将对象上传到 AWS S3 而不使用 aws-sdk-go 创建文件

Question

我正在尝试使用 golang sdk 将对象上传到 AWS S3，而无需在我的系统中创建文件（尝试仅上传字符串）。但我很难做到这一点。谁能给我一个示例，说明如何在无需创建文件的情况下上传到 AWS S3？

AWS 上传文件示例：

// Creates a S3 Bucket in the region configured in the shared config
// or AWS_REGION environment variable.
//
// Usage:
//    go run s3_upload_object.go BUCKET_NAME FILENAME
func main() {
    if len(os.Args) != 3 {
        exitErrorf("bucket and file name required\nUsage: %s bucket_name filename",
            os.Args[0])
    }

    bucket := os.Args[1]
    filename := os.Args[2]

    file, err := os.Open(filename)
    if err != nil {
        exitErrorf("Unable to open file %q, %v", err)
    }

    defer file.Close()

    // Initialize a session in us-west-2 that the SDK will use to load
    // credentials from the shared credentials file ~/.aws/credentials.
    sess, err := session.NewSession(&aws.Config{
        Region: aws.String("us-west-2")},
    )

    // Setup the S3 Upload Manager. Also see the SDK doc for the Upload Manager
    // for more information on configuring part size, and concurrency.
    //
    // http://docs.aws.amazon.com/sdk-for-go/api/service/s3/s3manager/#NewUploader
    uploader := s3manager.NewUploader(sess)

    // Upload the file's body to S3 bucket as an object with the key being the
    // same as the filename.
    _, err = uploader.Upload(&s3manager.UploadInput{
        Bucket: aws.String(bucket),

        // Can also use the `filepath` standard library package to modify the
        // filename as need for an S3 object key. Such as turning absolute path
        // to a relative path.
        Key: aws.String(filename),

        // The file to be uploaded. io.ReadSeeker is preferred as the Uploader
        // will be able to optimize memory when uploading large content. io.Reader
        // is supported, but will require buffering of the reader's bytes for
        // each part.
        Body: file,
    })
    if err != nil {
        // Print the error and exit.
        exitErrorf("Unable to upload %q to %q, %v", filename, bucket, err)
    }

    fmt.Printf("Successfully uploaded %q to %q\n", filename, bucket)
}

我已经尝试以编程方式创建文件，但它正在我的系统上创建文件，然后将其上传到 S3。

Answer 1

在此答案中，我将发布与此问题相关的所有对我有用的内容。非常感谢@ThunderCat 和@Flimzy 提醒我上传请求的body 参数已经是一个io.Reader。我将发布一些示例代码，评论我从这个问题中学到的东西以及它如何帮助我解决这个问题。也许这会帮助像我和@AlokKumarSingh 这样的其他人。

案例 1：您已经在内存中拥有数据（例如，从 Kafka、Kinesis 或 SQS 等流式传输/消息传递服务接收数据）

func main() {
    if len(os.Args) != 3 {
        fmt.Printf(
            "bucket and file name required\nUsage: %s bucket_name filename",
            os.Args[0],
        )
    }

    bucket := os.Args[1]
    filename := os.Args[2]

    // this is your data that you have in memory
    // in this example it is hard coded but it may come from very distinct
    // sources, like streaming services for example.
    data := "Hello, world!"

    // create a reader from data data in memory
    reader := strings.NewReader(data)

    sess, err := session.NewSession(&aws.Config{
        Region: aws.String("us-east-1")},
    )
    uploader := s3manager.NewUploader(sess)

    _, err = uploader.Upload(&s3manager.UploadInput{
        Bucket: aws.String(bucket),
        Key: aws.String(filename),
        // here you pass your reader
        // the aws sdk will manage all the memory and file reading for you
        Body: reader,
    })
    if err != nil {.
        fmt.Printf("Unable to upload %q to %q, %v", filename, bucket, err)
    }

    fmt.Printf("Successfully uploaded %q to %q\n", filename, bucket)
}

案例 2：您已经有一个持久化文件并且想要上传它，但您不想将整个文件保留在内存中：

func main() {
    if len(os.Args) != 3 {
        fmt.Printf(
            "bucket and file name required\nUsage: %s bucket_name filename",
            os.Args[0],
        )
    }

    bucket := os.Args[1]
    filename := os.Args[2]

    // open your file
    // the trick here is that the method os.Open just returns for you a reader
    // for the desired file, so you will not maintain the whole file in memory.
    // I know this might sound obvious, but for a starter (as I was at the time
    // of the question) it is not.
    fileReader, err := os.Open(filename)
    if err != nil {
        fmt.Printf("Unable to open file %q, %v", err)
    }
    defer fileReader.Close()

    sess, err := session.NewSession(&aws.Config{
        Region: aws.String("us-east-1")},
    )
    uploader := s3manager.NewUploader(sess)

    _, err = uploader.Upload(&s3manager.UploadInput{
        Bucket: aws.String(bucket),
        Key:    aws.String(filename),
        // here you pass your reader
        // the aws sdk will manage all the memory and file reading for you
        Body: fileReader,
    })
    if err != nil {
        fmt.Printf("Unable to upload %q to %q, %v", filename, bucket, err)
    }

    fmt.Printf("Successfully uploaded %q to %q\n", filename, bucket)
}

案例 3：这就是我在系统的最终版本中实现它的方式，但要理解我为什么这样做，我必须给你一些背景知识。

我的用例发生了一些变化。上传代码将成为 Lambda 中的一个函数，结果文件非常庞大。此更改意味着什么：如果我通过附加到 Lambda 函数的 API Gateway 中的入口点上传文件，我将不得不等待整个文件在 Lambda 中完成上传。由于 lambda 是根据调用的持续时间和内存使用量来定价的，因此这可能是一个非常大的问题。

所以，为了解决这个问题，我使用了预签名的帖子 URL 进行上传。这对架构/工作流程有何影响？

我没有从我的后端代码上传到 S3，而是创建并验证了一个 URL，用于在后端将对象发布到 S3，然后将此 URL 发送到前端。有了这个，我刚刚实现了对该 URL 的分段上传。我知道这比问题要具体得多，但发现这个解决方案并不容易，所以我认为在这里为其他人记录它是个好主意。

以下是如何在 nodejs 中创建预签名 URL 的示例。

const AWS = require('aws-sdk');

module.exports.upload = async (event, context, callback) => {

  const s3 = new AWS.S3({ signatureVersion: 'v4' });
  const body = JSON.parse(event.body);

  const params = {
    Bucket: process.env.FILES_BUCKET_NAME,
    Fields: {
      key: body.filename,
    },
    Expires: 60 * 60
  }

  let promise = new Promise((resolve, reject) => {
    s3.createPresignedPost(params, (err, data) => {
      if (err) {
        reject(err);
      } else {
        resolve(data);
      }
    });
  })

  return await promise
    .then((data) => {
      return {
        statusCode: 200,
        body: JSON.stringify({
          message: 'Successfully created a pre-signed post url.',
          data: data,
        })
      }
    })
    .catch((err) => {
      return {
        statusCode: 400,
        body: JSON.stringify({
          message: 'An error occurred while trying to create a pre-signed post url',
          error: err,
        })
      }
    });
};

如果要使用go也是一样的思路，只需要改de sdk即可。

Answer 2

UploadInput 结构的Body 字段只是一个io.Reader。所以传递任何你想要的io.Reader——它不需要是一个文件。

Answer 3

这是我编写的一个小实现，它利用管道并包含超时。

package example

import (
    "context"
    "fmt"
    "io"
    "sync"
    "time"

    "github.com/aws/aws-sdk-go/service/s3/s3manager"
)

func FileWriter(ctx context.Context, uploader *s3manager.Uploader, wg *sync.WaitGroup, bucket string, key string, timeout time.Duration) (writer *io.PipeWriter) {
    // create a per-file flush timeout
    fileCtx, cancel := context.WithTimeout(ctx, timeout)

    // pipes are open until one end is closed
    pr, pw := io.Pipe()

    wg.Add(1)
    go func() {
        params := &s3manager.UploadInput{
            Bucket: aws.String(bucket),
            Key:    aws.String(key),
            Body:   pr,
        }

        // blocking
        _, err := uploader.Upload(params)
        if err != nil {
            fmt.Printf("Unable to upload, %v. Bucket: %s", err, bucket)
        }

        // always call context cancel functions!
        cancel()
        wg.Done()
    }()

    // when context is cancelled, close the pipe
    go func() {
        <-fileCtx.Done()
        // should check fileCtx.Err() here
        if err := pw.Close(); err != nil {
            fmt.Printf("Unable to close")
        }
    }()

    return pw
}

Answer 4

这是我最后写的内容

func (s *S3Sink) upload() {
    now := time.Now()
    key := s.getNewKey(now)

    _, err := s.uploader.Upload(&s3manager.UploadInput{
        Bucket: aws.String(s.bucket),
        Key:    aws.String(key),
        Body:   s.bodyBuf,
    })

    if err != nil {
        glog.Errorf("Error uploading %s to s3, %v", key, err)
    }
    glog.Infof("Uploaded at %s", key)
    s.lastUploadTimestamp = now.UnixNano()

    s.bodyBuf.Truncate(0)
}

更多详情如下： https://github.com/heptiolabs/eventrouter/blob/20edca33bc6e20465810d49bdb213119464eb440/sinks/s3sink.go#L185-L201