04d242c60c
* Save the filename for files uploaded from disk. This could be used in the future to extract source data if the filename is from a known site. * Save both the image URL and the page URL for files uploaded from source. This is needed for multi-file uploads. The image URL is the URL of the file actually downloaded from the source. This can be different from the URL given by the user, if the user tried to upload a sample URL and we automatically changed it to the original URL. The page URL is the URL of the page containing the image. We don't always know this, for example if someone uploads a Twitter image without the bookmarklet, then we can't find the page URL. * Add a fix script to backfill URLs for existing uploads. For file uploads, the filename will be set to "unknown.jpg". For source uploads, we fetch the source data again to get the image and page URLs. This may fail for uploads that have been deleted from the source since uploading.
23 lines
770 B
Ruby
Executable File
23 lines
770 B
Ruby
Executable File
#!/usr/bin/env ruby
|
|
|
|
require_relative "base"
|
|
|
|
UploadMediaAsset.includes(:upload, :media_asset).where(source_url: "").find_each do |uma|
|
|
upload = uma.upload
|
|
|
|
if upload.source_strategy.present?
|
|
source_url = uma.upload.source_strategy.image_url
|
|
page_url = uma.upload.source_strategy.page_url
|
|
else
|
|
file_ext = uma.media_asset.file_ext
|
|
source_url = "file://unknown.#{file_ext}"
|
|
end
|
|
|
|
raise "No source url for #{page_url}" if source_url.blank?
|
|
|
|
uma.update_columns(source_url: source_url, page_url: page_url)
|
|
puts ({ upload_id: uma.upload.id, upload_media_asset_id: uma.id, source_url: source_url, page_url: page_url }).to_json
|
|
rescue Exception => e
|
|
puts ({ upload_id: uma.upload.id, upload_media_asset_id: uma.id, error: e.message }).to_json
|
|
end
|