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.

163 lines
5.9 KiB

8 years ago
<script src="/dist/tesseract.dev.js"></script>
8 years ago
<script>
function progressUpdate(packet){
var log = document.getElementById('log');
if(log.firstChild && log.firstChild.status === packet.status){
if('progress' in packet){
var progress = log.firstChild.querySelector('progress')
progress.value = packet.progress
}
}else{
var line = document.createElement('div');
line.status = packet.status;
var status = document.createElement('div')
status.className = 'status'
status.appendChild(document.createTextNode(packet.status))
line.appendChild(status)
if('progress' in packet){
var progress = document.createElement('progress')
progress.value = packet.progress
progress.max = 1
line.appendChild(progress)
}
if(packet.status == 'done'){
var pre = document.createElement('pre')
pre.appendChild(document.createTextNode(packet.data.data.text))
8 years ago
line.innerHTML = ''
8 years ago
line.appendChild(pre)
8 years ago
8 years ago
}
log.insertBefore(line, log.firstChild)
}
}
async function recognizeFile(file) {
document.querySelector("#log").innerHTML = ''
const corePath = window.navigator.userAgent.indexOf("Edge") > -1
? '../../node_modules/tesseract.js-core/tesseract-core.asm.js'
: '../../node_modules/tesseract.js-core/tesseract-core.wasm.js';
8 years ago
const lang = document.querySelector('#langsel').value
const data = await Tesseract.recognize(file, lang, {
corePath,
logger: progressUpdate,
});
progressUpdate({ status: 'done', data });
8 years ago
}
</script>
<select id="langsel" onchange="window.lastFile && recognizeFile(window.lastFile)">
<option value='afr' > Afrikaans </option>
<option value='ara' > Arabic </option>
<option value='aze' > Azerbaijani </option>
<option value='bel' > Belarusian </option>
<option value='ben' > Bengali </option>
<option value='bul' > Bulgarian </option>
<option value='cat' > Catalan </option>
<option value='ces' > Czech </option>
<option value='chi_sim' > Chinese </option>
<option value='chi_tra' > Traditional Chinese </option>
<option value='chr' > Cherokee </option>
<option value='dan' > Danish </option>
<option value='deu' > German </option>
<option value='ell' > Greek </option>
<option value='eng' selected> English </option>
<option value='enm' > English (Old) </option>
8 years ago
<option value='meme' > Internet Meme </option>
<option value='epo' > Esperanto </option>
<option value='epo_alt' > Esperanto alternative </option>
<option value='est' > Estonian </option>
<option value='eus' > Basque </option>
<option value='fin' > Finnish </option>
<option value='fra' > French </option>
<option value='frk' > Frankish </option>
<option value='frm' > French (Old) </option>
<option value='glg' > Galician </option>
<option value='grc' > Ancient Greek </option>
<option value='heb' > Hebrew </option>
<option value='hin' > Hindi </option>
<option value='hrv' > Croatian </option>
<option value='hun' > Hungarian </option>
<option value='ind' > Indonesian </option>
<option value='isl' > Icelandic </option>
<option value='ita' > Italian </option>
<option value='ita_old' > Italian (Old) </option>
<option value='jpn' > Japanese </option>
<option value='kan' > Kannada </option>
<option value='kor' > Korean </option>
<option value='lav' > Latvian </option>
<option value='lit' > Lithuanian </option>
<option value='mal' > Malayalam </option>
<option value='mkd' > Macedonian </option>
<option value='mlt' > Maltese </option>
<option value='msa' > Malay </option>
<option value='nld' > Dutch </option>
<option value='nor' > Norwegian </option>
<option value='pol' > Polish </option>
<option value='por' > Portuguese </option>
<option value='ron' > Romanian </option>
<option value='rus' > Russian </option>
<option value='slk' > Slovakian </option>
<option value='slv' > Slovenian </option>
<option value='spa' > Spanish </option>
<option value='spa_old' > Old Spanish </option>
<option value='sqi' > Albanian </option>
<option value='srp' > Serbian (Latin) </option>
<option value='swa' > Swahili </option>
<option value='swe' > Swedish </option>
<option value='tam' > Tamil </option>
<option value='tel' > Telugu </option>
<option value='tgl' > Tagalog </option>
<option value='tha' > Thai </option>
<option value='tur' > Turkish </option>
<option value='ukr' > Ukrainian </option>
<option value='vie' > Vietnamese </option>
</select>
<button onclick="recognizeFile('../../tests/assets/images/simple.png')">Sample Image</button>
<input type="file" onchange="recognizeFile(window.lastFile=this.files[0])">
8 years ago
<div id="log"></div>
<style>
#log > div {
color: #313131;
border-top: 1px solid #dadada;
padding: 9px;
display: flex;
}
#log > div:first-child {
border: 0;
}
.status {
min-width: 250px;
}
#log {
border: 1px solid #dadada;
padding: 10px;
margin-top: 20px;
min-height: 100px;
}
body {
font-family: sans-serif;
margin: 30px;
}
progress {
display: block;
width: 100%;
transition: opacity 0.5s linear;
}
progress[value="1"] {
opacity: 0.5;
}
</style>