spark-reviews mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From GitBox <...@apache.org>
Subject [GitHub] [spark] maropu commented on a change in pull request #24851: [SPARK-27303][GRAPH] Add Spark Graph API
Date Fri, 25 Oct 2019 07:16:46 GMT
maropu commented on a change in pull request #24851: [SPARK-27303][GRAPH] Add Spark Graph API
URL: https://github.com/apache/spark/pull/24851#discussion_r338910953
 
 

 ##########
 File path: graph/api/src/main/scala/org/apache/spark/graph/api/NodeDatasetBuilder.scala
 ##########
 @@ -0,0 +1,86 @@
+/*
+ * 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.spark.graph.api
+
+import scala.collection.JavaConverters._
+
+import org.apache.spark.annotation.Evolving
+import org.apache.spark.sql.{Dataset, Row}
+
+/**
+ * A builder for [[NodeDataset]].
+ *
+ * @param ds Dataset containing a single node in each row
+ * @since 3.0.0
+ */
+@Evolving
+final class NodeDatasetBuilder(val ds: Dataset[Row]) {
+
+  private var idColumn: String = CypherSession.ID_COLUMN
+  private var labelSet: Set[String] = Set.empty
+  private var properties: Map[String, String] = Map.empty
+
+  /**
+   * @param idColumn column that contains the node identifier
+   * @since 3.0.0
+   */
+  def idColumn(idColumn: String): NodeDatasetBuilder = {
+    if (idColumn.isEmpty) {
+      throw new IllegalArgumentException("idColumn must not be empty")
+    }
+    this.idColumn = idColumn;
+    this
+  }
+
+  /**
+   * @param labelSet labels that are assigned to all nodes
+   * @since 3.0.0
+   */
+  def labelSet(labelSet: Array[String]): NodeDatasetBuilder = {
+    this.labelSet = labelSet.toSet
+    this
+  }
+
+  /**
+   * @param properties mapping from property keys to corresponding columns
+   * @since 3.0.0
+   */
+  def properties(properties: Map[String, String]): NodeDatasetBuilder = {
+    this.properties = properties
+    this
+  }
+
+  /**
+   * @param properties mapping from property keys to corresponding columns
+   * @since 3.0.0
+   */
+  def properties(properties: java.util.Map[String, String]): NodeDatasetBuilder = {
+    this.properties = properties.asScala.toMap
+    this
+  }
+
+  /**
+   * Creates a `NodeDataset` from the specified builder parameters.
+   *
 
 Review comment:
   nit: remove this blank line.

----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
users@infra.apache.org


With regards,
Apache Git Services

---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org


Mime
View raw message