From db7e734eba785aedfd9d26360e1367f1e7ac04bf Mon Sep 17 00:00:00 2001 From: Vikas Gupta Date: Fri, 28 Jul 2023 08:50:55 +0530 Subject: [PATCH] cache obv dupe pairs for performance --- .../core/src/main/java/zingg/common/core/executor/Matcher.java | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/common/core/src/main/java/zingg/common/core/executor/Matcher.java b/common/core/src/main/java/zingg/common/core/executor/Matcher.java index e222ce97c..6fb794665 100644 --- a/common/core/src/main/java/zingg/common/core/executor/Matcher.java +++ b/common/core/src/main/java/zingg/common/core/executor/Matcher.java @@ -189,7 +189,7 @@ protected ZFrame getObvDupePairs(ZFrame blocked) { return null; } - ZFrame obvDupePairs = blocked.joinOnCol(prefixedColsDF, obvDupeDFFilter); + ZFrame obvDupePairs = blocked.joinOnCol(prefixedColsDF, obvDupeDFFilter).cache(); obvDupePairs = obvDupePairs.filter(obvDupePairs.gt(ColName.ID_COL)); obvDupePairs = massageAllEquals(obvDupePairs);