我正在尝试使用apachehudi框架在hivemetastore中创建一个外部文件。它可以连接到配置单元元存储区，但在尝试创建表时在连接后引发异常。

dataFrame.writeStream
      .format("org.apache.hudi")
      .option(HoodieWriteConfig.TABLE_NAME, tableName)
      .option(DataSourceWriteOptions.HIVE_TABLE_OPT_KEY,tableName)
      .option(DataSourceWriteOptions.OPERATION_OPT_KEY, DataSourceWriteOptions.UPSERT_OPERATION_OPT_VAL)
      .option(DataSourceWriteOptions.HIVE_SYNC_ENABLED_OPT_KEY, "true")
      .option(DataSourceWriteOptions.HIVE_AUTO_CREATE_DATABASE_OPT_KEY, "true")
      .option(DataSourceWriteOptions.DEFAULT_HIVE_ASSUME_DATE_PARTITION_OPT_VAL, "false")
           .option(DataSourceWriteOptions.PARTITIONPATH_FIELD_OPT_KEY, "partition_id")
            .option(DataSourceWriteOptions.HIVE_PARTITION_FIELDS_OPT_KEY, "partition_id")
            .option(DataSourceWriteOptions.HIVE_URL_OPT_KEY, "jdbc:hive2://localhost:10000")
      .option(DataSourceWriteOptions.RECORDKEY_FIELD_OPT_KEY, key)
      .option(DataSourceWriteOptions.PRECOMBINE_FIELD_OPT_KEY, combineKey)
      .option(DataSourceWriteOptions.OPERATION_OPT_KEY, DataSourceWriteOptions.UPSERT_OPERATION_OPT_VAL)
      .option("checkpointLocation", "/tmp/test/checkpoint")
      .option("spark.kryo.registrationRequired", "true")
      .option("hoodie.upsert.shuffle.parallelism", "1")
      .outputMode("append")
      .start("s3a://testbucket/test")

依赖项：

scalaVersion := "2.12.1"

libraryDependencies += "org.apache.spark" %% "spark-core" % "3.1.1"
libraryDependencies += "org.apache.spark" %% "spark-sql" % "3.1.1"
libraryDependencies += "org.apache.spark" %% "spark-sql-kafka-0-10" % "3.1.1"
libraryDependencies += "org.apache.spark" %% "spark-streaming" % "3.1.1" % "provided"
libraryDependencies += "org.apache.spark" %% "spark-streaming-kafka-0-10" % "3.1.1"
libraryDependencies += "org.apache.hudi" %% "hudi-spark-bundle" % "0.7.0"
libraryDependencies += "org.apache.hadoop" % "hadoop-common" % "3.1.4"
libraryDependencies += "org.apache.hadoop" % "hadoop-hdfs" % "3.1.1"
libraryDependencies += "org.apache.hadoop" % "hadoop-client" % "3.1.1"
libraryDependencies += "org.apache.hadoop" % "hadoop-aws" % "3.1.1"
libraryDependencies += "org.apache.spark" %% "spark-hive" % "3.1.1"
libraryDependencies += "org.apache.hive" % "hive-jdbc" % "3.1.1"
libraryDependencies += "org.apache.hive" % "hive-metastore" % "3.1.1"
libraryDependencies += "org.apache.hive" % "hive-exec" % "3.1.1"
dependencyOverrides += "org.apache.hadoop" % "hadoop-common" % "3.1.1"
dependencyOverrides += "org.apache.commons" % "commons-lang3" % "3.9"

出现以下异常：

org.apache.hudi.hive.HoodieHiveSyncException: Failed in executing SQL CREATE EXTERNAL TABLE  IF NOT EXISTS `default`.......' org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe' STORED AS INPUTFORMAT 'org.apache.hudi.hadoop.HoodieParquetInputFormat' OUTPUTFORMAT 'org.apache.hadoop.hive.ql.io.parquet.MapredParquetOutputFormat' LOCATION 's3a://testbucket/test'

Caused by: org.apache.hive.service.cli.HiveSQLException: Error running query: java.lang.NoClassDefFoundError: org/apache/hadoop/fs/StreamCapabilities
    at org.apache.hive.jdbc.Utils.verifySuccess(Utils.java:300) ~[hive-jdbc-3.1.1.jar:3.1.1]
    at org.apache.hive.jdbc.Utils.verifySuccessWithInfo(Utils.java:286) ~[hive-jdbc-3.1.1.jar:3.1.1]
    at org.apache.hive.jdbc.HiveStatement.runAsyncOnServer(HiveStatement.java:324) ~[hive-jdbc-3.1.1.jar:3.1.1]
    at org.apache.hive.jdbc.HiveStatement.execute(HiveStatement.java:265) ~[hive-jdbc-3.1.1.jar:3.1.1]
    at org.apache.hudi.hive.HoodieHiveClient.updateHiveSQL(HoodieHiveClient.java:367) ~[hudi-spark-bundle_2.12-0.7.0.jar:0.7.0]
    ... 37 more