Javascript Tesseract Node.js-使用;“朗”;选择导致崩溃
Tesseract.js的基本用法与英语不同,会导致整个系统崩溃:Javascript Tesseract Node.js-使用;“朗”;选择导致崩溃,javascript,node.js,ocr,tesseract,Javascript,Node.js,Ocr,Tesseract,Tesseract.js的基本用法与英语不同,会导致整个系统崩溃: var options = { lang: 'deu', }; var image = require("path").join(__dirname, 'lib/images/ocr-test-text.png'); var Tesseract = require('tesseract.js') Tesseract.recognize(image, options) .progress(function (info
var options = {
lang: 'deu',
};
var image = require("path").join(__dirname, 'lib/images/ocr-test-text.png');
var Tesseract = require('tesseract.js')
Tesseract.recognize(image, options)
.progress(function (info) {
console.log(info);
})
.then(function (data) {
console.log('done', data);
process.exit();
})
触发以下错误:
> node index.js
{ status: 'loading tesseract core' }
{ status: 'loaded tesseract core' }
{ status: 'initializing tesseract', progress: 0 }
pre-main prep time: 68 ms
{ status: 'initializing tesseract', progress: 1 }
{ status: 'downloading deu.traineddata.gz',
loaded: 116,
progress: 0.00011697604814572795 }
events.js:182
throw er; // Unhandled 'error' event
^
Error: incorrect header check
at Gunzip.zlibOnError (zlib.js:146:15)
Github问题:
知道发生了什么吗
更新:
按照第一个答案的说明,下载“deu”traineddata后,出现以下错误:
export TESSDATA_PREFIX=/opt/TESSDATA && node get-text-from-image.js /opt/app/out/image.png
params [ '/opt/app/out/image.png' ]
progress { status: 'loading tesseract core' }
progress { status: 'loaded tesseract core' }
progress { status: 'initializing tesseract', progress: 0 }
pre-main prep time: 62 ms
progress { status: 'initializing tesseract', progress: 1 }
progress { status: 'loading deu.traineddata', progress: 0 }
progress { status: 'loading deu.traineddata', progress: 1 }
progress { status: 'initializing api', progress: 0 }
Failed loading language 'deu'
Tesseract couldn't load any languages!
progress { status: 'initializing api', progress: 0.3 }
progress { status: 'initializing api', progress: 0.6 }
progress { status: 'initializing api', progress: 1 }
progress { status: 'recognizing text', progress: 0 }
AdaptedTemplates != NULL:Error:Assert failed:in file ../classify/adaptmatch.cpp, line 190
/opt/app/node_modules/tesseract.js-core/index.js:4
function f(a){throw a;}var h=void 0,i=!0,j=null,k=!1;function aa(){return function(){}}function ba(a){return function(){return a}}var n,Module;Module||(Module=eval("(function() { try { return TesseractCore || {} } catch(e) { return {} } })()"));var ca={},da;for(da in Module)Module.hasOwnProperty(da)&&(ca[da]=Module[da]);var ea=i,fa=!ea&&i;
^
abort() at Error
at Na (/opt/app/node_modules/tesseract.js-core/index.js:32:26)
at Object.ka [as abort] (/opt/app/node_modules/tesseract.js-core/index.js:507:108)
at _abort (/opt/app/node_modules/tesseract.js-core/index.js:373:173)
at $L (/opt/app/node_modules/tesseract.js-core/index.js:383:55709)
at jpa (/opt/app/node_modules/tesseract.js-core/index.js:388:22274)
at lT (/opt/app/node_modules/tesseract.js-core/index.js:387:80568)
at mT (/opt/app/node_modules/tesseract.js-core/index.js:387:80700)
at Array.BS (/opt/app/node_modules/tesseract.js-core/index.js:387:69011)
at bP (/opt/app/node_modules/tesseract.js-core/index.js:383:110121)
at jT (/opt/app/node_modules/tesseract.js-core/index.js:387:80280)
If this abort() is unexpected, build with -s ASSERTIONS=1 which can give more information.
它无法打开deu.traineddata.gz的包-不知道为什么。您可能希望自己下载该文件并尝试手动压缩它。不过,这不是政府建议的方式;你还可以试试别的 在运行node.js的机器上下载语言文件,并将它们放在某处 在环境中,确保变量
TESSDATA\u PREFIX
指向该位置。例如,您可以将它们放在/opt/tessdata
中。如果这样做,您可以如下设置TESSDATA\u前缀
:
export TESSDATA_PREFIX=/opt/tessdata
再试一次;这一次,它不应该试图自行下载和解包。谢谢!我尝试了你的第二个建议-下载并设置env var,但这会输出一个不同的错误。你是否确实将文件放入了
/opt/tessdata
?我的意思是作为一个例子,你应该用/opt/tessdata
代替你实际放置它们的目录。很抱歉造成混淆,我编辑了我的答案。