jp2007 · October 15, 2015 17:26 · Aug 15, 2014 · Aug 15, 2014 · Aug 15, 2014 · Aug 15, 2014
diff --git a/install_spark.md b/install_spark.md
@@ -13,17 +13,16 @@ brew install apache-spark
 Get the Spark Cassandra Connector
 ---------------------------------
 
-Create a directory for the connector and its support libs and cd into the directory:
+Clone the download script from Github Gist:
 
 ```
-mkdir connector
-cd connector
+git clone https://gist.github.com/b700fe70f0025a519171.git
 ```
 
-Clone the download script from Github Gist:
+Rename the cloned directory:
 
 ```
-git clone https://gist.github.com/b700fe70f0025a519171.git
+mv b700fe70f0025a519171 connector
 ```
 
 Run the script:
@@ -36,7 +35,7 @@ Start the Spark Master and a Worker
 -----------------------------------
 
 ```
-./usr/local/Cellar/apache-spark/sbin/start-all.sh
+./usr/local/Cellar/apache-spark/1.0.2/libexec/sbin/start-all.sh
 ```
 
 Testing the install
@@ -77,13 +76,13 @@ import org.apache.spark._
 
 val conf = new SparkConf()
 conf.set("spark.cassandra.connection.host", "127.0.0.1")
-conf.set("spark.home","/usr/local/Cellar/apache-spark/")
+conf.set("spark.home","/usr/local/Cellar/apache-spark/1.0.2/libexec")
 
 // You may not need these two settings if you haven't set up password authentication in Cassandra
 conf.set("spark.cassandra.auth.username", "cassandra")
 conf.set("spark.cassandra.auth.password", "cassandra")
 
-val sc = new SparkContext("spark://ip-10-0-0-192:7077", "Cassandra Connector Test", conf)
+val sc = new SparkContext("spark://localhost:7077", "Cassandra Connector Test", conf)
 sc.addJar("path/to/connector/cassandra-driver-core-2.0.3.jar")
 sc.addJar("path/to/connector/cassandra-thrift-2.0.9.jar")
 sc.addJar("path/to/connector/commons-codec-1.2.jar")

diff --git a/install_spark.md b/install_spark.md
@@ -32,6 +32,13 @@ Run the script:
 bash install_connector.sh
 ```
 
+Start the Spark Master and a Worker
+-----------------------------------
+
+```
+./usr/local/Cellar/apache-spark/sbin/start-all.sh
+```
+
 Testing the install
 -------------------
 

diff --git a/install_spark.md b/install_spark.md
@@ -1,5 +1,5 @@
-Install and Setup Spark for Cassandra on Max OS X
-=================================================
+Install, Setup, and Test Spark and Cassandra on Mac OS X
+========================================================
 
 This Gist assumes you already followed the instructions to [install Cassandra](https://gist.github.com/hkhamm/a9a2b45dd749e5d3b3ae), created a keyspace and table, and added some data.
 

diff --git a/install_spark.md b/install_spark.md
@@ -0,0 +1,111 @@
+Install and Setup Spark for Cassandra on Max OS X
+=================================================
+
+This Gist assumes you already followed the instructions to [install Cassandra](https://gist.github.com/hkhamm/a9a2b45dd749e5d3b3ae), created a keyspace and table, and added some data.
+
+Install Apache Spark
+--------------------
+
+```
+brew install apache-spark
+```
+
+Get the Spark Cassandra Connector
+---------------------------------
+
+Create a directory for the connector and its support libs and cd into the directory:
+
+```
+mkdir connector
+cd connector
+```
+
+Clone the download script from Github Gist:
+
+```
+git clone https://gist.github.com/b700fe70f0025a519171.git
+```
+
+Run the script:
+
+```
+bash install_connector.sh
+```
+
+Testing the install
+-------------------
+
+Make a note of the path to your connector directory. 
+
+Open the Spark Shell with the connector:
+
+
+```
+spark-shell --driver-class-path $(echo path/to/connector/*.jar | sed 's/ /:/g')
+```
+
+Wait for everything to load. Once it is finished, you'll see a scala prompt:
+
+```
+scala >
+```
+
+You'll need to stop the default SparkContext, since you'll create your own with the script.
+
+```
+scala > sc.stop
+```
+
+Once that is finished, get ready to paste the script in:
+
+```
+scala > :paste
+```
+
+Paste in this script, make sure to change the path to the connector and to change keyspace and table to the names of your keyspace and table:
+
+```
+import com.datastax.spark.connector._
+import org.apache.spark._
+
+val conf = new SparkConf()
+conf.set("spark.cassandra.connection.host", "127.0.0.1")
+conf.set("spark.home","/usr/local/Cellar/apache-spark/")
+
+// You may not need these two settings if you haven't set up password authentication in Cassandra
+conf.set("spark.cassandra.auth.username", "cassandra")
+conf.set("spark.cassandra.auth.password", "cassandra")
+
+val sc = new SparkContext("spark://ip-10-0-0-192:7077", "Cassandra Connector Test", conf)
+sc.addJar("path/to/connector/cassandra-driver-core-2.0.3.jar")
+sc.addJar("path/to/connector/cassandra-thrift-2.0.9.jar")
+sc.addJar("path/to/connector/commons-codec-1.2.jar")
+sc.addJar("path/to/connector/commons-lang3-3.1.jar")
+sc.addJar("path/to/connector/commons-logging-1.1.1.jar")
+sc.addJar("path/to/connector/guava-16.0.1.jar")
+sc.addJar("path/to/connector/httpclient-4.2.5.jar")
+sc.addJar("path/to/connector/httpcore-4.2.4.jar")
+sc.addJar("path/to/connector/joda-convert-1.6.jar")
+sc.addJar("path/to/connector/joda-time-2.3.jar")
+sc.addJar("path/to/connector/libthrift-0.9.1.jar")
+sc.addJar("path/to/connector/lz4-1.2.0.jar")
+sc.addJar("path/to/connector/metrics-core-3.0.2.jar")
+sc.addJar("path/to/connector/netty-3.9.0.Final.jar")
+sc.addJar("path/to/connector/slf4j-api-1.7.5.jar")
+sc.addJar("path/to/connector/snappy-java-1.0.5.jar")
+sc.addJar("path/to/connector/spark-cassandra-connector_2.10-1.0.0-rc2.jar")
+
+val table = sc.cassandraTable("keyspace", "table")
+table.count
+
+```
+
+Make sure you are on a new line after 'table.count', then hit ctl-D to get out of paste mode.
+
+If everything is set up correctly it should start running the script and at the end it will print out the number of rows in your Cassandra database.
+
+Thanks to Al Toby, Open Source Mechanic at DataStax, for the connector installation script and for the [blog post](http://planetcassandra.org/blog/installing-the-cassandra-spark-oss-stack/) that helped me write this guide.
+
+Have fun with Spark and Cassandra!
+
+
No results found