From 3c96411e21c916f15338f916c43e7a7719ad353a Mon Sep 17 00:00:00 2001
From: Vinish Reddy <vinishreddygunner17@gmail.com>
Date: Tue, 7 Jul 2026 15:57:48 -0700
Subject: [PATCH] [736] Make the bundled xtable-utilities jar runnable again

Running the bundled utilities jar the way the docs describe
(java -jar xtable-utilities_2.12-*-bundled.jar --datasetConfig config.yaml)
failed on a chain of NoClassDefFoundErrors, and syncing *to* Hudi was
silently skipped. Two upstream changes caused this: #822 replaced the
maven-shade "bundle everything" default with an explicit artifactSet
allowlist, and the Hudi 1.x bump split hudi-common into hudi-common +
hudi-io + hudi-hadoop-common.

Runtime dependencies dropped from the shaded jar:

  org.slf4j:slf4j-api                -> org/slf4j/LoggerFactory
  org.apache.hudi:hudi-hadoop-common -> org/apache/hudi/hadoop/fs/HadoopFSUtils
  org.apache.hudi:hudi-io            -> (runtime transitive, not allowlisted)
  org.openjdk.jol:jol-core           -> org/openjdk/jol/info/GraphLayout  (#736)

Fixes:
- Add slf4j-api, hudi-io and jol-core to the shade allowlist.
- jol-core is pinned to test scope by the parent dependencyManagement, so
  override it to runtime (Hudi's ObjectSizeCalculator loads it at runtime).
- hudi-hadoop-common is only a provided/test transitive, so declare it as a
  runtime dependency of the standalone bundle and allowlist it.
- hudi-java-client was declared twice (compile + a redundant test-scoped
  copy); Maven's last-declaration-wins downgraded it to test scope, so the
  shade plugin excluded the Hudi write client (HoodieJavaEngineContext) and
  RunSync skipped HudiConversionTarget. Remove the redundant test declaration
  so the compile one takes effect and the write client is bundled.

Verified end-to-end via java -jar against real tables:
- Hudi (table v9, metadata table enabled) -> Delta + Iceberg: reads the Hudi
  metadata table (the ObjectSizeCalculator/jol path from this issue) and
  reports "Sync is successful for the following formats ICEBERG,DELTA".
- Iceberg -> Hudi: writes a real Hudi table (.hoodie timeline with a
  completed replacecommit) and reports "Sync is successful ... HUDI".

Closes #736.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
---
 xtable-utilities/pom.xml | 32 ++++++++++++++++++++++++++------
 1 file changed, 26 insertions(+), 6 deletions(-)

diff --git a/xtable-utilities/pom.xml b/xtable-utilities/pom.xml
index 67142199d..d8832abf5 100644
--- a/xtable-utilities/pom.xml
+++ b/xtable-utilities/pom.xml
@@ -153,6 +153,20 @@
             <groupId>org.apache.hudi</groupId>
             <artifactId>hudi-common</artifactId>
         </dependency>
+        <!--
+          Hudi 1.x split the former hudi-common into hudi-common + hudi-io +
+          hudi-hadoop-common. xtable-core compiles against these with the Hudi
+          Spark bundle in provided scope (a real Spark cluster supplies them),
+          but the standalone utilities jar has no such runtime, so it must bundle
+          hudi-hadoop-common itself (hudi-io comes in transitively at runtime).
+          Without this, RunSync fails with NoClassDefFoundError:
+          org/apache/hudi/hadoop/fs/HadoopFSUtils.
+        -->
+        <dependency>
+            <groupId>org.apache.hudi</groupId>
+            <artifactId>hudi-hadoop-common</artifactId>
+            <version>${hudi.version}</version>
+        </dependency>
         <dependency>
             <groupId>org.apache.hudi</groupId>
             <artifactId>hudi-java-client</artifactId>
@@ -232,15 +246,17 @@
             <artifactId>hudi-spark${spark.version.prefix}-bundle_${scala.binary.version}</artifactId>
             <scope>test</scope>
         </dependency>
-        <dependency>
-            <groupId>org.apache.hudi</groupId>
-            <artifactId>hudi-java-client</artifactId>
-            <scope>test</scope>
-        </dependency>
+        <!--
+          Hudi's ObjectSizeCalculator loads org.openjdk.jol at runtime (not only in tests),
+          so the bundled utilities jar must ship it. The parent dependencyManagement pins
+          jol-core to test scope, so override to runtime here and add it to the shaded
+          artifactSet below. See https://github.com/apache/incubator-xtable/issues/736.
+        -->
         <dependency>
             <groupId>org.openjdk.jol</groupId>
             <artifactId>jol-core</artifactId>
-            <scope>test</scope>
+            <version>${jol.core.version}</version>
+            <scope>runtime</scope>
         </dependency>
     </dependencies>
 
@@ -574,6 +590,8 @@
                             <include>org.apache.httpcomponents.core5:httpcore5-h2</include>
                             <include>org.apache.hudi:hudi-client-common</include>
                             <include>org.apache.hudi:hudi-common</include>
+                            <include>org.apache.hudi:hudi-hadoop-common</include>
+                            <include>org.apache.hudi:hudi-io</include>
                             <include>org.apache.hudi:hudi-java-client</include>
                             <include>org.apache.hudi:hudi-timeline-service</include>
                             <include>org.apache.iceberg:iceberg-api</include>
@@ -696,6 +714,7 @@
                             <include>org.json4s:json4s-scalap_${scala.binary.version}</include>
                             <include>org.lz4:lz4-java</include>
                             <include>org.objenesis:objenesis</include>
+                            <include>org.openjdk.jol:jol-core</include>
                             <include>org.reactivestreams:reactive-streams</include>
                             <include>org.roaringbitmap:RoaringBitmap</include>
                             <include>org.roaringbitmap:shims</include>
@@ -707,6 +726,7 @@
                             <include>org.scala-lang.modules:scala-xml_${scala.binary.version}</include>
                             <include>org.slf4j:jcl-over-slf4j</include>
                             <include>org.slf4j:jul-to-slf4j</include>
+                            <include>org.slf4j:slf4j-api</include>
                             <include>org.slf4j:slf4j-reload4j</include>
                             <include>org.threeten:threeten-extra</include>
                             <include>org.threeten:threetenbp</include>