#!/usr/bin/env node
// Regenerate the import fixture corpus (issue #63, ADR 0009) from the committed
// `*.src.html` sources: for each source, write `<name>.docx`, `<name>.odt`, and
// the expected Markdown snapshot for each format. Run against a reachable pandoc
// sidecar (the pinned `pandoc/core:3.6`, so snapshots match CI):
//
//   docker run --rm -p 3030:3030 pandoc/core:3.6 server
//   PANDOC_URL=http://localhost:3030 node scripts/gen-import-fixtures.mjs
//
// The pipeline mirrors ImportService: `html → <ext>` builds the document, then
// `<ext> → html` (embed-resources) → `html → gfm` reproduces what an import
// would parse, with image data URIs normalised to a stable token.

import { readFileSync, writeFileSync, readdirSync } from 'node:fs';
import { fileURLToPath } from 'node:url';
import { dirname, join } from 'node:path';

const FIXTURES = join(dirname(fileURLToPath(import.meta.url)), '..', 'fixtures', 'import');
const PANDOC_URL = process.env.PANDOC_URL ?? 'http://localhost:3030';
const MARKDOWN_FORMAT = 'gfm-implicit_figures-raw_html';

/** POST a conversion to pandoc-server. Without an `Accept` header the server
 * returns text for text writers and raw bytes for binary ones (docx/odt). */
async function pandoc(params, binaryOut = false) {
  const res = await fetch(`${PANDOC_URL}/`, {
    method: 'POST',
    headers: { 'Content-Type': 'application/json' },
    body: JSON.stringify(params),
  });
  if (!res.ok) throw new Error(`pandoc ${res.status}: ${await res.text()}`);
  return binaryOut ? Buffer.from(await res.arrayBuffer()) : res.text();
}

async function buildDocument(html, ext) {
  return pandoc({ text: html, from: 'html', to: ext, standalone: true }, true);
}

async function toExpectedMarkdown(documentBytes, ext) {
  const embedded = await pandoc({
    text: documentBytes.toString('base64'),
    from: ext,
    to: 'html',
    standalone: false,
    'embed-resources': true,
  });
  const md = await pandoc({
    text: embedded,
    from: 'html',
    to: MARKDOWN_FORMAT,
    standalone: false,
    wrap: 'none',
  });
  return md.replace(/data:image\/[a-zA-Z0-9.+-]+;base64,[A-Za-z0-9+/=]+/g, 'data:embedded-image');
}

const sources = readdirSync(FIXTURES).filter((f) => f.endsWith('.src.html'));
for (const source of sources) {
  const name = source.replace(/\.src\.html$/, '');
  const html = readFileSync(join(FIXTURES, source), 'utf8');
  for (const ext of ['docx', 'odt']) {
    const bytes = await buildDocument(html, ext);
    writeFileSync(join(FIXTURES, `${name}.${ext}`), bytes);
    writeFileSync(
      join(FIXTURES, `${name}.${ext}.expected.md`),
      await toExpectedMarkdown(bytes, ext),
    );
    console.log(`wrote ${name}.${ext} (+ expected.md)`);
  }
}