spark.sql操作hive報錯怎么辦

這篇文章主要介紹spark.sql操作hive報錯怎么辦，文中介紹的非常詳細，具有一定的參考價值，感興趣的小伙伴們一定要看完！

下面報錯只存在spark.sql操作hive，而使用hive終端不報錯

只需將hive的lib目錄下 hive-hcatalog-core-2.3.4.jar 拷貝到spark的/spark/jars/ 下，重新初始化spark即可

sqlDF = oa.spark.sql("select * from user_action limit 2")
sqlDF.show()
---------------------------------------------------------------------------
Py4JJavaError                             Traceback (most recent call last)
<ipython-input-54-202cba0e658f> in <module>
      1 sqlDF = oa.spark.sql("select * from user_action limit 2")
----> 2 sqlDF.show()

~/bigdata/spark/python/pyspark/sql/dataframe.py in show(self, n, truncate)
    334         """
    335         if isinstance(truncate, bool) and truncate:
--> 336             print(self._jdf.showString(n, 20))
    337         else:
    338             print(self._jdf.showString(n, int(truncate)))

~/bigdata/spark/python/lib/py4j-0.10.7-src.zip/py4j/java_gateway.py in __call__(self, *args)
   1255         answer = self.gateway_client.send_command(command)
   1256         return_value = get_return_value(
-> 1257             answer, self.gateway_client, self.target_id, self.name)
   1258 
   1259         for temp_arg in temp_args:

~/bigdata/spark/python/pyspark/sql/utils.py in deco(*a, **kw)
     61     def deco(*a, **kw):
     62         try:
---> 63             return f(*a, **kw)
     64         except py4j.protocol.Py4JJavaError as e:
     65             s = e.java_exception.toString()

~/bigdata/spark/python/lib/py4j-0.10.7-src.zip/py4j/protocol.py in get_return_value(answer, gateway_client, target_id, name)
    326                 raise Py4JJavaError(
    327                     "An error occurred while calling {0}{1}{2}.\n".
--> 328                     format(target_id, ".", name), value)
    329             else:
    330                 raise Py4JError(

Py4JJavaError: An error occurred while calling o1022.showString.
: java.lang.RuntimeException: java.lang.ClassNotFoundException: org.apache.hive.hcatalog.data.JsonSerDe
    at org.apache.hadoop.hive.ql.plan.TableDesc.getDeserializerClass(TableDesc.java:74)
    at org.apache.spark.sql.hive.execution.HiveTableScanExec.addColumnMetadataToConf(HiveTableScanExec.scala:121)
    at org.apache.spark.sql.hive.execution.HiveTableScanExec.hadoopConf$lzycompute(HiveTableScanExec.scala:99)
    at org.apache.spark.sql.hive.execution.HiveTableScanExec.hadoopConf(HiveTableScanExec.scala:96)
    at org.apache.spark.sql.hive.execution.HiveTableScanExec.org$apache$spark$sql$hive$execution$HiveTableScanExec$$hadoopReader$lzycompute(HiveTableScanExec.scala:108)
    at org.apache.spark.sql.hive.execution.HiveTableScanExec.org$apache$spark$sql$hive$execution$HiveTableScanExec$$hadoopReader(HiveTableScanExec.scala:103)
    at org.apache.spark.sql.hive.execution.HiveTableScanExec$$anonfun$11.apply(HiveTableScanExec.scala:192)
    at org.apache.spark.sql.hive.execution.HiveTableScanExec$$anonfun$11.apply(HiveTableScanExec.scala:192)
    at org.apache.spark.util.Utils$.withDummyCallSite(Utils.scala:2475)
    at org.apache.spark.sql.hive.execution.HiveTableScanExec.doExecute(HiveTableScanExec.scala:191)
    at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:117)
    at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:117)
    at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:138)
    at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
    at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:135)
    at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:116)
    at org.apache.spark.sql.execution.SparkPlan.getByteArrayRdd(SparkPlan.scala:228)
    at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:311)
    at org.apache.spark.sql.execution.CollectLimitExec.executeCollect(limit.scala:38)
    at org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$collectFromPlan(Dataset.scala:2865)
    at org.apache.spark.sql.Dataset$$anonfun$head$1.apply(Dataset.scala:2154)
    at org.apache.spark.sql.Dataset$$anonfun$head$1.apply(Dataset.scala:2154)
    at org.apache.spark.sql.Dataset$$anonfun$55.apply(Dataset.scala:2846)
    at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:65)
    at org.apache.spark.sql.Dataset.withAction(Dataset.scala:2845)
    at org.apache.spark.sql.Dataset.head(Dataset.scala:2154)
    at org.apache.spark.sql.Dataset.take(Dataset.scala:2367)
    at org.apache.spark.sql.Dataset.showString(Dataset.scala:241)
    at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
    at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
    at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
    at java.lang.reflect.Method.invoke(Method.java:498)
    at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)
    at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
    at py4j.Gateway.invoke(Gateway.java:282)
    at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
    at py4j.commands.CallCommand.execute(CallCommand.java:79)
    at py4j.GatewayConnection.run(GatewayConnection.java:238)
    at java.lang.Thread.run(Thread.java:748)
Caused by: java.lang.ClassNotFoundException: org.apache.hive.hcatalog.data.JsonSerDe
    at java.net.URLClassLoader.findClass(URLClassLoader.java:382)
    at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
    at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
    at java.lang.Class.forName0(Native Method)
    at java.lang.Class.forName(Class.java:348)
    at org.apache.hadoop.hive.ql.plan.TableDesc.getDeserializerClass(TableDesc.java:71)
    ... 38 more

運行Spark SQL報The specified datastore driver ("com.mysql.jdbc.Driver") was not found in the CLASSPATH. 

方法一樣，將jdbc的驅動jar包放到spark的jar文件夾下

以上是“spark.sql操作hive報錯怎么辦”這篇文章的所有內容，感謝各位的閱讀！希望分享的內容對大家有幫助，更多相關知識，歡迎關注億速云行業資訊頻道！