GetPDF() with Scheduler returns the same PDF file #488
Description
First of all, great work with this project! It's an impressive feat so far, despite the performance difference between this and native Tesseract.
Describe the bug
When using a Scheduler with multiple Workers, creating a GetPDF() job returns the same PDF document repeatedly, even though the Scheduler processes multiple different files.
To Reproduce
Steps to reproduce the behavior:
const {createWorker, createScheduler} = require('tesseract.js');
const fs = require('fs');
const scheduler = createScheduler();
const nWorkers = 4;
async function initialize() {
for (let i = 0; i < nWorkers; i++) {
let worker = createWorker({
cachePath: 'langs',
langPath: 'langs',
logger: m => console.log(m)
});
await worker.load();
await worker.loadLanguage('dan-fast');
await worker.initialize('dan-fast');
scheduler.addWorker(worker);
}
console.log('OCR initialized');
}
async function recognize(imagePath) {
const filePath = imagePath.split('/').slice(-1).pop();
const result = await scheduler.addJob('recognize', imagePath);
const {data} = await scheduler.addJob('getPDF', filePath);
fs.writeFileSync(`images/ocr-${filePath.replace('.png', '.pdf')}`, Buffer.from(data));
return result.data.text
}
initialize()
.then(() => {
const promises = [];
for (let i = 0; i < 3; i++) {
const promise = recognize(`images/page-${i+1}.png`)
promises.push(promise);
}
return Promise.all(promises)
})
.then((results) => {
results.forEach((res) => {
console.log('-----------');
console.log(res);
})
})
.then(() => {
return scheduler.terminate();
});
Expected behavior
GetPDF() should be able to produce the PDF file (or its byte representation) associated with a given recognition job, or the PDF byte representation should be part of the result from the recognition job.
The current operating model disables OCR-PDF rendering when using a scheduler, making processing a document with several pages more time-consuming.
Screenshots
Versions:
- OS: Mac OS 10.13.6
- Node: v12.18.1
- Tesseract.js: 2.1.3