MaashkinoozheandClaude Opus 5.5
e0dacd81c6
- Chapter rows show when you first finished a chapter (setting: date + hour, date, off) from a new durable progress doneAt; older reads fall back to the reading clock's earliest remembered completion. - chapter.json keeps added (arrival in this library, now kept on replace) plus x-dates.source (source upload, bulk imports flagged), x-dates.release (official, for a later metadata job) and x-dates.ecosystem (first entry into any Manga Circus library; carried over peering, earliest wins, clamped). - Rows show one release date by tier: official > source upload > ecosystem > library, with all known dates in the tooltip (setting to hide). - Fixes: WeebCentral dates came from the chapter page, which has none (every chapter got the download time); they now come from the full chapter list. MangaDex no longer writes a group's publishAt into added. Peering sends dates. - tools/backfill-chapter-dates.js migrates an existing library (dry run default). - Coverage dry run on the server: docs/chapter-dates-coverage-2026-10-24.md. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
66 lines
3.3 KiB
JavaScript
66 lines
3.3 KiB
JavaScript
'use strict';
|
|
const { volumeKey } = require('../../chapter-identity');
|
|
const { batchFlags } = require('../../chapter-dates');
|
|
|
|
// First-party, pure parsing functions. This module never fetches remote content.
|
|
const decode = value => value.replace(/&/g, '&').replace(/'/g, "'").replace(/"/g, '"').replace(/<[^>]+>/g, '').trim();
|
|
const absolute = (base, value) => new URL(value, base).href;
|
|
|
|
function series({ html, url }) {
|
|
const title = decode(html.match(/<h1\b[^>]*>([\s\S]*?)<\/h1>/i)?.[1] || 'Untitled');
|
|
const listUrl = html.match(/hx-get="([^"]+\/full-chapter-list)"/i)?.[1];
|
|
return { title, listUrl: listUrl ? absolute(url, listUrl) : null };
|
|
}
|
|
|
|
function catalog({ html, url }) {
|
|
const found = [];
|
|
const re = /<a\b[^>]*href="([^"]*\/chapters\/([A-Z0-9]+)[^"]*)"[^>]*>([\s\S]*?)<\/a>/gi;
|
|
for (const match of html.matchAll(re)) {
|
|
const text = decode(match[3]).replace(/\s+/g, ' ');
|
|
const season = Number(text.match(/^S(\d+)\s*-/i)?.[1] || 0) || null;
|
|
const regular = text.match(/\b(?:Chapter|Rating|Episode|Night|Log|Act|Scene|Kapitel|File|Battle)\s*[.:]?\s*([0-9]+(?:\.[0-9]+)?)/i)?.[1];
|
|
const volume = !regular ? text.match(/^Volume\s+([0-9]+(?:\.[0-9]+)?)(?!\d)/i)?.[1] : null;
|
|
const prologue = text.match(/Prologue(?:\s+([0-9]+))?/i)?.[1];
|
|
const number = regular || (prologue ? `0.${prologue.padStart(2, '0')}` : /Prologue/i.test(text) ? '0' : null);
|
|
// The full chapter list carries each upload time; the chapter page itself has none.
|
|
const uploaded = match[3].match(/datetime="([^"]+)"/i)?.[1];
|
|
const uploadedAt = uploaded && Number.isFinite(Date.parse(uploaded)) ? uploaded : undefined;
|
|
if (number) found.push({
|
|
id: match[2], number, title: regular ? '' : `Prologue ${prologue || ''}`.trim(),
|
|
...(season ? { book: { number: season, title: `Season ${season}` } } : {}),
|
|
url: absolute(url, match[1]), raw: text, ...(uploadedAt ? { uploadedAt } : {}),
|
|
});
|
|
else if (volume) found.push({
|
|
id: match[2], number: volumeKey(match[2]), title: '', special: true,
|
|
label: `Volume ${volume}`, releaseKind: 'volume', volume,
|
|
book: { number: Number(volume), title: `Volume ${volume}` },
|
|
url: absolute(url, match[1]), raw: text, ...(uploadedAt ? { uploadedAt } : {}),
|
|
});
|
|
}
|
|
const chapters = [...new Map(found.map(chapter => [chapter.id, chapter])).values()];
|
|
// Back-catalog chapters were imported together; their upload time is not a release date.
|
|
batchFlags(chapters.map(chapter => chapter.uploadedAt)).forEach((batch, index) => {
|
|
if (batch !== null) chapters[index].uploadBatch = batch;
|
|
});
|
|
const chapterLinks = [...html.matchAll(/<a\b[^>]*href="[^"]*\/chapters\/[A-Z0-9]+[^"]*"/gi)].length;
|
|
return { chapters, chapterLinks };
|
|
}
|
|
|
|
function chapter({ html, url }) {
|
|
return {
|
|
manifestUrl: html.match(/['"](https?:\/\/weebcentral\.com\/chapters\/[^'"]+\/images\?is_prev=[^'"]+)['"]/i)?.[1]
|
|
|| `${url}/images?is_prev=False`,
|
|
};
|
|
}
|
|
|
|
function pages({ html, url }) {
|
|
const urls = [];
|
|
for (const match of html.matchAll(/<img\b[^>]*(?:src|data-src)="([^"]+)"/gi)) {
|
|
const pageUrl = absolute(url, match[1].replace(/&/g, '&'));
|
|
if (!pageUrl.startsWith('data:')) urls.push(pageUrl);
|
|
}
|
|
return { pages: [...new Set(urls)] };
|
|
}
|
|
|
|
module.exports = { series, catalog, chapter, pages };
|