sulthan/mangaBookmark
1
0
Fork 0
Code Issues 4 Pull Requests Actions Packages Projects Releases Wiki Activity

lightnovelworld Series identity is read from the chapter page (#80) (#92)

Browse Source 
Implements spec #80 / ADR-0008 — Gitea issues #86, #87, #88, #89, #90, all closed.

A Reader bookmarks a novel on lightnovelworld and it never shows a New Chapter, because the Series identity was derived from the chapter address instead of read from the page. One Series can publish under several Chapter Slugs, so the derived key points at a slug that 404s.

- **#89** — the userscript's lnw adapter stops deriving `seriesUrl`/`seriesId` from the path. It reads the page's own pointer (`a[aria-label='All Chapter']`), falling back to the microdata breadcrumb's second crumb, and carries `chapterSlug` on the page object, stored nowhere.
- **#87** — the Poll's lnw chapter scan is unscoped (no stored-slug pattern can cover a Series' whole list) and truncated at the `wpd-threads` comment thread, the one region a visitor can write to. Marker absent means skip and log with the body length, never scan whole. Corrects the `maxBodyBytes` headroom comment to the measured 3.5x.
- **#86** — the scan fixture is now text trimmed from a real, wholly-fetched Series page instead of a hand-written cross-series anchor that no live page carries.
- **#90** — stale stored rows repair themselves on the next chapter visit: a pure transform over cache, queue and last-checked map, silent to the Reader, with progress, favourite and lifecycle bucket preserved when two rows merge.
- **#88** — an env-gated live canary (`SMOKE_LNW_SERIES_URL`) proving the marker still occurs exactly once and still follows the last chapter anchor, asserted against the production symbols themselves.

Verified on the merged branch: `go test ./...` green, `gofmt -l internal/latest/` silent, both userscripts `node --check` clean, 35/35 + 29/29 logic tests. Live canary green (marker once at byte 612,182 of 651,795). #90 verified on device with Playwright.

Open follow-up: **#91** — the userscript's client-side latest-chapter scan is still scoped to the derived slug.

Reviewed-on: #92
Co-authored-by: Sulthan Zaki <sultankiki05@gmail.com>
Co-committed-by: Sulthan Zaki <sultankiki05@gmail.com>
This commit was merged in pull request #92.
This commit is contained in:
Sulthan Zaki
2026-08-11 18:21:50 +07:00
committed by sulthan
parent 90d8ab72ad
commit e7e22a12a5
13 changed files with 1731 additions and 551 deletions
Download Patch File Download Diff File Expand all files Collapse all files
userscript/novel-bookmark.user.js
+180 -6
View File
@@ -132,9 +132,30 @@
},
};
// The host shape this adapter owns. One definition so the pointer validator
// and `matches` cannot drift apart (a leading subdomain is allowed).
const lnwHostRe = /(^|\.)lightnovelworld\.net$/;
// A chapter page's pointer is its own link back to its Series. The href is
// page markup, so validate before trusting: resolve it against the page
// address, require the host above and the /novel/<slug>/ Series path.
// Anything else is not a pointer.
function seriesIdFromLnwPointer(href, base) {
if (!href) return null;
let u;
try {
u = new URL(href, base);
} catch (e) {
return null;
}
if (!lnwHostRe.test(u.hostname)) return null;
const m = u.pathname.match(/^\/novel\/([^/]+)\/?$/);
return m ? m[1] : null;
}
const lightnovelworld = {
site: "lightnovelworld",
matches: (loc) => /(^|\.)lightnovelworld\.net$/.test(loc.hostname),
matches: (loc) => lnwHostRe.test(loc.hostname),
detect(loc) {
const path = loc.pathname;
// /<slug>-chapter-<n>/ — flat, at the site root, not under /novel/. The
@@ -142,16 +163,38 @@
// words still resolves to the right series.
let m = path.match(/^\/(.+)-chapter-([0-9]+(?:\.[0-9]+)?)\/?$/);
if (m) {
// The address is not the identity on this Site: the slug in the path
// is a Chapter Slug, which can differ from the Series slug and is
// never computable from it. The Series address is read from the
// page's own pointer — a silent fallback to derivation is the defect
// this replaced, not a safety net.
const chapterSlug = m[1];
const pointer = document.querySelector("a[aria-label='All Chapter']");
let seriesId = pointer ? seriesIdFromLnwPointer(pointer.getAttribute("href"), loc.href) : null;
if (!seriesId) {
// Fallback: the microdata breadcrumb's second crumb is the Series.
// Scoped to the BreadcrumbList because itemprop="item" is not
// unique to it (the header nav uses microdata too).
const crumb = document.querySelector(
'[itemtype="http://schema.org/BreadcrumbList"] a[itemprop="item"][href*="/novel/"]'
);
seriesId = crumb ? seriesIdFromLnwPointer(crumb.getAttribute("href"), loc.href) : null;
}
// Neither pointer present, nor either pointing at a /novel/<slug>/
// address on this host: not a page the script understands, so no
// Bookmark under an invented identity.
if (!seriesId) return { type: "other" };
const num = parseFloat(m[2]);
const h1 = document.querySelector("h1.entry-title");
const heading = h1 ? h1.textContent || "" : "";
return {
type: "chapter",
site: this.site,
seriesId: m[1],
seriesId: seriesId,
chapterSlug: chapterSlug,
// The heading is "<Series> Chapter <n>"; drop the suffix.
title: heading.replace(/\s*Chapter\s+[0-9.]+\s*$/i, "").trim(),
seriesUrl: "https://lightnovelworld.net/novel/" + m[1] + "/",
seriesUrl: "https://lightnovelworld.net/novel/" + seriesId + "/",
chapterLabel: "Chapter " + m[2],
chapterNum: isNaN(num) ? null : num,
chapterUrl: loc.href,
@@ -165,6 +208,7 @@
type: "series",
site: this.site,
seriesId: m[1],
chapterSlug: null,
title: h1 ? (h1.textContent || "").trim() : "",
seriesUrl: "https://lightnovelworld.net/novel/" + m[1] + "/",
chapterLabel: null,
@@ -200,6 +244,102 @@
return ADAPTERS.find((a) => a.site === site) || null;
}
// A stale lightnovelworld row is one keyed under the Chapter Slug its
// address was built from, while the page's pointer names a different
// Series. All three storage sites must move together: the cache row alone
// leaves a queued write replaying under a key whose row no longer exists
// (that write is silently lost), and a last-checked timestamp left behind
// re-fetches the repaired row on the next visit. A repair must never cost a
// Reader the chapter they were tracking, so when a row already holds the
// repaired key the two rows merge and the farther-ahead progress wins.
// Pure: no storage access, no module state, no clock.
function repairLnwStaleRow(list, queue, lastChecked, page) {
if (
!page ||
page.site !== "lightnovelworld" ||
!page.chapterSlug ||
!page.seriesId ||
page.chapterSlug === page.seriesId
) {
return { list, queue, lastChecked };
}
const oldKey = "lightnovelworld:" + page.chapterSlug;
const newKey = "lightnovelworld:" + page.seriesId;
const stale = list.find((b) => b.key === oldKey);
if (!stale) return { list, queue, lastChecked };
let listOut;
const existing = list.find((b) => b.key === newKey);
if (existing) {
// Duplicate case (spec user story 2): one row must survive, and it is
// the one already under the repaired key — with the stale row's
// progress carried across when it is ahead, favourite OR'd, and the
// stronger lifecycle bucket kept (finished > archived > reading, so a
// merge can never silently un-archive or un-finish a row).
const merged = Object.assign({}, existing);
if (
existing.last_chapter_num == null ||
(stale.last_chapter_num != null && stale.last_chapter_num > existing.last_chapter_num)
) {
merged.last_chapter = stale.last_chapter;
merged.last_chapter_num = stale.last_chapter_num;
merged.last_chapter_url = stale.last_chapter_url;
}
merged.favorite = !!(existing.favorite || stale.favorite);
const rank = (s) => ({ finished: 2, archived: 1, reading: 0 }[s || "reading"] || 0);
merged.status = rank(stale.status) > rank(existing.status) ? stale.status : existing.status;
merged.updated_at = Math.max(existing.updated_at || 0, stale.updated_at || 0);
listOut = list.filter((b) => b.key !== oldKey).map((b) => (b.key === newKey ? merged : b));
} else {
listOut = list.map((b) =>
b.key === oldKey
? Object.assign({}, b, {
key: newKey,
series_id: page.seriesId,
series_url: page.seriesUrl,
})
: b
);
}
let queueOut = queue;
const oldEntry = queue.find((e) => e.key === oldKey);
if (oldEntry) {
const survivor = queue.find((x) => x.key === newKey);
if (!survivor) {
queueOut = queue.map((e) => (e.key === oldKey ? Object.assign({}, e, { key: newKey }) : e));
} else {
// Both keys hold a marker and one row survives, so the two collapse
// into one entry under the repaired key (the queue's one-entry-per-key
// invariant). sendStatus is sticky — an archive intent from either
// marker survives, the queue's own rule — and the worse attempts
// count wins. The stale-key marker's op is dropped: the row it
// described is retired by the merge itself.
queueOut = queue
.filter((e) => e.key !== oldKey && e.key !== newKey)
.concat([
{
key: newKey,
op: survivor.op,
sendStatus: survivor.sendStatus || oldEntry.sendStatus,
attempts: Math.max(survivor.attempts || 0, oldEntry.attempts || 0),
},
]);
}
}
let lastCheckedOut = lastChecked;
if (oldKey in lastChecked) {
lastCheckedOut = Object.assign({}, lastChecked);
// Max, not overwrite: a timestamp already under the repaired key must
// not be rolled back to an older one.
lastCheckedOut[newKey] = Math.max(lastCheckedOut[newKey] || 0, lastCheckedOut[oldKey]);
delete lastCheckedOut[oldKey];
}
return { list: listOut, queue: queueOut, lastChecked: lastCheckedOut };
}
// Highest chapter the site lists, or null when the markup yields nothing.
// seriesId is only consulted by adapters whose pages carry other series'
// chapter links; the rest ignore it.
@@ -1199,7 +1339,8 @@
// Refresh + navigation
// ============================================================
async function refresh() {
async function refresh(awaitFirst) {
if (awaitFirst) await awaitFirst; // repair sync lands before we adopt the server's view of it
await drain(); // push what we owe before adopting the server's view of it
loading = true;
render();
@@ -1214,9 +1355,41 @@
}
}
// Runs the repair on every navigation, silently: rewrites a stale
// lightnovelworld row to the page's discovered identity, persists all three
// sites, and syncs through the queue-backed path so an offline repair parks
// and replays later. No toast — the Reader never asked for this. Returns
// the sync promise (or null when nothing changed) so init can hold the
// server view until the repair has landed. When the transform returns its
// inputs unchanged there is nothing to do.
function applyLnwStaleRowRepair() {
const lastChecked = loadLastChecked();
const out = repairLnwStaleRow(state.list, queue, lastChecked, state.page);
if (out.list === state.list && out.queue === queue && out.lastChecked === lastChecked) {
return null;
}
state.list = out.list;
reindex(); // byKey answers under the old key until rebuilt
saveCache(state.list);
queue.splice(0, queue.length, ...out.queue); // closures hold this array instance
saveQueue(queue);
saveLastChecked(out.lastChecked);
// Queue-backed sync, outcome swallowed: the repaired row is PUT (with its
// bucket when archived — the only status a userscript write may send) and
// the old server bookmark is deleted so no duplicate survives on the
// wire. The delete parks under the retired key while offline — the
// teardown of the old identity, not a new record of the Chapter Slug.
const key = keyOf(state.page);
return Promise.all([
pushBookmark(key, statusOf(state.byKey[key]) === "archived"),
pushDelete("lightnovelworld:" + state.page.chapterSlug),
]).catch(() => {});
}
let lastUrl = location.href;
function onNavigate() {
state.page = detect();
applyLnwStaleRowRepair();
render();
maybeAutoUpdate();
maybeCaptureLatestOnSeriesPage();
@@ -1329,13 +1502,14 @@
function init() {
buildUI();
state.page = detect();
const repair = applyLnwStaleRowRepair();
render();
installNavWatcher();
installLongPress();
window.addEventListener("online", drain); // signal returned while the page stayed open
// Sync first: both auto-record and the latest-chapter checks below need to
// know which series are bookmarked and how fresh they are.
refresh().then(() => {
refresh(repair).then(() => {
maybeAutoUpdate();
maybeCaptureLatestOnSeriesPage();
backgroundRefreshLatest();
@@ -1576,7 +1750,7 @@
// Exposes pure logic only — see userscript/test/novel-logic.test.js.
// ============================================================
if (typeof window === "undefined" && typeof module === "object" && module.exports) {
module.exports = { novelfull, lightnovelworld, anchorsFromHTML, statusOf, kindOf, maxChapter, escapeRe };
module.exports = { novelfull, lightnovelworld, anchorsFromHTML, statusOf, kindOf, maxChapter, escapeRe, repairLnwStaleRow };
}
// ============================================================