtils + +import org.apache.spark.sql.catalyst.expressions.Attribute +import org.apache.spark.sql.internal.SQLConf +import org.apache.spark.sql.sources.DataSourceRegister +import org.apache.spark.sql.sources.v2.DataSourceV2 +import org.apache.spark.sql.sources.v2.reader._ +import org.apache.spark.util.Utils + +/** + * A trait that can be used by data source v2 related query plans(both logical and physical), to + * provide a string format of the data source information for explain. + */ +trait DataSourceV2StringFormat { + + /** + * The instance of this data source implementation. Note that we only consider its class in + * equals/hashCode, not the instance itself. + */ + def source: DataSourceV2 + + /** + * The output of the data source reader, w.r.t. column pruning. + */ + def output: Seq[Attribute] + + /** + * The options for this data source reader. + */ + def options: Map[String, String] + + /** + * The created data source reader. Here we use it to get the filters that has been pushed down + * so far, itself doesn't take part in the equals/hashCode. + */ + def reader: DataSourceReader + + private lazy val filters = reader match { + case s: SupportsPushDownCatalystFilters => s.pushedCatalystFilters().toSet + case s: SupportsPushDownFilters => s.pushedFilters().toSet + case _ => Set.empty + } + + private def sourceName: String = source match { + case registered: DataSourceRegister => registered.shortName() + case _ => source.getClass.getSimpleName.stripSuffix("$") + } + + def metadataString: String = { + val entries = scala.collection.mutable.ArrayBuffer.empty[(String, String)] + + if (filters.nonEmpty) { + entries += "Pushed Filters" -> filters.mkString("[", ", ", "]") + } + + // TODO: we should only display some standard options like path, table, etc. + entries ++= options + + val outputStr = Utils.truncatedString(output, "[", ", ", "]") + + val entriesStr = if (entries.nonEmpty) { + Utils.truncatedString(entries.map { + case (key, value) => StringUtils.abbreviate(redact(key + ":" + value), 100) --- End diff -- If you look at the `SQLConf.stringRedationPattern`, the default pattern is empty. So it needs customization anyway, and this implementation is easier to customize. If we redact the entire map, I'm not sure how to write a regex to precisely match the password part.
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org