Merge pull request #626 from zinggAI/obviousDupes

cache obv dupe pairs for performance
zinggAI · Jul 28, 2023 · bb3102c · bb3102c
2 parents a8dc931 + db7e734
commit bb3102c
Showing 1 changed file with 1 addition and 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
@@ -189,7 +189,7 @@ protected ZFrame<D,R,C> getObvDupePairs(ZFrame<D,R,C> blocked) {
 			return null;
 		}
 
-		ZFrame<D, R, C> obvDupePairs = blocked.joinOnCol(prefixedColsDF, obvDupeDFFilter);
+		ZFrame<D, R, C> obvDupePairs = blocked.joinOnCol(prefixedColsDF, obvDupeDFFilter).cache();
 		obvDupePairs = obvDupePairs.filter(obvDupePairs.gt(ColName.ID_COL));
 		obvDupePairs = massageAllEquals(obvDupePairs);