tapir/internal/adapters/youtube/youtube_test.go

package youtube

import (
	"context"
	"fmt"
	"net/http"
	"net/http/httptest"
	"testing"

	"gitea.d-ma.be/mathias/tapir/internal/domain"
)

// --- fakes ------------------------------------------------------------------

// fakeSecrets records the references it was asked to resolve, proving the
// adapter resolves OAuth material by reference (never holding the token itself).
type fakeSecrets struct {
	byRef     map[string]string
	requested []string
}

func (f *fakeSecrets) Get(_ context.Context, ref string) (string, error) {
	f.requested = append(f.requested, ref)
	v, ok := f.byRef[ref]
	if !ok {
		return "", fmt.Errorf("no secret for ref %q", ref)
	}
	return v, nil
}

// newTestAdapter wires an adapter against an httptest server: BaseURL points at
// the server and the server's transport is injected so the live OAuth2 exchange
// is skipped while SecretStore resolution still runs.
func newTestAdapter(t *testing.T, handler http.HandlerFunc) (*Adapter, *fakeSecrets) {
	t.Helper()
	srv := httptest.NewServer(handler)
	t.Cleanup(srv.Close)

	secrets := &fakeSecrets{byRef: map[string]string{
		"op://HomeLab/tapir-youtube#refresh": "super-secret-refresh-token",
	}}
	a := New(Config{
		ClientID:           "cid",
		ClientSecret:       "csecret",
		TokenSecretRef:     "op://HomeLab/tapir-youtube#refresh",
		ConnectionID:       "conn-1",
		PreferredLanguages: []string{"en"},
		BaseURL:            srv.URL,
		PlayerBaseURL:      srv.URL,
	}, secrets)
	a.transport = srv.Client().Transport
	return a, secrets
}

// --- subscriptions ----------------------------------------------------------

func TestListSubscriptions(t *testing.T) {
	a, secrets := newTestAdapter(t, func(w http.ResponseWriter, r *http.Request) {
		if r.URL.Path != "/subscriptions" {
			t.Errorf("unexpected path %q", r.URL.Path)
		}
		if got := r.URL.Query().Get("mine"); got != "true" {
			t.Errorf("expected mine=true, got %q", got)
		}
		_, _ = w.Write([]byte(`{
			"items": [
				{"id": "sub-a", "snippet": {"title": "Acme Talks", "resourceId": {"channelId": "UC_acme"}}},
				{"id": "sub-b", "snippet": {"title": "Beta Lab", "resourceId": {"channelId": "UC_beta"}}}
			]
		}`))
	})

	subs, err := a.ListSubscriptions(context.Background(), "u1")
	if err != nil {
		t.Fatalf("ListSubscriptions: %v", err)
	}
	if len(subs) != 2 {
		t.Fatalf("expected 2 subscriptions, got %d", len(subs))
	}
	if subs[0].ChannelID != "UC_acme" || subs[0].ChannelTitle != "Acme Talks" {
		t.Errorf("unexpected first subscription: %+v", subs[0])
	}
	if subs[0].UserID != "u1" || subs[0].ConnectionID != "conn-1" || !subs[0].Active {
		t.Errorf("subscription not wired to user/connection: %+v", subs[0])
	}
	// The refresh token was resolved by reference, never read from config directly.
	if len(secrets.requested) == 0 || secrets.requested[0] != "op://HomeLab/tapir-youtube#refresh" {
		t.Errorf("expected token resolved by ref, got %v", secrets.requested)
	}
}

func TestListSubscriptionsPaginates(t *testing.T) {
	a, _ := newTestAdapter(t, func(w http.ResponseWriter, r *http.Request) {
		switch r.URL.Query().Get("pageToken") {
		case "":
			_, _ = w.Write([]byte(`{"nextPageToken":"p2","items":[{"id":"s1","snippet":{"title":"One","resourceId":{"channelId":"c1"}}}]}`))
		case "p2":
			_, _ = w.Write([]byte(`{"items":[{"id":"s2","snippet":{"title":"Two","resourceId":{"channelId":"c2"}}}]}`))
		default:
			t.Errorf("unexpected pageToken %q", r.URL.Query().Get("pageToken"))
		}
	})

	subs, err := a.ListSubscriptions(context.Background(), "u1")
	if err != nil {
		t.Fatalf("ListSubscriptions: %v", err)
	}
	if len(subs) != 2 {
		t.Fatalf("expected 2 subscriptions across pages, got %d", len(subs))
	}
}

// --- new videos -------------------------------------------------------------

func TestNewVideos(t *testing.T) {
	a, _ := newTestAdapter(t, func(w http.ResponseWriter, r *http.Request) {
		if r.URL.Path != "/search" {
			t.Errorf("unexpected path %q", r.URL.Path)
		}
		if got := r.URL.Query().Get("channelId"); got != "UC_acme" {
			t.Errorf("expected channelId=UC_acme, got %q", got)
		}
		_, _ = w.Write([]byte(`{
			"items": [
				{"id": {"videoId": "vid1"}, "snippet": {"title": "Designing for Attention", "publishedAt": "2026-06-01T10:00:00Z"}},
				{"id": {"videoId": "vid2"}, "snippet": {"title": "Second", "publishedAt": "2026-05-31T10:00:00Z"}}
			]
		}`))
	})

	sub := domain.Subscription{ID: "s1", UserID: "u1", ChannelID: "UC_acme"}
	vids, err := a.NewVideos(context.Background(), sub)
	if err != nil {
		t.Fatalf("NewVideos: %v", err)
	}
	if len(vids) != 2 {
		t.Fatalf("expected 2 videos, got %d", len(vids))
	}
	v := vids[0]
	if v.ProviderVideoID != "vid1" || v.Title != "Designing for Attention" {
		t.Errorf("unexpected video: %+v", v)
	}
	if v.Provider != domain.ProviderYouTube || v.URL != "https://www.youtube.com/watch?v=vid1" {
		t.Errorf("video not wired correctly: %+v", v)
	}
	if v.UserID != "u1" || v.SubscriptionID != "s1" {
		t.Errorf("video not scoped to user/subscription: %+v", v)
	}
	if v.PublishedAt.IsZero() {
		t.Errorf("expected publishedAt parsed, got zero")
	}
}

// --- transcript: captions present (player response + timedtext baseUrl) ------

// captionTracksJSON builds a player-response body whose captionTracks point their
// baseUrls back at the test server (via the request Host), so the unauthenticated
// baseUrl GET lands on the same httptest handler.
func playerBody(host string) string {
	base := "http://" + host
	return `{"captions":{"playerCaptionsTracklistRenderer":{"captionTracks":[
		{"baseUrl":"` + base + `/api/timedtext?lang=sv","languageCode":"sv"},
		{"baseUrl":"` + base + `/api/timedtext?lang=en&kind=asr","languageCode":"en","kind":"asr"},
		{"baseUrl":"` + base + `/api/timedtext?lang=en","languageCode":"en"}
	]}}}`
}

// TestFetchTranscriptWithCaptions: ANDROID player response yields tracks; the en
// non-asr track is preferred over both the sv track and the en asr track; its
// srv3 timedtext XML is fetched unauthenticated and reduced to plain text.
func TestFetchTranscriptWithCaptions(t *testing.T) {
	a, _ := newTestAdapter(t, func(w http.ResponseWriter, r *http.Request) {
		switch r.URL.Path {
		case "/youtubei/v1/player":
			if r.Method != http.MethodPost {
				t.Errorf("player must be POST, got %s", r.Method)
			}
			if h := r.Header.Get("Authorization"); h != "" {
				t.Errorf("player request must not be authenticated, got Authorization=%q", h)
			}
			_, _ = w.Write([]byte(playerBody(r.Host)))
		case "/api/timedtext":
			if h := r.Header.Get("Authorization"); h != "" {
				t.Errorf("timedtext request must not be authenticated, got Authorization=%q", h)
			}
			switch r.URL.Query().Get("kind") {
			case "asr":
				_, _ = w.Write([]byte(`<timedtext format="3"><body><p t="0" d="1">WRONG asr track</p></body></timedtext>`))
			default:
				if got := r.URL.Query().Get("lang"); got != "en" {
					t.Errorf("expected en track selected, got lang=%q", got)
				}
				_, _ = w.Write([]byte(`<?xml version="1.0" encoding="utf-8" ?><timedtext format="3"><body>` +
					`<p t="0" d="2000">Hello world</p>` +
					`<p t="2000" d="2000">Hello world</p>` +
					`<p t="4000" d="2000">Second line</p>` +
					`</body></timedtext>`))
			}
		default:
			t.Errorf("unexpected path %q", r.URL.Path)
		}
	})

	v := domain.Video{ID: "v1", UserID: "u1", ProviderVideoID: "vid1"}
	tr, err := a.FetchTranscript(context.Background(), v)
	if err != nil {
		t.Fatalf("FetchTranscript: %v", err)
	}
	if tr.Source != domain.SourceCaptions {
		t.Fatalf("expected SourceCaptions, got %q", tr.Source)
	}
	if tr.Language != "en" {
		t.Errorf("expected preferred language en, got %q", tr.Language)
	}
	// Consecutive duplicate cue collapsed; asr track not chosen.
	want := "Hello world\nSecond line"
	if tr.Content != want {
		t.Errorf("transcript text mismatch:\n got %q\nwant %q", tr.Content, want)
	}
	if !tr.HasText() {
		t.Error("expected HasText() true")
	}
}

// TestFetchTranscriptJSON3: a json3 timedtext body parses to clean text.
func TestFetchTranscriptJSON3(t *testing.T) {
	a, _ := newTestAdapter(t, func(w http.ResponseWriter, r *http.Request) {
		switch r.URL.Path {
		case "/youtubei/v1/player":
			base := "http://" + r.Host
			_, _ = w.Write([]byte(`{"captions":{"playerCaptionsTracklistRenderer":{"captionTracks":[` +
				`{"baseUrl":"` + base + `/api/timedtext?lang=en","languageCode":"en"}]}}}`))
		case "/api/timedtext":
			_, _ = w.Write([]byte(`{"events":[` +
				`{"segs":[{"utf8":"Hello "},{"utf8":"world"}]},` +
				`{"segs":[{"utf8":"\n"}]},` +
				`{"segs":[{"utf8":"Second line"}]}]}`))
		default:
			t.Errorf("unexpected path %q", r.URL.Path)
		}
	})

	tr, err := a.FetchTranscript(context.Background(), domain.Video{ID: "v1", UserID: "u1", ProviderVideoID: "vid1"})
	if err != nil {
		t.Fatalf("FetchTranscript: %v", err)
	}
	if tr.Source != domain.SourceCaptions {
		t.Fatalf("expected SourceCaptions, got %q", tr.Source)
	}
	if want := "Hello world\nSecond line"; tr.Content != want {
		t.Errorf("json3 text mismatch:\n got %q\nwant %q", tr.Content, want)
	}
}

// --- transcript: no captions => SourceNone, no error ------------------------

func TestFetchTranscriptNoCaptionsReturnsSourceNone(t *testing.T) {
	a, _ := newTestAdapter(t, func(w http.ResponseWriter, r *http.Request) {
		if r.URL.Path == "/api/timedtext" {
			t.Errorf("timedtext must not be fetched when no track exists")
		}
		// Player response with no captions block at all.
		_, _ = w.Write([]byte(`{"videoDetails":{"videoId":"vid-nocaps"}}`))
	})

	v := domain.Video{ID: "v1", UserID: "u1", ProviderVideoID: "vid-nocaps"}
	tr, err := a.FetchTranscript(context.Background(), v)
	if err != nil {
		t.Fatalf("expected no error for missing captions, got %v", err)
	}
	if tr.Source != domain.SourceNone {
		t.Fatalf("expected SourceNone, got %q", tr.Source)
	}
	if tr.HasText() {
		t.Error("expected HasText() false for SourceNone")
	}
	if tr.Content != "" {
		t.Errorf("expected empty content, got %q", tr.Content)
	}
}

// A 403/empty baseUrl fetch degrades to SourceNone, never an error (the explicit
// quick-fix: a finicky unofficial endpoint must not produce an error spew).
func TestFetchTranscriptBaseURLForbiddenDegrades(t *testing.T) {
	a, _ := newTestAdapter(t, func(w http.ResponseWriter, r *http.Request) {
		switch r.URL.Path {
		case "/youtubei/v1/player":
			base := "http://" + r.Host
			_, _ = w.Write([]byte(`{"captions":{"playerCaptionsTracklistRenderer":{"captionTracks":[` +
				`{"baseUrl":"` + base + `/api/timedtext?lang=en","languageCode":"en"}]}}}`))
		case "/api/timedtext":
			w.WriteHeader(http.StatusForbidden)
		}
	})

	tr, err := a.FetchTranscript(context.Background(), domain.Video{ID: "v1", UserID: "u1", ProviderVideoID: "vid1"})
	if err != nil {
		t.Fatalf("403 on baseUrl must degrade, not error: %v", err)
	}
	if tr.Source != domain.SourceNone {
		t.Fatalf("expected SourceNone on 403, got %q", tr.Source)
	}
}

// An empty baseUrl on the selected track degrades to SourceNone, never an error.
func TestFetchTranscriptEmptyBaseURLDegrades(t *testing.T) {
	a, _ := newTestAdapter(t, func(w http.ResponseWriter, r *http.Request) {
		if r.URL.Path == "/api/timedtext" {
			t.Errorf("must not fetch an empty baseUrl")
		}
		_, _ = w.Write([]byte(`{"captions":{"playerCaptionsTracklistRenderer":{"captionTracks":[` +
			`{"baseUrl":"","languageCode":"en"}]}}}`))
	})

	tr, err := a.FetchTranscript(context.Background(), domain.Video{ID: "v1", UserID: "u1", ProviderVideoID: "vid1"})
	if err != nil {
		t.Fatalf("empty baseUrl must degrade, not error: %v", err)
	}
	if tr.Source != domain.SourceNone {
		t.Fatalf("expected SourceNone on empty baseUrl, got %q", tr.Source)
	}
}