import assert from 'node:assert/strict';
import { describe, it } from 'node:test';
import { extractContent, formatBytes } from '../src/extract.ts';

const MAX = 10_000;

describe('extractContent', () => {
	it('returns images inline as base64 without touching the bytes', async () => {
		const png = Buffer.from('89504e470d0a1a0a', 'hex');
		const result = await extractContent(png, 'image/png', 'a.png', MAX);
		assert.equal(result.kind, 'image');
		assert.equal(result.image?.base64, png.toString('base64'));
		assert.equal(result.image?.mimeType, 'image/png');
	});

	it('reads plain text and normalises CRLF', async () => {
		const result = await extractContent(Buffer.from('a\r\nb\r\n\r\n\r\n\r\nc'), 'text/plain', 'a.txt', MAX);
		assert.equal(result.kind, 'text');
		assert.equal(result.text, 'a\nb\n\nc');
	});

	it('recognises text even when the server mislabels it as octet-stream', async () => {
		const result = await extractContent(Buffer.from('hello world'), 'application/octet-stream', 'note', MAX);
		assert.equal(result.kind, 'text');
		assert.equal(result.text, 'hello world');
	});

	it('reports binary content instead of emitting mojibake', async () => {
		const bytes = Buffer.from([0x00, 0x01, 0x02, 0xff, 0xfe, 0x00]);
		const result = await extractContent(bytes, 'application/octet-stream', 'blob.bin', MAX);
		assert.equal(result.kind, 'binary');
		assert.match(result.note, /no text extractor/);
	});

	it('truncates at the limit and says so', async () => {
		const result = await extractContent(Buffer.from('x'.repeat(5000)), 'text/plain', 'a.txt', 100);
		assert.equal(result.truncated, true);
		assert.equal(result.text?.length, 100);
		assert.match(result.note, /truncated to 100 characters \(of 5000\)/);
	});

	it('turns a parser failure into a note rather than throwing', async () => {
		const result = await extractContent(Buffer.from('not really a pdf'), 'application/pdf', 'broken.pdf', MAX);
		assert.equal(result.kind, 'binary');
		assert.match(result.note, /Could not extract text|no text extractor/);
	});
});

describe('formatBytes', () => {
	it('scales units', () => {
		assert.equal(formatBytes(512), '512 B');
		assert.equal(formatBytes(2048), '2.0 KB');
		assert.equal(formatBytes(5 * 1024 * 1024), '5.0 MB');
	});
});