Read lnw Series identity from the chapter page pointer (#89)

The lightnovelworld chapter branch no longer derives the Series address by string-manipulating the chapter path: on ~7% of novels the Chapter Slug diverges from the Series slug and the derived address 404s on every Poll. The identity now comes from the page's own a[aria-label='All Chapter'] pointer (breadcrumb's second crumb as fallback), validated as a lightnovelworld.net /novel/<slug>/ address; no pointer resolves to type: other. The Chapter Slug rides on the detected page object only (chapterSlug; null on a series page) and is written to no store, for the stale-row repair in #90. Harness: document.querySelector now answers attribute selectors with an element exposing getAttribute (attrEls table, cleared by reset()). AGENTS.md records that the Series address is discovered, not derived.
2026-08-11 11:48:46 +07:00
parent c400c91a80
commit a4da2e2f00
3 changed files with 182 additions and 5 deletions
@@ -20,8 +20,13 @@ globalThis.location = { href: "about:blank", hostname: "", pathname: "/", origin

 let metaTags = {};
 let elements = {};
+// Attribute selectors (the lightnovelworld Series pointer) answer with an
+// element exposing getAttribute, like the meta branch below.
+let attrEls = {};
 globalThis.document = {
  querySelector(sel) {
+    const attr = attrEls[sel];
+    if (attr != null) return attr;
    const m = sel.match(/^meta\[property="([^"]+)"\]$/);
    if (m) {
      const v = metaTags[m[1]];
@@ -52,6 +57,7 @@ function loc(href) {
 function reset() {
  metaTags = {};
  elements = {};
+  attrEls = {};
 }

 // ============================================================
@@ -115,11 +121,18 @@ test("lightnovelworld.detect reads a series page", () => {
  assert.equal(p.site, "lightnovelworld");
  assert.equal(p.seriesId, "a-will-eternal");
  assert.equal(p.title, "A Will Eternal");
+  // A series page's address *is* its identity; there is no Chapter Slug.
+  assert.equal(p.chapterSlug, null);
 });

 test("lightnovelworld.detect strips the chapter suffix off the heading", () => {
  reset();
  elements = { "h1.entry-title": "A Will Eternal Chapter 1298" };
+  attrEls = {
+    "a[aria-label='All Chapter']": {
+      getAttribute: () => "https://lightnovelworld.net/novel/a-will-eternal/",
+    },
+  };
  const url = "https://lightnovelworld.net/a-will-eternal-chapter-1298/";
  const p = lightnovelworld.detect(loc(url));
  assert.equal(p.type, "chapter");
@@ -130,6 +143,126 @@ test("lightnovelworld.detect strips the chapter suffix off the heading", () => {
  assert.equal(p.seriesUrl, "https://lightnovelworld.net/novel/a-will-eternal/");
 });

+test("lightnovelworld.detect reads the Series identity from the page pointer on a chapter page", () => {
+  reset();
+  elements = { "h1.entry-title": "A Will Eternal Chapter 1298" };
+  attrEls = {
+    // Verbatim from the real page (research note §3): the All Chapter anchor
+    // carries the absolute Series address.
+    "a[aria-label='All Chapter']": {
+      getAttribute: () => "https://lightnovelworld.net/novel/a-will-eternal/",
+    },
+  };
+  const url = "https://lightnovelworld.net/a-will-eternal-chapter-1298/";
+  const p = lightnovelworld.detect(loc(url));
+  assert.equal(p.type, "chapter");
+  assert.equal(p.seriesId, "a-will-eternal");
+  assert.equal(p.seriesUrl, "https://lightnovelworld.net/novel/a-will-eternal/");
+  assert.equal(p.chapterSlug, "a-will-eternal");
+  assert.equal(p.chapterNum, 1298);
+});
+
+test("lightnovelworld.detect falls back to the breadcrumb when the pointer is absent", () => {
+  reset();
+  elements = { "h1.entry-title": "My Longevity Simulation Chapter 1" };
+  attrEls = {
+    // Verbatim from the real page (research note §3): position 2 of the
+    // microdata BreadcrumbList is the Series.
+    '[itemtype="http://schema.org/BreadcrumbList"] a[itemprop="item"][href*="/novel/"]': {
+      getAttribute: () => "https://lightnovelworld.net/novel/immortality-simulator/",
+    },
+  };
+  const url = "https://lightnovelworld.net/my-longevity-simulation-chapter-1/";
+  const p = lightnovelworld.detect(loc(url));
+  assert.equal(p.type, "chapter");
+  assert.equal(p.seriesId, "immortality-simulator");
+  assert.equal(p.seriesUrl, "https://lightnovelworld.net/novel/immortality-simulator/");
+  assert.equal(p.chapterSlug, "my-longevity-simulation");
+});
+
+test("lightnovelworld.detect resolves to other when the page carries no pointer", () => {
+  reset();
+  elements = { "h1.entry-title": "My Longevity Simulation Chapter 1" };
+  const p = lightnovelworld.detect(
+    loc("https://lightnovelworld.net/my-longevity-simulation-chapter-1/")
+  );
+  assert.equal(p.type, "other");
+});
+
+test("lightnovelworld pins the divergent novel: the pointer's slug wins over the address's", () => {
+  // Regression pin for the derivation defect (research note §2/§3): the
+  // chapter address is built from "my-longevity-simulation" but the Series
+  // is published as "immortality-simulator". If the adapter ever derives the
+  // identity from the address again, this test goes red.
+  reset();
+  elements = { "h1.entry-title": "My Longevity Simulation Chapter 1" };
+  attrEls = {
+    "a[aria-label='All Chapter']": {
+      getAttribute: () => "https://lightnovelworld.net/novel/immortality-simulator/",
+    },
+  };
+  const url = "https://lightnovelworld.net/my-longevity-simulation-chapter-1/";
+  const p = lightnovelworld.detect(loc(url));
+  assert.equal(p.type, "chapter");
+  assert.equal(p.seriesId, "immortality-simulator");
+  assert.equal(p.seriesUrl, "https://lightnovelworld.net/novel/immortality-simulator/");
+  assert.equal(p.chapterSlug, "my-longevity-simulation");
+  assert.notEqual(p.chapterSlug, p.seriesId);
+});
+
+test("lightnovelworld.detect resolves a novel whose heading ends in a chapter number", () => {
+  // The split novel from research §4.4, chapter 200 (published under the
+  // current slug). Its heading ends "…Not Them All Chapter 200", which would
+  // false-match a selector that looks for the text "All Chapter".
+  reset();
+  elements = {
+    "h1.entry-title": "All Jobs and Classes I Just Wanted One Skill Not Them All Chapter 200",
+  };
+  attrEls = {
+    "a[aria-label='All Chapter']": {
+      getAttribute: () =>
+        "https://lightnovelworld.net/novel/all-jobs-and-classes-i-just-wanted-one-skill-not-them-all/",
+    },
+  };
+  const url =
+    "https://lightnovelworld.net/all-jobs-and-classes-i-just-wanted-one-skill-not-them-all-chapter-200/";
+  const p = lightnovelworld.detect(loc(url));
+  assert.equal(p.type, "chapter");
+  assert.equal(p.seriesId, "all-jobs-and-classes-i-just-wanted-one-skill-not-them-all");
+  assert.equal(p.title, "All Jobs and Classes I Just Wanted One Skill Not Them All");
+  assert.equal(p.chapterNum, 200);
+  assert.equal(p.chapterSlug, "all-jobs-and-classes-i-just-wanted-one-skill-not-them-all");
+});
+
+test("lightnovelworld.detect resolves both Chapter Slugs of the split novel to one Series", () => {
+  // Research note §4.4: this Series serves chapters 1-99 under one Chapter
+  // Slug and 100-423 under another; both chapter addresses are live and both
+  // point back at the same Series. An old deep link must not get a different
+  // identity than a current one.
+  reset();
+  elements = { "h1.entry-title": "All Jobs and Classes I Just Wanted One Skill Not Chapter 1" };
+  attrEls = {
+    "a[aria-label='All Chapter']": {
+      getAttribute: () =>
+        "https://lightnovelworld.net/novel/all-jobs-and-classes-i-just-wanted-one-skill-not-them-all/",
+    },
+  };
+  const oldSlug = lightnovelworld.detect(
+    loc("https://lightnovelworld.net/all-jobs-and-classes-i-just-wanted-one-skill-not-chapter-1/")
+  );
+  const currentSlug = lightnovelworld.detect(
+    loc(
+      "https://lightnovelworld.net/all-jobs-and-classes-i-just-wanted-one-skill-not-them-all-chapter-404/"
+    )
+  );
+  assert.equal(oldSlug.type, "chapter");
+  assert.equal(oldSlug.seriesId, "all-jobs-and-classes-i-just-wanted-one-skill-not-them-all");
+  assert.equal(oldSlug.chapterSlug, "all-jobs-and-classes-i-just-wanted-one-skill-not");
+  assert.equal(currentSlug.type, "chapter");
+  assert.equal(currentSlug.seriesId, "all-jobs-and-classes-i-just-wanted-one-skill-not-them-all");
+  assert.equal(currentSlug.chapterSlug, "all-jobs-and-classes-i-just-wanted-one-skill-not-them-all");
+});
+
 test("lightnovelworld.detect returns other for non-series paths", () => {
  reset();
  assert.equal(lightnovelworld.detect(loc("https://lightnovelworld.net/")).type, "other");