使用Spark和Java对不同的Mongo集合进行读写

<dependency>
    <groupId>org.mongodb</groupId>
    <artifactId>mongo-java-driver</artifactId>
    <version>3.12.10</version>
</dependency>
<dependency>
    <groupId>org.mongodb.spark</groupId>
    <artifactId>mongo-spark-connector_2.12</artifactId>
    <version>3.0.1</version>
</dependency>

SparkSession spark = SparkSession.builder()
        .appName("MongoDB Example")
        .master("local[*]") // 设置Spark的master节点
        .config("spark.mongodb.input.uri", "mongodb://localhost/test.inputCollection") // 设置输入集合的URI
        .config("spark.mongodb.output.uri", "mongodb://localhost/test.outputCollection") // 设置输出集合的URI
        .getOrCreate();

Dataset<Row> inputDataset = spark.read().format("mongo").load();

Dataset<Row> processedDataset = inputDataset.filter("age > 30").groupBy("gender").agg(avg("salary"));

processedDataset.write().format("mongo").mode("overwrite").save();