1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
|
/*
* 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.
*/
// scalastyle:off println
package org.apache.spark.examples
import java.nio.ByteBuffer
import java.util.Collections
import org.apache.cassandra.hadoop.ConfigHelper
import org.apache.cassandra.hadoop.cql3.CqlConfigHelper
import org.apache.cassandra.hadoop.cql3.CqlOutputFormat
import org.apache.cassandra.hadoop.cql3.CqlPagingInputFormat
import org.apache.cassandra.utils.ByteBufferUtil
import org.apache.hadoop.mapreduce.Job
import org.apache.spark.{SparkConf, SparkContext}
/*
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 (prod_id text, sale_count int, PRIMARY KEY (prod_id));
CREATE TABLE ordercf (user_id text,
time timestamp,
prod_id text,
quantity int,
PRIMARY KEY (user_id, time));
INSERT INTO ordercf (user_id,
time,
prod_id,
quantity) VALUES ('bob', 1385983646000, 'iphone', 1);
INSERT INTO ordercf (user_id,
time,
prod_id,
quantity) VALUES ('tom', 1385983647000, 'samsung', 4);
INSERT INTO ordercf (user_id,
time,
prod_id,
quantity) VALUES ('dora', 1385983648000, 'nokia', 2);
INSERT INTO ordercf (user_id,
time,
prod_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 : <cassandra_node> <cassandra_port>
* Usage: ./bin/spark-submit examples.jar \
* --class org.apache.spark.examples.CassandraCQLTest localhost 9160
*/
object CassandraCQLTest {
def main(args: Array[String]) {
val sparkConf = new SparkConf().setAppName("CQLTestApp")
val sc = new SparkContext(sparkConf)
val cHost: String = args(0)
val cPort: String = args(1)
val KeySpace = "retail"
val InputColumnFamily = "ordercf"
val OutputColumnFamily = "salecount"
val job = Job.getInstance()
job.setInputFormatClass(classOf[CqlPagingInputFormat])
val configuration = job.getConfiguration
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 = "UPDATE " + KeySpace + "." + OutputColumnFamily + " SET sale_count = ? "
CqlConfigHelper.setOutputCql(job.getConfiguration(), query)
job.setOutputFormatClass(classOf[CqlOutputFormat])
ConfigHelper.setOutputColumnFamily(job.getConfiguration(), KeySpace, OutputColumnFamily)
ConfigHelper.setOutputInitialAddress(job.getConfiguration(), cHost)
ConfigHelper.setOutputRpcPort(job.getConfiguration(), cPort)
ConfigHelper.setOutputPartitioner(job.getConfiguration(), "Murmur3Partitioner")
val casRdd = sc.newAPIHadoopRDD(job.getConfiguration(),
classOf[CqlPagingInputFormat],
classOf[java.util.Map[String, ByteBuffer]],
classOf[java.util.Map[String, ByteBuffer]])
println("Count: " + casRdd.count)
val productSaleRDD = casRdd.map {
case (key, value) =>
(ByteBufferUtil.string(value.get("prod_id")), ByteBufferUtil.toInt(value.get("quantity")))
}
val aggregatedRDD = productSaleRDD.reduceByKey(_ + _)
aggregatedRDD.collect().foreach {
case (productId, saleCount) => println(productId + ":" + saleCount)
}
val casoutputCF = aggregatedRDD.map {
case (productId, saleCount) =>
val outKey = Collections.singletonMap("prod_id", ByteBufferUtil.bytes(productId))
val outVal = Collections.singletonList(ByteBufferUtil.bytes(saleCount))
(outKey, outVal)
}
casoutputCF.saveAsNewAPIHadoopFile(
KeySpace,
classOf[java.util.Map[String, ByteBuffer]],
classOf[java.util.List[ByteBuffer]],
classOf[CqlOutputFormat],
job.getConfiguration()
)
sc.stop()
}
}
// scalastyle:on println
|
