14.3 Spark-SQL基于PostgreSQL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: 'org.postgresql', name: 'postgresql', version: '42.2.2'

SparkSession spark = SparkSession
        .builder()
        .appName("Java Spark SQL basic example")
//                .config("spark.some.config.option", "some-value")
        .getOrCreate();

Properties connectionProperties = new Properties();
connectionProperties.put("user", "busuanzi");
connectionProperties.put("password", "wxl123");

Dataset<Row> jdbcDF2 = spark.read()
        .jdbc("jdbc:postgresql://192.168.56.110:5432/busuanzidb", "public.top_projects", connectionProperties);

jdbcDF2.show();

myDF2.write()
        .mode(SaveMode.Append)
        .jdbc("jdbc:postgresql://192.168.56.110:5432/busuanzidb", "public.top_projects", connectionProperties);

spark.sql("SELECT * FROM onev r JOIN twov s ON r.username = s.username")
        .show();