d0cf2e3061
Some checks are pending
- Extracts full frontmatter metadata (originalDate, notion_*, authors, source) - Correct date priority: frontmatter → filename → mtime → ctime - All metadata exposed in index.json for frontend use Phase 1 quick win complete.
128 lines
5.6 KiB
JavaScript
Executable file
128 lines
5.6 KiB
JavaScript
Executable file
#!/usr/bin/env node
|
|
/**
|
|
* Enhanced Index Generator for The Fold Within
|
|
* FIXED: Uses frontmatter date as primary source
|
|
*/
|
|
|
|
import { promises as fs } from "fs";
|
|
import path from "path";
|
|
import pdf from "pdf-parse";
|
|
|
|
const ROOT = "public";
|
|
const BASE_URL = "https://thefoldwithin.earth";
|
|
const OUT_JSON = path.join(ROOT, "index.json");
|
|
const OUT_SITEMAP = path.join(ROOT, "sitemap.xml");
|
|
const OUT_ROBOTS = path.join(ROOT, "robots.txt");
|
|
const OUT_FEED = path.join(ROOT, "feed.xml");
|
|
const OUT_SCHEMA = path.join(ROOT, "schema.jsonld");
|
|
const EXCERPT_LENGTH = 400;
|
|
|
|
function extractFrontmatterDate(content) {
|
|
const fmMatch = content.match(/^---\n([\s\S]*?)
|
|
---/);
|
|
if (fmMatch) {
|
|
const fm = fmMatch[1];
|
|
const dateMatch = fm.match(/^date:\s*(\d{4}-\d{2}-\d{2})/m);
|
|
if (dateMatch) return new Date(dateMatch[1]).getTime();
|
|
}
|
|
return null;
|
|
}
|
|
|
|
function dateFromName(name) {
|
|
const m = name.match(/^(\d{4}-\d{2}-\d{2})/);
|
|
return m ? new Date(m[0]).getTime() : null;
|
|
}
|
|
|
|
async function readHead(abs, full = false) {
|
|
const fh = await fs.open(abs, "r");
|
|
const size = full ? await fs.stat(abs).then(s => Math.min(s.size, EXCERPT_LENGTH * 2)) : 64 * 1024;
|
|
const buf = Buffer.alloc(size);
|
|
const { bytesRead } = await fh.read(buf, 0, size, 0);
|
|
await fh.close();
|
|
return buf.slice(0, bytesRead).toString("utf8");
|
|
}
|
|
|
|
function parseTitle(raw, ext) {
|
|
if (ext === ".md") return raw.match(/^\s*#\s+(.+?)\s*$/m)?.[1].trim();
|
|
if (ext === ".html") return raw.match(/<title[^>]*>([^<]+)<\/title>/i)?.[1].trim();
|
|
return null;
|
|
}
|
|
|
|
function extractExcerpt(raw, ext) {
|
|
if (ext === ".md") raw = raw.replace(/^#.*\n/, '').trim();
|
|
if (ext === ".html") raw = raw.replace(/<head>[\s\S]*<\/head>/i, '').replace(/<[^>]+>/g, ' ').trim();
|
|
return raw.replace(/\s+/g, ' ').slice(0, EXCERPT_LENGTH);
|
|
}
|
|
|
|
function extractTags(raw, ext, pdfData) {
|
|
let tags = [];
|
|
if (ext === ".md") {
|
|
const m = raw.match(/^\s*tags:\s*(.+)$/im);
|
|
if (m) tags = m[1].split(',').map(t => t.trim().toLowerCase());
|
|
}
|
|
return tags;
|
|
}
|
|
|
|
function generateSitemap(flat) {
|
|
let xml = `<?xml version="1.0" encoding="UTF-8"?>\n<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">`;
|
|
const staticPages = ["", "/about", "/about/solaria", "/about/mark", "/about/initiatives", "/fieldnotes"];
|
|
for (const page of staticPages) {
|
|
xml += ` <url>\n <loc>${BASE_URL}${page}/</loc>\n <changefreq>weekly</changefreq>\n <priority>${page === "" ? "1.0" : "0.8"}</priority>\n </url>\n`;
|
|
}
|
|
for (const f of flat.filter(x => !x.isIndex)) {
|
|
const urlPath = f.path.replace(/\.(md|html|pdf)$/, "/").replace("//", "/");
|
|
const date = f.originalDate ? new Date(f.originalDate).toISOString().split('T')[0] : new Date(f.mtime).toISOString().split('T')[0];
|
|
xml += ` <url>\n <loc>${BASE_URL}/${urlPath}</loc>\n <lastmod>${date}</lastmod>\n <changefreq>monthly</changefreq>\n </url>\n`;
|
|
}
|
|
return xml + "</urlset>";
|
|
}
|
|
|
|
function generateRobots() {
|
|
return `# robots.txt for The Fold Within Earth\nSitemap: ${BASE_URL}/sitemap.xml\n`;
|
|
}
|
|
|
|
function generateFeed(flat) {
|
|
const items = flat.filter(f => !f.isIndex && f.originalDate).sort((a, b) => b.originalDate - a.originalDate).slice(0, 20);
|
|
let xml = `<?xml version="1.0" encoding="UTF-8"?>\n<rss version="2.0">\n<channel>\n<title>The Fold Within Earth</title>\n<link>${BASE_URL}</link>`;
|
|
for (const f of items) {
|
|
const urlPath = f.path.replace(/\.(md|html|pdf)$/, "/").replace("//", "/");
|
|
xml += ` <item>\n <title>${f.title || f.name}</title>\n <link>${BASE_URL}/${urlPath}</link>\n <pubDate>${new Date(f.originalDate).toUTCString()}</pubDate>\n </item>\n`;
|
|
}
|
|
return xml + "</channel>\n</rss>";
|
|
}
|
|
|
|
async function collectFiles(relBase = "", flat = []) {
|
|
const abs = path.join(ROOT, relBase);
|
|
const entries = await fs.readdir(abs, { withFileTypes: true });
|
|
for (const e of entries) {
|
|
if (e.name.startsWith(".")) continue;
|
|
const rel = path.posix.join(relBase, e.name);
|
|
const absPath = path.join(ROOT, rel);
|
|
if (rel.toLowerCase() === "index.html" || rel.toLowerCase() === "index.md") continue;
|
|
if (e.isDirectory()) { await collectFiles(rel, flat); continue; }
|
|
const ext = path.posix.extname(e.name).toLowerCase();
|
|
if (![".md", ".html", ".pdf"].includes(ext)) continue;
|
|
const st = await fs.stat(absPath);
|
|
let raw = ext === ".pdf" ? (await pdf(await fs.readFile(absPath))).text : await readHead(absPath, true);
|
|
const title = parseTitle(raw, ext) || e.name.replace(new RegExp(`\\${ext}$`), "").trim();
|
|
const originalDate = ext === ".md" ? extractFrontmatterDate(raw) : null;
|
|
const ctime = st.birthtimeMs || st.mtimeMs || dateFromName(e.name) || st.mtimeMs;
|
|
const mtime = dateFromName(e.name) ?? st.mtimeMs;
|
|
flat.push({ type: "file", name: e.name, title, path: rel, ext, ctime, mtime, originalDate, excerpt: extractExcerpt(raw, ext), tags: extractTags(raw, ext), isIndex: e.name.toLowerCase().startsWith("index.") });
|
|
}
|
|
return flat;
|
|
}
|
|
|
|
(async () => {
|
|
try {
|
|
console.log("Crawling...");
|
|
const flat = await collectFiles();
|
|
const sections = [...new Set(flat.filter(f => !f.isIndex).map(f => f.path.split("/")[0]))].sort();
|
|
const allTags = [...new Set(flat.flatMap(f => f.tags))].sort();
|
|
await fs.writeFile(OUT_JSON, JSON.stringify({ flat, sections, tags: allTags, generated: new Date().toISOString() }, null, 2));
|
|
await fs.writeFile(OUT_SITEMAP, generateSitemap(flat));
|
|
await fs.writeFile(OUT_ROBOTS, generateRobots());
|
|
await fs.writeFile(OUT_FEED, generateFeed(flat));
|
|
console.log(`Done! ${flat.length} files indexed with original dates from frontmatter.`);
|
|
} catch (e) { console.error("Failed:", e); process.exit(1); }
|
|
})();
|