Support for Source and Sink Operators for Apache Iceberg for the Java Platform

wayang-api/wayang-api-scala-java/src/main/scala/org/apache/wayang/api/DataQuanta.scala

@@ -1013,7 +1013,6 @@ class DataQuanta[Out: ClassTag](val operator: ElementaryOperator, outputIndex: I
     this.planBuilder.buildAndExplain(toJson)
   }
 
-
   /**
     * Write the data quanta in this instance to a text file. Triggers execution.
     *
@@ -1027,6 +1026,44 @@ class DataQuanta[Out: ClassTag](val operator: ElementaryOperator, outputIndex: I
     writeTextFileJava(url, toSerializableFunction(formatterUdf), udfLoad)
   }
 
+  /**
+    * Write the data quanta in this instance to a iceberg table. Triggers execution.
+    *
+    * @param catalog          Iceberg Catalog
+    * @param schema           Iceberg Schema of the table to create
+    * @param tableIdentifier  Iceberg Table Identifier of the table to create
+    * @param outputFileFormat File format of the output data files
+    */
+
+  def writeIcebergTable(catalog: org.apache.iceberg.catalog.Catalog, 
+                      schema: org.apache.iceberg.Schema, 
+                      tableIdentifier: org.apache.iceberg.catalog.TableIdentifier,
+                      outputFileFormat: org.apache.iceberg.FileFormat): Unit = {
+    writeIcebergTableJava(catalog, schema, tableIdentifier, outputFileFormat)
+  }
+
+  /**
+    * Write the data quanta in this instance to a iceberg table. Triggers execution.
+    *
+    * @param catalog          Iceberg Catalog
+    * @param schema           Iceberg Schema of the table to create
+    * @param tableIdentifier  Iceberg Table Identifier of the table to create
+    * @param outputFileFormat File format of the output data files
+    */
+  def writeIcebergTableJava(
+    catalog: org.apache.iceberg.catalog.Catalog, 
+    schema: org.apache.iceberg.Schema, 
+    tableIdentifier: org.apache.iceberg.catalog.TableIdentifier,
+    outputFileFormat: org.apache.iceberg.FileFormat ): Unit = {
+
+    val sink = new ApacheIcebergSink(catalog, schema, tableIdentifier, outputFileFormat)
+
+    sink.setName(s"*#-> Write to Iceberg Table Sink ")
+    this.connectTo(sink, 0)
+    this.planBuilder.sinks += sink
+    this.planBuilder.buildAndExecute()
+    this.planBuilder.sinks.clear()
+  }
  /**
   * Write the data quanta in this instance to a text file. Triggers execution.
   *
@@ -1090,6 +1127,8 @@ class DataQuanta[Out: ClassTag](val operator: ElementaryOperator, outputIndex: I
     this.planBuilder.sinks.clear()
   }
 
+
+
   /**
    * Write the data quanta in this instance to a Object file. Triggers execution.
    *

wayang-api/wayang-api-scala-java/src/main/scala/org/apache/wayang/api/DataQuantaBuilder.scala

@@ -499,6 +499,27 @@ trait DataQuantaBuilder[+This <: DataQuantaBuilder[_, Out], Out] extends Logging
     this.dataQuanta().writeTextFileJava(url, formatterUdf, udfLoadProfileEstimator)
   }
 
+    /**
+    * Feed the built [[DataQuanta]] into a [[org.apache.wayang.basic.operators.IcebergTableSink]]. This triggers
+    * execution of the constructed [[WayangPlan]].
+    *
+    * @param catalog          Iceberg Catalog
+    * @param schema           Iceberg Schema of the table to create
+    * @param tableIdentifier  Iceberg Table Identifier of the table to create
+    * @param outputFileFormat File format of the output data files    
+    * @return the collected data quanta
+    */
+
+  def writeIcebergTable(catalog: org.apache.iceberg.catalog.Catalog, 
+                      schema: org.apache.iceberg.Schema, 
+                      tableIdentifier: org.apache.iceberg.catalog.TableIdentifier,
+                      outputFileFormat: org.apache.iceberg.FileFormat,
+                      jobName: String): Unit = {
+    this.javaPlanBuilder.withJobName(jobName)
+    this.dataQuanta().writeIcebergTableJava(catalog, schema, tableIdentifier, outputFileFormat)
+
+  }
+
   /**
     * Feed the built [[DataQuanta]] into a [[org.apache.wayang.basic.operators.KafkaTopicSink]]. This triggers
     * execution of the constructed [[WayangPlan]].

wayang-api/wayang-api-scala-java/src/main/scala/org/apache/wayang/api/JavaPlanBuilder.scala

@@ -25,7 +25,7 @@ import java.util.{Collection => JavaCollection}
 import org.apache.commons.lang3.Validate
 import org.apache.wayang.api.util.DataQuantaBuilderCache
 import org.apache.wayang.basic.data.Record
-import org.apache.wayang.basic.operators.{AmazonS3Source, AzureBlobStorageSource, GoogleCloudStorageSource, KafkaTopicSource, ParquetSource, TableSource, TextFileSource}
+import org.apache.wayang.basic.operators.{AmazonS3Source, AzureBlobStorageSource, GoogleCloudStorageSource, KafkaTopicSource, ParquetSource, TableSource, TextFileSource, ApacheIcebergSource}
 import org.apache.wayang.commons.util.profiledb.model.Experiment
 import org.apache.wayang.core.api.WayangContext
 import org.apache.wayang.core.plan.wayangplan._
@@ -72,6 +72,22 @@ class JavaPlanBuilder(wayangCtx: WayangContext, jobName: String) {
   def readParquet(url: String, projection: Array[String] = null): UnarySourceDataQuantaBuilder[UnarySourceDataQuantaBuilder[_, Record], Record] =
     createSourceBuilder(ParquetSource.create(url, projection))(ClassTag(classOf[Record]))
 
+  /**
+   * Read an Apache Iceberg table and provide it as a dataset of [[Record]]s.
+   *
+   * @param catalog the Iceberg catalog containing the table
+   * @param tableIdentifier the identifier of the Iceberg table to read
+   * @param filterExpressions optional array of filter expressions to apply during the read
+   * @param projectionColumns optional array of column names to project (select specific columns)
+   * @return [[DataQuantaBuilder]] for the Iceberg table
+   */
+  def readApacheIcebergTable(
+    catalog: org.apache.iceberg.catalog.Catalog, 
+    tableIdentifier: org.apache.iceberg.catalog.TableIdentifier, 
+    filterExpressions: Array[org.apache.iceberg.expressions.Expression] = null, 
+    projectionColumns: Array[String] = null): UnarySourceDataQuantaBuilder[UnarySourceDataQuantaBuilder[_, Record], Record] =
+      createSourceBuilder(ApacheIcebergSource.create(catalog, tableIdentifier, filterExpressions, projectionColumns))(ClassTag(classOf[Record]))
+
   /**
     * Read a text file from a Google Cloud Storage bucket and provide it as a dataset of [[String]]s, one per line.
     *

wayang-api/wayang-api-scala-java/src/main/scala/org/apache/wayang/api/PlanBuilder.scala

@@ -24,7 +24,7 @@ package org.apache.wayang.api
 import org.apache.commons.lang3.Validate
 import org.apache.wayang.api
 import org.apache.wayang.basic.data.Record
-import org.apache.wayang.basic.operators.{AmazonS3Source, AzureBlobStorageSource, CollectionSource, GoogleCloudStorageSource, ObjectFileSource, ParquetSource, TableSource, TextFileSource}
+import org.apache.wayang.basic.operators.{AmazonS3Source, AzureBlobStorageSource, CollectionSource, GoogleCloudStorageSource, ObjectFileSource, ParquetSource, TableSource, TextFileSource, ApacheIcebergSource}
 import org.apache.wayang.commons.util.profiledb.model.Experiment
 import org.apache.wayang.core.api.WayangContext
 import org.apache.wayang.core.plan.wayangplan._
@@ -140,6 +140,21 @@ class PlanBuilder(private[api] val wayangContext: WayangContext, private var job
    */
   def readParquet(url: String, projection: Array[String] = null): DataQuanta[Record] = load(ParquetSource.create(url, projection))
 
+  /**
+   * Read an Apache Iceberg table and provide it as a dataset of [[Record]]s.
+   *
+   * @param catalog the Iceberg catalog containing the table
+   * @param tableIdentifier the identifier of the Iceberg table to read
+   * @param filterExpressions optional array of filter expressions to apply during the read
+   * @param projectionColumns optional array of column names to project (select specific columns)
+   * @return [[DataQuanta]] of [[Record]] for the Iceberg table
+   */
+  def readApacheIcebergTable(
+    catalog: org.apache.iceberg.catalog.Catalog, 
+    tableIdentifier: org.apache.iceberg.catalog.TableIdentifier, 
+    filterExpressions: Array[org.apache.iceberg.expressions.Expression] = null, 
+    projectionColumns: Array[String] = null): DataQuanta[Record] = load(ApacheIcebergSource.create(catalog, tableIdentifier, filterExpressions, projectionColumns))
+
  /**
     * Read a text file from a Google Cloud Storage bucket and provide it as a dataset of [[String]]s, one per line.
     *

wayang-commons/wayang-basic/pom.xml

@@ -34,6 +34,11 @@
         This modules represents the base Wayang package with the default operators and functions.
     </description>
 
+      <properties>
+        <iceberg.version>1.6.0</iceberg.version>
+        <hadoop.version>3.3.6</hadoop.version>
+    </properties>
+
 <dependencyManagement>
     <dependencies>
         <!-- Google Cloud Libraries BOM -->
@@ -132,6 +137,45 @@
             <groupId>com.azure</groupId>
             <artifactId>azure-identity</artifactId>
         </dependency>
+
+
+        <!-- Apache Iceberg properties-->
+
+        <dependency>
+            <groupId>org.apache.iceberg</groupId>
+            <artifactId>iceberg-core</artifactId>
+            <version>${iceberg.version}</version>
+        </dependency>
+        <dependency>
+            <groupId>org.apache.iceberg</groupId>
+            <artifactId>iceberg-api</artifactId>
+            <version>${iceberg.version}</version>
+        </dependency>
+        <dependency>
+            <groupId>org.apache.iceberg</groupId>
+            <artifactId>iceberg-parquet</artifactId>
+            <version>${iceberg.version}</version>
+        </dependency>
+        <dependency>
+            <groupId>org.apache.iceberg</groupId>
+            <artifactId>iceberg-data</artifactId>
+            <version>${iceberg.version}</version>
+        </dependency>
+        <dependency>
+            <groupId>org.apache.hadoop</groupId>
+            <artifactId>hadoop-common</artifactId>
+            <version>${hadoop.version}</version>
+        </dependency>
+        <dependency>
+            <groupId>org.apache.hadoop</groupId>
+            <artifactId>hadoop-client</artifactId>
+            <version>${hadoop.version}</version>
+        </dependency>
+        <dependency>
+            <groupId>org.slf4j</groupId>
+            <artifactId>slf4j-simple</artifactId>
+            <version>2.0.16</version>
+        </dependency>
 
 
     </dependencies>

wayang-commons/wayang-basic/src/main/java/org/apache/wayang/basic/operators/ApacheIcebergSink.java

@@ -0,0 +1,76 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements.  See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership.  The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License.  You may obtain a copy of the License at
+ *
+ *     http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package org.apache.wayang.basic.operators;
+
+import org.apache.wayang.core.plan.wayangplan.UnarySink;
+import org.apache.wayang.core.types.DataSetType;
+
+import org.apache.iceberg.Schema;
+import org.apache.iceberg.catalog.Catalog;
+import org.apache.iceberg.catalog.TableIdentifier;
+import org.apache.iceberg.FileFormat;
+import org.apache.wayang.basic.data.Record;
+
+/**
+ * This {@link UnarySink} writes all incoming data quanta to an iceberg table.
+ * Either if the table does not exists it will create new, otherwise append.
+ * 
+ * @param <T> Data Type if the incoming Data Quanta
+ */
+public class ApacheIcebergSink extends UnarySink<org.apache.wayang.basic.data.Record> {
+
+    protected final Catalog catalog;
+    protected final Schema schema;
+    protected final TableIdentifier tableIdentifier;
+    protected final FileFormat outputFileFormat;
+
+    /**
+     *
+     * @param catalog         Iceberg catalog used to resolve the target table; must
+     *                        not be {@code null}
+     * @param schema          Iceberg write schema; must be compatible with the
+     *                        target table
+     * @param tableIdentifier fully qualified identifier of the target table
+     * 
+     * @param outputFileFormat {@link FileFormat} the format of the output data files
+     */
+    public ApacheIcebergSink(Catalog catalog, Schema schema, TableIdentifier tableIdentifier, FileFormat outputFileFormat) {
+        super(DataSetType.createDefault(Record.class));
+        this.catalog = catalog;
+        this.schema = schema;
+        this.tableIdentifier = tableIdentifier;
+        this.outputFileFormat = outputFileFormat;
+    }
+
+    /**
+     * Creates a copied instance.
+     *
+     * @param that should be copied
+     */
+    public ApacheIcebergSink(ApacheIcebergSink that) {
+        super(that);
+        this.catalog = that.catalog;
+        this.schema = that.schema;
+        this.tableIdentifier = that.tableIdentifier;
+        this.outputFileFormat = that.outputFileFormat;
+    }
+
+    public FileFormat getOutputFileFormat() {
+        return this.outputFileFormat;
+    }
+}