|
|
|
|
<!DOCTYPE HTML>
|
|
|
|
|
<html>
|
|
|
|
|
<head>
|
|
|
|
|
<script src="/dist/tesseract.min.js"></script>
|
|
|
|
|
</head>
|
|
|
|
|
<body>
|
|
|
|
|
<input type="file" id="uploader" multiple>
|
|
|
|
|
<script type="module">
|
|
|
|
|
|
|
|
|
|
// This example builds on "basic-efficient.html".
|
|
|
|
|
// Rather than using a single worker, a scheduler manages a pool of multiple workers.
|
|
|
|
|
// While performance is similar for a single file, this parallel processing results in significantly
|
|
|
|
|
// faster speeds when used with multiple files.
|
|
|
|
|
|
|
|
|
|
const scheduler = Tesseract.createScheduler();
|
|
|
|
|
|
|
|
|
|
// Creates worker and adds to scheduler
|
|
|
|
|
const workerGen = async () => {
|
|
|
|
|
const worker = await Tesseract.createWorker("eng", 1, {
|
|
|
|
|
corePath: '../../node_modules/tesseract.js-core',
|
|
|
|
|
workerPath: "/dist/worker.min.js",
|
|
|
|
|
logger: function(m){console.log(m);}
|
|
|
|
|
});
|
|
|
|
|
scheduler.addWorker(worker);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
const workerN = 4;
|
|
|
|
|
(async () => {
|
|
|
|
|
const resArr = Array(workerN);
|
|
|
|
|
for (let i=0; i<workerN; i++) {
|
|
|
|
|
resArr[i] = await workerGen();
|
|
|
|
|
}
|
|
|
|
|
})();
|
|
|
|
|
|
|
|
|
|
const recognize = async function(evt){
|
|
|
|
|
const files = evt.target.files;
|
|
|
|
|
|
|
|
|
|
for (let i=0; i<files.length; i++) {
|
|
|
|
|
scheduler.addJob('recognize', files[i]).then((x) => console.log(x.data.text))
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
const elm = document.getElementById('uploader');
|
|
|
|
|
elm.addEventListener('change', recognize);
|
|
|
|
|
</script>
|
|
|
|
|
</body>
|
|
|
|
|
</html>
|
