spark 连接 hive 线下与集群运行

spark连接hive本来就是很简单的事情，但是因为各种环境冲突，搞了半天，下面是scala代码实现(本地测试时最好不要取当天的数据，容易触发集群)

package com.features.dl

/**
  * @author Supeihuang
  * @date 2020/2/21
  * @description file description
  */
object HiveT {
  def main(args: Array[String]): Unit = {

    import org.apache.spark.sql.SparkSession
    val sparkBuilder = SparkSession.builder()
    val sparkSession = sparkBuilder.appName("Hive Test").enableHiveSupport().getOrCreate()
    val df = sparkSession.sql("select app_id from recommend_readtime_log where dt='20200221' limit 100")
    df.show()
  }
}

仅仅有代码还是不够的还缺少了资源文件hive-site.xml，根据自己的集群进行配置。部分集群配置如下：

<?xml version="1.0" encoding="UTF-8"?>

<!--Autogenerated by Cloudera Manager-->
<configuration>
  <property>
    <name>hive.metastore.uris</name>
    <value>thrift://n2.hdfs2.meiyoucloud.com:9083</value>
  </property>
  <property>
    <name>hive.metastore.client.socket.timeout</name>
    <value>300</value>
  </property>
  <property>
    <name>hive.metastore.warehouse.dir</name>
    <value>/user/hive/warehouse</value>
  </property>
  <property>
    <name>hive.warehouse.subdir.inherit.perms</name>
    <value>true</value>
  </property>
  <property>
    <name>hive.auto.convert.join</name>
    <value>true</value>
  </property>
  <property>
    <name>hive.auto.convert.join.noconditionaltask.size</name>
    <value>20971520</value>
  </property>
  <property>
    <name>hive.optimize.bucketmapjoin.sortedmerge</name>
    <value>false</value>
  </property>
  <property>
    <name>hive.smbjoin.cache.rows</name>
    <value>10000</value>
  </property>
  <property>
    <name>hive.server2.logging.operation.enabled</name>
    <value>true</value>
  </property>
  <property>
    <name>hive.server2.logging.operation.log.location</name>
    <value>/var/log/hive/operation_logs</value>
  </property>
  <property>
    <name>mapred.reduce.tasks</name>
    <value>-1</value>
  </property>
  <property>
    <name>hive.exec.reducers.bytes.per.reducer</name>
    <value>67108864</value>
  </property>
  <property>
    <name>hive.exec.copyfile.maxsize</name>
    <value>33554432</value>
  </property>
  <property>
    <name>hive.exec.reducers.max</name>
    <value>1099</value>
  </property>
  <property>
    <name>hive.vectorized.groupby.checkinterval</name>
    <value>4096</value>
  </property>
  <property>
    <name>hive.vectorized.groupby.flush.percent</name>
    <value>0.1</value>
  </property>
  <property>
    <name>hive.compute.query.using.stats</name>
    <value>false</value>
  </property>
  <property>
    <name>hive.vectorized.execution.enabled</name>
    <value>true</value>
  </property>
  <property>
    <name>hive.vectorized.execution.reduce.enabled</name>
    <value>false</value>
  </property>
  <property>
    <name>hive.merge.mapfiles</name>
    <value>true</value>
  </property>
  <property>
    <name>hive.merge.mapredfiles</name>
    <value>false</value>
  </property>
  <property>
    <name>hive.cbo.enable</name>
    <value>false</value>
  </property>
  <property>
    <name>hive.fetch.task.conversion</name>
    <value>minimal</value>
  </property>
  <property>
    <name>hive.fetch.task.conversion.threshold</name>
    <value>268435456</value>
  </property>
  <property>
    <name>hive.limit.pushdown.memory.usage</name>
    <value>0.1</value>
  </property>
  <property>
    <name>hive.merge.sparkfiles</name>
    <value>true</value>
  </property>
  <property>
    <name>hive.merge.smallfiles.avgsize</name>
    <value>16777216</value>
  </property>
  <property>
    <name>hive.merge.size.per.task</name>
    <value>268435456</value>
  </property>
  <property>
    <name>hive.optimize.reducededuplication</name>
    <value>true</value>
  </property>
  <property>
    <name>hive.optimize.reducededuplication.min.reducer</name>
    <value>4</value>
  </property>
  <property>
    <name>hive.map.aggr</name>
    <value>true</value>
  </property>
  <property>
    <name>hive.map.aggr.hash.percentmemory</name>
    <value>0.5</value>
  </property>
  <property>
    <name>hive.optimi