langzi_0371的博客

package com.lzimport org.apache.spark.sql.SparkSessionimport org.elasticsearch.hadoop.cfg.ConfigurationOptionsimport scala.collection.Mapobject Es2Hive { def main(args: Array[String]): Unit = { val spark: SparkSession = SparkSession.builder()

CREATE external TABLE `mongodb_dingtalk.mongodb_test`(`companyName` string,`sources` array<struct<contact:string,contactJob:string,site:string,source:string,sourceHref:string>>)STORED BY 'com.mongodb.hadoop.hive.MongoStorageHandler'WITH SE

报错如下：Exception in thread "main" java.lang.StackOverflowError at java.util.regex.Pattern$Loop.match(Pattern.java:4779) at java.util.regex.Pattern$GroupTail.match(Pattern.java:4731) at java.util.regex.Pattern$Curly.match0(Pattern.java:4286) at java.util

原因是数据中有中文，而数据库表编码不支持，在hive导入mysql时设置编码集。drop table companynameandsource;create table companynameandsource( companyname text, source text)DEFAULT CHARSET=utf8;

记录一个数据拆分案例select id,userid,from_unixtime(cast(adddate/1000 as bigint),'yyyy-MM-dd') as adddate,from_unixtime(cast(updatedate/1000 as bigint),'yyyy-MM-dd') as updatedate,get_json_object(tag1,'$.id') as setting_id,-- get_json_object(tag1,'$.enable') as