discourse/spec/services/external_upload_manager_spec.rb
Martin Brennan b500949ef6
FEATURE: Initial implementation of direct S3 uploads with uppy and stubs (#13787)
This adds a few different things to allow for direct S3 uploads using uppy. **These changes are still not the default.** There are hidden `enable_experimental_image_uploader` and `enable_direct_s3_uploads`  settings that must be turned on for any of this code to be used, and even if they are turned on only the User Card Background for the user profile actually uses uppy-image-uploader.

A new `ExternalUploadStub` model and database table is introduced in this pull request. This is used to keep track of uploads that are uploaded to a temporary location in S3 with the direct to S3 code, and they are eventually deleted a) when the direct upload is completed and b) after a certain time period of not being used. 

### Starting a direct S3 upload

When an S3 direct upload is initiated with uppy, we first request a presigned PUT URL from the new `generate-presigned-put` endpoint in `UploadsController`. This generates an S3 key in the `temp` folder inside the correct bucket path, along with any metadata from the clientside (e.g. the SHA1 checksum described below). This will also create an `ExternalUploadStub` and store the details of the temp object key and the file being uploaded.

Once the clientside has this URL, uppy will upload the file direct to S3 using the presigned URL. Once the upload is complete we go to the next stage.

### Completing a direct S3 upload

Once the upload to S3 is done we call the new `complete-external-upload` route with the unique identifier of the `ExternalUploadStub` created earlier. Only the user who made the stub can complete the external upload. One of two paths is followed via the `ExternalUploadManager`.

1. If the object in S3 is too large (currently 100mb defined by `ExternalUploadManager::DOWNLOAD_LIMIT`) we do not download and generate the SHA1 for that file. Instead we create the `Upload` record via `UploadCreator` and simply copy it to its final destination on S3 then delete the initial temp file. Several modifications to `UploadCreator` have been made to accommodate this.

2. If the object in S3 is small enough, we download it. When the temporary S3 file is downloaded, we compare the SHA1 checksum generated by the browser with the actual SHA1 checksum of the file generated by ruby. The browser SHA1 checksum is stored on the object in S3 with metadata, and is generated via the `UppyChecksum` plugin. Keep in mind that some browsers will not generate this due to compatibility or other issues.

    We then follow the normal `UploadCreator` path with one exception. To cut down on having to re-upload the file again, if there are no changes (such as resizing etc) to the file in `UploadCreator` we follow the same copy + delete temp path that we do for files that are too large.

3. Finally we return the serialized upload record back to the client

There are several errors that could happen that are handled by `UploadsController` as well.

Also in this PR is some refactoring of `displayErrorForUpload` to handle both uppy and jquery file uploader errors.
2021-07-28 08:42:25 +10:00

223 lines
7.6 KiB
Ruby

# frozen_string_literal: true
require 'rails_helper'
RSpec.describe ExternalUploadManager do
fab!(:user) { Fabricate(:user) }
let(:type) { "card_background" }
let!(:logo_file) { file_from_fixtures("logo.png") }
let!(:pdf_file) { file_from_fixtures("large.pdf", "pdf") }
let(:object_size) { 1.megabyte }
let(:etag) { "e696d20564859cbdf77b0f51cbae999a" }
let(:client_sha1) { Upload.generate_digest(object_file) }
let(:sha1) { Upload.generate_digest(object_file) }
let(:object_file) { logo_file }
let(:metadata_headers) { {} }
let!(:external_upload_stub) { Fabricate(:image_external_upload_stub, created_by: user) }
let(:upload_base_url) { "https://#{SiteSetting.s3_upload_bucket}.s3.#{SiteSetting.s3_region}.amazonaws.com" }
subject do
ExternalUploadManager.new(external_upload_stub)
end
before do
SiteSetting.authorized_extensions += "|pdf"
SiteSetting.max_attachment_size_kb = 210.megabytes / 1000
setup_s3
stub_head_object
stub_download_object_filehelper
stub_copy_object
stub_delete_object
end
describe "#can_promote?" do
it "returns false if the external stub status is not created" do
external_upload_stub.update!(status: ExternalUploadStub.statuses[:uploaded])
expect(subject.can_promote?).to eq(false)
end
end
describe "#promote_to_upload!" do
context "when stubbed upload is < DOWNLOAD_LIMIT (small enough to download + generate sha)" do
let!(:external_upload_stub) { Fabricate(:image_external_upload_stub, created_by: user) }
let(:object_size) { 1.megabyte }
let(:object_file) { logo_file }
context "when the download of the s3 file fails" do
before do
FileHelper.stubs(:download).returns(nil)
end
it "raises an error" do
expect { subject.promote_to_upload! }.to raise_error(ExternalUploadManager::DownloadFailedError)
end
end
context "when the upload is not in the created status" do
before do
external_upload_stub.update!(status: ExternalUploadStub.statuses[:uploaded])
end
it "raises an error" do
expect { subject.promote_to_upload! }.to raise_error(ExternalUploadManager::CannotPromoteError)
end
end
context "when the upload does not get changed in UploadCreator (resized etc.)" do
it "copies the stubbed upload on S3 to its new destination and deletes it" do
upload = subject.promote_to_upload!
expect(WebMock).to have_requested(
:put,
"#{upload_base_url}/original/1X/#{upload.sha1}.png",
).with(headers: { 'X-Amz-Copy-Source' => "#{SiteSetting.s3_upload_bucket}/#{external_upload_stub.key}" })
expect(WebMock).to have_requested(
:delete,
"#{upload_base_url}/#{external_upload_stub.key}"
)
end
it "errors if the image upload is too big" do
SiteSetting.max_image_size_kb = 1
upload = subject.promote_to_upload!
expect(upload.errors.full_messages).to include(
"Filesize " + I18n.t("upload.images.too_large", max_size_kb: SiteSetting.max_image_size_kb)
)
end
it "errors if the extension is not supported" do
SiteSetting.authorized_extensions = ""
upload = subject.promote_to_upload!
expect(upload.errors.full_messages).to include(
"Original filename " + I18n.t("upload.unauthorized", authorized_extensions: "")
)
end
end
context "when the upload does get changed by the UploadCreator" do
let(:file) { file_from_fixtures("should_be_jpeg.heic", "images") }
it "creates a new upload in s3 (not copy) and deletes the original stubbed upload" do
upload = subject.promote_to_upload!
expect(WebMock).to have_requested(
:put,
"#{upload_base_url}/original/1X/#{upload.sha1}.png"
)
expect(WebMock).to have_requested(
:delete, "#{upload_base_url}/#{external_upload_stub.key}"
)
end
end
context "when the sha has been set on the s3 object metadata by the clientside JS" do
let(:metadata_headers) { { "x-amz-meta-sha1-checksum" => client_sha1 } }
context "when the downloaded file sha1 does not match the client sha1" do
let(:client_sha1) { "blahblah" }
it "raises an error and marks upload as failed" do
expect { subject.promote_to_upload! }.to raise_error(ExternalUploadManager::ChecksumMismatchError)
expect(external_upload_stub.reload.status).to eq(ExternalUploadStub.statuses[:failed])
end
end
end
end
context "when stubbed upload is > DOWNLOAD_LIMIT (too big to download, generate a fake sha)" do
let(:object_size) { 200.megabytes }
let(:object_file) { pdf_file }
let!(:external_upload_stub) { Fabricate(:attachment_external_upload_stub, created_by: user) }
before do
UploadCreator.any_instance.stubs(:generate_fake_sha1_hash).returns("testbc60eb18e8f974cbfae8bb0f069c3a311024")
end
it "does not try and download the file" do
FileHelper.expects(:download).never
subject.promote_to_upload!
end
it "generates a fake sha for the upload record" do
upload = subject.promote_to_upload!
expect(upload.sha1).not_to eq(sha1)
expect(upload.original_sha1).to eq(nil)
expect(upload.filesize).to eq(object_size)
end
it "marks the stub as uploaded" do
subject.promote_to_upload!
expect(external_upload_stub.reload.status).to eq(ExternalUploadStub.statuses[:uploaded])
end
it "copies the stubbed upload on S3 to its new destination and deletes it" do
upload = subject.promote_to_upload!
expect(WebMock).to have_requested(
:put,
"#{upload_base_url}/original/1X/#{upload.sha1}.pdf"
).with(headers: { 'X-Amz-Copy-Source' => "#{SiteSetting.s3_upload_bucket}/#{external_upload_stub.key}" })
expect(WebMock).to have_requested(
:delete, "#{upload_base_url}/#{external_upload_stub.key}"
)
end
end
end
def stub_head_object
stub_request(
:head,
"#{upload_base_url}/#{external_upload_stub.key}"
).to_return(
status: 200,
headers: {
ETag: etag,
"Content-Length" => object_size,
"Content-Type" => "image/png",
}.merge(metadata_headers)
)
end
def stub_download_object_filehelper
signed_url = Discourse.store.signed_url_for_path(external_upload_stub.key)
uri = URI.parse(signed_url)
signed_url = uri.to_s.gsub(uri.query, "")
stub_request(:get, signed_url).with(query: hash_including({})).to_return(
status: 200,
body: object_file.read
)
end
def stub_copy_object
copy_object_result = <<~BODY
<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n
<CopyObjectResult
xmlns=\"http://s3.amazonaws.com/doc/2006-03-01/\">
<LastModified>2021-07-19T04:10:41.000Z</LastModified>
<ETag>&quot;#{etag}&quot;</ETag>
</CopyObjectResult>
BODY
stub_request(
:put,
"#{upload_base_url}/original/1X/testbc60eb18e8f974cbfae8bb0f069c3a311024.pdf"
).to_return(
status: 200,
headers: { "ETag" => etag },
body: copy_object_result
)
stub_request(
:put,
"#{upload_base_url}/original/1X/bc975735dfc6409c1c2aa5ebf2239949bcbdbd65.png"
).to_return(
status: 200,
headers: { "ETag" => etag },
body: copy_object_result
)
end
def stub_delete_object
stub_request(
:delete, "#{upload_base_url}/#{external_upload_stub.key}"
).to_return(
status: 200
)
end
end