// The document `content` union member: Ghost post HTML → at.markpub.markdown.
// site.standard.document's content union is open (`closed: false`), so the
// member needs no lexicon registration — but a shared $type is a shared
// contract: at.markpub.markdown (markpub.at, AramZS) is a community lexicon
// for markdown-in-a-union that standard.site viewers understand. The markdown
// here is *derived* from Ghost's HTML (Ghost emits html/lexical/plaintext,
// never markdown), which is why `renderingRules` is omitted: nothing ever
// renders our pages from it.
// Design: docs/superpowers/specs/2026-07-06-markpub-content-design.md

import TurndownService from 'turndown';
import { gfm } from 'turndown-plugin-gfm';

export const MARKPUB_MARKDOWN_TYPE = 'at.markpub.markdown';

const turndown = new TurndownService({
  headingStyle:   'atx',
  codeBlockStyle: 'fenced',
});
turndown.use(gfm);

// Ghost wraps every editor card in <figure class="kg-card kg-*-card">. Only
// captioned images need a rule (the defaults would smear the figcaption into
// the surrounding text); every other card type degrades through the generic
// rules — bookmark cards to links, embed iframes to nothing.
turndown.addRule('kgImageCard', {
  filter: (node) =>
    node.nodeName === 'FIGURE' &&
    /\bkg-image-card\b/.test(node.getAttribute('class') ?? ''),
  replacement: (_content, node) => {
    const img = node.querySelector('img');
    if (!img) return '';
    const image   = `![${img.getAttribute('alt') ?? ''}](${img.getAttribute('src') ?? ''})`;
    // Caption text is not markdown-escaped — a caption containing * or _ may
    // render with stray emphasis; accepted degradation.
    const caption = node.querySelector('figcaption')?.textContent?.trim();
    return caption ? `\n\n${image}\n\n*${caption}*\n\n` : `\n\n${image}\n\n`;
  },
});

/**
 * Record-ready `content` union member for a post body, or null when there is
 * nothing to say: empty HTML, HTML that converts to empty markdown (e.g. an
 * embed-only post), or a converter throw. Null means the record simply omits
 * `content` — a conversion bug must never fail a sync.
 */
export function buildMarkpubContent(html: string): Record<string, unknown> | null {
  if (!html.trim()) return null;

  let markdown: string;
  try {
    markdown = turndown.turndown(html);
  } catch (err) {
    console.error('  markdown conversion failed, omitting content:', (err as Error).message);
    return null;
  }
  if (!markdown.trim()) return null;

  return {
    $type:  MARKPUB_MARKDOWN_TYPE,
    text:   { markdown },
    flavor: 'gfm',
  };
}