Fix image url in README.md and release 1.0.19

Fix initialization when calling from other Worker

.eslintrc

@@ -1,17 +0,0 @@
-{
-  "extends": "airbnb-base",
-  "parser": "babel-eslint",
-  "env": {
-    "browser": true,
-    "node": true,
-    "mocha": true,
-    "worker": true
-  },
-  "rules": {
-    "no-underscore-dangle": 0,
-    "no-console": 0,
-    "global-require": 0,
-    "camelcase": 0,
-    "no-control-regex": 0
-  }
-}

.github/FUNDING.yml

@@ -1,9 +0,0 @@
-# These are supported funding model platforms
-
-github: # Replace with up to 4 GitHub Sponsors-enabled usernames e.g., [user1, user2]
-patreon: # Replace with a single Patreon username
-open_collective: tesseractjs
-ko_fi: # Replace with a single Ko-fi username
-tidelift: npm/tesseract.js
-community_bridge: # Replace with a single Community Bridge project-name e.g., cloud-foundry
-custom: ["https://etherscan.io/address/0x74ace8c74535d6dac03ebdc708ca2fba54796ef2"]

.github/ISSUE_TEMPLATE/bug_report.md

@@ -1,38 +0,0 @@
----
-name: Bug report
-about: Create a report to help us improve
-title: ''
-labels: ''
-assignees: ''
-
----
-
-**Describe the bug**
-A clear and concise description of what the bug is.
-
-**To Reproduce**
-Steps to reproduce the behavior:
-1. Go to '...'
-2. Click on '....'
-3. Scroll down to '....'
-4. See error
-
-**Expected behavior**
-A clear and concise description of what you expected to happen.
-
-**Screenshots**
-If applicable, add screenshots to help explain your problem.
-
-**Desktop (please complete the following information):**
- - OS: [e.g. iOS]
- - Browser [e.g. chrome, safari]
- - Version [e.g. 22]
-
-**Smartphone (please complete the following information):**
- - Device: [e.g. iPhone6]
- - OS: [e.g. iOS8.1]
- - Browser [e.g. stock browser, safari]
- - Version [e.g. 22]
-
-**Additional context**
-Add any other context about the problem here.

.github/ISSUE_TEMPLATE/feature_request.md

@@ -1,20 +0,0 @@
----
-name: Feature request
-about: Suggest an idea for this project
-title: ''
-labels: ''
-assignees: ''
-
----
-
-**Is your feature request related to a problem? Please describe.**
-A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]
-
-**Describe the solution you'd like**
-A clear and concise description of what you want to happen.
-
-**Describe alternatives you've considered**
-A clear and concise description of any alternative solutions or features you've considered.
-
-**Additional context**
-Add any other context or screenshots about the feature request here.

.github/SECURITY.md

@@ -1,5 +0,0 @@
-## Security contact information
-
-To report a security vulnerability, please use the
-[Tidelift security contact](https://tidelift.com/security).
-Tidelift will coordinate the fix and disclosure.

.github/workflows/codeql-analysis.yml

@@ -1,71 +0,0 @@
-# For most projects, this workflow file will not need changing; you simply need
-# to commit it to your repository.
-#
-# You may wish to alter this file to override the set of languages analyzed,
-# or to provide custom queries or build logic.
-name: "CodeQL"
-
-on:
-  push:
-    branches: [master]
-  pull_request:
-    # The branches below must be a subset of the branches above
-    branches: [master]
-  schedule:
-    - cron: '0 17 * * 6'
-
-jobs:
-  analyze:
-    name: Analyze
-    runs-on: ubuntu-latest
-
-    strategy:
-      fail-fast: false
-      matrix:
-        # Override automatic language detection by changing the below list
-        # Supported options are ['csharp', 'cpp', 'go', 'java', 'javascript', 'python']
-        language: ['javascript']
-        # Learn more...
-        # https://docs.github.com/en/github/finding-security-vulnerabilities-and-errors-in-your-code/configuring-code-scanning#overriding-automatic-language-detection
-
-    steps:
-    - name: Checkout repository
-      uses: actions/checkout@v2
-      with:
-        # We must fetch at least the immediate parents so that if this is
-        # a pull request then we can checkout the head.
-        fetch-depth: 2
-
-    # If this run was triggered by a pull request event, then checkout
-    # the head of the pull request instead of the merge commit.
-    - run: git checkout HEAD^2
-      if: ${{ github.event_name == 'pull_request' }}
-
-    # Initializes the CodeQL tools for scanning.
-    - name: Initialize CodeQL
-      uses: github/codeql-action/init@v1
-      with:
-        languages: ${{ matrix.language }}
-        # If you wish to specify custom queries, you can do so here or in a config file.
-        # By default, queries listed here will override any specified in a config file. 
-        # Prefix the list here with "+" to use these queries and those in the config file.
-        # queries: ./path/to/local/query, your-org/your-repo/queries@main
-
-    # Autobuild attempts to build any compiled languages  (C/C++, C#, or Java).
-    # If this step fails, then you should remove it and run the build manually (see below)
-    - name: Autobuild
-      uses: github/codeql-action/autobuild@v1
-
-    # ℹ️ Command-line programs to run using the OS shell.
-    # 📚 https://git.io/JvXDl
-
-    # ✏️ If the Autobuild fails above, remove it and uncomment the following three lines
-    #    and modify them (or add more) to build your code if your project
-    #    uses a compiled language
-
-    #- run: |
-    #   make bootstrap
-    #   make release
-
-    - name: Perform CodeQL Analysis
-      uses: github/codeql-action/analyze@v1

.github/workflows/node.js.yml

@@ -1,29 +0,0 @@
-# This workflow will do a clean install of node dependencies, build the source code and run tests across different versions of node
-# For more information see: https://help.github.com/actions/language-and-framework-guides/using-nodejs-with-github-actions
-
-name: Node.js CI
-
-on:
-  push:
-    branches: [ master ]
-  pull_request:
-    branches: [ master ]
-
-jobs:
-  build:
-
-    runs-on: ubuntu-latest
-
-    strategy:
-      matrix:
-        node-version: [14.x, 16.x]
-
-    steps:
-    - uses: actions/checkout@v2
-    - name: Use Node.js ${{ matrix.node-version }}
-      uses: actions/setup-node@v1
-      with:
-        node-version: ${{ matrix.node-version }}
-    - run: npm ci
-    - run: npm run lint
-    - run: npm test

.gitignore

@@ -3,8 +3,4 @@ node_modules/*
 yarn.lock
 tesseract.dev.js
 worker.dev.js
-/*.traineddata
+*.traineddata
-/examples/**/*.traineddata
-.nyc_output
-dist/
-*.swp

.gitpod.Dockerfile

@@ -1,2 +0,0 @@
-FROM gitpod/workspace-full
-RUN sudo apt-get update && sudo apt-get install -y libgtk-3-0 libx11-xcb1 libnss3 libxss1 libasound2

.gitpod.yml

@@ -1,9 +0,0 @@
-image:
-  file: .gitpod.Dockerfile
-tasks:
-  - command: gp await-port 3000 && sleep 3 && gp preview $(gp url 3000)/examples/browser/demo.html
-  - init: npm install
-    command: npm start
-ports:
-  - port: 3000
-    onOpen: ignore

.npmignore

@@ -1,3 +0,0 @@
-tests
-.nyc_output
-.github

README.md

@@ -1,197 +1,303 @@
-<p align="center">
+# [Tesseract.js](http://tesseract.projectnaptha.com/)
-<a href="https://tesseract.projectnaptha.com/"><img width="256px" height="256px" alt="Tesseract.js" src="./docs/images/tesseract.png"></a>
-</p>
-
-![Lint & Test](https://github.com/naptha/tesseract.js/workflows/Node.js%20CI/badge.svg)
-![CodeQL](https://github.com/naptha/tesseract.js/workflows/CodeQL/badge.svg)
-[![Gitpod Ready-to-Code](https://img.shields.io/badge/Gitpod-ready--to--code-blue?logo=gitpod)](https://github.com/naptha/tesseract.js) 
-[![Financial Contributors on Open Collective](https://opencollective.com/tesseractjs/all/badge.svg?label=financial+contributors)](https://opencollective.com/tesseractjs) [![npm version](https://badge.fury.io/js/tesseract.js.svg)](https://badge.fury.io/js/tesseract.js)
-[![Maintenance](https://img.shields.io/badge/Maintained%3F-yes-green.svg)](https://github.com/naptha/tesseract.js/graphs/commit-activity)
-[![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
-[![Code Style](https://badgen.net/badge/code%20style/airbnb/ff5a5f?icon=airbnb)](https://github.com/airbnb/javascript)
-[![Downloads Total](https://img.shields.io/npm/dt/tesseract.js.svg)](https://www.npmjs.com/package/tesseract.js)
-[![Downloads Month](https://img.shields.io/npm/dm/tesseract.js.svg)](https://www.npmjs.com/package/tesseract.js)
 
-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/))
 
-Image Recognition
+[![NPM version][tesseractjs-npm-image]][tesseractjs-npm-url]
+
+[tesseractjs-npm-image]: https://img.shields.io/npm/v/tesseract.js.svg
+[tesseractjs-npm-url]: https://npmjs.org/package/tesseract.js
+
+**Tesseract.js v2 alpha is now available!! Check [HERE](https://github.com/naptha/tesseract.js) for more information.**
 
-[![fancy demo gif](./docs/images/demo.gif)](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/))
+
+[![fancy demo gif](https://raw.githubusercontent.com/naptha/tesseract.js/support/1.x/docs/images/demo.gif)](http://tesseract.projectnaptha.com)
 
-Video Real-time Recognition
+Tesseract.js works with script tags, [webpack](https://webpack.js.org/)/[Browserify](http://browserify.org/), and [Node.js](https://nodejs.org/en/). [After you install it](#installation), using it is as simple as
 
-<p align="center">
+  ```javascript
-  <a href="https://github.com/jeromewu/tesseract.js-video"><img alt="Tesseract.js Video" src="./docs/images/video-demo.gif"></a>
+Tesseract.recognize(myImage)
-</p>
+         .progress(function  (p) { console.log('progress', p)    })
+         .then(function (result) { console.log('result', result) })
+```
 
+[Check out the docs](#docs) for a full treatment of the API.
 
+## Provenance
 Tesseract.js wraps an [emscripten](https://github.com/kripken/emscripten) [port](https://github.com/naptha/tesseract.js-core) of the [Tesseract](https://github.com/tesseract-ocr/tesseract) [OCR](https://en.wikipedia.org/wiki/Optical_character_recognition) Engine.
-It works in the browser using [webpack](https://webpack.js.org/) or plain script tags with a [CDN](#CDN) and on the server with [Node.js](https://nodejs.org/en/).
-After you [install it](#installation), using it is as simple as:
 
+
+# Installation
+
+Tesseract.js works with a `<script>` tag via local copy or CDN, with webpack and Browserify via `npm`, and on Node.js via `npm`. [Check out the docs](#docs) for a full treatment of the API.
+
+## &lt;script />
+
+You can simply include Tesseract.js with a CDN like this:
+```html
+<script src='https://cdn.jsdelivr.net/gh/naptha/tesseract.js@v1.0.14/dist/tesseract.min.js'></script>
+```
+
+After including your scripts, the `Tesseract` variable will be defined globally!
+
+## Dependency
+First:
+```shell
+> yarn add tesseract.js
+```
+or
+```
+> npm install tesseract.js --save
+```
+> Note: Tesseract.js currently requires Node.js v6.8.0 or higher.
+
+
+## Usage
+```javascript
+var Tesseract = require('tesseract.js')
+```
+
+or
+```javascript
+import Tesseract from 'tesseract.js'
+```
+
+
+# Docs
+
+* [Tesseract.recognize](#tesseractrecognizeimage-imagelike-options---tesseractjob)
+  + [Simple Example](#simple-example)
+  + [More Complicated Example](#more-complicated-example)
+* [Tesseract.detect](#tesseractdetectimage-imagelike---tesseractjob)
+* [ImageLike](#imagelike)
+* [TesseractJob](#tesseractjob)
+  + [TesseractJob.progress](#tesseractjobprogresscallback-function---tesseractjob)
+  + [TesseractJob.then](#tesseractjobthencallback-function---tesseractjob)
+  + [TesseractJob.catch](#tesseractjobcatchcallback-function---tesseractjob)
+  + [TesseractJob.finally](#tesseractjobfinallycallback-function---tesseractjob)
+* [Local Installation](#local-installation)
+  + [corePath](#corepath)
+  + [workerPath](#workerpath)
+  + [langPath](#langpath)
+* [Contributing](#contributing)
+  + [Development](#development)
+  + [Building Static Files](#building-static-files)
+  + [Send us a Pull Request!](#send-us-a-pull-request)
+
+
+## Tesseract.recognize(image: [ImageLike](#imagelike)[, options]) -> [TesseractJob](#tesseractjob)
+Figures out what words are in `image`, where the words are in `image`, etc.
+> Note: `image` should 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](./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`, `catch` and `finally` methods can be used to act on the result.
+
+### Simple Example:
 ```javascript
-import Tesseract from 'tesseract.js';
+Tesseract.recognize(myImage)
-
+.then(function(result){
-Tesseract.recognize(
+    console.log(result)
-  'https://tesseract.projectnaptha.com/img/eng_bw.png',
+})
-  'eng',
+```
-  { logger: m => console.log(m) }
+
-).then(({ data: { text } }) => {
+### More Complicated Example:
-  console.log(text);
+```javascript
+// if we know our image is of spanish words without the letter 'e':
+Tesseract.recognize(myImage, {
+    lang: 'spa',
+    tessedit_char_blacklist: 'e'
+})
+.then(function(result){
+    console.log(result)
 })
 ```
 
-Or more imperative
+
+
+
+## Tesseract.detect(image: [ImageLike](#imagelike)) -> [TesseractJob](#tesseractjob)
+
+Figures out what script (e.g. 'Latin', 'Chinese') the words in  image are written in.
+
+- `image` is any [ImageLike](#imagelike) object.
+
+Returns a [TesseractJob](#tesseractjob) whose `then`, `progress`, `catch` and `finally` methods can be used to act on the result of the script.
+
 
 ```javascript
-import { createWorker } from 'tesseract.js';
+Tesseract.detect(myImage)
-
+.then(function(result){
-const worker = createWorker({
+    console.log(result)
-  logger: m => console.log(m)
+})
-});
+```
-
-(async () => {
-  await worker.load();
-  await worker.loadLanguage('eng');
-  await worker.initialize('eng');
-  const { data: { text } } = await worker.recognize('https://tesseract.projectnaptha.com/img/eng_bw.png');
-  console.log(text);
-  await worker.terminate();
-})();
-```
-
-[Check out the docs](#documentation) for a full explanation of the API.
-
-## Major changes in v3
-- Significantly faster performance
-   - Runtime reduction of 84% for Browser and 96% for Node.js when recognizing the [example images](./examples/data)
-- Upgrade to Tesseract v5.1.0 (using emscripten 3.1.18)
-- Added SIMD-enabled build for supported devices
-- Added support:
-   - Node.js version 18
-- Removed support:
-   - ASM.js version, any other old versions of Tesseract.js-core (<3.0.0) 
-   - Node.js versions 10 and 12
-
-## Major changes in v2
-- Upgrade to tesseract v4.1.1 (using emscripten 1.39.10 upstream)
-- Support multiple languages at the same time, eg: eng+chi\_tra for English and Traditional Chinese
-- Supported image formats: png, jpg, bmp, pbm
-- Support WebAssembly (fallback to ASM.js when browser doesn't support)
-- Support Typescript
-
-Read a story about v2: <a href="https://jeromewu.github.io/why-i-refactor-tesseract.js-v2/">Why I refactor tesseract.js v2?</a><br>
-  Check the <a href="https://github.com/naptha/tesseract.js/tree/support/1.x">support/1.x</a> branch for version 1
-## Installation
-Tesseract.js works with a `<script>` tag via local copy or CDN, with webpack via `npm` and on Node.js with `npm/yarn`.
-
-
-### CDN
-```html
-<!-- v2 -->
-<script src='https://unpkg.com/tesseract.js@v2.1.0/dist/tesseract.min.js'></script>
 
-<!-- v1 -->
+
-<script src='https://unpkg.com/tesseract.js@1.0.19/src/index.js'></script>
+## ImageLike
+
+The main Tesseract.js functions take an `image` parameter, which should be something that is like an image. What's considered "image-like" differs depending on whether it is being run from the browser or through NodeJS.
+
+
+On a browser, an image can be:
+- an `img`, `video`, or `canvas` element
+- a CanvasRenderingContext2D (returned by `canvas.getContext('2d')`)
+- a `File` object (from a file `<input>` or drag-drop event)
+- a `Blob` object
+- a `ImageData` instance (an object containing `width`, `height` and `data` properties)
+- a path or URL to an accessible image (the image must either be hosted locally or accessible by CORS)
+
+
+
+
+In Node.js, an image can be
+- a path to a local image
+- a `Buffer` instance containing a `PNG` or `JPEG` image
+- a `ImageData` instance (an object containing `width`, `height` and `data` properties)
+
+
+## TesseractJob
+
+A TesseractJob is 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.
+
+Typical use is:
+```javascript
+Tesseract.recognize(myImage)
+    .progress(message => console.log(message))
+    .catch(err => console.error(err))
+    .then(result => console.log(result))
+    .finally(resultOrError => console.log(resultOrError))
 ```
-After including the script the `Tesseract` variable will be globally available.
 
+Which is equivalent to:
+```javascript
+var job1 = Tesseract.recognize(myImage);
 
-### Node.js
+job1.progress(message => console.log(message));
 
-**Tesseract.js v3 requires Node.js v14 or higher**
+job1.catch(err => console.error(err));
 
-```shell
+job1.then(result => console.log(result));
-# For v3
-npm install tesseract.js
-yarn add tesseract.js
 
-# For v2
+job1.finally(resultOrError => console.log(resultOrError));
-npm install tesseract.js@2
-yarn add tesseract.js@2
 ```
 
 
-## Documentation
 
-* [Examples](./docs/examples.md)
+### TesseractJob.progress(callback: function) -> TesseractJob
-* [Image Format](./docs/image-format.md)
+Sets `callback` as the function that will be called every time the job progresses.
-* [API](./docs/api.md)
+- `callback` is a function with the signature `callback(progress)` where `progress` is a json object.
-* [Local Installation](./docs/local-installation.md)
-* [FAQ](./docs/faq.md)
 
-## Use tesseract.js the way you like!
+For example:
+```javascript
+Tesseract.recognize(myImage)
+    .progress(function(message){console.log('progress is: ', message)})
+```
 
-- Offline Version: https://github.com/jeromewu/tesseract.js-offline
+The console will show something like:
-- Electron Version: https://github.com/jeromewu/tesseract.js-electron
+```javascript
-- Custom Traineddata: https://github.com/jeromewu/tesseract.js-custom-traineddata
+progress is: {loaded_lang_model: "eng", from_cache: true}
-- Chrome Extension #1: https://github.com/jeromewu/tesseract.js-chrome-extension
+progress is: {initialized_with_lang: "eng"}
-- Chrome Extension #2: https://github.com/fxnoob/image-to-text
+progress is: {set_variable: Object}
-- Firefox Extension: https://github.com/gnonio/korporize
+progress is: {set_variable: Object}
-- With Vue: https://github.com/jeromewu/tesseract.js-vue-app
+progress is: {recognized: 0}
-- With Angular: https://github.com/jeromewu/tesseract.js-angular-app
+progress is: {recognized: 0.3}
-- With React: https://github.com/jeromewu/tesseract.js-react-app
+progress is: {recognized: 0.6}
-- Typescript: https://github.com/jeromewu/tesseract.js-typescript
+progress is: {recognized: 0.9}
-- Video Real-time Recognition: https://github.com/jeromewu/tesseract.js-video
+progress is: {recognized: 1}
+```
 
-## Contributing
 
-### Development
+### TesseractJob.then(callback: function) -> TesseractJob
-To run a development copy of Tesseract.js do the following:
+Sets `callback` as the function that will be called if and when the job successfully completes.
-```shell
+- `callback` is a function with the signature `callback(result)` where `result` is a json object.
-# First we clone the repository
-git clone https://github.com/naptha/tesseract.js.git
-cd tesseract.js
 
-# Then we install the dependencies
-npm install
 
-# And finally we start the development server
+For example:
-npm start
+```javascript
+Tesseract.recognize(myImage)
+    .then(function(result){console.log('result is: ', result)})
 ```
 
-The development server will be available at http://localhost:3000/examples/browser/demo.html in your favorite browser.
+The console will show something like:
-It will automatically rebuild `tesseract.dev.js` and `worker.dev.js` when you change files in the **src** folder.
+```javascript
+result is: {
+    blocks: Array[1]
+    confidence: 87
+    html: "<div class='ocr_page' id='page_1' ..."
+    lines: Array[3]
+    oem: "DEFAULT"
+    paragraphs: Array[1]
+    psm: "SINGLE_BLOCK"
+    symbols: Array[33]
+    text: "Hello World↵from beyond↵the Cosmic Void↵↵"
+    version: "3.04.00"
+    words: Array[7]
+}
+```
 
-### Online Setup with a single Click
+### TesseractJob.catch(callback: function) -> TesseractJob
+Sets `callback` as the function that will be called if the job fails.
+- `callback` is a function with the signature `callback(error)` where `error` is a json object.
 
-You can use Gitpod(A free online VS Code like IDE) for contributing. With a single click it will launch a ready to code workspace with the build & start scripts already in process and within a few seconds it will spin up the dev server so that you can start contributing straight away without wasting any time. 
+### 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.
 
-[![Open in Gitpod](https://gitpod.io/button/open-in-gitpod.svg)](https://gitpod.io/#https://github.com/naptha/tesseract.js/blob/master/examples/browser/demo.html)
+## Local Installation
 
-### Building Static Files
+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.
-To build the compiled static files just execute the following:
+
-```shell
+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.
-npm run build
+
+```javascript
+window.Tesseract = Tesseract.create({
+    workerPath: '/path/to/worker.js',
+    langPath: 'https://tessdata.projectnaptha.com/3.02/',
+    corePath: 'https://cdn.jsdelivr.net/gh/naptha/tesseract.js-core@0.1.0/index.js',
+})
 ```
-This will output the files into the `dist` directory.
 
-## Contributors
+### corePath
+A string specifying the location of the [tesseract.js-core library](https://github.com/naptha/tesseract.js-core), with default value 'https://cdn.jsdelivr.net/gh/naptha/tesseract.js-core@0.1.0/index.js'. Set this string before calling `Tesseract.recognize` and `Tesseract.detect` if you want Tesseract.js to use a different file.
 
-### Code Contributors
+### workerPath
+A string specifying the location of the [worker.js](./dist/worker.js) file. Set this string before calling `Tesseract.recognize` and `Tesseract.detect` if you want Tesseract.js to use a different file.
 
-This project exists thanks to all the people who contribute. [[Contribute](CONTRIBUTING.md)].
+### langPath
-<a href="https://github.com/naptha/tesseract.js/graphs/contributors"><img src="https://opencollective.com/tesseractjs/contributors.svg?width=890&button=false" /></a>
+A string specifying the location of the tesseract language files, with default value 'https://cdn.jsdelivr.net/gh/naptha/tessdata@gh-pages/3.02/'. Language file URLs are calculated according to the formula `langPath + langCode + '.traineddata.gz'`. Set this string before calling `Tesseract.recognize` and `Tesseract.detect` if you want Tesseract.js to use different language files.
 
-### Financial Contributors
 
-Become a financial contributor and help us sustain our community. [[Contribute](https://opencollective.com/tesseractjs/contribute)]
+## Contributing
+### Development
+To run a development copy of tesseract.js, first clone this repo.
+```shell
+> git clone https://github.com/naptha/tesseract.js.git
+```
+
+Then, `cd tesseract.js && npm install && npm start`
+```shell
+> cd tesseract.js
+> npm install && npm start
 
-#### Individuals
+  ... a bunch of npm stuff ...
 
-<a href="https://opencollective.com/tesseractjs"><img src="https://opencollective.com/tesseractjs/individuals.svg?width=890"></a>
+  Starting up http-server, serving ./
+  Available on:
+    http://127.0.0.1:7355
+    http://[your ip]:7355
 
-#### Organizations
+```
+
+Then open `http://localhost:7355/examples/file-input/demo.html` in your favorite browser. The devServer automatically rebuilds `tesseract.js` and `tesseract.worker.js` when you change files in the src folder.
 
-Support this project with your organization. Your logo will show up here with a link to your website. [[Contribute](https://opencollective.com/tesseractjs/contribute)]
+### Building Static Files
+After you've cloned the repo and run `npm install` as described in the [Development Section](#development), you can build static library files in the dist folder with
+```shell
+> npm run build
+```
 
-<a href="https://opencollective.com/tesseractjs/organization/0/website"><img src="https://opencollective.com/tesseractjs/organization/0/avatar.svg"></a>
+### Send us a Pull Request!
-<a href="https://opencollective.com/tesseractjs/organization/1/website"><img src="https://opencollective.com/tesseractjs/organization/1/avatar.svg"></a>
+Thanks :)
-<a href="https://opencollective.com/tesseractjs/organization/2/website"><img src="https://opencollective.com/tesseractjs/organization/2/avatar.svg"></a>
-<a href="https://opencollective.com/tesseractjs/organization/3/website"><img src="https://opencollective.com/tesseractjs/organization/3/avatar.svg"></a>
-<a href="https://opencollective.com/tesseractjs/organization/4/website"><img src="https://opencollective.com/tesseractjs/organization/4/avatar.svg"></a>
-<a href="https://opencollective.com/tesseractjs/organization/5/website"><img src="https://opencollective.com/tesseractjs/organization/5/avatar.svg"></a>
-<a href="https://opencollective.com/tesseractjs/organization/6/website"><img src="https://opencollective.com/tesseractjs/organization/6/avatar.svg"></a>
-<a href="https://opencollective.com/tesseractjs/organization/7/website"><img src="https://opencollective.com/tesseractjs/organization/7/avatar.svg"></a>
-<a href="https://opencollective.com/tesseractjs/organization/8/website"><img src="https://opencollective.com/tesseractjs/organization/8/avatar.svg"></a>
-<a href="https://opencollective.com/tesseractjs/organization/9/website"><img src="https://opencollective.com/tesseractjs/organization/9/avatar.svg"></a>

dist/tesseract.js

@@ -0,0 +1,640 @@
+(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){
+// shim for using process in browser
+var process = module.exports = {};
+
+// cached from whatever global is present so that test runners that stub it
+// don't break things.  But we need to wrap it in a try catch in case it is
+// wrapped in strict mode code which doesn't define any globals.  It's inside a
+// function because try/catches deoptimize in certain engines.
+
+var cachedSetTimeout;
+var cachedClearTimeout;
+
+function defaultSetTimout() {
+    throw new Error('setTimeout has not been defined');
+}
+function defaultClearTimeout () {
+    throw new Error('clearTimeout has not been defined');
+}
+(function () {
+    try {
+        if (typeof setTimeout === 'function') {
+            cachedSetTimeout = setTimeout;
+        } else {
+            cachedSetTimeout = defaultSetTimout;
+        }
+    } catch (e) {
+        cachedSetTimeout = defaultSetTimout;
+    }
+    try {
+        if (typeof clearTimeout === 'function') {
+            cachedClearTimeout = clearTimeout;
+        } else {
+            cachedClearTimeout = defaultClearTimeout;
+        }
+    } catch (e) {
+        cachedClearTimeout = defaultClearTimeout;
+    }
+} ())
+function runTimeout(fun) {
+    if (cachedSetTimeout === setTimeout) {
+        //normal enviroments in sane situations
+        return setTimeout(fun, 0);
+    }
+    // if setTimeout wasn't available but was latter defined
+    if ((cachedSetTimeout === defaultSetTimout || !cachedSetTimeout) && setTimeout) {
+        cachedSetTimeout = setTimeout;
+        return setTimeout(fun, 0);
+    }
+    try {
+        // when when somebody has screwed with setTimeout but no I.E. maddness
+        return cachedSetTimeout(fun, 0);
+    } catch(e){
+        try {
+            // When we are in I.E. but the script has been evaled so I.E. doesn't trust the global object when called normally
+            return cachedSetTimeout.call(null, fun, 0);
+        } catch(e){
+            // same as above but when it's a version of I.E. that must have the global object for 'this', hopfully our context correct otherwise it will throw a global error
+            return cachedSetTimeout.call(this, fun, 0);
+        }
+    }
+
+
+}
+function runClearTimeout(marker) {
+    if (cachedClearTimeout === clearTimeout) {
+        //normal enviroments in sane situations
+        return clearTimeout(marker);
+    }
+    // if clearTimeout wasn't available but was latter defined
+    if ((cachedClearTimeout === defaultClearTimeout || !cachedClearTimeout) && clearTimeout) {
+        cachedClearTimeout = clearTimeout;
+        return clearTimeout(marker);
+    }
+    try {
+        // when when somebody has screwed with setTimeout but no I.E. maddness
+        return cachedClearTimeout(marker);
+    } catch (e){
+        try {
+            // When we are in I.E. but the script has been evaled so I.E. doesn't  trust the global object when called normally
+            return cachedClearTimeout.call(null, marker);
+        } catch (e){
+            // same as above but when it's a version of I.E. that must have the global object for 'this', hopfully our context correct otherwise it will throw a global error.
+            // Some versions of I.E. have different rules for clearTimeout vs setTimeout
+            return cachedClearTimeout.call(this, marker);
+        }
+    }
+
+
+
+}
+var queue = [];
+var draining = false;
+var currentQueue;
+var queueIndex = -1;
+
+function cleanUpNextTick() {
+    if (!draining || !currentQueue) {
+        return;
+    }
+    draining = false;
+    if (currentQueue.length) {
+        queue = currentQueue.concat(queue);
+    } else {
+        queueIndex = -1;
+    }
+    if (queue.length) {
+        drainQueue();
+    }
+}
+
+function drainQueue() {
+    if (draining) {
+        return;
+    }
+    var timeout = runTimeout(cleanUpNextTick);
+    draining = true;
+
+    var len = queue.length;
+    while(len) {
+        currentQueue = queue;
+        queue = [];
+        while (++queueIndex < len) {
+            if (currentQueue) {
+                currentQueue[queueIndex].run();
+            }
+        }
+        queueIndex = -1;
+        len = queue.length;
+    }
+    currentQueue = null;
+    draining = false;
+    runClearTimeout(timeout);
+}
+
+process.nextTick = function (fun) {
+    var args = new Array(arguments.length - 1);
+    if (arguments.length > 1) {
+        for (var i = 1; i < arguments.length; i++) {
+            args[i - 1] = arguments[i];
+        }
+    }
+    queue.push(new Item(fun, args));
+    if (queue.length === 1 && !draining) {
+        runTimeout(drainQueue);
+    }
+};
+
+// v8 likes predictible objects
+function Item(fun, array) {
+    this.fun = fun;
+    this.array = array;
+}
+Item.prototype.run = function () {
+    this.fun.apply(null, this.array);
+};
+process.title = 'browser';
+process.browser = true;
+process.env = {};
+process.argv = [];
+process.version = ''; // empty string to avoid regexp issues
+process.versions = {};
+
+function noop() {}
+
+process.on = noop;
+process.addListener = noop;
+process.once = noop;
+process.off = noop;
+process.removeListener = noop;
+process.removeAllListeners = noop;
+process.emit = noop;
+process.prependListener = noop;
+process.prependOnceListener = noop;
+
+process.listeners = function (name) { return [] }
+
+process.binding = function (name) {
+    throw new Error('process.binding is not supported');
+};
+
+process.cwd = function () { return '/' };
+process.chdir = function (dir) {
+    throw new Error('process.chdir is not supported');
+};
+process.umask = function() { return 0; };
+
+},{}],2:[function(require,module,exports){
+module.exports={
+  "name": "tesseract.js",
+  "version": "1.0.19",
+  "description": "Pure Javascript Multilingual OCR",
+  "main": "src/index.js",
+  "scripts": {
+    "start": "concurrently --kill-others \"watchify src/index.js  -t [ envify --TESS_ENV development ] -t [ babelify --presets [ es2015 ] ] -o dist/tesseract.dev.js --standalone Tesseract\" \"watchify src/browser/worker.js  -t [ envify --TESS_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 && uglifyjs dist/tesseract.js --source-map -o dist/tesseract.min.js && uglifyjs dist/worker.js --source-map -o dist/worker.min.js",
+    "release": "npm run build && git commit -am 'new release' && git push && git tag `jq -r '.version' package.json` && git push origin --tags && npm publish"
+  },
+  "browser": {
+    "./src/node/index.js": "./src/browser/index.js"
+  },
+  "author": "",
+  "license": "Apache-2.0",
+  "devDependencies": {
+    "babel-preset-es2015": "^6.16.0",
+    "babelify": "^7.3.0",
+    "browserify": "^13.1.0",
+    "concurrently": "^3.1.0",
+    "envify": "^3.4.1",
+    "http-server": "^0.9.0",
+    "pako": "^1.0.3",
+    "uglify-js": "^3.4.9",
+    "watchify": "^3.7.0"
+  },
+  "dependencies": {
+    "file-type": "^3.8.0",
+    "isomorphic-fetch": "^2.2.1",
+    "is-url": "1.2.2",
+    "jpeg-js": "^0.2.0",
+    "level-js": "^2.2.4",
+    "node-fetch": "^1.6.3",
+    "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"
+}
+
+},{}],3:[function(require,module,exports){
+(function (process){
+'use strict';
+
+var defaultOptions = {
+    // workerPath: 'https://cdn.jsdelivr.net/gh/naptha/tesseract.js@0.2.0/dist/worker.js',
+    corePath: 'https://cdn.jsdelivr.net/gh/naptha/tesseract.js-core@0.1.0/index.js',
+    langPath: 'https://tessdata.projectnaptha.com/3.02/'
+};
+
+if (process.env.TESS_ENV === "development") {
+    console.debug('Using Development Configuration');
+    defaultOptions.workerPath = location.protocol + '//' + location.host + '/dist/worker.dev.js?nocache=' + Math.random().toString(36).slice(3);
+} else {
+    var version = require('../../package.json').version;
+    defaultOptions.workerPath = 'https://cdn.jsdelivr.net/gh/naptha/tesseract.js@' + version + '/dist/worker.js';
+}
+
+exports.defaultOptions = defaultOptions;
+
+exports.spawnWorker = function spawnWorker(instance, workerOptions) {
+    if (Blob && URL) {
+        var blob = new Blob(['importScripts("' + workerOptions.workerPath + '");'], {
+            type: 'application/javascript'
+        });
+        var worker = new Worker(URL.createObjectURL(blob));
+    } else {
+        var worker = new Worker(workerOptions.workerPath);
+    }
+
+    worker.onmessage = function (e) {
+        var packet = e.data;
+        instance._recv(packet);
+    };
+    return worker;
+};
+
+exports.terminateWorker = function (instance) {
+    instance.worker.terminate();
+};
+
+exports.sendPacket = function sendPacket(instance, packet) {
+    loadImage(packet.payload.image, function (img) {
+        packet.payload.image = img;
+        instance.worker.postMessage(packet);
+    });
+};
+
+function loadImage(image, cb) {
+    if (typeof image === 'string') {
+        if (/^\#/.test(image)) {
+            // element css selector
+            return loadImage(document.querySelector(image), cb);
+        } else if (/(blob|data)\:/.test(image)) {
+            // data url
+            var im = new Image();
+            im.src = image;
+            im.onload = function (e) {
+                return loadImage(im, cb);
+            };
+            im.onerror = function (e) {
+                throw e;
+            };
+            return;
+        } else {
+            var xhr = new XMLHttpRequest();
+            xhr.open('GET', image, true);
+            xhr.responseType = "blob";
+
+            xhr.onload = function (e) {
+                if (xhr.status >= 400) {
+                    throw new Error('Fail to get image as Blob');
+                } else {
+                    loadImage(xhr.response, cb);
+                }
+            };
+            xhr.onerror = function (e) {
+                throw e;
+            };
+
+            xhr.send(null);
+            return;
+        }
+    } else if (image instanceof File) {
+        // files
+        var fr = new FileReader();
+        fr.onload = function (e) {
+            return loadImage(fr.result, cb);
+        };
+        fr.onerror = function (e) {
+            throw e;
+        };
+        fr.readAsDataURL(image);
+        return;
+    } else if (image instanceof Blob) {
+        return loadImage(URL.createObjectURL(image), cb);
+    } else if (image.getContext) {
+        // canvas element
+        return loadImage(image.getContext('2d'), cb);
+    } else if (image.tagName == "IMG" || image.tagName == "VIDEO") {
+        // image element or video element
+        var c = document.createElement('canvas');
+        c.width = image.naturalWidth || image.videoWidth;
+        c.height = image.naturalHeight || image.videoHeight;
+        var ctx = c.getContext('2d');
+        ctx.drawImage(image, 0, 0);
+        return loadImage(ctx, cb);
+    } else if (image.getImageData) {
+        // canvas context
+        var data = image.getImageData(0, 0, image.canvas.width, image.canvas.height);
+        return loadImage(data, cb);
+    } else {
+        return cb(image);
+    }
+    throw new Error('Missing return in loadImage cascade');
+}
+
+}).call(this,require('_process'))
+},{"../../package.json":2,"_process":1}],4:[function(require,module,exports){
+"use strict";
+
+// The result of dump.js is a big JSON tree
+// which can be easily serialized (for instance
+// to be sent from a webworker to the main app
+// or through Node's IPC), but we want
+// a (circular) DOM-like interface for walking
+// through the data. 
+
+module.exports = function circularize(page) {
+    page.paragraphs = [];
+    page.lines = [];
+    page.words = [];
+    page.symbols = [];
+
+    page.blocks.forEach(function (block) {
+        block.page = page;
+
+        block.lines = [];
+        block.words = [];
+        block.symbols = [];
+
+        block.paragraphs.forEach(function (para) {
+            para.block = block;
+            para.page = page;
+
+            para.words = [];
+            para.symbols = [];
+
+            para.lines.forEach(function (line) {
+                line.paragraph = para;
+                line.block = block;
+                line.page = page;
+
+                line.symbols = [];
+
+                line.words.forEach(function (word) {
+                    word.line = line;
+                    word.paragraph = para;
+                    word.block = block;
+                    word.page = page;
+                    word.symbols.forEach(function (sym) {
+                        sym.word = word;
+                        sym.line = line;
+                        sym.paragraph = para;
+                        sym.block = block;
+                        sym.page = page;
+
+                        sym.line.symbols.push(sym);
+                        sym.paragraph.symbols.push(sym);
+                        sym.block.symbols.push(sym);
+                        sym.page.symbols.push(sym);
+                    });
+                    word.paragraph.words.push(word);
+                    word.block.words.push(word);
+                    word.page.words.push(word);
+                });
+                line.block.lines.push(line);
+                line.page.lines.push(line);
+            });
+            para.page.paragraphs.push(para);
+        });
+    });
+    return page;
+};
+
+},{}],5:[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 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.log(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":3}],6:[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 version = require('../package.json').version;
+
+var create = function create() {
+	var workerOptions = arguments.length > 0 && arguments[0] !== undefined ? arguments[0] : {};
+
+	var worker = new TesseractWorker(Object.assign({}, adapter.defaultOptions, workerOptions));
+	worker.create = create;
+	worker.version = version;
+	return worker;
+};
+
+var TesseractWorker = function () {
+	function TesseractWorker(workerOptions) {
+		_classCallCheck(this, TesseractWorker);
+
+		this.worker = null;
+		this.workerOptions = workerOptions;
+		this._currentJob = null;
+		this._queue = [];
+	}
+
+	_createClass(TesseractWorker, [{
+		key: 'recognize',
+		value: function recognize(image) {
+			var _this = this;
+
+			var options = arguments.length > 1 && arguments[1] !== undefined ? arguments[1] : {};
+
+			return this._delay(function (job) {
+				if (typeof options === 'string') options = { lang: options };
+				options.lang = options.lang || 'eng';
+
+				job._send('recognize', { image: image, options: options, workerOptions: _this.workerOptions });
+			});
+		}
+	}, {
+		key: 'detect',
+		value: function detect(image) {
+			var _this2 = this;
+
+			var options = arguments.length > 1 && arguments[1] !== undefined ? arguments[1] : {};
+
+			return this._delay(function (job) {
+				job._send('detect', { image: image, options: options, workerOptions: _this2.workerOptions });
+			});
+		}
+	}, {
+		key: 'terminate',
+		value: function terminate() {
+			if (this.worker) adapter.terminateWorker(this);
+			this.worker = null;
+			this._currentJob = null;
+			this._queue = [];
+		}
+	}, {
+		key: '_delay',
+		value: function _delay(fn) {
+			var _this3 = this;
+
+			if (!this.worker) this.worker = adapter.spawnWorker(this, this.workerOptions);
+
+			var job = new TesseractJob(this);
+			this._queue.push(function (e) {
+				_this3._queue.shift();
+				_this3._currentJob = job;
+				fn(job);
+			});
+			if (!this._currentJob) this._dequeue();
+			return job;
+		}
+	}, {
+		key: '_dequeue',
+		value: function _dequeue() {
+			this._currentJob = null;
+			if (this._queue.length) {
+				this._queue[0]();
+			}
+		}
+	}, {
+		key: '_recv',
+		value: function _recv(packet) {
+			if (packet.status === 'resolve' && packet.action === 'recognize') {
+				packet.data = circularize(packet.data);
+			}
+
+			if (this._currentJob.id === packet.jobId) {
+				this._currentJob._handle(packet);
+			} else {
+				console.warn('Job ID ' + packet.jobId + ' not known.');
+			}
+		}
+	}]);
+
+	return TesseractWorker;
+}();
+
+module.exports = create();
+
+},{"../package.json":2,"./common/circularize.js":4,"./common/job":5,"./node/index.js":3}]},{},[6])(6)
+});

docs/api.md

@@ -1,448 +0,0 @@
-# API
-
-- [createWorker()](#create-worker)
-  - [Worker.load](#worker-load)
-  - [Worker.writeText](#worker-writeText)
-  - [Worker.readText](#worker-readText)
-  - [Worker.removeFile](#worker-removeFile)
-  - [Worker.FS](#worker-FS)
-  - [Worker.loadLanguage](#worker-load-language)
-  - [Worker.initialize](#worker-initialize)
-  - [Worker.setParameters](#worker-set-parameters)
-  - [Worker.recognize](#worker-recognize)
-  - [Worker.detect](#worker-detect)
-  - [Worker.terminate](#worker-terminate)
-- [createScheduler()](#create-scheduler)
-  - [Scheduler.addWorker](#scheduler-add-worker)
-  - [Scheduler.addJob](#scheduler-add-job)
-  - [Scheduler.getQueueLen](#scheduler-get-queue-len)
-  - [Scheduler.getNumWorkers](#scheduler-get-num-workers)
-- [setLogging()](#set-logging)
-- [recognize()](#recognize)
-- [detect()](#detect)
-- [PSM](#psm)
-- [OEM](#oem)
-
----
-
-<a name="create-worker"></a>
-## createWorker(options): Worker
-
-createWorker is a factory function that creates a tesseract worker, a worker is basically a Web Worker in browser and Child Process in Node.
-
-**Arguments:**
-
-- `options` an object of customized options
-  - `corePath` path for tesseract-core.js script
-  - `langPath` path for downloading traineddata, do not include `/` at the end of the path
-  - `workerPath` path for downloading worker script
-  - `dataPath` path for saving traineddata in WebAssembly file system, not common to modify
-  - `cachePath` path for the cached traineddata, more useful for Node, for browser it only changes the key in IndexDB
-  - `cacheMethod` a string to indicate the method of cache management, should be one of the following options
-    - write: read cache and write back (default method)
-    - readOnly: read cache and not to write back
-    - refresh: not to read cache and write back
-    - none: not to read cache and not to write back
-  - `workerBlobURL` a boolean to define whether to use Blob URL for worker script, default: true
-  - `gzip` a boolean to define whether the traineddata from the remote is gzipped, default: true
-  - `logger` a function to log the progress, a quick example is `m => console.log(m)`
-  - `errorHandler` a function to handle worker errors, a quick example is `err => console.error(err)`
-
-
-**Examples:**
-
-```javascript
-const { createWorker } = Tesseract;
-const worker = createWorker({
-  langPath: '...',
-  logger: m => console.log(m),
-});
-```
-
-## Worker
-
-A Worker helps you to do the OCR related tasks, it takes few steps to setup Worker before it is fully functional. The full flow is:
-
-- load
-- FS functions // optional
-- loadLanguauge
-- initialize
-- setParameters // optional
-- recognize or detect
-- terminate
-
-Each function is async, so using async/await or Promise is required. When it is resolved, you get an object:
-
-```json
-{
-  "jobId": "Job-1-123",
-  "data": { ... }
-}
-```
-
-jobId is generated by Tesseract.js, but you can put your own when calling any of the function above.
-
-<a name="worker-load"></a>
-### Worker.load(jobId): Promise
-
-Worker.load() loads tesseract.js-core scripts (download from remote if not presented), it makes Web Worker/Child Process ready for next action.
-
-**Arguments:**
-
-- `jobId` Please see details above
-
-**Examples:**
-
-```javascript
-(async () => {
-  await worker.load();
-})();
-```
-
-<a name="worker-writeText"></a>
-### Worker.writeText(path, text, jobId): Promise
-
-Worker.writeText() writes a text file to the path specified in MEMFS, it is useful when you want to use some features that requires tesseract.js
-to read file from file system.
-
-**Arguments:**
-
-- `path` text file path
-- `text` content of the text file
-- `jobId` Please see details above
-
-**Examples:**
-
-```javascript
-(async () => {
-  await worker.writeText('tmp.txt', 'Hi\nTesseract.js\n');
-})();
-```
-
-<a name="worker-readText"></a>
-### Worker.readText(path, jobId): Promise
-
-Worker.readText() reads a text file to the path specified in MEMFS, it is useful when you want to check the content.
-
-**Arguments:**
-
-- `path` text file path
-- `jobId` Please see details above
-
-**Examples:**
-
-```javascript
-(async () => {
-  const { data } = await worker.readText('tmp.txt');
-  console.log(data);
-})();
-```
-
-<a name="worker-removeFile"></a>
-### Worker.removeFile(path, jobId): Promise
-
-Worker.readFile() remove a file in MEMFS, it is useful when you want to free the memory.
-
-**Arguments:**
-
-- `path` file path
-- `jobId` Please see details above
-
-**Examples:**
-
-```javascript
-(async () => {
-  await worker.removeFile('tmp.txt');
-})();
-```
-
-<a name="worker-FS"></a>
-### Worker.FS(method, args, jobId): Promise
-
-Worker.FS() is a generic FS function to do anything you want, you can check [HERE](ihttps://emscripten.org/docs/api_reference/Filesystem-API.html) for all functions.
-
-**Arguments:**
-
-- `method` method name
-- `args` array of arguments to pass  
-- `jobId` Please see details above
-
-**Examples:**
-
-```javascript
-(async () => {
-  await worker.FS('writeFile', ['tmp.txt', 'Hi\nTesseract.js\n']);
-  // equal to:
-  // await worker.readText('tmp.txt', 'Hi\nTesseract.js\n');
-})();
-```
-
-<a name="worker-load-language"></a>
-### Worker.loadLanguage(langs, jobId): Promise
-
-Worker.loadLanguage() loads traineddata from cache or download traineddata from remote, and put traineddata into the WebAssembly file system.
-
-**Arguments:**
-
-- `langs` a string to indicate the languages traineddata to download, multiple languages are concated with **+**, ex: **eng+chi\_tra**
-- `jobId` Please see details above
-
-**Examples:**
-
-```javascript
-(async () => {
-  await worker.loadLanguage('eng+chi_tra');
-})();
-```
-
-<a name="worker-initialize"></a>
-### Worker.initialize(langs, oem, jobId): Promise
-
-Worker.initialize() initializes the Tesseract API, make sure it is ready for doing OCR tasks.
-
-**Arguments:**
-
-- `langs` a string to indicate the languages loaded by Tesseract API, it can be the subset of the languauge traineddata you loaded from Worker.loadLanguage.
-- `oem` a enum to indicate the OCR Engine Mode you use
-- `jobId` Please see details above
-
-**Examples:**
-
-```javascript
-(async () => {
-  /** You can load more languages in advance, but use only part of them in Worker.initialize() */
-  await worker.loadLanguage('eng+chi_tra');
-  await worker.initialize('eng');
-})();
-```
-<a name="worker-set-parameters"></a>
-### Worker.setParameters(params, jobId): Promise
-
-Worker.setParameters() set parameters for Tesseract API (using SetVariable()), it changes the behavior of Tesseract and some parameters like tessedit\_char\_whitelist is very useful.
-
-**Arguments:**
-
-- `params` an object with key and value of the parameters
-- `jobId` Please see details above
-
-**Supported Paramters:**
-
-| name                        | type   | default value     | description                                                                                                                     |
-| --------------------------- | ------ | ----------------- | ------------------------------------------------------------------------------------------------------------------------------- |
-| tessedit\_ocr\_engine\_mode | enum   | OEM.DEFAULT       | Check [HERE](https://github.com/tesseract-ocr/tesseract/blob/4.0.0/src/ccstruct/publictypes.h#L268) for definition of each mode |
-| tessedit\_pageseg\_mode     | enum   | PSM.SINGLE\_BLOCK | Check [HERE](https://github.com/tesseract-ocr/tesseract/blob/4.0.0/src/ccstruct/publictypes.h#L163) for definition of each mode |
-| tessedit\_char\_whitelist   | string | ''                | setting white list characters makes the result only contains these characters, useful the content in image is limited           |
-| preserve\_interword\_spaces | string | '0'               | '0' or '1', keeps the space between words                                                                                       |
-| user\_defined\_dpi          | string | ''                | Define custom dpi, use to fix **Warning: Invalid resolution 0 dpi. Using 70 instead.**                                          |
-| tessjs\_create\_hocr        | string | '1'               | only 2 values, '0' or '1', when the value is '1', tesseract.js includes hocr in the result                                      |
-| tessjs\_create\_tsv         | string | '1'               | only 2 values, '0' or '1', when the value is '1', tesseract.js includes tsv in the result                                       |
-| tessjs\_create\_box         | string | '0'               | only 2 values, '0' or '1', when the value is '1', tesseract.js includes box in the result                                       |
-| tessjs\_create\_unlv        | string | '0'               | only 2 values, '0' or '1', when the value is '1', tesseract.js includes unlv in the result                                      |
-| tessjs\_create\_osd         | string | '0'               | only 2 values, '0' or '1', when the value is '1', tesseract.js includes osd in the result                                       |
-
-**Examples:**
-
-```javascript
-(async () => {
-  await worker.setParameters({
-    tessedit_char_whitelist: '0123456789',
-  });
-})
-```
-
-<a name="worker-recognize"></a>
-### Worker.recognize(image, options, jobId): Promise
-
-Worker.recognize() provides core function of Tesseract.js as it executes OCR
-
-Figures out what words are in `image`, where the words are in `image`, etc.
-> Note: `image` should be sufficiently high resolution.
-> Often, the same image will get much better results if you upscale it before calling `recognize`.
-
-**Arguments:**
-
-- `image` see [Image Format](./image-format.md) for more details.
-- `options` a object of customized options
-  - `rectangle` an object to specify the regions you want to recognized in the image, should contain top, left, width and height, see example below.
-- `jobId` Please see details above
-
-**Output:**
-
-**Examples:**
-
-```javascript
-const { createWorker } = Tesseract;
-(async () => {
-  const worker = createWorker();
-  await worker.load();
-  await worker.loadLanguage('eng');
-  await worker.initialize('eng');
-  const { data: { text } } = await worker.recognize(image);
-  console.log(text);
-})();
-```
-
-With rectangle
-
-```javascript
-const { createWorker } = Tesseract;
-(async () => {
-  const worker = createWorker();
-  await worker.load();
-  await worker.loadLanguage('eng');
-  await worker.initialize('eng');
-  const { data: { text } } = await worker.recognize(image, {
-    rectangle: { top: 0, left: 0, width: 100, height: 100 },
-  });
-  console.log(text);
-})();
-```
-
-<a name="worker-detect"></a>
-### Worker.detect(image, jobId): Promise
-
-Worker.detect() does OSD (Orientation and Script Detection) to the image instead of OCR.
-
-**Arguments:**
-
-- `image` see [Image Format](./image-format.md) for more details.
-- `jobId` Please see details above
-
-**Examples:**
-
-```javascript
-const { createWorker } = Tesseract;
-(async () => {
-  const worker = createWorker();
-  await worker.load();
-  await worker.loadLanguage('eng');
-  await worker.initialize('eng');
-  const { data } = await worker.detect(image);
-  console.log(data);
-})();
-```
-
-<a name="worker-terminate"></a>
-### Worker.terminate(jobId): Promise
-
-Worker.terminate() terminates the worker and cleans up
-
-```javascript
-(async () => {
-  await worker.terminate();
-})();
-```
-
-<a name="create-scheduler"></a>
-## createScheduler(): Scheduler
-
-createScheduler() is a factory function to create a scheduler, a scheduler manages a job queue and workers to enable multiple workers to work together, it is useful when you want to speed up your performance.
-
-**Examples:**
-
-```javascript
-const { createScheduler } = Tesseract;
-const scheduler = createScheduler();
-```
-
-### Scheduler
-
-<a name="scheduler-add-worker"></a>
-### Scheduler.addWorker(worker): string
-
-Scheduler.addWorker() adds a worker into the worker pool inside scheduler, it is suggested to add one worker to only one scheduler.
-
-**Arguments:**
-
-- `worker` see Worker above
-
-**Examples:**
-
-```javascript
-const { createWorker, createScheduler } = Tesseract;
-const scheduler = createScheduler();
-const worker = createWorker();
-scheduler.addWorker(worker);
-```
-
-<a name="scheduler-add-job"></a>
-### Scheduler.addJob(action, ...payload): Promise
-
-Scheduler.addJob() adds a job to the job queue and scheduler waits and finds an idle worker to take the job.
-
-**Arguments:**
-
-- `action` a string to indicate the action you want to do, right now only **recognize** and **detect** are supported
-- `payload` a arbitrary number of args depending on the action you called.
-
-**Examples:**
-
-```javascript
-(async () => {
- const { data: { text } } = await scheduler.addJob('recognize', image, options);
- const { data } = await scheduler.addJob('detect', image);
-})();
-```
-
-<a name="scheduler-get-queue-len"></a>
-### Scheduler.getQueueLen(): number
-
-Scheduler.getNumWorkers() returns the length of job queue.
-
-<a name="scheduler-get-num-workers"></a>
-### Scheduler.getNumWorkers(): number
-
-Scheduler.getNumWorkers() returns number of workers added into the scheduler
-
-<a name="scheduler-terminate"></a>
-### Scheduler.terminate(): Promise
-
-Scheduler.terminate() terminates all workers added, useful to do quick clean up.
-
-**Examples:**
-
-```javascript
-(async () => {
-  await scheduler.terminate();
-})();
-```
-
-<a name="set-logging"></a>
-## setLogging(logging: boolean)
-
-setLogging() sets the logging flag, you can `setLogging(true)` to see detailed information, useful for debugging.
-
-**Arguments:**
-
-- `logging` boolean to define whether to see detailed logs, default: false
-
-**Examples:**
-
-```javascript
-const { setLogging } = Tesseract;
-setLogging(true);
-```
-
-<a name="recognize"></a>
-## recognize(image, langs, options): Promise
-
-recognize() is a function to quickly do recognize() task, it is not recommended to use in real application, but useful when you want to save some time.
-
-See [Tesseract.js](../src/Tesseract.js)
-
-<a name="detect"></a>
-## detect(image, options): Promise
-
-Same background as recognize(), but it does detect instead.
-
-See [Tesseract.js](../src/Tesseract.js)
-
-<a name="psm"></a>
-## PSM
-
-See [PSM.js](../src/constants/PSM.js)
-
-<a name="oem"></a>
-## OEM
-
-See [OEM.js](../src/constants/OEM.js)

docs/examples.md

@@ -1,226 +0,0 @@
-# Tesseract.js Examples
-
-You can also check [examples](../examples) folder.
-
-### basic
-
-```javascript
-const { createWorker } = require('tesseract.js');
-
-const worker = createWorker();
-
-(async () => {
-  await worker.load();
-  await worker.loadLanguage('eng');
-  await worker.initialize('eng');
-  const { data: { text } } = await worker.recognize('https://tesseract.projectnaptha.com/img/eng_bw.png');
-  console.log(text);
-  await worker.terminate();
-})();
-```
-
-### with detailed progress 
-
-```javascript
-const { createWorker } = require('tesseract.js');
-
-const worker = createWorker({
-  logger: m => console.log(m), // Add logger here
-});
-
-(async () => {
-  await worker.load();
-  await worker.loadLanguage('eng');
-  await worker.initialize('eng');
-  const { data: { text } } = await worker.recognize('https://tesseract.projectnaptha.com/img/eng_bw.png');
-  console.log(text);
-  await worker.terminate();
-})();
-```
-
-### with multiple languages, separate by '+'
-
-```javascript
-const { createWorker } = require('tesseract.js');
-
-const worker = createWorker();
-
-(async () => {
-  await worker.load();
-  await worker.loadLanguage('eng+chi_tra');
-  await worker.initialize('eng+chi_tra');
-  const { data: { text } } = await worker.recognize('https://tesseract.projectnaptha.com/img/eng_bw.png');
-  console.log(text);
-  await worker.terminate();
-})();
-```
-### with whitelist char (^2.0.0-beta.1)
-
-```javascript
-const { createWorker } = require('tesseract.js');
-
-const worker = createWorker();
-
-(async () => {
-  await worker.load();
-  await worker.loadLanguage('eng');
-  await worker.initialize('eng');
-  await worker.setParameters({
-    tessedit_char_whitelist: '0123456789',
-  });
-  const { data: { text } } = await worker.recognize('https://tesseract.projectnaptha.com/img/eng_bw.png');
-  console.log(text);
-  await worker.terminate();
-})();
-```
-
-### with different pageseg mode (^2.0.0-beta.1)
-
-Check here for more details of pageseg mode: https://github.com/tesseract-ocr/tesseract/blob/4.0.0/src/ccstruct/publictypes.h#L163
-
-```javascript
-const { createWorker, PSM } = require('tesseract.js');
-
-const worker = createWorker();
-
-(async () => {
-  await worker.load();
-  await worker.loadLanguage('eng');
-  await worker.initialize('eng');
-  await worker.setParameters({
-    tessedit_pageseg_mode: PSM.SINGLE_BLOCK,
-  });
-  const { data: { text } } = await worker.recognize('https://tesseract.projectnaptha.com/img/eng_bw.png');
-  console.log(text);
-  await worker.terminate();
-})();
-```
-
-### with pdf output (^2.0.0-beta.1)
-
-Please check **examples** folder for details.
-
-Browser: [download-pdf.html](../examples/browser/download-pdf.html)
-Node: [download-pdf.js](../examples/node/download-pdf.js)
-
-### with only part of the image (^2.0.1)
-
-**One rectangle**
-
-```javascript
-const { createWorker } = require('tesseract.js');
-
-const worker = createWorker();
-const rectangle = { left: 0, top: 0, width: 500, height: 250 };
-
-(async () => {
-  await worker.load();
-  await worker.loadLanguage('eng');
-  await worker.initialize('eng');
-  const { data: { text } } = await worker.recognize('https://tesseract.projectnaptha.com/img/eng_bw.png', { rectangle });
-  console.log(text);
-  await worker.terminate();
-})();
-```
-
-**Multiple Rectangles**
-
-```javascript
-const { createWorker } = require('tesseract.js');
-
-const worker = createWorker();
-const rectangles = [
-  {
-    left: 0,
-    top: 0,
-    width: 500,
-    height: 250,
-  },
-  {
-    left: 500,
-    top: 0,
-    width: 500,
-    height: 250,
-  },
-];
-
-(async () => {
-  await worker.load();
-  await worker.loadLanguage('eng');
-  await worker.initialize('eng');
-  const values = [];
-  for (let i = 0; i < rectangles.length; i++) {
-    const { data: { text } } = await worker.recognize('https://tesseract.projectnaptha.com/img/eng_bw.png', { rectangle: rectangles[i] });
-    values.push(text);
-  }
-  console.log(values);
-  await worker.terminate();
-})();
-```
-
-**Multiple Rectangles (with scheduler to do recognition in parallel)**
-
-```javascript
-const { createWorker, createScheduler } = require('tesseract.js');
-
-const scheduler = createScheduler();
-const worker1 = createWorker();
-const worker2 = createWorker();
-const rectangles = [
-  {
-    left: 0,
-    top: 0,
-    width: 500,
-    height: 250,
-  },
-  {
-    left: 500,
-    top: 0,
-    width: 500,
-    height: 250,
-  },
-];
-
-(async () => {
-  await worker1.load();
-  await worker2.load();
-  await worker1.loadLanguage('eng');
-  await worker2.loadLanguage('eng');
-  await worker1.initialize('eng');
-  await worker2.initialize('eng');
-  scheduler.addWorker(worker1);
-  scheduler.addWorker(worker2);
-  const results = await Promise.all(rectangles.map((rectangle) => (
-    scheduler.addJob('recognize', 'https://tesseract.projectnaptha.com/img/eng_bw.png', { rectangle })
-  )));
-  console.log(results.map(r => r.data.text));
-  await scheduler.terminate();
-})();
-```
-
-### with multiple workers to speed up (^2.0.0-beta.1)
-
-```javascript
-const { createWorker, createScheduler } = require('tesseract.js');
-
-const scheduler = createScheduler();
-const worker1 = createWorker();
-const worker2 = createWorker();
-
-(async () => {
-  await worker1.load();
-  await worker2.load();
-  await worker1.loadLanguage('eng');
-  await worker2.loadLanguage('eng');
-  await worker1.initialize('eng');
-  await worker2.initialize('eng');
-  scheduler.addWorker(worker1);
-  scheduler.addWorker(worker2);
-  /** Add 10 recognition jobs */
-  const results = await Promise.all(Array(10).fill(0).map(() => (
-    scheduler.addJob('recognize', 'https://tesseract.projectnaptha.com/img/eng_bw.png')
-  )))
-  console.log(results);
-  await scheduler.terminate(); // It also terminates all workers.
-})();
-```

docs/faq.md

@@ -1,42 +0,0 @@
-FAQ
-===
-
-## How does tesseract.js download and keep \*.traineddata?
-
-The language model is downloaded by `worker.loadLanguage()` and you need to pass the langs to `worker.initialize()`.
-
-During the downloading of language model, Tesseract.js will first check if \*.traineddata already exists. (browser: [IndexedDB](https://developer.mozilla.org/en-US/docs/Web/API/IndexedDB_API), Node.js: fs, in the folder you execute the command) If the \*.traineddata doesn't exist, it will fetch \*.traineddata.gz from [tessdata](https://github.com/naptha/tessdata), ungzip and store in IndexedDB or fs, you can delete it manually and it will download again for you.
-
-## How can I train my own \*.traineddata?
-
-For tesseract.js v2, check [TrainingTesseract 4.00](https://tesseract-ocr.github.io/tessdoc/TrainingTesseract-4.00)
-
-For tesseract.js v1, check [Training Tesseract 3.03–3.05](https://tesseract-ocr.github.io/tessdoc/Training-Tesseract-3.03%E2%80%933.05)
-
-## How can I get HOCR, TSV, Box, UNLV, OSD?
-
-Starting from 2.0.0-beta.1, you can get all these information in the final result.
-
-```javascript
-import { createWorker } from 'tesseract.js';
-const worker = createWorker({
-  logger: m => console.log(m)
-});
-
-(async () => {
-  await worker.load();
-  await worker.loadLanguage('eng');
-  await worker.initialize('eng');
-  await worker.setParameters({
-    tessedit_create_box: '1',
-    tessedit_create_unlv: '1',
-    tessedit_create_osd: '1',
-  });
-  const { data: { text, hocr, tsv, box, unlv } } = await worker.recognize('https://tesseract.projectnaptha.com/img/eng_bw.png');
-  console.log(text);
-  console.log(hocr);
-  console.log(tsv);
-  console.log(box);
-  console.log(unlv);
-})();
-```

docs/image-format.md

@@ -1,18 +0,0 @@
-# Image Format
-
-The main Tesseract.js functions (ex. recognize, detect) take an `image` parameter.  The image formats and data types supported are listed below. 
-
-Support Image Formats: **bmp, jpg, png, pbm, webp**
-
-For browser and Node, supported data types are:
- - string with base64 encoded image (fits `data:image\/([a-zA-Z]*);base64,([^"]*)` regexp)
- - buffer
-
-For browser only, supported data types are:
- - `File` or `Blob` object
- - `img` or `canvas` element
-
-For Node only, supported data types are:
- - string containing a path to local image
-
-Note: images must be a supported image format **and** a supported data type.  For example, a buffer containing a png image is supported.  A buffer containing raw pixel data is not supported. 

docs/local-installation.md

@@ -1,38 +0,0 @@
-## Local Installation
-
-Check here for examples: https://github.com/naptha/tesseract.js/blob/master/docs/examples.md 
-
-In browser environment, `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 pass extra arguments to `TesseractWorker` to specify custom paths for workers, languages, and core.
-
-In Node.js environment, the only path you may want to customize is languages/langPath.
-
-```javascript
-Tesseract.recognize(image, langs, {
-  workerPath: 'https://unpkg.com/tesseract.js@v2.0.0/dist/worker.min.js',
-  langPath: 'https://tessdata.projectnaptha.com/4.0.0',
-  corePath: 'https://unpkg.com/tesseract.js-core@v2.0.0/tesseract-core.wasm.js',
-})
-```
-
-Or
-
-```javascript
-const worker = createWorker({
-  workerPath: 'https://unpkg.com/tesseract.js@v2.0.0/dist/worker.min.js',
-  langPath: 'https://tessdata.projectnaptha.com/4.0.0',
-  corePath: 'https://unpkg.com/tesseract.js-core@v2.0.0/tesseract-core.wasm.js',
-});
-```
-
-### workerPath
-A string specifying the location of the [worker.js](./dist/worker.min.js) file.
-
-### langPath
-A string specifying the location of the tesseract language files, with default value 'https://tessdata.projectnaptha.com/4.0.0'. Language file URLs are calculated according to the formula `langPath + langCode + '.traineddata.gz'`.
-
-### corePath
-A string specifying the location of the [tesseract.js-core library](https://github.com/naptha/tesseract.js-core), with default value 'https://unpkg.com/tesseract.js-core@v2.0.0/tesseract-core.wasm.js' (fallback to tesseract-core.asm.js when WebAssembly is not available).
-
-Another WASM option is 'https://unpkg.com/tesseract.js-core@v2.0.0/tesseract-core.js' which is a script that loads 'https://unpkg.com/tesseract.js-core@v2.0.0/tesseract-core.wasm'. But it fails to fetch at this moment.

docs/tesseract_lang_list.md

@@ -1,3 +1,72 @@
 # Tesseract Languages
 
-Please check [HERE](https://tesseract-ocr.github.io/tessdoc/Data-Files#data-files-for-version-400-november-29-2016) for supported languages
+The `lang` property of the options object passed to `Tesseract.recognize` can have one of the following values (the default is `'eng'`.):
+
+| `lang`    | Language              | 
+|-----------|-----------------------| 
+| 'afr'     | Afrikaans             | 
+| 'ara'     | Arabic                | 
+| 'aze'     | Azerbaijani           | 
+| 'bel'     | Belarusian            | 
+| 'ben'     | Bengali               | 
+| 'bul'     | Bulgarian             | 
+| 'cat'     | Catalan               | 
+| 'ces'     | Czech                 | 
+| 'chi_sim' | Chinese               | 
+| 'chi_tra' | Traditional Chinese   | 
+| 'chr'     | Cherokee              | 
+| 'dan'     | Danish                | 
+| 'deu'     | German                | 
+| 'ell'     | Greek                 | 
+| 'eng'     | English                | 
+| 'enm'     | English (Old)         | 
+| 'epo'     | Esperanto             | 
+| 'epo_alt' | Esperanto alternative | 
+| 'equ'     | Math                  | 
+| 'est'     | Estonian              | 
+| 'eus'     | Basque                | 
+| 'fas'     |Persian (Farsi)        |
+| 'fin'     | Finnish               | 
+| 'fra'     | French                | 
+| 'frk'     | Frankish              | 
+| 'frm'     | French (Old)          | 
+| 'glg'     | Galician              | 
+| 'grc'     | Ancient Greek         | 
+| 'heb'     | Hebrew                | 
+| 'hin'     | Hindi                 | 
+| 'hrv'     | Croatian              | 
+| 'hun'     | Hungarian             | 
+| 'ind'     | Indonesian            | 
+| 'isl'     | Icelandic             | 
+| 'ita'     | Italian               | 
+| 'ita_old' | Italian (Old)         | 
+| 'jpn'     | Japanese              | 
+| 'kan'     | Kannada               | 
+| 'kor'     | Korean                | 
+| 'lav'     | Latvian               | 
+| 'lit'     | Lithuanian            | 
+| 'mal'     | Malayalam             | 
+| 'mkd'     | Macedonian            | 
+| 'mlt'     | Maltese               | 
+| 'msa'     | Malay                 | 
+| 'nld'     | Dutch                 | 
+| 'nor'     | Norwegian             | 
+| 'pol'     | Polish                | 
+| 'por'     | Portuguese            | 
+| 'ron'     | Romanian              | 
+| 'rus'     | Russian               | 
+| 'slk'     | Slovakian             | 
+| 'slv'     | Slovenian             | 
+| 'spa'     | Spanish               | 
+| 'spa_old' | Old Spanish           | 
+| 'sqi'     | Albanian              | 
+| 'srp'     | Serbian (Latin)       | 
+| 'swa'     | Swahili               | 
+| 'swe'     | Swedish               | 
+| 'tam'     | Tamil                 | 
+| 'tel'     | Telugu                | 
+| 'tgl'     | Tagalog               | 
+| 'tha'     | Thai                  | 
+| 'tur'     | Turkish               | 
+| 'ukr'     | Ukrainian             | 
+| 'vie'     | Vietnamese            | 

examples/browser/basic-edge.html

@@ -1,37 +0,0 @@
-<!DOCTYPE HTML>
-<html>
-  <head>
-    <script src="/dist/tesseract.dev.js"></script>
-  </head>
-  <body>
-    <input type="file" id="uploader">
-    <script>
-      const recognize = function(evt){
-        const files = evt.target.files;
-        const worker = Tesseract.createWorker({
-          /*
-           * As Edge don't support webassembly,
-           * here we force to use asm.js version.
-           */
-          corePath: '../../node_modules/tesseract.js-core/tesseract-core.asm.js',
-          logger: function(m){console.log(m);},
-          /*
-           * As there is no indexedDB in earlier version
-           * of Edge, here we disable cache.
-           */
-          cacheMethod: 'none',
-        });
-        Promise.resolve()
-          .then(() => worker.load())
-          .then(() => worker.loadLanguage('eng'))
-          .then(() => worker.initialize('eng'))
-          .then(() => worker.recognize(files[0]))
-          .then((ret) => {
-            console.log(ret.data.text);
-          });
-      }
-      const elm = document.getElementById('uploader');
-      elm.addEventListener('change', recognize);
-    </script>
-  </body>
-</html>

examples/browser/basic.html

@@ -1,19 +0,0 @@
-<html>
-  <head>
-    <script src="/dist/tesseract.dev.js"></script>
-  </head>
-  <body>
-    <input type="file" id="uploader">
-    <script>
-      const recognize = async ({ target: { files }  }) => {
-        const { data: { text } } = await Tesseract.recognize(files[0], 'eng', {
-          corePath: '../../node_modules/tesseract.js-core/tesseract-core.wasm.js',
-          logger: m => console.log(m),
-        });
-        console.log(text);
-      }
-      const elm = document.getElementById('uploader');
-      elm.addEventListener('change', recognize);
-    </script>
-  </body>
-</html>

examples/browser/benchmark.html

@@ -1,33 +0,0 @@
-<html>
-  <head>
-    <script src="/dist/tesseract.dev.js"></script>
-  </head>
-  <body>
-    <textarea id="message">Working...</textarea>
-
-    <script>
-      const { createWorker } = Tesseract;
-      const worker = createWorker();
-      (async () => {
-        await worker.load();
-        await worker.loadLanguage('eng');
-        await worker.initialize('eng');
-        
-        const fileArr = ["../data/meditations.jpg", "../data/tyger.jpg", "../data/testocr.png"];
-        let timeTotal = 0;
-        for (let file of fileArr) {
-            let time1 = Date.now();
-            for (let i=0; i < 10; i++) {
-                await worker.recognize(file);
-            }
-            let time2 = Date.now();
-            const timeDif = (time2 - time1) / 1e3;
-            timeTotal += timeDif;
-            document.getElementById('message').innerHTML += "\n" + file + " [x10] runtime: " + timeDif + "s";
-        }
-        document.getElementById('message').innerHTML += "\nTotal runtime: " + timeTotal + "s";
-
-      })();
-    </script>
-  </body>
-</html>

examples/browser/download-pdf.html

@@ -1,52 +0,0 @@
-<html>
-  <head>
-    <script src="/dist/tesseract.dev.js"></script>
-  </head>
-  <body>
-    <div>
-      <input type="file" id="uploader">
-      <button id="download-pdf" disabled="true">Download PDF</button>
-    </div>
-    <textarea id="board" readonly rows="8" cols="80">Upload an image file</textarea>
-    <script>
-      const { createWorker } = Tesseract;
-      const worker = createWorker({
-        corePath: '/node_modules/tesseract.js-core/tesseract-core.wasm.js',
-        logger: m => console.log(m),
-      });
-      const uploader = document.getElementById('uploader');
-      const dlBtn = document.getElementById('download-pdf');
-      const recognize = async ({ target: { files }  }) => {
-        await worker.load();
-        await worker.loadLanguage('eng');
-        await worker.initialize('eng');
-        const { data: { text } } = await worker.recognize(files[0]);
-        const board = document.getElementById('board');
-        board.value = text;
-        dlBtn.disabled = false;
-      };
-      const downloadPDF = async () => {
-        const filename = 'tesseract-ocr-result.pdf';
-        const { data } = await worker.getPDF('Tesseract OCR Result');
-        const blob = new Blob([new Uint8Array(data)], { type: 'application/pdf' });
-        if (navigator.msSaveBlob) {
-          // IE 10+
-          navigator.msSaveBlob(blob, filename);
-        } else {
-          const link = document.createElement('a');
-          if (link.download !== undefined) {
-            const url = URL.createObjectURL(blob);
-            link.setAttribute('href', url);
-            link.setAttribute('download', filename);
-            link.style.visibility = 'hidden';
-            document.body.appendChild(link);
-            link.click();
-            document.body.removeChild(link);
-          }
-        }
-      };
-      uploader.addEventListener('change', recognize);
-      dlBtn.addEventListener('click', downloadPDF);
-    </script>
-  </body>
-</html>

examples/file-input/README.md

@@ -0,0 +1 @@
+# 

examples/file-input/basic.html

@@ -0,0 +1,2 @@
+<script src="/dist/tesseract.dev.js"></script>
+<input type="file" onchange="Tesseract.recognize(this.files[0]).progress(function(data){console.log(data)}).then(function(data){console.log(data)})">

examples/file-input/demo.html

@@ -27,7 +27,7 @@ function progressUpdate(packet){
 
 		if(packet.status == 'done'){
 			var pre = document.createElement('pre')
-			pre.appendChild(document.createTextNode(packet.data.data.text))
+			pre.appendChild(document.createTextNode(packet.data.text))
 			line.innerHTML = ''
 			line.appendChild(pre)
 
@@ -37,18 +37,21 @@ function progressUpdate(packet){
 	}
 }
 
-async function recognizeFile(file) {
+function recognizeFile(file){
 	document.querySelector("#log").innerHTML = ''
-  const corePath = window.navigator.userAgent.indexOf("Edge") > -1
+
-    ? '../../node_modules/tesseract.js-core/tesseract-core.asm.js'
+	Tesseract.recognize(file, {
-    : '../../node_modules/tesseract.js-core/tesseract-core.wasm.js';
+		lang: document.querySelector('#langsel').value
-
+	})
-  const lang = document.querySelector('#langsel').value
+		.progress(function(packet){
-  const data = await Tesseract.recognize(file, lang, {
+			console.info(packet)
-    corePath,
+			progressUpdate(packet)
-    logger: progressUpdate,
+
-  });
+		})
-  progressUpdate({ status: 'done', data });
+		.then(function(data){
+			console.log(data)
+			progressUpdate({ status: 'done', data: data })
+		})
 }
 </script>
 <select id="langsel" onchange="window.lastFile && recognizeFile(window.lastFile)">
@@ -71,6 +74,7 @@ async function recognizeFile(file) {
 <option value='meme'     > Internet Meme                </option>
 <option value='epo'     > Esperanto             </option>
 <option value='epo_alt' > Esperanto alternative </option>
+<option value='equ'     > Math                  </option>
 <option value='est'     > Estonian              </option>
 <option value='eus'     > Basque                </option>
 <option value='fin'     > Finnish               </option>
@@ -119,7 +123,7 @@ async function recognizeFile(file) {
 <option value='vie'     > Vietnamese            </option>
 </select>
 
-<button onclick="recognizeFile('../../tests/assets/images/simple.png')">Sample Image</button>
+<button onclick="recognizeFile('../node/cosmic.png')">Sample Image</button>
 <input type="file" onchange="recognizeFile(window.lastFile=this.files[0])">
 
 <div id="log"></div>

examples/node/basic.js

@@ -0,0 +1,15 @@
+// replace this with require('tesseract.js')
+var Tesseract = require('../../'),
+    image = require('path').resolve(__dirname, 'cosmic.png');
+
+Tesseract.recognize(image)
+    .then(data => {
+        console.log('then\n', data.text)
+    })
+    .catch(err => {
+      console.log('catch\n', err);
+    })
+    .finally(e => {
+      console.log('finally\n');
+      process.exit();
+    });

examples/node/benchmark.js

@@ -1,27 +0,0 @@
-#!/usr/bin/env node
-const path = require('path');
-const { createWorker } = require('../../');
-
-const worker = createWorker();
-
-(async () => {
-  await worker.load();
-  await worker.loadLanguage('eng');
-  await worker.initialize('eng');
-  const fileArr = ["../data/meditations.jpg", "../data/tyger.jpg", "../data/testocr.png"];
-  let timeTotal = 0;
-  for (let file of fileArr) {
-      let time1 = Date.now();
-      for (let i=0; i < 10; i++) {
-          await worker.recognize(file)
-      }
-      let time2 = Date.now();
-      const timeDif = (time2 - time1) / 1e3;
-      timeTotal += timeDif;
-
-      console.log(file + " [x10] runtime: " + timeDif + "s");
-    }
-console.log("Total runtime: " + timeTotal + "s");
-
-await worker.terminate();
-})();

examples/node/detect.js

@@ -1,13 +1,12 @@
-#!/usr/bin/env node
+// replace this with require('tesseract.js')
-const path = require('path');
+var Tesseract = require('../../'),
-const Tesseract = require('../../');
+	image = require('path').resolve(__dirname, 'cosmic.png');
 
-const [,, imagePath] = process.argv;
+Tesseract.detect(image)
-const image = path.resolve(__dirname, (imagePath || '../../tests/assets/images/cosmic.png'));
+	.progress(function(info){
-
+		console.log(info);
-console.log(`Recognizing ${image}`);
+	})
-
+	.then(function(data){
-Tesseract.detect(image, { logger: m => console.log(m) })
+		console.log('done', data);
-  .then(({ data }) => {
+		process.exit();
-    console.log(data);
+	})
-  });

examples/node/download-pdf.js

@@ -1,22 +0,0 @@
-#!/usr/bin/env node
-const path = require('path');
-const fs = require('fs');
-const { createWorker } = require('../../');
-
-const [,, imagePath] = process.argv;
-const image = path.resolve(__dirname, (imagePath || '../../tests/assets/images/cosmic.png'));
-
-console.log(`Recognizing ${image}`);
-
-(async () => {
-  const worker = createWorker();
-  await worker.load();
-  await worker.loadLanguage('eng');
-  await worker.initialize('eng');
-  const { data: { text } } = await worker.recognize(image);
-  console.log(text);
-  const { data } = await worker.getPDF('Tesseract OCR Result');
-  fs.writeFileSync('tesseract-ocr-result.pdf', Buffer.from(data));
-  console.log('Generate PDF: tesseract-ocr-result.pdf');
-  await worker.terminate();
-})();

examples/node/recognize.js

@@ -1,20 +0,0 @@
-#!/usr/bin/env node
-const path = require('path');
-const { createWorker } = require('../../');
-
-const [,, imagePath] = process.argv;
-const image = path.resolve(__dirname, (imagePath || '../../tests/assets/images/cosmic.png'));
-
-console.log(`Recognizing ${image}`);
-const worker = createWorker({
-  logger: m => console.log(m),
-});
-
-(async () => {
-  await worker.load();
-  await worker.loadLanguage('eng');
-  await worker.initialize('eng');
-  const { data: { text } } = await worker.recognize(image);
-  console.log(text);
-  await worker.terminate();
-})();

package.json

@@ -1,78 +1,39 @@
 {
   "name": "tesseract.js",
-  "version": "3.0.3",
+  "version": "1.0.19",
   "description": "Pure Javascript Multilingual OCR",
   "main": "src/index.js",
-  "types": "src/index.d.ts",
-  "unpkg": "dist/tesseract.min.js",
-  "jsdelivr": "dist/tesseract.min.js",
   "scripts": {
-    "start": "node scripts/server.js",
+    "start": "concurrently --kill-others \"watchify src/index.js  -t [ envify --TESS_ENV development ] -t [ babelify --presets [ es2015 ] ] -o dist/tesseract.dev.js --standalone Tesseract\" \"watchify src/browser/worker.js  -t [ envify --TESS_ENV development ] -t [ babelify --presets [ es2015 ] ] -o dist/worker.dev.js\" \"http-server -p 7355\"",
-    "build": "rimraf dist && webpack --config scripts/webpack.config.prod.js && rollup -c scripts/rollup.esm.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 && uglifyjs dist/tesseract.js --source-map -o dist/tesseract.min.js && uglifyjs dist/worker.js --source-map -o dist/worker.min.js",
-    "profile:tesseract": "webpack-bundle-analyzer dist/tesseract-stats.json",
+    "release": "npm run build && git commit -am 'new release' && git push && git tag `jq -r '.version' package.json` && git push origin --tags && npm publish"
-    "profile:worker": "webpack-bundle-analyzer dist/worker-stats.json",
-    "prepublishOnly": "npm run build",
-    "wait": "rimraf dist && wait-on http://localhost:3000/dist/tesseract.dev.js",
-    "test": "npm-run-all -p -r start test:all",
-    "test:all": "npm-run-all wait test:browser:* test:node:all",
-    "test:node": "nyc mocha --exit --bail --require ./scripts/test-helper.js",
-    "test:node:all": "npm run test:node -- ./tests/*.test.js",
-    "test:browser-tpl": "mocha-headless-chrome -a incognito -a no-sandbox -a disable-setuid-sandbox -a disable-logging -t 300000",
-    "test:browser:detect": "npm run test:browser-tpl -- -f ./tests/detect.test.html",
-    "test:browser:recognize": "npm run test:browser-tpl -- -f ./tests/recognize.test.html",
-    "test:browser:scheduler": "npm run test:browser-tpl -- -f ./tests/scheduler.test.html",
-    "test:browser:FS": "npm run test:browser-tpl -- -f ./tests/FS.test.html",
-    "lint": "eslint src",
-    "lint:fix": "eslint --fix src",
-    "postinstall": "opencollective-postinstall || true"
   },
   "browser": {
-    "./src/worker/node/index.js": "./src/worker/browser/index.js"
+    "./src/node/index.js": "./src/browser/index.js"
   },
   "author": "",
-  "contributors": [
-    "jeromewu"
-  ],
   "license": "Apache-2.0",
   "devDependencies": {
-    "@babel/core": "^7.18.7",
+    "babel-preset-es2015": "^6.16.0",
-    "@babel/preset-env": "^7.18.7",
+    "babelify": "^7.3.0",
-    "@rollup/plugin-commonjs": "^22.0.2",
+    "browserify": "^13.1.0",
-    "acorn": "^6.4.0",
+    "concurrently": "^3.1.0",
-    "babel-loader": "^8.2.0",
+    "envify": "^3.4.1",
-    "buffer": "^6.0.3",
+    "http-server": "^0.9.0",
-    "cors": "^2.8.5",
+    "pako": "^1.0.3",
-    "eslint": "^7.2.0",
+    "uglify-js": "^3.4.9",
-    "eslint-config-airbnb-base": "^14.2.0",
+    "watchify": "^3.7.0"
-    "eslint-plugin-import": "^2.22.1",
-    "expect.js": "^0.3.1",
-    "express": "^4.17.1",
-    "mocha": "^8.1.3",
-    "mocha-headless-chrome": "^2.0.3",
-    "npm-run-all": "^4.1.5",
-    "nyc": "^15.1.0",
-    "rimraf": "^2.7.1",
-    "rollup": "^2.79.0",
-    "wait-on": "^3.3.0",
-    "webpack": "^5.74.0",
-    "webpack-bundle-analyzer": "^4.6.0",
-    "webpack-cli": "^4.10.0",
-    "webpack-dev-middleware": "^5.3.3"
   },
   "dependencies": {
-    "babel-eslint": "^10.1.0",
+    "file-type": "^3.8.0",
-    "bmp-js": "^0.1.0",
+    "isomorphic-fetch": "^2.2.1",
-    "file-type": "^12.4.1",
+    "is-url": "1.2.2",
-    "idb-keyval": "^3.2.0",
+    "jpeg-js": "^0.2.0",
-    "is-electron": "^2.2.0",
+    "level-js": "^2.2.4",
-    "is-url": "^1.2.4",
+    "node-fetch": "^1.6.3",
-    "node-fetch": "^2.6.0",
+    "object-assign": "^4.1.0",
-    "opencollective-postinstall": "^2.0.2",
+    "png.js": "^0.2.1",
-    "regenerator-runtime": "^0.13.3",
+    "tesseract.js-core": "^1.0.2"
-    "resolve-url": "^0.2.1",
-    "tesseract.js-core": "^3.0.2",
-    "wasm-feature-detect": "^1.2.11",
-    "zlibjs": "^0.3.1"
   },
   "repository": {
     "type": "git",
@@ -81,9 +42,5 @@
   "bugs": {
     "url": "https://github.com/naptha/tesseract.js/issues"
   },
-  "homepage": "https://github.com/naptha/tesseract.js",
+  "homepage": "https://github.com/naptha/tesseract.js"
-  "collective": {
-    "type": "opencollective",
-    "url": "https://opencollective.com/tesseractjs"
-  }
 }

scripts/.eslintrc

@@ -1,5 +0,0 @@
-{
-  "rules": {
-    "import/no-extraneous-dependencies": 0
-  }
-}

scripts/rollup.esm.js

@@ -1,13 +0,0 @@
-import commonjs from "@rollup/plugin-commonjs";
-
-export default [
-  {
-    input: "dist/tesseract.min.js",
-    output: {
-      file: "dist/tesseract.esm.min.js",
-      format: "esm",
-      banner: "/* eslint-disable */",
-    },
-    plugins: [commonjs()],
-  },
-];

scripts/server.js

@@ -1,17 +0,0 @@
-const webpack = require('webpack');
-const middleware = require('webpack-dev-middleware');
-const express = require('express');
-const path = require('path');
-const cors = require('cors');
-const webpackConfig = require('./webpack.config.dev');
-
-const compiler = webpack(webpackConfig);
-const app = express();
-
-app.use(cors());
-app.use('/', express.static(path.resolve(__dirname, '..')));
-app.use(middleware(compiler, { publicPath: '/dist', writeToDisk: true }));
-
-module.exports = app.listen(3000, () => {
-  console.log('Server is running on the port no. 3000');
-});

scripts/test-helper.js

@@ -1,9 +0,0 @@
-const constants = require('../tests/constants');
-global.expect = require('expect.js');
-global.fs = require('fs');
-global.path = require('path');
-global.Tesseract = require('../src');
-
-Object.keys(constants).forEach((key) => {
-  global[key] = constants[key];
-});

scripts/webpack.config.common.js

@@ -1,28 +0,0 @@
-module.exports = {
-  resolve: {
-    fallback: {
-      buffer: require.resolve('buffer/'),
-    },
-  },
-  module: {
-    rules: [
-      {
-        test: /\.m?js$/,
-        // exclude: /(node_modules|bower_components)/,
-        use: {
-          loader: 'babel-loader',
-          options: {
-            presets: [
-              [
-                '@babel/preset-env',
-                {
-                  targets: 'last 2 versions',
-                },
-              ],
-            ],
-          },
-        },
-      },
-    ],
-  },
-};

scripts/webpack.config.dev.js

@@ -1,48 +0,0 @@
-const path = require('path');
-const webpack = require('webpack');
-const { BundleAnalyzerPlugin } = require('webpack-bundle-analyzer');
-const common = require('./webpack.config.common');
-
-const genConfig = ({
-  entry, filename, library, libraryTarget,
-}) => ({
-  ...common,
-  mode: 'development',
-  entry,
-  output: {
-    filename,
-    library,
-    libraryTarget,
-  },
-  plugins: [
-    new webpack.ProvidePlugin({
-      Buffer: ['buffer', 'Buffer'],
-    }),
-    new webpack.DefinePlugin({
-      'process.env': {
-        TESS_ENV: JSON.stringify('development'),
-      },
-    }),
-    new BundleAnalyzerPlugin({
-      analyzerMode: 'disable',
-      statsFilename: `${filename.split('.')[0]}-stats.json`,
-      generateStatsFile: true
-    }),
-  ],
-  devServer: {
-    allowedHosts: ['localhost', '.gitpod.io'],
-  },
-});
-
-module.exports = [
-  genConfig({
-    entry: path.resolve(__dirname, '..', 'src', 'index.js'),
-    filename: 'tesseract.dev.js',
-    library: 'Tesseract',
-    libraryTarget: 'umd',
-  }),
-  genConfig({
-    entry: path.resolve(__dirname, '..', 'src', 'worker-script', 'browser', 'index.js'),
-    filename: 'worker.dev.js',
-  }),
-];

scripts/webpack.config.prod.js

@@ -1,36 +0,0 @@
-const path = require('path');
-const common = require('./webpack.config.common');
-const webpack = require('webpack');
-
-const genConfig = ({
-  entry, filename, library, libraryTarget,
-}) => ({
-  ...common,
-  mode: 'production',
-  devtool: 'source-map',
-  entry,
-  output: {
-    path: path.resolve(__dirname, '..', 'dist'),
-    filename,
-    library,
-    libraryTarget,
-  },
-  plugins: [
-    new webpack.ProvidePlugin({
-      Buffer: ['buffer', 'Buffer'],
-    }),
-  ]
-});
-
-module.exports = [
-  genConfig({
-    entry: path.resolve(__dirname, '..', 'src', 'index.js'),
-    filename: 'tesseract.min.js',
-    library: 'Tesseract',
-    libraryTarget: 'umd',
-  }),
-  genConfig({
-    entry: path.resolve(__dirname, '..', 'src', 'worker-script', 'browser', 'index.js'),
-    filename: 'worker.min.js',
-  }),
-];

src/Tesseract.js

@@ -1,28 +0,0 @@
-const createWorker = require('./createWorker');
-
-const recognize = async (image, langs, options) => {
-  const worker = createWorker(options);
-  await worker.load();
-  await worker.loadLanguage(langs);
-  await worker.initialize(langs);
-  return worker.recognize(image)
-    .finally(async () => {
-      await worker.terminate();
-    });
-};
-
-const detect = async (image, options) => {
-  const worker = createWorker(options);
-  await worker.load();
-  await worker.loadLanguage('osd');
-  await worker.initialize('osd');
-  return worker.detect(image)
-    .finally(async () => {
-      await worker.terminate();
-    });
-};
-
-module.exports = {
-  recognize,
-  detect,
-};

src/browser/index.js

@@ -0,0 +1,105 @@
+var defaultOptions = {
+    // workerPath: 'https://cdn.jsdelivr.net/gh/naptha/tesseract.js@0.2.0/dist/worker.js',
+    corePath: 'https://cdn.jsdelivr.net/gh/naptha/tesseract.js-core@0.1.0/index.js',    
+    langPath: 'https://tessdata.projectnaptha.com/3.02/',
+}
+
+if (process.env.TESS_ENV === "development") {
+    console.debug('Using Development Configuration')
+    defaultOptions.workerPath = location.protocol + '//' + location.host + '/dist/worker.dev.js?nocache=' + Math.random().toString(36).slice(3)
+}else{
+    var version = require('../../package.json').version;
+    defaultOptions.workerPath = 'https://cdn.jsdelivr.net/gh/naptha/tesseract.js@' + version + '/dist/worker.js'
+}
+
+exports.defaultOptions = defaultOptions;
+
+
+exports.spawnWorker = function spawnWorker(instance, workerOptions){
+    if(Blob && URL){
+        var blob = new Blob(['importScripts("' + workerOptions.workerPath + '");'], {
+            type: 'application/javascript'
+        });
+        var worker = new Worker(URL.createObjectURL(blob));
+    }else{
+        var worker = new Worker(workerOptions.workerPath)
+    }
+
+    worker.onmessage = function(e){
+        var packet = e.data;
+        instance._recv(packet)
+    }
+    return worker
+}
+
+exports.terminateWorker = function(instance){
+    instance.worker.terminate()
+}
+
+exports.sendPacket = function sendPacket(instance, packet){
+    loadImage(packet.payload.image, function(img){
+        packet.payload.image = img
+        instance.worker.postMessage(packet) 
+    })
+}
+
+
+function loadImage(image, cb){
+    if(typeof image === 'string'){
+        if(/^\#/.test(image)){
+            // element css selector
+            return loadImage(document.querySelector(image), cb)
+        }else if(/(blob|data)\:/.test(image)){
+            // data url
+            var im = new Image
+            im.src = image;
+            im.onload = e => loadImage(im, cb);
+            im.onerror = e => { throw e; };
+            return
+        }else{
+            var xhr = new XMLHttpRequest();
+            xhr.open('GET', image, true)
+            xhr.responseType = "blob";
+            
+            xhr.onload = e => {
+                if (xhr.status >= 400){
+                  throw new Error('Fail to get image as Blob');
+                }else{
+                    loadImage(xhr.response, cb);
+                }
+            };
+            xhr.onerror = e => { throw e; }; 
+            
+            xhr.send(null)
+            return
+        }
+    }else if(image instanceof File){
+        // files
+        var fr = new FileReader()
+        fr.onload = e => loadImage(fr.result, cb);
+        fr.onerror = e => { throw e; }; 
+        fr.readAsDataURL(image)
+        return
+    }else if(image instanceof Blob){
+        return loadImage(URL.createObjectURL(image), cb)
+    }else if(image.getContext){
+        // canvas element
+        return loadImage(image.getContext('2d'), cb)
+    }else if(image.tagName == "IMG" || image.tagName == "VIDEO"){
+        // image element or video element
+        var c = document.createElement('canvas');
+        c.width  = image.naturalWidth  || image.videoWidth;
+        c.height = image.naturalHeight || image.videoHeight;
+        var ctx = c.getContext('2d');
+        ctx.drawImage(image, 0, 0);
+        return loadImage(ctx, cb)
+    }else if(image.getImageData){
+        // canvas context
+        var data = image.getImageData(0, 0, image.canvas.width, image.canvas.height);
+        return loadImage(data, cb)
+    }else{
+        return cb(image)
+    }
+    throw new Error('Missing return in loadImage cascade')
+
+}

src/browser/lang.js

@@ -0,0 +1,76 @@
+const leveljs = require('level-js')
+
+// something about trying to store these language files in indexedDB
+// causes iOS Safari to crash
+
+var iOS = /iPad|iPhone|iPod/.test(navigator.userAgent);
+var noIDB = typeof indexedDB === 'undefined' || iOS;
+
+var db = noIDB ? { open: (_, cb) =>  cb(true) } : leveljs('./tessdata2')
+
+var langdata = require('../common/langdata.json')
+
+module.exports = function getLanguageData(req, res, cb){
+    var lang = req.options.lang;
+
+    function saveDataFile(data){
+        try {
+            db.put(lang, data, err => console.log('cached', lang, err))
+        } finally {
+            cb(data)    
+        }
+    }
+
+    db.open({ compression: false }, err => {
+        if (err) return fetchLanguageData(req, res, cb);
+        db.get(lang, (err, data) => {
+            if (err) return fetchLanguageData(req, res, saveDataFile);
+            res.progress({ status: 'found in cache ' + lang + '.traineddata' })
+            cb(data)
+        })
+    })
+}
+
+
+const ungzip = require('pako/lib/inflate.js').ungzip;
+
+function fetchLanguageData(req, res, cb){
+    var lang = req.options.lang;
+    var langfile = lang + '.traineddata.gz';
+    var url = req.workerOptions.langPath + langfile;
+
+    var xhr = new XMLHttpRequest();
+    xhr.open('GET', url, true);
+    xhr.responseType = 'arraybuffer';
+    xhr.onerror = e => {
+        xhr.onprogress = xhr.onload = null
+        cb(xhr, null)
+    }
+    xhr.onprogress = e => 
+        res.progress({
+            status: 'downloading ' + langfile,
+            loaded: e.loaded,
+            progress: Math.min(1, e.loaded / langdata[lang])
+        });
+
+    xhr.onload = e => {
+        if (!(xhr.status == 200 || (xhr.status == 0 && xhr.response))) return res.reject('Error downloading language ' + url);
+        res.progress({ status: 'unzipping ' + langfile, progress: 0 })
+
+        // in case the gzips are already ungzipped or extra gzipped
+        var response = new Uint8Array(xhr.response)
+        try {
+            var n = 2;
+            while(response[0] == 0x1f && response[1] == 0x8b){
+                response = ungzip(response);
+                res.progress({ status: 'unzipping ' + langfile, progress: 1 - 1 / (n++) })
+            }
+        } catch (err) {
+            return res.reject('Error unzipping language file ' + langfile + '\n' + err.message)
+        }
+        res.progress({ status: 'unzipping ' + langfile, progress: 1 })
+        
+        cb(response)
+    }
+    xhr.send()
+}

src/browser/worker.js

@@ -0,0 +1,23 @@
+const workerUtils = require('../common/worker.js')
+
+if (process.env.TESS_ENV === "development") {
+    console.debug('Using Development Worker')
+}
+
+global.addEventListener('message', function(e){
+    var packet = e.data;
+    workerUtils.dispatchHandlers(packet, obj => postMessage(obj))
+})
+
+exports.getCore = function(req, res){
+    if(!global.TesseractCore){
+        res.progress({ status: 'loading tesseract core', progress: 0 })
+        importScripts(req.workerOptions.corePath)
+        res.progress({ status: 'loading tesseract core', progress: 1 })
+    }
+    return TesseractCore
+}
+
+exports.getLanguageData = require('./lang.js')
+
+workerUtils.setAdapter(module.exports);

src/common/circularize.js

@@ -0,0 +1,63 @@
+// The result of dump.js is a big JSON tree
+// which can be easily serialized (for instance
+// to be sent from a webworker to the main app
+// or through Node's IPC), but we want
+// a (circular) DOM-like interface for walking
+// through the data. 
+
+module.exports = function circularize(page){
+    page.paragraphs = []
+    page.lines = []
+    page.words = []
+    page.symbols = []
+
+    page.blocks.forEach(function(block){
+        block.page = page;
+
+        block.lines = []
+        block.words = []
+        block.symbols = []
+
+        block.paragraphs.forEach(function(para){
+            para.block = block;
+            para.page = page;
+
+            para.words = []
+            para.symbols = []
+            
+            para.lines.forEach(function(line){
+                line.paragraph = para;
+                line.block = block;
+                line.page = page;
+
+                line.symbols = []
+
+                line.words.forEach(function(word){
+                    word.line = line;
+                    word.paragraph = para;
+                    word.block = block;
+                    word.page = page;
+                    word.symbols.forEach(function(sym){
+                        sym.word = word;
+                        sym.line = line;
+                        sym.paragraph = para;
+                        sym.block = block;
+                        sym.page = page;
+                        
+                        sym.line.symbols.push(sym)
+                        sym.paragraph.symbols.push(sym)
+                        sym.block.symbols.push(sym)
+                        sym.page.symbols.push(sym)
+                    })
+                    word.paragraph.words.push(word)
+                    word.block.words.push(word)
+                    word.page.words.push(word)
+                })
+                line.block.lines.push(line)
+                line.page.lines.push(line)
+            })
+            para.page.paragraphs.push(para)
+        })
+    })
+    return page
+}

src/common/desaturate.js

@@ -0,0 +1,24 @@
+// This converts an image to grayscale
+
+module.exports = function desaturate(image){
+    var width, height;
+    if(image.data){
+        var src       = image.data;
+            width     = image.width, 
+            height    = image.height;
+        var dst       = new Uint8Array(width * height);
+        var srcLength = src.length | 0, srcLength_16 = (srcLength - 16) | 0;
+        
+        for (var i = 0, j = 0; i <= srcLength_16; i += 16, j += 4) {
+            // convert to grayscale 4 pixels at a time; eveything with alpha gets put in front of 50% gray
+            dst[j]     = (((src[i] * 77 + src[i+1] * 151 + src[i+2] * 28) * src[i+3]) + ((255-src[i+3]) << 15) + 32768) >> 16
+            dst[j+1]   = (((src[i+4] * 77 + src[i+5] * 151 + src[i+6] * 28) * src[i+7]) + ((255-src[i+7]) << 15) + 32768) >> 16
+            dst[j+2]   = (((src[i+8] * 77 + src[i+9] * 151 + src[i+10] * 28) * src[i+11]) + ((255-src[i+11]) << 15) + 32768) >> 16
+            dst[j+3]   = (((src[i+12] * 77 + src[i+13] * 151 + src[i+14] * 28) * src[i+15]) + ((255-src[i+15]) << 15) + 32768) >> 16
+        }
+        for (; i < srcLength; i += 4, ++j) //finish up
+            dst[j]     = (((src[i] * 77 + src[i+1] * 151 + src[i+2] * 28) * src[i+3]) + ((255-src[i+3]) << 15) + 32768) >> 16
+        image = dst;
+    } else { throw 'Invalid ImageData' }
+    return image
+}

src/common/dump.js

@@ -0,0 +1,164 @@
+module.exports = function DumpLiterallyEverything(Module, base){
+    var ri = base.GetIterator();
+    var blocks = [];
+    var block, para, textline, word, symbol;
+
+    function enumToString(value, prefix){
+       return (Object.keys(Module)
+           .filter(function(e){ return e.substr(0, prefix.length + 1) == prefix + '_' })
+           .filter(function(e){ return Module[e] === value })
+           .map(function(e){ return e.slice(prefix.length + 1) })[0])
+    }
+
+    ri.Begin()
+    do {
+        if(ri.IsAtBeginningOf(Module.RIL_BLOCK)){
+            var poly = ri.BlockPolygon();
+            var polygon = null;
+            // BlockPolygon() returns null when automatic page segmentation is off
+            if(Module.getPointer(poly) > 0){
+                var n = poly.get_n(),
+                    px = poly.get_x(),
+                    py = poly.get_y(),
+                    polygon = [];
+                for(var i = 0; i < n; i++){
+                    polygon.push([px.getValue(i), py.getValue(i)]);
+                }
+                Module._ptaDestroy(Module.getPointer(poly));    
+            }
+            
+            block = {
+                paragraphs: [],
+
+                text: ri.GetUTF8Text(Module.RIL_BLOCK),
+                confidence: ri.Confidence(Module.RIL_BLOCK),
+                baseline: ri.getBaseline(Module.RIL_BLOCK),
+                bbox: ri.getBoundingBox(Module.RIL_BLOCK),
+
+                blocktype: enumToString(ri.BlockType(), 'PT'),
+                polygon: polygon
+            }
+            blocks.push(block)
+        }
+        if(ri.IsAtBeginningOf(Module.RIL_PARA)){
+            para = {
+                lines: [],
+
+                text: ri.GetUTF8Text(Module.RIL_PARA),
+                confidence: ri.Confidence(Module.RIL_PARA),
+                baseline: ri.getBaseline(Module.RIL_PARA),
+                bbox: ri.getBoundingBox(Module.RIL_PARA),
+
+                is_ltr: !!ri.ParagraphIsLtr()
+            }
+            block.paragraphs.push(para)
+        }
+        if(ri.IsAtBeginningOf(Module.RIL_TEXTLINE)){
+            textline = {
+                words: [],
+
+                text: ri.GetUTF8Text(Module.RIL_TEXTLINE),
+                confidence: ri.Confidence(Module.RIL_TEXTLINE),
+                baseline: ri.getBaseline(Module.RIL_TEXTLINE),
+                bbox: ri.getBoundingBox(Module.RIL_TEXTLINE)
+            }
+            para.lines.push(textline)
+        }
+        if(ri.IsAtBeginningOf(Module.RIL_WORD)){
+            var fontInfo = ri.getWordFontAttributes(),
+                wordDir = ri.WordDirection();
+            word = {
+                symbols: [],
+                choices: [],
+
+                text: ri.GetUTF8Text(Module.RIL_WORD),
+                confidence: ri.Confidence(Module.RIL_WORD),
+                baseline: ri.getBaseline(Module.RIL_WORD),
+                bbox: ri.getBoundingBox(Module.RIL_WORD),
+
+                is_numeric: !!ri.WordIsNumeric(),
+                in_dictionary: !!ri.WordIsFromDictionary(),
+                direction: enumToString(wordDir, 'DIR'),
+                language: ri.WordRecognitionLanguage(),
+
+                is_bold: fontInfo.is_bold,
+                is_italic: fontInfo.is_italic,
+                is_underlined: fontInfo.is_underlined,
+                is_monospace: fontInfo.is_monospace,
+                is_serif: fontInfo.is_serif,
+                is_smallcaps: fontInfo.is_smallcaps,
+                font_size: fontInfo.pointsize,
+                font_id: fontInfo.font_id,
+                font_name: fontInfo.font_name,
+            }
+            var wc = new Module.WordChoiceIterator(ri);
+            do {
+                word.choices.push({
+                    text: wc.GetUTF8Text(),
+                    confidence: wc.Confidence()
+                })
+            } while (wc.Next());
+            Module.destroy(wc)
+            textline.words.push(word)
+        }
+        
+        var image = null;
+        // var pix = ri.GetBinaryImage(Module.RIL_SYMBOL)
+        // var image = pix2array(pix);
+        // // for some reason it seems that things stop working if you destroy pics
+        // Module._pixDestroy(Module.getPointer(pix));
+        if(ri.IsAtBeginningOf(Module.RIL_SYMBOL)){
+            symbol = {
+                choices: [],
+                image: image,
+
+                text: ri.GetUTF8Text(Module.RIL_SYMBOL),
+                confidence: ri.Confidence(Module.RIL_SYMBOL),
+                baseline: ri.getBaseline(Module.RIL_SYMBOL),
+                bbox: ri.getBoundingBox(Module.RIL_SYMBOL),
+
+                is_superscript: !!ri.SymbolIsSuperscript(),
+                is_subscript: !!ri.SymbolIsSubscript(),
+                is_dropcap: !!ri.SymbolIsDropcap(),
+            }
+            word.symbols.push(symbol)
+            var ci = new Module.ChoiceIterator(ri);
+            do {
+                symbol.choices.push({
+                    text: ci.GetUTF8Text(),
+                    confidence: ci.Confidence()
+                })
+            } while (ci.Next());
+            Module.destroy(ci)
+        }
+    } while (ri.Next(Module.RIL_SYMBOL));
+    Module.destroy(ri)
+
+    return {
+        text: base.GetUTF8Text(),
+        html: deindent(base.GetHOCRText()),
+
+        confidence: base.MeanTextConf(),
+
+        blocks: blocks,
+
+        psm: enumToString(base.GetPageSegMode(), 'PSM'),
+        oem: enumToString(base.oem(), 'OEM'),
+        version: base.Version(),
+    }
+}
+
+// the generated HOCR is excessively indented, so
+// we get rid of that indentation
+
+function deindent(html){
+    var lines = html.split('\n')
+    if(lines[0].substring(0, 2) === "  "){
+        for (var i = 0; i < lines.length; i++) {
+            if (lines[i].substring(0,2) === "  ") {
+                lines[i] = lines[i].slice(2)
+            }
+        };
+    }
+    return lines.join('\n')
+}

src/common/job.js

@@ -0,0 +1,81 @@
+const adapter = require('../node/index.js')
+
+let jobCounter = 0;
+
+module.exports = class TesseractJob {
+    constructor(instance){
+        this.id = 'Job-' + (++jobCounter) + '-' + Math.random().toString(16).slice(3, 8)
+
+        this._instance = instance;
+        this._resolve = []
+        this._reject = []
+        this._progress = []
+        this._finally = []
+    }
+
+    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;
+    }
+    finally(fn) {
+        this._finally.push(fn)
+        return this;  
+    }
+    _send(action, payload){
+        adapter.sendPacket(this._instance, {
+            jobId: this.id,
+            action: action,
+            payload: payload
+        })
+    }
+
+    _handle(packet){
+        var data = packet.data;
+        let runFinallyCbs = false;
+
+        if(packet.status === 'resolve'){
+            if(this._resolve.length === 0) console.log(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()
+            runFinallyCbs = true;
+        }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()
+            runFinallyCbs = true;
+        }else if(packet.status === 'progress'){
+            this._progress.forEach(fn => fn(data))
+        }else{
+            console.warn('Message type unknown', packet.status)
+        }
+
+        if (runFinallyCbs) {
+            this._finally.forEach(fn => fn(data));
+        }
+    }
+}

src/common/langdata.json

@@ -0,0 +1 @@
+{"afr": 1079573, "ara": 1701536, "aze": 1420865, "bel": 1276820, "ben": 6772012, "bul": 1605615, "cat": 1652368, "ces": 1035441, "chi_sim": 17710414, "chi_tra": 24717749, "chr": 320649, "dan-frak": 677656, "dan": 1972936, "deu-frak": 822644, "deu": 991656, "ell": 859719, "eng": 9453554, "enm": 619254, "epo": 1241212, "equ": 821130, "est": 1905040, "eus": 1641190, "fin": 979418, "fra": 1376221, "frk": 5912963, "frm": 5147082, "glg": 1674938, "grc": 3012615, "heb": 1051501, "hin": 6590065, "hrv": 1926995, "hun": 3074473, "ind": 1874776, "isl": 1634041, "ita": 948593, "ita_old": 3436571, "jpn": 13507168, "kan": 4390317, "kor": 5353098, "lav": 1843944, "lit": 1779240, "mal": 5966263, "meme": 88453, "mkd": 1163087, "mlt": 1463001, "msa": 1665427, "nld": 1134708, "nor": 2191610, "osd": 4274649, "pol": 7024662, "por": 909359, "ron": 915680, "rus": 5969957, "slk-frak": 289885, "slk": 2217342, "slv": 1611338, "spa": 883170, "spa_old": 5647453, "sqi": 1667041, "srp": 1770244, "swa": 757916, "swe": 2451917, "tam": 3498763, "tel": 5795246, "tgl": 1496256, "tha": 3811136, "tur": 3563264, "ukr": 937566, "vie": 2195922}

src/common/worker.js

@@ -0,0 +1,165 @@
+var latestJob,
+    Module,
+    base,
+    adapter = {},
+    dump = require('./dump.js'),
+    desaturate = require('./desaturate.js');
+
+function dispatchHandlers(packet, send){
+    function respond(status, data){
+        send({
+            jobId: packet.jobId,
+            status,
+            action: packet.action,
+            data
+        });
+    }
+    respond.resolve = respond.bind(this, 'resolve');
+    respond.reject = respond.bind(this, 'reject');
+    respond.progress = respond.bind(this, 'progress');
+
+    latestJob = respond;
+
+    try {
+        if(packet.action === 'recognize'){
+            handleRecognize(packet.payload, respond);
+        } else if (packet.action === 'detect'){
+            handleDetect(packet.payload, respond);
+        }
+    } catch (err) {
+        // Prepare exception to travel through postMessage
+        err = err.toString();
+
+        respond.reject(err)
+    }
+}
+exports.dispatchHandlers = dispatchHandlers;
+
+exports.setAdapter = function setAdapter(impl){
+    adapter = impl;
+};
+
+
+function handleInit(req, res){
+    var MIN_MEMORY = 100663296;
+
+    if(['chi_sim', 'chi_tra', 'jpn'].includes(req.options.lang)){
+        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: MIN_MEMORY,
+            TesseractProgress(percent){
+                latestJob.progress({ status: 'recognizing text', progress: Math.max(0, (percent-30)/70) });
+            },
+            onRuntimeInitialized() {}
+        });
+
+        Module.FS_createPath("/", "tessdata", true, true);
+        base = new Module.TessBaseAPI();
+        res.progress({ status: 'initializing tesseract', progress: 1 });
+    }
+}
+
+function setImage(Module, base, image){
+    var imgbin = desaturate(image),
+        width = image.width,
+        height = image.height;
+
+    var ptr = Module.allocate(imgbin, 'i8', Module.ALLOC_NORMAL);
+    base.SetImage(Module.wrapPointer(ptr), width, height, 1, width);
+    base.SetRectangle(0, 0, width, height);
+    return ptr;
+}
+
+function loadLanguage(req, res, cb){
+    var lang = req.options.lang,
+        langFile = lang + '.traineddata';
+
+    if(!Module._loadedLanguages) Module._loadedLanguages = {};
+    if(lang in Module._loadedLanguages) return cb();
+
+    adapter.getLanguageData(req, res, function(data){
+        res.progress({ status: 'loading ' + langFile, progress: 0 });
+        Module.FS_createDataFile('tessdata', langFile, data, true, false);
+        Module._loadedLanguages[lang] = true;
+        res.progress({ status: 'loading ' + langFile, progress: 1 });
+        cb();
+    })
+}
+
+
+
+function handleRecognize(req, res){
+    handleInit(req, res);
+
+    loadLanguage(req, res, () => {
+        var options = req.options;
+
+        function progressUpdate(progress){
+            res.progress({ status: 'initializing api', progress: progress });
+        }
+
+        progressUpdate(0);
+        base.Init(null, req.options.lang);
+        progressUpdate(.3);
+
+        for (var option in options) {
+            if (options.hasOwnProperty(option)) {
+                base.SetVariable(option, options[option]);
+            }
+        }
+
+        progressUpdate(.6);
+        var ptr = setImage(Module, base, req.image);
+        progressUpdate(1);
+
+        base.Recognize(null);
+
+        var result = dump(Module, base);
+
+        base.End();
+        Module._free(ptr);
+
+        res.resolve(result);
+    })
+}
+
+
+function handleDetect(req, res){
+    handleInit(req, res);
+    req.options.lang = 'osd';
+    loadLanguage(req, res, () => {
+        base.Init(null, 'osd');
+        base.SetPageSegMode(Module.PSM_OSD_ONLY);
+
+        var ptr = setImage(Module, base, req.image),
+            results = new Module.OSResults();
+
+        if(!base.DetectOS(results)){
+            base.End();
+            Module._free(ptr);
+            res.reject("Failed to detect OS");
+        } else {
+            var best = results.get_best_result(),
+                oid = best.get_orientation_id(),
+                sid = best.get_script_id();
+
+            base.End();
+            Module._free(ptr);
+
+            res.resolve({
+                tesseract_script_id: sid,
+                script: results.get_unicharset().get_script_from_script_id(sid),
+                script_confidence: best.get_sconfidence(),
+                orientation_degrees: [0, 270, 180, 90][oid],
+                orientation_confidence: best.get_oconfidence()
+            });
+        }
+    });
+}

src/constants/OEM.js

@@ -1,12 +0,0 @@
-/*
- * OEM = OCR Engine Mode, and there are 4 possible modes.
- *
- * By default tesseract.js uses LSTM_ONLY mode.
- *
- */
-module.exports = {
-  TESSERACT_ONLY: 0,
-  LSTM_ONLY: 1,
-  TESSERACT_LSTM_COMBINED: 2,
-  DEFAULT: 3,
-};

src/constants/PSM.js

@@ -1,19 +0,0 @@
-/*
- * PSM = Page Segmentation Mode
- */
-module.exports = {
-  OSD_ONLY: '0',
-  AUTO_OSD: '1',
-  AUTO_ONLY: '2',
-  AUTO: '3',
-  SINGLE_COLUMN: '4',
-  SINGLE_BLOCK_VERT_TEXT: '5',
-  SINGLE_BLOCK: '6',
-  SINGLE_LINE: '7',
-  SINGLE_WORD: '8',
-  CIRCLE_WORD: '9',
-  SINGLE_CHAR: '10',
-  SPARSE_TEXT: '11',
-  SPARSE_TEXT_OSD: '12',
-  RAW_LINE: '13',
-};

src/constants/config.js

@@ -1,5 +0,0 @@
-const OEM = require('./OEM');
-
-module.exports = {
-  defaultOEM: OEM.DEFAULT,
-};

src/constants/defaultOptions.js

@@ -1,13 +0,0 @@
-module.exports = {
-  /*
-   * default path for downloading *.traineddata
-   */
-  langPath: 'https://tessdata.projectnaptha.com/4.0.0',
-  /*
-   * Use BlobURL for worker script by default
-   * TODO: remove this option
-   *
-   */
-  workerBlobURL: true,
-  logger: () => {},
-};

src/constants/languages.js

@@ -1,218 +0,0 @@
-/*
- * languages with existing tesseract traineddata
- * https://tesseract-ocr.github.io/tessdoc/Data-Files#data-files-for-version-400-november-29-2016
- */
-
-/**
- * @typedef {object} Languages
- * @property {string} AFR Afrikaans
- * @property {string} AMH Amharic
- * @property {string} ARA Arabic
- * @property {string} ASM Assamese
- * @property {string} AZE Azerbaijani
- * @property {string} AZE_CYRL Azerbaijani - Cyrillic
- * @property {string} BEL Belarusian
- * @property {string} BEN Bengali
- * @property {string} BOD Tibetan
- * @property {string} BOS Bosnian
- * @property {string} BUL Bulgarian
- * @property {string} CAT Catalan; Valencian
- * @property {string} CEB Cebuano
- * @property {string} CES Czech
- * @property {string} CHI_SIM Chinese - Simplified
- * @property {string} CHI_TRA Chinese - Traditional
- * @property {string} CHR Cherokee
- * @property {string} CYM Welsh
- * @property {string} DAN Danish
- * @property {string} DEU German
- * @property {string} DZO Dzongkha
- * @property {string} ELL Greek, Modern (1453-)
- * @property {string} ENG English
- * @property {string} ENM English, Middle (1100-1500)
- * @property {string} EPO Esperanto
- * @property {string} EST Estonian
- * @property {string} EUS Basque
- * @property {string} FAS Persian
- * @property {string} FIN Finnish
- * @property {string} FRA French
- * @property {string} FRK German Fraktur
- * @property {string} FRM French, Middle (ca. 1400-1600)
- * @property {string} GLE Irish
- * @property {string} GLG Galician
- * @property {string} GRC Greek, Ancient (-1453)
- * @property {string} GUJ Gujarati
- * @property {string} HAT Haitian; Haitian Creole
- * @property {string} HEB Hebrew
- * @property {string} HIN Hindi
- * @property {string} HRV Croatian
- * @property {string} HUN Hungarian
- * @property {string} IKU Inuktitut
- * @property {string} IND Indonesian
- * @property {string} ISL Icelandic
- * @property {string} ITA Italian
- * @property {string} ITA_OLD Italian - Old
- * @property {string} JAV Javanese
- * @property {string} JPN Japanese
- * @property {string} KAN Kannada
- * @property {string} KAT Georgian
- * @property {string} KAT_OLD Georgian - Old
- * @property {string} KAZ Kazakh
- * @property {string} KHM Central Khmer
- * @property {string} KIR Kirghiz; Kyrgyz
- * @property {string} KOR Korean
- * @property {string} KUR Kurdish
- * @property {string} LAO Lao
- * @property {string} LAT Latin
- * @property {string} LAV Latvian
- * @property {string} LIT Lithuanian
- * @property {string} MAL Malayalam
- * @property {string} MAR Marathi
- * @property {string} MKD Macedonian
- * @property {string} MLT Maltese
- * @property {string} MSA Malay
- * @property {string} MYA Burmese
- * @property {string} NEP Nepali
- * @property {string} NLD Dutch; Flemish
- * @property {string} NOR Norwegian
- * @property {string} ORI Oriya
- * @property {string} PAN Panjabi; Punjabi
- * @property {string} POL Polish
- * @property {string} POR Portuguese
- * @property {string} PUS Pushto; Pashto
- * @property {string} RON Romanian; Moldavian; Moldovan
- * @property {string} RUS Russian
- * @property {string} SAN Sanskrit
- * @property {string} SIN Sinhala; Sinhalese
- * @property {string} SLK Slovak
- * @property {string} SLV Slovenian
- * @property {string} SPA Spanish; Castilian
- * @property {string} SPA_OLD Spanish; Castilian - Old
- * @property {string} SQI Albanian
- * @property {string} SRP Serbian
- * @property {string} SRP_LATN Serbian - Latin
- * @property {string} SWA Swahili
- * @property {string} SWE Swedish
- * @property {string} SYR Syriac
- * @property {string} TAM Tamil
- * @property {string} TEL Telugu
- * @property {string} TGK Tajik
- * @property {string} TGL Tagalog
- * @property {string} THA Thai
- * @property {string} TIR Tigrinya
- * @property {string} TUR Turkish
- * @property {string} UIG Uighur; Uyghur
- * @property {string} UKR Ukrainian
- * @property {string} URD Urdu
- * @property {string} UZB Uzbek
- * @property {string} UZB_CYRL Uzbek - Cyrillic
- * @property {string} VIE Vietnamese
- * @property {string} YID Yiddish
- */
-
-/**
-  * @type {Languages}
-  */
-module.exports = {
-  AFR: 'afr',
-  AMH: 'amh',
-  ARA: 'ara',
-  ASM: 'asm',
-  AZE: 'aze',
-  AZE_CYRL: 'aze_cyrl',
-  BEL: 'bel',
-  BEN: 'ben',
-  BOD: 'bod',
-  BOS: 'bos',
-  BUL: 'bul',
-  CAT: 'cat',
-  CEB: 'ceb',
-  CES: 'ces',
-  CHI_SIM: 'chi_sim',
-  CHI_TRA: 'chi_tra',
-  CHR: 'chr',
-  CYM: 'cym',
-  DAN: 'dan',
-  DEU: 'deu',
-  DZO: 'dzo',
-  ELL: 'ell',
-  ENG: 'eng',
-  ENM: 'enm',
-  EPO: 'epo',
-  EST: 'est',
-  EUS: 'eus',
-  FAS: 'fas',
-  FIN: 'fin',
-  FRA: 'fra',
-  FRK: 'frk',
-  FRM: 'frm',
-  GLE: 'gle',
-  GLG: 'glg',
-  GRC: 'grc',
-  GUJ: 'guj',
-  HAT: 'hat',
-  HEB: 'heb',
-  HIN: 'hin',
-  HRV: 'hrv',
-  HUN: 'hun',
-  IKU: 'iku',
-  IND: 'ind',
-  ISL: 'isl',
-  ITA: 'ita',
-  ITA_OLD: 'ita_old',
-  JAV: 'jav',
-  JPN: 'jpn',
-  KAN: 'kan',
-  KAT: 'kat',
-  KAT_OLD: 'kat_old',
-  KAZ: 'kaz',
-  KHM: 'khm',
-  KIR: 'kir',
-  KOR: 'kor',
-  KUR: 'kur',
-  LAO: 'lao',
-  LAT: 'lat',
-  LAV: 'lav',
-  LIT: 'lit',
-  MAL: 'mal',
-  MAR: 'mar',
-  MKD: 'mkd',
-  MLT: 'mlt',
-  MSA: 'msa',
-  MYA: 'mya',
-  NEP: 'nep',
-  NLD: 'nld',
-  NOR: 'nor',
-  ORI: 'ori',
-  PAN: 'pan',
-  POL: 'pol',
-  POR: 'por',
-  PUS: 'pus',
-  RON: 'ron',
-  RUS: 'rus',
-  SAN: 'san',
-  SIN: 'sin',
-  SLK: 'slk',
-  SLV: 'slv',
-  SPA: 'spa',
-  SPA_OLD: 'spa_old',
-  SQI: 'sqi',
-  SRP: 'srp',
-  SRP_LATN: 'srp_latn',
-  SWA: 'swa',
-  SWE: 'swe',
-  SYR: 'syr',
-  TAM: 'tam',
-  TEL: 'tel',
-  TGK: 'tgk',
-  TGL: 'tgl',
-  THA: 'tha',
-  TIR: 'tir',
-  TUR: 'tur',
-  UIG: 'uig',
-  UKR: 'ukr',
-  URD: 'urd',
-  UZB: 'uzb',
-  UZB_CYRL: 'uzb_cyrl',
-  VIE: 'vie',
-  YID: 'yid',
-};

src/createJob.js

@@ -1,21 +0,0 @@
-const getId = require('./utils/getId');
-
-let jobCounter = 0;
-
-module.exports = ({
-  id: _id,
-  action,
-  payload = {},
-}) => {
-  let id = _id;
-  if (typeof id === 'undefined') {
-    id = getId('Job', jobCounter);
-    jobCounter += 1;
-  }
-
-  return {
-    id,
-    action,
-    payload,
-  };
-};

src/createScheduler.js

@@ -1,80 +0,0 @@
-const createJob = require('./createJob');
-const { log } = require('./utils/log');
-const getId = require('./utils/getId');
-
-let schedulerCounter = 0;
-
-module.exports = () => {
-  const id = getId('Scheduler', schedulerCounter);
-  const workers = {};
-  const runningWorkers = {};
-  let jobQueue = [];
-
-  schedulerCounter += 1;
-
-  const getQueueLen = () => jobQueue.length;
-  const getNumWorkers = () => Object.keys(workers).length;
-
-  const dequeue = () => {
-    if (jobQueue.length !== 0) {
-      const wIds = Object.keys(workers);
-      for (let i = 0; i < wIds.length; i += 1) {
-        if (typeof runningWorkers[wIds[i]] === 'undefined') {
-          jobQueue[0](workers[wIds[i]]);
-          break;
-        }
-      }
-    }
-  };
-
-  const queue = (action, payload) => (
-    new Promise((resolve, reject) => {
-      const job = createJob({ action, payload });
-      jobQueue.push(async (w) => {
-        jobQueue.shift();
-        runningWorkers[w.id] = job;
-        try {
-          resolve(await w[action].apply(this, [...payload, job.id]));
-        } catch (err) {
-          reject(err);
-        } finally {
-          delete runningWorkers[w.id];
-          dequeue();
-        }
-      });
-      log(`[${id}]: Add ${job.id} to JobQueue`);
-      log(`[${id}]: JobQueue length=${jobQueue.length}`);
-      dequeue();
-    })
-  );
-
-  const addWorker = (w) => {
-    workers[w.id] = w;
-    log(`[${id}]: Add ${w.id}`);
-    log(`[${id}]: Number of workers=${getNumWorkers()}`);
-    dequeue();
-    return w.id;
-  };
-
-  const addJob = async (action, ...payload) => {
-    if (getNumWorkers() === 0) {
-      throw Error(`[${id}]: You need to have at least one worker before adding jobs`);
-    }
-    return queue(action, payload);
-  };
-
-  const terminate = async () => {
-    Object.keys(workers).forEach(async (wid) => {
-      await workers[wid].terminate();
-    });
-    jobQueue = [];
-  };
-
-  return {
-    addWorker,
-    addJob,
-    terminate,
-    getQueueLen,
-    getNumWorkers,
-  };
-};

src/createWorker.js

@@ -1,198 +0,0 @@
-const resolvePaths = require('./utils/resolvePaths');
-const circularize = require('./utils/circularize');
-const createJob = require('./createJob');
-const { log } = require('./utils/log');
-const getId = require('./utils/getId');
-const { defaultOEM } = require('./constants/config');
-const {
-  defaultOptions,
-  spawnWorker,
-  terminateWorker,
-  onMessage,
-  loadImage,
-  send,
-} = require('./worker/node');
-
-let workerCounter = 0;
-
-module.exports = (_options = {}) => {
-  const id = getId('Worker', workerCounter);
-  const {
-    logger,
-    errorHandler,
-    ...options
-  } = resolvePaths({
-    ...defaultOptions,
-    ..._options,
-  });
-  const resolves = {};
-  const rejects = {};
-  let worker = spawnWorker(options);
-
-  workerCounter += 1;
-
-  const setResolve = (action, res) => {
-    resolves[action] = res;
-  };
-
-  const setReject = (action, rej) => {
-    rejects[action] = rej;
-  };
-
-  const startJob = ({ id: jobId, action, payload }) => (
-    new Promise((resolve, reject) => {
-      log(`[${id}]: Start ${jobId}, action=${action}`);
-      setResolve(action, resolve);
-      setReject(action, reject);
-      send(worker, {
-        workerId: id,
-        jobId,
-        action,
-        payload,
-      });
-    })
-  );
-
-  const load = (jobId) => (
-    startJob(createJob({
-      id: jobId, action: 'load', payload: { options },
-    }))
-  );
-
-  const writeText = (path, text, jobId) => (
-    startJob(createJob({
-      id: jobId,
-      action: 'FS',
-      payload: { method: 'writeFile', args: [path, text] },
-    }))
-  );
-
-  const readText = (path, jobId) => (
-    startJob(createJob({
-      id: jobId,
-      action: 'FS',
-      payload: { method: 'readFile', args: [path, { encoding: 'utf8' }] },
-    }))
-  );
-
-  const removeFile = (path, jobId) => (
-    startJob(createJob({
-      id: jobId,
-      action: 'FS',
-      payload: { method: 'unlink', args: [path] },
-    }))
-  );
-
-  const FS = (method, args, jobId) => (
-    startJob(createJob({
-      id: jobId,
-      action: 'FS',
-      payload: { method, args },
-    }))
-  );
-
-  const loadLanguage = (langs = 'eng', jobId) => (
-    startJob(createJob({
-      id: jobId,
-      action: 'loadLanguage',
-      payload: { langs, options },
-    }))
-  );
-
-  const initialize = (langs = 'eng', oem = defaultOEM, jobId) => (
-    startJob(createJob({
-      id: jobId,
-      action: 'initialize',
-      payload: { langs, oem },
-    }))
-  );
-
-  const setParameters = (params = {}, jobId) => (
-    startJob(createJob({
-      id: jobId,
-      action: 'setParameters',
-      payload: { params },
-    }))
-  );
-
-  const recognize = async (image, opts = {}, jobId) => (
-    startJob(createJob({
-      id: jobId,
-      action: 'recognize',
-      payload: { image: await loadImage(image), options: opts },
-    }))
-  );
-
-  const getPDF = (title = 'Tesseract OCR Result', textonly = false, jobId) => (
-    startJob(createJob({
-      id: jobId,
-      action: 'getPDF',
-      payload: { title, textonly },
-    }))
-  );
-
-  const detect = async (image, jobId) => (
-    startJob(createJob({
-      id: jobId,
-      action: 'detect',
-      payload: { image: await loadImage(image) },
-    }))
-  );
-
-  const terminate = async () => {
-    if (worker !== null) {
-      /*
-      await startJob(createJob({
-        id: jobId,
-        action: 'terminate',
-      }));
-      */
-      terminateWorker(worker);
-      worker = null;
-    }
-    return Promise.resolve();
-  };
-
-  onMessage(worker, ({
-    workerId, jobId, status, action, data,
-  }) => {
-    if (status === 'resolve') {
-      log(`[${workerId}]: Complete ${jobId}`);
-      let d = data;
-      if (action === 'recognize') {
-        d = circularize(data);
-      } else if (action === 'getPDF') {
-        d = Array.from({ ...data, length: Object.keys(data).length });
-      }
-      resolves[action]({ jobId, data: d });
-    } else if (status === 'reject') {
-      rejects[action](data);
-      if (errorHandler) {
-        errorHandler(data);
-      } else {
-        throw Error(data);
-      }
-    } else if (status === 'progress') {
-      logger({ ...data, userJobId: jobId });
-    }
-  });
-
-  return {
-    id,
-    worker,
-    setResolve,
-    setReject,
-    load,
-    writeText,
-    readText,
-    removeFile,
-    FS,
-    loadLanguage,
-    initialize,
-    setParameters,
-    recognize,
-    getPDF,
-    detect,
-    terminate,
-  };
-};

src/index.d.ts

@@ -1,231 +0,0 @@
-declare namespace Tesseract {
-  function createScheduler(): Scheduler
-  function createWorker(options?: Partial<WorkerOptions>): Worker
-  function setLogging(logging: boolean): void
-  function recognize(image: ImageLike, langs?: string, options?: Partial<WorkerOptions>): Promise<RecognizeResult>
-  function detect(image: ImageLike, options?: Partial<WorkerOptions>): any
-
-  interface Scheduler {
-    addWorker(worker: Worker): string
-    addJob(action: string, ...args: any[]): Promise<ConfigResult | RecognizeResult | DetectResult>
-    terminate(): Promise<any>
-    getQueueLen(): number
-    getNumWorkers(): number
-  }
-
-  interface Worker {
-    load(jobId?: string): Promise<ConfigResult>
-    writeText(path: string, text: string, jobId?: string): Promise<ConfigResult>
-    readText(path: string, jobId?: string): Promise<ConfigResult>
-    removeText(path: string, jobId?: string): Promise<ConfigResult>
-    FS(method: string, args: any[], jobId?: string): Promise<ConfigResult>
-    loadLanguage(langs?: string | Lang[], jobId?: string): Promise<ConfigResult>
-    initialize(langs?: string | Lang[], oem?: OEM, jobId?: string): Promise<ConfigResult>
-    setParameters(params: Partial<WorkerParams>, jobId?: string): Promise<ConfigResult>
-    recognize(image: ImageLike, options?: Partial<RecognizeOptions>, jobId?: string): Promise<RecognizeResult>
-    detect(image: ImageLike, jobId?: string): Promise<DetectResult>
-    terminate(jobId?: string): Promise<ConfigResult>
-    getPDF(title?: string, textonly?: boolean, jobId?: string):Promise<GetPDFResult>
-  }
-
-  interface Lang {
-    code: string;
-    data: unknown;
-  }
-
-  interface WorkerOptions {
-    corePath: string
-    langPath: string
-    cachePath: string
-    dataPath: string
-    workerPath: string
-    cacheMethod: string
-    workerBlobURL: boolean
-    gzip: boolean
-    logger: (arg: any) => void,
-    errorHandler: (arg: any) => void
-  }
-  interface WorkerParams {
-    tessedit_ocr_engine_mode: OEM
-    tessedit_pageseg_mode: PSM
-    tessedit_char_whitelist: string
-    preserve_interword_spaces: string
-    user_defined_dpi: string
-    tessjs_create_hocr: string
-    tessjs_create_tsv: string
-    tessjs_create_box: string
-    tessjs_create_unlv: string
-    tessjs_create_osd: string
-  }
-  interface RecognizeOptions {
-    rectangle: Rectangle
-  }
-  interface ConfigResult {
-    jobId: string
-    data: any
-  }
-  interface RecognizeResult {
-    jobId: string
-    data: Page
-  }
-  interface GetPDFResult {
-    jobId: string
-    data: number[]
-  }
-  interface DetectResult {
-    jobId: string
-    data: DetectData
-  }
-  interface DetectData {
-    tesseract_script_id: number
-    script: string
-    script_confidence: number
-    orientation_degrees: number
-    orientation_confidence: number
-  }
-  interface Rectangle {
-    left: number
-    top: number
-    width: number
-    height: number
-  }
-  enum OEM {
-    TESSERACT_ONLY,
-    LSTM_ONLY,
-    TESSERACT_LSTM_COMBINED,
-    DEFAULT,
-  }
-  enum PSM {
-    OSD_ONLY = '0',
-    AUTO_OSD = '1',
-    AUTO_ONLY = '2',
-    AUTO = '3',
-    SINGLE_COLUMN = '4',
-    SINGLE_BLOCK_VERT_TEXT = '5',
-    SINGLE_BLOCK = '6',
-    SINGLE_LINE = '7',
-    SINGLE_WORD = '8',
-    CIRCLE_WORD = '9',
-    SINGLE_CHAR = '10',
-    SPARSE_TEXT = '11',
-    SPARSE_TEXT_OSD = '12',
-    RAW_LINE = '13'
-  }
-  type ImageLike = string | HTMLImageElement | HTMLCanvasElement | HTMLVideoElement
-    | CanvasRenderingContext2D | File | Blob | ImageData | Buffer;
-  interface Block {
-    paragraphs: Paragraph[];
-    text: string;
-    confidence: number;
-    baseline: Baseline;
-    bbox: Bbox;
-    blocktype: string;
-    polygon: any;
-    page: Page;
-    lines: Line[];
-    words: Word[];
-    symbols: Symbol[];
-  }
-  interface Baseline {
-    x0: number;
-    y0: number;
-    x1: number;
-    y1: number;
-    has_baseline: boolean;
-  }
-  interface Bbox {
-    x0: number;
-    y0: number;
-    x1: number;
-    y1: number;
-  }
-  interface Line {
-    words: Word[];
-    text: string;
-    confidence: number;
-    baseline: Baseline;
-    bbox: Bbox;
-    paragraph: Paragraph;
-    block: Block;
-    page: Page;
-    symbols: Symbol[];
-  }
-  interface Paragraph {
-    lines: Line[];
-    text: string;
-    confidence: number;
-    baseline: Baseline;
-    bbox: Bbox;
-    is_ltr: boolean;
-    block: Block;
-    page: Page;
-    words: Word[];
-    symbols: Symbol[];
-  }
-  interface Symbol {
-    choices: Choice[];
-    image: any;
-    text: string;
-    confidence: number;
-    baseline: Baseline;
-    bbox: Bbox;
-    is_superscript: boolean;
-    is_subscript: boolean;
-    is_dropcap: boolean;
-    word: Word;
-    line: Line;
-    paragraph: Paragraph;
-    block: Block;
-    page: Page;
-  }
-  interface Choice {
-    text: string;
-    confidence: number;
-  }
-  interface Word {
-    symbols: Symbol[];
-    choices: Choice[];
-    text: string;
-    confidence: number;
-    baseline: Baseline;
-    bbox: Bbox;
-    is_numeric: boolean;
-    in_dictionary: boolean;
-    direction: string;
-    language: string;
-    is_bold: boolean;
-    is_italic: boolean;
-    is_underlined: boolean;
-    is_monospace: boolean;
-    is_serif: boolean;
-    is_smallcaps: boolean;
-    font_size: number;
-    font_id: number;
-    font_name: string;
-    line: Line;
-    paragraph: Paragraph;
-    block: Block;
-    page: Page;
-  }
-  interface Page {
-    blocks: Block[];
-    confidence: number;
-    lines: Line[];
-    oem: string;
-    osd: string;
-    paragraphs: Paragraph[];
-    psm: string;
-    symbols: Symbol[];
-    text: string;
-    version: string;
-    words: Word[];
-    hocr: string | null;
-    tsv: string | null;
-    box: string | null;
-    unlv: string | null;
-    sd: string | null;
-  }
-}
-
-export = Tesseract;
-export as namespace Tesseract;

src/index.js

@@ -1,27 +1,75 @@
-/**
+const adapter = require('./node/index.js')
- *
+const circularize = require('./common/circularize.js')
- * Entry point for tesseract.js, should be the entry when bundling.
+const TesseractJob = require('./common/job');
- *
+const version = require('../package.json').version;
- * @fileoverview entry point for tesseract.js
+
- * @author Kevin Kwok <antimatter15@gmail.com>
+const create = function(workerOptions = {}){
- * @author Guillermo Webster <gui@mit.edu>
+	var worker = new TesseractWorker(Object.assign({}, adapter.defaultOptions, workerOptions));
- * @author Jerome Wu <jeromewus@gmail.com>
+	worker.create = create;
- */
+	worker.version = version;
-require('regenerator-runtime/runtime');
+	return worker;
-const createScheduler = require('./createScheduler');
+}
-const createWorker = require('./createWorker');
+
-const Tesseract = require('./Tesseract');
+class TesseractWorker {
-const languages = require('./constants/languages');
+	constructor(workerOptions){
-const OEM = require('./constants/OEM');
+		this.worker = null;
-const PSM = require('./constants/PSM');
+		this.workerOptions = workerOptions;
-const { setLogging } = require('./utils/log');
+		this._currentJob = null;
-
+		this._queue = [];
-module.exports = {
+	}
-  languages,
+
-  OEM,
+	recognize(image, options = {}){
-  PSM,
+		return this._delay(job => {
-  createScheduler,
+			if (typeof options === 'string') options = {lang: options}
-  createWorker,
+			options.lang = options.lang || 'eng';
-  setLogging,
+
-  ...Tesseract,
+			job._send('recognize', { image, options, workerOptions: this.workerOptions });
-};
+		})
+	}
+	detect(image, options = {}){
+		return this._delay(job => {
+			job._send('detect', { image, options, workerOptions: this.workerOptions });
+		})
+	}
+
+	terminate(){
+		if(this.worker) adapter.terminateWorker(this);
+		this.worker = null;
+		this._currentJob = null;
+		this._queue = [];
+	}
+
+	_delay(fn){
+		if(!this.worker) this.worker = adapter.spawnWorker(this, this.workerOptions);
+
+		var job = new TesseractJob(this);
+		this._queue.push(e => {
+			this._queue.shift();
+			this._currentJob = job;
+			fn(job);
+		});
+		if(!this._currentJob) this._dequeue();
+		return job;
+	}
+
+	_dequeue(){
+		this._currentJob = null;
+		if(this._queue.length){
+			this._queue[0]();
+		}
+	}
+
+	_recv(packet){
+        if(packet.status === 'resolve' && packet.action === 'recognize'){
+            packet.data = circularize(packet.data);
+        }
+
+		if(this._currentJob.id === packet.jobId){
+			this._currentJob._handle(packet)
+		} else {
+			console.warn('Job ID ' + packet.jobId + ' not known.')
+		}
+	}
+}
+
+module.exports = create();

src/node/index.js

@@ -0,0 +1,89 @@
+const fetch = require('isomorphic-fetch'),
+    isURL = require('is-url'),
+    fork = require('child_process').fork,
+    fs = require('fs');
+
+exports.defaultOptions = {
+    workerPath: require('path').join(__dirname, 'worker.js'),
+    langPath: 'https://tessdata.projectnaptha.com/3.02/',
+}
+
+exports.spawnWorker = function spawnWorker(instance, workerOptions){
+    var cp = fork(workerOptions.workerPath);
+    cp.on('message', packet => {
+        instance._recv(packet);
+    });
+    return cp;
+}
+
+exports.terminateWorker = function(instance){
+    instance.worker.kill();
+}
+
+exports.sendPacket = function sendPacket(instance, packet){
+    loadImage(packet.payload.image, img => {
+        packet.payload.image = img;
+        instance.worker.send(packet);
+    });
+}
+
+
+function loadImage(image, cb){
+    
+    if(typeof image === 'string'){
+        if (isURL(image)) {
+            fetch(image)
+            .then(resp => resp.buffer())
+            .then(buffer => loadImage(buffer, cb))
+            .catch(err => console.error(err));
+        } else {
+            fs.readFile(image, function(err, buffer){
+                if (err) throw err;
+                loadImage(buffer, cb);
+            });
+        }
+        return;
+    } else if (image instanceof Buffer){
+        var mime = require('file-type')(image).mime
+
+        if(mime === 'image/png'){
+            var PNGReader = require('png.js');
+            var reader = new PNGReader(image);
+            reader.parse(function(err, png){
+                if (err) throw err;
+
+                var image = {
+                    width: png.getWidth(),
+                    height: png.getHeight()
+                }
+                image.data = new Uint8Array(image.width * image.height * 4)
+                for(var j = 0; j < image.height; j++){
+                    for(var i = 0; i < image.width; i++){
+                        var offset = 4 * (i + j * image.width),
+                            pix = png.getPixel(i, j);
+
+                        image.data[offset] = pix[0];
+                        image.data[offset + 1] = pix[1];
+                        image.data[offset + 2] = pix[2];
+                        image.data[offset + 3] = pix[3];
+                    }
+                }
+                loadImage(image, cb);
+            });
+            return;
+        } else if (mime === 'image/jpeg'){
+            loadImage(require('jpeg-js').decode(image), cb);
+            return;
+        }
+
+        // TODO: support for TIFF, NetPBM, BMP, etc.
+    }
+
+    // node uses json.stringify for ipc which means we need to turn
+    // fancy arrays into raw arrays
+    if(image && image.data && image.data.length && !Array.isArray(image.data)){
+        image.data = Array.from(image.data);
+        return loadImage(image, cb)
+    }
+    cb(image);
+}

src/node/lang.js

@@ -0,0 +1,47 @@
+const https = require("https"),
+      http = require("http"),
+      zlib = require("zlib"),
+      fs   = require("fs"),
+      path = require("path"),
+      isURL = require("is-url");
+
+var langdata = require('../common/langdata.json')
+
+function getLanguageData(req, res, cb){
+    var lang = req.options.lang,
+        langfile = lang + '.traineddata.gz';
+    
+    // langPath defaults to a URL where languages can be downloaded. If a custom path is specified
+    // and it is a local path, use that instead
+    var localPath = isURL(req.workerOptions.langPath) ? 
+        lang + '.traineddata' : 
+        path.join(req.workerOptions.langPath, lang + '.traineddata');
+
+    var fetchProtocol = req.workerOptions.langPath.startsWith('http://') ? http : https;
+
+    fs.readFile(localPath, function (err, data) {
+        if(!err) return cb(new Uint8Array(data));
+
+        fetchProtocol.get(req.workerOptions.langPath + langfile, stream => {
+            var received_bytes = 0;
+            stream.on('data', function(chunk) {
+                received_bytes += chunk.length;
+                res.progress({ 
+                    status: 'downloading ' + langfile, 
+                    loaded: received_bytes,
+                    progress: Math.min(1, received_bytes / langdata[lang])
+                });
+
+            });
+
+            var gunzip = zlib.createGunzip();
+            stream.pipe(gunzip).pipe(fs.createWriteStream(lang + '.traineddata'))
+            gunzip.on('end',() => {
+                getLanguageData(req, stream, cb)
+            });
+        });
+    });
+}
+
+
+module.exports = getLanguageData;

src/node/worker.js

@@ -0,0 +1,19 @@
+const workerUtils = require('../common/worker.js')
+
+process.on('message', function(packet){
+    workerUtils.dispatchHandlers(packet, obj => process.send(obj))
+})
+
+var TesseractCore;
+exports.getCore = function(req, res){
+    if(!TesseractCore){
+        res.progress({ status: 'loading tesseract core' })
+        TesseractCore = require('tesseract.js-core')
+        res.progress({ status: 'loaded tesseract core' })
+    }
+    return TesseractCore
+}
+
+exports.getLanguageData = require('./lang.js')
+
+workerUtils.setAdapter(module.exports);

src/utils/circularize.js

@@ -1,54 +0,0 @@
-/**
- * In the recognition result of tesseract, there
- * is a deep JSON object for details, it has around
- *
- * The result of dump.js is a big JSON tree
- * which can be easily serialized (for instance
- * to be sent from a webworker to the main app
- * or through Node's IPC), but we want
- * a (circular) DOM-like interface for walking
- * through the data.
- *
- * @fileoverview DOM-like interface for walking through data
- * @author Kevin Kwok <antimatter15@gmail.com>
- * @author Guillermo Webster <gui@mit.edu>
- * @author Jerome Wu <jeromewus@gmail.com>
- */
-
-module.exports = (page) => {
-  const blocks = [];
-  const paragraphs = [];
-  const lines = [];
-  const words = [];
-  const symbols = [];
-
-  page.blocks.forEach((block) => {
-    block.paragraphs.forEach((paragraph) => {
-      paragraph.lines.forEach((line) => {
-        line.words.forEach((word) => {
-          word.symbols.forEach((sym) => {
-            symbols.push({
-              ...sym, page, block, paragraph, line, word,
-            });
-          });
-          words.push({
-            ...word, page, block, paragraph, line,
-          });
-        });
-        lines.push({
-          ...line, page, block, paragraph,
-        });
-      });
-      paragraphs.push({
-        ...paragraph, page, block,
-      });
-    });
-    blocks.push({
-      ...block, page,
-    });
-  });
-
-  return {
-    ...page, blocks, paragraphs, lines, words, symbols,
-  };
-};

src/utils/getEnvironment.js

@@ -1,21 +0,0 @@
-const isElectron = require('is-electron');
-
-module.exports = (key) => {
-  const env = {};
-
-  if (typeof WorkerGlobalScope !== 'undefined') {
-    env.type = 'webworker';
-  } else if (isElectron()) {
-    env.type = 'electron';
-  } else if (typeof window === 'object') {
-    env.type = 'browser';
-  } else if (typeof process === 'object' && typeof require === 'function') {
-    env.type = 'node';
-  }
-
-  if (typeof key === 'undefined') {
-    return env;
-  }
-
-  return env[key];
-};

src/utils/getId.js

@@ -1,3 +0,0 @@
-module.exports = (prefix, cnt) => (
-  `${prefix}-${cnt}-${Math.random().toString(16).slice(3, 8)}`
-);

src/utils/log.js

@@ -1,9 +0,0 @@
-let logging = false;
-
-exports.logging = logging;
-
-exports.setLogging = (_logging) => {
-  logging = _logging;
-};
-
-exports.log = (...args) => (logging ? console.log.apply(this, args) : null);

src/utils/resolvePaths.js

@@ -1,12 +0,0 @@
-const isBrowser = require('./getEnvironment')('type') === 'browser';
-const resolveURL = isBrowser ? require('resolve-url') : s => s; // eslint-disable-line
-
-module.exports = (options) => {
-  const opts = { ...options };
-  ['corePath', 'workerPath', 'langPath'].forEach((key) => {
-    if (options[key]) {
-      opts[key] = resolveURL(opts[key]);
-    }
-  });
-  return opts;
-};

src/worker-script/browser/cache.js

@@ -1,10 +0,0 @@
-const { set, get, del } = require('idb-keyval');
-
-module.exports = {
-  readCache: get,
-  writeCache: set,
-  deleteCache: del,
-  checkCache: (path) => (
-    get(path).then((v) => typeof v !== 'undefined')
-  ),
-};

src/worker-script/browser/getCore.js

@@ -1,30 +0,0 @@
-const { simd } = require('wasm-feature-detect');
-const { dependencies } = require('../../../package.json');
-
-module.exports = async (corePath, res) => {
-  if (typeof global.TesseractCore === 'undefined') {
-    res.progress({ status: 'loading tesseract core', progress: 0 });
-
-    // If the user specifies a core path, we use that
-    // Otherwise, we detect the correct core based on SIMD support
-    let corePathImport = corePath;
-    if (!corePathImport) {
-      const simdSupport = await simd();
-      if (simdSupport) {
-        corePathImport = `https://unpkg.com/tesseract.js-core@v${dependencies['tesseract.js-core'].substring(1)}/tesseract-core-simd.wasm.js`;
-      } else {
-        corePathImport = `https://unpkg.com/tesseract.js-core@v${dependencies['tesseract.js-core'].substring(1)}/tesseract-core.wasm.js`;
-      }
-    }
-
-    global.importScripts(corePathImport);
-
-    if (typeof global.TesseractCoreWASM !== 'undefined' && typeof WebAssembly === 'object') {
-      global.TesseractCore = global.TesseractCoreWASM;
-    } else {
-      throw Error('Failed to load TesseractCore');
-    }
-    res.progress({ status: 'loading tesseract core', progress: 1 });
-  }
-  return global.TesseractCore;
-};

src/worker-script/browser/gunzip.js

@@ -1 +0,0 @@
-module.exports = require('zlibjs').gunzipSync;

src/worker-script/browser/index.js

@@ -1,32 +0,0 @@
-/**
- *
- * Browser worker scripts
- *
- * @fileoverview Browser worker implementation
- * @author Kevin Kwok <antimatter15@gmail.com>
- * @author Guillermo Webster <gui@mit.edu>
- * @author Jerome Wu <jeromewus@gmail.com>
- */
-
-const worker = require('..');
-const getCore = require('./getCore');
-const gunzip = require('./gunzip');
-const cache = require('./cache');
-
-/*
- * register message handler
- */
-global.addEventListener('message', ({ data }) => {
-  worker.dispatchHandlers(data, (obj) => postMessage(obj));
-});
-
-/*
- * getCore is a sync function to load and return
- * TesseractCore.
- */
-worker.setAdapter({
-  getCore,
-  gunzip,
-  fetch: () => {},
-  ...cache,
-});

src/worker-script/constants/defaultParams.js

@@ -1,14 +0,0 @@
-/*
- * default params for tesseract.js
- */
-const PSM = require('../../constants/PSM');
-
-module.exports = {
-  tessedit_pageseg_mode: PSM.SINGLE_BLOCK,
-  tessedit_char_whitelist: '',
-  tessjs_create_hocr: '1',
-  tessjs_create_tsv: '1',
-  tessjs_create_box: '0',
-  tessjs_create_unlv: '0',
-  tessjs_create_osd: '0',
-};

src/worker-script/index.js

@@ -1,313 +0,0 @@
-/**
- *
- * Worker script for browser and node
- *
- * @fileoverview Worker script for browser and node
- * @author Kevin Kwok <antimatter15@gmail.com>
- * @author Guillermo Webster <gui@mit.edu>
- * @author Jerome Wu <jeromewus@gmail.com>
- */
-require('regenerator-runtime/runtime');
-const fileType = require('file-type');
-const isURL = require('is-url');
-const dump = require('./utils/dump');
-const isWebWorker = require('../utils/getEnvironment')('type') === 'webworker';
-const setImage = require('./utils/setImage');
-const defaultParams = require('./constants/defaultParams');
-const { log, setLogging } = require('../utils/log');
-
-/*
- * Tesseract Module returned by TesseractCore.
- */
-let TessModule;
-/*
- * TessearctBaseAPI instance
- */
-let api = null;
-let latestJob;
-let adapter = {};
-let params = defaultParams;
-
-const load = async ({ workerId, jobId, payload: { options: { corePath, logging } } }, res) => {
-  setLogging(logging);
-  if (!TessModule) {
-    const Core = await adapter.getCore(corePath, res);
-
-    res.progress({ workerId, status: 'initializing tesseract', progress: 0 });
-
-    Core({
-      TesseractProgress(percent) {
-        latestJob.progress({
-          workerId,
-          jobId,
-          status: 'recognizing text',
-          progress: Math.max(0, (percent - 30) / 70),
-        });
-      },
-    }).then((tessModule) => {
-      TessModule = tessModule;
-      res.progress({ workerId, status: 'initialized tesseract', progress: 1 });
-      res.resolve({ loaded: true });
-    });
-  } else {
-    res.resolve({ loaded: true });
-  }
-};
-
-const FS = ({ workerId, payload: { method, args } }, res) => {
-  log(`[${workerId}]: FS.${method} with args ${args}`);
-  res.resolve(TessModule.FS[method](...args));
-};
-
-const loadLanguage = async ({
-  workerId,
-  payload: {
-    langs,
-    options: {
-      langPath,
-      dataPath,
-      cachePath,
-      cacheMethod,
-      gzip = true,
-    },
-  },
-},
-res) => {
-  const loadAndGunzipFile = async (_lang) => {
-    const lang = typeof _lang === 'string' ? _lang : _lang.code;
-    const readCache = ['refresh', 'none'].includes(cacheMethod)
-      ? () => Promise.resolve()
-      : adapter.readCache;
-    let data = null;
-
-    try {
-      const _data = await readCache(`${cachePath || '.'}/${lang}.traineddata`);
-      if (typeof _data !== 'undefined') {
-        log(`[${workerId}]: Load ${lang}.traineddata from cache`);
-        res.progress({ workerId, status: 'loading language traineddata (from cache)', progress: 0.5 });
-        data = _data;
-      } else {
-        throw Error('Not found in cache');
-      }
-    } catch (e) {
-      log(`[${workerId}]: Load ${lang}.traineddata from ${langPath}`);
-      if (typeof _lang === 'string') {
-        let path = null;
-
-        if (isURL(langPath) || langPath.startsWith('moz-extension://') || langPath.startsWith('chrome-extension://') || langPath.startsWith('file://')) { /** When langPath is an URL */
-          path = langPath;
-        }
-
-        if (path !== null) {
-          const fetchUrl = `${path}/${lang}.traineddata${gzip ? '.gz' : ''}`;
-          const resp = await (isWebWorker ? fetch : adapter.fetch)(fetchUrl);
-          if (!resp.ok) {
-            throw Error(`Network error while fetching ${fetchUrl}. Response code: ${resp.status}`);
-          }
-          data = await resp.arrayBuffer();
-        } else {
-          data = await adapter.readCache(`${langPath}/${lang}.traineddata${gzip ? '.gz' : ''}`);
-        }
-      } else {
-        data = _lang.data; // eslint-disable-line
-      }
-    }
-
-    data = new Uint8Array(data);
-
-    const type = fileType(data);
-    if (typeof type !== 'undefined' && type.mime === 'application/gzip') {
-      data = adapter.gunzip(data);
-    }
-
-    if (TessModule) {
-      if (dataPath) {
-        try {
-          TessModule.FS.mkdir(dataPath);
-        } catch (err) {
-          res.reject(err.toString());
-        }
-      }
-      TessModule.FS.writeFile(`${dataPath || '.'}/${lang}.traineddata`, data);
-    }
-
-    if (['write', 'refresh', undefined].includes(cacheMethod)) {
-      await adapter.writeCache(`${cachePath || '.'}/${lang}.traineddata`, data);
-    }
-
-    return Promise.resolve(data);
-  };
-
-  res.progress({ workerId, status: 'loading language traineddata', progress: 0 });
-  try {
-    await Promise.all((typeof langs === 'string' ? langs.split('+') : langs).map(loadAndGunzipFile));
-    res.progress({ workerId, status: 'loaded language traineddata', progress: 1 });
-    res.resolve(langs);
-  } catch (err) {
-    res.reject(err.toString());
-  }
-};
-
-const setParameters = ({ payload: { params: _params } }, res) => {
-  Object.keys(_params)
-    .filter((k) => !k.startsWith('tessjs_'))
-    .forEach((key) => {
-      api.SetVariable(key, _params[key]);
-    });
-  params = { ...params, ..._params };
-
-  if (typeof res !== 'undefined') {
-    res.resolve(params);
-  }
-};
-
-const initialize = ({
-  workerId,
-  payload: { langs: _langs, oem },
-}, res) => {
-  const langs = (typeof _langs === 'string')
-    ? _langs
-    : _langs.map((l) => ((typeof l === 'string') ? l : l.data)).join('+');
-
-  try {
-    res.progress({
-      workerId, status: 'initializing api', progress: 0,
-    });
-    if (api !== null) {
-      api.End();
-    }
-    api = new TessModule.TessBaseAPI();
-    const status = api.Init(null, langs, oem);
-    if (status === -1) {
-      res.reject('initialization failed');
-    }
-    params = defaultParams;
-    setParameters({ payload: { params } });
-    res.progress({
-      workerId, status: 'initialized api', progress: 1,
-    });
-    res.resolve();
-  } catch (err) {
-    res.reject(err.toString());
-  }
-};
-
-const recognize = ({ payload: { image, options: { rectangle: rec } } }, res) => {
-  try {
-    const ptr = setImage(TessModule, api, image);
-    if (typeof rec === 'object') {
-      api.SetRectangle(rec.left, rec.top, rec.width, rec.height);
-    }
-    api.Recognize(null);
-    res.resolve(dump(TessModule, api, params));
-    TessModule._free(ptr);
-  } catch (err) {
-    res.reject(err.toString());
-  }
-};
-
-const getPDF = ({ payload: { title, textonly } }, res) => {
-  const pdfRenderer = new TessModule.TessPDFRenderer('tesseract-ocr', '/', textonly);
-  pdfRenderer.BeginDocument(title);
-  pdfRenderer.AddImage(api);
-  pdfRenderer.EndDocument();
-  TessModule._free(pdfRenderer);
-
-  res.resolve(TessModule.FS.readFile('/tesseract-ocr.pdf'));
-};
-
-const detect = ({ payload: { image } }, res) => {
-  try {
-    const ptr = setImage(TessModule, api, image);
-    const results = new TessModule.OSResults();
-
-    if (!api.DetectOS(results)) {
-      api.End();
-      TessModule._free(ptr);
-      res.reject('Failed to detect OS');
-    } else {
-      const best = results.best_result;
-      const oid = best.orientation_id;
-      const sid = best.script_id;
-
-      TessModule._free(ptr);
-
-      res.resolve({
-        tesseract_script_id: sid,
-        script: results.unicharset.get_script_from_script_id(sid),
-        script_confidence: best.sconfidence,
-        orientation_degrees: [0, 270, 180, 90][oid],
-        orientation_confidence: best.oconfidence,
-      });
-    }
-  } catch (err) {
-    res.reject(err.toString());
-  }
-};
-
-const terminate = (_, res) => {
-  try {
-    if (api !== null) {
-      api.End();
-    }
-    res.resolve({ terminated: true });
-  } catch (err) {
-    res.reject(err.toString());
-  }
-};
-
-/**
- * dispatchHandlers
- *
- * @name dispatchHandlers
- * @function worker data handler
- * @access public
- * @param {object} data
- * @param {string} data.jobId - unique job id
- * @param {string} data.action - action of the job, only recognize and detect for now
- * @param {object} data.payload - data for the job
- * @param {function} send - trigger job to work
- */
-exports.dispatchHandlers = (packet, send) => {
-  const res = (status, data) => {
-    send({
-      ...packet,
-      status,
-      data,
-    });
-  };
-  res.resolve = res.bind(this, 'resolve');
-  res.reject = res.bind(this, 'reject');
-  res.progress = res.bind(this, 'progress');
-
-  latestJob = res;
-
-  try {
-    ({
-      load,
-      FS,
-      loadLanguage,
-      initialize,
-      setParameters,
-      recognize,
-      getPDF,
-      detect,
-      terminate,
-    })[packet.action](packet, res);
-  } catch (err) {
-    /** Prepare exception to travel through postMessage */
-    res.reject(err.toString());
-  }
-};
-
-/**
- * setAdapter
- *
- * @name setAdapter
- * @function
- * @access public
- * @param {object} adapter - implementation of the worker, different in browser and node environment
- */
-exports.setAdapter = (_adapter) => {
-  adapter = _adapter;
-};

src/worker-script/node/cache.js

@@ -1,16 +0,0 @@
-const util = require('util');
-const fs = require('fs');
-
-module.exports = {
-  readCache: util.promisify(fs.readFile),
-  writeCache: util.promisify(fs.writeFile),
-  deleteCache: (path) => (
-    util.promisify(fs.unlink)(path)
-      .catch(() => {})
-  ),
-  checkCache: (path) => (
-    util.promisify(fs.access)(path, fs.F_OK)
-      .then((err) => (err === null))
-      .catch(() => false)
-  ),
-};

src/worker-script/node/getCore.js

@@ -1,20 +0,0 @@
-const { simd } = require('wasm-feature-detect');
-
-let TesseractCore = null;
-/*
- * getCore is a sync function to load and return
- * TesseractCore.
- */
-module.exports = async (_, res) => {
-  if (TesseractCore === null) {
-    const simdSupport = await simd();
-    res.progress({ status: 'loading tesseract core', progress: 0 });
-    if (simdSupport) {
-      TesseractCore = require('tesseract.js-core/tesseract-core-simd');
-    } else {
-      TesseractCore = require('tesseract.js-core/tesseract-core');
-    }
-    res.progress({ status: 'loaded tesseract core', progress: 1 });
-  }
-  return TesseractCore;
-};

src/worker-script/node/gunzip.js

@@ -1 +0,0 @@
-module.exports = require('zlib').gunzipSync;

src/worker-script/node/index.js

@@ -1,30 +0,0 @@
-/**
- *
- * Tesseract Worker Script for Node
- *
- * @fileoverview Node worker implementation
- * @author Kevin Kwok <antimatter15@gmail.com>
- * @author Guillermo Webster <gui@mit.edu>
- * @author Jerome Wu <jeromewus@gmail.com>
- */
-
-const fetch = require('node-fetch');
-const { parentPort } = require('worker_threads');
-const worker = require('..');
-const getCore = require('./getCore');
-const gunzip = require('./gunzip');
-const cache = require('./cache');
-
-/*
- * register message handler
- */
-parentPort.on('message', (packet) => {
-  worker.dispatchHandlers(packet, (obj) => parentPort.postMessage(obj));
-});
-
-worker.setAdapter({
-  getCore,
-  gunzip,
-  fetch,
-  ...cache,
-});

src/worker-script/utils/dump.js

@@ -1,201 +0,0 @@
-/**
- *
- * Dump data to a big JSON tree
- *
- * @fileoverview dump data to JSON tree
- * @author Kevin Kwok <antimatter15@gmail.com>
- * @author Guillermo Webster <gui@mit.edu>
- * @author Jerome Wu <jeromewus@gmail.com>
- */
-
-/**
- * deindent
- *
- * The generated HOCR is excessively indented, so
- * we get rid of that indentation
- *
- * @name deindent
- * @function deindent string
- * @access public
- */
-const deindent = (html) => {
-  const lines = html.split('\n');
-  if (lines[0].substring(0, 2) === '  ') {
-    for (let i = 0; i < lines.length; i += 1) {
-      if (lines[i].substring(0, 2) === '  ') {
-        lines[i] = lines[i].slice(2);
-      }
-    }
-  }
-  return lines.join('\n');
-};
-
-/**
- * dump
- *
- * @name dump
- * @function dump recognition result to a JSON object
- * @access public
- */
-module.exports = (TessModule, api, {
-  tessjs_create_hocr,
-  tessjs_create_tsv,
-  tessjs_create_box,
-  tessjs_create_unlv,
-  tessjs_create_osd,
-}) => {
-  const ri = api.GetIterator();
-  const {
-    RIL_BLOCK,
-    RIL_PARA,
-    RIL_TEXTLINE,
-    RIL_WORD,
-    RIL_SYMBOL,
-  } = TessModule;
-  const blocks = [];
-  let block;
-  let para;
-  let textline;
-  let word;
-  let symbol;
-
-  const enumToString = (value, prefix) => (
-    Object.keys(TessModule)
-      .filter((e) => (e.startsWith(`${prefix}_`) && TessModule[e] === value))
-      .map((e) => e.slice(prefix.length + 1))[0]
-  );
-
-  ri.Begin();
-  do {
-    if (ri.IsAtBeginningOf(RIL_BLOCK)) {
-      const poly = ri.BlockPolygon();
-      let polygon = null;
-      // BlockPolygon() returns null when automatic page segmentation is off
-      if (TessModule.getPointer(poly) > 0) {
-        const n = poly.get_n();
-        const px = poly.get_x();
-        const py = poly.get_y();
-        polygon = [];
-        for (let i = 0; i < n; i += 1) {
-          polygon.push([px.getValue(i), py.getValue(i)]);
-        }
-        /*
-         * TODO: find out why _ptaDestroy doesn't work
-         */
-        // TessModule._ptaDestroy(TessModule.getPointer(poly));
-      }
-
-      block = {
-        paragraphs: [],
-        text: ri.GetUTF8Text(RIL_BLOCK),
-        confidence: ri.Confidence(RIL_BLOCK),
-        baseline: ri.getBaseline(RIL_BLOCK),
-        bbox: ri.getBoundingBox(RIL_BLOCK),
-        blocktype: enumToString(ri.BlockType(), 'PT'),
-        polygon,
-      };
-      blocks.push(block);
-    }
-    if (ri.IsAtBeginningOf(RIL_PARA)) {
-      para = {
-        lines: [],
-        text: ri.GetUTF8Text(RIL_PARA),
-        confidence: ri.Confidence(RIL_PARA),
-        baseline: ri.getBaseline(RIL_PARA),
-        bbox: ri.getBoundingBox(RIL_PARA),
-        is_ltr: !!ri.ParagraphIsLtr(),
-      };
-      block.paragraphs.push(para);
-    }
-    if (ri.IsAtBeginningOf(RIL_TEXTLINE)) {
-      textline = {
-        words: [],
-        text: ri.GetUTF8Text(RIL_TEXTLINE),
-        confidence: ri.Confidence(RIL_TEXTLINE),
-        baseline: ri.getBaseline(RIL_TEXTLINE),
-        bbox: ri.getBoundingBox(RIL_TEXTLINE),
-      };
-      para.lines.push(textline);
-    }
-    if (ri.IsAtBeginningOf(RIL_WORD)) {
-      const fontInfo = ri.getWordFontAttributes();
-      const wordDir = ri.WordDirection();
-      word = {
-        symbols: [],
-        choices: [],
-
-        text: ri.GetUTF8Text(RIL_WORD),
-        confidence: ri.Confidence(RIL_WORD),
-        baseline: ri.getBaseline(RIL_WORD),
-        bbox: ri.getBoundingBox(RIL_WORD),
-
-        is_numeric: !!ri.WordIsNumeric(),
-        in_dictionary: !!ri.WordIsFromDictionary(),
-        direction: enumToString(wordDir, 'DIR'),
-        language: ri.WordRecognitionLanguage(),
-
-        is_bold: fontInfo.is_bold,
-        is_italic: fontInfo.is_italic,
-        is_underlined: fontInfo.is_underlined,
-        is_monospace: fontInfo.is_monospace,
-        is_serif: fontInfo.is_serif,
-        is_smallcaps: fontInfo.is_smallcaps,
-        font_size: fontInfo.pointsize,
-        font_id: fontInfo.font_id,
-        font_name: fontInfo.font_name,
-      };
-      const wc = new TessModule.WordChoiceIterator(ri);
-      do {
-        word.choices.push({
-          text: wc.GetUTF8Text(),
-          confidence: wc.Confidence(),
-        });
-      } while (wc.Next());
-      TessModule.destroy(wc);
-      textline.words.push(word);
-    }
-
-    // let image = null;
-    // var pix = ri.GetBinaryImage(TessModule.RIL_SYMBOL)
-    // var image = pix2array(pix);
-    // // for some reason it seems that things stop working if you destroy pics
-    // TessModule._pixDestroy(TessModule.getPointer(pix));
-    if (ri.IsAtBeginningOf(RIL_SYMBOL)) {
-      symbol = {
-        choices: [],
-        image: null,
-        text: ri.GetUTF8Text(RIL_SYMBOL),
-        confidence: ri.Confidence(RIL_SYMBOL),
-        baseline: ri.getBaseline(RIL_SYMBOL),
-        bbox: ri.getBoundingBox(RIL_SYMBOL),
-        is_superscript: !!ri.SymbolIsSuperscript(),
-        is_subscript: !!ri.SymbolIsSubscript(),
-        is_dropcap: !!ri.SymbolIsDropcap(),
-      };
-      word.symbols.push(symbol);
-      const ci = new TessModule.ChoiceIterator(ri);
-      do {
-        symbol.choices.push({
-          text: ci.GetUTF8Text(),
-          confidence: ci.Confidence(),
-        });
-      } while (ci.Next());
-      // TessModule.destroy(i);
-    }
-  } while (ri.Next(RIL_SYMBOL));
-  TessModule.destroy(ri);
-
-  return {
-    text: api.GetUTF8Text(),
-    hocr: tessjs_create_hocr === '1' ? deindent(api.GetHOCRText()) : null,
-    tsv: tessjs_create_tsv === '1' ? api.GetTSVText() : null,
-    box: tessjs_create_box === '1' ? api.GetBoxText() : null,
-    unlv: tessjs_create_unlv === '1' ? api.GetUNLVText() : null,
-    osd: tessjs_create_osd === '1' ? api.GetOsdText() : null,
-    confidence: api.MeanTextConf(),
-    blocks,
-    psm: enumToString(api.GetPageSegMode(), 'PSM'),
-    oem: enumToString(api.oem(), 'OEM'),
-    version: api.Version(),
-  };
-};

src/worker-script/utils/setImage.js

@@ -1,63 +0,0 @@
-const bmp = require('bmp-js');
-const fileType = require('file-type');
-
-/**
- * setImage
- *
- * @name setImage
- * @function set image in tesseract for recognition
- * @access public
- */
-module.exports = (TessModule, api, image) => {
-  const buf = Buffer.from(Array.from({ ...image, length: Object.keys(image).length }));
-  const type = fileType(buf);
-  let bytesPerPixel = 0;
-  let data = null;
-  let pix = null;
-  let w = 0;
-  let h = 0;
-
-  const exif = buf.slice(0, 500).toString().match(/\x01\x12\x00\x03\x00\x00\x00\x01\x00(.)/)?.[1]?.charCodeAt(0) || 1;
-
-  /*
-   * Leptonica supports uncompressed but not compressed bmp files
-   * @see https://github.com/DanBloomberg/leptonica/issues/607#issuecomment-1068802516
-   * We therefore use bmp-js to process all bmp files
-   */
-  if (type && type.mime === 'image/bmp') {
-    const bmpBuf = bmp.decode(buf);
-    data = TessModule._malloc(bmpBuf.data.length * Uint8Array.BYTES_PER_ELEMENT);
-    TessModule.HEAPU8.set(bmpBuf.data, data);
-    w = bmpBuf.width;
-    h = bmpBuf.height;
-    bytesPerPixel = 4;
-  } else {
-    const ptr = TessModule._malloc(buf.length * Uint8Array.BYTES_PER_ELEMENT);
-    TessModule.HEAPU8.set(buf, ptr);
-    pix = TessModule._pixReadMem(ptr, buf.length);
-    if (TessModule.getValue(pix + (7 * 4), 'i32') === 0) {
-      /*
-       * Set a yres default value to prevent warning from tesseract
-       * See kMinCredibleResolution in tesseract/src/ccstruct/publictypes.h
-       */
-      TessModule.setValue(pix + (7 * 4), 300, 'i32');
-    }
-    [w, h] = Array(2).fill(0)
-      .map((v, idx) => (
-        TessModule.getValue(pix + (idx * 4), 'i32')
-      ));
-  }
-
-  /*
-   * As some image format (ex. bmp) is not supported natiely by tesseract,
-   * sometimes it will not return pix directly, but data and bytesPerPixel
-   * for another SetImage usage.
-   *
-   */
-  if (data === null) {
-    api.SetImage(pix, undefined, undefined, undefined, undefined, exif);
-  } else {
-    api.SetImage(data, w, h, bytesPerPixel, w * bytesPerPixel, exif);
-  }
-  return data === null ? pix : data;
-};

src/worker/browser/defaultOptions.js

@@ -1,18 +0,0 @@
-const resolveURL = require('resolve-url');
-const { version } = require('../../../package.json');
-const defaultOptions = require('../../constants/defaultOptions');
-
-/*
- * Default options for browser worker
- */
-module.exports = {
-  ...defaultOptions,
-  workerPath: (typeof process !== 'undefined' && process.env.TESS_ENV === 'development')
-    ? resolveURL(`/dist/worker.dev.js?nocache=${Math.random().toString(36).slice(3)}`)
-    : `https://unpkg.com/tesseract.js@v${version}/dist/worker.min.js`,
-  /*
-   * If browser doesn't support WebAssembly,
-   * load ASM version instead
-   */
-  corePath: null,
-};

src/worker/browser/index.js

@@ -1,24 +0,0 @@
-/**
- *
- * Tesseract Worker adapter for browser
- *
- * @fileoverview Tesseract Worker adapter for browser
- * @author Kevin Kwok <antimatter15@gmail.com>
- * @author Guillermo Webster <gui@mit.edu>
- * @author Jerome Wu <jeromewus@gmail.com>
- */
-const defaultOptions = require('./defaultOptions');
-const spawnWorker = require('./spawnWorker');
-const terminateWorker = require('./terminateWorker');
-const onMessage = require('./onMessage');
-const send = require('./send');
-const loadImage = require('./loadImage');
-
-module.exports = {
-  defaultOptions,
-  spawnWorker,
-  terminateWorker,
-  onMessage,
-  send,
-  loadImage,
-};

src/worker/browser/loadImage.js

@@ -1,68 +0,0 @@
-const resolveURL = require('resolve-url');
-
-/**
- * readFromBlobOrFile
- *
- * @name readFromBlobOrFile
- * @function
- * @access private
- */
-const readFromBlobOrFile = (blob) => (
-  new Promise((resolve, reject) => {
-    const fileReader = new FileReader();
-    fileReader.onload = () => {
-      resolve(fileReader.result);
-    };
-    fileReader.onerror = ({ target: { error: { code } } }) => {
-      reject(Error(`File could not be read! Code=${code}`));
-    };
-    fileReader.readAsArrayBuffer(blob);
-  })
-);
-
-/**
- * loadImage
- *
- * @name loadImage
- * @function load image from different source
- * @access private
- */
-const loadImage = async (image) => {
-  let data = image;
-  if (typeof image === 'undefined') {
-    return 'undefined';
-  }
-
-  if (typeof image === 'string') {
-    // Base64 Image
-    if (/data:image\/([a-zA-Z]*);base64,([^"]*)/.test(image)) {
-      data = atob(image.split(',')[1])
-        .split('')
-        .map((c) => c.charCodeAt(0));
-    } else {
-      const resp = await fetch(resolveURL(image));
-      data = await resp.arrayBuffer();
-    }
-  } else if (image instanceof HTMLElement) {
-    if (image.tagName === 'IMG') {
-      data = await loadImage(image.src);
-    }
-    if (image.tagName === 'VIDEO') {
-      data = await loadImage(image.poster);
-    }
-    if (image.tagName === 'CANVAS') {
-      await new Promise((resolve) => {
-        image.toBlob(async (blob) => {
-          data = await readFromBlobOrFile(blob);
-          resolve();
-        });
-      });
-    }
-  } else if (image instanceof File || image instanceof Blob) {
-    data = await readFromBlobOrFile(image);
-  }
-
-  return new Uint8Array(data);
-};
-
-module.exports = loadImage;

src/worker/browser/onMessage.js

@@ -1,5 +0,0 @@
-module.exports = (worker, handler) => {
-  worker.onmessage = ({ data }) => { // eslint-disable-line
-    handler(data);
-  };
-};

src/worker/browser/send.js

@@ -1,10 +0,0 @@
-/**
- * send
- *
- * @name send
- * @function send packet to worker and create a job
- * @access public
- */
-module.exports = async (worker, packet) => {
-  worker.postMessage(packet);
-};

src/worker/browser/spawnWorker.js

@@ -1,20 +0,0 @@
-/**
- * spawnWorker
- *
- * @name spawnWorker
- * @function create a new Worker in browser
- * @access public
- */
-module.exports = ({ workerPath, workerBlobURL }) => {
-  let worker;
-  if (Blob && URL && workerBlobURL) {
-    const blob = new Blob([`importScripts("${workerPath}");`], {
-      type: 'application/javascript',
-    });
-    worker = new Worker(URL.createObjectURL(blob));
-  } else {
-    worker = new Worker(workerPath);
-  }
-
-  return worker;
-};

src/worker/browser/terminateWorker.js

@@ -1,10 +0,0 @@
-/**
- * terminateWorker
- *
- * @name terminateWorker
- * @function terminate worker
- * @access public
- */
-module.exports = (worker) => {
-  worker.terminate();
-};

src/worker/node/defaultOptions.js

@@ -1,10 +0,0 @@
-const path = require('path');
-const defaultOptions = require('../../constants/defaultOptions');
-
-/*
- * Default options for node worker
- */
-module.exports = {
-  ...defaultOptions,
-  workerPath: path.join(__dirname, '..', '..', 'worker-script', 'node', 'index.js'),
-};