You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hudi.apache.org by GitBox <gi...@apache.org> on 2022/03/18 19:13:57 UTC
[GitHub] [hudi] alexeykudinkin commented on a change in pull request #4996: [HUDI-3594] Supporting Composite Expressions over Data Table Columns in Data Skipping flow
alexeykudinkin commented on a change in pull request #4996:
URL: https://github.com/apache/hudi/pull/4996#discussion_r827336158
##########
File path: hudi-client/hudi-spark-client/src/main/scala/org/apache/spark/sql/HoodieCatalystExpressionUtils.scala
##########
@@ -0,0 +1,127 @@
+/*
+ * 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
+
+import org.apache.spark.sql.catalyst.analysis.{UnresolvedAttribute, UnresolvedFunction}
+import org.apache.spark.sql.catalyst.expressions.{AttributeReference, Expression, SubqueryExpression}
+import org.apache.spark.sql.catalyst.plans.logical.{Filter, LocalRelation, LogicalPlan}
+import org.apache.spark.sql.types.StructType
+
+trait HoodieCatalystExpressionUtils {
+
+ /**
+ * Parses and resolves expression against the attributes of the given table schema.
+ *
+ * For example:
+ * <pre>
+ * ts > 1000 and ts <= 1500
+ * </pre>
+ * will be resolved as
+ * <pre>
+ * And(GreaterThan(ts#590L > 1000), LessThanOrEqual(ts#590L <= 1500))
+ * </pre>
+ *
+ * Where <pre>ts</pre> is a column of the provided [[tableSchema]]
+ *
+ * @param spark spark session
+ * @param exprString string representation of the expression to parse and resolve
+ * @param tableSchema table schema encompassing attributes to resolve against
+ * @return Resolved filter expression
+ */
+ def resolveExpr(spark: SparkSession, exprString: String, tableSchema: StructType): Expression = {
Review comment:
Did not change
##########
File path: hudi-client/hudi-spark-client/src/main/scala/org/apache/spark/sql/HoodieCatalystExpressionUtils.scala
##########
@@ -0,0 +1,127 @@
+/*
+ * 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
+
+import org.apache.spark.sql.catalyst.analysis.{UnresolvedAttribute, UnresolvedFunction}
+import org.apache.spark.sql.catalyst.expressions.{AttributeReference, Expression, SubqueryExpression}
+import org.apache.spark.sql.catalyst.plans.logical.{Filter, LocalRelation, LogicalPlan}
+import org.apache.spark.sql.types.StructType
+
+trait HoodieCatalystExpressionUtils {
+
+ /**
+ * Parses and resolves expression against the attributes of the given table schema.
+ *
+ * For example:
+ * <pre>
+ * ts > 1000 and ts <= 1500
+ * </pre>
+ * will be resolved as
+ * <pre>
+ * And(GreaterThan(ts#590L > 1000), LessThanOrEqual(ts#590L <= 1500))
+ * </pre>
+ *
+ * Where <pre>ts</pre> is a column of the provided [[tableSchema]]
+ *
+ * @param spark spark session
+ * @param exprString string representation of the expression to parse and resolve
+ * @param tableSchema table schema encompassing attributes to resolve against
+ * @return Resolved filter expression
+ */
+ def resolveExpr(spark: SparkSession, exprString: String, tableSchema: StructType): Expression = {
+ val expr = spark.sessionState.sqlParser.parseExpression(exprString)
+ resolveExpr(spark, expr, tableSchema)
+ }
+
+ /**
+ * Resolves provided expression (unless already resolved) against the attributes of the given table schema.
+ *
+ * For example:
+ * <pre>
+ * ts > 1000 and ts <= 1500
+ * </pre>
+ * will be resolved as
+ * <pre>
+ * And(GreaterThan(ts#590L > 1000), LessThanOrEqual(ts#590L <= 1500))
+ * </pre>
+ *
+ * Where <pre>ts</pre> is a column of the provided [[tableSchema]]
+ *
+ * @param spark spark session
+ * @param expr Catalyst expression to be resolved (if not yet)
+ * @param tableSchema table schema encompassing attributes to resolve against
+ * @return Resolved filter expression
+ */
+ def resolveExpr(spark: SparkSession, expr: Expression, tableSchema: StructType): Expression = {
+ val analyzer = spark.sessionState.analyzer
+ val schemaFields = tableSchema.fields
+
+ val resolvedExpr = {
+ val plan: LogicalPlan = Filter(expr, LocalRelation(schemaFields.head, schemaFields.drop(1): _*))
+ analyzer.execute(plan).asInstanceOf[Filter].condition
+ }
+
+ if (!hasUnresolvedRefs(resolvedExpr)) {
+ resolvedExpr
+ } else {
+ throw new IllegalStateException("unresolved attribute")
+ }
+ }
+
+ /**
+ * Split the given predicates into two sequence predicates:
+ * - predicates that references partition columns only(and involves no sub-query);
+ * - other predicates.
+ *
+ * @param sparkSession The spark session
+ * @param predicates The predicates to be split
+ * @param partitionColumns The partition columns
+ * @return (partitionFilters, dataFilters)
+ */
+ def splitPartitionAndDataPredicates(sparkSession: SparkSession,
Review comment:
Did not change
--
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: commits-unsubscribe@hudi.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org