Files
tapir/internal/adapters/store/videos_test.go
T
mathias 2e6fa570a3 feat(store): OnboardBurstVideoIDs — junk-avoiding burst selection (ADR-028)
Newest-first but quality-aware: excludes a video when its duration is KNOWN and
outside [minSeconds, maxSeconds], dropping Shorts and multi-hour livestream VODs
that waste a scarce caption fetch on a poor first impression. NULL/unknown
duration is kept (degrade-open) but ranked after known-good rows. 0/0 bounds
disable the filter (pure newest-first, the reversibility lever). RLS-scoped.
NewestUnsummarizedVideoIDs is left in place for callers that want pure-newest.
2026-06-11 18:41:20 +02:00

221 lines
7.3 KiB
Go

package store_test
import (
"context"
"testing"
"time"
"github.com/stretchr/testify/require"
"gitea.d-ma.be/mathias/tapir/internal/domain"
)
func ytVideo(userID, provVideoID, title string) domain.Video {
return domain.Video{
UserID: userID,
Provider: domain.ProviderYouTube,
ProviderVideoID: provVideoID,
Title: title,
URL: "https://www.youtube.com/watch?v=" + provVideoID,
PublishedAt: time.Date(2026, 6, 1, 12, 0, 0, 0, time.UTC),
// SubscriptionID is a provider resource id, not a UUID — must not be
// written to the UUID column. Set it to prove UpsertVideo ignores it.
SubscriptionID: "yt-subscription-resource-id",
}
}
func TestUpsertVideo_ReturnsStableID(t *testing.T) {
ctx := context.Background()
s := newStore(t)
resetDB(t, rawPool(t))
id1, err := s.UpsertVideo(ctx, ytVideo(userA, "dQw4w9WgXcQ", "first title"))
require.NoError(t, err)
require.NotEmpty(t, id1)
// Same (user, provider, provider_video_id) -> same row, same id, updated meta.
id2, err := s.UpsertVideo(ctx, ytVideo(userA, "dQw4w9WgXcQ", "updated title"))
require.NoError(t, err)
require.Equal(t, id1, id2, "idempotent upsert must return the same durable id")
p := rawPool(t)
var (
title string
count int
)
require.NoError(t, p.QueryRow(ctx,
`SELECT title FROM videos WHERE id = $1`, id1).Scan(&title))
require.Equal(t, "updated title", title, "second upsert must update metadata in place")
require.NoError(t, p.QueryRow(ctx,
`SELECT count(*) FROM videos WHERE user_id = $1`, userA).Scan(&count))
require.Equal(t, 1, count, "must not duplicate the row")
}
func TestUpsertVideo_PersistsAndPreservesDuration(t *testing.T) {
ctx := context.Background()
s := newStore(t)
resetDB(t, rawPool(t))
// First upsert carries a known duration (ADR-028: discovery enriches it).
v := ytVideo(userA, "dur0000001x", "with duration")
v.DurationSeconds = 750
id, err := s.UpsertVideo(ctx, v)
require.NoError(t, err)
p := rawPool(t)
readDuration := func() *int {
var d *int
require.NoError(t, p.QueryRow(ctx, `SELECT duration_s FROM videos WHERE id = $1`, id).Scan(&d))
return d
}
require.NotNil(t, readDuration())
require.Equal(t, 750, *readDuration(), "duration must persist")
// A later upsert that does NOT know the duration (0) must not clobber it —
// the channel_title backfill stance (migration 014): COALESCE-preserve.
v2 := ytVideo(userA, "dur0000001x", "title updated, duration unknown")
v2.DurationSeconds = 0
_, err = s.UpsertVideo(ctx, v2)
require.NoError(t, err)
require.NotNil(t, readDuration(), "a 0/unknown re-upsert must not erase a known duration")
require.Equal(t, 750, *readDuration())
}
func TestUpsertVideo_IDMatchesSummaryDedup(t *testing.T) {
ctx := context.Background()
s := newStore(t)
resetDB(t, rawPool(t))
// Upsert assigns the durable video id; a summary delivered under that id
// must then show up in SeenVideoIDs — this is the cross-restart dedup chain.
id, err := s.UpsertVideo(ctx, ytVideo(userA, "abc123", "t"))
require.NoError(t, err)
require.NoError(t, s.Deliver(ctx, summary(userA, id, "the summary")))
seen, err := s.SeenVideoIDs(ctx, userA)
require.NoError(t, err)
require.True(t, seen[id], "the upserted video id must match the summary dedup key")
}
func TestUpsertVideo_PerUserIsolation(t *testing.T) {
ctx := context.Background()
s := newStore(t)
resetDB(t, rawPool(t))
idA, err := s.UpsertVideo(ctx, ytVideo(userA, "same-provider-id", "a"))
require.NoError(t, err)
idB, err := s.UpsertVideo(ctx, ytVideo(userB, "same-provider-id", "b"))
require.NoError(t, err)
require.NotEqual(t, idA, idB, "same provider video for two users must be two distinct rows")
}
func TestNewestUnsummarizedVideoIDs(t *testing.T) {
ctx := context.Background()
s := newStore(t)
resetDB(t, rawPool(t))
mk := func(user, pid string, day int) string {
v := ytVideo(user, pid, pid)
v.PublishedAt = time.Date(2026, 6, day, 12, 0, 0, 0, time.UTC)
id, err := s.UpsertVideo(ctx, v)
require.NoError(t, err)
return id
}
_ = mk(userA, "a1vid000001", 1)
id2 := mk(userA, "a2vid000002", 2)
id3 := mk(userA, "a3vid000003", 3)
id4 := mk(userA, "a4vid000004", 4)
mk(userB, "b1vid000009", 9) // userB's newest — must never leak via RLS
// The newest (v4) is summarized, so it's excluded from "unsummarized".
require.NoError(t, s.Deliver(ctx, summary(userA, id4, "done")))
// Cap 2, newest-first unsummarized: v3 then v2 (v4 excluded; userB excluded).
got, err := s.NewestUnsummarizedVideoIDs(ctx, userA, 2)
require.NoError(t, err)
require.Equal(t, []string{id3, id2}, got)
none, err := s.NewestUnsummarizedVideoIDs(ctx, userA, 0)
require.NoError(t, err)
require.Empty(t, none, "limit 0 returns nothing")
}
func TestOnboardBurstVideoIDs(t *testing.T) {
ctx := context.Background()
s := newStore(t)
resetDB(t, rawPool(t))
mk := func(user, pid string, day, dur int) string {
v := ytVideo(user, pid, pid)
v.PublishedAt = time.Date(2026, 6, day, 12, 0, 0, 0, time.UTC)
v.DurationSeconds = dur // 0 == unknown (NULL)
id, err := s.UpsertVideo(ctx, v)
require.NoError(t, err)
return id
}
good1 := mk(userA, "good0000001", 5, 600) // 10m, newest known-good
tooLong := mk(userA, "toolong0001", 4, 20000) // > maxSeconds -> dropped
_ = tooLong
tooShort := mk(userA, "tooshort001", 3, 30) // < minSeconds -> dropped
_ = tooShort
unknown := mk(userA, "unknown0001", 2, 0) // NULL duration -> kept, ranked last
good2 := mk(userA, "good0000002", 1, 800) // known-good but oldest
mk(userB, "bvid0000009", 9, 600) // userB -> must not leak via RLS
const minSec, maxSec = 60, 14400
// Known-good ranked before unknown, each newest-first within its group; the
// too-long and too-short videos are excluded by their known duration.
got, err := s.OnboardBurstVideoIDs(ctx, userA, 5, minSec, maxSec)
require.NoError(t, err)
require.Equal(t, []string{good1, good2, unknown}, got,
"known-good first (newest-first), then unknown-duration; junk excluded")
// Cap is honoured.
capped, err := s.OnboardBurstVideoIDs(ctx, userA, 2, minSec, maxSec)
require.NoError(t, err)
require.Equal(t, []string{good1, good2}, capped)
// Bounds disabled (0/0) == pure newest-first, nothing excluded.
all, err := s.OnboardBurstVideoIDs(ctx, userA, 10, 0, 0)
require.NoError(t, err)
require.ElementsMatch(t, []string{good1, tooLong, tooShort, unknown, good2}, all,
"0/0 bounds disable the duration filter (prior newest-first behaviour)")
// limit <= 0 returns nothing.
none, err := s.OnboardBurstVideoIDs(ctx, userA, 0, minSec, maxSec)
require.NoError(t, err)
require.Empty(t, none)
}
func TestUpsertVideoPersistsChannelAndDistinctChannels(t *testing.T) {
ctx := context.Background()
s := newStore(t)
resetDB(t, rawPool(t))
mk := func(pid, channel string) {
v := ytVideo(userA, pid, pid)
v.ChannelTitle = channel
_, err := s.UpsertVideo(ctx, v)
require.NoError(t, err)
}
mk("aa11111aaaa", "Acme Talks")
mk("bb22222bbbb", "Acme Talks") // same channel
mk("cc33333cccc", "Zeta Channel")
// userB's channel must not leak.
vb := ytVideo(userB, "dd44444dddd", "x")
vb.ChannelTitle = "Bravo Only"
_, err := s.UpsertVideo(ctx, vb)
require.NoError(t, err)
got, err := s.DistinctChannels(ctx, userA)
require.NoError(t, err)
require.Equal(t, []string{"Acme Talks", "Zeta Channel"}, got,
"distinct, alphabetical, user-scoped (no Bravo Only)")
}