Files
silo-server/internal/recommendations/accuracy_test.go
8b70357703 feat(ebooks): first-class ebook libraries, scanner, and reader (#124)
* docs: define ebook architecture matching audiobooks

* docs: plan ebook audiobook-parity implementation

* feat: add ebook scanner parser foundation

* fix: harden ebook scanner foundation

* fix: handle ebook isbn labels

* fix: guard ebook subtree scans

* feat: scan ebook libraries in core

* fix: preserve ebook scan people credits

* fix: refresh ebook scan metadata safely

* feat: persist ebook series membership

* test: cover ebook series persistence decisions

* fix: address ebook scanner PR review

* docs: clarify ebook foundation PR scope

* feat: add ebook metadata enricher

* fix: harden ebook poster cache

* feat: wire ebook metadata sync task

* feat: expose ebook library metadata setup

* feat: add ebook catalog scope support

* feat: add ebook detail view

* feat: label ebook file versions by format

* feat: use file-size copy for downloads

* feat: use file language in download dialog

* test: cover ebook detail authors and downloads

* fix: drop narrator credits from ebook scanner merges

* fix: align ebook collection filters with book media

* fix: drop asin provider ids from ebook enrichment

* fix: force ebook people refresh for stale narrators

* chore: omit ebook planning docs from branch

* feat: add ebook detail related content

* feat: add ebook reader file entrypoint

* feat: render ebooks with foliate reader

* feat: persist ebook reader progress

* feat: add ebook reader controls

* feat: extract ebook pdf metadata

* feat: favor scanner isbn during ebook enrichment

* feat: extract fbz ebook metadata

* feat: count cbz ebook pages

* feat: show ebook file page counts

* feat: show ebook download summaries

* feat: switch ebook reader files

* feat: prefer epub for ebook read action

* feat: surface ebook reader progress

* feat: sync ebook reader progress cache

* feat: hide ebook read action for unsupported files

* feat: filter ebook reader file selector

* fix: serve fbz ebook archives with reader mime type

* fix: detect fbz ebooks from compound filename

* fix: authorize fbz ebooks from compound filename

* fix: scope ebook catalog facets

* fix: reject narrator queries for ebooks

* fix: build ebook recommendation text from authors

* fix: include ebooks in embedding eligibility

* fix: include ebooks in recommendation media mix

* fix: include ebooks in recently added recommendations

* feat: include ebook progress in recommendation signals

* feat: include ebooks in continue watching sections

* feat: include ebooks in catalog progress metrics

* fix: read ebook isbn from epub metadata

* fix: filter ebook asin provider aliases

* fix: fall back from unsupported ebook reader files

* fix: sort ebook catalogs by reader progress

* fix: filter ebook catalogs by reader progress

* fix: include ebooks in last watched catalog filters

* feat: reflect ebook reader progress in item user state

* feat: share ebook progress state across item surfaces

* feat: report ebook scan progress

* fix: include ebook activity in recommendations

* fix: expose ebook reader progress on item detail

* fix: support ebook subtree scans

* fix: honor profile header for ebook item progress

* fix: add ebook library default sections

* fix: route ebook continue cards to reader

* fix: hide watched toggle for ebooks

* fix: route ebook watch tonight cards to reader

* fix: route ebook hero actions to reader

* fix: detect archive ebook reader formats by filename

* feat: cache embedded ebook covers during scan

* fix: encode ebook hero reader links

* fix: persist non-epub ebook reader progress

* fix: scope narrator catalog badges to audiobooks

* fix: merge ebook reader progress during item repair

* fix: label ebook progress filters as read

* fix: show ebook related rails as book covers

* fix: remove txt ebook reader support

* fix: reject txt ebook reader files

* fix: label ebook advanced filters as read

* fix: label ebook personalized sorts as read

* fix: remove plain text reader loader path

* test: cover ebook unread catalog rules

* fix: preserve ebook reader library context

* fix: link ebook genres with library scope

* fix: encode related rail item links

* fix: encode catalog card item links

* fix: encode hero and continue item links

* fix: encode watch tonight item links

* fix: encode recommendation and search item links

* test: cover ebook scan format set

* fix: label ebook search results clearly

* fix: make global search prompt media neutral

* fix: encode catalog read API ids

* fix: encode item API ids

* fix: include ebook reader vendor in docker build

* fix: make ebook reader build clean

* fix: clean ebook embedded descriptions

* docs: plan ebook reader shell parity

* feat: add ebook reader shell controls

* fix: widen ebook scrolled reader flow

* fix: remove scrolled reader content width cap

* docs: plan ebook reader full parity

* feat: persist ebook reader config

* feat: add ebook annotations and bookmarks

* feat: add ebook reader tools and aids

* feat: add ebook advanced reader settings

* fix: keep ebook reader panel in viewport

* fix: use foliate sizing units for ebook scroll flow

* fix: keep ebook settings controls readable

* fix: simplify ebook reader settings controls

* feat(ebooks): extract local covers during scan (#98)

* feat(ebooks): extract local covers during scan

* fix(ebooks): read nullable poster paths during cover scan

* fix(catalog): coalesce nullable media artwork fields

* fix(ebooks): group sibling formats by book identity

* fix(ebooks): tolerate legacy ebook metadata encodings

* fix(ebooks): decode PDF hex metadata strings

* fix(ebooks): harden local cover extraction and format grouping

Address review findings on the local cover scan:

- Restrict generic sidecar covers (cover.jpg, folder.png, ...) to
  single-book directories, always accept images named after the book
  file, and apply exactly one cover per reconcile with sidecar taking
  precedence over the embedded cover.
- Replace the read-then-write poster update with an atomic conditional
  UPDATE (ItemRepository.SetLocalPoster) so provider/admin artwork is
  never clobbered by concurrent writers, and refresh locally owned
  posters when the extracted cover bytes change (thumbhash compare).
- Preserve UTF-8 PDF Info strings (including a UTF-8 BOM) instead of
  forcing everything through Windows-1252; the cp1252 fallback now only
  applies to non-UTF-8 bytes.
- Select EPUB covers by manifest media-type with properties="cover-image"
  outranking the EPUB2 meta name="cover" id, so XHTML cover pages no
  longer shadow the real image.
- Order CBZ pages naturally (2.jpg before 10.jpg, ch2/ before ch10/)
  when picking the cover page, via a single O(n) min-scan.
- Bump the ebook content group key scheme to version 2 and reprocess
  rows written under older versions so pre-existing libraries gain
  sibling-format grouping instead of accumulating duplicates.
- Group different formats only (a same-format sibling with colliding
  sparse metadata stays a separate item) and stop a joining sibling's
  embedded metadata from overwriting a provider-matched item.
- Decode any IANA-labelled OPF/FB2 XML charset (windows-1251, koi8-r,
  shift_jis, ...) via x/net/html/charset, and wire the charset reader
  into FB2 parsing which previously had none.
- Strip the full .fb2.zip double extension from filename-derived titles
  and group keys.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

---------

Co-authored-by: rxwatcher <rxwatcher@users.noreply.github.com>
Co-authored-by: Quick <31828688+Quick104@users.noreply.github.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>

* feat(ebooks): add reader profiles and ruler (#99)

* feat(ebooks): extract local covers during scan

* fix(ebooks): read nullable poster paths during cover scan

* fix(catalog): coalesce nullable media artwork fields

* fix(ebooks): group sibling formats by book identity

* fix(ebooks): tolerate legacy ebook metadata encodings

* fix(ebooks): decode PDF hex metadata strings

* feat(ebooks): add reader profiles and ruler

* fix(ebooks): address reader ruler and profile review findings

- skip renderer setStyles/render when computed styles and attributes are
  unchanged, so ruler position updates no longer re-style the book view
- drag the ruler via a local draft that commits on release, with the
  surface rect cached at pointer-down
- migrate font values persisted before the generic stacks (Inter,
  Georgia, Merriweather, legacy serif) so the font select never renders
  blank, with a Custom fallback option for unknown values
- make the ruler band click-through and move dragging to a dedicated
  keyboard-accessible slider handle so links and text selection keep
  working under the band
- share font stacks between options and profiles via READER_FONT_STACKS
- surface the active reading profile, move presets to the top of the
  settings panel, and drop the redundant profile button aria-labels

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix(ebooks): resolve prefer-const lint error in readest document lib

`pnpm run lint` failed on the branch because `direction` is never
reassigned in getDirection; split the destructure so only the
reassigned `writingMode` stays mutable.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

---------

Co-authored-by: rxwatcher <rxwatcher@users.noreply.github.com>
Co-authored-by: Quick <31828688+Quick104@users.noreply.github.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>

* Merge branch 'main' into work/ebooks-reader-base

Brings the ebook integration branch up to date with main (audiobook
library redesign, continue-watching rework and card affordances,
quic-go bump, jellycompat fixes). Conflict resolutions favor main's
generalized mechanisms and register ebooks with them:

- media scope validation goes through IsValidMediaScope (now including
  "ebook" alongside main's "video" group scope), in Go and in the web
  filter/search types
- continue-watching uses main's typed rails; reading-type sections pull
  resume points from ebook_reader_progress and the ebook library default
  section is wired to ContinueTypeConfig(ContinueTypeReading)
- item_repo keeps main's derived select-list machinery (itemColumnExpr)
  and both poster accessors (GetPoster/SetLocalPoster for ebook covers,
  GetPosterPath for audiobook covers)
- web cards/hero/watch-tonight adopt main's buildMediaPlayHref helpers,
  which now route ebooks to /reader/ebook and encode content ids;
  ebook affordances (BookOpen icon, Read verb, percent-read subtitle)
  carry over onto main's reworked components
- LibraryForm ebook support ported into main's refactored
  useLibraryForm/libraryTypes modules

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix(docker): copy foliate-js vendor into Dockerfile.dev frontend stage

foliate-js is a file:vendor/foliate-js dependency, so pnpm install needs
the vendor directory before the lockfile install layer. The production
Dockerfile already copies it; the dev image was missed, breaking
make dev-deploy with ENOENT on /app/web/vendor/foliate-js.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* feat(ebooks): render Continue Reading sections as upright poster cards

All-ebook continue sections previously fell through to the horizontal
16:9 wide card; include ebooks in the poster-variant check so book
covers render in their natural 2:3 framing.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix(ui): stop related-rail highlight ring clipping on detail pages

Move the current-item ring onto the cover artwork with a themed
ring-offset color (matching the sidebar profile highlight) and give
the scroll container top headroom so the ring is not cut off by
overflow-x-auto. Applies to both ebook and audiobook detail rails.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix(scanner): harden ebook scanning against data loss and bad metadata

- Reconcile missing ebook files like video/audio, with real per-root walk
  failure tracking (failed/unmounted roots are excluded from deletion),
  symlinked-root support via the shared logical walker, and the empty-root
  cleanup allowance before any destructive reconciliation.
- Create ebook items as 'pending' so enrichment can promote them to
  'matched' (backfill migration included), and protect matched items from
  re-scan clobbering: title/year skipped, people/series fill-empty only.
- PDF metadata: scan head + tail windows (non-linearized PDFs keep the Info
  dict at the end), require proper key delimiters, head values win.
- Cap plain .fb2 reads like .fbz entries; drop .md as an ebook format.
- gofmt internal/scanner/audiobook.go (pre-existing drift).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix(ebooks): make enrichment failures non-terminal with dedicated backoff state

- Provider errors now record a failure (capped retries) instead of stamping
  last_refreshed, which permanently excluded items after transient outages.
- Unconfigured metadata chains and the scan-window membership race skip the
  item without stamping or burning a retry.
- Failure tracking moves to a new ebook_enrichment_state table, decoupling
  it from media_items.refresh_failures (shared with metadata refresh debt).
- Preserve non-author people credits when persisting enrichment results.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix(catalog): gate ebook progress on hidden history and centralize threshold

- Apply user_history_hidden_items gating (video semantics) to the ebook
  watched/in-progress filters, progress sort plan, and Continue Reading.
- Continue Reading pages past dismissed items via the shared collector and
  dedupes items across pages (also fixes the video path's latent exposure).
- Centralize the 0.9 finished threshold as models.EbookFinishedProgressThreshold
  with a single SQL-interpolated mirror in catalog.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix(recommendations): correct watcher counting and wire ebook taste signals

- itemWatchersQuery dedupes to distinct (watcher, item) rows so one
  binge-watcher can no longer satisfy minWatchers; the eligibility floor
  now counts distinct accounts rather than profiles.
- Hidden-history gating on GetEbookReaderProgressForUser (signal reader).
- Ebook reading produces canonical implicit taste signals (weighted like
  the equivalent movie progress ratio); ebooks join taste-seed candidates.
- Stale GetRecentlyAddedItems doc comment corrected.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix(api): harden ebook reader endpoints and serve a Content-Security-Policy

- Serve a CSP on all SPA HTML responses: blob/srcdoc book iframes inherit
  it, so script-src 'self' 'wasm-unsafe-eval' blocks script execution from
  malicious book content (sandbox alone is defeated by the WebKit
  allow-scripts requirement). Threat model documented on the constant.
- X-Content-Type-Options: nosniff on frontend, jellycompat, and ebook file
  responses; MIME resolution can no longer fall through to octet-stream
  for an admitted ebook file.
- Annotation PATCH: presence-aware field semantics (absent keeps, present
  sets/clears), invariant re-validation on the merged row, and an atomic
  SELECT ... FOR UPDATE read-merge-write.
- Request size caps (413) on progress/config/annotation writes;
  Content-Disposition via mime.FormatMediaType; hidden-history gating in
  the shared ebook progress lister; FK-cascade indexes for reader tables.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* feat(api): native read-state endpoints for ebooks

- POST/DELETE /watched/{id} accepts ebook content IDs: mark read upserts
  progress 1.0 preserving the reader's file/location (or picks the
  preferred reader file for never-opened books); mark unread mirrors video
  unwatch semantics and deletes the progress row.
- /history/remove accepts ebooks: hides via user_history_hidden_items
  without touching the reading position (hidden != unread; next reading
  activity resurfaces the book, mirroring video re-watch).
- Access-filter checks match the video branch; shared logic lives in
  ebook_read_state.go. Sort metrics/user-state thresholds use the shared
  constant; profile-header fallback deduplicated.

Clients: response is {type: "ebook", affected_count: 1, played: bool};
the existing watched SSE event fires.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix(web): harden the ebook reader UI

- Open-flow race: cancellation checked after every await with full stale-run
  teardown (no wrong-file progress saves, no leaked views/blob URLs);
  book.destroy() on cleanup.
- Progress: monotonic stale-response guard; visibilitychange flush uses the
  refresh-capable client, pagehide uses keepalive; per-book cross-format
  progress documented as deliberate.
- Settings: side effects out of the setState updater; local edits no longer
  clobbered by late server config; pending saves flushed on unmount/pagehide.
- TTS: generation token so Stop actually stops (Chromium/Firefox synthetic
  events); Media Session uninstalled on unmount.
- External book links: http(s) only, opened with noopener,noreferrer.
- apiBlob 512 MiB guard with a user-facing error; fraction bookmarks
  navigable; search-result key collisions fixed; dead e-ink code removed;
  getLibrarySortRelevanceScope deduplicated; md format dropped.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* feat(web): mark read/unread affordances for ebooks

- Item detail gets a Mark Read/Unread button; card menus drop the ebook
  gate and share type-aware labels/toasts (also dedupes audiobook wording).
- Watched-state invalidation includes the reader progress query key so the
  Continue button and percent refresh after toggling.
- Continue Reading dismiss copy for ebooks; dismissal path now URL-encodes
  item IDs (ebook content IDs can contain reserved characters).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* docs: record the PR #124 review and hardening pass

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

---------

Co-authored-by: rxwatcher <rxwatcher@users.noreply.github.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-06-10 08:18:35 -04:00

328 lines
11 KiB
Go

package recommendations
import (
"slices"
"testing"
"github.com/Silo-Server/silo-server/internal/config"
)
func TestApplyGenreCapCountsAllGenres(t *testing.T) {
items := []ScoredItem{
{MediaItemID: "a", Score: 1.0},
{MediaItemID: "b", Score: 0.9},
{MediaItemID: "c", Score: 0.8},
{MediaItemID: "d", Score: 0.7},
}
genres := map[string][]string{
"a": {"Action", "Drama"},
"b": {"Action", "Comedy"},
"c": {"Action", "Thriller"},
"d": {"Comedy"},
}
capped := applyGenreCap(items, genres, 0.67)
if len(capped) != 3 {
t.Fatalf("expected 3 capped items, got %d", len(capped))
}
for _, item := range capped {
if item.MediaItemID == "c" {
t.Fatalf("expected lowest-scored Action item to be removed, got %#v", capped)
}
}
}
func TestHNSWEfSearchUsesCandidateLimitFloor(t *testing.T) {
tests := []struct {
name string
candidateLimit int
want int
}{
{name: "raises small scans", candidateLimit: 40, want: minHNSWEfSearch},
{name: "keeps exact floor", candidateLimit: minHNSWEfSearch, want: minHNSWEfSearch},
{name: "keeps larger scans", candidateLimit: 900, want: 900},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
if got := hnswEfSearch(tt.candidateLimit); got != tt.want {
t.Fatalf("hnswEfSearch(%d) = %d, want %d", tt.candidateLimit, got, tt.want)
}
})
}
}
func TestApplyMediaTypeFloorAddsAvailableSupplementalType(t *testing.T) {
items := []ScoredItem{
{MediaItemID: "s1", Score: 1.00},
{MediaItemID: "s2", Score: 0.99},
{MediaItemID: "s3", Score: 0.98},
{MediaItemID: "s4", Score: 0.97},
{MediaItemID: "s5", Score: 0.96},
{MediaItemID: "s6", Score: 0.95},
{MediaItemID: "s7", Score: 0.94},
{MediaItemID: "s8", Score: 0.93},
{MediaItemID: "s9", Score: 0.92},
{MediaItemID: "s10", Score: 0.91},
}
candidates := append([]ScoredItem(nil), items...)
candidates = append(candidates,
ScoredItem{MediaItemID: "m1", Score: 0.90},
ScoredItem{MediaItemID: "m2", Score: 0.89},
)
mediaTypes := map[string]string{
"s1": "series", "s2": "series", "s3": "series", "s4": "series", "s5": "series",
"s6": "series", "s7": "series", "s8": "series", "s9": "series", "s10": "series",
"m1": "movie", "m2": "movie",
}
mixed := applyMediaTypeFloor(items, candidates, mediaTypes)
if got := len(mixed); got != len(items) {
t.Fatalf("expected result length to stay %d, got %d", len(items), got)
}
if got := countMediaType(mixed, mediaTypes, "movie"); got != 2 {
t.Fatalf("expected 2 movies from supplemental candidates, got %d in %#v", got, mixed)
}
if slices.ContainsFunc(mixed, func(item ScoredItem) bool { return item.MediaItemID == "s10" }) {
t.Fatalf("expected lowest-ranked series tail item to be replaced, got %#v", mixed)
}
}
func TestApplyMediaTypeFloorAddsAvailableAudiobooks(t *testing.T) {
items := []ScoredItem{
{MediaItemID: "m1", Score: 1.00},
{MediaItemID: "m2", Score: 0.99},
{MediaItemID: "m3", Score: 0.98},
{MediaItemID: "m4", Score: 0.97},
{MediaItemID: "m5", Score: 0.96},
{MediaItemID: "m6", Score: 0.95},
{MediaItemID: "m7", Score: 0.94},
{MediaItemID: "m8", Score: 0.93},
{MediaItemID: "m9", Score: 0.92},
{MediaItemID: "m10", Score: 0.91},
}
candidates := append([]ScoredItem(nil), items...)
candidates = append(candidates,
ScoredItem{MediaItemID: "a1", Score: 0.90},
ScoredItem{MediaItemID: "a2", Score: 0.89},
)
mediaTypes := map[string]string{
"m1": "movie", "m2": "movie", "m3": "movie", "m4": "movie", "m5": "movie",
"m6": "movie", "m7": "movie", "m8": "movie", "m9": "movie", "m10": "movie",
"a1": "audiobook", "a2": "audiobook",
}
mixed := applyMediaTypeFloor(items, candidates, mediaTypes)
if got := countMediaType(mixed, mediaTypes, "audiobook"); got != 2 {
t.Fatalf("expected 2 audiobooks from supplemental candidates, got %d in %#v", got, mixed)
}
}
func TestApplyMediaTypeFloorNoopsWithoutSupplementalType(t *testing.T) {
items := []ScoredItem{
{MediaItemID: "s1", Score: 1.00},
{MediaItemID: "s2", Score: 0.99},
{MediaItemID: "s3", Score: 0.98},
{MediaItemID: "s4", Score: 0.97},
{MediaItemID: "s5", Score: 0.96},
}
mediaTypes := map[string]string{
"s1": "series", "s2": "series", "s3": "series", "s4": "series", "s5": "series",
}
mixed := applyMediaTypeFloor(items, items, mediaTypes)
if !slices.EqualFunc(mixed, items, func(a, b ScoredItem) bool {
return a.MediaItemID == b.MediaItemID && a.Score == b.Score
}) {
t.Fatalf("expected unchanged result without supplemental type, got %#v", mixed)
}
}
func TestApplyMediaTypeFloorIncludesEbookSupplement(t *testing.T) {
items := []ScoredItem{
{MediaItemID: "s1", Score: 1.00},
{MediaItemID: "s2", Score: 0.99},
{MediaItemID: "s3", Score: 0.98},
{MediaItemID: "s4", Score: 0.97},
{MediaItemID: "s5", Score: 0.96},
}
candidates := append([]ScoredItem(nil), items...)
candidates = append(candidates, ScoredItem{MediaItemID: "e1", Score: 0.95})
mediaTypes := map[string]string{
"s1": "series",
"s2": "series",
"s3": "series",
"s4": "series",
"s5": "series",
"e1": "ebook",
}
mixed := applyMediaTypeFloor(items, candidates, mediaTypes)
if got := countMediaType(mixed, mediaTypes, "ebook"); got != 1 {
t.Fatalf("expected 1 ebook from supplemental candidates, got %d in %#v", got, mixed)
}
}
func TestApplyGenreCapDoesNotCollapseConcentratedRows(t *testing.T) {
items := []ScoredItem{
{MediaItemID: "a", Score: 1.0},
{MediaItemID: "b", Score: 0.9},
{MediaItemID: "c", Score: 0.8},
{MediaItemID: "d", Score: 0.7},
{MediaItemID: "e", Score: 0.6},
{MediaItemID: "f", Score: 0.5},
}
genres := map[string][]string{
"a": {"Science Fiction", "Drama"},
"b": {"Science Fiction", "Drama"},
"c": {"Science Fiction", "Drama"},
"d": {"Science Fiction", "Drama"},
"e": {"Science Fiction", "Drama"},
"f": {"Science Fiction", "Drama"},
}
capped := applyGenreCap(items, genres, 0.4)
if len(capped) != 3 {
t.Fatalf("got %d capped items, want retained half of concentrated row", len(capped))
}
if capped[0].MediaItemID != "a" || capped[1].MediaItemID != "b" || capped[2].MediaItemID != "c" {
t.Fatalf("unexpected capped items: %#v", capped)
}
}
func TestCollaborativeSupportAggregatesAcrossPeers(t *testing.T) {
candidates := map[string]collaborativeCandidate{}
addCollaborativeSupport(candidates, "shared", 0.4)
addCollaborativeSupport(candidates, "shared", 0.3)
addCollaborativeSupport(candidates, "single", 0.6)
if candidates["shared"].score <= candidates["single"].score {
t.Fatalf("shared score = %f, single score = %f; expected aggregated shared support to win", candidates["shared"].score, candidates["single"].score)
}
if candidates["shared"].support != 2 {
t.Fatalf("shared support = %d, want 2", candidates["shared"].support)
}
}
func TestCowatchMatrixTreatsProfilesAsDistinctWatchers(t *testing.T) {
watchers := map[string][]string{
"a": {"1:p1", "1:p2"},
"b": {"1:p1", "1:p2"},
}
pairs := computeCowatchMatrix(watchers, 2, 2, 10)
if len(pairs) != 2 {
t.Fatalf("got %d co-watch pairs, want 2: %#v", len(pairs), pairs)
}
for _, pair := range pairs {
if pair.CowatchCount != 2 {
t.Fatalf("cowatch count = %d, want two profile identities: %#v", pair.CowatchCount, pair)
}
}
}
func TestCompatiblePeerContentRatingsIncludesLowerAndExcludesHigher(t *testing.T) {
ratings := compatiblePeerContentRatings("PG-13")
for _, want := range []string{"G", "PG", "PG-13", "TV-14"} {
if !slices.Contains(ratings, want) {
t.Fatalf("expected %q in compatible ratings: %#v", want, ratings)
}
}
for _, blocked := range []string{"R", "NC-17", "TV-MA"} {
if slices.Contains(ratings, blocked) {
t.Fatalf("did not expect %q in compatible ratings: %#v", blocked, ratings)
}
}
}
func TestMMRLambdaUsesConfiguredGlobalOverride(t *testing.T) {
engine := &Engine{cfg: config.RecommendationsConfig{DiversityLambda: 0.25}}
if got := engine.mmrLambda(0.8); got != 0.25 {
t.Fatalf("mmrLambda = %f, want configured override", got)
}
engine.cfg.DiversityLambda = 1.2
if got := engine.mmrLambda(0.8); got != 0.8 {
t.Fatalf("mmrLambda = %f, want fallback default for invalid override", got)
}
}
func TestEmbeddingTextNeedsRefreshIncludesEmptyCanonicalText(t *testing.T) {
if !embeddingTextNeedsRefresh("model-a", "", "generated text", "model-a") {
t.Fatal("expected same-model row with empty canonical text to be stale")
}
if !embeddingTextNeedsRefresh("model-a", "old text", "generated text", "model-a") {
t.Fatal("expected changed canonical text to be stale")
}
if embeddingTextNeedsRefresh("model-a", "generated text", "generated text", "model-a") {
t.Fatal("did not expect matching model and canonical text to be stale")
}
}
func TestBuildTasteClustersDeterministic(t *testing.T) {
items := []clusterItem{
clusterTestItem("a1", []float32{1, 0}, 1, "Action"),
clusterTestItem("a2", []float32{0.98, 0.02}, 0.9, "Action"),
clusterTestItem("a3", []float32{0.95, 0.05}, 0.8, "Action"),
clusterTestItem("a4", []float32{0.9, 0.1}, 0.7, "Action"),
clusterTestItem("a5", []float32{0.88, 0.12}, 0.6, "Action"),
clusterTestItem("a6", []float32{0.86, 0.14}, 0.5, "Action"),
clusterTestItem("d1", []float32{0, 1}, 1, "Drama"),
clusterTestItem("d2", []float32{0.02, 0.98}, 0.9, "Drama"),
clusterTestItem("d3", []float32{0.05, 0.95}, 0.8, "Drama"),
clusterTestItem("d4", []float32{0.1, 0.9}, 0.7, "Drama"),
clusterTestItem("d5", []float32{0.12, 0.88}, 0.6, "Drama"),
clusterTestItem("d6", []float32{0.14, 0.86}, 0.5, "Drama"),
}
first := buildTasteClusters(items)
second := buildTasteClusters(items)
if len(first) != len(second) {
t.Fatalf("cluster count changed: %d vs %d", len(first), len(second))
}
for i := range first {
if first[i].Label != second[i].Label ||
first[i].MemberCount != second[i].MemberCount ||
first[i].TotalWeight != second[i].TotalWeight {
t.Fatalf("cluster %d changed: %#v vs %#v", i, first[i], second[i])
}
}
}
func TestDeduplicateThenTrimKeepsBackfillCandidates(t *testing.T) {
seen := map[string]struct{}{"already-seen": {}}
items := []ScoredItem{
{MediaItemID: "already-seen", Score: 1.0},
{MediaItemID: "next-best", Score: 0.9},
{MediaItemID: "backfill", Score: 0.8},
}
row := ForYouRow{Items: deduplicateItems(items, seen)}
rows := trimRows([]ForYouRow{row}, 2)
if len(rows[0].Items) != 2 {
t.Fatalf("got %d items, want 2", len(rows[0].Items))
}
if rows[0].Items[0].MediaItemID != "next-best" || rows[0].Items[1].MediaItemID != "backfill" {
t.Fatalf("unexpected retained items: %#v", rows[0].Items)
}
}
func clusterTestItem(id string, embedding []float32, weight float64, genre string) clusterItem {
return clusterItem{
itemID: id,
embedding: embedding,
weight: weight,
genres: []string{genre},
}
}