Merge #169: The pass remembers when a Site called a work completed

# Conflicts: # backend/internal/latest/poller_test.go
2026-08-22 23:27:29 +07:00
parent 4d6773692d 86da47850c
commit 5a32943528
5 changed files with 217 additions and 10 deletions
@@ -2725,6 +2725,7 @@ func TestRunOnceForcedPassReclaimFailureDoesNotFailPoll(t *testing.T) {
 		t.Fatalf("Cover = %q, want the replacement %q", got.Cover, want)
 	}
 }
+
 // failureRow reads one Series' failure row as stored, for the poller tests
 // that must see the table the store API writes (ADR-0016).
 func failureRow(t *testing.T, dbURL, site, seriesID string) (word string, since int64, found bool) {
@@ -2940,3 +2941,154 @@ func TestPollFailureDoesNotChangePacing(t *testing.T) {
 		t.Fatalf("second pass fetched %d series, want both again", got)
 	}
 }
+
+// readSiteCompletedAt reads the poller's site_completed_at column directly:
+// it is a poller fact with no client-visible getter, and #170 is the surface
+// that will read it.
+func readSiteCompletedAt(t *testing.T, dbURL, site, seriesID string) int64 {
+	t.Helper()
+	db, err := sql.Open("pgx", dbURL)
+	if err != nil {
+		t.Fatalf("open %s: %v", dbURL, err)
+	}
+	defer db.Close()
+	var at int64
+	if err := db.QueryRow(
+		`SELECT site_completed_at FROM series WHERE site = $1 AND series_id = $2`,
+		site, seriesID).Scan(&at); err != nil {
+		t.Fatalf("read site_completed_at %s:%s: %v", site, seriesID, err)
+	}
+	return at
+}
+
+// seedSiteCompletedAt writes the column directly, for the refused/unreachable
+// tests that need a pre-existing stamp.
+func seedSiteCompletedAt(t *testing.T, dbURL, site, seriesID string, at int64) {
+	t.Helper()
+	db, err := sql.Open("pgx", dbURL)
+	if err != nil {
+		t.Fatalf("open %s: %v", dbURL, err)
+	}
+	defer db.Close()
+	if _, err := db.Exec(
+		`UPDATE series SET site_completed_at = $3 WHERE site = $1 AND series_id = $2`,
+		site, seriesID, at); err != nil {
+		t.Fatalf("seed site_completed_at %s:%s: %v", site, seriesID, err)
+	}
+}
+
+// A completed page stamps site_completed_at with the pass's own clock; the
+// same page an hour later is due again but must not move the stamp — the age
+// #170 prints is "since the Site first said so", not the age of the last
+// Poll. The transition is zero-versus-nonzero, so the exact value asserted
+// here is load-bearing.
+func TestRunOnceSiteCompletedStampsOnce(t *testing.T) {
+	s, dbURL := newTestStore(t)
+	const (
+		key       = "asura:chronicles-of-the-demon-faction-f886a8af"
+		seriesID  = "chronicles-of-the-demon-faction-f886a8af"
+		seriesURL = "https://asurascans.com/comics/chronicles-of-the-demon-faction-f886a8af"
+	)
+	completed := asuraSeriesFixture + asuraCompletedFixture
+	at := time.UnixMilli(5_000_000)
+	seedForCheck(t, s, key, seriesURL, at.Add(-time.Hour).UnixMilli())
+
+	newTestPoller(t, s, &fakeFetcher{body: completed, status: 200}, at).runOnce(context.Background())
+	if got := readSiteCompletedAt(t, dbURL, "asura", seriesID); got != at.UnixMilli() {
+		t.Fatalf("site_completed_at after completed poll = %d, want %d", got, at.UnixMilli())
+	}
+
+	hourLater := at.Add(time.Hour)
+	newTestPoller(t, s, &fakeFetcher{body: completed, status: 200}, hourLater).runOnce(context.Background())
+	if got := readSiteCompletedAt(t, dbURL, "asura", seriesID); got != at.UnixMilli() {
+		t.Fatalf("site_completed_at after a second completed poll = %d, want the original stamp %d", got, at.UnixMilli())
+	}
+}
+
+// An ongoing page is the inverse transition: a never-hinted Series stays zero
+// (an ordinary Poll of an ongoing Series writes nothing), and a hinted one is
+// zeroed — the Site no longer says completed, so the claim must not outlive
+// the evidence.
+func TestRunOnceOngoingPageClearsOrSkipsSiteCompleted(t *testing.T) {
+	s, dbURL := newTestStore(t)
+	const (
+		key       = "asura:chronicles-of-the-demon-faction-f886a8af"
+		seriesID  = "chronicles-of-the-demon-faction-f886a8af"
+		seriesURL = "https://asurascans.com/comics/chronicles-of-the-demon-faction-f886a8af"
+	)
+	ongoing := asuraSeriesFixture + asuraOngoingFixture
+	at := time.UnixMilli(5_000_000)
+	seedForCheck(t, s, key, seriesURL, at.Add(-time.Hour).UnixMilli())
+
+	newTestPoller(t, s, &fakeFetcher{body: ongoing, status: 200}, at).runOnce(context.Background())
+	if got := readSiteCompletedAt(t, dbURL, "asura", seriesID); got != 0 {
+		t.Fatalf("site_completed_at after ongoing poll of a never-hinted series = %d, want 0", got)
+	}
+
+	seedSiteCompletedAt(t, dbURL, "asura", seriesID, at.UnixMilli())
+	hourLater := at.Add(time.Hour)
+	newTestPoller(t, s, &fakeFetcher{body: ongoing, status: 200}, hourLater).runOnce(context.Background())
+	if got := readSiteCompletedAt(t, dbURL, "asura", seriesID); got != 0 {
+		t.Fatalf("site_completed_at after ongoing poll of a hinted series = %d, want 0", got)
+	}
+}
+
+// A refused or unreachable read reaches nothing after checkOne's error switch:
+// a challenge is not evidence about the work, so a pre-seeded stamp must
+// survive both.
+func TestRunOnceRefusedOrUnreachableLeavesSiteCompletedUntouched(t *testing.T) {
+	now := time.UnixMilli(5_000_000)
+
+	t.Run("refused", func(t *testing.T) {
+		s, dbURL := newTestStore(t)
+		const (
+			key       = "asura:chronicles-of-the-demon-faction-f886a8af"
+			seriesID  = "chronicles-of-the-demon-faction-f886a8af"
+			seriesURL = "https://asurascans.com/comics/chronicles-of-the-demon-faction-f886a8af"
+		)
+		seedForCheck(t, s, key, seriesURL, 0)
+		seedSiteCompletedAt(t, dbURL, "asura", seriesID, now.UnixMilli())
+		newTestPoller(t, s, &fakeFetcher{status: 403}, now).runOnce(context.Background())
+		if got := readSiteCompletedAt(t, dbURL, "asura", seriesID); got != now.UnixMilli() {
+			t.Fatalf("site_completed_at after refused poll = %d, want the pre-seeded %d", got, now.UnixMilli())
+		}
+	})
+
+	t.Run("mid-loop unreachable", func(t *testing.T) {
+		s, dbURL := newTestStore(t)
+		seedForCheck(t, s, "comix:c", "https://comix.to/title/c", 0)
+		seedSiteCompletedAt(t, dbURL, "comix", "c", now.UnixMilli())
+		interrupted := fmt.Errorf("%w: %w", errBrowserInterrupted, errors.New("restart"))
+		browser := &fakeFetcher{status: 200, err: interrupted}
+		p := newTestPoller(t, s, &fakeFetcher{status: 200}, now)
+		p.BrowserFetch = browser
+		p.runLanePass(context.Background(), "comix", false)
+		if got := readSiteCompletedAt(t, dbURL, "comix", "c"); got != now.UnixMilli() {
+			t.Fatalf("site_completed_at after unreachable poll = %d, want the pre-seeded %d", got, now.UnixMilli())
+		}
+	})
+}
+
+// The regression AC2's second sentence exists to prevent: the completed write
+// must not ride the chapter setter, so a completed page whose chapter number
+// is unchanged — checkOne's equality early return — still stamps the column.
+func TestRunOnceSiteCompletedWritesDespiteUnchangedChapter(t *testing.T) {
+	s, dbURL := newTestStore(t)
+	const (
+		key       = "asura:chronicles-of-the-demon-faction-f886a8af"
+		seriesID  = "chronicles-of-the-demon-faction-f886a8af"
+		seriesURL = "https://asurascans.com/comics/chronicles-of-the-demon-faction-f886a8af"
+	)
+	completed := asuraSeriesFixture + asuraCompletedFixture
+	at := time.UnixMilli(5_000_000)
+	seedForCheck(t, s, key, seriesURL, 0)
+	// The page parses Chapter 181 as the latest; store the same number so the
+	// equality early return fires and only the completed write can run.
+	if err := s.SetLatestChapter("asura", seriesID, "Chapter 181", 181); err != nil {
+		t.Fatalf("seed latest chapter: %v", err)
+	}
+	newTestPoller(t, s, &fakeFetcher{body: completed, status: 200}, at).runOnce(context.Background())
+	if got := readSiteCompletedAt(t, dbURL, "asura", seriesID); got != at.UnixMilli() {
+		t.Fatalf("site_completed_at after unchanged-chapter completed poll = %d, want %d", got, at.UnixMilli())
+	}
+}