Spark与mongodb的结合

Mongodb

Mongodb的安装
实验环境：ubuntu16.04

安装：suso apt-get install mongodb
查看版本：mongo -version
启动和关闭mongodb
service mongodb start
service mongodb stop
shell命令使用mongodb:   mongo

Spark-MongoDB

MongoDB-Spark连机器官网

import com.mongodb.spark.MongoSpark;
import com.mongodb.spark.config.WriteConfig;

import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.api.java.function.Function;
import org.apache.spark.sql.SparkSession;
import org.bson.Document;
import static java.util.Arrays.asList;
import java.util.HashMap;
import java.util.Map;

public final class WriteToMongoDBWriteConfig {

  public static void main(final String[] args) throws InterruptedException {

    SparkSession spark = SparkSession.builder()
      .master("local")
      .appName("MongoSparkConnectorIntro")
      .config("spark.mongodb.input.uri", "mongodb://127.0.0.1/Spark.myCollection")
      .config("spark.mongodb.output.uri", "mongodb://127.0.0.1/Spark.myCollection")
      .getOrCreate();

    JavaSparkContext jsc = new JavaSparkContext(spark.sparkContext());

    // Create a custom WriteConfig
    Map<String, String> writeOverrides = new HashMap<String, String>();
    writeOverrides.put("collection", "spark");
    writeOverrides.put("writeConcern.w", "majority");
    WriteConfig writeConfig = WriteConfig.create(jsc).withOptions(writeOverrides);

    JavaRDD<Document> sparkDocuments = jsc.parallelize(asList(1, 2, 3, 4, 5, 6, 7, 8, 9, 10)).map
         (new Function<Integer, Document>() {
       public Document call(final Integer i) throws Exception {
               return Document.parse("{spark: " + i + "}");
             }
      });
          MongoSpark.save(sparkDocuments, writeConfig);

    jsc.close();

  }

}

.config("spark.mongodb.input.uri", "mongodb://127.0.0.1/Spark.myCollection")
.config("spark.mongodb.output.uri", "mongodb://127.0.0.1/Spark.myCollection")
      .getOrCreate();
此处的Spark是MongoDB的数据库名，myCollection类似MySQL的表名