2019-05-03 06:17:27 +08:00
|
|
|
# frozen_string_literal: true
|
|
|
|
|
2016-06-30 22:55:01 +08:00
|
|
|
require "uri"
|
2017-06-13 19:27:05 +08:00
|
|
|
require "mini_mime"
|
2015-06-01 17:13:56 +08:00
|
|
|
require_dependency "file_store/base_store"
|
2014-09-25 04:52:09 +08:00
|
|
|
require_dependency "s3_helper"
|
2014-04-15 19:04:14 +08:00
|
|
|
require_dependency "file_helper"
|
2013-08-01 05:26:34 +08:00
|
|
|
|
2013-11-06 02:04:47 +08:00
|
|
|
module FileStore
|
2013-08-01 05:26:34 +08:00
|
|
|
|
2013-11-06 02:04:47 +08:00
|
|
|
class S3Store < BaseStore
|
2015-05-25 23:59:00 +08:00
|
|
|
TOMBSTONE_PREFIX ||= "tombstone/"
|
|
|
|
|
2016-08-19 14:08:04 +08:00
|
|
|
def initialize(s3_helper = nil)
|
2020-12-31 02:13:13 +08:00
|
|
|
@s3_helper = s3_helper
|
|
|
|
end
|
|
|
|
|
|
|
|
def s3_helper
|
|
|
|
@s3_helper ||= S3Helper.new(s3_bucket,
|
2018-12-19 13:32:32 +08:00
|
|
|
Rails.configuration.multisite ? multisite_tombstone_prefix : TOMBSTONE_PREFIX
|
|
|
|
)
|
2014-09-25 04:52:09 +08:00
|
|
|
end
|
2013-08-01 05:26:34 +08:00
|
|
|
|
2015-05-30 00:39:47 +08:00
|
|
|
def store_upload(file, upload, content_type = nil)
|
2021-05-27 23:42:25 +08:00
|
|
|
upload.url = nil
|
2016-08-15 16:06:29 +08:00
|
|
|
path = get_path_for_upload(upload)
|
2020-01-16 11:50:27 +08:00
|
|
|
url, upload.etag = store_file(
|
|
|
|
file,
|
|
|
|
path,
|
|
|
|
filename: upload.original_filename,
|
|
|
|
content_type: content_type,
|
|
|
|
cache_locally: true,
|
|
|
|
private_acl: upload.secure?
|
|
|
|
)
|
2019-01-04 14:16:22 +08:00
|
|
|
url
|
2013-11-06 02:04:47 +08:00
|
|
|
end
|
2013-08-01 05:26:34 +08:00
|
|
|
|
2021-07-28 06:42:25 +08:00
|
|
|
def move_existing_stored_upload(existing_external_upload_key, upload, content_type = nil)
|
|
|
|
upload.url = nil
|
|
|
|
path = get_path_for_upload(upload)
|
|
|
|
url, upload.etag = store_file(
|
|
|
|
nil,
|
|
|
|
path,
|
|
|
|
filename: upload.original_filename,
|
|
|
|
content_type: content_type,
|
|
|
|
cache_locally: false,
|
|
|
|
private_acl: upload.secure?,
|
|
|
|
move_existing: true,
|
|
|
|
existing_external_upload_key: existing_external_upload_key
|
|
|
|
)
|
|
|
|
url
|
|
|
|
end
|
|
|
|
|
2019-11-18 09:25:42 +08:00
|
|
|
def store_optimized_image(file, optimized_image, content_type = nil, secure: false)
|
2021-05-27 23:42:25 +08:00
|
|
|
optimized_image.url = nil
|
2016-08-15 16:06:29 +08:00
|
|
|
path = get_path_for_optimized_image(optimized_image)
|
2019-11-18 09:25:42 +08:00
|
|
|
url, optimized_image.etag = store_file(file, path, content_type: content_type, private_acl: secure)
|
2019-01-04 14:16:22 +08:00
|
|
|
url
|
2016-08-12 17:18:19 +08:00
|
|
|
end
|
|
|
|
|
2021-07-28 06:42:25 +08:00
|
|
|
# File is an actual Tempfile on disk
|
|
|
|
#
|
|
|
|
# An existing_external_upload_key is given for cases where move_existing is specified.
|
|
|
|
# This is an object already uploaded directly to S3 that we are now moving
|
|
|
|
# to its final resting place with the correct sha and key.
|
|
|
|
#
|
2015-05-30 00:39:47 +08:00
|
|
|
# options
|
|
|
|
# - filename
|
|
|
|
# - content_type
|
|
|
|
# - cache_locally
|
2021-07-28 06:42:25 +08:00
|
|
|
# - move_existing
|
|
|
|
# - existing_external_upload_key
|
2015-05-30 00:39:47 +08:00
|
|
|
def store_file(file, path, opts = {})
|
2019-05-03 06:17:27 +08:00
|
|
|
path = path.dup
|
|
|
|
|
2016-10-18 01:16:29 +08:00
|
|
|
filename = opts[:filename].presence || File.basename(path)
|
2015-05-30 00:39:47 +08:00
|
|
|
# cache file locally when needed
|
|
|
|
cache_file(file, File.basename(path)) if opts[:cache_locally]
|
2016-10-18 01:16:29 +08:00
|
|
|
options = {
|
2019-11-18 09:25:42 +08:00
|
|
|
acl: opts[:private_acl] ? "private" : "public-read",
|
2019-08-07 01:55:17 +08:00
|
|
|
cache_control: 'max-age=31556952, public, immutable',
|
2017-06-13 19:27:05 +08:00
|
|
|
content_type: opts[:content_type].presence || MiniMime.lookup_by_filename(filename)&.content_type
|
2016-10-18 01:16:29 +08:00
|
|
|
}
|
2020-06-17 09:16:37 +08:00
|
|
|
|
2020-07-09 11:31:48 +08:00
|
|
|
# add a "content disposition: attachment" header with the original
|
|
|
|
# filename for everything but safe images (not SVG). audio and video will
|
|
|
|
# still stream correctly in HTML players, and when a direct link is
|
|
|
|
# provided to any file but an image it will download correctly in the
|
|
|
|
# browser.
|
|
|
|
if !FileHelper.is_inline_image?(filename)
|
2020-06-23 15:10:56 +08:00
|
|
|
options[:content_disposition] = ActionDispatch::Http::ContentDisposition.format(
|
|
|
|
disposition: "attachment", filename: filename
|
|
|
|
)
|
2020-06-17 09:16:37 +08:00
|
|
|
end
|
2018-11-29 12:11:48 +08:00
|
|
|
|
2018-12-03 12:04:14 +08:00
|
|
|
path.prepend(File.join(upload_path, "/")) if Rails.configuration.multisite
|
2018-11-29 12:11:48 +08:00
|
|
|
|
2019-01-04 14:16:22 +08:00
|
|
|
# if this fails, it will throw an exception
|
2021-07-28 06:42:25 +08:00
|
|
|
if opts[:move_existing] && opts[:existing_external_upload_key]
|
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 https://github.com/transloadit/uppy/commit/d613b849a6591083f8a0968aa8d66537e231bbcd. 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 06:46:54 +08:00
|
|
|
original_path = opts[:existing_external_upload_key]
|
2021-07-28 06:42:25 +08:00
|
|
|
path, etag = s3_helper.copy(
|
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 https://github.com/transloadit/uppy/commit/d613b849a6591083f8a0968aa8d66537e231bbcd. 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 06:46:54 +08:00
|
|
|
original_path,
|
2021-07-28 06:42:25 +08:00
|
|
|
path,
|
|
|
|
options: options
|
|
|
|
)
|
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 https://github.com/transloadit/uppy/commit/d613b849a6591083f8a0968aa8d66537e231bbcd. 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 06:46:54 +08:00
|
|
|
delete_file(original_path)
|
2021-07-28 06:42:25 +08:00
|
|
|
else
|
|
|
|
path, etag = s3_helper.upload(file, path, options)
|
|
|
|
end
|
2019-01-04 14:16:22 +08:00
|
|
|
|
|
|
|
# return the upload url and etag
|
2019-11-15 04:10:51 +08:00
|
|
|
[File.join(absolute_base_url, path), etag]
|
2013-11-06 02:04:47 +08:00
|
|
|
end
|
2013-08-01 05:26:34 +08:00
|
|
|
|
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 https://github.com/transloadit/uppy/commit/d613b849a6591083f8a0968aa8d66537e231bbcd. 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 06:46:54 +08:00
|
|
|
def delete_file(path)
|
|
|
|
# delete the object outright without moving to tombstone,
|
|
|
|
# not recommended for most use cases
|
|
|
|
s3_helper.delete_object(path)
|
|
|
|
end
|
|
|
|
|
2016-08-15 11:21:24 +08:00
|
|
|
def remove_file(url, path)
|
2015-05-30 00:39:47 +08:00
|
|
|
return unless has_been_uploaded?(url)
|
|
|
|
# copy the removed file to tombstone
|
2020-12-31 02:13:13 +08:00
|
|
|
s3_helper.remove(path, true)
|
2013-11-06 02:04:47 +08:00
|
|
|
end
|
2013-08-14 04:08:29 +08:00
|
|
|
|
2018-08-08 11:26:05 +08:00
|
|
|
def copy_file(url, source, destination)
|
|
|
|
return unless has_been_uploaded?(url)
|
2020-12-31 02:13:13 +08:00
|
|
|
s3_helper.copy(source, destination)
|
2018-08-08 11:26:05 +08:00
|
|
|
end
|
|
|
|
|
2013-11-06 02:04:47 +08:00
|
|
|
def has_been_uploaded?(url)
|
2015-05-26 17:47:33 +08:00
|
|
|
return false if url.blank?
|
2016-06-30 22:55:01 +08:00
|
|
|
|
2020-05-23 12:56:13 +08:00
|
|
|
begin
|
2020-06-17 15:47:05 +08:00
|
|
|
parsed_url = URI.parse(UrlHelper.encode(url))
|
2020-06-25 13:00:15 +08:00
|
|
|
rescue
|
2021-05-21 09:43:47 +08:00
|
|
|
# There are many exceptions possible here including Addressable::URI:: exceptions
|
2020-06-25 13:00:15 +08:00
|
|
|
# and URI:: exceptions, catch all may seem wide, but it makes no sense to raise ever
|
|
|
|
# on an invalid url here
|
2020-05-23 12:56:13 +08:00
|
|
|
return false
|
|
|
|
end
|
|
|
|
|
2016-06-30 22:55:01 +08:00
|
|
|
base_hostname = URI.parse(absolute_base_url).hostname
|
2020-05-23 12:56:13 +08:00
|
|
|
if url[base_hostname]
|
|
|
|
# if the hostnames match it means the upload is in the same
|
|
|
|
# bucket on s3. however, the bucket folder path may differ in
|
|
|
|
# some cases, and we do not want to assume the url is uploaded
|
|
|
|
# here. e.g. the path of the current site could be /prod and the
|
|
|
|
# other site could be /staging
|
|
|
|
if s3_bucket_folder_path.present?
|
|
|
|
return parsed_url.path.starts_with?("/#{s3_bucket_folder_path}")
|
|
|
|
else
|
|
|
|
return true
|
|
|
|
end
|
|
|
|
return false
|
|
|
|
end
|
2016-06-30 22:55:01 +08:00
|
|
|
|
2017-10-06 13:20:01 +08:00
|
|
|
return false if SiteSetting.Upload.s3_cdn_url.blank?
|
|
|
|
cdn_hostname = URI.parse(SiteSetting.Upload.s3_cdn_url || "").hostname
|
2020-05-23 12:56:13 +08:00
|
|
|
return true if cdn_hostname.presence && url[cdn_hostname]
|
|
|
|
false
|
|
|
|
end
|
|
|
|
|
|
|
|
def s3_bucket_folder_path
|
2020-12-31 02:13:13 +08:00
|
|
|
S3Helper.get_bucket_and_folder_path(s3_bucket)[1]
|
2013-11-06 02:04:47 +08:00
|
|
|
end
|
2013-08-14 04:08:29 +08:00
|
|
|
|
2017-10-06 13:20:01 +08:00
|
|
|
def s3_bucket_name
|
2020-12-31 02:13:13 +08:00
|
|
|
S3Helper.get_bucket_and_folder_path(s3_bucket)[0]
|
2017-10-06 13:20:01 +08:00
|
|
|
end
|
|
|
|
|
2013-11-06 02:04:47 +08:00
|
|
|
def absolute_base_url
|
2017-10-06 13:20:01 +08:00
|
|
|
@absolute_base_url ||= SiteSetting.Upload.absolute_base_url
|
2013-11-06 02:04:47 +08:00
|
|
|
end
|
2013-08-14 04:08:29 +08:00
|
|
|
|
2019-11-18 09:25:42 +08:00
|
|
|
def s3_upload_host
|
|
|
|
SiteSetting.Upload.s3_cdn_url.present? ? SiteSetting.Upload.s3_cdn_url : "https:#{absolute_base_url}"
|
|
|
|
end
|
|
|
|
|
2013-11-06 02:04:47 +08:00
|
|
|
def external?
|
|
|
|
true
|
|
|
|
end
|
2013-08-14 04:08:29 +08:00
|
|
|
|
2013-11-28 05:01:41 +08:00
|
|
|
def purge_tombstone(grace_period)
|
2020-12-31 02:13:13 +08:00
|
|
|
s3_helper.update_tombstone_lifecycle(grace_period)
|
2013-11-28 05:01:41 +08:00
|
|
|
end
|
|
|
|
|
2018-12-19 13:32:32 +08:00
|
|
|
def multisite_tombstone_prefix
|
|
|
|
File.join("uploads", "tombstone", RailsMultisite::ConnectionManagement.current_db, "/")
|
|
|
|
end
|
|
|
|
|
2019-07-04 23:32:51 +08:00
|
|
|
def download_url(upload)
|
|
|
|
return unless upload
|
|
|
|
"#{upload.short_path}?dl=1"
|
|
|
|
end
|
|
|
|
|
2015-05-26 11:08:31 +08:00
|
|
|
def path_for(upload)
|
2019-05-29 09:00:25 +08:00
|
|
|
url = upload&.url
|
2019-05-29 18:36:09 +08:00
|
|
|
FileStore::LocalStore.new.path_for(upload) if url && url[/^\/[^\/]/]
|
2015-05-26 11:08:31 +08:00
|
|
|
end
|
|
|
|
|
2019-07-04 23:32:51 +08:00
|
|
|
def url_for(upload, force_download: false)
|
2019-11-18 09:25:42 +08:00
|
|
|
upload.secure? || force_download ?
|
2021-07-28 06:42:25 +08:00
|
|
|
presigned_get_url(get_upload_key(upload), force_download: force_download, filename: upload.original_filename) :
|
2019-11-18 09:25:42 +08:00
|
|
|
upload.url
|
2019-06-06 11:27:24 +08:00
|
|
|
end
|
|
|
|
|
2021-07-28 06:42:25 +08:00
|
|
|
def path_from_url(url)
|
|
|
|
URI.parse(url).path.delete_prefix("/")
|
|
|
|
end
|
|
|
|
|
2015-05-27 10:02:57 +08:00
|
|
|
def cdn_url(url)
|
2017-10-06 13:20:01 +08:00
|
|
|
return url if SiteSetting.Upload.s3_cdn_url.blank?
|
2016-06-30 22:55:01 +08:00
|
|
|
schema = url[/^(https?:)?\/\//, 1]
|
2020-12-31 02:13:13 +08:00
|
|
|
folder = s3_bucket_folder_path.nil? ? "" : "#{s3_bucket_folder_path}/"
|
2018-11-29 12:11:48 +08:00
|
|
|
url.sub(File.join("#{schema}#{absolute_base_url}", folder), File.join(SiteSetting.Upload.s3_cdn_url, "/"))
|
2015-05-27 10:02:57 +08:00
|
|
|
end
|
|
|
|
|
2020-09-29 10:12:03 +08:00
|
|
|
def signed_url_for_path(path, expires_in: S3Helper::DOWNLOAD_URL_EXPIRES_AFTER_SECONDS, force_download: false)
|
2019-11-18 09:25:42 +08:00
|
|
|
key = path.sub(absolute_base_url + "/", "")
|
2021-07-28 06:42:25 +08:00
|
|
|
presigned_get_url(key, expires_in: expires_in, force_download: force_download)
|
|
|
|
end
|
|
|
|
|
|
|
|
def signed_url_for_temporary_upload(file_name, expires_in: S3Helper::UPLOAD_URL_EXPIRES_AFTER_SECONDS, metadata: {})
|
|
|
|
key = temporary_upload_path(file_name)
|
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 https://github.com/transloadit/uppy/commit/d613b849a6591083f8a0968aa8d66537e231bbcd. 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 06:46:54 +08:00
|
|
|
presigned_url(
|
|
|
|
key,
|
|
|
|
method: :put_object,
|
|
|
|
expires_in: expires_in,
|
|
|
|
opts: {
|
|
|
|
metadata: metadata,
|
|
|
|
acl: "private"
|
|
|
|
}
|
|
|
|
)
|
2021-07-28 06:42:25 +08:00
|
|
|
end
|
|
|
|
|
|
|
|
def temporary_upload_path(file_name)
|
2021-08-25 07:22:36 +08:00
|
|
|
s3_bucket_folder_path.nil? ? super(file_name) : super(file_name, folder_prefix: s3_bucket_folder_path)
|
2021-07-28 06:42:25 +08:00
|
|
|
end
|
|
|
|
|
|
|
|
def object_from_path(path)
|
|
|
|
s3_helper.object(path)
|
2019-11-18 09:25:42 +08:00
|
|
|
end
|
|
|
|
|
2015-05-30 00:39:47 +08:00
|
|
|
def cache_avatar(avatar, user_id)
|
|
|
|
source = avatar.url.sub(absolute_base_url + "/", "")
|
|
|
|
destination = avatar_template(avatar, user_id).sub(absolute_base_url + "/", "")
|
2020-12-31 02:13:13 +08:00
|
|
|
s3_helper.copy(source, destination)
|
2015-05-30 00:39:47 +08:00
|
|
|
end
|
2013-11-28 05:01:41 +08:00
|
|
|
|
2015-05-30 00:39:47 +08:00
|
|
|
def avatar_template(avatar, user_id)
|
|
|
|
UserAvatar.external_avatar_url(user_id, avatar.upload_id, avatar.width)
|
|
|
|
end
|
2013-08-01 05:26:34 +08:00
|
|
|
|
2016-08-19 14:08:04 +08:00
|
|
|
def s3_bucket
|
2017-10-06 13:20:01 +08:00
|
|
|
raise Discourse::SiteSettingMissing.new("s3_upload_bucket") if SiteSetting.Upload.s3_upload_bucket.blank?
|
|
|
|
SiteSetting.Upload.s3_upload_bucket.downcase
|
2015-05-30 00:39:47 +08:00
|
|
|
end
|
2018-11-27 03:24:51 +08:00
|
|
|
|
2019-02-15 03:04:35 +08:00
|
|
|
def list_missing_uploads(skip_optimized: false)
|
2019-02-01 12:40:48 +08:00
|
|
|
if SiteSetting.enable_s3_inventory
|
|
|
|
require 's3_inventory'
|
2019-02-20 00:24:35 +08:00
|
|
|
S3Inventory.new(s3_helper, :upload).backfill_etags_and_list_missing
|
|
|
|
S3Inventory.new(s3_helper, :optimized).backfill_etags_and_list_missing unless skip_optimized
|
2019-02-01 12:40:48 +08:00
|
|
|
else
|
2019-03-13 17:39:07 +08:00
|
|
|
list_missing(Upload.by_users, "original/")
|
2019-02-01 12:40:48 +08:00
|
|
|
list_missing(OptimizedImage, "optimized/") unless skip_optimized
|
|
|
|
end
|
2018-11-27 03:24:51 +08:00
|
|
|
end
|
|
|
|
|
2019-06-06 11:27:24 +08:00
|
|
|
def update_upload_ACL(upload)
|
|
|
|
key = get_upload_key(upload)
|
2019-11-18 09:25:42 +08:00
|
|
|
update_ACL(key, upload.secure?)
|
2019-06-06 11:27:24 +08:00
|
|
|
|
2019-11-18 09:25:42 +08:00
|
|
|
upload.optimized_images.find_each do |optimized_image|
|
|
|
|
optimized_image_key = get_path_for_optimized_image(optimized_image)
|
|
|
|
update_ACL(optimized_image_key, upload.secure?)
|
2019-06-06 11:27:24 +08:00
|
|
|
end
|
2019-11-18 09:25:42 +08:00
|
|
|
|
|
|
|
true
|
2019-06-06 11:27:24 +08:00
|
|
|
end
|
|
|
|
|
2019-07-02 02:38:36 +08:00
|
|
|
def download_file(upload, destination_path)
|
2020-12-31 02:13:13 +08:00
|
|
|
s3_helper.download_file(get_upload_key(upload), destination_path)
|
2019-07-02 02:38:36 +08:00
|
|
|
end
|
|
|
|
|
2020-01-13 07:12:27 +08:00
|
|
|
def copy_from(source_path)
|
|
|
|
local_store = FileStore::LocalStore.new
|
|
|
|
public_upload_path = File.join(local_store.public_dir, local_store.upload_path)
|
|
|
|
|
|
|
|
# The migration to S3 and lots of other code expects files to exist in public/uploads,
|
|
|
|
# so lets move them there before executing the migration.
|
|
|
|
if public_upload_path != source_path
|
|
|
|
if Dir.exist?(public_upload_path)
|
|
|
|
old_upload_path = "#{public_upload_path}_#{SecureRandom.hex}"
|
|
|
|
FileUtils.mv(public_upload_path, old_upload_path)
|
|
|
|
end
|
|
|
|
end
|
|
|
|
|
|
|
|
FileUtils.mkdir_p(File.expand_path("..", public_upload_path))
|
|
|
|
FileUtils.symlink(source_path, public_upload_path)
|
|
|
|
|
|
|
|
FileStore::ToS3Migration.new(
|
2020-04-20 02:24:27 +08:00
|
|
|
s3_options: FileStore::ToS3Migration.s3_options_from_site_settings,
|
2020-01-13 07:12:27 +08:00
|
|
|
migrate_to_multisite: Rails.configuration.multisite,
|
|
|
|
).migrate
|
|
|
|
|
|
|
|
ensure
|
|
|
|
FileUtils.rm(public_upload_path) if File.symlink?(public_upload_path)
|
|
|
|
FileUtils.mv(old_upload_path, public_upload_path) if old_upload_path
|
|
|
|
end
|
|
|
|
|
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 https://github.com/transloadit/uppy/commit/d613b849a6591083f8a0968aa8d66537e231bbcd. 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 06:46:54 +08:00
|
|
|
def abort_multipart(key:, upload_id:)
|
|
|
|
s3_helper.s3_client.abort_multipart_upload(
|
|
|
|
bucket: s3_bucket_name,
|
|
|
|
key: key,
|
|
|
|
upload_id: upload_id
|
|
|
|
)
|
|
|
|
end
|
|
|
|
|
|
|
|
def create_multipart(file_name, content_type)
|
|
|
|
key = temporary_upload_path(file_name)
|
|
|
|
response = s3_helper.s3_client.create_multipart_upload(
|
|
|
|
acl: "private",
|
|
|
|
bucket: s3_bucket_name,
|
|
|
|
key: key,
|
|
|
|
content_type: content_type
|
|
|
|
)
|
|
|
|
{ upload_id: response.upload_id, key: key }
|
|
|
|
end
|
|
|
|
|
|
|
|
def presign_multipart_part(upload_id:, key:, part_number:)
|
|
|
|
presigned_url(
|
|
|
|
key,
|
|
|
|
method: :upload_part,
|
|
|
|
expires_in: S3Helper::UPLOAD_URL_EXPIRES_AFTER_SECONDS,
|
|
|
|
opts: {
|
|
|
|
part_number: part_number,
|
|
|
|
upload_id: upload_id
|
|
|
|
}
|
|
|
|
)
|
|
|
|
end
|
|
|
|
|
|
|
|
def list_multipart_parts(upload_id:, key:)
|
|
|
|
s3_helper.s3_client.list_parts(
|
|
|
|
bucket: s3_bucket_name,
|
|
|
|
key: key,
|
|
|
|
upload_id: upload_id
|
|
|
|
)
|
|
|
|
end
|
|
|
|
|
|
|
|
def complete_multipart(upload_id:, key:, parts:)
|
|
|
|
s3_helper.s3_client.complete_multipart_upload(
|
|
|
|
bucket: s3_bucket_name,
|
|
|
|
key: key,
|
|
|
|
upload_id: upload_id,
|
|
|
|
multipart_upload: {
|
|
|
|
parts: parts
|
|
|
|
}
|
|
|
|
)
|
|
|
|
end
|
|
|
|
|
2018-11-27 03:24:51 +08:00
|
|
|
private
|
|
|
|
|
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 https://github.com/transloadit/uppy/commit/d613b849a6591083f8a0968aa8d66537e231bbcd. 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 06:46:54 +08:00
|
|
|
def presigned_url(
|
|
|
|
key,
|
|
|
|
method:,
|
|
|
|
expires_in: S3Helper::UPLOAD_URL_EXPIRES_AFTER_SECONDS,
|
|
|
|
opts: {}
|
|
|
|
)
|
2021-07-28 06:42:25 +08:00
|
|
|
signer = Aws::S3::Presigner.new(client: s3_helper.s3_client)
|
|
|
|
signer.presigned_url(
|
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 https://github.com/transloadit/uppy/commit/d613b849a6591083f8a0968aa8d66537e231bbcd. 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 06:46:54 +08:00
|
|
|
method,
|
|
|
|
{
|
|
|
|
bucket: s3_bucket_name,
|
|
|
|
key: key,
|
|
|
|
expires_in: expires_in,
|
|
|
|
}.merge(opts)
|
2021-07-28 06:42:25 +08:00
|
|
|
)
|
|
|
|
end
|
|
|
|
|
|
|
|
def presigned_get_url(
|
2020-07-03 11:42:36 +08:00
|
|
|
url,
|
|
|
|
force_download: false,
|
|
|
|
filename: false,
|
|
|
|
expires_in: S3Helper::DOWNLOAD_URL_EXPIRES_AFTER_SECONDS
|
|
|
|
)
|
|
|
|
opts = { expires_in: expires_in }
|
|
|
|
|
2019-11-18 09:25:42 +08:00
|
|
|
if force_download && filename
|
|
|
|
opts[:response_content_disposition] = ActionDispatch::Http::ContentDisposition.format(
|
|
|
|
disposition: "attachment", filename: filename
|
|
|
|
)
|
|
|
|
end
|
|
|
|
|
2021-07-28 06:42:25 +08:00
|
|
|
obj = object_from_path(url)
|
2019-11-18 09:25:42 +08:00
|
|
|
obj.presigned_url(:get, opts)
|
|
|
|
end
|
|
|
|
|
2019-06-06 11:27:24 +08:00
|
|
|
def get_upload_key(upload)
|
|
|
|
if Rails.configuration.multisite
|
|
|
|
File.join(upload_path, "/", get_path_for_upload(upload))
|
|
|
|
else
|
|
|
|
get_path_for_upload(upload)
|
|
|
|
end
|
|
|
|
end
|
|
|
|
|
2019-11-18 09:25:42 +08:00
|
|
|
def update_ACL(key, secure)
|
|
|
|
begin
|
2021-07-28 06:42:25 +08:00
|
|
|
object_from_path(key).acl.put(acl: secure ? "private" : "public-read")
|
2019-11-18 09:25:42 +08:00
|
|
|
rescue Aws::S3::Errors::NoSuchKey
|
|
|
|
Rails.logger.warn("Could not update ACL on upload with key: '#{key}'. Upload is missing.")
|
|
|
|
end
|
|
|
|
end
|
|
|
|
|
2018-11-27 03:24:51 +08:00
|
|
|
def list_missing(model, prefix)
|
|
|
|
connection = ActiveRecord::Base.connection.raw_connection
|
|
|
|
connection.exec('CREATE TEMP TABLE verified_ids(val integer PRIMARY KEY)')
|
|
|
|
marker = nil
|
2020-12-31 02:13:13 +08:00
|
|
|
files = s3_helper.list(prefix, marker)
|
2018-11-27 03:24:51 +08:00
|
|
|
|
|
|
|
while files.count > 0 do
|
|
|
|
verified_ids = []
|
|
|
|
|
|
|
|
files.each do |f|
|
2019-10-21 18:32:27 +08:00
|
|
|
id = model.where("url LIKE '%#{f.key}' AND etag = '#{f.etag}'").pluck_first(:id)
|
2018-11-27 03:24:51 +08:00
|
|
|
verified_ids << id if id.present?
|
|
|
|
marker = f.key
|
|
|
|
end
|
|
|
|
|
|
|
|
verified_id_clause = verified_ids.map { |id| "('#{PG::Connection.escape_string(id.to_s)}')" }.join(",")
|
|
|
|
connection.exec("INSERT INTO verified_ids VALUES #{verified_id_clause}")
|
2020-12-31 02:13:13 +08:00
|
|
|
files = s3_helper.list(prefix, marker)
|
2018-11-27 03:24:51 +08:00
|
|
|
end
|
|
|
|
|
2019-02-01 12:40:48 +08:00
|
|
|
missing_uploads = model.joins('LEFT JOIN verified_ids ON verified_ids.val = id').where("verified_ids.val IS NULL")
|
2018-11-27 03:24:51 +08:00
|
|
|
missing_count = missing_uploads.count
|
|
|
|
|
|
|
|
if missing_count > 0
|
|
|
|
missing_uploads.find_each do |upload|
|
|
|
|
puts upload.url
|
|
|
|
end
|
|
|
|
|
|
|
|
puts "#{missing_count} of #{model.count} #{model.name.underscore.pluralize} are missing"
|
|
|
|
end
|
|
|
|
ensure
|
2018-11-27 03:45:29 +08:00
|
|
|
connection.exec('DROP TABLE verified_ids') unless connection.nil?
|
2018-11-27 03:24:51 +08:00
|
|
|
end
|
2013-08-01 05:26:34 +08:00
|
|
|
end
|
|
|
|
end
|