feat: add best-effort PDF source converters (txt, html, docx)

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
2026-07-30 09:12:43 +02:00
parent 16b4f28b42
commit 05ff96b8b3
2 changed files with 106 additions and 0 deletions
@@ -1,6 +1,8 @@
 import fs from 'node:fs/promises';
 import mammoth from 'mammoth';
 import puppeteer from 'puppeteer';
+import * as pdfjsLib from 'pdfjs-dist/legacy/build/pdf.mjs';
+import { Document, Paragraph, TextRun, Packer } from 'docx';
 import { register } from './registry.js';

 async function renderHtmlToPdf(html, outputPath) {
@@ -42,9 +44,49 @@ async function convertDocxToPdf(inputPath, outputPath) {
  await renderHtmlToPdf(result.value, outputPath);
 }

+async function extractPdfPageTexts(inputPath) {
+  const data = new Uint8Array(await fs.readFile(inputPath));
+  const doc = await pdfjsLib.getDocument({ data }).promise;
+
+  const pageTexts = [];
+  for (let pageNum = 1; pageNum <= doc.numPages; pageNum += 1) {
+    const page = await doc.getPage(pageNum);
+    const content = await page.getTextContent();
+    pageTexts.push(content.items.map((item) => item.str).join(' '));
+  }
+  return pageTexts;
+}
+
+async function convertPdfToTxt(inputPath, outputPath) {
+  const pageTexts = await extractPdfPageTexts(inputPath);
+  await fs.writeFile(outputPath, pageTexts.join('\n\n'));
+}
+
+async function convertPdfToHtml(inputPath, outputPath) {
+  const pageTexts = await extractPdfPageTexts(inputPath);
+  const body = pageTexts.map((text) => `<p>${escapeHtml(text)}</p>`).join('\n');
+  await fs.writeFile(outputPath, `<html><body>${body}</body></html>`);
+}
+
+async function convertPdfToDocx(inputPath, outputPath) {
+  const pageTexts = await extractPdfPageTexts(inputPath);
+  const doc = new Document({
+    sections: [
+      {
+        children: pageTexts.map((text) => new Paragraph({ children: [new TextRun(text)] })),
+      },
+    ],
+  });
+  const buffer = await Packer.toBuffer(doc);
+  await fs.writeFile(outputPath, buffer);
+}
+
 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 });
+  register({ family: 'document', sourceFormat: 'pdf', targetFormat: 'txt', convert: convertPdfToTxt });
+  register({ family: 'document', sourceFormat: 'pdf', targetFormat: 'html', convert: convertPdfToHtml });
+  register({ family: 'document', sourceFormat: 'pdf', targetFormat: 'docx', convert: convertPdfToDocx });
 }