* docs(audiobooks): design spec for plugin absorption Plan to absorb silo-plugin-audiobooks into silo-server as a first-party feature. Audiobooks land in silo's existing SPA; ABS clients connect directly. Hard constraints: reuse existing tables (media_items, media_files, user_watch_progress, user_playback_sessions, people, item_people, library_collections); only two new tables (abs_sessions, podcast_feeds) and at most one column add (media_libraries.kind); silo's main :8080 listener handles ABS Socket.io natively. Out of scope: audiobook requests flow, smart collections, share links, external recommender, custom metadata providers, separate audiobook SPA. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * docs(audiobooks): implementation plan sub-plan 1 (discovery + schema) First of six sub-plans for the absorption. Six tasks: a discovery audit that resolves the spec's Risk questions, four idempotent SQL migrations (abs_sessions, podcast_feeds, media_libraries.kind, audiobooks.enabled feature flag), and an empty-but-compiling internal/audiobooks package scaffolded into cmd/silo. Lands as a strict no-op for users (feature flag defaults to false). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * docs(audiobooks): discovery findings for absorption sub-plan 1 Locks schema/code decisions for migrations 139-142 and downstream sub-plans. Resolves open Risk questions from the absorption design spec. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat(audiobooks): migration 139 add abs_sessions table Parallel of jellycompat_sessions for Audiobookshelf-compatible clients. Lets ABS mobile/desktop apps maintain a device-bound session that silo's audiobooks/abs handlers will validate. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * style(audiobooks): match codebase conventions in migration 139 Lowercases type keywords in the abs_sessions CREATE TABLE body to match neighboring migrations, fixes the client_version column alignment, and replaces the misleading "parallel to jellycompat_sessions" header comment with a more accurate description of the table's role. Cosmetic only — the running schema is unchanged. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat(audiobooks): migration 140 add podcast_feeds table Side table on media_items for RSS-subscribed podcasts. Holds feed URL, ETag/Last-Modified for conditional fetches, last-refresh timestamp, and the per-feed refresh interval consumed by the upcoming podcastfeed.Refresher scheduled task. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * style(audiobooks): uppercase PRIMARY KEY in migration 140 Aligns with the codebase convention (type keywords lowercase, constraint keywords uppercase) established in migration 139's post-style-fix form. Cosmetic only — running schema is unchanged. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * chore(audiobooks): migration 141 no-op for media_folders.type Sub-plan 1 originally reserved migration 141 to add a 'kind' column to media_libraries discriminating audiobook/podcast libraries. Discovery audit (sub-plan 1 Task 1) found that the actual table is media_folders and it already has a type text NOT NULL column with no CHECK constraint or enum, so 'audiobooks' and 'podcasts' can be added as future values without DDL. Landing this migration as a documented no-op preserves the version numbering audit trail and pins the decision in git history. The matching down migration is also a no-op. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat(audiobooks): migration 142 add audiobooks.enabled flag Server-settings row that gates the absorbed audiobooks feature. Defaults to 'false' so sub-plan 1 lands as a strict no-op; subsequent sub-plans branch on this flag and operators flip it to 'true' at cutover. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat(audiobooks): scaffold internal/audiobooks package Empty-but-compiling Service that reads the audiobooks.enabled feature flag from server_settings. Wired into cmd/silo so the package is referenced from the binary; no routes mounted, no scheduled tasks registered, no DB writes. Subsequent sub-plans hang scanner branches, ABS handlers, Socket.io, podcast refresher, and SPA pages off this Service. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * style(audiobooks): cosmetic cleanups in scaffolded package Two pre-emptive cleanups flagged by code review before sub-plan 2 copies the patterns: 1. Sort the internal/audiobooks import after internal/adminjob in cmd/silo/main.go (alphabetical). 2. Drop the redundant "audiobooks: " prefix from the Enabled() error wrap; matches how every other top-level service package (watchstate, scanqueue, metadata, etc.) formats errors. No behavior change. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * docs(audiobooks): implementation plan sub-plan 2 (scanner) Second of six sub-plans. 10 tasks: PersonKind constants for Author and Narrator, audio-extension recognizer, library-type helpers, a walkLogicalTree refactor (movieLibrary bool -> typed walkMode), chapter extraction via ffprobe, single-file and multi-file audiobook parsers, scanner write path producing media_items.type='audiobook', and a filesystem podcast parser (RSS deferred to sub-plan 5). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat(audiobooks): add Author and Narrator PersonKind constants Discovery audit confirmed item_people.kind is unconstrained smallint with values 1-6 in use. Reserve 7 = Author, 8 = Narrator for audiobook people-links written by the upcoming scanner branches. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat(audiobooks): add audio-extension recognizer for scanner Mirrors the existing videoExtensions/SupportsVideoFile pair. Used by upcoming audiobook and podcast scanner branches to filter directory walks. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat(audiobooks): library-type recognizers for scanner dispatch isAudiobookLibraryType and isPodcastLibraryType match singular and plural forms case-insensitively, mirroring isMovieLibraryType. Used by upcoming scanner walk branches (Task 4) that filter audio files into audiobook and podcast libraries. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * refactor(scanner): replace movieLibrary bool with typed walkMode Lets walkLogicalTree dispatch on multiple library shapes (video, movie, audiobook, podcast) without proliferating boolean flags. Behavior for existing video and movie libraries is unchanged; audiobook and podcast modes will be consumed by the upcoming audiobook.go and podcast.go parsers in later tasks of this sub-plan. walkModeFor() derives the mode from a media_folders.type string; unknown types default to walkModeVideo to preserve prior behavior for any caller still passing a raw type. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat(audiobooks): expose ffprobe format tags on ProbeData The audiobook scanner needs format-level tags (title, artist, album, date) for media_items metadata; ffprobe already parses them in ffprobeFormat.Tags but ProbeData previously discarded them. Add FormatTags map[string]string to ProbeData, populate it in convertProbeData via a new normalizeFormatTags helper that lowercases keys and trims values. Adds a fixture audiobook .m4b with embedded chapters (Intro/Outro) and format tags, and a test that verifies ProbeFile() returns both correctly. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat(audiobooks): parser for single-file audiobook folders parseAudiobookFolder reads tags + chapters via the existing ProbeFile (now that Task 5 exposes FormatTags on ProbeData) and produces a parsedAudiobook struct. Title falls back from "title" tag to "album"; author from "artist" -> "album_artist" -> "composer"; series from "album" -> "series" -> "mvnm" (Movement Name, used by some MP4 tools). Year parsed from "date" or "year" tags, tolerating ISO dates and parenthesized forms. Single-file case only; multi-file folders (one audio file per chapter) return a placeholder error and arrive in Task 7. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat(audiobooks): multi-file audiobook folder support Folders containing N audio files (one per chapter/part) get one parsedAudiobookFile per file; each file's chapter list is synthesized as a single chapter with title = filename stem. Title/author/series/ year come from the first file's tags. Also drops the duplicate pickFirstNonEmpty helper added in Task 6 in favor of the existing firstNonEmpty already in probe.go. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat(audiobooks): scanner write path produces audiobook media_items ScanAudiobookFolder walks an audiobooks-typed media folder and treats each immediate subdirectory as one audiobook. For each parsed audiobook it upserts: - one media_items row with type='audiobook' - one media_files row per audio file (with chapters JSONB) - author/narrator links in item_people (kind=7, kind=8) Adds itemRepo and personRepo to the Scanner struct, wired from fileRepo.Pool() in NewScanner — no constructor signature change needed. ScanFolder dispatches to this path when folder.Type='audiobooks', bypassing the per-file movie/TV pipeline because audiobooks are folder-scoped entities. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat(audiobooks): filesystem podcast scanner ScanPodcastFolder walks a podcasts-typed media folder, treating each subdirectory as a podcast show and each audio file inside as an episode. Writes media_items.type='podcast' + episodes rows + media_files rows. RSS-subscribed feeds (podcast_feeds table) arrive in sub-plan 5; this task covers filesystem-only ingestion. ScanFolder dispatches to this path when folder.Type='podcasts'. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * docs(audiobooks): implementation plan sub-plan 5 (podcasts) Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat(audiobooks): expose audiobooks/podcasts library types in admin UI Adds 'Audiobooks' and 'Podcasts' options to the library-type dropdown in the admin libraries page so operators can flag a folder as an audiobook or podcast library. Extends contentLevelsForType() so the admin UI's downstream filtering treats those types correctly (audiobook -> ['audiobook'], podcasts -> ['podcast', 'podcast_episode']). Backend scanner branches for these types were already wired in sub-plan 2. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * chore(migrations): renumber 139_abs_sessions to 147 for origin/main merge origin/main adds 139_media_requests at the same number our local audiobook branch had used for abs_sessions. Renumber ours to 147 to free up 139 for the upstream migration. The schema_versions row is updated in lockstep on the running database so the migrator sees the abs_sessions migration as already applied at its new version. Migrations 140-146 (podcast feeds, media_folders kind noop, audiobook feature flag, abs playback sessions, podcast episode guid, audiobook series, audiobook title cleanup) stay where they are — they don't collide with anything on origin/main. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * chore(migrations): renumber 140_podcast_feeds to 157 for origin/main merge origin/main added 140_user_permissions at the same version this branch had used for podcast_feeds. Renumber ours to 157 (next free above the collections-unify migration at 156) so 140 is free for the upstream migration. schema_versions on the running database is updated in lockstep so the migrator sees podcast_feeds as already applied at its new version. Same pattern asd59c1cb(renumber 139_abs_sessions to 147 for the prior main merge). Pending migrations after this rename: 132 (downloaded subtitles admin index, main), 140 (user_permissions, main), and 156 (unify_user_collections, this branch). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * chore(migrations): renumber 141_media_folders_kind_noop to 159 for origin/main merge Same shape aseb8f67d(the 140→157 renumber from the previous main merge). origin/main added 141_episode_title_sort_index at the same version this branch had used for media_folders_kind_noop. Renumber ours to 159 (next free above the audiobook_series truncate at 158) so 141 is open for the upstream migration. schema_versions on the running database is updated in lockstep so the migrator sees media_folders_kind_noop as already applied at its new version. Pending migrations on silo-prod after this rename: 141 (episode_title_sort_index, main) and any other newer ones from main that the branch hasn't picked up yet. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * chore(migrations): renumber 142_audiobooks_feature_flag to 160 for origin/main merge Companion to 3c6f062's 141 renumber — origin/main also added 142_episode_catalog_entries (alongside 141_episode_title_sort_index) at a version this branch had used for the audiobooks feature flag. Renumber ours to 160 so 142 is open for the upstream migration; schema_versions on silo-prod is updated in lockstep so the migrator sees audiobooks_feature_flag as already applied at its new version. This was the only remaining collision (verified by checking for duplicate version prefixes across migrations/). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(audiobooks): address foundation review comments * fix(audiobooks): tighten scanner identity handling * fix(audiobooks): propagate scanner cancellation * chore(audiobooks): adopt goose migration layout * docs(audiobooks): implementation plan sub-plan 3 (API + frontend MVP) Third of six sub-plans. 9 tasks: three REST endpoints (list/detail/ progress), TanStack Query hooks + types, three React pages (Library/Detail/Player), and navigation integration. Scoped to MVP — author/series indices, smart collections, share links, and other nice-to-haves from the spec are deferred. Streaming reuses silo's existing /api/v1/stream/{session_id}; no new transcode code. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat(audiobooks): list endpoint at GET /api/v1/audiobooks Paginated list of media_items with type='audiobook' scoped to the caller's accessible libraries via the existing access filter. Mirrors silo's existing list-style handlers for movies and series. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat(audiobooks): detail endpoint at GET /api/v1/audiobooks/{id} Returns the media_items row, its media_files (with chapters JSONB), author/narrator extracted from item_people (kinds 7/8), and the caller's per-profile listening progress from user_watch_progress. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat(audiobooks): progress endpoint at POST /api/v1/audiobooks/{id}/progress UPSERTs user_watch_progress for the caller's (user_id, profile_id, content_id). Body carries position_seconds; clients are expected to post every 5-10s during playback plus on pause/seek (matching silo's existing video progress cadence). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat(audiobooks): frontend types and TanStack Query hooks TypeScript types match the JSON shapes from the new /api/v1/audiobooks endpoints (list, detail, progress). Three hooks: useAudiobookLibrary (list), useAudiobook (detail), and useReportAudiobookProgress (mutation that invalidates the detail query on success so progress updates reflect immediately). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat(audiobooks): library grid page at /audiobooks Renders a paginated grid of audiobook cards using the useAudiobookLibrary hook. Each card links to /audiobooks/book/{id}. Cards show poster, title, and year; falls back to a "No cover" placeholder when the audiobook has no poster_url. Empty state hints to operators that they need to set a library's type to 'audiobooks'. Routes themselves are wired in Task 8 (navigation integration). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat(audiobooks): detail page with chapter list Renders cover, title, author, narrator, year, and overview alongside a chapter list. Clicking a chapter opens an inline sticky AudiobookPlayer at that chapter's start. A "Resume" button restarts playback at the saved progress position if present. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat(audiobooks): HTML5 audio player with chapter navigation Single-file audiobook playback for MVP. Multi-file queuing arrives in a follow-up. Streams via the existing /api/v1/direct-download GET endpoint. Position is reported to /api/v1/audiobooks/{id}/progress every 10s while playing plus on pause/seek/end. Skip-30s, playback rate select, chapter list panel. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat(audiobooks): wire navigation and routes Adds an Audiobooks entry to the sidebar and registers the two new routes (/audiobooks for the library grid, /audiobooks/book/:id for detail). The player renders inline inside the detail page; no dedicated player route is required for MVP. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(audiobooks): address native API review comments * feat(audiobooks): add ABS compatibility and polish * fix(audiobooks): stabilize ABS playback progress reporting * fix(audiobooks): clean up ABS branch review fixes * chore(audiobooks): adopt goose layout for ABS migrations * fix(audiobooks): align player seek bar props * feat(audiobooks): make libraries first-class catalog items * feat(admin): add server restart endpoint * fix(audiobooks): address review comment findings --------- Co-authored-by: RXWatcher <14085001+RXWatcher@users.noreply.github.com> Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
500 lines
14 KiB
Go
500 lines
14 KiB
Go
package scanner
|
|
|
|
import (
|
|
"context"
|
|
"encoding/json"
|
|
"fmt"
|
|
"os/exec"
|
|
"slices"
|
|
"strconv"
|
|
"strings"
|
|
|
|
"github.com/Silo-Server/silo-server/internal/lang"
|
|
)
|
|
|
|
// ffprobeOutput represents the top-level JSON output from ffprobe.
|
|
type ffprobeOutput struct {
|
|
Format ffprobeFormat `json:"format"`
|
|
Streams []ffprobeStream `json:"streams"`
|
|
Chapters []ffprobeChapter `json:"chapters"`
|
|
}
|
|
|
|
// ffprobeScalarString accepts ffprobe fields that may be emitted as either
|
|
// JSON strings or numbers depending on codec/container details.
|
|
type ffprobeScalarString string
|
|
|
|
func (s *ffprobeScalarString) UnmarshalJSON(data []byte) error {
|
|
if string(data) == "null" {
|
|
*s = ""
|
|
return nil
|
|
}
|
|
|
|
var str string
|
|
if err := json.Unmarshal(data, &str); err == nil {
|
|
*s = ffprobeScalarString(str)
|
|
return nil
|
|
}
|
|
|
|
var num json.Number
|
|
if err := json.Unmarshal(data, &num); err == nil {
|
|
*s = ffprobeScalarString(num.String())
|
|
return nil
|
|
}
|
|
|
|
return fmt.Errorf("unsupported ffprobe scalar %s", string(data))
|
|
}
|
|
|
|
// ffprobeFormat represents the "format" section of ffprobe JSON output.
|
|
type ffprobeFormat struct {
|
|
Filename string `json:"filename"`
|
|
FormatName string `json:"format_name"`
|
|
FormatLongName string `json:"format_long_name"`
|
|
Duration string `json:"duration"`
|
|
Size string `json:"size"`
|
|
BitRate string `json:"bit_rate"`
|
|
Tags map[string]string `json:"tags"`
|
|
}
|
|
|
|
// ffprobeStream represents a single stream entry in ffprobe JSON output.
|
|
type ffprobeStream struct {
|
|
Index int `json:"index"`
|
|
CodecName string `json:"codec_name"`
|
|
CodecLongName string `json:"codec_long_name"`
|
|
CodecType string `json:"codec_type"`
|
|
Profile string `json:"profile"`
|
|
Level int `json:"level"`
|
|
Width int `json:"width"`
|
|
Height int `json:"height"`
|
|
DisplayAspectRatio string `json:"display_aspect_ratio"`
|
|
FieldOrder string `json:"field_order"`
|
|
AvgFrameRate string `json:"avg_frame_rate"`
|
|
BitRate string `json:"bit_rate"`
|
|
ColorTransfer string `json:"color_transfer"`
|
|
ColorPrimaries string `json:"color_primaries"`
|
|
ColorSpace string `json:"color_space"`
|
|
PixFmt string `json:"pix_fmt"`
|
|
Refs int `json:"refs"`
|
|
BitsPerRawSample ffprobeScalarString `json:"bits_per_raw_sample"`
|
|
BitsPerSample ffprobeScalarString `json:"bits_per_sample"`
|
|
Channels int `json:"channels"`
|
|
ChannelLayout string `json:"channel_layout"`
|
|
SampleRate string `json:"sample_rate"`
|
|
Disposition ffprobeDisp `json:"disposition"`
|
|
Tags map[string]string `json:"tags"`
|
|
SideDataList []ffprobeSideData `json:"side_data_list"`
|
|
}
|
|
|
|
type ffprobeChapter struct {
|
|
ID int `json:"id"`
|
|
Start ffprobeScalarString `json:"start"`
|
|
End ffprobeScalarString `json:"end"`
|
|
TimeBase string `json:"time_base"`
|
|
StartTime ffprobeScalarString `json:"start_time"`
|
|
EndTime ffprobeScalarString `json:"end_time"`
|
|
Tags map[string]string `json:"tags"`
|
|
}
|
|
|
|
type ffprobeSideData struct {
|
|
SideDataType string `json:"side_data_type"`
|
|
DVProfile int `json:"dv_profile"`
|
|
DVBlPresent int `json:"dv_bl_present"`
|
|
DVElPresent int `json:"dv_el_present"`
|
|
}
|
|
|
|
// ffprobeDisp represents the disposition flags on a stream.
|
|
type ffprobeDisp struct {
|
|
Default int `json:"default"`
|
|
Forced int `json:"forced"`
|
|
}
|
|
|
|
// ProbeFile runs ffprobe on the given file and returns parsed ProbeData.
|
|
// ffprobePath is the path to the ffprobe binary. filePath is the media file to probe.
|
|
func ProbeFile(ctx context.Context, ffprobePath string, filePath string) (*ProbeData, error) {
|
|
cmd := exec.CommandContext(ctx, ffprobePath,
|
|
"-v", "quiet",
|
|
"-print_format", "json",
|
|
"-show_format",
|
|
"-show_streams",
|
|
"-show_chapters",
|
|
filePath,
|
|
)
|
|
|
|
output, err := cmd.Output()
|
|
if err != nil {
|
|
return nil, fmt.Errorf("ffprobe failed for %s: %w", filePath, err)
|
|
}
|
|
|
|
var raw ffprobeOutput
|
|
if err := json.Unmarshal(output, &raw); err != nil {
|
|
return nil, fmt.Errorf("ffprobe JSON parse failed for %s: %w", filePath, err)
|
|
}
|
|
|
|
return convertProbeData(&raw), nil
|
|
}
|
|
|
|
// FFprobePathFromFFmpeg derives the sibling ffprobe binary path from a configured ffmpeg path.
|
|
func FFprobePathFromFFmpeg(ffmpegPath string) string {
|
|
if i := strings.LastIndex(ffmpegPath, "ffmpeg"); i >= 0 {
|
|
ffprobePath := ffmpegPath[:i] + "ffprobe" + ffmpegPath[i+len("ffmpeg"):]
|
|
if ffprobePath != "" && ffprobePath != ffmpegPath {
|
|
return ffprobePath
|
|
}
|
|
}
|
|
return "ffprobe"
|
|
}
|
|
|
|
// convertProbeData transforms raw ffprobe JSON output into ProbeData.
|
|
func convertProbeData(raw *ffprobeOutput) *ProbeData {
|
|
pd := &ProbeData{
|
|
Container: detectContainer(raw.Format.FormatName),
|
|
}
|
|
|
|
// Parse duration from format (ffprobe reports seconds).
|
|
// Some containers (notably MKV) may produce duration in microseconds;
|
|
// detect and normalise to seconds when the value is unreasonably large.
|
|
if raw.Format.Duration != "" {
|
|
if dur, err := strconv.ParseFloat(raw.Format.Duration, 64); err == nil {
|
|
const maxReasonableSec = 100_000 // ~27.8 hours
|
|
if dur > maxReasonableSec {
|
|
dur = dur / 1_000_000 // microseconds → seconds
|
|
}
|
|
pd.Duration = int(dur)
|
|
}
|
|
}
|
|
|
|
// Parse bitrate from format (bps to kbps).
|
|
if raw.Format.BitRate != "" {
|
|
if br, err := strconv.Atoi(raw.Format.BitRate); err == nil {
|
|
pd.Bitrate = br / 1000
|
|
}
|
|
}
|
|
|
|
for _, s := range raw.Streams {
|
|
switch s.CodecType {
|
|
case "video":
|
|
track := VideoTrackInfo{
|
|
Title: firstNonEmpty(s.Tags["title"], s.CodecLongName, strings.ToUpper(s.CodecName)),
|
|
Codec: s.CodecName,
|
|
DolbyVision: dolbyVisionProfile(s.SideDataList),
|
|
Profile: s.Profile,
|
|
Level: s.Level,
|
|
Width: s.Width,
|
|
Height: s.Height,
|
|
AspectRatio: s.DisplayAspectRatio,
|
|
Interlaced: isInterlaced(s.FieldOrder),
|
|
FrameRate: normalizeFrameRate(s.AvgFrameRate),
|
|
Bitrate: parseNumeric(s.BitRate) / 1000,
|
|
VideoRange: videoRangeLabel(s),
|
|
ColorPrimaries: s.ColorPrimaries,
|
|
ColorSpace: s.ColorSpace,
|
|
ColorTransfer: s.ColorTransfer,
|
|
BitDepth: parseBitDepth(s),
|
|
PixelFormat: s.PixFmt,
|
|
ReferenceFrames: s.Refs,
|
|
}
|
|
pd.VideoTracks = append(pd.VideoTracks, track)
|
|
if pd.CodecVideo == "" {
|
|
pd.CodecVideo = s.CodecName
|
|
pd.Resolution = mapResolution(s.Width, s.Height)
|
|
pd.HDR = isHDR(s.ColorTransfer)
|
|
}
|
|
case "audio":
|
|
track := AudioTrackInfo{
|
|
Title: firstNonEmpty(s.Tags["title"], s.CodecLongName, strings.ToUpper(s.CodecName)),
|
|
EmbeddedTitle: s.Tags["title"],
|
|
Language: lang.Canonical(s.Tags["language"]),
|
|
Codec: s.CodecName,
|
|
Layout: s.ChannelLayout,
|
|
Channels: s.Channels,
|
|
Bitrate: parseNumeric(s.BitRate) / 1000,
|
|
SampleRate: parseNumeric(s.SampleRate),
|
|
BitDepth: parseBitDepth(s),
|
|
Default: s.Disposition.Default == 1,
|
|
}
|
|
pd.AudioTracks = append(pd.AudioTracks, track)
|
|
if pd.CodecAudio == "" {
|
|
pd.CodecAudio = s.CodecName
|
|
pd.AudioChannels = s.Channels
|
|
}
|
|
case "subtitle":
|
|
track := SubtitleTrackInfo{
|
|
Index: s.Index,
|
|
Codec: s.CodecName,
|
|
Language: lang.Canonical(s.Tags["language"]),
|
|
Title: firstNonEmpty(s.Tags["title"], strings.ToUpper(s.CodecName)),
|
|
EmbeddedTitle: s.Tags["title"],
|
|
Resolution: subtitleResolutionLabel(s),
|
|
Forced: s.Disposition.Forced == 1,
|
|
Default: s.Disposition.Default == 1,
|
|
HearingImpaired: dispositionFlag(s.Tags, "hearing_impaired"),
|
|
}
|
|
pd.SubtitleTracks = append(pd.SubtitleTracks, track)
|
|
}
|
|
}
|
|
|
|
pd.Chapters = normalizeChapters(raw.Chapters, pd.Duration)
|
|
pd.FormatTags = normalizeFormatTags(raw.Format.Tags)
|
|
|
|
return pd
|
|
}
|
|
|
|
func parseNumeric(raw string) int {
|
|
if raw == "" {
|
|
return 0
|
|
}
|
|
v, err := strconv.Atoi(raw)
|
|
if err != nil {
|
|
return 0
|
|
}
|
|
return v
|
|
}
|
|
|
|
func parseFloat(raw string) float64 {
|
|
if raw == "" {
|
|
return 0
|
|
}
|
|
value, err := strconv.ParseFloat(raw, 64)
|
|
if err != nil {
|
|
return 0
|
|
}
|
|
return value
|
|
}
|
|
|
|
func normalizeChapters(raw []ffprobeChapter, durationSeconds int) []ChapterInfo {
|
|
if len(raw) == 0 {
|
|
return []ChapterInfo{}
|
|
}
|
|
|
|
limit := float64(durationSeconds)
|
|
type chapterRange struct {
|
|
title string
|
|
start float64
|
|
end float64
|
|
}
|
|
|
|
ranges := make([]chapterRange, 0, len(raw))
|
|
for _, chapter := range raw {
|
|
start := parseFloat(string(chapter.StartTime))
|
|
end := parseFloat(string(chapter.EndTime))
|
|
if end <= 0 {
|
|
end = parseFloat(string(chapter.End))
|
|
}
|
|
if start <= 0 {
|
|
start = parseFloat(string(chapter.Start))
|
|
}
|
|
if limit > 0 {
|
|
if start < 0 {
|
|
start = 0
|
|
}
|
|
if end > limit {
|
|
end = limit
|
|
}
|
|
}
|
|
if end <= start {
|
|
continue
|
|
}
|
|
|
|
title := strings.TrimSpace(firstNonEmpty(
|
|
chapter.Tags["title"],
|
|
chapter.Tags["TITLE"],
|
|
))
|
|
ranges = append(ranges, chapterRange{
|
|
title: title,
|
|
start: start,
|
|
end: end,
|
|
})
|
|
}
|
|
|
|
if len(ranges) == 0 {
|
|
return []ChapterInfo{}
|
|
}
|
|
|
|
slices.SortStableFunc(ranges, func(a, b chapterRange) int {
|
|
switch {
|
|
case a.start < b.start:
|
|
return -1
|
|
case a.start > b.start:
|
|
return 1
|
|
case a.end < b.end:
|
|
return -1
|
|
case a.end > b.end:
|
|
return 1
|
|
default:
|
|
return 0
|
|
}
|
|
})
|
|
|
|
chapters := make([]ChapterInfo, 0, len(ranges))
|
|
for i, chapter := range ranges {
|
|
end := chapter.end
|
|
if i+1 < len(ranges) && ranges[i+1].start < end {
|
|
end = ranges[i+1].start
|
|
}
|
|
if end <= chapter.start {
|
|
continue
|
|
}
|
|
|
|
title := chapter.title
|
|
if title == "" {
|
|
title = fmt.Sprintf("Chapter %02d", len(chapters)+1)
|
|
}
|
|
chapters = append(chapters, ChapterInfo{
|
|
Index: len(chapters),
|
|
Title: title,
|
|
StartSeconds: chapter.start,
|
|
EndSeconds: end,
|
|
Source: "embedded",
|
|
})
|
|
}
|
|
|
|
return chapters
|
|
}
|
|
|
|
func parseBitDepth(s ffprobeStream) int {
|
|
if v := parseNumeric(string(s.BitsPerRawSample)); v > 0 {
|
|
return v
|
|
}
|
|
return parseNumeric(string(s.BitsPerSample))
|
|
}
|
|
|
|
func normalizeFrameRate(raw string) string {
|
|
if raw == "" || raw == "0/0" {
|
|
return ""
|
|
}
|
|
parts := strings.SplitN(raw, "/", 2)
|
|
if len(parts) != 2 {
|
|
return raw
|
|
}
|
|
num, err1 := strconv.ParseFloat(parts[0], 64)
|
|
den, err2 := strconv.ParseFloat(parts[1], 64)
|
|
if err1 != nil || err2 != nil || den == 0 {
|
|
return raw
|
|
}
|
|
return strconv.FormatFloat(num/den, 'f', 3, 64)
|
|
}
|
|
|
|
func isInterlaced(fieldOrder string) bool {
|
|
switch strings.ToLower(fieldOrder) {
|
|
case "tt", "bb", "tb", "bt":
|
|
return true
|
|
default:
|
|
return false
|
|
}
|
|
}
|
|
|
|
func videoRangeLabel(s ffprobeStream) string {
|
|
if dv := dolbyVisionProfile(s.SideDataList); dv != "" {
|
|
return "DolbyVision"
|
|
}
|
|
if isHDR(s.ColorTransfer) {
|
|
return "HDR"
|
|
}
|
|
return ""
|
|
}
|
|
|
|
func dolbyVisionProfile(sideData []ffprobeSideData) string {
|
|
for _, data := range sideData {
|
|
if strings.EqualFold(data.SideDataType, "DOVI configuration record") && data.DVProfile > 0 {
|
|
return fmt.Sprintf("Profile %d", data.DVProfile)
|
|
}
|
|
}
|
|
return ""
|
|
}
|
|
|
|
func subtitleResolutionLabel(s ffprobeStream) string {
|
|
if s.Width <= 0 || s.Height <= 0 {
|
|
return ""
|
|
}
|
|
return fmt.Sprintf("%dx%d", s.Width, s.Height)
|
|
}
|
|
|
|
func dispositionFlag(tags map[string]string, key string) bool {
|
|
if tags == nil {
|
|
return false
|
|
}
|
|
value := strings.TrimSpace(strings.ToLower(tags[key]))
|
|
return value == "1" || value == "true" || value == "yes"
|
|
}
|
|
|
|
func firstNonEmpty(values ...string) string {
|
|
for _, value := range values {
|
|
if strings.TrimSpace(value) != "" {
|
|
return value
|
|
}
|
|
}
|
|
return ""
|
|
}
|
|
|
|
// mapResolution converts video dimensions to a standard resolution string.
|
|
// Uses upper-bound bucketing (similar to Jellyfin) checking both width and
|
|
// height, which correctly handles ultra-wide and non-standard aspect ratios.
|
|
func mapResolution(width, height int) string {
|
|
switch {
|
|
case width <= 0 && height <= 0:
|
|
return ""
|
|
case width <= 854 && height <= 480:
|
|
return "480p"
|
|
case width <= 1280 && height <= 962:
|
|
return "720p"
|
|
case width <= 2560 && height <= 1440:
|
|
return "1080p"
|
|
case width <= 4096 && height <= 3072:
|
|
return "2160p"
|
|
case width <= 8192 && height <= 6144:
|
|
return "4320p"
|
|
default:
|
|
return "2160p"
|
|
}
|
|
}
|
|
|
|
// isHDR checks whether the color transfer characteristic indicates HDR content.
|
|
func isHDR(colorTransfer string) bool {
|
|
ct := strings.ToLower(colorTransfer)
|
|
return strings.Contains(ct, "smpte2084") || strings.Contains(ct, "arib-std-b67")
|
|
}
|
|
|
|
// normalizeFormatTags lowercases tag keys so callers can look up
|
|
// "title", "artist", "album" without worrying about ffprobe's mixed-case
|
|
// output. Trims whitespace from values.
|
|
func normalizeFormatTags(raw map[string]string) map[string]string {
|
|
if len(raw) == 0 {
|
|
return nil
|
|
}
|
|
out := make(map[string]string, len(raw))
|
|
for k, v := range raw {
|
|
out[strings.ToLower(strings.TrimSpace(k))] = strings.TrimSpace(v)
|
|
}
|
|
return out
|
|
}
|
|
|
|
// detectContainer maps ffprobe format names to common container names.
|
|
func detectContainer(formatName string) string {
|
|
// ffprobe format_name can contain multiple names separated by commas
|
|
// e.g. "mov,mp4,m4a,3gp,3g2,mj2"
|
|
parts := strings.Split(formatName, ",")
|
|
for _, p := range parts {
|
|
p = strings.TrimSpace(p)
|
|
switch p {
|
|
case "matroska", "webm":
|
|
return "mkv"
|
|
case "mov", "mp4", "m4a":
|
|
return "mp4"
|
|
case "avi":
|
|
return "avi"
|
|
case "mpegts":
|
|
return "ts"
|
|
case "flv":
|
|
return "flv"
|
|
case "ogg":
|
|
return "ogg"
|
|
case "wmv", "asf":
|
|
return "wmv"
|
|
}
|
|
}
|
|
// Fallback: return first part
|
|
if len(parts) > 0 && parts[0] != "" {
|
|
return strings.TrimSpace(parts[0])
|
|
}
|
|
return formatName
|
|
}
|