将对象上载到AWS S3，而不使用aws go创建文件。

Question

我正在尝试使用golang将一个对象上传到AWS S3，而不需要在我的系统中创建一个文件(尝试只上传字符串)。但我很难做到这一点。有人能给我举一个例子，说明我如何在不需要创建文件的情况下上传到AWS S3？

关于如何上载文件的AWS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该文件，但它正在我的系统上创建文件，然后将其上传到S3。

Answer 1

Body结构的UploadInput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 2

在这个答案中，我将张贴所有对我有用的与这个问题有关的东西。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。我将张贴一些示例代码，评论我从这个问题中学到了什么，以及它如何帮助我解决这个问题。也许这会帮助像我和@AlokKumarSingh这样的人。

案例1:您已经有了内存中的数据(例如，从诸如Kafka、Kinesis或SQS这样的流/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:您已经有了一个持久化文件，并且希望上传它，但是您不想将整个文件保存在内存中：

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:这是我在系统的最终版本上实现它的方式，但是要理解为什么要这样做，我必须给出一些背景。

我的用例进化了一点。上传代码将是Lambda中的一个函数，文件结果显示是巨大的。这意味着什么?如果我通过一个附加到Lambda函数的API网关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。因为lambda是根据调用的持续时间和内存使用情况来定价的，所以这可能是一个很大的问题。

因此，为了解决这个问题，我在上传时使用了一个预先签名的post URL。这对架构/工作流有何影响？

我不是从后端代码上传到S3，而是创建并验证一个URL，用于将对象发送到后端的S3，并将该URL发送到前端。有了它，我就实现了一个多部分上传到那个URL。我知道这比这个问题要具体得多，但要找到这个解决方案并不容易，所以我认为最好在这里为其他人记录一下。

下面是如何在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,
        })
      }
    });
};

如果您想使用go --这是相同的想法，您只需更改de即可。

Answer 3

下面是我编写的一个小实现，它利用管道并合并超时。

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
}