mangaBookmark/backend/internal/latest/acquire_test.go

package latest

import (
	"context"
	"errors"
	"testing"
	"time"

	"bookmarkmanager/backend/internal/store"
)

// The series page carries both facts, which is the whole argument for taking
// them from one fetch.
const asuraSeriesAndCoverFixture = asuraSeriesFixture + asuraCoverFixture

const (
	acquireKey       = "asura:chronicles-of-the-demon-faction-f886a8af"
	acquireSeriesID  = "chronicles-of-the-demon-faction-f886a8af"
	acquireSeriesURL = "https://asurascans.com/comics/chronicles-of-the-demon-faction-f886a8af"
	acquireCoverURL  = "https://cdn.asurascans.com/asura-images/covers/chronicles-of-the-demon-faction.d4dcb8.webp"
)

const (
	kaganeKey       = "kagane:019f84bc-9ba0-7ed9-86f5-8b905ec7c28b"
	kaganeSeriesID  = "019f84bc-9ba0-7ed9-86f5-8b905ec7c28b"
	kaganeSeriesURL = "https://kagane.to/series/019f84bc-9ba0-7ed9-86f5-8b905ec7c28b"
	kaganeImageID   = "019fe11a-84c3-7fc3-a84b-88787374b617"
	kaganeCoverSrc  = "https://kagane.to/api/v2/image/" + kaganeImageID + "/compressed"
)

// kagane's browser-fetched body is one JSON object carrying both the chapter
// list (series_books) and the cover image ids (series_covers), so the single
// acquisition fetch yields both facts.
const kaganeSeriesAndCoverFixture = `{"series_id":"019f84bc-9ba0-7ed9-86f5-8b905ec7c28b",` +
	`"series_books":[{"book_id":"b","title":"Episode 41","chapter_no":"41","sort_no":41}],` +
	`"series_covers":[{"cover_id":"019fe11a-84d1-714b-9cf4-2827f277f3c0","language":"en",` +
	`"image_id":"019fe11a-84c3-7fc3-a84b-88787374b617"}]}`

const (
	novelfullKey       = "novelfull:reverend-insanity"
	novelfullSeriesID  = "reverend-insanity"
	novelfullSeriesURI = "https://novelfull.com/reverend-insanity.html"
	novelfullCoverURL  = "https://novelfull.com/uploads/webp/novel/reverend-insanity-82661d911a.webp"
)

// newAcquirer wires an acquirer onto the store's creation hook, which is how
// main wires it: the write path is what starts an acquisition.
func newAcquirer(s *store.Store, page *fakeFetcher, covers *fakeBytesCoverFetcher) *Acquirer {
	a := &Acquirer{Store: s, Fetch: page, Covers: covers}
	s.OnSeriesCreated = a.Acquire
	return a
}

func bookmarkNewSeries(t *testing.T, s *store.Store, seriesURL string) store.Bookmark {
	t.Helper()
	stored, err := s.Upsert(s.OwnerID(), store.Bookmark{
		Key: acquireKey, Site: "asura", SeriesID: acquireSeriesID,
		Title: "Chronicles of the Demon Faction", SeriesURL: seriesURL,
		Cover: "https://evil.example/client-supplied.jpg", UpdatedAt: 1000,
	})
	if err != nil {
		t.Fatalf("Upsert: %v", err)
	}
	return stored
}

func readBookmark(t *testing.T, s *store.Store, key string) store.Bookmark {
	t.Helper()
	b, ok, err := s.Get(s.OwnerID(), key)
	if err != nil || !ok {
		t.Fatalf("Get %q = %v, %v", key, ok, err)
	}
	return b
}

func bookmarkNewKaganeSeries(t *testing.T, s *store.Store) store.Bookmark {
	t.Helper()
	stored, err := s.Upsert(s.OwnerID(), store.Bookmark{
		Key: kaganeKey, Site: "kagane", SeriesID: kaganeSeriesID,
		Title: "Infinite Decryption", SeriesURL: kaganeSeriesURL, UpdatedAt: 1000,
	})
	if err != nil {
		t.Fatalf("Upsert: %v", err)
	}
	return stored
}

func bookmarkNewNovelfullSeries(t *testing.T, s *store.Store) store.Bookmark {
	t.Helper()
	stored, err := s.Upsert(s.OwnerID(), store.Bookmark{
		Key: novelfullKey, Site: "novelfull", SeriesID: novelfullSeriesID,
		Title: "Reverend Insanity", SeriesURL: novelfullSeriesURI, UpdatedAt: 1000,
	})
	if err != nil {
		t.Fatalf("Upsert: %v", err)
	}
	return stored
}

// The reported bug: a Reader bookmarks a Series nobody holds and expects the
// Cover, not a broken image. Both facts come from the one series-page fetch.
func TestAcquireFillsChapterAndCoverFromOneFetch(t *testing.T) {
	s, _ := newTestStore(t)
	page := &fakeFetcher{body: asuraSeriesAndCoverFixture, status: 200}
	covers := &fakeBytesCoverFetcher{body: []byte("cover-bytes"), contentType: "image/jpeg"}
	acq := newAcquirer(s, page, covers)

	// The write itself must not carry the acquisition: it returns before the
	// Cover exists, and the field is empty until the bytes land.
	stored := bookmarkNewSeries(t, s, acquireSeriesURL)
	if stored.Cover != "" {
		t.Fatalf("Cover on the creating write = %q, want empty", stored.Cover)
	}
	acq.Wait()

	if got := page.callCount(); got != 1 {
		t.Fatalf("series page fetches = %d, want exactly 1", got)
	}
	if got := covers.callCount(); got != 1 {
		t.Fatalf("cover fetches = %d, want 1", got)
	}
	got := readBookmark(t, s, acquireKey)
	if got.LatestChapterNum == nil || *got.LatestChapterNum != 181 {
		t.Fatalf("LatestChapterNum = %v, want 181", got.LatestChapterNum)
	}
	if want := testCoverBaseURL + "/covers/" + store.CoverAddress(acquireCoverURL); got.Cover != want {
		t.Fatalf("Cover = %q, want the absolute address %q", got.Cover, want)
	}
	body, contentType, ok, err := s.CoverByAddress(store.CoverAddress(acquireCoverURL))
	if err != nil || !ok {
		t.Fatalf("CoverByAddress = %v, %v", ok, err)
	}
	if string(body) != "cover-bytes" || contentType != "image/jpeg" {
		t.Fatalf("stored cover = (%q, %q), want the fetched bytes", body, contentType)
	}
}

// A Series that already exists is not re-acquired: no fetch, and the Cover it
// already has is left alone.
func TestAcquireSkipsAnExistingSeries(t *testing.T) {
	s, _ := newTestStore(t)
	page := &fakeFetcher{body: asuraSeriesAndCoverFixture, status: 200}
	covers := &fakeBytesCoverFetcher{body: []byte("cover-bytes"), contentType: "image/jpeg"}
	acq := newAcquirer(s, page, covers)

	bookmarkNewSeries(t, s, acquireSeriesURL)
	acq.Wait()
	bookmarkNewSeries(t, s, acquireSeriesURL)
	acq.Wait()

	if got := page.callCount(); got != 1 {
		t.Fatalf("series page fetches = %d, want 1 — an existing series is not re-acquired", got)
	}
	if got := covers.callCount(); got != 1 {
		t.Fatalf("cover fetches = %d, want 1", got)
	}
	got := readBookmark(t, s, acquireKey)
	if want := testCoverBaseURL + "/covers/" + store.CoverAddress(acquireCoverURL); got.Cover != want {
		t.Fatalf("Cover = %q, want the acquired one %q", got.Cover, want)
	}
}

// A Site that is down costs the Cover and nothing else.
func TestAcquireFailureLeavesTheBookmarkIntact(t *testing.T) {
	cases := []struct {
		name   string
		page   *fakeFetcher
		covers *fakeBytesCoverFetcher
		// wantLatest is the chapter that still lands; 0 means none did.
		wantLatest float64
	}{
		{
			"the series page is unreachable",
			&fakeFetcher{err: errors.New("connection reset")},
			&fakeBytesCoverFetcher{body: []byte("cover-bytes"), contentType: "image/jpeg"},
			0,
		},
		{
			"the series page answers with a challenge",
			&fakeFetcher{body: challengeFixture, status: 200},
			&fakeBytesCoverFetcher{body: []byte("cover-bytes"), contentType: "image/jpeg"},
			0,
		},
		{
			"only the cover bytes fail",
			&fakeFetcher{body: asuraSeriesAndCoverFixture, status: 200},
			&fakeBytesCoverFetcher{err: errors.New("403")},
			181,
		},
	}
	for _, tc := range cases {
		t.Run(tc.name, func(t *testing.T) {
			s, _ := newTestStore(t)
			acq := newAcquirer(s, tc.page, tc.covers)

			stored := bookmarkNewSeries(t, s, acquireSeriesURL)
			acq.Wait()

			got := readBookmark(t, s, acquireKey)
			if got.Cover != "" {
				t.Fatalf("Cover = %q, want empty rather than an address that 404s", got.Cover)
			}
			if got.Title != stored.Title || got.UpdatedAt != stored.UpdatedAt {
				t.Fatalf("bookmark = %+v, want it untouched by the failed acquisition", got)
			}
			if tc.wantLatest == 0 {
				if got.LatestChapterNum != nil {
					t.Fatalf("LatestChapterNum = %v, want none captured", *got.LatestChapterNum)
				}
				return
			}
			if got.LatestChapterNum == nil || *got.LatestChapterNum != tc.wantLatest {
				t.Fatalf("LatestChapterNum = %v, want %v", got.LatestChapterNum, tc.wantLatest)
			}
		})
	}
}

// series_url arrives in a client-supplied body, so the acquisition reuses the
// poller's gate rather than deriving a second one: a non-https scheme, a
// site the parsers do not know, or a host pinned to another site is refused
// before the server spends a request from its own network position.
func TestAcquireRefusesAnUnfetchableSeriesURL(t *testing.T) {
	for _, seriesURL := range []string{
		"http://asurascans.com/comics/x",
		"file:///etc/passwd",
		"",
	} {
		t.Run(seriesURL, func(t *testing.T) {
			s, _ := newTestStore(t)
			page := &fakeFetcher{body: asuraSeriesAndCoverFixture, status: 200}
			acq := newAcquirer(s, page, &fakeBytesCoverFetcher{})

			bookmarkNewSeries(t, s, seriesURL)
			acq.Wait()

			if got := page.callCount(); got != 0 {
				t.Fatalf("fetches for %q = %d, want 0", seriesURL, got)
			}
		})
	}
}

// blockingFetcher stands in for a Site that never answers, so a synchronous
// acquisition would be visible as a stalled write rather than a slow one.
type blockingFetcher struct {
	release <-chan struct{}
	body    string
}

func (f *blockingFetcher) Get(ctx context.Context, _ string) (string, int, error) {
	select {
	case <-f.release:
		return f.body, 200, nil
	case <-ctx.Done():
		return "", 0, ctx.Err()
	}
}

// The Reader's write may not wait on a third-party Site: with the acquisition
// wedged on an unanswering page, the PUT still returns.
func TestAcquireDoesNotBlockTheWrite(t *testing.T) {
	s, _ := newTestStore(t)
	release := make(chan struct{})
	acq := &Acquirer{Store: s, Fetch: &blockingFetcher{release: release, body: asuraSeriesAndCoverFixture}}
	s.OnSeriesCreated = acq.Acquire

	upserted := make(chan error, 1)
	go func() {
		_, err := s.Upsert(s.OwnerID(), store.Bookmark{
			Key: acquireKey, Site: "asura", SeriesID: acquireSeriesID,
			Title: "Chronicles of the Demon Faction", SeriesURL: acquireSeriesURL, UpdatedAt: 1000,
		})
		upserted <- err
	}()
	select {
	case err := <-upserted:
		if err != nil {
			t.Fatalf("Upsert: %v", err)
		}
	case <-time.After(10 * time.Second):
		t.Fatal("the creating write blocked on the acquisition")
	}
	close(release)
	acq.Wait()
}

// The second symptom of #47: a kagane Series bookmarked from a chapter page
// gets its Cover at creation, with the bytes fetched through the browser
// sidecar — the only path that clears the challenge — into the
// content-addressed store.
func TestAcquireKaganeCoverThroughBrowser(t *testing.T) {
	s, _ := newTestStore(t)
	tlsPage := &fakeFetcher{body: "", status: 403}
	browserPage := &fakeFetcher{body: kaganeSeriesAndCoverFixture, status: 200}
	covers := &fakeCoverFetcher{body: []byte("cover-bytes"), contentType: "image/webp"}
	acq := &Acquirer{
		Store: s, Fetch: tlsPage, BrowserFetch: browserPage,
		BrowserCoverFetch: covers, Covers: &fakeBytesCoverFetcher{},
	}
	s.OnSeriesCreated = acq.Acquire

	bookmarkNewKaganeSeries(t, s)
	acq.Wait()

	if got := tlsPage.callCount(); got != 0 {
		t.Fatalf("plain-TLS page fetches = %d, want 0 — kagane pages are browser-only", got)
	}
	if got := browserPage.callCount(); got != 1 {
		t.Fatalf("browser page fetches = %d, want 1", got)
	}
	if got := covers.callCount(); got != 1 {
		t.Fatalf("browser cover fetches = %d, want 1", got)
	}
	if got := covers.calls[0]; got != kaganeImageID {
		t.Fatalf("browser cover fetched image id %q, want %q", got, kaganeImageID)
	}
	got := readBookmark(t, s, kaganeKey)
	if want := testCoverBaseURL + "/covers/" + store.CoverAddress(kaganeCoverSrc); got.Cover != want {
		t.Fatalf("Cover = %q, want the content-addressed URL %q", got.Cover, want)
	}
	body, contentType, ok, err := s.CoverByAddress(store.CoverAddress(kaganeCoverSrc))
	if err != nil || !ok {
		t.Fatalf("CoverByAddress = %v, %v", ok, err)
	}
	if string(body) != "cover-bytes" || contentType != "image/webp" {
		t.Fatalf("stored cover = (%q, %q), want the browser-fetched bytes", body, contentType)
	}
}

// novelfull needs the browser only for its HTML: the cover URL comes out of
// the browser-fetched page, but the bytes go over plain TLS through the
// ordinary gated fetcher, never through the browser (issue #62).
func TestAcquireNovelfullCoverOverPlainTLS(t *testing.T) {
	s, _ := newTestStore(t)
	browserPage := &fakeFetcher{body: novelfullSeriesFixture + novelfullCoverFixture, status: 200}
	covers := &fakeBytesCoverFetcher{body: []byte("cover-bytes"), contentType: "image/webp"}
	acq := &Acquirer{
		Store: s, Fetch: &fakeFetcher{body: "", status: 403},
		BrowserFetch: browserPage, Covers: covers,
	}
	s.OnSeriesCreated = acq.Acquire

	bookmarkNewNovelfullSeries(t, s)
	acq.Wait()

	if got := browserPage.callCount(); got != 1 {
		t.Fatalf("browser page fetches = %d, want 1", got)
	}
	if got := covers.callCount(); got != 1 {
		t.Fatalf("cover fetches = %d, want 1 — novelfull bytes never touch the browser", got)
	}
	if got := covers.calls[0]; got != novelfullCoverURL {
		t.Fatalf("cover fetched from %q, want %q", got, novelfullCoverURL)
	}
	got := readBookmark(t, s, novelfullKey)
	if want := testCoverBaseURL + "/covers/" + store.CoverAddress(novelfullCoverURL); got.Cover != want {
		t.Fatalf("Cover = %q, want %q", got.Cover, want)
	}
}

// With no browser sidecar configured, kagane is simply not acquired: no
// request is spent on a page that could only ever answer with a challenge,
// and nothing falls back to a plain fetch.
func TestAcquireKaganeSkippedWithoutBrowser(t *testing.T) {
	s, _ := newTestStore(t)
	tlsPage := &fakeFetcher{body: kaganeSeriesAndCoverFixture, status: 200}
	acq := &Acquirer{
		Store: s, Fetch: tlsPage,
		Covers: &fakeBytesCoverFetcher{body: []byte("x"), contentType: "image/webp"},
	}
	s.OnSeriesCreated = acq.Acquire

	bookmarkNewKaganeSeries(t, s)
	acq.Wait()

	if got := tlsPage.callCount(); got != 0 {
		t.Fatalf("plain-TLS fetches for kagane = %d, want 0", got)
	}
	if got := readBookmark(t, s, kaganeKey); got.Cover != "" {
		t.Fatalf("Cover = %q, want empty without a browser", got.Cover)
	}
}

// The byte half of "nothing falls back to a plain fetch": with a browser for
// the page but none for the bytes, a kagane Cover stays absent and the TLS
// cover fetcher is never consulted.
func TestAcquireKaganeBytesNeverFallBackToPlainTLS(t *testing.T) {
	s, _ := newTestStore(t)
	browserPage := &fakeFetcher{body: kaganeSeriesAndCoverFixture, status: 200}
	tlsCovers := &fakeBytesCoverFetcher{body: []byte("cover-bytes"), contentType: "image/webp"}
	acq := &Acquirer{
		Store: s, Fetch: &fakeFetcher{body: "", status: 403},
		BrowserFetch: browserPage, Covers: tlsCovers,
	}
	s.OnSeriesCreated = acq.Acquire

	bookmarkNewKaganeSeries(t, s)
	acq.Wait()

	if got := tlsCovers.callCount(); got != 0 {
		t.Fatalf("plain-TLS cover fetches = %d, want 0 — kagane bytes are browser-only", got)
	}
	if got := readBookmark(t, s, kaganeKey); got.Cover != "" {
		t.Fatalf("Cover = %q, want empty without a browser cover fetcher", got.Cover)
	}
}

// novelfull's no-browser degradation differs from kagane's: only its HTML
// needs the sidecar, so when the page body is available — the challenge is a
// live time-varying fact that sometimes answers a plain request — the Cover
// still lands, bytes over plain TLS.
func TestAcquireNovelfullCoverWithoutBrowser(t *testing.T) {
	s, _ := newTestStore(t)
	tlsPage := &fakeFetcher{body: novelfullSeriesFixture + novelfullCoverFixture, status: 200}
	covers := &fakeBytesCoverFetcher{body: []byte("cover-bytes"), contentType: "image/webp"}
	acq := &Acquirer{Store: s, Fetch: tlsPage, Covers: covers}
	s.OnSeriesCreated = acq.Acquire

	bookmarkNewNovelfullSeries(t, s)
	acq.Wait()

	if got := covers.callCount(); got != 1 {
		t.Fatalf("cover fetches = %d, want 1", got)
	}
	got := readBookmark(t, s, novelfullKey)
	if want := testCoverBaseURL + "/covers/" + store.CoverAddress(novelfullCoverURL); got.Cover != want {
		t.Fatalf("Cover = %q, want %q", got.Cover, want)
	}
}