Fix StatementInvalid exception when uploading https://files.catbox.moe/vxoe2p.mp4. This was a result of multiple bugs: * First, generating thumbnails for the video failed. This was because the video uses the AV1 codec, which FFmpeg failed to decode. It failed because our version of FFmpeg was built without the `--enable-libdav1d` flag, so it uses the builtin AV1 decoder, which apparently can't handle this particular video (it spews a bunch of errors about "Failed to get pixel format" and "missing sequence header" and "failed to get reference frame"). * Because generating the thumbnails failed, an exception was raised. We tried to save the error message in the upload_media_assets.error field. However, this also failed because the error message was 77kb long (it contained the entire output of the ffmpeg command), but the `upload_media_assets` table had a btree index on the `error` column, which meant the maximum length of the error column was limited to ~2.7kb. This lead to a StatementInvalid exception being raised. * Because the StatementInvalid exception was raised while we were trying to set the upload media asset's status to `failed`, the upload was left stuck in the `processing` state rather than being set to the `failed` state. * Because the upload was stuck in the `processing` state, the upload page would hang forever waiting for the upload to complete. The fixes are to: * Build FFmpeg with `--enable-libdav1d` to use libdav1d for decoding AV1 videos instead of the builtin AV1 decoder. * Remove the index on the `upload_media_assets.error` column so that setting overly long error messages won't fail. * Catch unexpected exceptions in ProcessUploadMediaAssetJob so we can mark uploads as failed, even if `process_upload!` itself fails because it raises an unexpected exception inside its own exception handler. * Check that the video is playable with `MediaFile::Video#is_corrupt?` before allowing it to be uploaded. This way we can return a better error message if we can't generate thumbnails because the video isn't playable. This requires decoding the entire video, so it means uploads may take several seconds longer for long videos. It's also a security risk in case ffmpeg has any bugs. * Define `MediaAsset#preview!` as raising an exception on error, so it's clear that generating thumbnails can fail. Define `MediaAsset#preview` as returning nil on error for when we don't care about the cause of the error.
132 lines
4.8 KiB
Ruby
132 lines
4.8 KiB
Ruby
# frozen_string_literal: true
|
|
|
|
# An API client for Danbooru's internal IQDB instance. Can add images, remove
|
|
# images, and search for images in IQDB.
|
|
#
|
|
# @see https://github.com/danbooru/iqdb
|
|
class IqdbClient
|
|
class Error < StandardError; end
|
|
attr_reader :iqdb_url, :http
|
|
|
|
# Create a new IQDB API client.
|
|
# @param iqdb_url [String] the base URL of the IQDB server
|
|
# @param http [Danbooru::Http] the HTTP client to use
|
|
def initialize(iqdb_url: Danbooru.config.iqdb_url.to_s, http: Danbooru::Http.internal)
|
|
@iqdb_url = iqdb_url.chomp("/")
|
|
@http = http
|
|
end
|
|
|
|
def enabled?
|
|
iqdb_url.present?
|
|
end
|
|
|
|
concerning :QueryMethods do
|
|
# Search for an image by file, URL, hash, or post ID.
|
|
def search(post_id: nil, media_asset_id: nil, file: nil, hash: nil, url: nil, image_url: nil, file_url: nil, similarity: 0.0, high_similarity: 65.0, limit: 20)
|
|
limit = limit.to_i.clamp(1, 1000)
|
|
similarity = similarity.to_f.clamp(0.0, 100.0)
|
|
high_similarity = high_similarity.to_f.clamp(0.0, 100.0)
|
|
|
|
if file.present?
|
|
file = file.tempfile
|
|
elsif url.present?
|
|
extractor = Source::Extractor.find(url)
|
|
raise Error, "Can't do reverse image search: #{url} has multiple images. Enter the URL of a single image." if extractor.image_urls.size > 1
|
|
|
|
download_url = extractor.image_urls.first
|
|
file = Source::Extractor.find(download_url).download_file!(download_url)
|
|
elsif image_url.present?
|
|
file = Source::Extractor.find(image_url).download_file!(image_url)
|
|
elsif file_url.present?
|
|
file = Source::Extractor.find(file_url).download_file!(file_url)
|
|
elsif post_id.present?
|
|
file = Post.find(post_id).file(:preview)
|
|
elsif media_asset_id.present?
|
|
file = MediaAsset.find(media_asset_id).variant("360x360").open_file
|
|
end
|
|
|
|
if hash.present?
|
|
results = query_hash(hash, limit: limit)
|
|
elsif file.present?
|
|
results = query_file(file, limit: limit)
|
|
else
|
|
results = []
|
|
end
|
|
|
|
process_results(results, similarity, high_similarity)
|
|
ensure
|
|
file.try(:close)
|
|
end
|
|
|
|
# Transform the JSON returned by IQDB to add the full post data for each
|
|
# match.
|
|
# @param matches [Array<Hash>] the array of IQDB matches
|
|
# @param low_similarity [Float] the threshold for a result to be considered low similarity
|
|
# @param high_similarity [Float] the threshold for a result to be considered high similarity
|
|
# @return [(Array, Array, Array)] the set of high similarity, low similarity, and all matches
|
|
def process_results(matches, low_similarity, high_similarity)
|
|
matches = matches.select { |result| result["score"] >= low_similarity }
|
|
post_ids = matches.map { |match| match["post_id"] }
|
|
posts = Post.includes(:media_asset).where(id: post_ids).group_by(&:id).transform_values(&:first)
|
|
|
|
matches = matches.map do |match|
|
|
post = posts.fetch(match["post_id"], nil)
|
|
match.with_indifferent_access.merge(post: post) if post
|
|
end.compact
|
|
|
|
high_similarity_matches, low_similarity_matches = matches.partition { |match| match["score"] >= high_similarity }
|
|
[high_similarity_matches, low_similarity_matches, matches]
|
|
end
|
|
end
|
|
|
|
# Add a post to IQDB.
|
|
# @param post [Post] the post to add
|
|
def add_post(post)
|
|
return unless enabled? && post.has_preview?
|
|
preview_file = post.file(:preview)
|
|
add(post.id, preview_file)
|
|
end
|
|
|
|
concerning :HttpMethods do
|
|
# Search for an image in IQDB by hash.
|
|
# @param hash [String] the IQDB hash to search
|
|
def query_hash(hash, limit: 20)
|
|
request(:post, "query", params: { hash: hash, limit: limit })
|
|
end
|
|
|
|
# Search for an image file in IQDB.
|
|
# @param file [File] the image to search
|
|
def query_file(file, limit: 20)
|
|
media_file = MediaFile.open(file)
|
|
preview = media_file.preview!(Danbooru.config.small_image_width, Danbooru.config.small_image_width)
|
|
file = HTTP::FormData::File.new(preview)
|
|
request(:post, "query", form: { file: file }, params: { limit: limit })
|
|
end
|
|
|
|
# Add a post to IQDB.
|
|
# @param post_id [Integer] the post to add
|
|
# @param file [File] the image to add
|
|
def add(post_id, file)
|
|
file = HTTP::FormData::File.new(file)
|
|
request(:post, "images/#{post_id}", form: { file: file })
|
|
end
|
|
|
|
# Remove an image from IQDB.
|
|
# @param post_id [Integer] the post to remove
|
|
def remove(post_id)
|
|
request(:delete, "images/#{post_id}")
|
|
end
|
|
|
|
# Send a request to IQDB.
|
|
# @param method [String] the HTTP method
|
|
# @param url [String] the IQDB url
|
|
# @param options [Hash] the URL params to send
|
|
def request(method, url, **options)
|
|
return [] if !enabled?
|
|
response = http.timeout(30).send(method, "#{iqdb_url}/#{url}", **options)
|
|
raise Error, "IQDB error: #{response.parse}" if response.status != 200
|
|
response.parse
|
|
end
|
|
end
|
|
end
|