Github user ericl commented on a diff in the pull request:
https://github.com/apache/spark/pull/13505#discussion_r65821217
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/package.scala
---
@@ -86,11 +88,42 @@ package object expressions {
/**
* Helper functions for working with `Seq[Attribute]`.
*/
- implicit class AttributeSeq(attrs: Seq[Attribute]) {
+ implicit class AttributeSeq(val attrs: Seq[Attribute]) {
/** Creates a StructType with a schema matching this `Seq[Attribute]`.
*/
def toStructType: StructType = {
StructType(attrs.map(a => StructField(a.name, a.dataType,
a.nullable)))
}
+
+ // It's possible that `attrs` is a linked list, which can lead to bad
O(n^2) loops when
+ // accessing attributes by their ordinals. To avoid this performance
penalty, convert the input
+ // to an array.
+ private lazy val attrsArray = attrs.toArray
+
+ private lazy val exprIdToOrdinal = {
+ val arr = attrsArray
+ val map = Maps.newHashMapWithExpectedSize[ExprId, Int](arr.length)
+ var index = 0
+ while (index < arr.length) {
+ val exprId = arr(index).exprId
+ if (!map.containsKey(exprId)) {
+ map.put(exprId, index)
+ }
+ index += 1
+ }
+ map
+ }
+
+ /**
+ * Returns the attribute at the given index.
+ */
+ def apply(ordinal: Int): Attribute = attrsArray(ordinal)
+
+ /**
+ * Returns the index of first attribute with a matching expression id,
or -1 if no match exists.
+ */
+ def getOrdinalWithExprId(exprId: ExprId): Int = {
--- End diff --
Would `indexOf` be more clear?
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
