Spring Boot与Spark、Cassandra系统集成开发示例

CREATE KEYSPACE hfcb WITH REPLICATION = { 'class' : 'SimpleStrategy', 'replication_factor' : 3 };

CREATE TABLE person (
 id text PRIMARY KEY,
 first_name text,
 last_name text
);

insert into person (id,first_name,last_name) values('1','wang','yunfei');
insert into person (id,first_name,last_name) values('2','peng','chao');
insert into person (id,first_name,last_name) values('3','li','jian');
insert into person (id,first_name,last_name) values('4','zhang','jie');
insert into person (id,first_name,last_name) values('5','liang','wei');

cassandra-clientutil-3.0.2.jar
cassandra-driver-core-3.1.4.jar
guava-16.0.1.jar
cassandra-thrift-3.0.2.jar 
joda-convert-1.2.jar
joda-time-2.9.9.jar
libthrift-0.9.1.jar
spark-cassandra-connector_2.10-1.5.1.jar

SPARK_CLASSPATH=/opt/spark/managed-lib/*

<dependency>
   <groupId>com.datastax.spark</groupId>
   <artifactId>spark-cassandra-connector_2.10</artifactId>
   <version>1.5.1</version>
  </dependency>
  <dependency>
   <groupId>org.apache.spark</groupId>
   <artifactId>spark-core_2.10</artifactId>
   <version>1.5.1</version>
  </dependency>
  <dependency>
   <groupId>org.apache.spark</groupId>
   <artifactId>spark-sql_2.10</artifactId>
   <version>1.5.1</version>
  </dependency>

spark.master: spark://master:7077
cassandra.host: 192.168.1.140
cassandra.keyspace: hfcb

@Configuration
public class SparkCassandraConfig {
 @Value("${spark.master}")
 String sparkMasterUrl;
 @Value("${cassandra.host}")
 String cassandraHost;
 @Value("${cassandra.keyspace}")
 String cassandraKeyspace;
 @Bean
 public JavaSparkContext javaSparkContext(){
  SparkConf conf = new SparkConf(true)
    .set("spark.cassandra.connection.host", cassandraHost)
//    .set("spark.cassandra.auth.username", "cassandra")
//    .set("spark.cassandra.auth.password", "cassandra")
    .set("spark.submit.deployMode", "client");
  JavaSparkContext context = new JavaSparkContext(sparkMasterUrl, "SparkDemo", conf);
  return context;
 }
 @Bean
 public CassandraSQLContext sqlContext(){
  CassandraSQLContext cassandraSQLContext = new CassandraSQLContext(javaSparkContext().sc());
  cassandraSQLContext.setKeyspace(cassandraKeyspace);
  return cassandraSQLContext;
 }
 }

@Repository
public class PersonRepository {
 @Autowired
 CassandraSQLContext cassandraSQLContext;
 public Long countPerson(){
  DataFrame people = cassandraSQLContext.sql("select * from person order by id");
  return people.count();
 }
}