14.4 Spark-SQL基于Cassandra数据分析编程实例

compile group: 'org.apache.spark', name: 'spark-core_2.11', version: '2.3.1'
compile group: 'org.apache.spark', name: 'spark-sql_2.11', version: '2.3.1'
compile group: 'com.datastax.spark', name: 'spark-cassandra-connector_2.11', version: '2.3.0'

SparkSession spark = SparkSession
        .builder()
        .appName("Java Spark SQL basic example")
//            .config("spark.some.config.option", "some-value")
        .config("spark.cassandra.connection.host", "192.168.56.110")
        .config("spark.cassandra.auth.username", "busuanzi")
        .config("spark.cassandra.auth.password", "busuanzi.org")
        .config("spark.cassandra.connection.port", "9042")
        .getOrCreate();

ds1.write()
        .format("org.apache.spark.sql.cassandra")
        .options(new HashMap<String, String>() {
            {
                put("keyspace", "busuanzi_org");
                put("table", "top_n_url");
            }
        }).mode("append").save();

Dataset<Row> ds = spark.read()
        .format("org.apache.spark.sql.cassandra")
        .options(new HashMap<String, String>(){
            {
                put("keyspace", "busuanzi_org");
                put("table", "top_n_url");
            }
        }).load();
ds.show();

ds.createOrReplaceTempView("dsv");

ds.select("username", "projects", "comment").distinct().show();