From 2ab5a8d419d869525b1c110372a7782875caa88b Mon Sep 17 00:00:00 2001
From: Fred Storage Liu <fred.liu@databricks.com>
Date: Wed, 28 Aug 2024 10:37:39 -0700
Subject: [PATCH] Uniform iceberg conversion transaction should not convert
 commit with only AddFiles without datachange (#3615)

<!--
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

Uniform iceberg conversion transaction should not convert commit with
only AddFiles without datachange. Otherwise it will result in duplicate
AddFile in Iceberg.



## How was this patch tested?

Manual tested with Spark; UT will be added in future PR.

## 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'.
-->
---
 .../delta/icebergShaded/IcebergConverter.scala   | 16 ++++++++++++----
 1 file changed, 12 insertions(+), 4 deletions(-)

diff --git a/iceberg/src/main/scala/org/apache/spark/sql/delta/icebergShaded/IcebergConverter.scala b/iceberg/src/main/scala/org/apache/spark/sql/delta/icebergShaded/IcebergConverter.scala
index a4fc84e7cff..cd6eb29a31c 100644
--- a/iceberg/src/main/scala/org/apache/spark/sql/delta/icebergShaded/IcebergConverter.scala
+++ b/iceberg/src/main/scala/org/apache/spark/sql/delta/icebergShaded/IcebergConverter.scala
@@ -467,6 +467,7 @@ class IcebergConverter(spark: SparkSession)
         var hasRemoves = false
         var hasDataChange = false
         var hasCommitInfo = false
+        var commitInfo: Option[CommitInfo] = None
         breakable {
           for (action <- actionsToCommit) {
             action match {
@@ -476,7 +477,9 @@ class IcebergConverter(spark: SparkSession)
               case r: RemoveFile =>
                 hasRemoves = true
                 if (r.dataChange) hasDataChange = true
-              case _: CommitInfo => hasCommitInfo = true
+              case ci: CommitInfo =>
+                commitInfo = Some(ci)
+                hasCommitInfo = true
               case _ => // Do nothing
             }
             if (hasAdds && hasRemoves && hasDataChange && hasCommitInfo) break // Short-circuit
@@ -510,9 +513,14 @@ class IcebergConverter(spark: SparkSession)
           }
           overwriteHelper.commit()
         } else if (hasAdds) {
-          val appendHelper = icebergTxn.getAppendOnlyHelper()
-          addsAndRemoves.foreach(action => appendHelper.add(action.add))
-          appendHelper.commit()
+          if (!hasRemoves && !hasDataChange && allDeltaActionsCaptured) {
+            logInfo(s"Skip Iceberg conversion for commit that only has AddFiles " +
+              s"without any RemoveFiles or data change. CommitInfo: $commitInfo")
+          } else {
+            val appendHelper = icebergTxn.getAppendOnlyHelper()
+              addsAndRemoves.foreach(action => appendHelper.add(action.add))
+              appendHelper.commit()
+          }
         } else if (hasRemoves) {
           val removeHelper = icebergTxn.getRemoveOnlyHelper()
           addsAndRemoves.foreach(action => removeHelper.remove(action.remove))