无法从 Hadoop 会议获取访问密钥和密钥

Question

我有如下代码 -

import java.io.InputStream
import java.net.URI
import java.util
import com.amazonaws.auth.AWSCredentialsProviderChain
import com.amazonaws.{ClientConfiguration, Protocol}
import com.amazonaws.services.s3.AmazonS3Client
import com.amazonaws.services.s3.model._
import org.apache.hadoop.conf.{Configuration => HadoopConfiguration}
import org.apache.hadoop.fs.{Path => HadoopPath}
import org.apache.hadoop.fs.s3a.{BasicAWSCredentialsProvider, S3AFileSystem}
import com.amazonaws.services.s3.model.ObjectListing
import scala.annotation.tailrec
object FileOperation {
  val uri = new URI("s3a://bucket-name/prefixKey/file.json")
  val fs: S3AFileSystem = new S3AFileSystem()
  def getAWSClient: AmazonS3Client = {
    val conf: HadoopConfiguration = new HadoopConfiguration(true)
    val awsConf: ClientConfiguration = new ClientConfiguration()
    val secureConnections: Boolean = conf.getBoolean("fs.s3a.connection.ssl.enabled", false)
    awsConf.setProtocol(if (secureConnections) Protocol.HTTPS else Protocol.HTTP)
    val accessKey: String = conf.get("fs.s3a.access.key", null.asInstanceOf[String])
    val secretKey: String = conf.get("fs.s3a.secret.key", null.asInstanceOf[String])
    println(s"inside getAWSClient accessKey -> $accessKey ; secretKey -> $secretKey")
    val credentials = new AWSCredentialsProviderChain(new BasicAWSCredentialsProvider(accessKey, secretKey))
    val s3: AmazonS3Client = new AmazonS3Client(credentials, awsConf)
    s3.setEndpoint(conf.get("fs.s3a.endpoint", null.asInstanceOf[String]))
    s3
  }
  def getEntries(recursive: Boolean): Seq[URI] = {
    @tailrec
    def collectEntries(summaries: util.Iterator[S3ObjectSummary], collected: Seq[HadoopPath]): Seq[HadoopPath] = {
      if (summaries.hasNext) {
        val summary: S3ObjectSummary = summaries.next()
        val newPath: String = "s3a://" + summary.getBucketName + "/" + summary.getKey
        collectEntries(summaries, collected :+ {
          fs.initialize(new URI(newPath), new HadoopConfiguration(true))
          new HadoopPath(new URI(newPath))
        })
      } else collected
    }
    val prefixKey: String = if (!(uri.getScheme != null && uri.getPath.isEmpty)) uri.getPath.substring(1) else ""
    val objects: ObjectListing = getAWSClient.listObjects(uri.getHost, prefixKey)
    if (objects.getObjectSummaries.isEmpty) throw new java.nio.file.NoSuchFileException(uri.toString)
    else {
      collectEntries(objects.getObjectSummaries.iterator(), Seq.empty).map(path => path.toUri)
    }
  }
  def asStream: InputStream = {
    val prefixKey1 = if (!(uri.getScheme != null && uri.getPath.isEmpty)) uri.getPath.substring(1) else ""
    val s3object: S3Object = getAWSClient.getObject(new GetObjectRequest(uri.getHost, prefixKey1))
    s3object.getObjectContent
  }
}

函数

getEntrys中对函数getAWSClient的调用有效，但asStream函数中的调用获得空访问密钥和私有密钥。 getEntries 函数用于列出文件夹下的文件，而 asStream 函数返回此类文件的输入流，该文件用于创建 BufferedSource，然后读取内容。

下面是Hadoop核心.xml文件。有人可以帮我解释为什么访问密钥和密钥在 asStream 函数中显示为空。

<?xml version="1.0" encoding="UTF-8"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<!-- Sample config for Hadoop S3A client. -->
<configuration>
    <property>
        <name>fs.s3a.access.key</name>
        <value>xxxxxxxx</value>
    </property>
    <property>
        <name>fs.s3a.secret.key</name>
        <value>yyyyyyy</value>
    </property>
    <property>
        <name>fs.s3a.connection.ssl.enabled</name>
        <value>false</value>
    </property>
    <property>
        <name>fs.s3a.endpoint</name>
        <value>dev:80</value>
    </property>
    <property>
        <name>fs.s3a.imp</name>
        <value>org.apache.hadoop.fs.s3a.S3A</value>
    </property>
    <property>
        <name>fs.s3a.path.style.access</name>
        <value>true</value>
    </property>
</configuration>

Answer 1

1. S3A连接器不提供其机密，因为它们是"秘密"。
2. S3AFileSystem 类不希望initialize()被多次调用。创建线程池和 AWS Transfer 管理器等昂贵的内容，并且仅在FileSystem.close()调用中清理。你的代码会泄漏这些。如果我们知道人们正在尝试这样做(现在我们做到了！(，我们将添加一个检查并快速失败。

如果你调用FileSystem.listFiles(path, true)你会得到一个路径下所有对象的递归列表，每千个后代条目只有一个 HTTP 请求 S3;这似乎是你正在对listObjects.

哦，如果你想要FS正在使用的配置，请调用fs.getConf()。如果机密是在 XML 文件中传递的，这将包含机密。如果它们保存在JCECKs文件或其他安全存储中，则有点棘手。