refactor(workflow-core): remove unused hadoop Iceberg catalog

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 {

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",

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}
@@ -59,32 +58,14 @@ 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.
     * - Sets the file I/O implementation to `HadoopFileIO`.
     *
     * @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.

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 = {