Ombrora/convert
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: add md<->html document converters

Browse Source 
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
This commit is contained in:
anthony
2026-07-31 08:31:00 +02:00
co-authored by Claude Sonnet 5
parent 28b6edac82
commit 1595c5e0af
2 changed files with 43 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/converters/document.js
+17 -1
View File
@@ -2,7 +2,9 @@ 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 { Document, Paragraph, TextRun, HeadingLevel, Packer } from 'docx';
import MarkdownIt from 'markdown-it';
import TurndownService from 'turndown';
import { register } from './registry.js';
async function renderHtmlToPdf(html, outputPath) {
@@ -44,6 +46,18 @@ async function convertDocxToPdf(inputPath, outputPath) {
await renderHtmlToPdf(result.value, outputPath);
}
async function convertMdToHtml(inputPath, outputPath) {
const markdown = await fs.readFile(inputPath, 'utf8');
const html = new MarkdownIt().render(markdown);
await fs.writeFile(outputPath, html);
}
async function convertHtmlToMd(inputPath, outputPath) {
const html = await fs.readFile(inputPath, 'utf8');
const markdown = new TurndownService({ headingStyle: 'atx' }).turndown(html);
await fs.writeFile(outputPath, markdown);
}
async function extractPdfPageTexts(inputPath) {
const data = new Uint8Array(await fs.readFile(inputPath));
const doc = await pdfjsLib.getDocument({ data }).promise;
@@ -85,6 +99,8 @@ 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: 'md', targetFormat: 'html', convert: convertMdToHtml });
register({ family: 'document', sourceFormat: 'html', targetFormat: 'md', convert: convertHtmlToMd });
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 });