dorfteich/apps/api/scripts/gen-classified-reference-docs.mjs

/**
 * Regenerate the classified reference documents (issue #209, ADR 0022):
 * `apps/api/assets/reference-vs-nfd.docx` / `.odt`.
 *
 * The DOCX/ODT export of a classified page passes these to pandoc via
 * `--reference-doc`; pandoc copies the reference's page setup — including
 * headers and footers — into its output, which is how the VS-NfD marking
 * repeats on every page in Word and LibreOffice without being deletable
 * body text.
 *
 * The binaries are DERIVED files: base = the default reference documents of
 * the PINNED pandoc (`pandoc/core:3.6`, the exact sidecar the stages run),
 * plus a header and footer carrying the marking. Never edit the binaries by
 * hand — edit this script and re-run it (Docker required):
 *
 *   node apps/api/scripts/gen-classified-reference-docs.mjs
 *
 * The marking wording comes from @dorfteich/shared (single source, ADR
 * 0022); the shared package must be built (`pnpm --filter @dorfteich/shared
 * build`).
 */
import { execFileSync } from 'node:child_process';
import { mkdirSync, writeFileSync } from 'node:fs';
import { dirname, join } from 'node:path';
import { fileURLToPath } from 'node:url';

import { classificationMarking } from '@dorfteich/shared';
import { strToU8, strFromU8, unzipSync, zipSync } from 'fflate';

const PANDOC_IMAGE = 'pandoc/core:3.6';
const MARKING = classificationMarking('vs_nfd');
const outDir = join(dirname(fileURLToPath(import.meta.url)), '../assets');

function defaultReference(name) {
  return execFileSync('docker', ['run', '--rm', PANDOC_IMAGE, '--print-default-data-file', name], {
    maxBuffer: 64 * 1024 * 1024,
  });
}

function escapeXml(value) {
  return value.replace(/&/g, '&amp;').replace(/</g, '&lt;').replace(/>/g, '&gt;');
}

/** DOCX: add word/header1.xml + word/footer1.xml, register them in the
 * content types and document relationships, and reference them from the
 * document's sectPr — Word repeats them on every page. */
function patchDocx(bytes) {
  const zip = unzipSync(new Uint8Array(bytes));
  const marking = escapeXml(MARKING);

  const partXml = (root) =>
    `<?xml version="1.0" encoding="UTF-8" standalone="yes"?>\n` +
    `<w:${root} xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main">` +
    `<w:p><w:pPr><w:jc w:val="center"/></w:pPr>` +
    `<w:r><w:rPr><w:b/></w:rPr><w:t xml:space="preserve">${marking}</w:t></w:r>` +
    `</w:p></w:${root}>`;
  zip['word/header1.xml'] = strToU8(partXml('hdr'));
  zip['word/footer1.xml'] = strToU8(partXml('ftr'));

  const types = strFromU8(zip['[Content_Types].xml']);
  zip['[Content_Types].xml'] = strToU8(
    types.replace(
      '</Types>',
      '<Override PartName="/word/header1.xml" ContentType="application/vnd.openxmlformats-officedocument.wordprocessingml.header+xml" />' +
        '<Override PartName="/word/footer1.xml" ContentType="application/vnd.openxmlformats-officedocument.wordprocessingml.footer+xml" />' +
        '</Types>',
    ),
  );

  const rels = strFromU8(zip['word/_rels/document.xml.rels']);
  zip['word/_rels/document.xml.rels'] = strToU8(
    rels.replace(
      '</Relationships>',
      '<Relationship Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/header" Id="rIdVsNfdHeader" Target="header1.xml" />' +
        '<Relationship Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/footer" Id="rIdVsNfdFooter" Target="footer1.xml" />' +
        '</Relationships>',
    ),
  );

  const doc = strFromU8(zip['word/document.xml']);
  if (!doc.includes('<w:sectPr>')) throw new Error('reference.docx has no sectPr');
  zip['word/document.xml'] = strToU8(
    doc.replace(
      '<w:sectPr>',
      '<w:sectPr>' +
        '<w:headerReference xmlns:r="http://schemas.openxmlformats.org/officeDocument/2006/relationships" w:type="default" r:id="rIdVsNfdHeader" />' +
        '<w:footerReference xmlns:r="http://schemas.openxmlformats.org/officeDocument/2006/relationships" w:type="default" r:id="rIdVsNfdFooter" />',
    ),
  );

  return zipSync(zip);
}

/** ODT: give the Standard master page a header with the marking and put the
 * marking next to the existing page number in its footer — LibreOffice
 * repeats master-page headers/footers on every page. */
function patchOdt(bytes) {
  const zip = unzipSync(new Uint8Array(bytes));
  const marking = escapeXml(MARKING);
  const styles = strFromU8(zip['styles.xml']);
  if (!styles.includes('<style:footer>')) throw new Error('reference.odt has no footer');
  const patched = styles
    .replace(
      '<style:footer>',
      `<style:header><text:p text:style-name="MP1">${marking}</text:p></style:header><style:footer>`,
    )
    .replace(
      '<style:footer>\n        <text:p text:style-name="MP1">',
      `<style:footer>\n        <text:p text:style-name="MP1">${marking} · `,
    );
  zip['styles.xml'] = strToU8(patched);
  return zipSync(zip);
}

mkdirSync(outDir, { recursive: true });
writeFileSync(join(outDir, 'reference-vs-nfd.docx'), patchDocx(defaultReference('reference.docx')));
writeFileSync(join(outDir, 'reference-vs-nfd.odt'), patchOdt(defaultReference('reference.odt')));
console.log(`generated reference-vs-nfd.docx/.odt in ${outDir} (marking: ${MARKING})`);