Use QUALIFY clause in deduplicate macro for Redshift (#811)

* refactor: Use QUALIFY syntax in deduplicate() macro for Redshift * chore: Update changelog --------- Co-authored-by: Yauhen Sobaleu <[email protected]>
dbt-labs · Jul 25, 2023 · a17d66f · a17d66f
1 parent 9cd5988
commit a17d66f
Show file tree

Hide file tree

Showing 2 changed files with 11 additions and 2 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -11,9 +11,11 @@
 # Unreleased
 ## Fixes
 - deduplicate macro for Databricks now uses the QUALIFY clause, which fixes NULL columns issues from the default natural join logic
+- deduplicate macro for Redshift now uses the QUALIFY clause, which fixes NULL columns issues from the default natural join logic
 
 ## Contributors:
 [@graciegoheen](https://github.com/graciegoheen)
+[@yauhen-sobaleu](https://github.com/yauhen-sobaleu)
 
 # dbt utils v1.1.1
 ## New features

diff --git a/macros/sql/deduplicate.sql b/macros/sql/deduplicate.sql
@@ -29,10 +29,17 @@
 
 {%- endmacro -%}
 
-{# Redshift should use default instead of Postgres #}
+-- Redshift has the `QUALIFY` syntax:
+-- https://docs.aws.amazon.com/redshift/latest/dg/r_QUALIFY_clause.html
 {% macro redshift__deduplicate(relation, partition_by, order_by) -%}
 
-    {{ return(dbt_utils.default__deduplicate(relation, partition_by, order_by=order_by)) }}
+    select *
+    from {{ relation }} as tt
+    qualify
+        row_number() over (
+            partition by {{ partition_by }}
+            order by {{ order_by }}
+        ) = 1
 
 {% endmacro %}