feat: add md<->docx document converters

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

src/converters/document.js

@@ -64,6 +64,118 @@ async function convertMdToPdf(inputPath, outputPath) {
   await renderHtmlToPdf(html, outputPath);
 }
 
+const MARKDOWN_HEADING_LEVELS = {
+  h1: HeadingLevel.HEADING_1,
+  h2: HeadingLevel.HEADING_2,
+  h3: HeadingLevel.HEADING_3,
+  h4: HeadingLevel.HEADING_4,
+  h5: HeadingLevel.HEADING_5,
+  h6: HeadingLevel.HEADING_6,
+};
+
+function markdownInlineTokensToRuns(children) {
+  const runs = [];
+  let bold = false;
+  let italics = false;
+  for (const token of children ?? []) {
+    if (token.type === 'strong_open') bold = true;
+    else if (token.type === 'strong_close') bold = false;
+    else if (token.type === 'em_open') italics = true;
+    else if (token.type === 'em_close') italics = false;
+    else if (token.type === 'text' || token.type === 'code_inline') {
+      if (token.content) runs.push(new TextRun({ text: token.content, bold, italics }));
+    } else if (token.type === 'softbreak' || token.type === 'hardbreak') {
+      runs.push(new TextRun({ text: ' ' }));
+    }
+  }
+  return runs;
+}
+
+function markdownToDocxParagraphs(markdownText) {
+  const tokens = new MarkdownIt().parse(markdownText, {});
+  const paragraphs = [];
+  const listStack = [];
+
+  for (let i = 0; i < tokens.length; i += 1) {
+    const token = tokens[i];
+
+    if (token.type === 'heading_open') {
+      const inline = tokens[i + 1];
+      paragraphs.push(
+        new Paragraph({
+          heading: MARKDOWN_HEADING_LEVELS[token.tag],
+          children: markdownInlineTokensToRuns(inline.children),
+        })
+      );
+      i += 2;
+      continue;
+    }
+
+    if (token.type === 'bullet_list_open') {
+      listStack.push({ type: 'bullet' });
+      continue;
+    }
+    if (token.type === 'ordered_list_open') {
+      listStack.push({ type: 'ordered', counter: 0 });
+      continue;
+    }
+    if (token.type === 'bullet_list_close' || token.type === 'ordered_list_close') {
+      listStack.pop();
+      continue;
+    }
+    if (token.type === 'list_item_open') {
+      const current = listStack[listStack.length - 1];
+      if (current?.type === 'ordered') current.counter += 1;
+      continue;
+    }
+    if (token.type === 'list_item_close') {
+      continue;
+    }
+
+    if (token.type === 'paragraph_open') {
+      const inline = tokens[i + 1];
+      const runs = markdownInlineTokensToRuns(inline.children);
+      const current = listStack[listStack.length - 1];
+      if (current?.type === 'bullet') {
+        paragraphs.push(new Paragraph({ children: runs, bullet: { level: listStack.length - 1 } }));
+      } else if (current?.type === 'ordered') {
+        paragraphs.push(
+          new Paragraph({ children: [new TextRun({ text: `${current.counter}. ` }), ...runs] })
+        );
+      } else {
+        paragraphs.push(new Paragraph({ children: runs }));
+      }
+      i += 2;
+      continue;
+    }
+
+    if (token.type === 'fence' || token.type === 'code_block') {
+      if (token.content.trim()) paragraphs.push(new Paragraph({ children: [new TextRun({ text: token.content })] }));
+      continue;
+    }
+
+    if (token.type === 'hr') {
+      paragraphs.push(new Paragraph({ children: [new TextRun({ text: '---' })] }));
+    }
+  }
+
+  return paragraphs;
+}
+
+async function convertDocxToMd(inputPath, outputPath) {
+  const result = await mammoth.convertToHtml({ path: inputPath });
+  const markdown = new TurndownService({ headingStyle: 'atx' }).turndown(result.value);
+  await fs.writeFile(outputPath, markdown);
+}
+
+async function convertMdToDocx(inputPath, outputPath) {
+  const markdown = await fs.readFile(inputPath, 'utf8');
+  const paragraphs = markdownToDocxParagraphs(markdown);
+  const doc = new Document({ sections: [{ children: paragraphs }] });
+  const buffer = await Packer.toBuffer(doc);
+  await fs.writeFile(outputPath, buffer);
+}
+
 async function extractPdfPageTexts(inputPath) {
   const data = new Uint8Array(await fs.readFile(inputPath));
   const doc = await pdfjsLib.getDocument({ data }).promise;
@@ -109,6 +221,8 @@ export function registerDocumentConverters() {
   register({ family: 'document', sourceFormat: 'html', targetFormat: 'md', convert: convertHtmlToMd });
   register({ family: 'document', sourceFormat: 'md', targetFormat: 'pdf', convert: convertMdToPdf });
   register({ family: 'document', sourceFormat: 'pdf', targetFormat: 'md', convert: convertPdfToTxt });
+  register({ family: 'document', sourceFormat: 'docx', targetFormat: 'md', convert: convertDocxToMd });
+  register({ family: 'document', sourceFormat: 'md', targetFormat: 'docx', convert: convertMdToDocx });
   register({ family: 'document', sourceFormat: 'docx', targetFormat: 'pdf', convert: convertDocxToPdf });
   register({ family: 'document', sourceFormat: 'pdf', targetFormat: 'txt', convert: convertPdfToTxt });
   register({ family: 'document', sourceFormat: 'pdf', targetFormat: 'html', convert: convertPdfToHtml });

test/converters/document.test.js

@@ -112,4 +112,33 @@ describe('document converters', () => {
     const detected = await detectInputMime(outputPath);
     expect(detected.mime).toBe('application/pdf');
   }, 20000);
+
+  it('converts DOCX to MD containing the source text', async () => {
+    const outputPath = path.join(tmpDir, 'from-docx.md');
+    const entry = resolve('docx', 'md');
+
+    await entry.convert(docxFixturePath, outputPath);
+
+    const markdown = await fs.readFile(outputPath, 'utf8');
+    expect(markdown).toContain('Hello from the fixture document');
+  }, 20000);
+
+  it('converts MD to DOCX preserving headings, bold text, and bullet lists', async () => {
+    const inputPath = path.join(tmpDir, 'fixture-for-docx.md');
+    await fs.writeFile(
+      inputPath,
+      '# Report Title\n\nSome **bold** finding.\n\n- first point\n- second point\n'
+    );
+    const outputPath = path.join(tmpDir, 'from-md.docx');
+    const entry = resolve('md', 'docx');
+
+    await entry.convert(inputPath, outputPath);
+
+    const mammoth = await import('mammoth');
+    const result = await mammoth.default.convertToHtml({ path: outputPath });
+    expect(result.value).toContain('Report Title');
+    expect(result.value).toContain('<strong>bold</strong>');
+    expect(result.value).toContain('first point');
+    expect(result.value).toContain('<li>');
+  }, 20000);
 });