Socket
Socket
Sign inDemoInstall

tesseract.js

Package Overview
Dependencies
13
Maintainers
2
Versions
67
Alerts
File Explorer

Advanced tools

npm Scripts
License

Install Socket

Detect and block malicious and high-risk dependencies

Install

Comparing version 1.0.3 to 1.0.5

LICENSE.md
src/common/job.js
test/node/arabic.js
test/node/arabic.png
test/node/english.js
test/node/tyger.jpg
test/node/tyger.txt

254

dist/tesseract.js

@@ -269,2 +269,46 @@ (function(f){if(typeof exports==="object"&&typeof module!=="undefined"){module.exports=f()}else if(typeof define==="function"&&define.amd){define([],f)}else{var g;if(typeof window!=="undefined"){g=window}else if(typeof global!=="undefined"){g=global}else if(typeof self!=="undefined"){g=self}else{g=this}g.Tesseract = f()}})(function(){var define,module,exports;return (function e(t,n,r){function s(o,u){if(!n[o]){if(!t[o]){var a=typeof require=="function"&&require;if(!u&&a)return a(o,!0);if(i)return i(o,!0);var f=new Error("Cannot find module '"+o+"'");throw f.code="MODULE_NOT_FOUND",f}var l=n[o]={exports:{}};t[o][0].call(l.exports,function(e){var n=t[o][1][e];return s(n?n:e)},l,l.exports,e,t,n,r)}return n[o].exports}var i=typeof require=="function"&&require;for(var o=0;o<r.length;o++)s(r[o]);return s})({1:[function(require,module,exports){

},{}],3:[function(require,module,exports){
module.exports={
"name": "tesseract.js",
"version": "1.0.5",
"description": "Pure Javascript Multilingual OCR",
"main": "src/index.js",
"scripts": {
"test": "echo \"Error: no test specified\" & exit 1",
"start": "watchify src/index.js -t [ envify --NODE_ENV development ] -t [ babelify --presets [ es2015 ] ] -o dist/tesseract.dev.js --standalone Tesseract & watchify src/browser/worker.js -t [ envify --NODE_ENV development ] -t [ babelify --presets [ es2015 ] ] -o dist/worker.dev.js & http-server -p 7355",
"build": "browserify src/index.js -t [ babelify --presets [ es2015 ] ] -o dist/tesseract.js --standalone Tesseract && browserify src/browser/worker.js -t [ babelify --presets [ es2015 ] ] -o dist/worker.js",
"release": "git tag `jq -r '.version' package.json`"
},
"browser": {
"./src/node/index.js": "./src/browser/index.js"
},
"author": "",
"license": "Apache",
"devDependencies": {
"babel-preset-es2015": "^6.16.0",
"babelify": "^7.3.0",
"browserify": "^13.1.0",
"envify": "^3.4.1",
"http-server": "^0.9.0",
"watchify": "^3.7.0",
"pako": "^1.0.3"
},
"dependencies": {
"file-type": "^3.8.0",
"jpeg-js": "^0.2.0",
"level-js": "^2.2.4",
"object-assign": "^4.1.0",
"png.js": "^0.2.1",
"tesseract.js-core": "^1.0.2"
},
"repository": {
"type": "git",
"url": "https://github.com/naptha/tesseract.js.git"
},
"bugs": {
"url": "https://github.com/naptha/tesseract.js/issues"
},
"homepage": "https://github.com/naptha/tesseract.js"
}
},{}],4:[function(require,module,exports){
(function (process){

@@ -274,3 +318,3 @@ 'use strict';

var defaultOptions = {
workerPath: 'https://cdn.rawgit.com/naptha/tesseract.js/0.2.0/dist/worker.js',
// workerPath: 'https://cdn.rawgit.com/naptha/tesseract.js/0.2.0/dist/worker.js',
corePath: 'https://cdn.rawgit.com/naptha/tesseract.js-core/0.1.0/index.js',

@@ -283,2 +327,5 @@ langPath: 'https://cdn.rawgit.com/naptha/tessdata/gh-pages/3.02/'

defaultOptions.workerPath = location.protocol + '//' + location.host + '/dist/worker.dev.js';
} else {
var version = require('../../package.json').version;
defaultOptions.workerPath = 'https://cdn.rawgit.com/naptha/tesseract.js/' + version + '/dist/worker.js';
}

@@ -375,3 +422,3 @@

}).call(this,require('_process'))
},{"_process":2}],4:[function(require,module,exports){
},{"../../package.json":3,"_process":2}],5:[function(require,module,exports){
"use strict";

@@ -443,3 +490,3 @@

},{}],5:[function(require,module,exports){
},{}],6:[function(require,module,exports){
'use strict';

@@ -451,5 +498,118 @@

var adapter = require('../node/index.js');
var jobCounter = 0;
module.exports = function () {
function TesseractJob(instance) {
_classCallCheck(this, TesseractJob);
this.id = 'Job-' + ++jobCounter + '-' + Math.random().toString(16).slice(3, 8);
this._instance = instance;
this._resolve = [];
this._reject = [];
this._progress = [];
this._finally = [];
}
_createClass(TesseractJob, [{
key: 'then',
value: function then(resolve, reject) {
if (this._resolve.push) {
this._resolve.push(resolve);
} else {
resolve(this._resolve);
}
if (reject) this.catch(reject);
return this;
}
}, {
key: 'catch',
value: function _catch(reject) {
if (this._reject.push) {
this._reject.push(reject);
} else {
reject(this._reject);
}
return this;
}
}, {
key: 'progress',
value: function progress(fn) {
this._progress.push(fn);
return this;
}
}, {
key: 'finally',
value: function _finally(fn) {
this._finally.push(fn);
return this;
}
}, {
key: '_send',
value: function _send(action, payload) {
adapter.sendPacket(this._instance, {
jobId: this.id,
action: action,
payload: payload
});
}
}, {
key: '_handle',
value: function _handle(packet) {
var data = packet.data;
var runFinallyCbs = false;
if (packet.status === 'resolve') {
if (this._resolve.length === 0) console.debug(data);
this._resolve.forEach(function (fn) {
var ret = fn(data);
if (ret && typeof ret.then == 'function') {
console.warn('TesseractJob instances do not chain like ES6 Promises. To convert it into a real promise, use Promise.resolve.');
}
});
this._resolve = data;
this._instance._dequeue();
runFinallyCbs = true;
} else if (packet.status === 'reject') {
if (this._reject.length === 0) console.error(data);
this._reject.forEach(function (fn) {
return fn(data);
});
this._reject = data;
this._instance._dequeue();
runFinallyCbs = true;
} else if (packet.status === 'progress') {
this._progress.forEach(function (fn) {
return fn(data);
});
} else {
console.warn('Message type unknown', packet.status);
}
if (runFinallyCbs) {
this._finally.forEach(function (fn) {
return fn(data);
});
}
}
}]);
return TesseractJob;
}();
},{"../node/index.js":4}],7:[function(require,module,exports){
'use strict';
var _createClass = function () { function defineProperties(target, props) { for (var i = 0; i < props.length; i++) { var descriptor = props[i]; descriptor.enumerable = descriptor.enumerable || false; descriptor.configurable = true; if ("value" in descriptor) descriptor.writable = true; Object.defineProperty(target, descriptor.key, descriptor); } } return function (Constructor, protoProps, staticProps) { if (protoProps) defineProperties(Constructor.prototype, protoProps); if (staticProps) defineProperties(Constructor, staticProps); return Constructor; }; }();
function _classCallCheck(instance, Constructor) { if (!(instance instanceof Constructor)) { throw new TypeError("Cannot call a class as a function"); } }
var adapter = require('./node/index.js');
var circularize = require('./common/circularize.js');
var TesseractJob = require('./common/job');
var objectAssign = require('object-assign');
var version = require('../package.json').version;

@@ -460,2 +620,3 @@ function create(workerOptions) {

worker.create = create;
worker.version = version;
return worker;

@@ -549,87 +710,2 @@ }

var jobCounter = 0;
var TesseractJob = function () {
function TesseractJob(instance) {
_classCallCheck(this, TesseractJob);
this.id = 'Job-' + ++jobCounter + '-' + Math.random().toString(16).slice(3, 8);
this._instance = instance;
this._resolve = [];
this._reject = [];
this._progress = [];
}
_createClass(TesseractJob, [{
key: 'then',
value: function then(resolve, reject) {
if (this._resolve.push) {
this._resolve.push(resolve);
} else {
resolve(this._resolve);
}
if (reject) this.catch(reject);
return this;
}
}, {
key: 'catch',
value: function _catch(reject) {
if (this._reject.push) {
this._reject.push(reject);
} else {
reject(this._reject);
}
return this;
}
}, {
key: 'progress',
value: function progress(fn) {
this._progress.push(fn);
return this;
}
}, {
key: '_send',
value: function _send(action, payload) {
adapter.sendPacket(this._instance, {
jobId: this.id,
action: action,
payload: payload
});
}
}, {
key: '_handle',
value: function _handle(packet) {
var data = packet.data;
if (packet.status === 'resolve') {
if (this._resolve.length === 0) console.debug(data);
this._resolve.forEach(function (fn) {
var ret = fn(data);
if (ret && typeof ret.then == 'function') {
console.warn('TesseractJob instances do not chain like ES6 Promises. To convert it into a real promise, use Promise.resolve.');
}
});
this._resolve = data;
this._instance._dequeue();
} else if (packet.status === 'reject') {
if (this._reject.length === 0) console.error(data);
this._reject.forEach(function (fn) {
return fn(data);
});
this._reject = data;
this._instance._dequeue();
} else if (packet.status === 'progress') {
this._progress.forEach(function (fn) {
return fn(data);
});
} else {
console.warn('Message type unknown', packet.status);
}
}
}]);
return TesseractJob;
}();
var DefaultTesseract = create();

@@ -639,3 +715,3 @@

},{"./common/circularize.js":4,"./node/index.js":3,"object-assign":1}]},{},[5])(5)
},{"../package.json":3,"./common/circularize.js":5,"./common/job":6,"./node/index.js":4,"object-assign":1}]},{},[7])(7)
});

2

docs/tesseract_lang_list.md

@@ -21,3 +21,3 @@ # Tesseract Languages

| 'ell' | Greek |
| 'eng' | Enlish |
| 'eng' | English |
| 'enm' | English (Old) |

@@ -24,0 +24,0 @@ | 'epo' | Esperanto |

16

examples/node/basic.js

@@ -0,6 +1,14 @@

var path = require('path');
var Tesseract = require('../../') // replace this with require('tesseract.js')
var image = path.resolve(__dirname, 'cosmic.png');
Tesseract.recognize('cosmic.png')
.then(function(data){
console.log(data.text)
})
Tesseract.recognize(image)
.then(data => {
console.log('then\n', data.text)
})
.catch(err => {
console.log('catch\n', err);
})
.finally(e => {
console.log('finally\n');
});

4

examples/node/detect.js

@@ -0,4 +1,6 @@

var path = require('path');
var Tesseract = require('../../') // replace this with require('tesseract.js')
var image = path.resolve(__dirname, 'cosmic.png');
Tesseract.detect('cosmic.png')
Tesseract.detect(image)
.progress(function(info){

@@ -5,0 +7,0 @@ console.log(info)

7

package.json
{
"name": "tesseract.js",
"version": "1.0.3",
"version": "1.0.5",
"description": "Pure Javascript Multilingual OCR",

@@ -9,3 +9,4 @@ "main": "src/index.js",

"start": "watchify src/index.js -t [ envify --NODE_ENV development ] -t [ babelify --presets [ es2015 ] ] -o dist/tesseract.dev.js --standalone Tesseract & watchify src/browser/worker.js -t [ envify --NODE_ENV development ] -t [ babelify --presets [ es2015 ] ] -o dist/worker.dev.js & http-server -p 7355",
"build": "browserify src/index.js -t [ babelify --presets [ es2015 ] ] -o dist/tesseract.js --standalone Tesseract && browserify src/browser/worker.js -t [ babelify --presets [ es2015 ] ] -o dist/worker.js"
"build": "browserify src/index.js -t [ babelify --presets [ es2015 ] ] -o dist/tesseract.js --standalone Tesseract && browserify src/browser/worker.js -t [ babelify --presets [ es2015 ] ] -o dist/worker.js",
"release": "git tag `jq -r '.version' package.json` && git push origin --tags && npm publish"
},

@@ -16,3 +17,3 @@ "browser": {

"author": "",
"license": "MIT",
"license": "Apache",
"devDependencies": {

@@ -19,0 +20,0 @@ "babel-preset-es2015": "^6.16.0",

55

README.md

@@ -5,3 +5,3 @@ # [Tesseract.js](http://tesseract.projectnaptha.com/)

Tesseract.js is a javascript library that gets words in [almost any language](./tesseract_lang_list.md) out of images. ([Demo](http://tesseract.projectnaptha.com/))
Tesseract.js is a javascript library that gets words in [almost any language](./docs/tesseract_lang_list.md) out of images. ([Demo](http://tesseract.projectnaptha.com/))

@@ -40,3 +40,5 @@ <!-- Under the hood, Tesseract.js wraps [tesseract.js-core](https://github.com/naptha/tesseract.js-core), an [emscripten](https://github.com/kripken/emscripten) port of the [Tesseract OCR Engine](https://github.com/tesseract-ocr/tesseract).

```
> Note: Tesseract.js currently requires node v6.8.0 or greater.
Then

@@ -65,3 +67,4 @@ ```javascript

+ [TesseractJob.catch(callback: function) -> TesseractJob](#tesseractjoberrorcallback-function---tesseractjob)
* [Tesseract Configuration](#tesseract-configuration)
+ [TesseractJob.finally(callback: function) -> TesseractJob](#tesseractjobfinallycallback-function---tesseractjob)
* [Local Installation](#local-installation)
+ [corePath](#corepath)

@@ -77,9 +80,12 @@ + [workerPath](#workerpath)

## Tesseract.recognize(image: [ImageLike](#imagelike)[, options]) -> [TesseractJob](#tesseractjob)
Figures out what words are in `image`, where the words are in `image`, etc.
Figures out what words are in `image`, where the words are in `image`, etc.
> Note: `image` should be be sufficiently high resolution.
> Often, the same image will get much better results if you upscale it before calling `recognize`.
- `image` is any [ImageLike](#imagelike) object.
- `options` is either absent (in which case it is interpreted as `'eng'`), a string specifing a language short code from the [language list](./tesseract_lang_list.md), or a flat json object that may:
+ include properties that override some subset of the [default tesseract parameters](./tesseract_parameters.md)
+ include a `lang` property with a value from the [list of lang parameters](./tesseract_lang_list.md)
- `options` is either absent (in which case it is interpreted as `'eng'`), a string specifing a language short code from the [language list](./docs/tesseract_lang_list.md), or a flat json object that may:
+ include properties that override some subset of the [default tesseract parameters](./docs/tesseract_parameters.md)
+ include a `lang` property with a value from the [list of lang parameters](./docs/tesseract_lang_list.md)
Returns a [TesseractJob](#tesseractjob) whose `then`, `progress`, and `catch` methods can be used to act on the result.
Returns a [TesseractJob](#tesseractjob) whose `then`, `progress`, `catch` and `finally` methods can be used to act on the result.

@@ -115,3 +121,3 @@ ### Simple Example:

Returns a [TesseractJob](#tesseractjob) whose `then`, `progress`, and `error` methods can be used to act on the result of the script.
Returns a [TesseractJob](#tesseractjob) whose `then`, `progress`, `error` and `finally` methods can be used to act on the result of the script.

@@ -151,3 +157,3 @@

A TesseractJob is an an object returned by a call to `recognize` or `detect`. It's inspired by the ES6 Promise interface and provides `then` and `catch` methods. One important difference is that these methods return the job itself (to enable chaining) rather than new.
A TesseractJob is an an object returned by a call to `recognize` or `detect`. It's inspired by the ES6 Promise interface and provides `then` and `catch` methods. It also provides `finally` method, which will be fired regardless of the job fate. One important difference is that these methods return the job itself (to enable chaining) rather than new.

@@ -157,5 +163,6 @@ Typical use is:

Tesseract.recognize(myImage)
.progress(function(message){console.log(message)})
.catch(function(err){console.error(err)})
.then(function(result){console.log(result)})
.progress(message => console.log(message))
.catch(err => console.error(err))
.then(result => console.log(result))
.finally(resultOrError => console.log(resultOrError))
```

@@ -167,7 +174,9 @@

job1.progress(function(message){console.log(message)});
job1.progress(message => console.log(message));
job1.catch(function(err){console.error(err)});
job1.catch(err => console.error(err));
job1.then(function(result){console.log(result)})
job1.then(result => console.log(result));
job1.finally(resultOrError => console.log(resultOrError));
```

@@ -209,3 +218,3 @@

Tesseract.recognize(myImage)
.then(function(result){console.log('result is: 'result)})
.then(function(result){console.log('result is: ', result)})
```

@@ -215,3 +224,3 @@

```javascript
progress is: {
result is: {
blocks: Array[1]

@@ -233,6 +242,14 @@ confidence: 87

Sets `callback` as the function that will be called if the job fails.
- `callback` is a function with the signature `callback(erros)` where `error` is a json object.
- `callback` is a function with the signature `callback(error)` where `error` is a json object.
## Tesseract Configuration
### TesseractJob.finally(callback: function) -> TesseractJob
Sets `callback` as the function that will be called regardless if the job fails or success.
- `callback` is a function with the signature `callback(resultOrError)` where `resultOrError` is a json object.
## Local Installation
In the browser, `tesseract.js` simply provides the API layer. Internally, it opens a WebWorker to handle requests. That worker itself loads code from the Emscripten-built `tesseract.js-core` which itself is hosted on a CDN. Then it dynamically loads language files hosted on another CDN.
Because of this we recommend loading `tesseract.js` from a CDN. But if you really need to have all your files local, you can use the `Tesseract.create` function which allows you to specify custom paths for workers, languages, and core.
```javascript

@@ -239,0 +256,0 @@ window.Tesseract = Tesseract.create({

5

src/browser/index.js
var defaultOptions = {
workerPath: 'https://cdn.rawgit.com/naptha/tesseract.js/0.2.0/dist/worker.js',
// workerPath: 'https://cdn.rawgit.com/naptha/tesseract.js/0.2.0/dist/worker.js',
corePath: 'https://cdn.rawgit.com/naptha/tesseract.js-core/0.1.0/index.js',

@@ -10,2 +10,5 @@ langPath: 'https://cdn.rawgit.com/naptha/tessdata/gh-pages/3.02/',

defaultOptions.workerPath = location.protocol + '//' + location.host + '/dist/worker.dev.js'
}else{
var version = require('../../package.json').version;
defaultOptions.workerPath = 'https://cdn.rawgit.com/naptha/tesseract.js/' + version + '/dist/worker.js'
}

@@ -12,0 +15,0 @@

24

src/common/worker.js

@@ -21,6 +21,10 @@ var latestJob;

if(packet.action === 'recognize'){
handleRecognize(packet.payload, respond)
}else if(packet.action === 'detect'){
handleDetect(packet.payload, respond)
try {
if(packet.action === 'recognize'){
handleRecognize(packet.payload, respond)
}else if(packet.action === 'detect'){
handleDetect(packet.payload, respond)
}
} catch (err) {
respond.reject(err)
}

@@ -36,8 +40,15 @@ }

function handleInit(req, res){
if(!Module){
var MIN_MEMORY = 100663296;
if(['chi_sim', 'chi_tra', 'jpn'].indexOf(req.options.lang) != -1){
MIN_MEMORY = 167772160;
}
if(!Module || Module.TOTAL_MEMORY < MIN_MEMORY){
var Core = adapter.getCore(req, res);
res.progress({ status: 'initializing tesseract', progress: 0 })
Module = Core({
TOTAL_MEMORY: req.memory,
TOTAL_MEMORY: MIN_MEMORY,
TesseractProgress(percent){

@@ -48,2 +59,3 @@ latestJob.progress({ status: 'recognizing text', progress: Math.max(0, (percent-30)/70) })

})
Module.FS_createPath("/", "tessdata", true, true)

@@ -50,0 +62,0 @@ base = new Module.TessBaseAPI()

74

src/index.js
const adapter = require('./node/index.js')
const circularize = require('./common/circularize.js')
const TesseractJob = require('./common/job');
const objectAssign = require('object-assign');
const version = require('../package.json').version;

@@ -9,2 +11,3 @@ function create(workerOptions){

worker.create = create;
worker.version = version;
return worker;

@@ -79,73 +82,4 @@ }

var jobCounter = 0;
class TesseractJob {
constructor(instance){
this.id = 'Job-' + (++jobCounter) + '-' + Math.random().toString(16).slice(3, 8)
this._instance = instance;
this._resolve = []
this._reject = []
this._progress = []
}
then(resolve, reject){
if(this._resolve.push){
this._resolve.push(resolve)
}else{
resolve(this._resolve)
}
if(reject) this.catch(reject);
return this;
}
catch(reject){
if(this._reject.push){
this._reject.push(reject)
}else{
reject(this._reject)
}
return this;
}
progress(fn){
this._progress.push(fn)
return this;
}
_send(action, payload){
adapter.sendPacket(this._instance, {
jobId: this.id,
action: action,
payload: payload
})
}
_handle(packet){
var data = packet.data;
if(packet.status === 'resolve'){
if(this._resolve.length === 0) console.debug(data);
this._resolve.forEach(fn => {
var ret = fn(data);
if(ret && typeof ret.then == 'function'){
console.warn('TesseractJob instances do not chain like ES6 Promises. To convert it into a real promise, use Promise.resolve.')
}
})
this._resolve = data;
this._instance._dequeue()
}else if(packet.status === 'reject'){
if(this._reject.length === 0) console.error(data);
this._reject.forEach(fn => fn(data))
this._reject = data;
this._instance._dequeue()
}else if(packet.status === 'progress'){
this._progress.forEach(fn => fn(data))
}else{
console.warn('Message type unknown', packet.status)
}
}
}
var DefaultTesseract = create()
module.exports = DefaultTesseract
module.exports = DefaultTesseract

1

src/node/index.js

@@ -35,2 +35,3 @@ const path = require('path')

fs.readFile(image, function(err, buffer){
if (err) throw err;
loadImage(buffer, cb)

@@ -37,0 +38,0 @@ })

.npmignore

Sorry, the diff of this file is not supported yet

demo.gif

Sorry, the diff of this file is not supported yet

dist/worker.js

Sorry, the diff of this file is too big to display

docs/tesseract_parameters.md

Sorry, the diff of this file is too big to display

SocketSocket SOC 2 Logo

Product

  • Package Alerts
  • Integrations
  • Docs
  • Pricing
  • FAQ
  • Roadmap

About

Packages

Stay in touch

Get open source security insights delivered straight into your inbox.

  • Terms
  • Privacy
  • Security

Made with ⚡️ by Socket Inc