33 lines
1.5 KiB
JavaScript
33 lines
1.5 KiB
JavaScript
const test = require('node:test');
|
|
const assert = require('node:assert/strict');
|
|
const fs = require('node:fs');
|
|
const path = require('node:path');
|
|
const vm = require('node:vm');
|
|
const zlib = require('node:zlib');
|
|
|
|
const runtime = {window: {}, Blob, Response, DecompressionStream, TextDecoder, Uint8Array};
|
|
vm.createContext(runtime);
|
|
vm.runInContext(fs.readFileSync(path.join(__dirname, 'docview.js'), 'utf8'), runtime);
|
|
|
|
function pdfWithStream(content, compressed = false) {
|
|
const stream = compressed ? zlib.deflateSync(Buffer.from(content, 'latin1')) : Buffer.from(content, 'latin1');
|
|
const filter = compressed ? ' /Filter /FlateDecode' : '';
|
|
const prefix = `%PDF-1.4\n1 0 obj\n<< /Length ${stream.length}${filter} >>\nstream\n`;
|
|
return Buffer.concat([Buffer.from(prefix, 'latin1'), stream, Buffer.from('\nendstream\nendobj\n%%EOF', 'latin1')]);
|
|
}
|
|
|
|
test('PDF text extraction handles literal strings and escaped parentheses', async () => {
|
|
const pdf = pdfWithStream('BT /F1 12 Tf 72 700 Td (Hello \\(PDF\\)) Tj ET');
|
|
assert.equal(await runtime.window.DocView.pdf(pdf), 'Hello (PDF)');
|
|
});
|
|
|
|
test('PDF text extraction inflates streams and keeps TJ word spacing', async () => {
|
|
const pdf = pdfWithStream('BT /F1 12 Tf [(lightweight) -250 ( parser)] TJ ET', true);
|
|
assert.equal(await runtime.window.DocView.pdf(pdf), 'lightweight parser');
|
|
});
|
|
|
|
test('PDF text extraction reports scanned or non-text PDFs without OCR', async () => {
|
|
const pdf = pdfWithStream('q 0 0 100 100 re f Q');
|
|
await assert.rejects(runtime.window.DocView.pdf(pdf), /без OCR/);
|
|
});
|