From d1d009cd86d92e3249b31edb6296d0b88b8b1486 Mon Sep 17 00:00:00 2001
From: Zhipeng Mao <zhipeng.mao@databricks.com>
Date: Thu, 12 Dec 2024 20:09:46 +0100
Subject: [PATCH] [3.3][SPARK] Add test for Identity Column merge metadata
 conflict (#3970)

<!--
Thanks for sending a pull request!  Here are some tips for you:
1. If this is your first time, please read our contributor guidelines:
https://github.com/delta-io/delta/blob/master/CONTRIBUTING.md
2. If the PR is unfinished, add '[WIP]' in your PR title, e.g., '[WIP]
Your PR title ...'.
  3. Be sure to keep the PR description updated to reflect all changes.
  4. Please write your PR title to summarize what this PR proposes.
5. If possible, provide a concise example to reproduce the issue for a
faster review.
6. If applicable, include the corresponding issue number in the PR title
and link it in the body.
-->

#### Which Delta project/connector is this regarding?
<!--
Please add the component selected below to the beginning of the pull
request title
For example: [Spark] Title of my pull request
-->

- [x] Spark
- [ ] Standalone
- [ ] Flink
- [ ] Kernel
- [ ] Other (fill in here)

## Description
It adds a test for identity column to verify merge will be aborted if
high water mark is changed after analysis and before execution.
<!--
- Describe what this PR changes.
- Describe why we need the change.

If this PR resolves an issue be sure to include "Resolves #XXX" to
correctly link and close the issue upon merge.
-->

## How was this patch tested?
Test-only.
<!--
If tests were added, say they were added here. Please make sure to test
the changes thoroughly including negative and positive cases if
possible.
If the changes were tested in any way other than unit tests, please
clarify how you tested step by step (ideally copy and paste-able, so
that other reviewers can test and check, and descendants can verify in
the future).
If the changes were not tested, please explain why.
-->

## Does this PR introduce _any_ user-facing changes?

<!--
If yes, please clarify the previous behavior and the change this PR
proposes - provide the console output, description and/or an example to
show the behavior difference if possible.
If possible, please also clarify if this is a user-facing change
compared to the released Delta Lake versions or within the unreleased
branches such as master.
If no, write 'No'.
-->
No.
---
 .../delta/IdentityColumnConflictSuite.scala   | 24 +++++++++++++++++++
 1 file changed, 24 insertions(+)

diff --git a/spark/src/test/scala/org/apache/spark/sql/delta/IdentityColumnConflictSuite.scala b/spark/src/test/scala/org/apache/spark/sql/delta/IdentityColumnConflictSuite.scala
index e56b57aa21b..04c06020661 100644
--- a/spark/src/test/scala/org/apache/spark/sql/delta/IdentityColumnConflictSuite.scala
+++ b/spark/src/test/scala/org/apache/spark/sql/delta/IdentityColumnConflictSuite.scala
@@ -276,6 +276,30 @@ trait IdentityColumnConflictSuiteBase
       tblIsoLevel = Some(Serializable)
     )
   }
+
+  test("high watermark changes after analysis but before execution of merge") {
+    val tblName = getRandomTableName
+    withIdentityColumnTable(GeneratedAsIdentityType.GeneratedAlways, tblName) {
+      // Create a QueryExecution object for a MERGE statement, and it forces the command to be
+      // analyzed, but does not execute the command yet.
+      val parsedMerge = spark.sessionState.sqlParser.parsePlan(
+        s"""MERGE INTO $tblName t
+           |USING (SELECT * FROM range(1000)) s
+           |ON t.id = s.id
+           |WHEN NOT MATCHED THEN INSERT (value) VALUES (s.id)""".stripMargin)
+      val qeMerge = new QueryExecution(spark, parsedMerge)
+      qeMerge.analyzed
+
+      // Insert a row, forcing the high watermark to be updated.
+      sql(s"INSERT INTO $tblName (value) VALUES (0)")
+
+      // Force merge to be executed. This should fail, as MERGE is still using the old high
+      // watermark in its insert action.
+      intercept[MetadataChangedException] {
+        qeMerge.commandExecuted
+      }
+    }
+  }
 }
 
 class IdentityColumnConflictScalaSuite