discourse/spec/services/external_upload_manager_spec.rb
Martin Brennan d295a16dab
FEATURE: Uppy direct S3 multipart uploads in composer (#14051)
This pull request introduces the endpoints required, and the JavaScript functionality in the `ComposerUppyUpload` mixin, for direct S3 multipart uploads. There are four new endpoints in the uploads controller:

* `create-multipart.json` - Creates the multipart upload in S3 along with an `ExternalUploadStub` record, storing information about the file in the same way as `generate-presigned-put.json` does for regular direct S3 uploads
* `batch-presign-multipart-parts.json` - Takes a list of part numbers and the unique identifier for an `ExternalUploadStub` record, and generates the presigned URLs for those parts if the multipart upload still exists and if the user has permission to access that upload
* `complete-multipart.json` - Completes the multipart upload in S3. Needs the full list of part numbers and their associated ETags which are returned when the part is uploaded to the presigned URL above. Only works if the user has permission to access the associated `ExternalUploadStub` record and the multipart upload still exists.

  After we confirm the upload is complete in S3, we go through the regular `UploadCreator` flow, the same as `complete-external-upload.json`, and promote the temporary upload S3 into a full `Upload` record, moving it to its final destination.
* `abort-multipart.json` - Aborts the multipart upload on S3 and destroys the `ExternalUploadStub` record if the user has permission to access that upload.

Also added are a few new columns to `ExternalUploadStub`:

* multipart - Whether or not this is a multipart upload
* external_upload_identifier - The "upload ID" for an S3 multipart upload
* filesize - The size of the file when the `create-multipart.json` or `generate-presigned-put.json` is called. This is used for validation.

When the user completes a direct S3 upload, either regular or multipart, we take the `filesize` that was captured when the `ExternalUploadStub` was first created and compare it with the final `Content-Length` size of the file where it is stored in S3. Then, if the two do not match, we throw an error, delete the file on S3, and ban the user from uploading files for N (default 5) minutes. This would only happen if the user uploads a different file than what they first specified, or in the case of multipart uploads uploaded larger chunks than needed. This is done to prevent abuse of S3 storage by bad actors.

Also included in this PR is an update to vendor/uppy.js. This has been built locally from the latest uppy source at d613b849a6. This must be done so that I can get my multipart upload changes into Discourse. When the Uppy team cuts a proper release, we can bump the package.json versions instead.
2021-08-25 08:46:54 +10:00

250 lines
8.8 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 "#ban_user_from_external_uploads!" do
after { Discourse.redis.flushdb }
it "bans the user from external uploads using a redis key" do
ExternalUploadManager.ban_user_from_external_uploads!(user: user)
expect(ExternalUploadManager.user_banned?(user)).to eq(true)
end
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, filesize: object_size) }
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, deletes the stub" do
expect { subject.promote_to_upload! }.to raise_error(ExternalUploadManager::ChecksumMismatchError)
expect(ExternalUploadStub.exists?(id: external_upload_stub.id)).to eq(false)
end
end
end
context "when the downloaded file size does not match the expected file size for the upload stub" do
before do
external_upload_stub.update!(filesize: 10)
end
after { Discourse.redis.flushdb }
it "raises an error, deletes the file immediately, and prevents the user from uploading external files for a few minutes" do
expect { subject.promote_to_upload! }.to raise_error(ExternalUploadManager::SizeMismatchError)
expect(ExternalUploadStub.exists?(id: external_upload_stub.id)).to eq(false)
expect(Discourse.redis.get("#{ExternalUploadManager::BAN_USER_REDIS_PREFIX}#{external_upload_stub.created_by_id}")).to eq("1")
expect(WebMock).to have_requested(
:delete,
"#{upload_base_url}/#{external_upload_stub.key}"
)
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, filesize: object_size) }
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