Github user cloud-fan commented on a diff in the pull request:
https://github.com/apache/spark/pull/21320#discussion_r199516297
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/planning/SelectedField.scala
---
@@ -0,0 +1,134 @@
+/*
+ * 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.planning
+
+import org.apache.spark.sql.catalyst.expressions._
+import org.apache.spark.sql.types._
+
+/**
+ * A Scala extractor that builds a
[[org.apache.spark.sql.types.StructField]] from a Catalyst
+ * complex type extractor. For example, consider a relation with the
following schema:
+ *
+ * {{{
+ * root
+ * |-- name: struct (nullable = true)
+ * | |-- first: string (nullable = true)
+ * | |-- last: string (nullable = true)
+ * }}}
+ *
+ * Further, suppose we take the select expression `name.first`. This will
parse into an
+ * `Alias(child, "first")`. Ignoring the alias, `child` matches the
following pattern:
+ *
+ * {{{
+ * GetStructFieldObject(
+ * AttributeReference("name", StructType(_), _, _),
+ * StructField("first", StringType, _, _))
+ * }}}
+ *
+ * [[SelectedField]] converts that expression into
+ *
+ * {{{
+ * StructField("name", StructType(Array(StructField("first",
StringType))))
+ * }}}
+ *
+ * by mapping each complex type extractor to a
[[org.apache.spark.sql.types.StructField]] with the
+ * same name as its child (or "parent" going right to left in the select
expression) and a data
+ * type appropriate to the complex type extractor. In our example, the
name of the child expression
+ * is "name" and its data type is a
[[org.apache.spark.sql.types.StructType]] with a single string
+ * field named "first".
+ *
+ * @param expr the top-level complex type extractor
+ */
+object SelectedField {
+ def unapply(expr: Expression): Option[StructField] = {
--- End diff --
nit: `Expression` -> `ExtractValue`?
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
