Merge ticket/87-lnw-scan-unscoped (#87)

backend/internal/latest/fetch.go

@@ -11,8 +11,9 @@ import (
 )
 
 // maxBodyBytes caps what a single series page can cost in memory. Real pages
-// measured 100-400 KB on 2026-07-26, so this is roughly 10x headroom and mostly
+// measured 100-400 KB on 2026-07-26; lightnovelworld runs larger — 685 KB and
-// guards against a proxy handing back something enormous.
+// 1.18 MB measured 2026-08-11 — so the headroom there is roughly 3.5x, and the
+// cap mostly guards against a proxy handing back something enormous.
 const maxBodyBytes = 4 << 20
 
 // chromeUA matches the client profile below. A Chrome fingerprint paired with a

backend/internal/latest/sites.go

@@ -3,6 +3,7 @@ package latest
 import (
 	"encoding/json"
 	"html"
+	"log"
 	"net/url"
 	"regexp"
 	"strconv"
@@ -58,11 +59,26 @@ var kaganeChapterRe = regexp.MustCompile(`"chapter_no":"([0-9.]+)"`)
 // "/<slug>/chapter-<n>[-<title-slug>].html". Verified live 2026-08-05.
 var novelfullSlugRe = regexp.MustCompile(`^/([^/?#]+)\.html$`)
 
-// lnwSlugRe does the same for lightnovelworld, whose series pages live under
+// lnwChapterRe matches any chapter-shaped address on lightnovelworld. Unlike
-// /novel/<slug>/ while its chapter URLs are flat at the site root:
+// asura, novelfull and comix — which scope to their stored series slug so a
-// "/<slug>-chapter-<n>/", absolute in the page's own anchors. Verified live
+// foreign chapter link cannot contribute — this Site's chapter addresses carry
-// 2026-08-05.
+// the Chapter Slug, which is not the Series identity: one Series may publish
-var lnwSlugRe = regexp.MustCompile(`^/novel/([^/?#]+)/?$`)
+// under several Chapter Slugs (measured 2026-08-11: a sampled novel serves
+// 1-99 under one slug and 100-423 under another), so no stored-slug pattern can
+// cover a Series' whole list. An unscoped match is safe because
+// latestChapterFrom truncates the body at the comment thread before scanning
+// (lnwCommentMarker); without that, a visitor's comment could set the Latest
+// Chapter on the shared Series row.
+var lnwChapterRe = regexp.MustCompile(`lightnovelworld\.net/[a-z0-9-]+-chapter-([0-9.]+)/`)
+
+// lnwCommentMarker is the boundary of lightnovelworld's server-rendered
+// wpdiscuz comment thread. It occurs exactly once per page and follows every
+// chapter anchor (measured 2026-08-11,
+// docs/research/lightnovelworld-chapter-vs-series-slug.md §6), so cutting the
+// body at its first occurrence keeps the whole chapter list while excluding a
+// region any visitor can write to. Absent means the page shape changed: the
+// body is skipped, never scanned whole.
+const lnwCommentMarker = "wpd-threads"
 
 // latestChapterFrom returns the highest chapter number body advertises for this
 // series. ok is false when the body yields nothing usable — an unknown site, an
@@ -82,6 +98,7 @@ var lnwSlugRe = regexp.MustCompile(`^/novel/([^/?#]+)/?$`)
 // such guarantee — demonicChapterRe matches any chaptered.php?manga=<id> anchor
 // with no per-series scoping, because the stored series_id for demonic is a
 // slug, not the numeric id the URL carries, so it cannot easily be scoped.
+// lightnovelworld is unscoped and body-truncated instead — see lnwChapterRe.
 func latestChapterFrom(site, seriesURL, body string) (latestChapter, bool) {
 	var re *regexp.Regexp
 	switch site {
@@ -126,15 +143,19 @@ func latestChapterFrom(site, seriesURL, body string) (latestChapter, bool) {
 		// and neither may contribute to the maximum.
 		re = regexp.MustCompile(`/` + regexp.QuoteMeta(m[1]) + `/chapter-([0-9.]+)`)
 	case "lightnovelworld":
-		u, err := url.Parse(seriesURL)
+		// The comment thread below the chapter list is the one region of the
-		if err != nil {
+		// page any visitor can write to, so the scan never reads past it (see
+		// lnwChapterRe). A body without the marker is skipped, never scanned
+		// whole — a redesign must degrade into staleness, not into a wrong
+		// shared value; the logged body length tells a markup change from a
+		// body the size cap cut short.
+		i := strings.Index(body, lnwCommentMarker)
+		if i < 0 {
+			log.Printf("latest poll %q: no %s marker in %d bytes", seriesURL, lnwCommentMarker, len(body))
 			return latestChapter{}, false
 		}
-		m := lnwSlugRe.FindStringSubmatch(u.Path)
+		body = body[:i]
-		if m == nil {
+		re = lnwChapterRe
-			return latestChapter{}, false
-		}
-		re = regexp.MustCompile(`lightnovelworld\.net/` + regexp.QuoteMeta(m[1]) + `-chapter-([0-9.]+)/`)
 	default:
 		return latestChapter{}, false
 	}

backend/internal/latest/sites_test.go

@@ -1,6 +1,9 @@
 package latest
 
-import "testing"
+import (
+	"strings"
+	"testing"
+)
 
 // Trimmed from https://asurascans.com/comics/chronicles-of-the-demon-faction-f886a8af
 // fetched 2026-07-26. The first anchor is the "First Chapter" shortcut: it is a
@@ -408,19 +411,33 @@ func TestLatestChapterFrom(t *testing.T) {
 			body:      novelfullSeriesFixture,
 			wantOK:    false,
 		},
+		// Stored before the slug split, so the address carries the ...-not
+		// Chapter Slug; the 100-423 block under the other slug must still win.
+		// The body is the chapter-list portion of lnwSeriesFixture with the
+		// comment block omitted; the marker is kept, because a body without it
+		// is skipped, not scanned.
 		{
-			name:      "lightnovelworld takes the max on a split-slug novel",
+			name:      "lightnovelworld max spans both chapter slugs",
+			site:      "lightnovelworld",
+			seriesURL: "https://lightnovelworld.net/novel/all-jobs-and-classes-i-just-wanted-one-skill-not/",
+			body:      strings.SplitN(lnwSeriesFixture, lnwCommentMarker, 2)[0] + lnwCommentMarker,
+			wantOK:    true, wantNum: 423, wantLabel: "Chapter 423",
+		},
+		{
+			name:      "lightnovelworld comment anchor cannot set the latest chapter",
 			site:      "lightnovelworld",
 			seriesURL: "https://lightnovelworld.net/novel/all-jobs-and-classes-i-just-wanted-one-skill-not-them-all/",
 			body:      lnwSeriesFixture,
 			wantOK:    true, wantNum: 423, wantLabel: "Chapter 423",
 		},
+		// Marker removed from the fixture, comment block still present: a
+		// redesign must degrade into a skip, never into the comment's number.
 		{
-			name:      "lightnovelworld tolerates a series url with no trailing slash",
+			name:      "lightnovelworld body without the comment marker is skipped",
 			site:      "lightnovelworld",
-			seriesURL: "https://lightnovelworld.net/novel/all-jobs-and-classes-i-just-wanted-one-skill-not-them-all",
+			seriesURL: "https://lightnovelworld.net/novel/all-jobs-and-classes-i-just-wanted-one-skill-not-them-all/",
-			body:      lnwSeriesFixture,
+			body:      strings.ReplaceAll(lnwSeriesFixture, lnwCommentMarker, ""),
-			wantOK:    true, wantNum: 423, wantLabel: "Chapter 423",
+			wantOK:    false,
 		},
 		{
 			name:      "lightnovelworld yields nothing on a challenge page",