Pure Javascript OCR for more than 100 Languages 📖🎉🖥
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

35 lines
991 B

6 years ago
#!/usr/bin/env node
const path = require('path');
5 years ago
const fs = require('fs');
const {
5 years ago
Tesseract, createScheduler, createWorker,
} = require('../../');
6 years ago
const [,, imagePath] = process.argv;
const image = path.resolve(__dirname, (imagePath || '../../tests/assets/images/cosmic.png'));
console.log(`Recognizing ${image}`);
(async () => {
const scheduler = createScheduler();
const worker = createWorker();
await worker.load();
await worker.loadLanguage('eng');
await worker.initialize('eng');
scheduler.addWorker(worker);
5 years ago
console.log((await scheduler.addJob('recognize', image)).text);
const data = await worker.getPDF('ocr', 'Tesseract OCR');
fs.writeFileSync('test.pdf', Buffer.from(data));
await scheduler.terminate();
})();
5 years ago
//Tesseract.recognize(image, 'eng', { logger: m => console.log(m) })
// .then(({ text }) => {
// console.log(text);
// });
//Tesseract.detect(image, { logger: m => console.log(m) })
// .then((data) => {
// console.log(data);
// });