Merge ticket/88-lnw-marker-canary (#88)

backend/internal/latest/smoke_lnw_test.go

@@ -0,0 +1,101 @@
+package latest
+
+import (
+	"context"
+	"fmt"
+	"net/http"
+	"os"
+	"strings"
+	"testing"
+	"time"
+)
+
+// lnwSeriesPageFloor is the smallest body that can still be a whole
+// lightnovelworld Series page. Whole pages measured 685 KB..1.18 MB on
+// 2026-08-11 and carry the marker at ~94% of the document, so a body under
+// 100 KB is a challenge, a notice, or a truncated read — asserting on it
+// would report the marker missing when it was never fetched.
+const lnwSeriesPageFloor = 100 << 10
+
+// TestSmokeLnwCommentBoundary is the live proof that the comment-thread marker
+// the lightnovelworld chapter scan truncates at (lnwCommentMarker,
+// "wpd-threads") still holds on the Site. The scan depends on it: when the
+// marker vanishes every Series is skipped and logged — correct, but silent
+// until a Reader notices their Latest Chapter has stopped moving. It runs only
+// when SMOKE_LNW_SERIES_URL is set — the URL of the live Series page to check.
+// The immortality-simulator page measured 2026-08-11
+// (docs/research/lightnovelworld-chapter-vs-series-slug.md) is the default to
+// point it at:
+//
+//	SMOKE_LNW_SERIES_URL=https://lightnovelworld.net/novel/immortality-simulator/ go test -v -run TestSmokeLnwCommentBoundary ./internal/latest
+//
+// A red run means the Site's markup has moved — the marker is gone, occurs
+// more than once, or no longer follows the last chapter anchor — and the scan
+// in sites.go is now skipping this Site. Revisit sites.go before anything
+// else; the test is not flaky. A Cloudflare challenge or a non-200 is
+// distinguished from a marker failure by the "not a marker failure" messages
+// below, which carry the observed status and body length.
+func TestSmokeLnwCommentBoundary(t *testing.T) {
+	seriesURL := os.Getenv("SMOKE_LNW_SERIES_URL")
+	if seriesURL == "" {
+		t.Skip("SMOKE_LNW_SERIES_URL unset")
+	}
+	if !fetchableSeriesURL("lightnovelworld", seriesURL) {
+		t.Fatalf("%q is not a fetchable lightnovelworld series URL", seriesURL)
+	}
+
+	f, err := NewTLSFetcher()
+	if err != nil {
+		t.Fatalf("NewTLSFetcher: %v", err)
+	}
+	ctx, cancel := context.WithTimeout(context.Background(), 60*time.Second)
+	defer cancel()
+	body, status, err := f.Get(ctx, seriesURL)
+	if err != nil {
+		t.Fatalf("Get: %v", err)
+	}
+	if status != http.StatusOK {
+		t.Fatalf("status = %d, body %d bytes — not a marker failure; the Site did not answer this IP with a Series page", status, len(body))
+	}
+	if len(body) < lnwSeriesPageFloor {
+		t.Fatalf("body %d bytes — not a whole Series page (measured 685 KB..1.18 MB); not a marker failure, likely a Cloudflare challenge or a non-Series response", len(body))
+	}
+	if !lnwChapterRe.MatchString(body) {
+		t.Fatalf("no chapter anchor in %d bytes — not a lightnovelworld Series page; not a marker failure, likely a Cloudflare challenge or a non-Series response", len(body))
+	}
+	markerIdx := strings.Index(body, lnwCommentMarker)
+	if failures := checkLnwCommentBoundary(body); len(failures) > 0 {
+		t.Fatalf("%s (body %d bytes)", strings.Join(failures, "; "), len(body))
+	}
+	t.Logf("ok: %q once at byte %d, body %d bytes", lnwCommentMarker, markerIdx, len(body))
+}
+
+// checkLnwCommentBoundary verifies the three marker assertions against a
+// fetched Series body: the marker occurs exactly once, every chapter anchor
+// precedes it, and at least one anchor precedes it at all. It returns one
+// human-readable failure per broken assertion — with observed offsets and body
+// length — and empty when the page is healthy.
+func checkLnwCommentBoundary(body string) []string {
+	markerIdx := strings.Index(body, lnwCommentMarker)
+	switch n := strings.Count(body, lnwCommentMarker); {
+	case n == 0:
+		return []string{fmt.Sprintf("%q occurs 0 times in %d bytes, want exactly 1", lnwCommentMarker, len(body))}
+	case n != 1:
+		return []string{fmt.Sprintf("%q occurs %d times in %d bytes (first at byte %d), want exactly 1", lnwCommentMarker, n, len(body), markerIdx)}
+	}
+	lastAnchor, anchorsBefore := -1, 0
+	for _, m := range lnwChapterRe.FindAllStringIndex(body, -1) {
+		if m[0] < markerIdx {
+			anchorsBefore++
+		}
+		lastAnchor = m[0]
+	}
+	var failures []string
+	if lastAnchor >= markerIdx {
+		failures = append(failures, fmt.Sprintf("last chapter anchor at byte %d does not precede the marker at byte %d", lastAnchor, markerIdx))
+	}
+	if anchorsBefore == 0 {
+		failures = append(failures, fmt.Sprintf("no chapter anchor before the marker at byte %d — the truncated prefix the scan sees yields nothing", markerIdx))
+	}
+	return failures
+}