From b275ca8cfcf410b44d5b6809971ac1de62ce5e6a Mon Sep 17 00:00:00 2001
From: anthonychengit <anthonyschenemail@gmail.com>
Date: Fri, 10 Jul 2026 00:32:04 -0700
Subject: [PATCH] refactor(workflow-core): remove unused hadoop Iceberg catalog

---
 common/config/src/main/resources/storage.conf |  2 +-
 .../core/storage/IcebergCatalogInstance.scala |  5 -----
 .../texera/amber/util/IcebergUtil.scala       | 21 +------------------
 .../iceberg/IcebergTableWriterSpec.scala      |  2 +-
 4 files changed, 3 insertions(+), 27 deletions(-)

diff --git a/common/config/src/main/resources/storage.conf b/common/config/src/main/resources/storage.conf
index a9709f9070d..ac34e1e6b84 100644
--- a/common/config/src/main/resources/storage.conf
+++ b/common/config/src/main/resources/storage.conf
@@ -21,7 +21,7 @@ storage {
     # Configuration for Apache Iceberg, used for storing the workflow results & stats
     iceberg {
         catalog {
-            type = rest # either hadoop, rest, or postgres
+            type = rest # either rest or postgres
             type = ${?STORAGE_ICEBERG_CATALOG_TYPE}
 
             rest {
diff --git a/common/workflow-core/src/main/scala/org/apache/texera/amber/core/storage/IcebergCatalogInstance.scala b/common/workflow-core/src/main/scala/org/apache/texera/amber/core/storage/IcebergCatalogInstance.scala
index cd4b3c8796f..6b85c51d2a7 100644
--- a/common/workflow-core/src/main/scala/org/apache/texera/amber/core/storage/IcebergCatalogInstance.scala
+++ b/common/workflow-core/src/main/scala/org/apache/texera/amber/core/storage/IcebergCatalogInstance.scala
@@ -44,11 +44,6 @@ object IcebergCatalogInstance {
       case Some(catalog) => catalog
       case None =>
         val catalog = StorageConfig.icebergCatalogType match {
-          case "hadoop" =>
-            IcebergUtil.createHadoopCatalog(
-              "texera_iceberg",
-              StorageConfig.fileStorageDirectoryPath
-            )
           case "rest" =>
             IcebergUtil.createRestCatalog(
               "texera_iceberg",
diff --git a/common/workflow-core/src/main/scala/org/apache/texera/amber/util/IcebergUtil.scala b/common/workflow-core/src/main/scala/org/apache/texera/amber/util/IcebergUtil.scala
index b8e46e5cc5b..4a725bbb69c 100644
--- a/common/workflow-core/src/main/scala/org/apache/texera/amber/util/IcebergUtil.scala
+++ b/common/workflow-core/src/main/scala/org/apache/texera/amber/util/IcebergUtil.scala
@@ -21,12 +21,11 @@ package org.apache.texera.amber.util
 
 import org.apache.texera.common.config.StorageConfig
 import org.apache.texera.amber.core.tuple.{Attribute, AttributeType, LargeBinary, Schema, Tuple}
-import org.apache.hadoop.conf.Configuration
 import org.apache.iceberg.catalog.{Catalog, SupportsNamespaces, TableIdentifier}
 import org.apache.iceberg.data.parquet.GenericParquetReaders
 import org.apache.iceberg.data.{GenericRecord, Record}
 import org.apache.iceberg.aws.s3.S3FileIO
-import org.apache.iceberg.hadoop.{HadoopCatalog, HadoopFileIO}
+import org.apache.iceberg.hadoop.HadoopFileIO
 import org.apache.iceberg.io.{CloseableIterator, InputFile}
 import org.apache.iceberg.jdbc.JdbcCatalog
 import org.apache.iceberg.parquet.{Parquet, ParquetValueReader}
@@ -59,7 +58,6 @@ object IcebergUtil {
   private val LARGE_BINARY_FIELD_SUFFIX = "__texera_large_binary_ptr"
 
   /**
-    * Creates and initializes a HadoopCatalog with the given parameters.
     * - Uses an empty Hadoop `Configuration`, meaning the local file system (or `file:/`) will be used by default
     * instead of HDFS.
     * - The `warehouse` parameter specifies the root directory for storing table data.
@@ -67,24 +65,7 @@ object IcebergUtil {
     *
     * @param catalogName the name of the catalog.
     * @param warehouse   the root path for the warehouse where the tables are stored.
-    * @return the initialized HadoopCatalog instance.
     */
-  def createHadoopCatalog(
-      catalogName: String,
-      warehouse: Path
-  ): HadoopCatalog = {
-    val catalog = new HadoopCatalog()
-    catalog.setConf(new Configuration) // Empty configuration, defaults to `file:/`
-    catalog.initialize(
-      catalogName,
-      Map(
-        "warehouse" -> warehouse.toString,
-        CatalogProperties.FILE_IO_IMPL -> classOf[HadoopFileIO].getName
-      ).asJava
-    )
-
-    catalog
-  }
 
   /**
     * Creates and initializes a RESTCatalog with the given parameters.
diff --git a/common/workflow-core/src/test/scala/org/apache/texera/amber/core/storage/result/iceberg/IcebergTableWriterSpec.scala b/common/workflow-core/src/test/scala/org/apache/texera/amber/core/storage/result/iceberg/IcebergTableWriterSpec.scala
index 5c823924170..d7e83157dbf 100644
--- a/common/workflow-core/src/test/scala/org/apache/texera/amber/core/storage/result/iceberg/IcebergTableWriterSpec.scala
+++ b/common/workflow-core/src/test/scala/org/apache/texera/amber/core/storage/result/iceberg/IcebergTableWriterSpec.scala
@@ -45,7 +45,7 @@ class IcebergTableWriterSpec extends AnyFlatSpec with BeforeAndAfterAll {
 
   override def beforeAll(): Unit = {
     warehouseDir = Files.createTempDirectory("iceberg-table-writer-spec")
-    catalog = IcebergUtil.createHadoopCatalog("writer-spec", warehouseDir)
+    catalog = IcebergUtil.createPostgresCatalog("writer-spec", warehouseDir)
   }
 
   override def afterAll(): Unit = {