171 lines
6.0 KiB
JavaScript
171 lines
6.0 KiB
JavaScript
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);
|
|
|
|
it('converts MD to HTML', async () => {
|
|
const inputPath = path.join(tmpDir, 'fixture.md');
|
|
await fs.writeFile(inputPath, '# Heading\n\nSome **bold** text.');
|
|
const outputPath = path.join(tmpDir, 'from-md.html');
|
|
const entry = resolve('md', 'html');
|
|
|
|
await entry.convert(inputPath, outputPath);
|
|
|
|
const html = await fs.readFile(outputPath, 'utf8');
|
|
expect(html).toContain('<h1>Heading</h1>');
|
|
expect(html).toContain('<strong>bold</strong>');
|
|
});
|
|
|
|
it('converts HTML to MD', async () => {
|
|
const inputPath = path.join(tmpDir, 'fixture-for-md.html');
|
|
await fs.writeFile(inputPath, '<h1>Heading</h1><p>Some <strong>bold</strong> text.</p>');
|
|
const outputPath = path.join(tmpDir, 'from-html.md');
|
|
const entry = resolve('html', 'md');
|
|
|
|
await entry.convert(inputPath, outputPath);
|
|
|
|
const markdown = await fs.readFile(outputPath, 'utf8');
|
|
expect(markdown).toContain('# Heading');
|
|
expect(markdown).toContain('**bold**');
|
|
});
|
|
|
|
it('converts MD to a valid PDF', async () => {
|
|
const inputPath = path.join(tmpDir, 'fixture-for-pdf.md');
|
|
await fs.writeFile(inputPath, '# Heading\n\nSome text.');
|
|
const outputPath = path.join(tmpDir, 'from-md.pdf');
|
|
const entry = resolve('md', 'pdf');
|
|
|
|
await entry.convert(inputPath, outputPath);
|
|
|
|
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);
|
|
|
|
it('copies MD content unchanged to TXT', async () => {
|
|
const inputPath = path.join(tmpDir, 'fixture-for-txt.md');
|
|
const content = '# Heading\n\nSome **bold** text.\n';
|
|
await fs.writeFile(inputPath, content);
|
|
const outputPath = path.join(tmpDir, 'from-md.txt');
|
|
const entry = resolve('md', 'txt');
|
|
|
|
await entry.convert(inputPath, outputPath);
|
|
|
|
const output = await fs.readFile(outputPath, 'utf8');
|
|
expect(output).toBe(content);
|
|
});
|
|
|
|
it('copies TXT content unchanged to MD', async () => {
|
|
const inputPath = path.join(tmpDir, 'fixture-for-md-from-txt.txt');
|
|
const content = 'Plain text content.\n';
|
|
await fs.writeFile(inputPath, content);
|
|
const outputPath = path.join(tmpDir, 'from-txt.md');
|
|
const entry = resolve('txt', 'md');
|
|
|
|
await entry.convert(inputPath, outputPath);
|
|
|
|
const output = await fs.readFile(outputPath, 'utf8');
|
|
expect(output).toBe(content);
|
|
});
|
|
});
|