Merge pull request apache#4019 from hansva/3908

Use compare using values by default in Unique rows hashset apache#3908
bumabo · Jun 6, 2024 · 3515546 · 3515546
2 parents 2ef60cf + 76b9bfe
commit 3515546
Show file tree

Hide file tree

Showing 2 changed files with 3 additions and 0 deletions.
diff --git a/...hop-user-manual/modules/ROOT/pages/pipeline/transforms/uniquerowsbyhashset.adoc b/...hop-user-manual/modules/ROOT/pages/pipeline/transforms/uniquerowsbyhashset.adoc
@@ -40,6 +40,8 @@ This transform differs from the xref:pipeline/transforms/uniquerows.adoc[Unique
 !===
 |===
 
+WARNING: When using this transform on larger sets of data there is a risk of hash collisions unless "Compare using stored row values" is enabled.
+
 == Options
 
 [options="header"]

diff --git a/.../java/org/apache/hop/pipeline/transforms/uniquerowsbyhashset/UniqueRowsByHashSetMeta.java b/.../java/org/apache/hop/pipeline/transforms/uniquerowsbyhashset/UniqueRowsByHashSetMeta.java
@@ -163,6 +163,7 @@ private void readData(Node transformNode) throws HopXmlException {
  public void setDefault() {
  rejectDuplicateRow = false;
  errorDescription = null;
+ storeValues = true;
  int nrFields = 0;
 
  allocate(nrFields);