fix(userscript): read comix titles from document.title, parse kagane volume chapters

comix.to is an SPA whose client router rewrites document.title but never touches the server-rendered og:title. The adapter read og:title, so a bookmark taken after a cold load got the homepage's title ("Comix - Read Comics online for free") and one taken after an in-page hop got the previous series' title. Titles now come from document.title, with the chapter page's " - Ch.<n>" tail stripped. comix also serves no og:image at all, which is why every comix bookmark fell back to the monogram placeholder. The cover is now the img whose alt matches the cleaned title. Both fixes need the page to have finished its client-side route change, and comix fills document.title a beat after the URL changes - later than the nav watcher's 300ms snapshot. The watcher therefore also re-detects when the detect() signature changes, not only when the URL does. kagane reader URLs carry no chapter number, so it comes out of og:title. Volume-numbered series render "<Series> - Volume <v> Chapter <n>" with no episode name, a shape the suffix regex did not match. One unmatched title caused both reported symptoms: the volume tail stayed in the stored title ("SP Baby - Volume 1 Chapter 1"), and chapterNum came back null so no chapter was ever recorded for the series. The regex now takes an optional "Volume <v> " segment. All three page shapes were captured live on 2026-08-08 and are pinned as regression tests in userscript/test/logic.test.js.
2026-08-08 23:03:09 +07:00
parent 2ef769d421
commit e72765df85
3 changed files with 115 additions and 21 deletions
@@ -44,6 +44,25 @@ Guidance for OpenCode (and Claude Code) working under `userscript/`. See root `A
  Encodings (incl. triple-encoded punctuation like `%25252D`) identical
  on /manga/ and /title/ pages, so decode-once seriesIds match — verified
  2026-07-28.
+- **comix.to**: series `/title/<id>-<slug>`, chapter
+  `/title/<id>-<slug>/<uploadId>-chapter-<n>`. Only the leading `<id>` is
+  identity — the slug re-renders when a series is renamed (`comixSeriesId`).
+  An SPA that **never rewrites `og:title`**: the server-rendered head keeps
+  whatever document loaded first, so on a cold load `og:title` is the homepage's
+  "Comix — Read Comics online for free" and after an in-page hop it is the
+  *previous* series' name. `document.title` is the one thing client routing does
+  update, so titles come from there, with the chapter page's `" · Ch.<n>"` tail
+  stripped. Covers likewise: `og:image` is absent, so the cover is the `img`
+  whose `alt` matches the cleaned title — verified live 2026-08-08.
+- **kagane.to**: series `/series/<uuid>`, reader
+  `/series/<uuid>/reader/<bookUuid>`. Reader URLs carry no chapter number, so
+  the number comes out of `og:title`. Two shapes exist: `"<Series> - Chapter
+  <n>[ - Episode <n>]"` and, for volume-numbered series, `"<Series> - Volume <v>
+  Chapter <n>"` with no episode name — both must yield a bare series title, or
+  the volume tail lands in the bookmark's title. Its covers are challenge- and
+  CORP-protected, so the web UI proxies them; the userscript still stores the
+  raw `og:image`. Behind a Cloudflare JS challenge, so the backend polls it
+  through the headless browser.
 - **novelfull.com** (novel script): series `/<slug>.html`, chapter
  `/<slug>/chapter-<n>[-<title-slug>].html`. No `og:*` tags at all — title from
  `h3.title` (series) or `a.truyen-title` (chapter), cover from
@@ -242,6 +242,12 @@
    matches: (loc) => /(^|\.)comix\.to$/.test(loc.hostname),
    detect(loc) {
      const path = loc.pathname;
+      // comix client-routes without ever rewriting og:title — the head keeps
+      // whatever the first server-rendered document carried, so a bookmark
+      // taken after a client route got the homepage's title, then the
+      // previous series'. document.title is the one thing its router does
+      // update. Verified live 2026-08-08; do not "restore" meta("og:title").
+      const pageTitle = cleanTitle(document.title);
      // /title/<id>-<slug>/<uploadId>-chapter-<n>. Several uploads (different
      // groups or languages) share one chapter number; the number is the
      // progress identity, the upload id is not.
@@ -252,8 +258,8 @@
          type: "chapter",
          site: this.site,
          seriesId: comixSeriesId(m[1]),
-          title: cleanTitle(meta("og:title")),
-          cover: coverFromPage(),
+          title: pageTitle,
+          cover: coverFromPage(pageTitle),
          seriesUrl: loc.origin + "/title/" + m[1],
          chapterLabel: "Chapter " + m[2],
          chapterNum: isNaN(num) ? null : num,
@@ -267,8 +273,8 @@
          type: "series",
          site: this.site,
          seriesId: comixSeriesId(m[1]),
-          title: cleanTitle(meta("og:title")),
-          cover: coverFromPage(),
+          title: pageTitle,
+          cover: coverFromPage(pageTitle),
          seriesUrl: loc.origin + "/title/" + m[1],
          chapterLabel: null,
          chapterNum: null,
@@ -277,7 +283,7 @@
      }
      return { type: "other" };

-      // comix chapter og:title is "<Title> · Ch.<n>"; series is clean.
+      // comix chapter document.title is "<Title> · Ch.<n>"; series is clean.
      function cleanTitle(t) {
        if (!t) return "";
        return t.replace(/\s*·\s*Ch\.[\d.]+\s*$/i, "").trim();
@@ -287,8 +293,7 @@
      // the DOM for a cover. Matching on alt rather than a class keeps it off
      // the site's styling: the cover is the image whose alt is the title.
      // Do not "simplify" this into meta("og:image") — that returns null.
-      function coverFromPage() {
-        const title = cleanTitle(meta("og:title"));
+      function coverFromPage(title) {
        if (!title || !document.querySelectorAll) return "";
        for (const img of document.querySelectorAll("img[alt]")) {
          if (img.getAttribute("alt") === title) return img.getAttribute("src") || "";
@@ -313,6 +318,14 @@
    },
  };

+  // Kagane builds the reader og:title suffix out of the book's metadata, so
+  // every combination occurs: the volume part appears only when the book has a
+  // volume_no, the episode part only when it has a non-empty title. All four
+  // shapes captured live 2026-08-08 — "SP Baby - Volume 1 Chapter 1" is the one
+  // the old trailing-space regex missed, which left both the number and the
+  // series title wrong.
+  const KAGANE_CHAPTER_SUFFIX = /\s-\s(?:Volume\s[\d.]+\s)?Chapter\s([\d.]+)(?:\s-\s.*)?$/i;
+
  const kagane = {
    site: "kagane",
    matches: (loc) => /(^|\.)kagane\.to$/.test(loc.hostname),
@@ -353,9 +366,8 @@
      }
      return { type: "other" };

-      // Reader og:title is "<Title> - Chapter <n> - <episode name>".
      function chapterNumFromTitle(t) {
-        const m = t && t.match(/\s-\sChapter\s([\d.]+)\s/);
+        const m = t && t.match(KAGANE_CHAPTER_SUFFIX);
        if (!m) return null;
        const num = parseFloat(m[1]);
        return isNaN(num) ? null : num;
@@ -363,7 +375,7 @@

      function cleanTitle(t) {
        if (!t) return "";
-        return t.replace(/\s-\sChapter\s[\d.]+\s-\s.*$/i, "").trim();
+        return t.replace(KAGANE_CHAPTER_SUFFIX, "").trim();
      }
    },
    // Reader hrefs are uuids with no number in them, so no maximum can be taken
@@ -1450,8 +1462,15 @@
  }

  let lastUrl = location.href;
-  function onNavigate() {
+  let lastPageSig = "";
+
+  function setPage() {
    state.page = detect();
+    lastPageSig = JSON.stringify(state.page);
+  }
+
+  function onNavigate() {
+    setPage();
    render();
    maybeAutoUpdate();
    maybeCaptureLatestOnSeriesPage();
@@ -1484,7 +1503,14 @@
    wrap("pushState");
    wrap("replaceState");
    window.addEventListener("popstate", fire);
-    setInterval(fire, 1500); // catch routes that bypass history
+    // Also catches routes that bypass history — and comix, which fills
+    // document.title a beat after the route changes, so the 300ms snapshot
+    // above can still hold the previous page's title. Re-detect whenever what
+    // we would read has changed, not only when the URL has.
+    setInterval(() => {
+      fire();
+      if (JSON.stringify(detect()) !== lastPageSig) onNavigate();
+    }, 1500);
  }

  // ============================================================
@@ -1563,7 +1589,7 @@

  function init() {
    buildUI();
-    state.page = detect();
+    setPage();
    render();
    installNavWatcher();
    installLongPress();
@@ -31,6 +31,9 @@ globalThis.location = {

 // og: meta tags the adapters read through meta(). Reassigned per test.
 let metaTags = {};
+// document.title. comix's SPA rewrites this on client routing but never
+// og:title, so the comix adapter reads it instead. Reassigned per test.
+let docTitle = "";
 // img[alt] elements comix's coverFromPage() scans. Reassigned per test; each
 // entry is {alt, src}.
 let pageImages = [];
@@ -48,6 +51,9 @@ globalThis.document = {
    }));
  },
  addEventListener() {},
+  get title() {
+    return docTitle;
+  },
  body: undefined,
 };

@@ -193,8 +199,15 @@ test("comixSeriesId leaves a bare id untouched", () => {
  assert.equal(comixSeriesId("n8we"), "n8we");
 });

+// comix is an SPA that rewrites document.title on client routing but leaves the
+// server-rendered og:title untouched, so every test here pins og:title to a
+// STALE value — the homepage title on first hop, the previous series after
+// that. Captured live 2026-08-08.
+const COMIX_STALE_HOME = "Comix - Read Comics online for free";
+
 test("comix detects a series page", () => {
-  metaTags = { "og:title": "Dungeons and Crayons" };
+  metaTags = { "og:title": COMIX_STALE_HOME };
+  docTitle = "Dungeons and Crayons";
  const p = comix.detect(loc("https://comix.to/title/n8we-dungeons-and-crayons"));
  assert.equal(p.type, "series");
  assert.equal(p.site, "comix");
@@ -204,8 +217,16 @@ test("comix detects a series page", () => {
  assert.equal(p.chapterNum, null);
 });

+test("comix ignores a previous series' stale og:title", () => {
+  metaTags = { "og:title": "Full-Time Awakening" };
+  docTitle = "Dungeons and Crayons";
+  const p = comix.detect(loc("https://comix.to/title/n8we-dungeons-and-crayons"));
+  assert.equal(p.title, "Dungeons and Crayons");
+});
+
 test("comix detects a chapter page and strips the Ch. suffix from the title", () => {
-  metaTags = { "og:title": "Dungeons and Crayons · Ch.80" };
+  metaTags = { "og:title": COMIX_STALE_HOME };
+  docTitle = "Dungeons and Crayons · Ch.80";
  const p = comix.detect(
    loc("https://comix.to/title/n8we-dungeons-and-crayons/11139891-chapter-80")
  );
@@ -218,7 +239,8 @@ test("comix detects a chapter page and strips the Ch. suffix from the title", ()
 });

 test("comix parses decimal chapter numbers", () => {
-  metaTags = { "og:title": "Dungeons and Crayons · Ch.80.5" };
+  metaTags = {};
+  docTitle = "Dungeons and Crayons · Ch.80.5";
  const p = comix.detect(
    loc("https://comix.to/title/n8we-dungeons-and-crayons/11139891-chapter-80.5")
  );
@@ -226,19 +248,19 @@ test("comix parses decimal chapter numbers", () => {
 });

 test("comix.detect reads the cover from an img whose alt matches the cleaned title", () => {
-  metaTags = { "og:title": "Dungeons and Crayons · Ch.80" };
+  metaTags = { "og:title": COMIX_STALE_HOME };
+  docTitle = "Dungeons and Crayons";
  pageImages = [
    { alt: "Some Other Series", src: "https://cdn.example/other.jpg" },
    { alt: "Dungeons and Crayons", src: "https://cdn.example/cover.jpg" },
  ];
-  const p = comix.detect(
-    loc("https://comix.to/title/n8we-dungeons-and-crayons/11139891-chapter-80")
-  );
+  const p = comix.detect(loc("https://comix.to/title/n8we-dungeons-and-crayons"));
  assert.equal(p.cover, "https://cdn.example/cover.jpg");
 });

 test("comix.detect leaves cover empty when no img alt matches the title", () => {
-  metaTags = { "og:title": "Dungeons and Crayons" };
+  metaTags = {};
+  docTitle = "Dungeons and Crayons";
  pageImages = [{ alt: "Some Other Series", src: "https://cdn.example/other.jpg" }];
  const p = comix.detect(loc("https://comix.to/title/n8we-dungeons-and-crayons"));
  assert.equal(p.cover, "");
@@ -315,6 +337,33 @@ test("kagane reads the chapter number out of og:title", () => {
  assert.equal(p.seriesUrl, "https://kagane.to/series/" + KAGANE_SERIES);
 });

+// Volume-numbered series render the suffix as "- Volume <v> Chapter <n>" with
+// no episode name, because the book carries volume_no and an empty title.
+// Captured live 2026-08-08 from SP Baby.
+test("kagane reads through a Volume-numbered chapter suffix", () => {
+  metaTags = {
+    "og:title": "SP Baby - Volume 1 Chapter 1",
+    "og:image": "https://kagane.to/api/v2/image/abc/compressed",
+  };
+  const p = kagane.detect(
+    loc("https://kagane.to/series/" + KAGANE_SERIES + "/reader/" + KAGANE_BOOK)
+  );
+  assert.equal(p.title, "SP Baby");
+  assert.equal(p.chapterNum, 1);
+  assert.equal(p.chapterLabel, "Chapter 1");
+});
+
+// A book with neither a volume nor an episode name ends the title right after
+// the number, which the old trailing-\s regex could not match.
+test("kagane reads a chapter suffix with no episode name", () => {
+  metaTags = { "og:title": "Some Series - Chapter 7.5" };
+  const p = kagane.detect(
+    loc("https://kagane.to/series/" + KAGANE_SERIES + "/reader/" + KAGANE_BOOK)
+  );
+  assert.equal(p.title, "Some Series");
+  assert.equal(p.chapterNum, 7.5);
+});
+
 test("kagane yields a null chapterNum when og:title has no chapter", () => {
  metaTags = { "og:title": "Infinite Decryption: The Strongest Level 0" };
  const p = kagane.detect(