From 3b1a3ec5d1aac8e5e15e694be709530fd343d8a3 Mon Sep 17 00:00:00 2001
From: Josh <5685731+marcantony@users.noreply.github.com>
Date: Sat, 31 Aug 2024 12:40:11 -0400
Subject: [PATCH] Fix performance of building row-level results (#577)

* Generate row-level results with withColumns

Iteratively using withColumn (singular) causes performance
issues when iterating over a large sequence of columns.

* Add back UNIQUENESS_ID
---
 src/main/scala/com/amazon/deequ/VerificationResult.scala | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/src/main/scala/com/amazon/deequ/VerificationResult.scala b/src/main/scala/com/amazon/deequ/VerificationResult.scala
index 6390db821..418a622e6 100644
--- a/src/main/scala/com/amazon/deequ/VerificationResult.scala
+++ b/src/main/scala/com/amazon/deequ/VerificationResult.scala
@@ -98,9 +98,7 @@ object VerificationResult {
     val columnNamesToMetrics: Map[String, Column] = verificationResultToColumn(verificationResult)
 
     val dataWithID = data.withColumn(UNIQUENESS_ID, monotonically_increasing_id())
-    columnNamesToMetrics.foldLeft(dataWithID)(
-      (dataWithID, newColumn: (String, Column)) =>
-        dataWithID.withColumn(newColumn._1, newColumn._2)).drop(UNIQUENESS_ID)
+    dataWithID.withColumns(columnNamesToMetrics).drop(UNIQUENESS_ID)
   }
 
   def checkResultsAsJson(verificationResult: VerificationResult,