feat: add DOCX/TXT/HTML document converters

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
2026-07-30 09:10:34 +02:00
parent a049be2fc8
commit 16b4f28b42
2 changed files with 127 additions and 0 deletions
@@ -0,0 +1,50 @@
+import fs from 'node:fs/promises';
+import mammoth from 'mammoth';
+import puppeteer from 'puppeteer';
+import { register } from './registry.js';
+
+async function renderHtmlToPdf(html, outputPath) {
+  const browser = await puppeteer.launch({
+    headless: true,
+    args: ['--no-sandbox', '--disable-setuid-sandbox'],
+  });
+  try {
+    const page = await browser.newPage();
+    await page.setContent(html, { waitUntil: 'networkidle0' });
+    await page.pdf({ path: outputPath, format: 'A4', printBackground: true });
+  } finally {
+    await browser.close();
+  }
+}
+
+function escapeHtml(text) {
+  return text.replace(/&/g, '&amp;').replace(/</g, '&lt;').replace(/>/g, '&gt;');
+}
+
+async function convertDocxToHtml(inputPath, outputPath) {
+  const result = await mammoth.convertToHtml({ path: inputPath });
+  await fs.writeFile(outputPath, result.value);
+}
+
+async function convertTxtToPdf(inputPath, outputPath) {
+  const text = await fs.readFile(inputPath, 'utf8');
+  const html = `<html><body><pre>${escapeHtml(text)}</pre></body></html>`;
+  await renderHtmlToPdf(html, outputPath);
+}
+
+async function convertHtmlToPdf(inputPath, outputPath) {
+  const html = await fs.readFile(inputPath, 'utf8');
+  await renderHtmlToPdf(html, outputPath);
+}
+
+async function convertDocxToPdf(inputPath, outputPath) {
+  const result = await mammoth.convertToHtml({ path: inputPath });
+  await renderHtmlToPdf(result.value, outputPath);
+}
+
+export function registerDocumentConverters() {
+  register({ family: 'document', sourceFormat: 'docx', targetFormat: 'html', convert: convertDocxToHtml });
+  register({ family: 'document', sourceFormat: 'txt', targetFormat: 'pdf', convert: convertTxtToPdf });
+  register({ family: 'document', sourceFormat: 'html', targetFormat: 'pdf', convert: convertHtmlToPdf });
+  register({ family: 'document', sourceFormat: 'docx', targetFormat: 'pdf', convert: convertDocxToPdf });
+}