[GitHub] [arrow-datafusion] alamb commented on a change in pull request #482: Support anti join

[GitBox <gi...@apache.org>]

alamb commented on a change in pull request #482:
URL: https://github.com/apache/arrow-datafusion/pull/482#discussion_r645146517



##########
File path: datafusion/src/physical_plan/hash_join.rs
##########
@@ -1725,6 +1736,40 @@ mod tests {
         Ok(())
     }
 
+    #[tokio::test]
+    async fn join_anti() -> Result<()> {
+        let left = build_table(
+            ("a1", &vec![1, 2, 2, 3, 5]),
+            ("b1", &vec![4, 5, 5, 7, 7]), // 7 does not exist on the right
+            ("c1", &vec![7, 8, 8, 9, 11]),
+        );
+        let right = build_table(
+            ("a2", &vec![10, 20, 30, 40]),
+            ("b1", &vec![4, 5, 6, 5]), // 5 is double on the right
+            ("c2", &vec![70, 80, 90, 100]),
+        );
+        let on = &[("b1", "b1")];
+
+        let join = join(left, right, on, &JoinType::Anti)?;
+
+        let columns = columns(&join.schema());
+        assert_eq!(columns, vec!["a1", "b1", "c1"]);
+
+        let stream = join.execute(0).await?;
+        let batches = common::collect(stream).await?;
+
+        let expected = vec![
+            "+----+----+----+",
+            "| a1 | b1 | c1 |",
+            "+----+----+----+",
+            "| 3  | 7  | 9  |",

Review comment:
       👍  `7, 7` 👍 




-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

For queries about this service, please contact Infrastructure at:
users@infra.apache.org