aws-sdk-s3 1.96.2 → 1.132.0

data/lib/aws-sdk-s3/file_downloader.rb

@@ -31,40 +31,61 @@ module Aws
           key: options[:key],
         }
         @params[:version_id] = options[:version_id] if options[:version_id]
-
-        case @mode
-        when 'auto' then multipart_download
-        when 'single_request' then single_request
-        when 'get_range'
-          if @chunk_size
-            resp = @client.head_object(@params)
-            multithreaded_get_by_ranges(construct_chunks(resp.content_length))
+        @params[:checksum_mode] = options[:checksum_mode] || 'ENABLED'
+        @on_checksum_validated = options[:on_checksum_validated]
+
+        validate!
+
+        Aws::Plugins::UserAgent.feature('s3-transfer') do
+          case @mode
+          when 'auto' then multipart_download
+          when 'single_request' then single_request
+          when 'get_range'
+            if @chunk_size
+              resp = @client.head_object(@params)
+              multithreaded_get_by_ranges(construct_chunks(resp.content_length))
+            else
+              msg = 'In :get_range mode, :chunk_size must be provided'
+              raise ArgumentError, msg
+            end
           else
-            msg = 'In :get_range mode, :chunk_size must be provided'
+            msg = "Invalid mode #{@mode} provided, "\
+                  'mode should be :single_request, :get_range or :auto'
             raise ArgumentError, msg
           end
-        else
-          msg = "Invalid mode #{@mode} provided, "\
-                'mode should be :single_request, :get_range or :auto'
-          raise ArgumentError, msg
         end
       end
 
       private
 
+      def validate!
+        if @on_checksum_validated && @params[:checksum_mode] != 'ENABLED'
+          raise ArgumentError, "You must set checksum_mode: 'ENABLED' " +
+            "when providing a on_checksum_validated callback"
+        end
+
+        if @on_checksum_validated && !@on_checksum_validated.respond_to?(:call)
+          raise ArgumentError, 'on_checksum_validated must be callable'
+        end
+      end
+
       def multipart_download
         resp = @client.head_object(@params.merge(part_number: 1))
         count = resp.parts_count
         if count.nil? || count <= 1
-          resp.content_length < MIN_CHUNK_SIZE ?
-            single_request :
+          if resp.content_length <= MIN_CHUNK_SIZE
+            single_request
+          else
             multithreaded_get_by_ranges(construct_chunks(resp.content_length))
+          end
         else
           # partNumber is an option
           resp = @client.head_object(@params)
-          resp.content_length < MIN_CHUNK_SIZE ?
-            single_request :
+          if resp.content_length <= MIN_CHUNK_SIZE
+            single_request
+          else
             compute_mode(resp.content_length, count)
+          end
         end
       end
 
@@ -82,10 +103,11 @@ module Aws
         offset = 0
         default_chunk_size = compute_chunk(file_size)
         chunks = []
-        while offset <= file_size
+        while offset < file_size
           progress = offset + default_chunk_size
-          chunks << "bytes=#{offset}-#{progress < file_size ? progress : file_size}"
-          offset = progress + 1
+          progress = file_size if progress > file_size
+          chunks << "bytes=#{offset}-#{progress - 1}"
+          offset = progress
         end
         chunks
       end
@@ -94,12 +116,9 @@ module Aws
         if @chunk_size && @chunk_size > file_size
           raise ArgumentError, ":chunk_size shouldn't exceed total file size."
         else
-          chunk_size = @chunk_size || [
-            (file_size.to_f / MAX_PARTS).ceil,
-            MIN_CHUNK_SIZE
+          @chunk_size || [
+            (file_size.to_f / MAX_PARTS).ceil, MIN_CHUNK_SIZE
           ].max.to_i
-          chunk_size -= 1 if file_size % chunk_size == 1
-          chunk_size
         end
       end
 
@@ -125,6 +144,9 @@ module Aws
                 @params.merge(param.to_sym => chunk)
               )
               write(resp)
+              if @on_checksum_validated && resp.checksum_validated
+                @on_checksum_validated.call(resp.checksum_validated, resp)
+              end
             end
           end
           threads.each(&:join)
@@ -134,13 +156,21 @@ module Aws
       def write(resp)
         range, _ = resp.content_range.split(' ').last.split('/')
         head, _ = range.split('-').map {|s| s.to_i}
-        IO.write(@path, resp.body.read, head)
+        File.write(@path, resp.body.read, head)
       end
 
       def single_request
-        @client.get_object(
+        resp = @client.get_object(
           @params.merge(response_target: @path)
         )
+
+        return resp unless @on_checksum_validated
+
+        if resp.checksum_validated
+          @on_checksum_validated.call(resp.checksum_validated, resp)
+        end
+
+        resp
       end
     end
   end

data/lib/aws-sdk-s3/file_uploader.rb

@@ -11,7 +11,7 @@ module Aws
 
       # @param [Hash] options
       # @option options [Client] :client
-      # @option options [Integer] :multipart_threshold (15728640)
+      # @option options [Integer] :multipart_threshold (104857600)
       def initialize(options = {})
         @options = options
         @client = options[:client] || Client.new
@@ -32,12 +32,19 @@ module Aws
       # @option options [Proc] :progress_callback
       #   A Proc that will be called when each chunk of the upload is sent.
       #   It will be invoked with [bytes_read], [total_sizes]
+      # @option options [Integer] :thread_count
+      #   The thread count to use for multipart uploads. Ignored for
+      #   objects smaller than the multipart threshold.
       # @return [void]
       def upload(source, options = {})
-        if File.size(source) >= multipart_threshold
-          MultipartFileUploader.new(@options).upload(source, options)
-        else
-          put_object(source, options)
+        Aws::Plugins::UserAgent.feature('s3-transfer') do
+          if File.size(source) >= multipart_threshold
+            MultipartFileUploader.new(@options).upload(source, options)
+          else
+            # remove multipart parameters not supported by put_object
+            options.delete(:thread_count)
+            put_object(source, options)
+          end
         end
       end
 

data/lib/aws-sdk-s3/multipart_file_uploader.rb

@@ -21,6 +21,10 @@ module Aws
         Client.api.operation(:create_multipart_upload).input.shape.member_names
       )
 
+      COMPLETE_OPTIONS = Set.new(
+        Client.api.operation(:complete_multipart_upload).input.shape.member_names
+      )
+
       # @api private
       UPLOAD_PART_OPTIONS = Set.new(
         Client.api.operation(:upload_part).input.shape.member_names
@@ -42,7 +46,7 @@ module Aws
       # @option options [Proc] :progress_callback
       #   A Proc that will be called when each chunk of the upload is sent.
       #   It will be invoked with [bytes_read], [total_sizes]
-      # @return [void]
+      # @return [Seahorse::Client::Response] - the CompleteMultipartUploadResponse
       def upload(source, options = {})
         if File.size(source) < MIN_PART_SIZE
           raise ArgumentError, FILE_TOO_SMALL
@@ -61,10 +65,10 @@ module Aws
 
       def complete_upload(upload_id, parts, options)
         @client.complete_multipart_upload(
-          bucket: options[:bucket],
-          key: options[:key],
-          upload_id: upload_id,
-          multipart_upload: { parts: parts }
+          **complete_opts(options).merge(
+            upload_id: upload_id,
+            multipart_upload: { parts: parts }
+          )
         )
       end
 
@@ -123,6 +127,13 @@ module Aws
         end
       end
 
+      def complete_opts(options)
+        COMPLETE_OPTIONS.inject({}) do |hash, key|
+          hash[key] = options[key] if options.key?(key)
+          hash
+        end
+      end
+
       def upload_part_opts(options)
         UPLOAD_PART_OPTIONS.inject({}) do |hash, key|
           hash[key] = options[key] if options.key?(key)
@@ -147,7 +158,15 @@ module Aws
                 end
                 resp = @client.upload_part(part)
                 part[:body].close
-                completed.push(etag: resp.etag, part_number: part[:part_number])
+                completed_part = {etag: resp.etag, part_number: part[:part_number]}
+
+                # get the requested checksum from the response
+                if part[:checksum_algorithm]
+                  k = "checksum_#{part[:checksum_algorithm].downcase}".to_sym
+                  completed_part[k] = resp[k]
+                end
+
+                completed.push(completed_part)
               end
               nil
             rescue => error
@@ -224,4 +243,4 @@ module Aws
       end
     end
   end
-end
+end

data/lib/aws-sdk-s3/multipart_stream_uploader.rb

@@ -26,6 +26,10 @@ module Aws
       UPLOAD_PART_OPTIONS =
         Set.new(Client.api.operation(:upload_part).input.shape.member_names)
 
+      # @api private
+      COMPLETE_UPLOAD_OPTIONS =
+        Set.new(Client.api.operation(:complete_multipart_upload).input.shape.member_names)
+
       # @option options [Client] :client
       def initialize(options = {})
         @client = options[:client] || Client.new
@@ -39,11 +43,13 @@ module Aws
 
       # @option options [required,String] :bucket
       # @option options [required,String] :key
-      # @return [void]
+      # @return [Seahorse::Client::Response] - the CompleteMultipartUploadResponse
       def upload(options = {}, &block)
-        upload_id = initiate_upload(options)
-        parts = upload_parts(upload_id, options, &block)
-        complete_upload(upload_id, parts, options)
+        Aws::Plugins::UserAgent.feature('s3-transfer') do
+          upload_id = initiate_upload(options)
+          parts = upload_parts(upload_id, options, &block)
+          complete_upload(upload_id, parts, options)
+        end
       end
 
       private
@@ -54,17 +60,22 @@ module Aws
 
       def complete_upload(upload_id, parts, options)
         @client.complete_multipart_upload(
-          bucket: options[:bucket],
-          key: options[:key],
-          upload_id: upload_id,
-          multipart_upload: { parts: parts })
+          **complete_opts(options).merge(
+            upload_id: upload_id,
+            multipart_upload: { parts: parts }
+          )
+        )
       end
 
       def upload_parts(upload_id, options, &block)
         completed = Queue.new
+        thread_errors = []
         errors = begin
           IO.pipe do |read_pipe, write_pipe|
-            threads = upload_in_threads(read_pipe, completed, upload_part_opts(options).merge(upload_id: upload_id))
+            threads = upload_in_threads(
+              read_pipe, completed,
+              upload_part_opts(options).merge(upload_id: upload_id),
+              thread_errors)
             begin
               block.call(write_pipe)
             ensure
@@ -74,7 +85,7 @@ module Aws
             threads.map(&:value).compact
           end
         rescue => e
-          [e]
+          thread_errors + [e]
         end
 
         if errors.empty?
@@ -113,6 +124,13 @@ module Aws
         end
       end
 
+      def complete_opts(options)
+        COMPLETE_UPLOAD_OPTIONS.inject({}) do |hash, key|
+          hash[key] = options[key] if options.key?(key)
+          hash
+        end
+      end
+
       def read_to_part_body(read_pipe)
         return if read_pipe.closed?
         temp_io = @tempfile ? Tempfile.new(TEMPFILE_PREIX) : StringIO.new(String.new)
@@ -130,7 +148,7 @@ module Aws
         end
       end
 
-      def upload_in_threads(read_pipe, completed, options)
+      def upload_in_threads(read_pipe, completed, options, thread_errors)
         mutex = Mutex.new
         part_number = 0
         @thread_count.times.map do
@@ -147,7 +165,14 @@ module Aws
                     part_number: thread_part_number,
                   )
                   resp = @client.upload_part(part)
-                  completed << {etag: resp.etag, part_number: part[:part_number]}
+                  completed_part = {etag: resp.etag, part_number: part[:part_number]}
+
+                  # get the requested checksum from the response
+                  if part[:checksum_algorithm]
+                    k = "checksum_#{part[:checksum_algorithm].downcase}".to_sym
+                    completed_part[k] = resp[k]
+                  end
+                  completed.push(completed_part)
                 ensure
                   if Tempfile === body
                     body.close
@@ -160,7 +185,10 @@ module Aws
               nil
             rescue => error
               # keep other threads from uploading other parts
-              mutex.synchronize { read_pipe.close_read unless read_pipe.closed? }
+              mutex.synchronize do
+                thread_errors.push(error)
+                read_pipe.close_read unless read_pipe.closed?
+              end
               error
             end
           end

data/lib/aws-sdk-s3/multipart_upload.rb

@@ -87,6 +87,12 @@ module Aws::S3
       data[:initiator]
     end
 
+    # The algorithm that was used to create a checksum of the object.
+    # @return [String]
+    def checksum_algorithm
+      data[:checksum_algorithm]
+    end
+
     # @!endgroup
 
     # @return [Client]
@@ -211,7 +217,9 @@ module Aws::S3
           :retry
         end
       end
-      Aws::Waiters::Waiter.new(options).wait({})
+      Aws::Plugins::UserAgent.feature('resource') do
+        Aws::Waiters::Waiter.new(options).wait({})
+      end
     end
 
     # @!group Actions
@@ -226,8 +234,8 @@ module Aws::S3
     # @option options [String] :request_payer
     #   Confirms that the requester knows that they will be charged for the
     #   request. Bucket owners need not specify this parameter in their
-    #   requests. For information about downloading objects from requester
-    #   pays buckets, see [Downloading Objects in Requestor Pays Buckets][1]
+    #   requests. For information about downloading objects from Requester
+    #   Pays buckets, see [Downloading Objects in Requester Pays Buckets][1]
     #   in the *Amazon S3 User Guide*.
     #
     #
@@ -235,8 +243,8 @@ module Aws::S3
     #   [1]: https://docs.aws.amazon.com/AmazonS3/latest/dev/ObjectsinRequesterPaysBuckets.html
     # @option options [String] :expected_bucket_owner
     #   The account ID of the expected bucket owner. If the bucket is owned by
-    #   a different account, the request will fail with an HTTP `403 (Access
-    #   Denied)` error.
+    #   a different account, the request fails with the HTTP status code `403
+    #   Forbidden` (access denied).
     # @return [Types::AbortMultipartUploadOutput]
     def abort(options = {})
       options = options.merge(
@@ -244,7 +252,9 @@ module Aws::S3
         key: @object_key,
         upload_id: @id
       )
-      resp = @client.abort_multipart_upload(options)
+      resp = Aws::Plugins::UserAgent.feature('resource') do
+        @client.abort_multipart_upload(options)
+      end
       resp.data
     end
 
@@ -255,21 +265,72 @@ module Aws::S3
     #       parts: [
     #         {
     #           etag: "ETag",
+    #           checksum_crc32: "ChecksumCRC32",
+    #           checksum_crc32c: "ChecksumCRC32C",
+    #           checksum_sha1: "ChecksumSHA1",
+    #           checksum_sha256: "ChecksumSHA256",
     #           part_number: 1,
     #         },
     #       ],
     #     },
+    #     checksum_crc32: "ChecksumCRC32",
+    #     checksum_crc32c: "ChecksumCRC32C",
+    #     checksum_sha1: "ChecksumSHA1",
+    #     checksum_sha256: "ChecksumSHA256",
     #     request_payer: "requester", # accepts requester
     #     expected_bucket_owner: "AccountId",
+    #     sse_customer_algorithm: "SSECustomerAlgorithm",
+    #     sse_customer_key: "SSECustomerKey",
+    #     sse_customer_key_md5: "SSECustomerKeyMD5",
     #   })
     # @param [Hash] options ({})
     # @option options [Types::CompletedMultipartUpload] :multipart_upload
     #   The container for the multipart upload request information.
+    # @option options [String] :checksum_crc32
+    #   This header can be used as a data integrity check to verify that the
+    #   data received is the same data that was originally sent. This header
+    #   specifies the base64-encoded, 32-bit CRC32 checksum of the object. For
+    #   more information, see [Checking object integrity][1] in the *Amazon S3
+    #   User Guide*.
+    #
+    #
+    #
+    #   [1]: https://docs.aws.amazon.com/AmazonS3/latest/userguide/checking-object-integrity.html
+    # @option options [String] :checksum_crc32c
+    #   This header can be used as a data integrity check to verify that the
+    #   data received is the same data that was originally sent. This header
+    #   specifies the base64-encoded, 32-bit CRC32C checksum of the object.
+    #   For more information, see [Checking object integrity][1] in the
+    #   *Amazon S3 User Guide*.
+    #
+    #
+    #
+    #   [1]: https://docs.aws.amazon.com/AmazonS3/latest/userguide/checking-object-integrity.html
+    # @option options [String] :checksum_sha1
+    #   This header can be used as a data integrity check to verify that the
+    #   data received is the same data that was originally sent. This header
+    #   specifies the base64-encoded, 160-bit SHA-1 digest of the object. For
+    #   more information, see [Checking object integrity][1] in the *Amazon S3
+    #   User Guide*.
+    #
+    #
+    #
+    #   [1]: https://docs.aws.amazon.com/AmazonS3/latest/userguide/checking-object-integrity.html
+    # @option options [String] :checksum_sha256
+    #   This header can be used as a data integrity check to verify that the
+    #   data received is the same data that was originally sent. This header
+    #   specifies the base64-encoded, 256-bit SHA-256 digest of the object.
+    #   For more information, see [Checking object integrity][1] in the
+    #   *Amazon S3 User Guide*.
+    #
+    #
+    #
+    #   [1]: https://docs.aws.amazon.com/AmazonS3/latest/userguide/checking-object-integrity.html
     # @option options [String] :request_payer
     #   Confirms that the requester knows that they will be charged for the
     #   request. Bucket owners need not specify this parameter in their
-    #   requests. For information about downloading objects from requester
-    #   pays buckets, see [Downloading Objects in Requestor Pays Buckets][1]
+    #   requests. For information about downloading objects from Requester
+    #   Pays buckets, see [Downloading Objects in Requester Pays Buckets][1]
     #   in the *Amazon S3 User Guide*.
     #
     #
@@ -277,8 +338,35 @@ module Aws::S3
     #   [1]: https://docs.aws.amazon.com/AmazonS3/latest/dev/ObjectsinRequesterPaysBuckets.html
     # @option options [String] :expected_bucket_owner
     #   The account ID of the expected bucket owner. If the bucket is owned by
-    #   a different account, the request will fail with an HTTP `403 (Access
-    #   Denied)` error.
+    #   a different account, the request fails with the HTTP status code `403
+    #   Forbidden` (access denied).
+    # @option options [String] :sse_customer_algorithm
+    #   The server-side encryption (SSE) algorithm used to encrypt the object.
+    #   This parameter is needed only when the object was created using a
+    #   checksum algorithm. For more information, see [Protecting data using
+    #   SSE-C keys][1] in the *Amazon S3 User Guide*.
+    #
+    #
+    #
+    #   [1]: https://docs.aws.amazon.com/AmazonS3/latest/dev/ServerSideEncryptionCustomerKeys.html
+    # @option options [String] :sse_customer_key
+    #   The server-side encryption (SSE) customer managed key. This parameter
+    #   is needed only when the object was created using a checksum algorithm.
+    #   For more information, see [Protecting data using SSE-C keys][1] in the
+    #   *Amazon S3 User Guide*.
+    #
+    #
+    #
+    #   [1]: https://docs.aws.amazon.com/AmazonS3/latest/dev/ServerSideEncryptionCustomerKeys.html
+    # @option options [String] :sse_customer_key_md5
+    #   The MD5 server-side encryption (SSE) customer managed key. This
+    #   parameter is needed only when the object was created using a checksum
+    #   algorithm. For more information, see [Protecting data using SSE-C
+    #   keys][1] in the *Amazon S3 User Guide*.
+    #
+    #
+    #
+    #   [1]: https://docs.aws.amazon.com/AmazonS3/latest/dev/ServerSideEncryptionCustomerKeys.html
     # @return [Object]
     def complete(options = {})
       options = options.merge(
@@ -286,7 +374,9 @@ module Aws::S3
         key: @object_key,
         upload_id: @id
       )
-      @client.complete_multipart_upload(options)
+      Aws::Plugins::UserAgent.feature('resource') do
+        @client.complete_multipart_upload(options)
+      end
       Object.new(
         bucket_name: @bucket_name,
         key: @object_key,
@@ -322,13 +412,16 @@ module Aws::S3
     #   parts = multipart_upload.parts({
     #     request_payer: "requester", # accepts requester
     #     expected_bucket_owner: "AccountId",
+    #     sse_customer_algorithm: "SSECustomerAlgorithm",
+    #     sse_customer_key: "SSECustomerKey",
+    #     sse_customer_key_md5: "SSECustomerKeyMD5",
     #   })
     # @param [Hash] options ({})
     # @option options [String] :request_payer
     #   Confirms that the requester knows that they will be charged for the
     #   request. Bucket owners need not specify this parameter in their
-    #   requests. For information about downloading objects from requester
-    #   pays buckets, see [Downloading Objects in Requestor Pays Buckets][1]
+    #   requests. For information about downloading objects from Requester
+    #   Pays buckets, see [Downloading Objects in Requester Pays Buckets][1]
     #   in the *Amazon S3 User Guide*.
     #
     #
@@ -336,8 +429,35 @@ module Aws::S3
     #   [1]: https://docs.aws.amazon.com/AmazonS3/latest/dev/ObjectsinRequesterPaysBuckets.html
     # @option options [String] :expected_bucket_owner
     #   The account ID of the expected bucket owner. If the bucket is owned by
-    #   a different account, the request will fail with an HTTP `403 (Access
-    #   Denied)` error.
+    #   a different account, the request fails with the HTTP status code `403
+    #   Forbidden` (access denied).
+    # @option options [String] :sse_customer_algorithm
+    #   The server-side encryption (SSE) algorithm used to encrypt the object.
+    #   This parameter is needed only when the object was created using a
+    #   checksum algorithm. For more information, see [Protecting data using
+    #   SSE-C keys][1] in the *Amazon S3 User Guide*.
+    #
+    #
+    #
+    #   [1]: https://docs.aws.amazon.com/AmazonS3/latest/dev/ServerSideEncryptionCustomerKeys.html
+    # @option options [String] :sse_customer_key
+    #   The server-side encryption (SSE) customer managed key. This parameter
+    #   is needed only when the object was created using a checksum algorithm.
+    #   For more information, see [Protecting data using SSE-C keys][1] in the
+    #   *Amazon S3 User Guide*.
+    #
+    #
+    #
+    #   [1]: https://docs.aws.amazon.com/AmazonS3/latest/dev/ServerSideEncryptionCustomerKeys.html
+    # @option options [String] :sse_customer_key_md5
+    #   The MD5 server-side encryption (SSE) customer managed key. This
+    #   parameter is needed only when the object was created using a checksum
+    #   algorithm. For more information, see [Protecting data using SSE-C
+    #   keys][1] in the *Amazon S3 User Guide*.
+    #
+    #
+    #
+    #   [1]: https://docs.aws.amazon.com/AmazonS3/latest/dev/ServerSideEncryptionCustomerKeys.html
     # @return [MultipartUploadPart::Collection]
     def parts(options = {})
       batches = Enumerator.new do |y|
@@ -346,7 +466,9 @@ module Aws::S3
           key: @object_key,
           upload_id: @id
         )
-        resp = @client.list_parts(options)
+        resp = Aws::Plugins::UserAgent.feature('resource') do
+          @client.list_parts(options)
+        end
         resp.each_page do |page|
           batch = []
           page.data.parts.each do |p|