discourse/spec/jobs/clean_up_uploads_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

318 lines
10 KiB
Ruby

# frozen_string_literal: true
require 'rails_helper'
describe Jobs::CleanUpUploads do
def fabricate_upload(attributes = {})
Fabricate(:upload, { created_at: 2.hours.ago }.merge(attributes))
end
fab! :expired_upload do
fabricate_upload
end
before do
SiteSetting.clean_up_uploads = true
SiteSetting.clean_orphan_uploads_grace_period_hours = 1
# pre-fabrication resets created_at, so re-expire the upload
expired_upload
freeze_time 2.hours.from_now
Jobs::CleanUpUploads.new.reset_last_cleanup!
end
it "only runs upload cleanup every grace period / 2 time" do
SiteSetting.clean_orphan_uploads_grace_period_hours = 48
expired = fabricate_upload(created_at: 49.hours.ago)
Jobs::CleanUpUploads.new.execute(nil)
expect(Upload.exists?(id: expired.id)).to eq(false)
upload = fabricate_upload(created_at: 72.hours.ago)
Jobs::CleanUpUploads.new.execute(nil)
expect(Upload.exists?(id: upload.id)).to eq(true)
freeze_time 25.hours.from_now
Jobs::CleanUpUploads.new.execute(nil)
expect(Upload.exists?(id: upload.id)).to eq(false)
end
it "deletes orphan uploads" do
expect do
Jobs::CleanUpUploads.new.execute(nil)
end.to change { Upload.count }.by(-1)
expect(Upload.exists?(id: expired_upload.id)).to eq(false)
end
describe 'when clean_up_uploads is disabled' do
before do
SiteSetting.clean_up_uploads = false
end
it 'should still delete invalid upload records' do
upload2 = fabricate_upload(
url: "",
retain_hours: nil
)
expect do
Jobs::CleanUpUploads.new.execute(nil)
end.to change { Upload.count }.by(-1)
expect(Upload.exists?(id: expired_upload.id)).to eq(true)
expect(Upload.exists?(id: upload2.id)).to eq(false)
end
end
it 'does not clean up upload site settings' do
begin
original_provider = SiteSetting.provider
SiteSetting.provider = SiteSettings::DbProvider.new(SiteSetting)
SiteSetting.clean_orphan_uploads_grace_period_hours = 1
system_upload = fabricate_upload(id: -999)
logo_upload = fabricate_upload
logo_small_upload = fabricate_upload
digest_logo_upload = fabricate_upload
mobile_logo_upload = fabricate_upload
large_icon_upload = fabricate_upload
opengraph_image_upload = fabricate_upload
twitter_summary_large_image_upload = fabricate_upload
favicon_upload = fabricate_upload
apple_touch_icon_upload = fabricate_upload
SiteSetting.logo = logo_upload
SiteSetting.logo_small = logo_small_upload
SiteSetting.digest_logo = digest_logo_upload
SiteSetting.mobile_logo = mobile_logo_upload
SiteSetting.large_icon = large_icon_upload
SiteSetting.opengraph_image = opengraph_image_upload
SiteSetting.twitter_summary_large_image =
twitter_summary_large_image_upload
SiteSetting.favicon = favicon_upload
SiteSetting.apple_touch_icon = apple_touch_icon_upload
Jobs::CleanUpUploads.new.execute(nil)
[
logo_upload,
logo_small_upload,
digest_logo_upload,
mobile_logo_upload,
large_icon_upload,
opengraph_image_upload,
twitter_summary_large_image_upload,
favicon_upload,
apple_touch_icon_upload,
system_upload
].each { |record| expect(Upload.exists?(id: record.id)).to eq(true) }
fabricate_upload
SiteSetting.opengraph_image = ''
Jobs::CleanUpUploads.new.execute(nil)
ensure
SiteSetting.delete_all
SiteSetting.provider = original_provider
end
end
it "does not clean up selectable avatars" do
avatar1_upload = fabricate_upload
avatar2_upload = fabricate_upload
SiteSetting.selectable_avatars = [avatar1_upload, avatar2_upload]
Jobs::CleanUpUploads.new.execute(nil)
expect(Upload.exists?(id: expired_upload.id)).to eq(false)
expect(Upload.exists?(id: avatar1_upload.id)).to eq(true)
expect(Upload.exists?(id: avatar2_upload.id)).to eq(true)
end
it "does not delete profile background uploads" do
profile_background_upload = fabricate_upload
UserProfile.last.upload_profile_background(profile_background_upload)
Jobs::CleanUpUploads.new.execute(nil)
expect(Upload.exists?(id: expired_upload.id)).to eq(false)
expect(Upload.exists?(id: profile_background_upload.id)).to eq(true)
end
it "does not delete card background uploads" do
card_background_upload = fabricate_upload
UserProfile.last.upload_card_background(card_background_upload)
Jobs::CleanUpUploads.new.execute(nil)
expect(Upload.exists?(id: expired_upload.id)).to eq(false)
expect(Upload.exists?(id: card_background_upload.id)).to eq(true)
end
it "does not delete category logo uploads" do
category_logo_upload = fabricate_upload
Fabricate(:category, uploaded_logo: category_logo_upload)
Jobs::CleanUpUploads.new.execute(nil)
expect(Upload.exists?(id: expired_upload.id)).to eq(false)
expect(Upload.exists?(id: category_logo_upload.id)).to eq(true)
end
it "does not delete category background url uploads" do
category_logo_upload = fabricate_upload
Fabricate(:category, uploaded_background: category_logo_upload)
Jobs::CleanUpUploads.new.execute(nil)
expect(Upload.exists?(id: expired_upload.id)).to eq(false)
expect(Upload.exists?(id: category_logo_upload.id)).to eq(true)
end
it "does not delete post uploads" do
upload = fabricate_upload
Fabricate(:post, uploads: [upload])
Jobs::CleanUpUploads.new.execute(nil)
expect(Upload.exists?(id: expired_upload.id)).to eq(false)
expect(Upload.exists?(id: upload.id)).to eq(true)
end
it "does not delete user uploaded avatar" do
upload = fabricate_upload
Fabricate(:user, uploaded_avatar: upload)
Jobs::CleanUpUploads.new.execute(nil)
expect(Upload.exists?(id: expired_upload.id)).to eq(false)
expect(Upload.exists?(id: upload.id)).to eq(true)
end
it "does not delete user gravatar" do
upload = fabricate_upload
Fabricate(:user, user_avatar: Fabricate(:user_avatar, gravatar_upload: upload))
Jobs::CleanUpUploads.new.execute(nil)
expect(Upload.exists?(id: expired_upload.id)).to eq(false)
expect(Upload.exists?(id: upload.id)).to eq(true)
end
it "does not delete user custom upload" do
upload = fabricate_upload
Fabricate(:user, user_avatar: Fabricate(:user_avatar, custom_upload: upload))
Jobs::CleanUpUploads.new.execute(nil)
expect(Upload.exists?(id: expired_upload.id)).to eq(false)
expect(Upload.exists?(id: upload.id)).to eq(true)
end
it "does not delete uploads in a queued post" do
upload = fabricate_upload
upload2 = fabricate_upload
upload3 = fabricate_upload
Fabricate(:reviewable_queued_post_topic, payload: {
raw: "#{upload.sha1}\n#{upload2.short_url}"
})
Fabricate(:reviewable_queued_post_topic,
payload: {
raw: "#{upload3.sha1}"
},
status: Reviewable.statuses[:rejected]
)
Jobs::CleanUpUploads.new.execute(nil)
expect(Upload.exists?(id: expired_upload.id)).to eq(false)
expect(Upload.exists?(id: upload.id)).to eq(true)
expect(Upload.exists?(id: upload2.id)).to eq(true)
expect(Upload.exists?(id: upload3.id)).to eq(false)
end
it "does not delete uploads in a draft" do
upload = fabricate_upload
upload2 = fabricate_upload
Draft.set(Fabricate(:user), "test", 0, "#{upload.sha1}\n#{upload2.short_url}")
Jobs::CleanUpUploads.new.execute(nil)
expect(Upload.exists?(id: expired_upload.id)).to eq(false)
expect(Upload.exists?(id: upload.id)).to eq(true)
expect(Upload.exists?(id: upload2.id)).to eq(true)
end
it "does not delete uploads with an access control post ID (secure uploads)" do
upload = fabricate_upload(access_control_post_id: Fabricate(:post).id, secure: true)
Jobs::CleanUpUploads.new.execute(nil)
expect(Upload.exists?(id: expired_upload.id)).to eq(false)
expect(Upload.exists?(id: upload.id)).to eq(true)
end
it "does not delete custom emojis" do
upload = fabricate_upload
CustomEmoji.create!(name: 'test', upload: upload)
Jobs::CleanUpUploads.new.execute(nil)
expect(Upload.exists?(id: expired_upload.id)).to eq(false)
expect(Upload.exists?(id: upload.id)).to eq(true)
end
it "does not delete user exported csv uploads" do
csv_file = fabricate_upload
UserExport.create(file_name: "export.csv", user_id: Fabricate(:user).id, upload_id: csv_file.id)
Jobs::CleanUpUploads.new.execute(nil)
expect(Upload.exists?(id: expired_upload.id)).to eq(false)
expect(Upload.exists?(id: csv_file.id)).to eq(true)
end
it "does not delete theme setting uploads" do
theme = Fabricate(:theme)
theme_upload = fabricate_upload
ThemeSetting.create!(theme: theme, data_type: ThemeSetting.types[:upload], value: theme_upload.url, name: "my_setting_name")
Jobs::CleanUpUploads.new.execute(nil)
expect(Upload.exists?(id: expired_upload.id)).to eq(false)
expect(Upload.exists?(id: theme_upload.id)).to eq(true)
end
it "does not delete badges uploads" do
badge_image = fabricate_upload
badge = Fabricate(:badge, image_upload_id: badge_image.id)
Jobs::CleanUpUploads.new.execute(nil)
expect(Upload.exists?(id: expired_upload.id)).to eq(false)
expect(Upload.exists?(id: badge_image.id)).to eq(true)
end
it "deletes external upload stubs that have expired" do
external_stub1 = Fabricate(:external_upload_stub, status: ExternalUploadStub.statuses[:created], created_at: 10.minutes.ago)
external_stub2 = Fabricate(:external_upload_stub, status: ExternalUploadStub.statuses[:created], created_at: (ExternalUploadStub::CREATED_EXPIRY_HOURS.hours + 10.minutes).ago)
external_stub3 = Fabricate(:external_upload_stub, status: ExternalUploadStub.statuses[:uploaded], created_at: 10.minutes.ago)
external_stub4 = Fabricate(:external_upload_stub, status: ExternalUploadStub.statuses[:uploaded], created_at: (ExternalUploadStub::UPLOADED_EXPIRY_HOURS.hours + 10.minutes).ago)
Jobs::CleanUpUploads.new.execute(nil)
expect(ExternalUploadStub.pluck(:id)).to contain_exactly(external_stub1.id, external_stub3.id)
end
end