[scala] [streaming] WindowJoin scala example added

flink-examples/flink-scala-examples/src/main/scala/org/apache/flink/examples/scala/streaming/windowing/WindowJoin.scala

@@ -0,0 +1,72 @@
+/*
+ * 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.flink.examples.scala.streaming.windowing
+
+import org.apache.flink.api.scala._
+import org.apache.flink.api.scala.streaming.StreamExecutionEnvironment
+import org.apache.flink.streaming.api.function.source.SourceFunction
+import org.apache.flink.util.Collector
+import scala.util.Random
+
+object WindowJoin {
+
+  case class Name(id: Long, name: String)
+  case class Age(id: Long, age: Int)
+  case class Person(name: String, age: Long)
+
+  def main(args: Array[String]) {
+
+    val env = StreamExecutionEnvironment.getExecutionEnvironment
+
+    //Create streams for names and ages by mapping the inputs to the corresponding objects
+    val names = env.addSource(nameStream _).map(x => Name(x._1, x._2))
+    val ages = env.addSource(ageStream _).map(x => Age(x._1, x._2))
+
+    //Join the two input streams by id on the last second and create new Person objects
+    //containing both name and age
+    val joined =
+      names.join(ages).onWindow(1000)
+                      .where("id").equalTo("id") { (n, a) => Person(n.name, a.age) }
+
+    joined print
+
+    env.execute("WindowJoin")
+  }
+
+  //Stream source for generating (id, name) pairs
+  def nameStream(out: Collector[(Long, String)]) = {
+    val names = Array("tom", "jerry", "alice", "bob", "john", "grace")
+
+    for (i <- 1 to 10000) {
+      if (i % 100 == 0) Thread.sleep(1000) else {
+        out.collect((i, names(Random.nextInt(names.length))))
+      }
+    }
+  }
+
+  //Stream source for generating (id, age) pairs
+  def ageStream(out: Collector[(Long, Int)]) = {
+    for (i <- 1 to 10000) {
+      if (i % 100 == 0) Thread.sleep(1000) else {
+        out.collect((i, Random.nextInt(90)))
+      }
+    }
+  }
+
+}

flink-scala/src/main/scala/org/apache/flink/api/scala/streaming/StreamExecutionEnvironment.scala

@@ -161,9 +161,25 @@ class StreamExecutionEnvironment(javaEnv: JavaEnv) {
    */
   def addSource[T: ClassTag: TypeInformation](function: SourceFunction[T]): DataStream[T] = {
     Validate.notNull(function, "Function must not be null.")
+    ClosureCleaner.clean(function, true)
     val typeInfo = implicitly[TypeInformation[T]]
     new DataStream[T](javaEnv.addSource(function, typeInfo))
   }
+
+   /**
+   * Create a DataStream using a user defined source function for arbitrary
+   * source functionality.
+   *
+   */
+  def addSource[T: ClassTag: TypeInformation](function: Collector[T] => Unit): DataStream[T] = {
+    Validate.notNull(function, "Function must not be null.")
+    val sourceFunction = new SourceFunction[T] {
+      override def invoke(out: Collector[T]) {
+        function(out)
+      }
+    }
+    addSource(sourceFunction)
+  }
 
   /**
    * Triggers the program execution. The environment will execute all parts of