MaxGekk commented on a change in pull request #27366: [SPARK-30648][SQL] Support filters pushdown in JSON datasource URL: https://github.com/apache/spark/pull/27366#discussion_r373797075
########## File path: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/StructFilters.scala ########## @@ -0,0 +1,161 @@ +/* + * 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.catalyst + +import scala.util.Try + +import org.apache.spark.sql.catalyst.expressions._ +import org.apache.spark.sql.sources +import org.apache.spark.sql.types.{BooleanType, StructType} + +/** + * The class provides API for applying pushed down filters to partially or + * fully set internal rows that have the struct schema. + * + * @param filters The pushed down source filters. The filters should refer to + * the fields of the provided schema. + * @param schema The required schema of records from datasource files. + */ +abstract class StructFilters(filters: Seq[sources.Filter], schema: StructType) { + + assert(filters.forall(StructFilters.checkFilterRefs(_, schema)), + "A pushed down filter refers to a non-existing schema field.") + + /** + * Applies pushed down source filters to the given row assuming that + * value at `index` has been already set. + * + * @param row The row with fully or partially set values. + * @param index The index of already set value. + * @return true if currently processed row can be skipped otherwise false. + */ + def skipRow(row: InternalRow, index: Int): Boolean + + /** + * Resets states of pushed down filters. The method must be called before + * precessing any new row otherwise skipRow() may return wrong result. + */ + def reset(): Unit + + /** + * Compiles source filters to a predicate. + */ + def toPredicate(filters: Seq[sources.Filter]): BasePredicate = { + val reducedExpr = filters + .sortBy(_.references.size) + .flatMap(StructFilters.filterToExpression(_, toRef)) + .reduce(And) + Predicate.create(reducedExpr) + } + + // Finds a filter attribute in the schema and converts it to a `BoundReference` + def toRef(attr: String): Option[BoundReference] = { + schema.getFieldIndex(attr).map { index => + val field = schema(index) + BoundReference(schema.fieldIndex(attr), field.dataType, field.nullable) + } + } +} + +object StructFilters { + private def checkFilterRefs(filter: sources.Filter, schema: StructType): Boolean = { + val fieldNames = schema.fields.map(_.name).toSet + filter.references.forall(fieldNames.contains(_)) Review comment: I have checked CSV datasource as well. Filters are pushed with correct case. So, if specified schema is `aaa integer, BBB integer` and `.filter($"AAA" === 2)`, pushed filter is `EqualTo("aaa", 2)` when `spark.sql.caseSensitive` is `false`. No need to worry about case sensitivity while binding filter references here. ---------------------------------------------------------------- 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. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
