feat: add DOCX/TXT/HTML document converters
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
This commit is contained in:
Claude Sonnet 5
@@ -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, '&').replace(/</g, '<').replace(/>/g, '>');
|
||||||
|
}
|
||||||
|
|
||||||
|
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 });
|
||||||
|
}
|
||||||
@@ -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);
|
||||||
|
});
|
||||||
Reference in New Issue
Block a user