使用java通过spark从cassandra表中获取最新记录

SparkConf sparkConf = new SparkConf()
        .setAppName("Get Latest Records from Cassandra")
        .setMaster("spark://localhost:7077");

JavaSparkContext sparkContext = new JavaSparkContext(sparkConf);

SparkSession sparkSession = SparkSession.builder()
        .appName("Get Latest Records from Cassandra")
        .config("spark.cassandra.connection.host", "localhost")
        .config("spark.cassandra.connection.port", "9042")
        .getOrCreate();

DataFrameReader dataFrameReader = sparkSession.read()
        .format("org.apache.spark.sql.cassandra")
        .option("keyspace", "your_keyspace_name")
        .option("table", "your_table_name");
Dataset<Row> dataset = dataFrameReader.load();

Dataset<Row> latestRecords = dataset.orderBy(dataset.col("timestamp").desc()).limit(10);

latestRecords.write()
        .format("org.apache.spark.sql.cassandra")
        .option("keyspace", "your_keyspace_name")
        .option("table", "new_table_name")
        .save();