通过spark将数据存储到elasticsearch
maven依赖<dependency><groupId>org.elasticsearch</groupId><artifactId>ela...
·
maven依赖
<dependency>
<groupId>org.elasticsearch</groupId>
<artifactId>elasticsearch-spark-20_2.11</artifactId>
<version>6.6.0</version>
</dependency>
package hgs.spark.es
import org.apache.spark.SparkConf
import org.apache.spark.SparkContext
import org.apache.spark.SparkContext._
import org.elasticsearch.spark._
import org.apache.spark.sql.SQLContext
object ViaSparkLoadDataToES {
def main(args: Array[String]): Unit = {
val conf = new SparkConf().setAppName("toEs").setMaster("local")
conf.set("es.resource", "mtest/IT")
conf.set("es.nodes", "bigdata00,bigdata01")
conf.set("es.port", "9200")
val context = new SparkContext(conf)
val sqlContext = new SQLContext(context)
import sqlContext.implicits._
val rdd = context.textFile( "d:\\person",1)
//val jsonrddDF = sqlContext.read.json(rdd)
rdd.saveJsonToEs("mtest/IT")
context.stop()
}
}
来自 “ ITPUB博客 ” ,链接:http://blog.itpub.net/31506529/viewspace-2637249/,如需转载,请注明出处,否则将追究法律责任。
转载于:http://blog.itpub.net/31506529/viewspace-2637249/
DAMO开发者矩阵,由阿里巴巴达摩院和中国互联网协会联合发起,致力于探讨最前沿的技术趋势与应用成果,搭建高质量的交流与分享平台,推动技术创新与产业应用链接,围绕“人工智能与新型计算”构建开放共享的开发者生态。
更多推荐


所有评论(0)