spark-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From pwendell <...@git.apache.org>
Subject [GitHub] spark pull request: Example for cassandra CQL read/write from spar...
Date Thu, 06 Mar 2014 04:58:31 GMT
Github user pwendell commented on a diff in the pull request:

    https://github.com/apache/spark/pull/87#discussion_r10331703
  
    --- Diff: examples/src/main/scala/org/apache/spark/examples/CassandraCQLTest.scala ---
    @@ -0,0 +1,124 @@
    +/*
    + * 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.examples
    +
    +import org.apache.spark.SparkContext
    +import org.apache.spark.SparkContext._
    +import org.apache.hadoop.mapreduce.Job
    +import org.apache.cassandra.hadoop.ConfigHelper
    +import org.apache.cassandra.utils.ByteBufferUtil
    +import org.apache.cassandra.hadoop.cql3.CqlPagingInputFormat
    +import org.apache.cassandra.db.IColumn
    +import org.apache.cassandra.hadoop.cql3.CqlConfigHelper
    +import org.apache.cassandra.hadoop.cql3.CqlOutputFormat
    +import scala.collection.JavaConversions._
    +import java.nio.ByteBuffer
    +import scala.collection.mutable.ListBuffer
    +import scala.collection.immutable.Map
    +
    +/*
    +  Need to create following keyspace and column family in cassandra before running this
example
    +  Start CQL shell using ./bin/cqlsh and execute following commands
    +  CREATE KEYSPACE retail WITH replication = {'class': 'SimpleStrategy', 'replication_factor':
1};
    +  use retail;
    +
    +  CREATE TABLE salecount (product_id text,sale_count int, PRIMARY KEY (product_id));
    +  CREATE TABLE ordercf (user_id text,
    +    time timestamp,
    +    product_id text,
    +    quantity int,
    +    PRIMARY KEY (user_id, time));
    +  INSERT INTO ordercf (user_id, time, product_id, quantity) VALUES ('bob', 1385983646000,
'iphone', 1);
    +  INSERT INTO ordercf (user_id, time, product_id, quantity) VALUES ('tom', 1385983647000,
'samsung', 4);
    +  INSERT INTO ordercf (user_id, time, product_id, quantity) VALUES ('dora', 1385983648000,
'nokia', 2);
    +  INSERT INTO ordercf (user_id, time, product_id, quantity) VALUES ('charlie', 1385983649000,
'iphone', 2);
    +*/
    + 
    +/*
    + * This example demonstrates how to read and write to cassandra column family created
using CQL3
    + * using Spark.
    + * Parameters : <spark_master> <cassandra_node> <cassandra_port>
    + * Usage: ./bin/run-example org.apache.spark.examples.CassandraCQLTest local[2] localhost
9160
    + *
    + */
    +object CassandraCQLTest {
    +
    +  def main(args: Array[String]) {
    +    val sc = new SparkContext(args(0), "CQLTestApp", System.getenv("SPARK_HOME"), SparkContext.jarOfClass(this.getClass))
    +    val cHost: String = args(1)
    +    val cPort: String = args(2)
    +    val KeySpace = "retail"
    +    val InputColumnFamily = "ordercf"
    +    val OutputColumnFamily = "salecount"
    +
    +    val job = new Job()
    +    job.setInputFormatClass(classOf[CqlPagingInputFormat])
    +    ConfigHelper.setInputInitialAddress(job.getConfiguration(), cHost)
    +    ConfigHelper.setInputRpcPort(job.getConfiguration(), cPort)
    +    ConfigHelper.setInputColumnFamily(job.getConfiguration(), KeySpace, InputColumnFamily)
    +    ConfigHelper.setInputPartitioner(job.getConfiguration(), "Murmur3Partitioner")
    +    CqlConfigHelper.setInputCQLPageRowSize(job.getConfiguration(), "3");
    +
    +    // CqlConfigHelper.setInputWhereClauses(job.getConfiguration(), "user_id='bob'");
    +
    +    // An UPDATE writes one or more columns to a record in a Cassandra column family.

    +    val query:String = "UPDATE " + KeySpace + "." + OutputColumnFamily + " SET sale_count
= ? "
    --- End diff --
    
    Typically we don't declare the `String` type in this situation: 
    
       val query = "UPDATE " + KeySpace + "." + OutputColumnFamily + " SET sale_count = ?
"
    
    or with interpolation
    
       val query = s"UPDATE $KeySpace.$OutputColumnFamily SET sale_count = ? "
    



---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastructure@apache.org or file a JIRA ticket
with INFRA.
---

Mime
View raw message