rustycms/scripts/normalize-quote-youtube-slugs.mjs

#!/usr/bin/env node
/**
 * Normalisiert quote und youtube_video: _slug und Dateiname = prefix + lesbarer Teil.
 * - quote: quote-{slugify(author)}
 * - youtube_video: youtube-video-{slugify(title)|slugify(id ohne Präfix)|youtubeId}
 * Aktualisiert alle Referenzen in content/de.
 */

import fs from "fs";
import path from "path";
import { fileURLToPath } from "url";

const __dirname = path.dirname(fileURLToPath(import.meta.url));
const CONTENT_DE = path.join(__dirname, "..", "content", "de");

function slugify(value) {
  if (value == null || value === "") return "";
  return String(value)
    .replace(/_/g, "-")
    .replace(/\s+/g, "-")
    .replace(/[^a-zA-Z0-9-]+/g, "-")
    .replace(/-+/g, "-")
    .replace(/^-|-$/g, "")
    .toLowerCase() || "untitled";
}

function stripPrefix(s, prefixes) {
  let t = s || "";
  for (const p of prefixes) {
    if (t.toLowerCase().startsWith(p.toLowerCase())) {
      t = t.slice(p.length).replace(/^-+/, "");
      break;
    }
  }
  return t;
}

function parseJson5(str) {
  try {
    return JSON.parse(str);
  } catch {
    return null;
  }
}

// ─── Quote: prefix + slugify(author) ─────────────────────────────────────
function processQuote(quoteDir) {
  if (!fs.existsSync(quoteDir)) return new Map();
  const files = fs.readdirSync(quoteDir).filter((f) => f.endsWith(".json5")).sort();
  const oldToNew = new Map();
  const used = new Set();

  for (const file of files) {
    const raw = fs.readFileSync(path.join(quoteDir, file), "utf8");
    const data = parseJson5(raw);
    const oldSlug = data?._slug || file.replace(/\.json5$/, "");
    const author = data?.author ?? "";
    const quoteText = data?.quote ?? "";
    let rest = slugify(author) || slugify(quoteText.slice(0, 50)) || "zitat";
    let newSlug = "quote-" + rest;
    let n = 0;
    while (used.has(newSlug)) {
      n++;
      newSlug = "quote-" + rest + (n === 1 ? "-1" : "-" + n);
    }
    used.add(newSlug);
    oldToNew.set(oldSlug, newSlug);
  }

  for (const file of files) {
    const filePath = path.join(quoteDir, file);
    const data = parseJson5(fs.readFileSync(filePath, "utf8"));
    const oldSlug = data?._slug || file.replace(/\.json5$/, "");
    const newSlug = oldToNew.get(oldSlug);
    if (!newSlug) continue;
    data._slug = newSlug;
    const newPath = path.join(quoteDir, newSlug + ".json5");
    fs.writeFileSync(newPath, JSON.stringify(data, null, 2) + "\n", "utf8");
    if (path.basename(newPath) !== file) fs.unlinkSync(filePath);
  }
  return oldToNew;
}

// ─── Youtube_video: prefix + title oder id (ohne Präfix) oder youtubeId ───
const YOUTUBE_ID_PREFIXES = [
  "youtube-video - ",
  "component-youtube-",
  "component-video-",
  "https-www-youtube-com-watch-v-",
  "https-youtu-be-",
];

function processYoutubeVideo(ytDir) {
  if (!fs.existsSync(ytDir)) return new Map();
  const files = fs.readdirSync(ytDir).filter((f) => f.endsWith(".json5")).sort();
  const oldToNew = new Map();
  const used = new Set();

  for (const file of files) {
    const raw = fs.readFileSync(path.join(ytDir, file), "utf8");
    const data = parseJson5(raw);
    const oldSlug = data?._slug || file.replace(/\.json5$/, "");
    const id = data?.id ?? "";
    const title = data?.title ?? "";
    const youtubeId = data?.youtubeId ?? "";
    let rest = slugify(title) || slugify(stripPrefix(id, YOUTUBE_ID_PREFIXES)) || slugify(stripPrefix(oldSlug, YOUTUBE_ID_PREFIXES)) || youtubeId.toLowerCase() || "untitled";
    let newSlug = "youtube-video-" + rest;
    let n = 0;
    while (used.has(newSlug)) {
      n++;
      newSlug = "youtube-video-" + rest + (n === 1 ? "-1" : "-" + n);
    }
    used.add(newSlug);
    oldToNew.set(oldSlug, newSlug);
  }

  for (const file of files) {
    const filePath = path.join(ytDir, file);
    const data = parseJson5(fs.readFileSync(filePath, "utf8"));
    const oldSlug = data?._slug || file.replace(/\.json5$/, "");
    const newSlug = oldToNew.get(oldSlug);
    if (!newSlug) continue;
    data._slug = newSlug;
    if (data.id && data.id === oldSlug) data.id = newSlug;
    const newPath = path.join(ytDir, newSlug + ".json5");
    fs.writeFileSync(newPath, JSON.stringify(data, null, 2) + "\n", "utf8");
    if (path.basename(newPath) !== file) fs.unlinkSync(filePath);
  }
  return oldToNew;
}

// ─── Main ────────────────────────────────────────────────────────────────
const quoteDir = path.join(CONTENT_DE, "quote");
const ytDir = path.join(CONTENT_DE, "youtube_video");

const mapQuote = processQuote(quoteDir);
const mapYoutube = processYoutubeVideo(ytDir);

const allMaps = [mapQuote, mapYoutube];
console.log("quote:", Object.fromEntries(mapQuote));
console.log("youtube_video:", Object.fromEntries(mapYoutube));

function walkDir(dir, fn) {
  const entries = fs.readdirSync(dir, { withFileTypes: true });
  for (const e of entries) {
    const full = path.join(dir, e.name);
    if (e.isDirectory()) walkDir(full, fn);
    else if (e.name.endsWith(".json5")) fn(full);
  }
}

walkDir(CONTENT_DE, (filePath) => {
  let content = fs.readFileSync(filePath, "utf8");
  let changed = false;
  for (const oldToNew of allMaps) {
    for (const [oldSlug, newSlug] of oldToNew) {
      if (oldSlug === newSlug) continue;
      const escaped = oldSlug.replace(/[.*+?^${}()|[\]\\]/g, "\\$&");
      const newContent = content.replace(new RegExp('"' + escaped + '"', "g"), '"' + newSlug + '"');
      if (newContent !== content) {
        content = newContent;
        changed = true;
      }
    }
  }
  if (changed) fs.writeFileSync(filePath, content, "utf8");
});

console.log("Fertig. Quote- und youtube-video-Slugs normalisiert und Referenzen aktualisiert.");