Fix langs TS typing (#570)

* Added webp test case per #548

* Added gif test per #499

.eslintrc

@@ -1,5 +1,6 @@
 {
-  "extends": "airbnb",
+  "extends": "airbnb-base",
+  "parser": "babel-eslint",
   "env": {
     "browser": true,
     "node": true,
@@ -10,6 +11,7 @@
     "no-underscore-dangle": 0,
     "no-console": 0,
     "global-require": 0,
-    "camelcase": 0
+    "camelcase": 0,
+    "no-control-regex": 0
   }
 }

.github/FUNDING.yml

@@ -4,6 +4,6 @@ github: # Replace with up to 4 GitHub Sponsors-enabled usernames e.g., [user1, u
 patreon: # Replace with a single Patreon username
 open_collective: tesseractjs
 ko_fi: # Replace with a single Ko-fi username
-tidelift: # Replace with a single Tidelift platform-name/package-name e.g., npm/babel
+tidelift: npm/tesseract.js
 community_bridge: # Replace with a single Community Bridge project-name e.g., cloud-foundry
-custom: # Replace with a single custom sponsorship URL
+custom: ["https://etherscan.io/address/0x74ace8c74535d6dac03ebdc708ca2fba54796ef2"]

.github/SECURITY.md

@@ -0,0 +1,5 @@
+## 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

@@ -0,0 +1,71 @@
+# 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

@@ -0,0 +1,29 @@
+# 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

.gitpod.Dockerfile

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

.gitpod.yml

@@ -1,7 +1,9 @@
+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
+    onOpen: ignore

.travis.yml

@@ -1,7 +0,0 @@
-language: node_js
-node_js:
-  - "lts/*" # Use LTS version
-
-script:
-  - npm run lint
-  - npm test

README.md

@@ -1,8 +1,10 @@
 <p align="center">
-<a href="https://tesseract.projectnaptha.com/"><img alt="Tesseract.js" src="https://tesseract.projectnaptha.com/img/logo_small.png"></a>
+<a href="https://tesseract.projectnaptha.com/"><img width="256px" height="256px" alt="Tesseract.js" src="./docs/images/tesseract.png"></a>
 </p>
 
-[![Build Status](https://travis-ci.org/naptha/tesseract.js.svg?branch=master)](https://travis-ci.org/naptha/tesseract.js)
+![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)
@@ -10,17 +12,19 @@
 [![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)
 
-<h3 align="center">
-  Version 2 beta is now available and under development in the master branch<br>
-  Check the <a href="https://github.com/naptha/tesseract.js/tree/support/1.x">support/1.x</a> branch for version 1
-</h3>
-
-<br>
-
 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
+
 [![fancy demo gif](./docs/images/demo.gif)](http://tesseract.projectnaptha.com)
 
+Video Real-time Recognition
+
+<p align="center">
+  <a href="https://github.com/jeromewu/tesseract.js-video"><img alt="Tesseract.js Video" src="./docs/images/video-demo.gif"></a>
+</p>
+
+
 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:
@@ -52,21 +56,32 @@ const worker = createWorker({
   await worker.initialize('eng');
   const { data: { text } } = await worker.recognize('https://tesseract.projectnaptha.com/img/eng_bw.png');
   console.log(text);
-  await woker.terminate();
+  await worker.terminate();
 })();
 ```
 
-[Check out the docs](#docs) for a full explanation of the API.
-
-
-## Major changes in v2 beta
-- Upgrade to tesseract v4.1 (using emscripten 1.38.45)
-- Support multiple languages at the same time, eg: eng+chi_tra for English and Traditional Chinese
+[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`.
 
@@ -74,7 +89,7 @@ Tesseract.js works with a `<script>` tag via local copy or CDN, with webpack via
 ### CDN
 ```html
 <!-- v2 -->
-<script src='https://unpkg.com/tesseract.js@v2.0.0-beta.1/dist/tesseract.min.js'></script>
+<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>
@@ -84,16 +99,16 @@ After including the script the `Tesseract` variable will be globally available.
 
 ### Node.js
 
-**Tesseract.js currently requires Node.js v6.8.0 or higher**
+**Tesseract.js v3 requires Node.js v14 or higher**
 
 ```shell
-# For v2
-npm install tesseract.js@next
-yarn add tesseract.js@next
-
-# For v1
+# For v3
 npm install tesseract.js
 yarn add tesseract.js
+
+# For v2
+npm install tesseract.js@2
+yarn add tesseract.js@2
 ```
 
 
@@ -105,6 +120,19 @@ yarn add tesseract.js
 * [Local Installation](./docs/local-installation.md)
 * [FAQ](./docs/faq.md)
 
+## Use tesseract.js the way you like!
+
+- Offline Version: https://github.com/jeromewu/tesseract.js-offline
+- Electron Version: https://github.com/jeromewu/tesseract.js-electron
+- Custom Traineddata: https://github.com/jeromewu/tesseract.js-custom-traineddata
+- Chrome Extension #1: https://github.com/jeromewu/tesseract.js-chrome-extension
+- Chrome Extension #2: https://github.com/fxnoob/image-to-text
+- Firefox Extension: https://github.com/gnonio/korporize
+- With Vue: https://github.com/jeromewu/tesseract.js-vue-app
+- With Angular: https://github.com/jeromewu/tesseract.js-angular-app
+- With React: https://github.com/jeromewu/tesseract.js-react-app
+- Typescript: https://github.com/jeromewu/tesseract.js-typescript
+- Video Real-time Recognition: https://github.com/jeromewu/tesseract.js-video
 
 ## Contributing
 
@@ -125,7 +153,9 @@ npm start
 The development server will be available at http://localhost:3000/examples/browser/demo.html in your favorite browser.
 It will automatically rebuild `tesseract.dev.js` and `worker.dev.js` when you change files in the **src** folder.
 
-You can also run the development server in Gitpod ( a free online IDE and dev environment for GitHub that will automate your dev setup ) with a single click.
+### Online Setup with a single Click
+
+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. 
 
 [![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)
 

docs/api.md

@@ -2,6 +2,10 @@
 
 - [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)
@@ -42,6 +46,7 @@ createWorker is a factory function that creates a tesseract worker, a worker is
   - `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:**
@@ -59,6 +64,7 @@ const worker = createWorker({
 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
@@ -93,6 +99,84 @@ Worker.load() loads tesseract.js-core scripts (download from remote if not prese
 })();
 ```
 
+<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
 
@@ -143,17 +227,18 @@ Worker.setParameters() set parameters for Tesseract API (using SetVariable()), i
 
 **Supported Paramters:**
 
-| name | type | default value | description |
-| ---- | ---- | ------------- | ----------- |
-| tessedit\_ocr\_engine\_mode | enum | OEM.LSTM\_ONLY | 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 |
-| 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 |
+| 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:**
 
@@ -177,8 +262,8 @@ Figures out what words are in `image`, where the words are in `image`, etc.
 **Arguments:**
 
 - `image` see [Image Format](./image-format.md) for more details.
-- `options` a object of customized optons
-  - `rectangles` an array of objects to specify the region you want to recognized in the image, the object should contain top, left, width and height, see example below.
+- `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:**
@@ -197,7 +282,7 @@ const { createWorker } = Tesseract;
 })();
 ```
 
-With rectangles
+With rectangle
 
 ```javascript
 const { createWorker } = Tesseract;
@@ -207,9 +292,7 @@ const { createWorker } = Tesseract;
   await worker.loadLanguage('eng');
   await worker.initialize('eng');
   const { data: { text } } = await worker.recognize(image, {
-    rectangles: [
-      { top: 0, left: 0, width: 100, height: 100 },
-    ],
+    rectangle: { top: 0, left: 0, width: 100, height: 100 },
   });
   console.log(text);
 })();
@@ -242,11 +325,7 @@ const { createWorker } = Tesseract;
 <a name="worker-terminate"></a>
 ### Worker.terminate(jobId): Promise
 
-Worker.terminate() terminates the worker and clean up
-
-**Arguments:**
-
-- `jobId` Please see details above
+Worker.terminate() terminates the worker and cleans up
 
 ```javascript
 (async () => {
@@ -257,7 +336,7 @@ Worker.terminate() terminates the worker and clean up
 <a name="create-scheduler"></a>
 ## createScheduler(): Scheduler
 
-createScheduler() is a factory function to create a scheduler, a scheduler manage a job queue and workers to enable multiple workers to work together, it is useful when you want to speed up your performance.
+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:**
 
@@ -271,7 +350,7 @@ const scheduler = createScheduler();
 <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 sheduler.
+Scheduler.addWorker() adds a worker into the worker pool inside scheduler, it is suggested to add one worker to only one scheduler.
 
 **Arguments:**
 
@@ -354,16 +433,16 @@ See [Tesseract.js](../src/Tesseract.js)
 <a name="detect"></a>
 ## detect(image, options): Promise
 
-Same background as recongize(), but it does detect instead.
+Same background as recognize(), but it does detect instead.
 
 See [Tesseract.js](../src/Tesseract.js)
 
 <a name="psm"></a>
 ## PSM
 
-See [PSM.js](../src/constatns/PSM.js)
+See [PSM.js](../src/constants/PSM.js)
 
 <a name="oem"></a>
 ## OEM
 
-See [OEM.js](../src/constatns/OEM.js)
+See [OEM.js](../src/constants/OEM.js)

docs/examples.md

@@ -2,17 +2,10 @@
 
 You can also check [examples](../examples) folder.
 
-Example repositories:
-
-- Offline version: https://github.com/jeromewu/tesseract.js-offline
-- With Vue: https://github.com/jeromewu/tesseract.js-vue-app
-- With Angular: https://github.com/jeromewu/tesseract.js-angular-app
-- Chrome Extension: https://github.com/jeromewu/tesseract.js-chrome-extension
-
 ### basic
 
 ```javascript
-import { createWorker } from 'tesseract.js';
+const { createWorker } = require('tesseract.js');
 
 const worker = createWorker();
 
@@ -29,7 +22,7 @@ const worker = createWorker();
 ### with detailed progress 
 
 ```javascript
-import { createWorker } from 'tesseract.js';
+const { createWorker } = require('tesseract.js');
 
 const worker = createWorker({
   logger: m => console.log(m), // Add logger here
@@ -48,7 +41,7 @@ const worker = createWorker({
 ### with multiple languages, separate by '+'
 
 ```javascript
-import { createWorker } from 'tesseract.js';
+const { createWorker } = require('tesseract.js');
 
 const worker = createWorker();
 
@@ -64,7 +57,7 @@ const worker = createWorker();
 ### with whitelist char (^2.0.0-beta.1)
 
 ```javascript
-import { createWorker } from 'tesseract.js';
+const { createWorker } = require('tesseract.js');
 
 const worker = createWorker();
 
@@ -86,7 +79,7 @@ const worker = createWorker();
 Check here for more details of pageseg mode: https://github.com/tesseract-ocr/tesseract/blob/4.0.0/src/ccstruct/publictypes.h#L163
 
 ```javascript
-import { createWorker, PSM } from 'tesseract.js';
+const { createWorker, PSM } = require('tesseract.js');
 
 const worker = createWorker();
 
@@ -110,30 +103,105 @@ 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 (^2.0.0-beta.1)
+### 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
-import { createWorker } from 'tesseract.js';
+const { createWorker } = require('tesseract.js');
 
 const worker = createWorker();
 const rectangles = [
-  { left: 0, top: 0, width: 500, height: 250 },
+  {
+    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 { data: { text } } = await worker.recognize('https://tesseract.projectnaptha.com/img/eng_bw.png', 'eng', { rectangles });
-  console.log(text);
+  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
-import { createWorker, createScheduler } from 'tesseract.js';
+const { createWorker, createScheduler } = require('tesseract.js');
 
 const scheduler = createScheduler();
 const worker1 = createWorker();
@@ -150,7 +218,7 @@ const worker2 = createWorker();
   scheduler.addWorker(worker2);
   /** Add 10 recognition jobs */
   const results = await Promise.all(Array(10).fill(0).map(() => (
-    await scheduler.addJob('recognize', 'https://tesseract.projectnaptha.com/img/eng_bw.png')
+    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

@@ -9,9 +9,9 @@ During the downloading of language model, Tesseract.js will first check if \*.tr
 
 ## How can I train my own \*.traineddata?
 
-For tesseract.js v2, check [TrainingTesseract 4.00](https://github.com/tesseract-ocr/tesseract/wiki/TrainingTesseract-4.00)
+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://github.com/tesseract-ocr/tesseract/wiki/Training-Tesseract-3.03%E2%80%933.05)
+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?
 

docs/image-format.md

@@ -1,17 +1,18 @@
 # Image Format
 
-Support Format: **bmp, jpg, png, pbm**
+The main Tesseract.js functions (ex. recognize, detect) take an `image` parameter.  The image formats and data types supported are listed below. 
 
-The main Tesseract.js functions (ex. recognize, detect) 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.
+Support Image Formats: **bmp, jpg, png, pbm, webp**
 
-On a browser, an image can be:
-- an `img`, `video`, or `canvas` element
-- a `File` object (from a file `<input>`)
-- a `Blob` object
-- a path or URL to an accessible image
-- a base64 encoded image fits `data:image\/([a-zA-Z]*);base64,([^"]*)` regexp
+For browser and Node, supported data types are:
+ - string with base64 encoded image (fits `data:image\/([a-zA-Z]*);base64,([^"]*)` regexp)
+ - buffer
 
-In Node.js, an image can be
-- a path to a local image
-- a Buffer storing binary image 
-- a base64 encoded image fits `data:image\/([a-zA-Z]*);base64,([^"]*)` regexp
+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

@@ -10,9 +10,9 @@ In Node.js environment, the only path you may want to customize is languages/lan
 
 ```javascript
 Tesseract.recognize(image, langs, {
-  workerPath: 'https://unpkg.com/tesseract.js@v2.0.0-beta.1/dist/worker.min.js',
+  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-beta.13/tesseract-core.wasm.js',
+  corePath: 'https://unpkg.com/tesseract.js-core@v2.0.0/tesseract-core.wasm.js',
 })
 ```
 
@@ -20,9 +20,9 @@ Or
 
 ```javascript
 const worker = createWorker({
-  workerPath: 'https://unpkg.com/tesseract.js@v2.0.0-beta.1/dist/worker.min.js',
+  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-beta.13/tesseract-core.wasm.js',
+  corePath: 'https://unpkg.com/tesseract.js-core@v2.0.0/tesseract-core.wasm.js',
 });
 ```
 
@@ -33,6 +33,6 @@ A string specifying the location of the [worker.js](./dist/worker.min.js) file.
 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-beta.13/tesseract-core.wasm.js' (fallback to tesseract-core.asm.js when WebAssembly is not available).
+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-beta.13/tesseract-core.js' which is a script that loads 'https://unpkg.com/tesseract.js-core@v2.0.0-beta.13/tesseract-core.wasm'. But it fails to fetch at this moment.
+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 +1,3 @@
 # Tesseract Languages
 
-Please check [HERE](https://github.com/tesseract-ocr/tesseract/wiki/Data-Files#data-files-for-version-400-november-29-2016) for supported languages
+Please check [HERE](https://tesseract-ocr.github.io/tessdoc/Data-Files#data-files-for-version-400-november-29-2016) for supported languages

examples/browser/basic-edge.html

@@ -0,0 +1,37 @@
+<!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/benchmark.html

@@ -0,0 +1,33 @@
+<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/demo.html

@@ -27,7 +27,7 @@ function progressUpdate(packet){
 
 		if(packet.status == 'done'){
 			var pre = document.createElement('pre')
-			pre.appendChild(document.createTextNode(packet.data.text))
+			pre.appendChild(document.createTextNode(packet.data.data.text))
 			line.innerHTML = ''
 			line.appendChild(pre)
 
@@ -71,7 +71,6 @@ 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>

examples/node/benchmark.js

@@ -0,0 +1,27 @@
+#!/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/recognize.js

@@ -1,13 +1,20 @@
 #!/usr/bin/env node
 const path = require('path');
-const Tesseract = require('../../');
+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),
+});
 
-Tesseract.recognize(image, 'eng', { logger: m => console.log(m) })
-  .then(({ data: { text } }) => {
-    console.log(text);
-  });
+(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

@@ -1,6 +1,6 @@
 {
   "name": "tesseract.js",
-  "version": "2.0.0-beta.1",
+  "version": "3.0.3",
   "description": "Pure Javascript Multilingual OCR",
   "main": "src/index.js",
   "types": "src/index.d.ts",
@@ -8,18 +8,22 @@
   "jsdelivr": "dist/tesseract.min.js",
   "scripts": {
     "start": "node scripts/server.js",
-    "build": "rimraf dist && webpack --config scripts/webpack.config.prod.js",
+    "build": "rimraf dist && webpack --config scripts/webpack.config.prod.js && rollup -c scripts/rollup.esm.js",
+    "profile:tesseract": "webpack-bundle-analyzer dist/tesseract-stats.json",
+    "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:one -- ./tests/*.test.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": {
@@ -31,38 +35,43 @@
   ],
   "license": "Apache-2.0",
   "devDependencies": {
-    "@babel/core": "^7.4.5",
-    "@babel/preset-env": "^7.4.5",
-    "acorn": "^6.1.1",
-    "babel-loader": "^8.0.6",
+    "@babel/core": "^7.18.7",
+    "@babel/preset-env": "^7.18.7",
+    "@rollup/plugin-commonjs": "^22.0.2",
+    "acorn": "^6.4.0",
+    "babel-loader": "^8.2.0",
+    "buffer": "^6.0.3",
     "cors": "^2.8.5",
-    "eslint": "^5.9.0",
-    "eslint-config-airbnb": "^17.1.0",
-    "eslint-plugin-import": "^2.14.0",
-    "eslint-plugin-jsx-a11y": "^6.1.2",
-    "eslint-plugin-react": "^7.11.1",
+    "eslint": "^7.2.0",
+    "eslint-config-airbnb-base": "^14.2.0",
+    "eslint-plugin-import": "^2.22.1",
     "expect.js": "^0.3.1",
-    "express": "^4.16.4",
-    "mocha": "^5.2.0",
-    "mocha-headless-chrome": "^2.0.2",
+    "express": "^4.17.1",
+    "mocha": "^8.1.3",
+    "mocha-headless-chrome": "^2.0.3",
     "npm-run-all": "^4.1.5",
-    "nyc": "^13.1.0",
-    "rimraf": "^2.6.3",
-    "wait-on": "^3.2.0",
-    "webpack": "^4.26.0",
-    "webpack-cli": "^3.1.2",
-    "webpack-dev-middleware": "^3.4.0"
+    "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": {
-    "axios": "^0.18.0",
+    "babel-eslint": "^10.1.0",
     "bmp-js": "^0.1.0",
-    "file-type": "^12.3.0",
+    "file-type": "^12.4.1",
     "idb-keyval": "^3.2.0",
-    "is-url": "1.2.2",
+    "is-electron": "^2.2.0",
+    "is-url": "^1.2.4",
+    "node-fetch": "^2.6.0",
     "opencollective-postinstall": "^2.0.2",
     "regenerator-runtime": "^0.13.3",
     "resolve-url": "^0.2.1",
-    "tesseract.js-core": "^2.0.0-beta.13",
+    "tesseract.js-core": "^3.0.2",
+    "wasm-feature-detect": "^1.2.11",
     "zlibjs": "^0.3.1"
   },
   "repository": {

scripts/rollup.esm.js

@@ -0,0 +1,13 @@
+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

@@ -13,5 +13,5 @@ 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 port 3000');
+  console.log('Server is running on the port no. 3000');
 });

scripts/webpack.config.common.js

@@ -1,4 +1,9 @@
 module.exports = {
+  resolve: {
+    fallback: {
+      buffer: require.resolve('buffer/'),
+    },
+  },
   module: {
     rules: [
       {

scripts/webpack.config.dev.js

@@ -1,5 +1,6 @@
 const path = require('path');
 const webpack = require('webpack');
+const { BundleAnalyzerPlugin } = require('webpack-bundle-analyzer');
 const common = require('./webpack.config.common');
 
 const genConfig = ({
@@ -14,11 +15,19 @@ const genConfig = ({
     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'],

scripts/webpack.config.prod.js

@@ -1,5 +1,6 @@
 const path = require('path');
 const common = require('./webpack.config.common');
+const webpack = require('webpack');
 
 const genConfig = ({
   entry, filename, library, libraryTarget,
@@ -14,6 +15,11 @@ const genConfig = ({
     library,
     libraryTarget,
   },
+  plugins: [
+    new webpack.ProvidePlugin({
+      Buffer: ['buffer', 'Buffer'],
+    }),
+  ]
 });
 
 module.exports = [

src/constants/PSM.js

@@ -15,4 +15,5 @@ module.exports = {
   SINGLE_CHAR: '10',
   SPARSE_TEXT: '11',
   SPARSE_TEXT_OSD: '12',
+  RAW_LINE: '13',
 };

src/constants/languages.js

@@ -0,0 +1,218 @@
+/*
+ * 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/createWorker.js

@@ -19,6 +19,7 @@ module.exports = (_options = {}) => {
   const id = getId('Worker', workerCounter);
   const {
     logger,
+    errorHandler,
     ...options
   } = resolvePaths({
     ...defaultOptions,
@@ -52,12 +53,44 @@ module.exports = (_options = {}) => {
     })
   );
 
-  const load = jobId => (
+  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,
@@ -106,12 +139,14 @@ module.exports = (_options = {}) => {
     }))
   );
 
-  const terminate = async (jobId) => {
+  const terminate = async () => {
     if (worker !== null) {
+      /*
       await startJob(createJob({
         id: jobId,
         action: 'terminate',
       }));
+      */
       terminateWorker(worker);
       worker = null;
     }
@@ -132,9 +167,13 @@ module.exports = (_options = {}) => {
       resolves[action]({ jobId, data: d });
     } else if (status === 'reject') {
       rejects[action](data);
-      throw Error(data);
+      if (errorHandler) {
+        errorHandler(data);
+      } else {
+        throw Error(data);
+      }
     } else if (status === 'progress') {
-      logger(data);
+      logger({ ...data, userJobId: jobId });
     }
   });
 
@@ -144,6 +183,10 @@ module.exports = (_options = {}) => {
     setResolve,
     setReject,
     load,
+    writeText,
+    readText,
+    removeFile,
+    FS,
     loadLanguage,
     initialize,
     setParameters,

src/index.d.ts

@@ -3,7 +3,7 @@ declare namespace Tesseract {
   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>)
+  function detect(image: ImageLike, options?: Partial<WorkerOptions>): any
 
   interface Scheduler {
     addWorker(worker: Worker): string
@@ -15,12 +15,22 @@ declare namespace Tesseract {
 
   interface Worker {
     load(jobId?: string): Promise<ConfigResult>
-    loadLanguage(langs?: string, jobId?: string): Promise<ConfigResult>
-    initialize(langs?: string, oem?: OEM, 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 {
@@ -32,12 +42,15 @@ declare namespace Tesseract {
     cacheMethod: string
     workerBlobURL: boolean
     gzip: boolean
-    logger: (any) => void
+    logger: (arg: any) => void,
+    errorHandler: (arg: any) => void
   }
   interface WorkerParams {
     tessedit_ocr_engine_mode: OEM
     tessedit_pageseg_mode: PSM
-    tessedit_char_whiltelist: string
+    tessedit_char_whitelist: string
+    preserve_interword_spaces: string
+    user_defined_dpi: string
     tessjs_create_hocr: string
     tessjs_create_tsv: string
     tessjs_create_box: string
@@ -45,7 +58,7 @@ declare namespace Tesseract {
     tessjs_create_osd: string
   }
   interface RecognizeOptions {
-    rectangles: Rectangle[]
+    rectangle: Rectangle
   }
   interface ConfigResult {
     jobId: string
@@ -55,6 +68,10 @@ declare namespace Tesseract {
     jobId: string
     data: Page
   }
+  interface GetPDFResult {
+    jobId: string
+    data: number[]
+  }
   interface DetectResult {
     jobId: string
     data: DetectData
@@ -72,13 +89,13 @@ declare namespace Tesseract {
     width: number
     height: number
   }
-  const enum OEM {
+  enum OEM {
     TESSERACT_ONLY,
     LSTM_ONLY,
     TESSERACT_LSTM_COMBINED,
     DEFAULT,
   }
-  const enum PSM {
+  enum PSM {
     OSD_ONLY = '0',
     AUTO_OSD = '1',
     AUTO_ONLY = '2',
@@ -92,11 +109,12 @@ declare namespace Tesseract {
     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;
+    paragraphs: Paragraph[];
     text: string;
     confidence: number;
     baseline: Baseline;
@@ -194,6 +212,7 @@ declare namespace Tesseract {
     confidence: number;
     lines: Line[];
     oem: string;
+    osd: string;
     paragraphs: Paragraph[];
     psm: string;
     symbols: Symbol[];

src/index.js

@@ -11,11 +11,13 @@ require('regenerator-runtime/runtime');
 const createScheduler = require('./createScheduler');
 const createWorker = require('./createWorker');
 const Tesseract = require('./Tesseract');
+const languages = require('./constants/languages');
 const OEM = require('./constants/OEM');
 const PSM = require('./constants/PSM');
 const { setLogging } = require('./utils/log');
 
 module.exports = {
+  languages,
   OEM,
   PSM,
   createScheduler,

src/utils/getEnvironment.js

@@ -1,10 +1,21 @@
+const isElectron = require('is-electron');
+
 module.exports = (key) => {
-  const env = {
-    type: (typeof window !== 'undefined') && (typeof window.document !== 'undefined') ? 'browser' : 'node',
-  };
+  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/resolvePaths.js

@@ -4,7 +4,7 @@ const resolveURL = isBrowser ? require('resolve-url') : s => s; // eslint-disabl
 module.exports = (options) => {
   const opts = { ...options };
   ['corePath', 'workerPath', 'langPath'].forEach((key) => {
-    if (typeof options[key] !== 'undefined') {
+    if (options[key]) {
       opts[key] = resolveURL(opts[key]);
     }
   });

src/worker-script/browser/cache.js

@@ -4,7 +4,7 @@ module.exports = {
   readCache: get,
   writeCache: set,
   deleteCache: del,
-  checkCache: path => (
-    get(path).then(v => typeof v !== 'undefined')
+  checkCache: (path) => (
+    get(path).then((v) => typeof v !== 'undefined')
   ),
 };

src/worker-script/browser/getCore.js

@@ -1,15 +1,26 @@
-module.exports = (corePath, res) => {
+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 });
-    global.importScripts(corePath);
-    /*
-     * Depending on whether the browser supports WebAssembly,
-     * the version of the TesseractCore will be different.
-     */
+
+    // 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 if (typeof global.TesseractCoreASM !== 'undefined') {
-      global.TesseractCore = global.TesseractCoreASM;
     } else {
       throw Error('Failed to load TesseractCore');
     }

src/worker-script/browser/index.js

@@ -8,17 +8,16 @@
  * @author Jerome Wu <jeromewus@gmail.com>
  */
 
-const worker = require('../');
+const worker = require('..');
 const getCore = require('./getCore');
 const gunzip = require('./gunzip');
-const resolveURL = require('./resolveURL');
 const cache = require('./cache');
 
 /*
  * register message handler
  */
 global.addEventListener('message', ({ data }) => {
-  worker.dispatchHandlers(data, obj => postMessage(obj));
+  worker.dispatchHandlers(data, (obj) => postMessage(obj));
 });
 
 /*
@@ -28,6 +27,6 @@ global.addEventListener('message', ({ data }) => {
 worker.setAdapter({
   getCore,
   gunzip,
-  resolveURL,
+  fetch: () => {},
   ...cache,
 });

src/worker-script/browser/resolveURL.js

@@ -1 +0,0 @@
-module.exports = require('resolve-url');

src/worker-script/constants/defaultParams.js

@@ -5,7 +5,7 @@ const PSM = require('../../constants/PSM');
 
 module.exports = {
   tessedit_pageseg_mode: PSM.SINGLE_BLOCK,
-  tessedit_char_whiltelist: '',
+  tessedit_char_whitelist: '',
   tessjs_create_hocr: '1',
   tessjs_create_tsv: '1',
   tessjs_create_box: '0',

src/worker-script/index.js

@@ -9,10 +9,9 @@
  */
 require('regenerator-runtime/runtime');
 const fileType = require('file-type');
-const axios = require('axios');
 const isURL = require('is-url');
 const dump = require('./utils/dump');
-const isBrowser = require('../utils/getEnvironment')('type') === 'browser';
+const isWebWorker = require('../utils/getEnvironment')('type') === 'webworker';
 const setImage = require('./utils/setImage');
 const defaultParams = require('./constants/defaultParams');
 const { log, setLogging } = require('../utils/log');
@@ -29,10 +28,10 @@ let latestJob;
 let adapter = {};
 let params = defaultParams;
 
-const load = ({ workerId, jobId, payload: { options: { corePath, logging } } }, res) => {
+const load = async ({ workerId, jobId, payload: { options: { corePath, logging } } }, res) => {
   setLogging(logging);
   if (!TessModule) {
-    const Core = adapter.getCore(corePath, res);
+    const Core = await adapter.getCore(corePath, res);
 
     res.progress({ workerId, status: 'initializing tesseract', progress: 0 });
 
@@ -55,6 +54,11 @@ const load = ({ workerId, jobId, payload: { options: { corePath, logging } } },
   }
 };
 
+const FS = ({ workerId, payload: { method, args } }, res) => {
+  log(`[${workerId}]: FS.${method} with args ${args}`);
+  res.resolve(TessModule.FS[method](...args));
+};
+
 const loadLanguage = async ({
   workerId,
   payload: {
@@ -68,7 +72,7 @@ const loadLanguage = async ({
     },
   },
 },
-  res) => {
+res) => {
   const loadAndGunzipFile = async (_lang) => {
     const lang = typeof _lang === 'string' ? _lang : _lang.code;
     const readCache = ['refresh', 'none'].includes(cacheMethod)
@@ -80,6 +84,7 @@ const loadLanguage = async ({
       const _data = await readCache(`${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');
@@ -89,18 +94,17 @@ const loadLanguage = async ({
       if (typeof _lang === 'string') {
         let path = null;
 
-        if (isURL(langPath) || langPath.startsWith('chrome-extension://') || langPath.startsWith('file://')) { /** When langPath is an URL */
+        if (isURL(langPath) || langPath.startsWith('moz-extension://') || langPath.startsWith('chrome-extension://') || langPath.startsWith('file://')) { /** When langPath is an URL */
           path = langPath;
-        } else if (process.browser) { /** When langPath is not an URL in browser */
-          path = adapter.resolveURL(langPath);
         }
 
         if (path !== null) {
-          const { data: _data } = await axios.get(
-            `${path}/${lang}.traineddata${gzip ? '.gz' : ''}`,
-            { responseType: 'arraybuffer' },
-          );
-          data = _data;
+          const fetchUrl = `${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' : ''}`);
         }
@@ -140,21 +144,13 @@ const loadLanguage = async ({
     res.progress({ workerId, status: 'loaded language traineddata', progress: 1 });
     res.resolve(langs);
   } catch (err) {
-    if (isBrowser && err instanceof DOMException) {
-      /*
-       * For some reason google chrome throw DOMException in loadLang,
-       * while other browser is OK, for now we ignore this exception
-       * and hopefully to find the root cause one day.
-       */
-    } else {
-      res.reject(err.toString());
-    }
+    res.reject(err.toString());
   }
 };
 
 const setParameters = ({ payload: { params: _params } }, res) => {
   Object.keys(_params)
-    .filter(k => !k.startsWith('tessjs_'))
+    .filter((k) => !k.startsWith('tessjs_'))
     .forEach((key) => {
       api.SetVariable(key, _params[key]);
     });
@@ -171,7 +167,7 @@ const initialize = ({
 }, res) => {
   const langs = (typeof _langs === 'string')
     ? _langs
-    : _langs.map(l => ((typeof l === 'string') ? l : l.data)).join('+');
+    : _langs.map((l) => ((typeof l === 'string') ? l : l.data)).join('+');
 
   try {
     res.progress({
@@ -181,7 +177,10 @@ const initialize = ({
       api.End();
     }
     api = new TessModule.TessBaseAPI();
-    api.Init(null, langs, oem);
+    const status = api.Init(null, langs, oem);
+    if (status === -1) {
+      res.reject('initialization failed');
+    }
     params = defaultParams;
     setParameters({ payload: { params } });
     res.progress({
@@ -193,14 +192,12 @@ const initialize = ({
   }
 };
 
-const recognize = ({ payload: { image, options: { rectangles = [] } } }, res) => {
+const recognize = ({ payload: { image, options: { rectangle: rec } } }, res) => {
   try {
     const ptr = setImage(TessModule, api, image);
-    rectangles.forEach(({
-      left, top, width, height,
-    }) => {
-      api.SetRectangle(left, top, width, height);
-    });
+    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);
@@ -288,6 +285,7 @@ exports.dispatchHandlers = (packet, send) => {
   try {
     ({
       load,
+      FS,
       loadLanguage,
       initialize,
       setParameters,

src/worker-script/node/cache.js

@@ -4,13 +4,13 @@ const fs = require('fs');
 module.exports = {
   readCache: util.promisify(fs.readFile),
   writeCache: util.promisify(fs.writeFile),
-  deleteCache: path => (
+  deleteCache: (path) => (
     util.promisify(fs.unlink)(path)
       .catch(() => {})
   ),
-  checkCache: path => (
+  checkCache: (path) => (
     util.promisify(fs.access)(path, fs.F_OK)
-      .then(err => (err === null))
+      .then((err) => (err === null))
       .catch(() => false)
   ),
 };

src/worker-script/node/getCore.js

@@ -1,12 +1,19 @@
+const { simd } = require('wasm-feature-detect');
+
 let TesseractCore = null;
 /*
  * getCore is a sync function to load and return
  * TesseractCore.
  */
-module.exports = (_, res) => {
+module.exports = async (_, res) => {
   if (TesseractCore === null) {
+    const simdSupport = await simd();
     res.progress({ status: 'loading tesseract core', progress: 0 });
-    TesseractCore = require('tesseract.js-core');
+    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/index.js

@@ -8,22 +8,23 @@
  * @author Jerome Wu <jeromewus@gmail.com>
  */
 
-const worker = require('../');
+const fetch = require('node-fetch');
+const { parentPort } = require('worker_threads');
+const worker = require('..');
 const getCore = require('./getCore');
-const resolveURL = require('./resolveURL');
 const gunzip = require('./gunzip');
 const cache = require('./cache');
 
 /*
  * register message handler
  */
-process.on('message', (packet) => {
-  worker.dispatchHandlers(packet, obj => process.send(obj));
+parentPort.on('message', (packet) => {
+  worker.dispatchHandlers(packet, (obj) => parentPort.postMessage(obj));
 });
 
 worker.setAdapter({
   getCore,
   gunzip,
-  resolveURL,
+  fetch,
   ...cache,
 });

src/worker-script/node/resolveURL.js

@@ -1 +0,0 @@
-module.exports = s => s;

src/worker-script/utils/dump.js

@@ -61,8 +61,8 @@ module.exports = (TessModule, api, {
 
   const enumToString = (value, prefix) => (
     Object.keys(TessModule)
-      .filter(e => (e.startsWith(`${prefix}_`) && TessModule[e] === value))
-      .map(e => e.slice(prefix.length + 1))[0]
+      .filter((e) => (e.startsWith(`${prefix}_`) && TessModule[e] === value))
+      .map((e) => e.slice(prefix.length + 1))[0]
   );
 
   ri.Begin();

src/worker-script/utils/setImage.js

@@ -17,10 +17,12 @@ module.exports = (TessModule, api, image) => {
   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;
+
   /*
-   * Although leptonica should support reading bmp, there is a bug of "compressed BMP files".
-   * As there is no solution, we need to use bmp-js for now.
-   * @see https://groups.google.com/forum/#!topic/tesseract-ocr/4mPD9zTxdxE
+   * 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);
@@ -53,9 +55,9 @@ module.exports = (TessModule, api, image) => {
    *
    */
   if (data === null) {
-    api.SetImage(pix);
+    api.SetImage(pix, undefined, undefined, undefined, undefined, exif);
   } else {
-    api.SetImage(data, w, h, bytesPerPixel, w * bytesPerPixel);
+    api.SetImage(data, w, h, bytesPerPixel, w * bytesPerPixel, exif);
   }
   return data === null ? pix : data;
 };

src/worker/browser/defaultOptions.js

@@ -1,5 +1,5 @@
 const resolveURL = require('resolve-url');
-const { version, dependencies } = require('../../../package.json');
+const { version } = require('../../../package.json');
 const defaultOptions = require('../../constants/defaultOptions');
 
 /*
@@ -14,5 +14,5 @@ module.exports = {
    * If browser doesn't support WebAssembly,
    * load ASM version instead
    */
-  corePath: `https://unpkg.com/tesseract.js-core@v${dependencies['tesseract.js-core'].substring(1)}/tesseract-core.${typeof WebAssembly === 'object' ? 'wasm' : 'asm'}.js`,
+  corePath: null,
 };

src/worker/browser/loadImage.js

@@ -1,4 +1,3 @@
-const axios = require('axios');
 const resolveURL = require('resolve-url');
 
 /**
@@ -8,7 +7,7 @@ const resolveURL = require('resolve-url');
  * @function
  * @access private
  */
-const readFromBlobOrFile = blob => (
+const readFromBlobOrFile = (blob) => (
   new Promise((resolve, reject) => {
     const fileReader = new FileReader();
     fileReader.onload = () => {
@@ -39,10 +38,10 @@ const loadImage = async (image) => {
     if (/data:image\/([a-zA-Z]*);base64,([^"]*)/.test(image)) {
       data = atob(image.split(',')[1])
         .split('')
-        .map(c => c.charCodeAt(0));
+        .map((c) => c.charCodeAt(0));
     } else {
-      const { data: _data } = await axios.get(resolveURL(image), { responseType: 'arraybuffer' });
-      data = _data;
+      const resp = await fetch(resolveURL(image));
+      data = await resp.arrayBuffer();
     }
   } else if (image instanceof HTMLElement) {
     if (image.tagName === 'IMG') {

src/worker/node/loadImage.js

@@ -1,6 +1,6 @@
 const util = require('util');
 const fs = require('fs');
-const axios = require('axios');
+const fetch = require('node-fetch');
 const isURL = require('is-url');
 
 const readFile = util.promisify(fs.readFile);
@@ -19,9 +19,9 @@ module.exports = async (image) => {
   }
 
   if (typeof image === 'string') {
-    if (isURL(image) || image.startsWith('chrome-extension://') || image.startsWith('file://')) {
-      const { data: _data } = await axios.get(image, { responseType: 'arraybuffer' });
-      data = _data;
+    if (isURL(image) || image.startsWith('moz-extension://') || image.startsWith('chrome-extension://') || image.startsWith('file://')) {
+      const resp = await fetch(image);
+      data = await resp.arrayBuffer();
     } else if (/data:image\/([a-zA-Z]*);base64,([^"]*)/.test(image)) {
       data = Buffer.from(image.split(',')[1], 'base64');
     } else {

src/worker/node/send.js

@@ -5,6 +5,6 @@
  * @function send packet to worker and create a job
  * @access public
  */
-module.exports = (worker, packet) => {
-  worker.send(packet);
+module.exports = async (worker, packet) => {
+  worker.postMessage(packet);
 };

src/worker/node/spawnWorker.js

@@ -1,4 +1,4 @@
-const { fork } = require('child_process');
+const { Worker } = require('worker_threads');
 
 /**
  * spawnWorker
@@ -7,6 +7,4 @@ const { fork } = require('child_process');
  * @function fork a new process in node
  * @access public
  */
-module.exports = ({ workerPath }) => (
-  fork(workerPath)
-);
+module.exports = ({ workerPath }) => new Worker(workerPath);

src/worker/node/terminateWorker.js

@@ -6,5 +6,5 @@
  * @access public
  */
 module.exports = (worker) => {
-  worker.kill();
+  worker.terminate();
 };

tests/FS.test.html

@@ -0,0 +1,18 @@
+<html>
+  <head>
+    <meta charset="utf-8">
+    <link rel="stylesheet" href="../node_modules/mocha/mocha.css">
+  </head>
+  <body>
+    <div id="mocha"></div>
+    <script src="../node_modules/mocha/mocha.js"></script>
+    <script src="../node_modules/expect.js/index.js"></script>
+    <script src="../dist/tesseract.dev.js"></script>
+    <script src="./constants.js"></script>
+    <script>mocha.setup('bdd');</script>
+    <script src="./FS.test.js"></script>
+    <script>
+      mocha.run();
+    </script>
+  </body>
+</html>

tests/FS.test.js

@@ -0,0 +1,37 @@
+const { createWorker } = Tesseract;
+const FS_WAIT = 500;
+const worker = createWorker(OPTIONS);
+before(function cb() {
+  this.timeout(0);
+  return worker.load();
+});
+
+describe('FS', async () => {
+  it('should write and read text from FS (using FS only)', () => {
+    [
+      SIMPLE_TEXT,
+    ].forEach(async (text) => {
+      const path = 'tmp.txt';
+      await worker.FS('writeFile', [path, SIMPLE_TEXT]);
+      setTimeout(async () => {
+        const { data } = await worker.FS('readFile', [path]);
+        await worker.FS('unlink', [path]);
+        expect(data.toString()).to.be(text);
+      }, FS_WAIT);
+    });
+  }).timeout(TIMEOUT);
+
+  it('should write and read text from FS (using writeFile, readFile)', () => {
+    [
+      SIMPLE_TEXT,
+    ].forEach(async (text) => {
+      const path = 'tmp2.txt';
+      await worker.writeText(path, SIMPLE_TEXT);
+      setTimeout(async () => {
+        const { data } = await worker.readText(path);
+        await worker.removeFile(path);
+        expect(data.toString()).to.be(text);
+      }, FS_WAIT);
+    });
+  }).timeout(TIMEOUT);
+});

tests/recognize.test.js

@@ -69,11 +69,9 @@ describe('recognize()', () => {
         const { data: { text } } = await worker.recognize(
           `${IMAGE_PATH}/${name}`,
           {
-            rectangles: [
-              {
-                top, left, width, height,
-              },
-            ],
+            rectangle: {
+              top, left, width, height,
+            },
           },
         );
         expect(text).to.be(ans);