我不知道为什么您提到的文档不起作用。也许您正在使用不同的依赖项？
这些文档有一个您可以下载的示例应用程序。这是一个测试非常少的项目，因此它不会创建作业或尝试在集群上运行它们——但这只是一个开始。另外，请注意它使用的是旧0.0.1版本的dbutils-api.
因此，要解决您当前的问题，请尝试从其他地方com.databricks.service.DBUtils导入，而不是使用：dbutils
import com.databricks.dbutils_v1.DBUtilsHolder.dbutils
或者，如果您愿意：
import com.databricks.dbutils_v1.{DBUtilsV1, DBUtilsHolder}
type DBUtils = DBUtilsV1
val dbutils: DBUtils = DBUtilsHolder.dbutils
另外，请确保您在 SBT 中具有以下依赖项（如果0.0.3不起作用，可以尝试使用版本 - 最新的是0.0.4）：
libraryDependencies += "com.databricks" % "dbutils-api_2.11" % "0.0.3"
这个问题和答案为我指明了正确的方向。答案包含一个指向有效的 Github 存储库的链接，该存储库使用dbutils：waimak。我希望这个 repo 可以帮助您解决有关 Databricks 配置和依赖项的更多问题。
祝你好运！
更新
我明白了，所以我们有两个相似但不相同的 API，并且没有在本地版本和后端版本之间切换的好方法（尽管 Databricks Connect 承诺它应该无论如何都可以工作）。请让我提出一个解决方法。
Scala方便编写适配器是好事。这是一个应该充当桥梁的代码片段——这里DBUtils定义的对象为 API 的两个版本提供了足够的 API 抽象：Databricks Connect one oncom.databricks.service.DBUtils和后端com.databricks.dbutils_v1.DBUtilsHolder.dbutilsAPI。我们能够通过加载和随后使用com.databricks.service.DBUtils直通反射来实现这一点——我们没有硬编码的导入。
package com.example.my.proxy.adapter
import org.apache.hadoop.fs.FileSystem
import org.apache.spark.sql.catalyst.DefinedByConstructorParams
import scala.util.Try
import scala.language.implicitConversions
import scala.language.reflectiveCalls
trait DBUtilsApi {
type FSUtils
type FileInfo
type SecretUtils
type SecretMetadata
type SecretScope
val fs: FSUtils
val secrets: SecretUtils
}
trait DBUtils extends DBUtilsApi {
trait FSUtils {
def dbfs: org.apache.hadoop.fs.FileSystem
def ls(dir: String): Seq[FileInfo]
def rm(dir: String, recurse: Boolean = false): Boolean
def mkdirs(dir: String): Boolean
def cp(from: String, to: String, recurse: Boolean = false): Boolean
def mv(from: String, to: String, recurse: Boolean = false): Boolean
def head(file: String, maxBytes: Int = 65536): String
def put(file: String, contents: String, overwrite: Boolean = false): Boolean
}
case class FileInfo(path: String, name: String, size: Long)
trait SecretUtils {
def get(scope: String, key: String): String
def getBytes(scope: String, key: String): Array[Byte]
def list(scope: String): Seq[SecretMetadata]
def listScopes(): Seq[SecretScope]
}
case class SecretMetadata(key: String) extends DefinedByConstructorParams
case class SecretScope(name: String) extends DefinedByConstructorParams
}
object DBUtils extends DBUtils {
import Adapters._
override lazy val (fs, secrets): (FSUtils, SecretUtils) = Try[(FSUtils, SecretUtils)](
(ReflectiveDBUtils.fs, ReflectiveDBUtils.secrets) // try to use the Databricks Connect API
).getOrElse(
(BackendDBUtils.fs, BackendDBUtils.secrets) // if it's not available, use com.databricks.dbutils_v1.DBUtilsHolder
)
private object Adapters {
// The apparent code copying here is for performance -- the ones for `ReflectiveDBUtils` use reflection, while
// the `BackendDBUtils` call the functions directly.
implicit class FSUtilsFromBackend(underlying: BackendDBUtils.FSUtils) extends FSUtils {
override def dbfs: FileSystem = underlying.dbfs
override def ls(dir: String): Seq[FileInfo] = underlying.ls(dir).map(fi => FileInfo(fi.path, fi.name, fi.size))
override def rm(dir: String, recurse: Boolean = false): Boolean = underlying.rm(dir, recurse)
override def mkdirs(dir: String): Boolean = underlying.mkdirs(dir)
override def cp(from: String, to: String, recurse: Boolean = false): Boolean = underlying.cp(from, to, recurse)
override def mv(from: String, to: String, recurse: Boolean = false): Boolean = underlying.mv(from, to, recurse)
override def head(file: String, maxBytes: Int = 65536): String = underlying.head(file, maxBytes)
override def put(file: String, contents: String, overwrite: Boolean = false): Boolean = underlying.put(file, contents, overwrite)
}
implicit class FSUtilsFromReflective(underlying: ReflectiveDBUtils.FSUtils) extends FSUtils {
override def dbfs: FileSystem = underlying.dbfs
override def ls(dir: String): Seq[FileInfo] = underlying.ls(dir).map(fi => FileInfo(fi.path, fi.name, fi.size))
override def rm(dir: String, recurse: Boolean = false): Boolean = underlying.rm(dir, recurse)
override def mkdirs(dir: String): Boolean = underlying.mkdirs(dir)
override def cp(from: String, to: String, recurse: Boolean = false): Boolean = underlying.cp(from, to, recurse)
override def mv(from: String, to: String, recurse: Boolean = false): Boolean = underlying.mv(from, to, recurse)
override def head(file: String, maxBytes: Int = 65536): String = underlying.head(file, maxBytes)
override def put(file: String, contents: String, overwrite: Boolean = false): Boolean = underlying.put(file, contents, overwrite)
}
implicit class SecretUtilsFromBackend(underlying: BackendDBUtils.SecretUtils) extends SecretUtils {
override def get(scope: String, key: String): String = underlying.get(scope, key)
override def getBytes(scope: String, key: String): Array[Byte] = underlying.getBytes(scope, key)
override def list(scope: String): Seq[SecretMetadata] = underlying.list(scope).map(sm => SecretMetadata(sm.key))
override def listScopes(): Seq[SecretScope] = underlying.listScopes().map(ss => SecretScope(ss.name))
}
implicit class SecretUtilsFromReflective(underlying: ReflectiveDBUtils.SecretUtils) extends SecretUtils {
override def get(scope: String, key: String): String = underlying.get(scope, key)
override def getBytes(scope: String, key: String): Array[Byte] = underlying.getBytes(scope, key)
override def list(scope: String): Seq[SecretMetadata] = underlying.list(scope).map(sm => SecretMetadata(sm.key))
override def listScopes(): Seq[SecretScope] = underlying.listScopes().map(ss => SecretScope(ss.name))
}
}
}
object BackendDBUtils extends DBUtilsApi {
import com.databricks.dbutils_v1
private lazy val dbutils: DBUtils = dbutils_v1.DBUtilsHolder.dbutils
override lazy val fs: FSUtils = dbutils.fs
override lazy val secrets: SecretUtils = dbutils.secrets
type DBUtils = dbutils_v1.DBUtilsV1
type FSUtils = dbutils_v1.DbfsUtils
type FileInfo = com.databricks.backend.daemon.dbutils.FileInfo
type SecretUtils = dbutils_v1.SecretUtils
type SecretMetadata = dbutils_v1.SecretMetadata
type SecretScope = dbutils_v1.SecretScope
}
object ReflectiveDBUtils extends DBUtilsApi {
// This throws a ClassNotFoundException when the Databricks Connection API isn't available -- it's much better than
// the NoClassDefFoundError, which we would get if we had a hard-coded import of com.databricks.service.DBUtils .
// As we're just using reflection, we're able to recover if it's not found.
private lazy val dbutils: DBUtils =
Class.forName("com.databricks.service.DBUtils$").getField("MODULE$").get().asInstanceOf[DBUtils]
override lazy val fs: FSUtils = dbutils.fs
override lazy val secrets: SecretUtils = dbutils.secrets
type DBUtils = AnyRef {
val fs: FSUtils
val secrets: SecretUtils
}
type FSUtils = AnyRef {
def dbfs: org.apache.hadoop.fs.FileSystem
def ls(dir: String): Seq[FileInfo]
def rm(dir: String, recurse: Boolean): Boolean
def mkdirs(dir: String): Boolean
def cp(from: String, to: String, recurse: Boolean): Boolean
def mv(from: String, to: String, recurse: Boolean): Boolean
def head(file: String, maxBytes: Int): String
def put(file: String, contents: String, overwrite: Boolean): Boolean
}
type FileInfo = AnyRef {
val path: String
val name: String
val size: Long
}
type SecretUtils = AnyRef {
def get(scope: String, key: String): String
def getBytes(scope: String, key: String): Array[Byte]
def list(scope: String): Seq[SecretMetadata]
def listScopes(): Seq[SecretScope]
}
type SecretMetadata = DefinedByConstructorParams { val key: String }
type SecretScope = DefinedByConstructorParams { val name: String }
}
如果您将val dbutils: DBUtils.type = com.databricks.service.DBUtils您在其中提到的Main替换为val dbutils: DBUtils.type = com.example.my.proxy.adapter.DBUtils，则所有内容都应该可以作为本地和远程的直接替换。
如果您有一些新NoClassDefFoundError的，请尝试将特定的依赖项添加到 JAR 作业中，或者尝试重新排列它们、更改版本或将依赖项标记为已提供。
这个适配器并不漂亮，它使用反射，但我希望它作为一种解决方法应该足够好。祝你好运 ：）