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 +1,77 @@
+import { describe, it, expect, beforeAll, afterAll } from 'vitest';
+import fs from 'node:fs/promises';
+import path from 'node:path';
+import os from 'node:os';
+import { Document, Paragraph, TextRun, Packer } from 'docx';
+import { registerDocumentConverters } from '../../src/converters/document.js';
+import { resolve } from '../../src/converters/registry.js';
+import { detectInputMime } from '../../src/mime.js';
+
+let tmpDir;
+let docxFixturePath;
+
+beforeAll(async () => {
+  registerDocumentConverters();
+  tmpDir = await fs.mkdtemp(path.join(os.tmpdir(), 'converter-document-'));
+
+  const doc = new Document({
+    sections: [
+      {
+        children: [new Paragraph({ children: [new TextRun('Hello from the fixture document')] })],
+      },
+    ],
+  });
+  const buffer = await Packer.toBuffer(doc);
+  docxFixturePath = path.join(tmpDir, 'fixture.docx');
+  await fs.writeFile(docxFixturePath, buffer);
+});
+
+afterAll(async () => {
+  await fs.rm(tmpDir, { recursive: true, force: true });
+});
+
+describe('document converters', () => {
+  it('converts DOCX to HTML containing the source text', async () => {
+    const outputPath = path.join(tmpDir, 'output.html');
+    const entry = resolve('docx', 'html');
+
+    await entry.convert(docxFixturePath, outputPath);
+
+    const html = await fs.readFile(outputPath, 'utf8');
+    expect(html).toContain('Hello from the fixture document');
+  }, 20000);
+
+  it('converts TXT to a valid PDF', async () => {
+    const inputPath = path.join(tmpDir, 'fixture.txt');
+    await fs.writeFile(inputPath, 'Plain text content for the PDF');
+    const outputPath = path.join(tmpDir, 'from-txt.pdf');
+    const entry = resolve('txt', 'pdf');
+
+    await entry.convert(inputPath, outputPath);
+
+    const detected = await detectInputMime(outputPath);
+    expect(detected.mime).toBe('application/pdf');
+  }, 20000);
+
+  it('converts HTML to a valid PDF', async () => {
+    const inputPath = path.join(tmpDir, 'fixture.html');
+    await fs.writeFile(inputPath, '<html><body><h1>Hello HTML</h1></body></html>');
+    const outputPath = path.join(tmpDir, 'from-html.pdf');
+    const entry = resolve('html', 'pdf');
+
+    await entry.convert(inputPath, outputPath);
+
+    const detected = await detectInputMime(outputPath);
+    expect(detected.mime).toBe('application/pdf');
+  }, 20000);
+
+  it('converts DOCX to a valid PDF', async () => {
+    const outputPath = path.join(tmpDir, 'from-docx.pdf');
+    const entry = resolve('docx', 'pdf');
+
+    await entry.convert(docxFixturePath, outputPath);
+
+    const detected = await detectInputMime(outputPath);
+    expect(detected.mime).toBe('application/pdf');
+  }, 20000);
+});