[BAHIR-37] Publish Bahir 2.0.0 documentation
Publish Bahir 2.0.0 documentation and update current documentation
to use artifacts from master : 2.1.0-SNAPSHOT
diff --git a/site/_data/navigation.yml b/site/_data/navigation.yml
index 16ccd13..037c18c 100644
--- a/site/_data/navigation.yml
+++ b/site/_data/navigation.yml
@@ -47,8 +47,10 @@
- title: Documentation
subcategories:
- - title: Current
+ - title: Bahir Spark Extensions - Current
url: /docs/spark/current/documentation
+ - title: Bahir Spark Extensions - 2.0.0
+ url: /docs/spark/2.0.0/documentation
- title: GitHub
url: https://github.com/apache/bahir
diff --git a/site/_data/project.yml b/site/_data/project.yml
index 422f40d..1de896a 100644
--- a/site/_data/project.yml
+++ b/site/_data/project.yml
@@ -22,8 +22,8 @@
description: Apache Bahir provides extensions to distributed analytic platforms such as Apache Spark.
download: /download
-latest_release: 2.0.0-preview
-latest_release_date: 07/01/2016
+latest_release: 2.0.0
+latest_release_date: 08/11/2016
dev_list: dev@bahir.apache.org
dev_list_subscribe: dev-subscribe@bahir.apache.org
diff --git a/site/docs/spark/2.0.0/documentation.md b/site/docs/spark/2.0.0/documentation.md
new file mode 100644
index 0000000..38148e9
--- /dev/null
+++ b/site/docs/spark/2.0.0/documentation.md
@@ -0,0 +1,46 @@
+---
+layout: page
+title: Extensions for Apache Spark
+description: Extensions for Apache Spark
+group: nav-right
+---
+<!--
+{% comment %}
+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.
+{% endcomment %}
+-->
+
+{% include JB/setup %}
+
+### Apache Bahir Extensions for Apache Spark
+
+<br/>
+
+#### Structured Streaming Data Sources
+
+[MQTT data source](../spark-sql-streaming-mqtt)
+
+<br/>
+
+#### Discretized Streams (DStreams) Connectors
+
+[Akka connector](../spark-streaming-akka)
+
+[MQTT connector](../spark-streaming-mqtt)
+
+[Twitter connector](../spark-streaming-twitter)
+
+[ZeroMQ connector](../spark-streaming-zeromq)
\ No newline at end of file
diff --git a/site/docs/spark/2.0.0/spark-sql-streaming-mqtt.md b/site/docs/spark/2.0.0/spark-sql-streaming-mqtt.md
new file mode 100644
index 0000000..6f512a1
--- /dev/null
+++ b/site/docs/spark/2.0.0/spark-sql-streaming-mqtt.md
@@ -0,0 +1,131 @@
+---
+layout: page
+title: Spark Structured Streaming MQTT
+description: Spark Structured Streaming MQTT
+group: nav-right
+---
+<!--
+{% comment %}
+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.
+{% endcomment %}
+-->
+
+{% include JB/setup %}
+
+A library for reading data from MQTT Servers using Spark SQL Streaming ( or Structured streaming.).
+
+## Linking
+
+Using SBT:
+
+ libraryDependencies += "org.apache.bahir" %% "spark-sql-streaming-mqtt" % "2.0.0"
+
+Using Maven:
+
+ <dependency>
+ <groupId>org.apache.bahir</groupId>
+ <artifactId>spark-sql-streaming-mqtt_2.11</artifactId>
+ <version>2.0.0</version>
+ </dependency>
+
+This library can also be added to Spark jobs launched through `spark-shell` or `spark-submit` by using the `--packages` command line option.
+For example, to include it when starting the spark shell:
+
+ $ bin/spark-shell --packages org.apache.bahir:spark-sql-streaming-mqtt_2.11:2.0.0
+
+Unlike using `--jars`, using `--packages` ensures that this library and its dependencies will be added to the classpath.
+The `--packages` argument can also be used with `bin/spark-submit`.
+
+This library is compiled for Scala 2.11 only, and intends to support Spark 2.0 onwards.
+
+## Examples
+
+A SQL Stream can be created with data streams received through MQTT Server using,
+
+ sqlContext.readStream
+ .format("org.apache.bahir.sql.streaming.mqtt.MQTTStreamSourceProvider")
+ .option("topic", "mytopic")
+ .load("tcp://localhost:1883")
+
+## Enable recovering from failures.
+
+Setting values for option `localStorage` and `clientId` helps in recovering in case of a restart, by restoring the state where it left off before the shutdown.
+
+ sqlContext.readStream
+ .format("org.apache.bahir.sql.streaming.mqtt.MQTTStreamSourceProvider")
+ .option("topic", "mytopic")
+ .option("localStorage", "/path/to/localdir")
+ .option("clientId", "some-client-id")
+ .load("tcp://localhost:1883")
+
+### Scala API
+
+An example, for scala API to count words from incoming message stream.
+
+ // Create DataFrame representing the stream of input lines from connection to mqtt server
+ val lines = spark.readStream
+ .format("org.apache.bahir.sql.streaming.mqtt.MQTTStreamSourceProvider")
+ .option("topic", topic)
+ .load(brokerUrl).as[(String, Timestamp)]
+
+ // Split the lines into words
+ val words = lines.map(_._1).flatMap(_.split(" "))
+
+ // Generate running word count
+ val wordCounts = words.groupBy("value").count()
+
+ // Start running the query that prints the running counts to the console
+ val query = wordCounts.writeStream
+ .outputMode("complete")
+ .format("console")
+ .start()
+
+ query.awaitTermination()
+
+Please see `MQTTStreamWordCount.scala` for full example.
+
+### Java API
+
+An example, for Java API to count words from incoming message stream.
+
+ // Create DataFrame representing the stream of input lines from connection to mqtt server.
+ Dataset<String> lines = spark
+ .readStream()
+ .format("org.apache.bahir.sql.streaming.mqtt.MQTTStreamSourceProvider")
+ .option("topic", topic)
+ .load(brokerUrl).select("value").as(Encoders.STRING());
+
+ // Split the lines into words
+ Dataset<String> words = lines.flatMap(new FlatMapFunction<String, String>() {
+ @Override
+ public Iterator<String> call(String x) {
+ return Arrays.asList(x.split(" ")).iterator();
+ }
+ }, Encoders.STRING());
+
+ // Generate running word count
+ Dataset<Row> wordCounts = words.groupBy("value").count();
+
+ // Start running the query that prints the running counts to the console
+ StreamingQuery query = wordCounts.writeStream()
+ .outputMode("complete")
+ .format("console")
+ .start();
+
+ query.awaitTermination();
+
+Please see `JavaMQTTStreamWordCount.java` for full example.
+
diff --git a/site/docs/spark/2.0.0/spark-streaming-akka.md b/site/docs/spark/2.0.0/spark-streaming-akka.md
new file mode 100644
index 0000000..9de0688
--- /dev/null
+++ b/site/docs/spark/2.0.0/spark-streaming-akka.md
@@ -0,0 +1,89 @@
+---
+layout: page
+title: Spark Streaming Akka
+description: Spark Streaming Akka
+group: nav-right
+---
+<!--
+{% comment %}
+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.
+{% endcomment %}
+-->
+
+{% include JB/setup %}
+
+A library for reading data from Akka Actors using Spark Streaming.
+
+## Linking
+
+Using SBT:
+
+ libraryDependencies += "org.apache.bahir" %% "spark-streaming-akka" % "2.0.0"
+
+Using Maven:
+
+ <dependency>
+ <groupId>org.apache.bahir</groupId>
+ <artifactId>spark-streaming-akka_2.11</artifactId>
+ <version>2.0.0</version>
+ </dependency>
+
+This library can also be added to Spark jobs launched through `spark-shell` or `spark-submit` by using the `--packages` command line option.
+For example, to include it when starting the spark shell:
+
+ $ bin/spark-shell --packages org.apache.bahir:spark-streaming_akka_2.11:2.0.0
+
+Unlike using `--jars`, using `--packages` ensures that this library and its dependencies will be added to the classpath.
+The `--packages` argument can also be used with `bin/spark-submit`.
+
+This library is cross-published for Scala 2.10 and Scala 2.11, so users should replace the proper Scala version (2.10 or 2.11) in the commands listed above.
+
+## Examples
+
+DStreams can be created with data streams received through Akka actors by using `AkkaUtils.createStream(ssc, actorProps, actor-name)`.
+
+### Scala API
+
+You need to extend `ActorReceiver` so as to store received data into Spark using `store(...)` methods. The supervisor strategy of
+this actor can be configured to handle failures, etc.
+
+ class CustomActor extends ActorReceiver {
+ def receive = {
+ case data: String => store(data)
+ }
+ }
+
+ // A new input stream can be created with this custom actor as
+ val ssc: StreamingContext = ...
+ val lines = AkkaUtils.createStream[String](ssc, Props[CustomActor](), "CustomReceiver")
+
+### Java API
+
+You need to extend `JavaActorReceiver` so as to store received data into Spark using `store(...)` methods. The supervisor strategy of
+this actor can be configured to handle failures, etc.
+
+ class CustomActor extends JavaActorReceiver {
+ @Override
+ public void onReceive(Object msg) throws Exception {
+ store((String) msg);
+ }
+ }
+
+ // A new input stream can be created with this custom actor as
+ JavaStreamingContext jssc = ...;
+ JavaDStream<String> lines = AkkaUtils.<String>createStream(jssc, Props.create(CustomActor.class), "CustomReceiver");
+
+See end-to-end examples at [Akka Examples](https://github.com/apache/bahir/tree/master/streaming-akka/examples)
diff --git a/site/docs/spark/2.0.0/spark-streaming-mqtt.md b/site/docs/spark/2.0.0/spark-streaming-mqtt.md
new file mode 100644
index 0000000..886bacb
--- /dev/null
+++ b/site/docs/spark/2.0.0/spark-streaming-mqtt.md
@@ -0,0 +1,71 @@
+---
+layout: page
+title: Spark Structured Streaming MQTT
+description: Spark Structured Streaming MQTT
+group: nav-right
+---
+<!--
+{% comment %}
+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.
+{% endcomment %}
+-->
+
+{% include JB/setup %}
+
+
+[MQTT](http://mqtt.org/) is MQTT is a machine-to-machine (M2M)/"Internet of Things" connectivity protocol. It was designed as an extremely lightweight publish/subscribe messaging transport. It is useful for connections with remote locations where a small code footprint is required and/or network bandwidth is at a premium.
+
+## Linking
+
+Using SBT:
+
+ libraryDependencies += "org.apache.bahir" %% "spark-streaming-mqtt" % "2.0.0"
+
+Using Maven:
+
+ <dependency>
+ <groupId>org.apache.bahir</groupId>
+ <artifactId>spark-streaming-mqtt_2.11</artifactId>
+ <version>2.0.0</version>
+ </dependency>
+
+This library can also be added to Spark jobs launched through `spark-shell` or `spark-submit` by using the `--packages` command line option.
+For example, to include it when starting the spark shell:
+
+ $ bin/spark-shell --packages org.apache.bahir:spark-streaming_mqtt_2.11:2.0.0
+
+Unlike using `--jars`, using `--packages` ensures that this library and its dependencies will be added to the classpath.
+The `--packages` argument can also be used with `bin/spark-submit`.
+
+This library is cross-published for Scala 2.10 and Scala 2.11, so users should replace the proper Scala version (2.10 or 2.11) in the commands listed above.
+
+## Examples
+
+### Scala API
+
+You need to extend `ActorReceiver` so as to store received data into Spark using `store(...)` methods. The supervisor strategy of
+this actor can be configured to handle failures, etc.
+
+ val lines = MQTTUtils.createStream(ssc, brokerUrl, topic)
+
+### Java API
+
+You need to extend `JavaActorReceiver` so as to store received data into Spark using `store(...)` methods. The supervisor strategy of
+this actor can be configured to handle failures, etc.
+
+ JavaDStream<String> lines = MQTTUtils.createStream(jssc, brokerUrl, topic);
+
+See end-to-end examples at [MQTT Examples](https://github.com/apache/bahir/tree/master/streaming-mqtt/examples)
\ No newline at end of file
diff --git a/site/docs/spark/2.0.0/spark-streaming-twitter.md b/site/docs/spark/2.0.0/spark-streaming-twitter.md
new file mode 100644
index 0000000..f04928a
--- /dev/null
+++ b/site/docs/spark/2.0.0/spark-streaming-twitter.md
@@ -0,0 +1,74 @@
+---
+layout: page
+title: Spark Streaming Twitter
+description: Spark Streaming Twitter
+group: nav-right
+---
+<!--
+{% comment %}
+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.
+{% endcomment %}
+-->
+
+{% include JB/setup %}
+
+A library for reading social data from [twitter](http://twitter.com/) using Spark Streaming.
+
+## Linking
+
+Using SBT:
+
+ libraryDependencies += "org.apache.bahir" %% "spark-streaming-twitter" % "2.0.0"
+
+Using Maven:
+
+ <dependency>
+ <groupId>org.apache.bahir</groupId>
+ <artifactId>spark-streaming-twitter_2.11</artifactId>
+ <version>2.0.0</version>
+ </dependency>
+
+This library can also be added to Spark jobs launched through `spark-shell` or `spark-submit` by using the `--packages` command line option.
+For example, to include it when starting the spark shell:
+
+ $ bin/spark-shell --packages org.apache.bahir:spark-streaming_twitter_2.11:2.0.0
+
+Unlike using `--jars`, using `--packages` ensures that this library and its dependencies will be added to the classpath.
+The `--packages` argument can also be used with `bin/spark-submit`.
+
+This library is cross-published for Scala 2.10 and Scala 2.11, so users should replace the proper Scala version (2.10 or 2.11) in the commands listed above.
+
+
+## Examples
+
+`TwitterUtils` uses Twitter4j to get the public stream of tweets using [Twitter's Streaming API](https://dev.twitter.com/docs/streaming-apis). Authentication information
+can be provided by any of the [methods](http://twitter4j.org/en/configuration.html) supported by Twitter4J library. You can import the `TwitterUtils` class and create a DStream with `TwitterUtils.createStream` as shown below.
+
+### Scala API
+
+ import org.apache.spark.streaming.twitter._
+
+ TwitterUtils.createStream(ssc, None)
+
+### Java API
+
+ import org.apache.spark.streaming.twitter.*;
+
+ TwitterUtils.createStream(jssc);
+
+
+You can also either get the public stream, or get the filtered stream based on keywords.
+See end-to-end examples at [Twitter Examples](https://github.com/apache/bahir/tree/master/streaming-twitter/examples)
\ No newline at end of file
diff --git a/site/docs/spark/2.0.0/spark-streaming-zeromq.md b/site/docs/spark/2.0.0/spark-streaming-zeromq.md
new file mode 100644
index 0000000..9c67a79
--- /dev/null
+++ b/site/docs/spark/2.0.0/spark-streaming-zeromq.md
@@ -0,0 +1,65 @@
+---
+layout: page
+title: Spark Streaming ZeroMQ
+description: Spark Streaming ZeroMQ
+group: nav-right
+---
+<!--
+{% comment %}
+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.
+{% endcomment %}
+-->
+
+{% include JB/setup %}
+
+A library for reading data from [ZeroMQ](http://zeromq.org/) using Spark Streaming.
+
+## Linking
+
+Using SBT:
+
+ libraryDependencies += "org.apache.bahir" %% "spark-streaming-zeromq" % "2.0.0"
+
+Using Maven:
+
+ <dependency>
+ <groupId>org.apache.bahir</groupId>
+ <artifactId>spark-streaming-zeromq_2.11</artifactId>
+ <version>2.0.0</version>
+ </dependency>
+
+This library can also be added to Spark jobs launched through `spark-shell` or `spark-submit` by using the `--packages` command line option.
+For example, to include it when starting the spark shell:
+
+ $ bin/spark-shell --packages org.apache.bahir:spark-streaming_zeromq_2.11:2.0.0
+
+Unlike using `--jars`, using `--packages` ensures that this library and its dependencies will be added to the classpath.
+The `--packages` argument can also be used with `bin/spark-submit`.
+
+This library is cross-published for Scala 2.10 and Scala 2.11, so users should replace the proper Scala version (2.10 or 2.11) in the commands listed above.
+
+## Examples
+
+
+### Scala API
+
+ val lines = ZeroMQUtils.createStream(ssc, ...)
+
+### Java API
+
+ JavaDStream<String> lines = ZeroMQUtils.createStream(jssc, ...);
+
+See end-to-end examples at [ZeroMQ Examples](https://github.com/apache/bahir/tree/master/streaming-zeromq/examples)
\ No newline at end of file
diff --git a/site/docs/spark/current/documentation.md b/site/docs/spark/current/documentation.md
index 16b6527..38148e9 100644
--- a/site/docs/spark/current/documentation.md
+++ b/site/docs/spark/current/documentation.md
@@ -31,16 +31,16 @@
#### Structured Streaming Data Sources
-[MQTT data source](/docs/spark/current/spark-sql-streaming-mqtt)
+[MQTT data source](../spark-sql-streaming-mqtt)
<br/>
#### Discretized Streams (DStreams) Connectors
-[Akka connector](/docs/spark/current/spark-streaming-akka)
+[Akka connector](../spark-streaming-akka)
-[MQTT connector](/docs/spark/current/spark-streaming-mqtt)
+[MQTT connector](../spark-streaming-mqtt)
-[Twitter connector](/docs/spark/current/spark-streaming-twitter)
+[Twitter connector](../spark-streaming-twitter)
-[ZeroMQ connector](/docs/spark/current/spark-streaming-zeromq)
\ No newline at end of file
+[ZeroMQ connector](../spark-streaming-zeromq)
\ No newline at end of file
