Verwenden von mehrteiligen Uploads mit Verzeichnis-Buckets

/**
 * This method creates a multipart upload request that generates a unique upload ID that is used to track
 * all the upload parts
 *
 * @param s3
 * @param bucketName - for example, 'doc-example-bucket--use1-az4--x-s3'
 * @param key
 * @return
 */
 private static String createMultipartUpload(S3Client s3, String bucketName, String key) {
 
     CreateMultipartUploadRequest createMultipartUploadRequest = CreateMultipartUploadRequest.builder() 
             .bucket(bucketName)
             .key(key)
             .build();
             
     String uploadId = null;
     
     try {
         CreateMultipartUploadResponse response = s3.createMultipartUpload(createMultipartUploadRequest);
         uploadId = response.uploadId();
     }
     catch (S3Exception e) {
         System.err.println(e.awsErrorDetails().errorMessage());
         System.exit(1);
     }
     return uploadId;

def create_multipart_upload(s3_client, bucket_name, key_name):
    '''
   Create a multipart upload to a directory bucket
   
   :param s3_client: boto3 S3 client
   :param bucket_name: The destination bucket for the multipart upload
   :param key_name: The key name for the object to be uploaded
   :return: The UploadId for the multipart upload if created successfully, else None
   '''
   
   try:
        mpu = s3_client.create_multipart_upload(Bucket = bucket_name, Key = key_name)
        return mpu['UploadId'] 
    except ClientError as e:
        logging.error(e)
        return None

/**
 * This method creates part requests and uploads individual parts to S3 and then returns all the completed parts
 *
 * @param s3
 * @param bucketName
 * @param key
 * @param uploadId
 * @throws IOException
 */
 private static ListCompletedPartmultipartUpload(S3Client s3, String bucketName, String key, String uploadId, String filePath) throws IOException {

        int partNumber = 1;
        ListCompletedPart completedParts = new ArrayList<>();
        ByteBuffer bb = ByteBuffer.allocate(1024 * 1024 * 5); // 5 MB byte buffer

        // read the local file, breakdown into chunks and process
        try (RandomAccessFile file = new RandomAccessFile(filePath, "r")) {
            long fileSize = file.length();
            int position = 0;
            while (position < fileSize) {
                file.seek(position);
                int read = file.getChannel().read(bb);

                bb.flip(); // Swap position and limit before reading from the buffer.
                UploadPartRequest uploadPartRequest = UploadPartRequest.builder()
                        .bucket(bucketName)
                        .key(key)
                        .uploadId(uploadId)
                        .partNumber(partNumber)
                        .build();

                UploadPartResponse partResponse = s3.uploadPart(
                        uploadPartRequest,
                        RequestBody.fromByteBuffer(bb));

                CompletedPart part = CompletedPart.builder()
                        .partNumber(partNumber)
                        .eTag(partResponse.eTag())
                        .build();
                completedParts.add(part);

                bb.clear();
                position += read;
                partNumber++;
            }
        } 
        
        catch (IOException e) {
            throw e;
        }
        return completedParts;
    }

def multipart_upload(s3_client, bucket_name, key_name, mpu_id, part_size):
    '''
    Break up a file into multiple parts and upload those parts to a directory bucket

    :param s3_client: boto3 S3 client
    :param bucket_name: Destination bucket for the multipart upload
    :param key_name: Key name for object to be uploaded and for the local file that's being uploaded
    :param mpu_id: The UploadId returned from the create_multipart_upload call
    :param part_size: The size parts that the object will be broken into, in bytes. 
                      Minimum 5 MiB, Maximum 5 GiB. There is no minimum size for the last part of your multipart upload.
    :return: part_list for the multipart upload if all parts are uploaded successfully, else None
    '''
    
    part_list = []
    try:
        with open(key_name, 'rb') as file:
            part_counter = 1
            while True:
                file_part = file.read(part_size)
                if not len(file_part):
                    break
                upload_part = s3_client.upload_part(
                    Bucket = bucket_name,
                    Key = key_name,
                    UploadId = mpu_id,
                    Body = file_part,
                    PartNumber = part_counter
                )
                part_list.append({'PartNumber': part_counter, 'ETag': upload_part['ETag']})
                part_counter += 1
    except ClientError as e:
        logging.error(e)
        return None
    return part_list

/**
 * This method completes the multipart upload request by collating all the upload parts
 * @param s3
 * @param bucketName - for example, 'doc-example-bucket--usw2-az1--x-s3'
 * @param key
 * @param uploadId
 * @param uploadParts
 */
 private static void completeMultipartUpload(S3Client s3, String bucketName, String key, String uploadId, ListCompletedPart uploadParts) {
        CompletedMultipartUpload completedMultipartUpload = CompletedMultipartUpload.builder()
                .parts(uploadParts)
                .build();

        CompleteMultipartUploadRequest completeMultipartUploadRequest =
                CompleteMultipartUploadRequest.builder()
                        .bucket(bucketName)
                        .key(key)
                        .uploadId(uploadId)
                        .multipartUpload(completedMultipartUpload)
                        .build();

        s3.completeMultipartUpload(completeMultipartUploadRequest);
    }

    public static void multipartUploadTest(S3Client s3, String bucketName, String key, String localFilePath)  {
        System.out.println("Starting multipart upload for: " + key);
        try {
            String uploadId = createMultipartUpload(s3, bucketName, key);
            System.out.println(uploadId);
            ListCompletedPart parts = multipartUpload(s3, bucketName, key, uploadId, localFilePath);
            completeMultipartUpload(s3, bucketName, key, uploadId, parts);
            System.out.println("Multipart upload completed for: " + key);
        } 
        
        catch (Exception e) {
            System.err.println(e.getMessage());
            System.exit(1);
        }
    }

def complete_multipart_upload(s3_client, bucket_name, key_name, mpu_id, part_list):
    '''
    Completes a multipart upload to a directory bucket

    :param s3_client: boto3 S3 client
    :param bucket_name: The destination bucket for the multipart upload
    :param key_name: The key name for the object to be uploaded
    :param mpu_id: The UploadId returned from the create_multipart_upload call
    :param part_list: The list of uploaded part numbers with their associated ETags 
    :return: True if the multipart upload was completed successfully, else False
    '''
    
    try:
        s3_client.complete_multipart_upload(
            Bucket = bucket_name,
            Key = key_name,
            UploadId = mpu_id,
            MultipartUpload = {
                'Parts': part_list
            }
        )
    except ClientError as e:
        logging.error(e)
        return False
    return True
    
if __name__ == '__main__':
    MB = 1024 ** 2
    region = 'us-west-2'
    bucket_name = 'BUCKET_NAME'
    key_name = 'OBJECT_NAME'
    part_size = 10 * MB
    s3_client = boto3.client('s3', region_name = region)
    mpu_id = create_multipart_upload(s3_client, bucket_name, key_name)
    if mpu_id is not None:
        part_list = multipart_upload(s3_client, bucket_name, key_name, mpu_id, part_size)
        if part_list is not None:
            if complete_multipart_upload(s3_client, bucket_name, key_name, mpu_id, part_list):
                print (f'{key_name} successfully uploaded through a ultipart upload to {bucket_name}')
            else:
                print (f'Could not upload {key_name} hrough a multipart upload to {bucket_name}')

public static void abortMultiPartUploads( S3Client s3, String bucketName ) {

         try {
             ListMultipartUploadsRequest listMultipartUploadsRequest = ListMultipartUploadsRequest.builder()
                     .bucket(bucketName)
                     .build();

             ListMultipartUploadsResponse response = s3.listMultipartUploads(listMultipartUploadsRequest);
             ListMultipartUpload uploads = response.uploads();

             AbortMultipartUploadRequest abortMultipartUploadRequest;
             for (MultipartUpload upload: uploads) {
                 abortMultipartUploadRequest = AbortMultipartUploadRequest.builder()
                         .bucket(bucketName)
                         .key(upload.key())
                         .uploadId(upload.uploadId())
                         .build();

                 s3.abortMultipartUpload(abortMultipartUploadRequest);
             }

         } 
         
         catch (S3Exception e) {
             System.err.println(e.getMessage());
             System.exit(1);
         }
     }

import logging
import boto3
from botocore.exceptions import ClientError


def abort_multipart_upload(s3_client, bucket_name, key_name, upload_id):
    '''
    Aborts a partial multipart upload in a directory bucket.
    
    :param s3_client: boto3 S3 client
    :param bucket_name: Bucket where the multipart upload was initiated - for example, 'doc-example-bucket--usw2-az1--x-s3'
    :param key_name: Name of the object for which the multipart upload needs to be aborted
    :param upload_id: Multipart upload ID for the multipart upload to be aborted
    :return: True if the multipart upload was successfully aborted, False if not
    '''
    try:
        s3_client.abort_multipart_upload(
            Bucket = bucket_name,
            Key = key_name,
            UploadId = upload_id
        )
    except ClientError as e:
        logging.error(e)
        return False
    return True


if __name__ == '__main__':
    region = 'us-west-2'
    bucket_name = 'BUCKET_NAME'
    key_name = 'KEY_NAME'
        upload_id = 'UPLOAD_ID'
    s3_client = boto3.client('s3', region_name = region)
    if abort_multipart_upload(s3_client, bucket_name, key_name, upload_id):
        print (f'Multipart upload for object {key_name} in {bucket_name} bucket has been aborted')
    else:
        print (f'Unable to abort multipart upload for object {key_name} in {bucket_name} bucket')

/**
 * This method creates a multipart upload request that generates a unique upload ID that is used to track
 * all the upload parts.
 *
 * @param s3
 * @param bucketName
 * @param key
 * @return
 */
 private static String createMultipartUpload(S3Client s3, String bucketName, String key) {
        CreateMultipartUploadRequest createMultipartUploadRequest = CreateMultipartUploadRequest.builder()
                .bucket(bucketName)
                .key(key)
                .build();
        String uploadId = null;
        try {
            CreateMultipartUploadResponse response = s3.createMultipartUpload(createMultipartUploadRequest);
            uploadId = response.uploadId();
        } catch (S3Exception e) {
            System.err.println(e.awsErrorDetails().errorMessage());
            System.exit(1);
        }
        return uploadId;
  }

  /**
   * Creates copy parts based on source object size and copies over individual parts
   *
   * @param s3
   * @param sourceBucket
   * @param sourceKey
   * @param destnBucket
   * @param destnKey
   * @param uploadId
   * @return
   * @throws IOException
   */
    public static ListCompletedPart multipartUploadCopy(S3Client s3, String sourceBucket, String sourceKey, String destnBucket, String destnKey, String uploadId) throws IOException {

        // Get the object size to track the end of the copy operation.
        HeadObjectRequest headObjectRequest = HeadObjectRequest
                .builder()
                .bucket(sourceBucket)
                .key(sourceKey)
                .build();
        HeadObjectResponse response = s3.headObject(headObjectRequest);
        Long objectSize = response.contentLength();

        System.out.println("Source Object size: " + objectSize);

        // Copy the object using 20 MB parts.
        long partSize = 20 * 1024 * 1024;
        long bytePosition = 0;
        int partNum = 1;
        ListCompletedPart completedParts = new ArrayList<>();
        while (bytePosition < objectSize) {
            // The last part might be smaller than partSize, so check to make sure
            // that lastByte isn't beyond the end of the object.
            long lastByte = Math.min(bytePosition + partSize - 1, objectSize - 1);

            System.out.println("part no: " + partNum + ", bytePosition: " + bytePosition + ", lastByte: " + lastByte);

            // Copy this part.
            UploadPartCopyRequest req = UploadPartCopyRequest.builder()
                    .uploadId(uploadId)
                    .sourceBucket(sourceBucket)
                    .sourceKey(sourceKey)
                    .destinationBucket(destnBucket)
                    .destinationKey(destnKey)
                    .copySourceRange("bytes="+bytePosition+"-"+lastByte)
                    .partNumber(partNum)
                    .build();
            UploadPartCopyResponse res = s3.uploadPartCopy(req);
            CompletedPart part = CompletedPart.builder()
                    .partNumber(partNum)
                    .eTag(res.copyPartResult().eTag())
                    .build();
            completedParts.add(part);
            partNum++;
            bytePosition += partSize;
        }
        return completedParts;
    }


    public static void multipartCopyUploadTest(S3Client s3, String srcBucket, String srcKey, String destnBucket, String destnKey)  {
        System.out.println("Starting multipart copy for: " + srcKey);
        try {
            String uploadId = createMultipartUpload(s3, destnBucket, destnKey);
            System.out.println(uploadId);
            ListCompletedPart parts = multipartUploadCopy(s3, srcBucket, srcKey,destnBucket,  destnKey, uploadId);
            completeMultipartUpload(s3, destnBucket, destnKey, uploadId, parts);
            System.out.println("Multipart copy completed for: " + srcKey);
        } catch (Exception e) {
            System.err.println(e.getMessage());
            System.exit(1);
        }
    }

import logging
import boto3
from botocore.exceptions import ClientError

def head_object(s3_client, bucket_name, key_name):
    '''
    Returns metadata for an object in a directory bucket

    :param s3_client: boto3 S3 client
    :param bucket_name: Bucket that contains the object to query for metadata
    :param key_name: Key name to query for metadata
    :return: Metadata for the specified object if successful, else None
    '''

    try:
        response = s3_client.head_object(
            Bucket = bucket_name,
            Key = key_name
        )
        return response
    except ClientError as e:
        logging.error(e)
        return None
    
def create_multipart_upload(s3_client, bucket_name, key_name):
    '''
    Create a multipart upload to a directory bucket

    :param s3_client: boto3 S3 client
    :param bucket_name: Destination bucket for the multipart upload
    :param key_name: Key name of the object to be uploaded
    :return: UploadId for the multipart upload if created successfully, else None
    '''
    
    try:
        mpu = s3_client.create_multipart_upload(Bucket = bucket_name, Key = key_name)
        return mpu['UploadId'] 
    except ClientError as e:
        logging.error(e)
        return None

def multipart_copy_upload(s3_client, source_bucket_name, key_name, target_bucket_name, mpu_id, part_size):
    '''
    Copy an object in a directory bucket to another bucket in multiple parts of a specified size
    
    :param s3_client: boto3 S3 client
    :param source_bucket_name: Bucket where the source object exists
    :param key_name: Key name of the object to be copied
    :param target_bucket_name: Destination bucket for copied object
    :param mpu_id: The UploadId returned from the create_multipart_upload call
    :param part_size: The size parts that the object will be broken into, in bytes. 
                      Minimum 5 MiB, Maximum 5 GiB. There is no minimum size for the last part of your multipart upload.
    :return: part_list for the multipart copy if all parts are copied successfully, else None
    '''
    
    part_list = []
    copy_source = {
        'Bucket': source_bucket_name,
        'Key': key_name
    }
    try:
        part_counter = 1
        object_size = head_object(s3_client, source_bucket_name, key_name)
        if object_size is not None:
            object_size = object_size['ContentLength']
        while (part_counter - 1) * part_size <object_size:
            bytes_start = (part_counter - 1) * part_size
            bytes_end = (part_counter * part_size) - 1
            upload_copy_part = s3_client.upload_part_copy (
                Bucket = target_bucket_name,
                CopySource = copy_source,
                CopySourceRange = f'bytes={bytes_start}-{bytes_end}',
                Key = key_name,
                PartNumber = part_counter,
                UploadId = mpu_id
            )
            part_list.append({'PartNumber': part_counter, 'ETag': upload_copy_part['CopyPartResult']['ETag']})
            part_counter += 1
    except ClientError as e:
        logging.error(e)
        return None
    return part_list

def complete_multipart_upload(s3_client, bucket_name, key_name, mpu_id, part_list):
    '''
    Completes a multipart upload to a directory bucket

    :param s3_client: boto3 S3 client
    :param bucket_name: Destination bucket for the multipart upload
    :param key_name: Key name of the object to be uploaded
    :param mpu_id: The UploadId returned from the create_multipart_upload call
    :param part_list: List of uploaded part numbers with associated ETags 
    :return: True if the multipart upload was completed successfully, else False
    '''
    
    try:
        s3_client.complete_multipart_upload(
            Bucket = bucket_name,
            Key = key_name,
            UploadId = mpu_id,
            MultipartUpload = {
                'Parts': part_list
            }
        )
    except ClientError as e:
        logging.error(e)
        return False
    return True

if __name__ == '__main__':
    MB = 1024 ** 2
    region = 'us-west-2'
    source_bucket_name = 'SOURCE_BUCKET_NAME'
    target_bucket_name = 'TARGET_BUCKET_NAME'
    key_name = 'KEY_NAME'
    part_size = 10 * MB
    s3_client = boto3.client('s3', region_name = region)
    mpu_id = create_multipart_upload(s3_client, target_bucket_name, key_name)
    if mpu_id is not None:
        part_list = multipart_copy_upload(s3_client, source_bucket_name, key_name, target_bucket_name, mpu_id, part_size)
        if part_list is not None:
            if complete_multipart_upload(s3_client, target_bucket_name, key_name, mpu_id, part_list):
                print (f'{key_name} successfully copied through multipart copy from {source_bucket_name} to {target_bucket_name}')
            else:
                print (f'Could not copy {key_name} through multipart copy from {source_bucket_name} to {target_bucket_name}')

 public static void listMultiPartUploads( S3Client s3, String bucketName) {
        try {
            ListMultipartUploadsRequest listMultipartUploadsRequest = ListMultipartUploadsRequest.builder()
                .bucket(bucketName)
                .build();
                
            ListMultipartUploadsResponse response = s3.listMultipartUploads(listMultipartUploadsRequest);
            List MultipartUpload uploads = response.uploads();
            for (MultipartUpload upload: uploads) {
                System.out.println("Upload in progress: Key = \"" + upload.key() + "\", id = " + upload.uploadId());
            }
      }
      catch (S3Exception e) {
            System.err.println(e.getMessage());
            System.exit(1);
      }
  }

import logging
import boto3
from botocore.exceptions import ClientError

def list_multipart_uploads(s3_client, bucket_name):
    '''
    List any incomplete multipart uploads in a directory bucket in e specified gion

    :param s3_client: boto3 S3 client
    :param bucket_name: Bucket to check for incomplete multipart uploads
    :return: List of incomplete multipart uploads if there are any, None if not
    '''
    
    try:
        response = s3_client.list_multipart_uploads(Bucket = bucket_name)
        if 'Uploads' in response.keys():
            return response['Uploads']
        else:
            return None 
    except ClientError as e:
        logging.error(e)

if __name__ == '__main__':
    bucket_name = 'BUCKET_NAME'
    region = 'us-west-2'
    s3_client = boto3.client('s3', region_name = region)
    multipart_uploads = list_multipart_uploads(s3_client, bucket_name)
    if multipart_uploads is not None:
        print (f'There are {len(multipart_uploads)} ncomplete multipart uploads for {bucket_name}')
    else:
        print (f'There are no incomplete multipart uploads for {bucket_name}')