Compare commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
f66c1bcdcc | ||
|
|
1e65c3b413 | ||
|
|
87c978774f | ||
|
|
70a9f1d4cd | ||
|
|
1d5b2c6365 | ||
|
|
62acfee2ed | ||
|
|
2907801aca | ||
|
|
59050c4db6 | ||
|
|
c320ed88aa | ||
|
|
bddd75d92e |
@@ -32,7 +32,10 @@ func serialize(mu *sync.Mutex, run discoveryRunner) discoveryRunner {
|
||||
type discoveryTrigger struct {
|
||||
ctx context.Context
|
||||
run discoveryRunner
|
||||
log *slog.Logger
|
||||
// onboard, when set, runs after the discovery pass to summarize a capped number
|
||||
// of the user's newest videos (Feature 1). Optional.
|
||||
onboard func(ctx context.Context, userID string)
|
||||
log *slog.Logger
|
||||
}
|
||||
|
||||
func (t *discoveryTrigger) Enqueue(userID string) {
|
||||
@@ -40,5 +43,8 @@ func (t *discoveryTrigger) Enqueue(userID string) {
|
||||
if _, err := t.run(t.ctx, userID); err != nil {
|
||||
t.log.Warn("discovery: connect-triggered pass had errors", "user", userID, "err", err)
|
||||
}
|
||||
if t.onboard != nil {
|
||||
t.onboard(t.ctx, userID)
|
||||
}
|
||||
}()
|
||||
}
|
||||
|
||||
+30
-3
@@ -210,7 +210,10 @@ func cmdServe(ctx context.Context, log *slog.Logger) error {
|
||||
ClientSecret: cfg.YTClientSecret,
|
||||
RedirectURL: cfg.YTConnectRedirectURL,
|
||||
}, secretStore, st, log)
|
||||
log.Info("web youtube connect enabled", "redirect", cfg.YTConnectRedirectURL)
|
||||
// Paste-a-URL (Feature 2): same YouTube credentials, per-user adapter built
|
||||
// per request. Mounting the /paste route keys off app.Fetcher being set.
|
||||
app.Fetcher = videoFetcher{cfg: cfg, secrets: secretStore}
|
||||
log.Info("web youtube connect + paste enabled", "redirect", cfg.YTConnectRedirectURL)
|
||||
}
|
||||
|
||||
// Immediate summarization for the web "Summarize" button. When the engine can
|
||||
@@ -249,9 +252,33 @@ func cmdServe(ctx context.Context, log *slog.Logger) error {
|
||||
// One lock shared by the scheduler and connect-triggered passes (#6) so
|
||||
// they never fetch concurrently — the single-fetcher invariant (ADR-018).
|
||||
runUser := serialize(&sync.Mutex{}, rawRunUser)
|
||||
// Onboarding burst (Feature 1): after the connect-triggered discovery pass,
|
||||
// summarize up to OnboardSummarizeCount of the user's NEWEST unsummarized
|
||||
// videos so a fresh account gets real summaries in its first session. Hard
|
||||
// cap; explicit, so it bypasses the recency window — but every fetch still
|
||||
// goes through globalFetchGate via the Processor. No-op when disabled
|
||||
// (count 0) or queue-only (no Processor).
|
||||
onboard := func(ctx context.Context, userID string) {
|
||||
if cfg.OnboardSummarizeCount <= 0 || app.Processor == nil {
|
||||
return
|
||||
}
|
||||
ids, err := st.NewestUnsummarizedVideoIDs(ctx, userID, cfg.OnboardSummarizeCount)
|
||||
if err != nil {
|
||||
log.Warn("onboarding: list newest unsummarized", "user", userID, "err", err)
|
||||
return
|
||||
}
|
||||
for _, id := range ids {
|
||||
if err := app.Processor.ProcessVideo(ctx, userID, id); err != nil {
|
||||
log.Warn("onboarding: summarize", "user", userID, "video", id, "err", err)
|
||||
}
|
||||
}
|
||||
if len(ids) > 0 {
|
||||
log.Info("onboarding burst complete", "user", userID, "summarized", len(ids), "cap", cfg.OnboardSummarizeCount)
|
||||
}
|
||||
}
|
||||
if app.Connect != nil {
|
||||
app.Connect.Discovery = &discoveryTrigger{ctx: ctx, run: runUser, log: log}
|
||||
log.Info("connect-triggered discovery enabled")
|
||||
app.Connect.Discovery = &discoveryTrigger{ctx: ctx, run: runUser, onboard: onboard, log: log}
|
||||
log.Info("connect-triggered discovery enabled", "onboard_cap", cfg.OnboardSummarizeCount)
|
||||
}
|
||||
go runScheduler(ctx, cfg.DiscoveryInterval, st, runUser, log)
|
||||
} else {
|
||||
|
||||
@@ -11,9 +11,29 @@ import (
|
||||
"gitea.d-ma.be/mathias/tapir/internal/adapters/youtube"
|
||||
"gitea.d-ma.be/mathias/tapir/internal/config"
|
||||
"gitea.d-ma.be/mathias/tapir/internal/domain"
|
||||
"gitea.d-ma.be/mathias/tapir/internal/ports"
|
||||
"gitea.d-ma.be/mathias/tapir/internal/usecase"
|
||||
"gitea.d-ma.be/mathias/tapir/internal/web"
|
||||
)
|
||||
|
||||
// videoFetcher adapts the YouTube adapter to web.VideoFetcher for the paste flow
|
||||
// (Feature 2). It builds a per-user adapter bound to that user's token ref and
|
||||
// resolves a single video's metadata via the Data API — ungated; only the later
|
||||
// transcript fetch goes through globalFetchGate.
|
||||
type videoFetcher struct {
|
||||
cfg config.Config
|
||||
secrets ports.SecretStore
|
||||
}
|
||||
|
||||
func (f videoFetcher) FetchVideo(ctx context.Context, userID, videoID string) (domain.Video, error) {
|
||||
a := youtube.New(youtube.Config{
|
||||
ClientID: f.cfg.YTClientID,
|
||||
ClientSecret: f.cfg.YTClientSecret,
|
||||
TokenSecretRef: web.YouTubeTokenRef(userID),
|
||||
}, f.secrets)
|
||||
return a.VideoByID(ctx, userID, videoID)
|
||||
}
|
||||
|
||||
// buildProcessor wires the summarization engine — YouTube source (captions-first),
|
||||
// AI-router summarizer, store sink — shared by `tapir run` and the web
|
||||
// "Summarize now" path so the wiring lives in one place. It returns (nil, nil) —
|
||||
|
||||
@@ -24,6 +24,12 @@ Feature: Connect and manage video accounts
|
||||
Then a discovery pass for my account is triggered right away
|
||||
And I do not have to wait for the next scheduled pass to see my videos
|
||||
|
||||
Scenario: Connecting summarizes my newest videos right away
|
||||
Given I have no connected video accounts
|
||||
When I connect my YouTube account
|
||||
Then up to the onboarding cap of my newest videos are summarized through the rate gate
|
||||
And the rest are left to the scheduled recency-bounded pass
|
||||
|
||||
Scenario: Tokens are never stored in the clear
|
||||
When I connect any video account
|
||||
Then no OAuth token value is stored in the database
|
||||
|
||||
@@ -0,0 +1,30 @@
|
||||
Feature: Paste a YouTube URL to summarize any video
|
||||
As a user
|
||||
I want to paste a YouTube link and get a summary
|
||||
So that I can pull the specific video I want now, even from channels I don't follow
|
||||
|
||||
Scenario: Paste a valid YouTube URL
|
||||
Given I am connected
|
||||
When I paste a valid YouTube video URL
|
||||
Then the video is added to my feed scoped to me
|
||||
And it is queued for summarization through the shared rate gate
|
||||
|
||||
Scenario: Pasting an invalid link is rejected
|
||||
When I paste something that is not a YouTube video URL
|
||||
Then I get a clear error and nothing is added
|
||||
|
||||
Scenario: Pasting a video that cannot be found is honest
|
||||
When I paste a URL whose video cannot be found
|
||||
Then I am told it couldn't be found and nothing is added
|
||||
|
||||
Scenario: Pasting the same video twice does not duplicate it
|
||||
Given I have pasted a video
|
||||
When I paste the same video again
|
||||
Then my feed still has exactly one entry for it
|
||||
|
||||
@pending
|
||||
# Covered by the engine's ADR-010 no-transcript terminal state (degrade-never-error);
|
||||
# there is no paste-specific test for it.
|
||||
Scenario: A pasted video with no captions resolves honestly
|
||||
When I paste a video that has no captions
|
||||
Then it resolves to the "no transcript available" terminal state
|
||||
@@ -53,7 +53,9 @@ func TestMigration010LoginEventsUpDown(t *testing.T) {
|
||||
require.True(t, loginEventsExists(t), "login_events must exist at latest migration")
|
||||
|
||||
m := fileMigrator(t)
|
||||
// 011, 012, 013 sit above 010; step them down first so 010 is exercised in isolation.
|
||||
// 011, 012, 013, 014 sit above 010; step them down first so 010 is exercised in isolation.
|
||||
require.NoError(t, m.Steps(-1), "down 014 drops channel_title, login_events intact")
|
||||
require.True(t, loginEventsExists(t), "014 down leaves login_events intact")
|
||||
require.NoError(t, m.Steps(-1), "down 013 drops channel_errors, login_events intact")
|
||||
require.True(t, loginEventsExists(t), "013 down leaves login_events intact")
|
||||
require.NoError(t, m.Steps(-1), "down 012 is a no-op, login_events intact")
|
||||
@@ -64,7 +66,7 @@ func TestMigration010LoginEventsUpDown(t *testing.T) {
|
||||
require.NoError(t, m.Steps(-1), "down 010 must drop login_events")
|
||||
require.False(t, loginEventsExists(t), "login_events must be gone after the down migration")
|
||||
|
||||
require.NoError(t, m.Steps(4), "up must recreate 010 then re-apply 011, 012, 013")
|
||||
require.NoError(t, m.Steps(5), "up must recreate 010 then re-apply 011, 012, 013, 014")
|
||||
require.True(t, loginEventsExists(t), "login_events must be restored after the up migration")
|
||||
}
|
||||
|
||||
@@ -87,6 +89,7 @@ func TestMigration011AutoSummarizeDefaultUpDown(t *testing.T) {
|
||||
require.Equal(t, "true", autoSummarizeDefault(t), "011 sets the default to TRUE")
|
||||
|
||||
m := fileMigrator(t)
|
||||
require.NoError(t, m.Steps(-1), "down 014 drops channel_title")
|
||||
require.NoError(t, m.Steps(-1), "down 013 drops channel_errors")
|
||||
require.NoError(t, m.Steps(-1), "down 012 is a no-op")
|
||||
require.NoError(t, m.Steps(-1), "down 011 reverts the column default")
|
||||
@@ -96,6 +99,31 @@ func TestMigration011AutoSummarizeDefaultUpDown(t *testing.T) {
|
||||
require.Equal(t, "true", autoSummarizeDefault(t))
|
||||
require.NoError(t, m.Steps(1), "up 012 runs clean (no FORCE RLS on fresh schema)")
|
||||
require.NoError(t, m.Steps(1), "up 013 creates channel_errors")
|
||||
require.NoError(t, m.Steps(1), "up 014 recreates channel_title")
|
||||
}
|
||||
|
||||
// channelTitleExists reports whether videos.channel_title is present.
|
||||
func channelTitleExists(t *testing.T) bool {
|
||||
t.Helper()
|
||||
var exists bool
|
||||
require.NoError(t, rawPool(t).QueryRow(context.Background(),
|
||||
`SELECT EXISTS (SELECT 1 FROM information_schema.columns
|
||||
WHERE table_name = 'videos' AND column_name = 'channel_title')`).Scan(&exists))
|
||||
return exists
|
||||
}
|
||||
|
||||
// TestMigration014VideoChannelTitleUpDown proves 014 is reversible: down drops
|
||||
// videos.channel_title, up recreates it.
|
||||
func TestMigration014VideoChannelTitleUpDown(t *testing.T) {
|
||||
newStore(t) // latest (014 applied)
|
||||
require.True(t, channelTitleExists(t), "channel_title exists at latest migration")
|
||||
|
||||
m := fileMigrator(t)
|
||||
require.NoError(t, m.Steps(-1), "down 014 must drop channel_title")
|
||||
require.False(t, channelTitleExists(t), "channel_title must be gone after the down migration")
|
||||
|
||||
require.NoError(t, m.Steps(1), "up 014 must recreate channel_title")
|
||||
require.True(t, channelTitleExists(t), "channel_title must be restored after the up migration")
|
||||
}
|
||||
|
||||
// TestMigration012FixAutoSummarizeRLS proves 012 runs cleanly and flips any
|
||||
|
||||
@@ -0,0 +1 @@
|
||||
ALTER TABLE videos DROP COLUMN channel_title;
|
||||
@@ -0,0 +1,8 @@
|
||||
-- Store the source channel's title per video so the list can offer a real
|
||||
-- channel filter (multi-select of the user's channels) instead of the dead
|
||||
-- free-text field that only ever matched the provider string. Nullable: existing
|
||||
-- rows backfill on the next discovery pass (UpsertVideo writes it); pasted videos
|
||||
-- get it immediately from videos.list. No FK to a channels table at Stage 0 — the
|
||||
-- title is a denormalised display/filter value, consistent with the existing
|
||||
-- subscription_id-stays-NULL stance (data-model.md).
|
||||
ALTER TABLE videos ADD COLUMN channel_title TEXT;
|
||||
@@ -29,6 +29,7 @@ type SummaryRow struct {
|
||||
ProviderVideoID string // videos.provider_video_id; empty when no videos row
|
||||
Title string // videos.title; empty when no videos row
|
||||
Channel string // videos.provider for now; empty when no videos row
|
||||
ChannelTitle string // videos.channel_title; the source channel, for display + filtering
|
||||
URL string // videos.url; empty when no videos row
|
||||
PublishedAt time.Time // videos.published_at; zero when absent
|
||||
Summary string
|
||||
@@ -137,7 +138,8 @@ const selectVideo = `
|
||||
COALESCE(s.created_at, v.seen_at),
|
||||
(s.id IS NOT NULL) AS summarized,
|
||||
v.summarize_requested,
|
||||
COALESCE(v.transcript_status, '')
|
||||
COALESCE(v.transcript_status, ''),
|
||||
COALESCE(v.channel_title, '')
|
||||
FROM videos v
|
||||
LEFT JOIN summaries s ON s.video_id = v.id AND s.user_id = v.user_id`
|
||||
|
||||
@@ -254,6 +256,7 @@ func scanVideoRow(rows pgx.Row) (SummaryRow, error) {
|
||||
&row.Summarized,
|
||||
&row.SummarizeRequested,
|
||||
&row.TranscriptStatus,
|
||||
&row.ChannelTitle,
|
||||
); err != nil {
|
||||
return SummaryRow{}, fmt.Errorf("store: scan video: %w", err)
|
||||
}
|
||||
|
||||
@@ -46,14 +46,15 @@ func (s *Store) UpsertVideo(ctx context.Context, v domain.Video) (string, error)
|
||||
}
|
||||
|
||||
if err := tx.QueryRow(ctx,
|
||||
`INSERT INTO videos (user_id, provider, provider_video_id, title, url, published_at)
|
||||
VALUES ($1, $2, $3, $4, $5, $6)
|
||||
`INSERT INTO videos (user_id, provider, provider_video_id, title, url, published_at, channel_title)
|
||||
VALUES ($1, $2, $3, $4, $5, $6, $7)
|
||||
ON CONFLICT (user_id, provider, provider_video_id) DO UPDATE SET
|
||||
title = EXCLUDED.title,
|
||||
url = EXCLUDED.url,
|
||||
published_at = EXCLUDED.published_at
|
||||
title = EXCLUDED.title,
|
||||
url = EXCLUDED.url,
|
||||
published_at = EXCLUDED.published_at,
|
||||
channel_title = COALESCE(NULLIF(EXCLUDED.channel_title, ''), videos.channel_title)
|
||||
RETURNING id`,
|
||||
v.UserID, provider, v.ProviderVideoID, v.Title, v.URL, nullTime(v.PublishedAt),
|
||||
v.UserID, provider, v.ProviderVideoID, v.Title, v.URL, nullTime(v.PublishedAt), v.ChannelTitle,
|
||||
).Scan(&id); err != nil {
|
||||
return fmt.Errorf("store: upsert video: %w", err)
|
||||
}
|
||||
@@ -72,3 +73,69 @@ func nullTime(t time.Time) *time.Time {
|
||||
}
|
||||
return &t
|
||||
}
|
||||
|
||||
// NewestUnsummarizedVideoIDs returns up to limit of the user's videos that have
|
||||
// no summary yet, newest first (published_at DESC, NULLS LAST). It caps the
|
||||
// connect-time onboarding burst (Feature 1) at a fixed count: the caller marks
|
||||
// these for summarization through the shared rate gate. RLS-scoped via withUser,
|
||||
// so it only ever sees the requesting user's rows. limit <= 0 returns nil.
|
||||
func (s *Store) NewestUnsummarizedVideoIDs(ctx context.Context, userID string, limit int) ([]string, error) {
|
||||
if limit <= 0 {
|
||||
return nil, nil
|
||||
}
|
||||
var ids []string
|
||||
if err := s.withUser(ctx, userID, func(tx pgx.Tx) error {
|
||||
rows, err := tx.Query(ctx,
|
||||
`SELECT v.id
|
||||
FROM videos v
|
||||
WHERE v.user_id = $1
|
||||
AND NOT EXISTS (
|
||||
SELECT 1 FROM summaries su
|
||||
WHERE su.user_id = v.user_id AND su.video_id = v.id)
|
||||
ORDER BY v.published_at DESC NULLS LAST, v.seen_at DESC
|
||||
LIMIT $2`, userID, limit)
|
||||
if err != nil {
|
||||
return fmt.Errorf("store: newest unsummarized: %w", err)
|
||||
}
|
||||
defer rows.Close()
|
||||
for rows.Next() {
|
||||
var id string
|
||||
if err := rows.Scan(&id); err != nil {
|
||||
return fmt.Errorf("store: scan newest unsummarized: %w", err)
|
||||
}
|
||||
ids = append(ids, id)
|
||||
}
|
||||
return rows.Err()
|
||||
}); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
return ids, nil
|
||||
}
|
||||
|
||||
// DistinctChannels returns the user's distinct, non-empty source channel titles
|
||||
// (the channels they have videos from), alphabetically — the option list for the
|
||||
// feed's channel filter. RLS-scoped via withUser.
|
||||
func (s *Store) DistinctChannels(ctx context.Context, userID string) ([]string, error) {
|
||||
var out []string
|
||||
if err := s.withUser(ctx, userID, func(tx pgx.Tx) error {
|
||||
rows, err := tx.Query(ctx,
|
||||
`SELECT DISTINCT channel_title FROM videos
|
||||
WHERE user_id = $1 AND channel_title IS NOT NULL AND channel_title <> ''
|
||||
ORDER BY channel_title`, userID)
|
||||
if err != nil {
|
||||
return fmt.Errorf("store: distinct channels: %w", err)
|
||||
}
|
||||
defer rows.Close()
|
||||
for rows.Next() {
|
||||
var c string
|
||||
if err := rows.Scan(&c); err != nil {
|
||||
return fmt.Errorf("store: scan channel: %w", err)
|
||||
}
|
||||
out = append(out, c)
|
||||
}
|
||||
return rows.Err()
|
||||
}); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
return out, nil
|
||||
}
|
||||
|
||||
@@ -81,3 +81,61 @@ func TestUpsertVideo_PerUserIsolation(t *testing.T) {
|
||||
|
||||
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 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)")
|
||||
}
|
||||
|
||||
@@ -0,0 +1,62 @@
|
||||
package youtube
|
||||
|
||||
import (
|
||||
"context"
|
||||
"errors"
|
||||
"net/http"
|
||||
"testing"
|
||||
|
||||
"gitea.d-ma.be/mathias/tapir/internal/domain"
|
||||
)
|
||||
|
||||
func TestVideoByID(t *testing.T) {
|
||||
const id = "dQw4w9WgXcQ"
|
||||
a, secrets := newTestAdapter(t, func(w http.ResponseWriter, r *http.Request) {
|
||||
if r.URL.Path != "/videos" {
|
||||
t.Errorf("unexpected path %q (must use videos.list)", r.URL.Path)
|
||||
}
|
||||
if got := r.URL.Query().Get("id"); got != id {
|
||||
t.Errorf("expected id=%s, got %q", id, got)
|
||||
}
|
||||
if got := r.URL.Query().Get("part"); got != "snippet" {
|
||||
t.Errorf("expected part=snippet, got %q", got)
|
||||
}
|
||||
_, _ = w.Write([]byte(`{"items":[{"snippet":{"title":"Never Gonna Give You Up","channelTitle":"Rick Astley","publishedAt":"2026-05-20T09:00:00Z"}}]}`))
|
||||
})
|
||||
|
||||
v, err := a.VideoByID(context.Background(), "u1", id)
|
||||
if err != nil {
|
||||
t.Fatalf("VideoByID: %v", err)
|
||||
}
|
||||
if v.UserID != "u1" {
|
||||
t.Errorf("UserID = %q, want u1", v.UserID)
|
||||
}
|
||||
if v.ProviderVideoID != id || v.Title != "Never Gonna Give You Up" {
|
||||
t.Errorf("unexpected video: %+v", v)
|
||||
}
|
||||
if v.ChannelTitle != "Rick Astley" {
|
||||
t.Errorf("ChannelTitle = %q, want Rick Astley", v.ChannelTitle)
|
||||
}
|
||||
if v.Provider != domain.ProviderYouTube || v.URL != "https://www.youtube.com/watch?v="+id {
|
||||
t.Errorf("video not wired correctly: %+v", v)
|
||||
}
|
||||
if v.PublishedAt.IsZero() {
|
||||
t.Errorf("expected publishedAt parsed, got zero")
|
||||
}
|
||||
if v.SubscriptionID != "" {
|
||||
t.Errorf("a pasted video must have no subscription, got %q", v.SubscriptionID)
|
||||
}
|
||||
if secrets.byRef == nil {
|
||||
t.Errorf("token must be resolved by reference through the SecretStore")
|
||||
}
|
||||
}
|
||||
|
||||
func TestVideoByIDNotFound(t *testing.T) {
|
||||
a, _ := newTestAdapter(t, func(w http.ResponseWriter, _ *http.Request) {
|
||||
_, _ = w.Write([]byte(`{"items":[]}`))
|
||||
})
|
||||
_, err := a.VideoByID(context.Background(), "u1", "missingvid0")
|
||||
if !errors.Is(err, domain.ErrVideoNotFound) {
|
||||
t.Fatalf("VideoByID for missing id = %v, want domain.ErrVideoNotFound", err)
|
||||
}
|
||||
}
|
||||
@@ -234,6 +234,7 @@ func (a *Adapter) NewVideos(ctx context.Context, sub domain.Subscription) ([]dom
|
||||
Provider: domain.ProviderYouTube,
|
||||
ProviderVideoID: vid,
|
||||
Title: item.Snippet.Title,
|
||||
ChannelTitle: sub.ChannelTitle,
|
||||
URL: "https://www.youtube.com/watch?v=" + vid,
|
||||
PublishedAt: item.Snippet.PublishedAt,
|
||||
})
|
||||
@@ -244,6 +245,38 @@ func (a *Adapter) NewVideos(ctx context.Context, sub domain.Subscription) ([]dom
|
||||
return videos, nil
|
||||
}
|
||||
|
||||
// VideoByID fetches a single video's metadata (videos.list, snippet) for an
|
||||
// arbitrary video id — including channels the user does not follow (paste-a-URL,
|
||||
// Feature 2). This is a Data API call (1 quota unit), NOT the rate-limited
|
||||
// caption path, so it is not gated: only the later transcript fetch goes through
|
||||
// globalFetchGate. UserID is set on the result and SubscriptionID is left empty
|
||||
// (a pasted video has no subscription parent). Returns ErrVideoNotFound when the
|
||||
// id resolves to no video.
|
||||
func (a *Adapter) VideoByID(ctx context.Context, userID, videoID string) (domain.Video, error) {
|
||||
client, err := a.httpClient(ctx, a.cfg.TokenSecretRef)
|
||||
if err != nil {
|
||||
return domain.Video{}, err
|
||||
}
|
||||
q := url.Values{"part": {"snippet"}, "id": {videoID}}
|
||||
var resp videoListResponse
|
||||
if err := a.getJSON(ctx, client, "/videos", q, &resp); err != nil {
|
||||
return domain.Video{}, fmt.Errorf("video by id %q: %w", videoID, err)
|
||||
}
|
||||
if len(resp.Items) == 0 {
|
||||
return domain.Video{}, fmt.Errorf("video %q: %w", videoID, domain.ErrVideoNotFound)
|
||||
}
|
||||
it := resp.Items[0]
|
||||
return domain.Video{
|
||||
UserID: userID,
|
||||
Provider: domain.ProviderYouTube,
|
||||
ProviderVideoID: videoID,
|
||||
Title: it.Snippet.Title,
|
||||
ChannelTitle: it.Snippet.ChannelTitle,
|
||||
URL: "https://www.youtube.com/watch?v=" + videoID,
|
||||
PublishedAt: it.Snippet.PublishedAt,
|
||||
}, nil
|
||||
}
|
||||
|
||||
// uploadsPlaylistID derives a channel's uploads playlist id at zero API cost:
|
||||
// a standard channel id "UCxxxx" maps to uploads playlist "UUxxxx". Returns
|
||||
// ok=false for ids that don't follow this convention (caller falls back to
|
||||
@@ -342,6 +375,16 @@ type playlistItemListResponse struct {
|
||||
} `json:"items"`
|
||||
}
|
||||
|
||||
type videoListResponse struct {
|
||||
Items []struct {
|
||||
Snippet struct {
|
||||
Title string `json:"title"`
|
||||
ChannelTitle string `json:"channelTitle"`
|
||||
PublishedAt time.Time `json:"publishedAt"`
|
||||
} `json:"snippet"`
|
||||
} `json:"items"`
|
||||
}
|
||||
|
||||
type channelListResponse struct {
|
||||
Items []struct {
|
||||
ContentDetails struct {
|
||||
|
||||
@@ -131,7 +131,7 @@ func TestNewVideos(t *testing.T) {
|
||||
}`))
|
||||
})
|
||||
|
||||
sub := domain.Subscription{ID: "s1", UserID: "u1", ChannelID: "UC_acme"}
|
||||
sub := domain.Subscription{ID: "s1", UserID: "u1", ChannelID: "UC_acme", ChannelTitle: "Acme Channel"}
|
||||
vids, err := a.NewVideos(context.Background(), sub)
|
||||
if err != nil {
|
||||
t.Fatalf("NewVideos: %v", err)
|
||||
@@ -143,6 +143,9 @@ func TestNewVideos(t *testing.T) {
|
||||
if v.ProviderVideoID != "vid1" || v.Title != "Designing for Attention" {
|
||||
t.Errorf("unexpected video: %+v", v)
|
||||
}
|
||||
if v.ChannelTitle != "Acme Channel" {
|
||||
t.Errorf("ChannelTitle = %q, want Acme Channel", v.ChannelTitle)
|
||||
}
|
||||
if v.Provider != domain.ProviderYouTube || v.URL != "https://www.youtube.com/watch?v=vid1" {
|
||||
t.Errorf("video not wired correctly: %+v", v)
|
||||
}
|
||||
|
||||
+45
-11
@@ -13,6 +13,7 @@ import (
|
||||
"os"
|
||||
"path/filepath"
|
||||
"sort"
|
||||
"strconv"
|
||||
"strings"
|
||||
"time"
|
||||
)
|
||||
@@ -79,6 +80,13 @@ type Config struct {
|
||||
// pre-recency behaviour). Default ~7 days.
|
||||
AutoSummarizeWindow time.Duration
|
||||
|
||||
// OnboardSummarizeCount caps how many of a freshly-connected user's newest
|
||||
// videos are summarized immediately on connect (the onboarding "it works"
|
||||
// burst). HARD-capped at maxOnboardSummarizeCount so onboarding can never
|
||||
// bulk-fetch; 0 disables the burst. Every fetch still flows through the shared
|
||||
// caption rate gate (ADR-014) — the cap bounds count, never the pacing. Default 3.
|
||||
OnboardSummarizeCount int
|
||||
|
||||
// DiscoveryInterval, when > 0, makes `serve` run in-process scheduled discovery
|
||||
// for ALL users on that cadence (ADR-018). Zero/unset = disabled, so dev and
|
||||
// tests never auto-fetch. Single-replica assumption — see cmdServe.
|
||||
@@ -108,17 +116,19 @@ func (c Config) DexConfigured() bool { return strings.TrimSpace(c.OIDCIssuer) !=
|
||||
|
||||
// Defaults (see docs/homelab-integration.md). All overridable via env.
|
||||
const (
|
||||
defaultGatewayURL = "http://koala:30401/v1"
|
||||
defaultSummarizerModel = "koala/phi4-mini"
|
||||
defaultSummarizerTimeout = 5 * time.Minute
|
||||
defaultYTTokenRef = "youtube/refresh_token"
|
||||
defaultYTConnectRedirectURL = "https://tapir.d-ma.be/oauth/youtube/callback"
|
||||
defaultOAuthRedirectAddr = "localhost:8080"
|
||||
defaultHTTPAddr = ":8080"
|
||||
defaultFetchBackoff = time.Hour
|
||||
defaultFetchRate = 2 * time.Second
|
||||
defaultPublicURL = "https://tapir.d-ma.be"
|
||||
defaultAutoSummarizeWindow = 7 * 24 * time.Hour
|
||||
defaultGatewayURL = "http://koala:30401/v1"
|
||||
defaultSummarizerModel = "koala/phi4-mini"
|
||||
defaultSummarizerTimeout = 5 * time.Minute
|
||||
defaultYTTokenRef = "youtube/refresh_token"
|
||||
defaultYTConnectRedirectURL = "https://tapir.d-ma.be/oauth/youtube/callback"
|
||||
defaultOAuthRedirectAddr = "localhost:8080"
|
||||
defaultHTTPAddr = ":8080"
|
||||
defaultFetchBackoff = time.Hour
|
||||
defaultFetchRate = 2 * time.Second
|
||||
defaultPublicURL = "https://tapir.d-ma.be"
|
||||
defaultAutoSummarizeWindow = 7 * 24 * time.Hour
|
||||
defaultOnboardSummarizeCount = 3
|
||||
maxOnboardSummarizeCount = 5
|
||||
)
|
||||
|
||||
// Load reads the environment into a Config, applying defaults. It does not
|
||||
@@ -183,6 +193,18 @@ func Load() (Config, error) {
|
||||
}
|
||||
c.AutoSummarizeWindow = autoWindow
|
||||
|
||||
onboard, err := intOr("TAPIR_ONBOARD_SUMMARIZE_COUNT", defaultOnboardSummarizeCount)
|
||||
if err != nil {
|
||||
return Config{}, err
|
||||
}
|
||||
if onboard < 0 {
|
||||
onboard = 0
|
||||
}
|
||||
if onboard > maxOnboardSummarizeCount {
|
||||
onboard = maxOnboardSummarizeCount
|
||||
}
|
||||
c.OnboardSummarizeCount = onboard
|
||||
|
||||
return c, nil
|
||||
}
|
||||
|
||||
@@ -247,6 +269,18 @@ func envOr(key, fallback string) string {
|
||||
return fallback
|
||||
}
|
||||
|
||||
func intOr(key string, fallback int) (int, error) {
|
||||
v := os.Getenv(key)
|
||||
if v == "" {
|
||||
return fallback, nil
|
||||
}
|
||||
n, err := strconv.Atoi(v)
|
||||
if err != nil {
|
||||
return 0, fmt.Errorf("config: %s=%q: %w", key, v, err)
|
||||
}
|
||||
return n, nil
|
||||
}
|
||||
|
||||
func durationOr(key string, fallback time.Duration) (time.Duration, error) {
|
||||
v := os.Getenv(key)
|
||||
if v == "" {
|
||||
|
||||
@@ -53,6 +53,38 @@ func TestLoad_AppliesDefaults(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
func TestLoad_OnboardSummarizeCount(t *testing.T) {
|
||||
cases := []struct {
|
||||
name, env string
|
||||
want int
|
||||
}{
|
||||
{"default", "", defaultOnboardSummarizeCount},
|
||||
{"explicit", "4", 4},
|
||||
{"zero disables", "0", 0},
|
||||
{"clamped to hard cap", "50", maxOnboardSummarizeCount},
|
||||
{"negative clamps to zero", "-3", 0},
|
||||
}
|
||||
for _, c := range cases {
|
||||
t.Run(c.name, func(t *testing.T) {
|
||||
setEnv(t, map[string]string{"TAPIR_ONBOARD_SUMMARIZE_COUNT": c.env})
|
||||
cfg, err := Load()
|
||||
if err != nil {
|
||||
t.Fatalf("Load: %v", err)
|
||||
}
|
||||
if cfg.OnboardSummarizeCount != c.want {
|
||||
t.Fatalf("OnboardSummarizeCount = %d, want %d", cfg.OnboardSummarizeCount, c.want)
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
func TestLoad_OnboardSummarizeCountInvalid(t *testing.T) {
|
||||
setEnv(t, map[string]string{"TAPIR_ONBOARD_SUMMARIZE_COUNT": "three"})
|
||||
if _, err := Load(); err == nil {
|
||||
t.Fatal("Load: want error for non-numeric TAPIR_ONBOARD_SUMMARIZE_COUNT")
|
||||
}
|
||||
}
|
||||
|
||||
func TestLoad_ParsesValues(t *testing.T) {
|
||||
setEnv(t, map[string]string{
|
||||
"TAPIR_USER_ID": "11111111-1111-1111-1111-111111111111",
|
||||
|
||||
@@ -3,10 +3,16 @@
|
||||
package domain
|
||||
|
||||
import (
|
||||
"errors"
|
||||
"fmt"
|
||||
"time"
|
||||
)
|
||||
|
||||
// ErrVideoNotFound is returned when a video id resolves to no video (deleted,
|
||||
// private, or a typo'd paste). Defined in domain so adapters and the web layer
|
||||
// share one sentinel without coupling to each other.
|
||||
var ErrVideoNotFound = errors.New("video not found")
|
||||
|
||||
// ErrChannelUnavailable is returned by a VideoSource when a channel's upload
|
||||
// playlist returns HTTP 404 — the channel was deleted or made private. The runner
|
||||
// stores these so the account page can surface them to the user.
|
||||
@@ -67,6 +73,7 @@ type Video struct {
|
||||
Provider Provider
|
||||
ProviderVideoID string
|
||||
Title string
|
||||
ChannelTitle string
|
||||
URL string
|
||||
PublishedAt time.Time
|
||||
SeenAt time.Time
|
||||
|
||||
+104
-14
@@ -3,6 +3,8 @@ package web
|
||||
import (
|
||||
"context"
|
||||
"errors"
|
||||
"html/template"
|
||||
"io"
|
||||
"log/slog"
|
||||
"net/http"
|
||||
"time"
|
||||
@@ -10,6 +12,7 @@ import (
|
||||
"github.com/a-h/templ"
|
||||
|
||||
"gitea.d-ma.be/mathias/tapir/internal/adapters/store"
|
||||
"gitea.d-ma.be/mathias/tapir/internal/domain"
|
||||
)
|
||||
|
||||
// Store is the read/write surface the web handlers depend on — a narrow port over
|
||||
@@ -18,6 +21,9 @@ import (
|
||||
// fake without a database.
|
||||
type Store interface {
|
||||
ListVideos(ctx context.Context, userID string, limit int) ([]store.SummaryRow, error)
|
||||
// DistinctChannels lists the user's source channels — the options for the
|
||||
// feed's channel multi-select filter.
|
||||
DistinctChannels(ctx context.Context, userID string) ([]string, error)
|
||||
GetSummaryByVideo(ctx context.Context, userID, videoID string) (*store.SummaryRow, error)
|
||||
GetVideoRow(ctx context.Context, userID, videoID string) (*store.SummaryRow, error)
|
||||
ActionsFor(ctx context.Context, userID string, videoIDs []string) (map[string][]string, error)
|
||||
@@ -30,6 +36,10 @@ type Store interface {
|
||||
SetAutoSummarize(ctx context.Context, userID string, enabled bool) error
|
||||
RequestSummarize(ctx context.Context, userID, videoID string) error
|
||||
|
||||
// UpsertVideo persists a pasted video (idempotent on user+provider+video id,
|
||||
// so it also dedups) and returns its durable store id.
|
||||
UpsertVideo(ctx context.Context, v domain.Video) (string, error)
|
||||
|
||||
// Account management (the /account page, disconnect, delete-account).
|
||||
ConnectionsForUser(ctx context.Context, userID string) ([]store.Connection, error)
|
||||
DeleteConnection(ctx context.Context, userID, provider string) error
|
||||
@@ -78,6 +88,9 @@ type App struct {
|
||||
// background goroutine (the "Summarize" button kicks it off). Nil = queue-only:
|
||||
// the button flips the DB flag and the next `tapir run` does the work.
|
||||
Processor Processor
|
||||
// Fetcher, when non-nil, resolves an arbitrary YouTube video id to metadata for
|
||||
// the paste-a-URL flow (Feature 2). Nil = the /paste route is not mounted.
|
||||
Fetcher VideoFetcher
|
||||
// Processing tracks in-flight immediate summarizations so the status endpoint
|
||||
// shows the animation until the summary lands. The zero value is ready to use.
|
||||
Processing ProcessingSet
|
||||
@@ -132,6 +145,9 @@ func (a *App) Router() http.Handler {
|
||||
app.HandleFunc("POST /v/{videoId}/action", a.handleAction)
|
||||
app.HandleFunc("POST /v/{videoId}/summarize", a.handleRequestSummarize)
|
||||
app.HandleFunc("POST /v/{videoId}/retry-now", a.handleRetryNow)
|
||||
if a.Fetcher != nil {
|
||||
app.HandleFunc("POST /paste", a.handlePaste)
|
||||
}
|
||||
app.HandleFunc("GET /v/{videoId}/status", a.handleStatus)
|
||||
app.HandleFunc("GET /register", a.handleRegisterForm)
|
||||
app.HandleFunc("POST /register", a.handleRegister)
|
||||
@@ -183,7 +199,7 @@ func (a *App) handleList(w http.ResponseWriter, r *http.Request) {
|
||||
}
|
||||
q := r.URL.Query()
|
||||
f := Filter{
|
||||
Channel: q.Get("channel"),
|
||||
Channels: nonEmptyStrings(q["channel"]),
|
||||
From: q.Get("from"),
|
||||
To: q.Get("to"),
|
||||
OnlySummarized: q.Get("summarized") == "1",
|
||||
@@ -198,25 +214,30 @@ func (a *App) handleList(w http.ResponseWriter, r *http.Request) {
|
||||
rows := f.apply(allRows)
|
||||
buckets := bucketRows(rows, a.recencyCutoff())
|
||||
|
||||
// hasConnected drives the empty state: a fresh account with a connection but
|
||||
// no discovery pass yet has zero rows, and we want it to read "connected,
|
||||
// summaries land gradually" rather than "nothing here". Only needed when the
|
||||
// list is empty.
|
||||
hasConnected := false
|
||||
if buckets.empty() {
|
||||
conns, err := a.Store.ConnectionsForUser(r.Context(), userID)
|
||||
if err != nil {
|
||||
a.serverError(w, r, "connections for user", err)
|
||||
return
|
||||
}
|
||||
hasConnected = len(conns) > 0
|
||||
// Channel options for the multi-select filter (the user's source channels).
|
||||
channels, err := a.Store.DistinctChannels(r.Context(), userID)
|
||||
if err != nil {
|
||||
a.serverError(w, r, "distinct channels", err)
|
||||
return
|
||||
}
|
||||
|
||||
// hasConnected drives both the paste box (shown to ANY connected user, #2) and
|
||||
// the empty-state copy (a fresh account with a connection but no discovery pass
|
||||
// yet reads "connected, summaries land gradually" rather than "nothing here").
|
||||
// Computed every render — not only when empty — so a user with videos still
|
||||
// gets the paste box.
|
||||
conns, err := a.Store.ConnectionsForUser(r.Context(), userID)
|
||||
if err != nil {
|
||||
a.serverError(w, r, "connections for user", err)
|
||||
return
|
||||
}
|
||||
hasConnected := len(conns) > 0
|
||||
|
||||
if isHTMX(r) {
|
||||
a.render(w, r, summaryList(buckets, hasConnected))
|
||||
return
|
||||
}
|
||||
a.render(w, r, ListPage(buckets, f, stats, takeFlash(w, r), hasConnected))
|
||||
a.render(w, r, ListPage(buckets, f, stats, takeFlash(w, r), hasConnected, channels))
|
||||
}
|
||||
|
||||
// handleDetail renders one summary in full (highlights, takeaways, action group).
|
||||
@@ -324,6 +345,75 @@ func (a *App) handleRequestSummarize(w http.ResponseWriter, r *http.Request) {
|
||||
a.render(w, r, VideoCard(*row))
|
||||
}
|
||||
|
||||
// handlePaste handles "paste a YouTube URL" (Feature 2). It parses the video id,
|
||||
// fetches metadata (Data API — ungated), upserts a subscription-less video row
|
||||
// scoped to the user (idempotent, so it also dedups), and — if the video isn't
|
||||
// already summarized — requests a summary and kicks off immediate processing
|
||||
// through the SAME rate gate as the Summarize button. An explicit paste is a
|
||||
// manual request, so it summarizes regardless of the recency window. A video that
|
||||
// turns out to have no captions resolves to the honest "no transcript" terminal
|
||||
// state via the engine (ADR-010), not an error here.
|
||||
func (a *App) handlePaste(w http.ResponseWriter, r *http.Request) {
|
||||
userID, ok := a.currentUserID(w, r)
|
||||
if !ok {
|
||||
return
|
||||
}
|
||||
videoID, err := parseYouTubeVideoID(r.FormValue("url"))
|
||||
if err != nil {
|
||||
a.pasteFailure(w, http.StatusBadRequest, "That doesn't look like a YouTube video link.")
|
||||
return
|
||||
}
|
||||
|
||||
v, err := a.Fetcher.FetchVideo(r.Context(), userID, videoID)
|
||||
if errors.Is(err, domain.ErrVideoNotFound) {
|
||||
a.pasteFailure(w, http.StatusNotFound, "That video couldn't be found — it may be private or removed.")
|
||||
return
|
||||
}
|
||||
if err != nil {
|
||||
a.serverError(w, r, "paste fetch", err)
|
||||
return
|
||||
}
|
||||
|
||||
id, err := a.Store.UpsertVideo(r.Context(), v)
|
||||
if err != nil {
|
||||
a.serverError(w, r, "paste upsert", err)
|
||||
return
|
||||
}
|
||||
row, err := a.Store.GetVideoRow(r.Context(), userID, id)
|
||||
if err != nil {
|
||||
a.serverError(w, r, "paste get video", err)
|
||||
return
|
||||
}
|
||||
|
||||
// Dedup: already in the feed with a summary — surface the existing entry,
|
||||
// don't re-summarize.
|
||||
if row.Summarized {
|
||||
a.render(w, r, VideoCard(*row))
|
||||
return
|
||||
}
|
||||
|
||||
// New or unsummarized: queue + (if a Processor is wired) summarize now, through
|
||||
// the shared gate. RequestSummarize makes it durable even if the process dies.
|
||||
if err := a.Store.RequestSummarize(r.Context(), userID, id); err != nil {
|
||||
a.serverError(w, r, "paste request summarize", err)
|
||||
return
|
||||
}
|
||||
if a.Processor != nil {
|
||||
a.startProcessing(userID, id)
|
||||
a.render(w, r, processingCard(*row))
|
||||
return
|
||||
}
|
||||
a.render(w, r, VideoCard(*row))
|
||||
}
|
||||
|
||||
// pasteFailure renders a minimal inline error fragment for the paste form (HTMX
|
||||
// swaps it in). No templ dependency so it renders even on a bad-input fast path.
|
||||
func (a *App) pasteFailure(w http.ResponseWriter, status int, msg string) {
|
||||
w.Header().Set("Content-Type", "text/html; charset=utf-8")
|
||||
w.WriteHeader(status)
|
||||
_, _ = io.WriteString(w, `<p class="paste-error" role="alert">`+template.HTMLEscapeString(msg)+`</p>`)
|
||||
}
|
||||
|
||||
// handleRetryNow handles the "Try now" button on rate-limited video cards. It
|
||||
// clears the rate_limited_at backoff so the scheduler won't skip the video, then
|
||||
// triggers an immediate ProcessVideo — same background path as handleRequestSummarize.
|
||||
|
||||
@@ -207,13 +207,15 @@ func TestListChannelFilter(t *testing.T) {
|
||||
resetDB(t, p)
|
||||
require.NoError(t, deliver(ctx, app, videoX, "body x"))
|
||||
seedVideo(t, p, videoX, "X Title", "https://x", time.Time{})
|
||||
_, err := p.Exec(ctx, `UPDATE videos SET channel_title = 'Acme Channel' WHERE id = $1`, videoX)
|
||||
require.NoError(t, err)
|
||||
|
||||
// Channel is "youtube" for seeded rows; a non-matching filter hides them.
|
||||
rec := do(t, app, httptest.NewRequest(http.MethodGet, "/?channel=vimeo", nil))
|
||||
// Selecting a different channel hides the row; selecting its channel shows it.
|
||||
rec := do(t, app, httptest.NewRequest(http.MethodGet, "/?channel=Other+Channel", nil))
|
||||
require.Equal(t, http.StatusOK, rec.Code)
|
||||
require.NotContains(t, body(t, rec), "X Title")
|
||||
|
||||
rec = do(t, app, httptest.NewRequest(http.MethodGet, "/?channel=youtube", nil))
|
||||
rec = do(t, app, httptest.NewRequest(http.MethodGet, "/?channel=Acme+Channel", nil))
|
||||
require.Contains(t, body(t, rec), "X Title")
|
||||
}
|
||||
|
||||
|
||||
@@ -0,0 +1,62 @@
|
||||
package web
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"net/url"
|
||||
"regexp"
|
||||
"strings"
|
||||
)
|
||||
|
||||
// youtubeVideoID matches a canonical YouTube video id: exactly 11 URL-safe chars.
|
||||
var youtubeVideoID = regexp.MustCompile(`^[A-Za-z0-9_-]{11}$`)
|
||||
|
||||
// parseYouTubeVideoID extracts the 11-character video id from a pasted YouTube
|
||||
// URL (watch?v=, youtu.be/, shorts/, embed/) or a bare id. It rejects non-YouTube
|
||||
// hosts and anything that doesn't yield a valid id, so the paste flow never tries
|
||||
// to fetch a video that can't exist (Feature 2).
|
||||
func parseYouTubeVideoID(raw string) (string, error) {
|
||||
s := strings.TrimSpace(raw)
|
||||
if s == "" {
|
||||
return "", fmt.Errorf("empty input")
|
||||
}
|
||||
|
||||
// Bare id (no URL) — accept directly.
|
||||
if youtubeVideoID.MatchString(s) {
|
||||
return s, nil
|
||||
}
|
||||
|
||||
// Accept scheme-less URLs (youtube.com/watch?v=...) by giving url.Parse a host.
|
||||
if !strings.Contains(s, "://") {
|
||||
s = "https://" + s
|
||||
}
|
||||
u, err := url.Parse(s)
|
||||
if err != nil {
|
||||
return "", fmt.Errorf("not a URL: %w", err)
|
||||
}
|
||||
|
||||
host := strings.ToLower(u.Hostname())
|
||||
isYouTube := host == "youtu.be" || host == "youtube.com" || strings.HasSuffix(host, ".youtube.com")
|
||||
if !isYouTube {
|
||||
return "", fmt.Errorf("not a YouTube URL: %q", host)
|
||||
}
|
||||
|
||||
var id string
|
||||
switch {
|
||||
case host == "youtu.be":
|
||||
// youtu.be/<id>
|
||||
id = strings.Trim(u.Path, "/")
|
||||
case u.Path == "/watch":
|
||||
id = u.Query().Get("v")
|
||||
default:
|
||||
// /shorts/<id>, /embed/<id>
|
||||
parts := strings.Split(strings.Trim(u.Path, "/"), "/")
|
||||
if len(parts) == 2 && (parts[0] == "shorts" || parts[0] == "embed") {
|
||||
id = parts[1]
|
||||
}
|
||||
}
|
||||
|
||||
if !youtubeVideoID.MatchString(id) {
|
||||
return "", fmt.Errorf("no YouTube video id in %q", raw)
|
||||
}
|
||||
return id, nil
|
||||
}
|
||||
@@ -0,0 +1,134 @@
|
||||
package web_test
|
||||
|
||||
import (
|
||||
"context"
|
||||
"net/http"
|
||||
"net/http/httptest"
|
||||
"net/url"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/stretchr/testify/require"
|
||||
|
||||
"gitea.d-ma.be/mathias/tapir/internal/domain"
|
||||
)
|
||||
|
||||
// fakeFetcher is a web.VideoFetcher returning a fixed video (or an error),
|
||||
// scoped to whatever (userID, videoID) the handler asks for.
|
||||
type fakeFetcher struct {
|
||||
title string
|
||||
err error
|
||||
calls int
|
||||
}
|
||||
|
||||
func (f *fakeFetcher) FetchVideo(_ context.Context, userID, videoID string) (domain.Video, error) {
|
||||
f.calls++
|
||||
if f.err != nil {
|
||||
return domain.Video{}, f.err
|
||||
}
|
||||
return domain.Video{
|
||||
UserID: userID,
|
||||
Provider: domain.ProviderYouTube,
|
||||
ProviderVideoID: videoID,
|
||||
Title: f.title,
|
||||
URL: "https://www.youtube.com/watch?v=" + videoID,
|
||||
}, nil
|
||||
}
|
||||
|
||||
func pasteReq(rawURL string) *http.Request {
|
||||
req := httptest.NewRequest(http.MethodPost, "/paste",
|
||||
strings.NewReader("url="+url.QueryEscape(rawURL)))
|
||||
req.Header.Set("Content-Type", "application/x-www-form-urlencoded")
|
||||
return req
|
||||
}
|
||||
|
||||
func TestPasteValidURLAddsAndRequests(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
app := newApp(t)
|
||||
resetDB(t, rawPool(t))
|
||||
app.Fetcher = &fakeFetcher{title: "Pasted Talk"}
|
||||
p := rawPool(t)
|
||||
|
||||
rec := do(t, app, pasteReq("https://youtu.be/dQw4w9WgXcQ"))
|
||||
require.Equal(t, http.StatusOK, rec.Code)
|
||||
|
||||
var (
|
||||
count, requested int
|
||||
title string
|
||||
)
|
||||
require.NoError(t, p.QueryRow(ctx,
|
||||
`SELECT count(*), coalesce(max(title),'') FROM videos
|
||||
WHERE user_id=$1 AND provider_video_id='dQw4w9WgXcQ'`, userID).Scan(&count, &title))
|
||||
require.Equal(t, 1, count, "pasted video added once, scoped to the user")
|
||||
require.Equal(t, "Pasted Talk", title)
|
||||
|
||||
require.NoError(t, p.QueryRow(ctx,
|
||||
`SELECT count(*) FROM videos
|
||||
WHERE user_id=$1 AND provider_video_id='dQw4w9WgXcQ' AND summarize_requested`,
|
||||
userID).Scan(&requested))
|
||||
require.Equal(t, 1, requested, "pasted video is queued for summarization (through the gate)")
|
||||
}
|
||||
|
||||
func TestPasteInvalidURLRejected(t *testing.T) {
|
||||
app := newApp(t)
|
||||
resetDB(t, rawPool(t))
|
||||
app.Fetcher = &fakeFetcher{title: "x"}
|
||||
|
||||
rec := do(t, app, pasteReq("definitely not a url"))
|
||||
require.Equal(t, http.StatusBadRequest, rec.Code)
|
||||
|
||||
var count int
|
||||
require.NoError(t, rawPool(t).QueryRow(context.Background(),
|
||||
`SELECT count(*) FROM videos WHERE user_id=$1`, userID).Scan(&count))
|
||||
require.Equal(t, 0, count, "invalid input adds nothing")
|
||||
}
|
||||
|
||||
func TestPasteVideoNotFound(t *testing.T) {
|
||||
app := newApp(t)
|
||||
resetDB(t, rawPool(t))
|
||||
app.Fetcher = &fakeFetcher{err: domain.ErrVideoNotFound}
|
||||
|
||||
rec := do(t, app, pasteReq("https://youtu.be/dQw4w9WgXcQ"))
|
||||
require.Equal(t, http.StatusNotFound, rec.Code)
|
||||
|
||||
var count int
|
||||
require.NoError(t, rawPool(t).QueryRow(context.Background(),
|
||||
`SELECT count(*) FROM videos WHERE user_id=$1`, userID).Scan(&count))
|
||||
require.Equal(t, 0, count, "a not-found video adds nothing")
|
||||
}
|
||||
|
||||
func TestPasteDedupNoDuplicate(t *testing.T) {
|
||||
app := newApp(t)
|
||||
resetDB(t, rawPool(t))
|
||||
app.Fetcher = &fakeFetcher{title: "Pasted Talk"}
|
||||
|
||||
require.Equal(t, http.StatusOK, do(t, app, pasteReq("https://youtu.be/dQw4w9WgXcQ")).Code)
|
||||
require.Equal(t, http.StatusOK, do(t, app, pasteReq("https://www.youtube.com/watch?v=dQw4w9WgXcQ")).Code)
|
||||
|
||||
var count int
|
||||
require.NoError(t, rawPool(t).QueryRow(context.Background(),
|
||||
`SELECT count(*) FROM videos WHERE user_id=$1 AND provider_video_id='dQw4w9WgXcQ'`,
|
||||
userID).Scan(&count))
|
||||
require.Equal(t, 1, count, "pasting the same video twice must not duplicate the row")
|
||||
}
|
||||
|
||||
func TestListShowsPasteFormForConnectedUserWithVideos(t *testing.T) {
|
||||
app := newApp(t)
|
||||
resetDB(t, rawPool(t))
|
||||
app.Fetcher = &fakeFetcher{title: "x"}
|
||||
p := rawPool(t)
|
||||
|
||||
// Connected user with a non-empty feed (the case the bug missed: hasConnected
|
||||
// was only computed for an empty feed).
|
||||
_, err := p.Exec(context.Background(),
|
||||
`INSERT INTO video_connections (user_id, provider, token_ref, status)
|
||||
VALUES ($1, 'youtube', 'youtube/x/refresh_token', 'active')`, userID)
|
||||
require.NoError(t, err)
|
||||
seedVideo(t, p, "11111111-1111-1111-1111-111111111111", "A talk", "https://youtu.be/aaaaaaaaaaa", time.Now())
|
||||
|
||||
rec := do(t, app, httptest.NewRequest(http.MethodGet, "/", nil))
|
||||
require.Equal(t, http.StatusOK, rec.Code)
|
||||
require.Contains(t, body(t, rec), `action="/paste"`,
|
||||
"a connected user must see the paste box even when the feed has videos")
|
||||
}
|
||||
@@ -0,0 +1,97 @@
|
||||
package web
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"context"
|
||||
"gitea.d-ma.be/mathias/tapir/internal/adapters/store"
|
||||
"strings"
|
||||
"testing"
|
||||
)
|
||||
|
||||
func TestParseYouTubeVideoID(t *testing.T) {
|
||||
const id = "dQw4w9WgXcQ"
|
||||
ok := []struct {
|
||||
name, in string
|
||||
}{
|
||||
{"watch", "https://www.youtube.com/watch?v=" + id},
|
||||
{"watch no www", "https://youtube.com/watch?v=" + id},
|
||||
{"watch m", "https://m.youtube.com/watch?v=" + id},
|
||||
{"watch extra params", "https://www.youtube.com/watch?v=" + id + "&t=42s&list=PLxyz"},
|
||||
{"watch param after", "https://www.youtube.com/watch?list=PLxyz&v=" + id},
|
||||
{"short link", "https://youtu.be/" + id},
|
||||
{"short link param", "https://youtu.be/" + id + "?si=abcd&t=1"},
|
||||
{"shorts", "https://www.youtube.com/shorts/" + id},
|
||||
{"embed", "https://www.youtube.com/embed/" + id},
|
||||
{"bare id", id},
|
||||
{"http scheme", "http://youtube.com/watch?v=" + id},
|
||||
{"no scheme", "youtube.com/watch?v=" + id},
|
||||
{"trailing space", " https://youtu.be/" + id + " "},
|
||||
}
|
||||
for _, c := range ok {
|
||||
t.Run(c.name, func(t *testing.T) {
|
||||
got, err := parseYouTubeVideoID(c.in)
|
||||
if err != nil {
|
||||
t.Fatalf("parseYouTubeVideoID(%q) error: %v", c.in, err)
|
||||
}
|
||||
if got != id {
|
||||
t.Fatalf("parseYouTubeVideoID(%q) = %q, want %q", c.in, got, id)
|
||||
}
|
||||
})
|
||||
}
|
||||
|
||||
bad := []struct {
|
||||
name, in string
|
||||
}{
|
||||
{"empty", ""},
|
||||
{"blank", " "},
|
||||
{"vimeo", "https://vimeo.com/123456789"},
|
||||
{"other host", "https://example.com/watch?v=" + id},
|
||||
{"watch no id", "https://www.youtube.com/watch?v="},
|
||||
{"short id", "https://youtu.be/abc"},
|
||||
{"long id", "https://youtu.be/" + id + "extra"},
|
||||
{"bad chars", "https://youtu.be/dQw4w9Wg!cQ"},
|
||||
{"not a url", "just some text"},
|
||||
{"channel url", "https://www.youtube.com/@somechannel"},
|
||||
}
|
||||
for _, c := range bad {
|
||||
t.Run("reject "+c.name, func(t *testing.T) {
|
||||
if got, err := parseYouTubeVideoID(c.in); err == nil {
|
||||
t.Fatalf("parseYouTubeVideoID(%q) = %q, want error", c.in, got)
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
func TestListPageShowsPasteFormOnlyWhenConnected(t *testing.T) {
|
||||
render := func(connected bool) string {
|
||||
var buf bytes.Buffer
|
||||
if err := ListPage(listBuckets{}, Filter{}, PipelineStats{}, "", connected, nil).Render(context.Background(), &buf); err != nil {
|
||||
t.Fatalf("render: %v", err)
|
||||
}
|
||||
return buf.String()
|
||||
}
|
||||
|
||||
html := render(true)
|
||||
if !strings.Contains(html, `name="url"`) || !strings.Contains(html, `action="/paste"`) {
|
||||
t.Errorf("connected feed must show the paste form")
|
||||
}
|
||||
if strings.Contains(render(false), `name="url"`) {
|
||||
t.Errorf("disconnected feed must not show the paste form")
|
||||
}
|
||||
}
|
||||
|
||||
func TestFilterMatchesMultipleChannels(t *testing.T) {
|
||||
f := Filter{Channels: []string{"Acme", "Zeta"}}
|
||||
row := func(ch string) store.SummaryRow { return store.SummaryRow{ChannelTitle: ch, Summarized: true} }
|
||||
|
||||
rows := []store.SummaryRow{row("Acme"), row("Beta"), row("Zeta")}
|
||||
got := f.apply(rows)
|
||||
if len(got) != 2 || got[0].ChannelTitle != "Acme" || got[1].ChannelTitle != "Zeta" {
|
||||
t.Fatalf("multi-channel filter = %+v, want Acme+Zeta only", got)
|
||||
}
|
||||
|
||||
// Empty selection = no channel constraint (all pass).
|
||||
if n := len(Filter{}.apply(rows)); n != 3 {
|
||||
t.Fatalf("no channel filter should pass all rows, got %d", n)
|
||||
}
|
||||
}
|
||||
@@ -3,6 +3,8 @@ package web
|
||||
import (
|
||||
"context"
|
||||
"sync"
|
||||
|
||||
"gitea.d-ma.be/mathias/tapir/internal/domain"
|
||||
)
|
||||
|
||||
// Processor runs the core summarization use case for a single already-discovered
|
||||
@@ -14,6 +16,14 @@ type Processor interface {
|
||||
ProcessVideo(ctx context.Context, userID, videoID string) error
|
||||
}
|
||||
|
||||
// VideoFetcher resolves an arbitrary YouTube video id to its metadata for the
|
||||
// paste-a-URL flow (Feature 2). It is a Data API call, NOT the rate-limited
|
||||
// caption path. Returns domain.ErrVideoNotFound for a deleted/private/typo'd id.
|
||||
// cmd/tapir wires a per-user YouTube adapter; nil disables the paste route.
|
||||
type VideoFetcher interface {
|
||||
FetchVideo(ctx context.Context, userID, videoID string) (domain.Video, error)
|
||||
}
|
||||
|
||||
// ProcessingSet tracks the (user, video) ids currently being summarized in-process
|
||||
// so the status endpoint can show the animation until the summary lands. It is
|
||||
// ephemeral (single-instance Stage-1): a restart drops it, and the DB holds the
|
||||
|
||||
+27
-5
@@ -2,6 +2,7 @@ package web
|
||||
|
||||
import (
|
||||
"regexp"
|
||||
"slices"
|
||||
"strings"
|
||||
"time"
|
||||
"unicode/utf8"
|
||||
@@ -333,7 +334,7 @@ type flashView struct {
|
||||
// flashMessages maps each flash code to its banner. An unknown code renders no
|
||||
// banner (flashFor returns ok=false), so a forged cookie value is inert.
|
||||
var flashMessages = map[string]flashView{
|
||||
flashConnected: {"success", "YouTube account connected."},
|
||||
flashConnected: {"success", "YouTube account connected — finding your subscriptions. Your newest videos will appear below as they're summarized."},
|
||||
flashConnectFailed: {"error", "Could not connect your YouTube account. Please try again."},
|
||||
flashDisconnected: {"success", "Account disconnected."},
|
||||
flashDeleted: {"success", "Your account and all its data were deleted."},
|
||||
@@ -469,7 +470,7 @@ func (b listBuckets) empty() bool {
|
||||
// Dates are kept as the raw YYYY-MM-DD strings so the form re-renders the user's
|
||||
// input verbatim; parsing happens in matchFilter.
|
||||
type Filter struct {
|
||||
Channel string
|
||||
Channels []string // selected channel titles; empty = all channels
|
||||
From string
|
||||
To string
|
||||
OnlySummarized bool // show only videos that have a summary
|
||||
@@ -480,7 +481,28 @@ type Filter struct {
|
||||
// filter) the bar is hidden so the connect CTA stands alone (UX review C1); a
|
||||
// filter that happens to match nothing still shows the bar so it can be cleared.
|
||||
func (f Filter) active() bool {
|
||||
return f.Channel != "" || f.From != "" || f.To != "" || f.OnlySummarized
|
||||
return len(f.Channels) > 0 || f.From != "" || f.To != "" || f.OnlySummarized
|
||||
}
|
||||
|
||||
// HasChannel reports whether a channel is currently selected (drives the
|
||||
// multi-select's selected state in the view).
|
||||
func (f Filter) HasChannel(c string) bool {
|
||||
return slices.Contains(f.Channels, c)
|
||||
}
|
||||
|
||||
// nonEmptyStrings drops blank entries. A channel multi-select submits real
|
||||
// channel titles; this guards against a stray empty value reaching the filter.
|
||||
func nonEmptyStrings(ss []string) []string {
|
||||
out := ss[:0:0]
|
||||
for _, s := range ss {
|
||||
if strings.TrimSpace(s) != "" {
|
||||
out = append(out, s)
|
||||
}
|
||||
}
|
||||
if len(out) == 0 {
|
||||
return nil
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
// matches reports whether a row satisfies the filter. Channel is an exact match;
|
||||
@@ -491,7 +513,7 @@ func (f Filter) matches(r store.SummaryRow) bool {
|
||||
if f.OnlySummarized && !r.Summarized {
|
||||
return false
|
||||
}
|
||||
if f.Channel != "" && r.Channel != f.Channel {
|
||||
if len(f.Channels) > 0 && !slices.Contains(f.Channels, r.ChannelTitle) {
|
||||
return false
|
||||
}
|
||||
if from, ok := parseDate(f.From); ok {
|
||||
@@ -521,7 +543,7 @@ func parseDate(s string) (time.Time, bool) {
|
||||
|
||||
// apply returns the subset of rows matching the filter, preserving order.
|
||||
func (f Filter) apply(rows []store.SummaryRow) []store.SummaryRow {
|
||||
if f.Channel == "" && f.From == "" && f.To == "" && !f.OnlySummarized {
|
||||
if len(f.Channels) == 0 && f.From == "" && f.To == "" && !f.OnlySummarized {
|
||||
return rows
|
||||
}
|
||||
out := rows[:0:0]
|
||||
|
||||
@@ -104,11 +104,14 @@ templ flashBanner(code string) {
|
||||
// #summary-list region; a non-HTMX request renders the whole page. flash carries
|
||||
// a one-shot notification (e.g. "connected", "registered") surfaced on arrival
|
||||
// after a POST→redirect.
|
||||
templ ListPage(b listBuckets, f Filter, stats PipelineStats, flash string, hasConnected bool) {
|
||||
templ ListPage(b listBuckets, f Filter, stats PipelineStats, flash string, hasConnected bool, channels []string) {
|
||||
@Layout("Tapir — Summaries") {
|
||||
@flashBanner(flash)
|
||||
if hasConnected {
|
||||
@pasteForm()
|
||||
}
|
||||
if !b.empty() || f.active() {
|
||||
@filterForm(f)
|
||||
@filterForm(f, channels)
|
||||
}
|
||||
if stats.RateLimited > 0 || stats.Pending > 0 || stats.NoText > 0 {
|
||||
@pipelineBar(stats)
|
||||
@@ -143,7 +146,29 @@ templ pipelineBar(s PipelineStats) {
|
||||
</div>
|
||||
}
|
||||
|
||||
templ filterForm(f Filter) {
|
||||
// pasteForm lets a connected user summarize any YouTube video by pasting its URL
|
||||
// (Feature 2). The result (a video card, or an inline error) swaps into
|
||||
// #paste-result; the next list refresh shows it inline. Summarization runs
|
||||
// through the shared caption rate gate like every other fetch.
|
||||
templ pasteForm() {
|
||||
<form
|
||||
class="paste"
|
||||
method="post"
|
||||
action="/paste"
|
||||
hx-post="/paste"
|
||||
hx-target="#paste-result"
|
||||
hx-swap="innerHTML"
|
||||
>
|
||||
<label>
|
||||
Summarize any video
|
||||
<input type="url" name="url" placeholder="Paste a YouTube link…" required/>
|
||||
</label>
|
||||
<button type="submit">Add</button>
|
||||
</form>
|
||||
<div id="paste-result"></div>
|
||||
}
|
||||
|
||||
templ filterForm(f Filter, channels []string) {
|
||||
<form
|
||||
class="filters"
|
||||
method="get"
|
||||
@@ -153,7 +178,16 @@ templ filterForm(f Filter) {
|
||||
hx-swap="innerHTML"
|
||||
hx-indicator="#filter-indicator"
|
||||
>
|
||||
<label>Channel <input type="text" name="channel" value={ f.Channel } placeholder="any"/></label>
|
||||
if len(channels) > 0 {
|
||||
<label>
|
||||
Channels
|
||||
<select name="channel" multiple size="4">
|
||||
for _, c := range channels {
|
||||
<option value={ c } selected?={ f.HasChannel(c) }>{ c }</option>
|
||||
}
|
||||
</select>
|
||||
</label>
|
||||
}
|
||||
<label class="filter-check">
|
||||
<input type="checkbox" name="summarized" value="1" if f.OnlySummarized { checked }/>
|
||||
Summarized only
|
||||
|
||||
+667
-581
File diff suppressed because it is too large
Load Diff
@@ -37,9 +37,16 @@ var scenarioCoverage = map[string]string{
|
||||
"An authenticated user on the welcome page sees their way in and out": "TestWelcomeLoggedIn",
|
||||
|
||||
// connect_account.feature
|
||||
"Connect a YouTube account": "TestCallbackExchangesAndRecordsConnection",
|
||||
"Connecting an account discovers videos immediately": "TestCallbackTriggersDiscovery",
|
||||
"Tokens are never stored in the clear": "TestCallbackExchangesAndRecordsConnection",
|
||||
"Connect a YouTube account": "TestCallbackExchangesAndRecordsConnection",
|
||||
"Connecting an account discovers videos immediately": "TestCallbackTriggersDiscovery",
|
||||
"Connecting summarizes my newest videos right away": "TestNewestUnsummarizedVideoIDs",
|
||||
"Tokens are never stored in the clear": "TestCallbackExchangesAndRecordsConnection",
|
||||
|
||||
// paste_url.feature
|
||||
"Paste a valid YouTube URL": "TestPasteValidURLAddsAndRequests",
|
||||
"Pasting an invalid link is rejected": "TestPasteInvalidURLRejected",
|
||||
"Pasting a video that cannot be found is honest": "TestPasteVideoNotFound",
|
||||
"Pasting the same video twice does not duplicate it": "TestPasteDedupNoDuplicate",
|
||||
"Revoking a connection stops watching but keeps history": "TestDisconnectRemovesTokenAndConnectionKeepsAccount",
|
||||
|
||||
// summarize_mode.feature
|
||||
|
||||
Reference in New Issue
Block a user