Update to v5 (#830)

.gitignore

@@ -1,8 +1,8 @@
 .DS_Store
 node_modules/*
 yarn.lock
-tesseract.dev.js
-worker.dev.js
+tesseract.min.js
+worker.min.js
 *.traineddata
 *.traineddata.gz
 .nyc_output

README.md

@@ -31,82 +31,32 @@ Video Real-time Recognition
 
 
 Tesseract.js wraps a [webassembly port](https://github.com/naptha/tesseract.js-core) of the [Tesseract](https://github.com/tesseract-ocr/tesseract) OCR 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/).
+It works in the browser using [webpack](https://webpack.js.org/), esm, 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:
 
-```javascript
-import Tesseract from 'tesseract.js';
-
-Tesseract.recognize(
-  'https://tesseract.projectnaptha.com/img/eng_bw.png',
-  'eng',
-  { logger: m => console.log(m) }
-).then(({ data: { text } }) => {
-  console.log(text);
-})
-```
-
-Or using workers (recommended for production use):
-
 ```javascript
 import { createWorker } from 'tesseract.js';
 
-const worker = await createWorker({
-  logger: m => console.log(m)
-});
-
 (async () => {
-  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);
+  const worker = await createWorker('eng');
+  const data = await worker.recognize('https://tesseract.projectnaptha.com/img/eng_bw.png');
+  console.log(data.text);
   await worker.terminate();
 })();
 ```
+When recognizing multiple images, users should create a worker once, run `worker.recognize` for each image, and then run `worker.terminate()` once at the end (rather than running the above snippet for every image). 
 
-For a basic overview of the functions, including the pros/cons of different approaches, see the [intro](./docs/intro.md).  [Check out the docs](#documentation) for a full explanation of the API.
-
-## Major changes in v4
-Version 4 includes many new features and bug fixes--see [this issue](https://github.com/naptha/tesseract.js/issues/662) for a full list.  Several highlights are below. 
-
-- Added rotation preprocessing options (including auto-rotate) for significantly better accuracy
-- Processed images (rotated, grayscale, binary) can now be retrieved
-- Improved support for parallel processing (schedulers)
-- Breaking changes:
-  - `createWorker` is now async
-  - `getPDF` function replaced by `pdf` recognize option
-
-## 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
-<!-- v4 -->
-<script src='https://cdn.jsdelivr.net/npm/tesseract.js@4/dist/tesseract.min.js'></script>
+<!-- v5 -->
+<script src='https://cdn.jsdelivr.net/npm/tesseract.js@5/dist/tesseract.min.js'></script>
 ```
-After including the script the `Tesseract` variable will be globally available.
+After including the script the `Tesseract` variable will be globally available and a worker can be created using `Tesseract.createWorker`.
 
+Alternatively, an ESM build (used with `import` syntax) can be found at `https://cdn.jsdelivr.net/npm/tesseract.js@5/dist/tesseract.esm.min.js`. 
 
 ### Node.js
 
@@ -122,16 +72,51 @@ npm install [email protected]
 yarn add [email protected]
 ```
 
-
 ## Documentation
 
-* [Intro](./docs/intro.md)
+* [Workers vs. Schedulers](./docs/workers_vs_schedulers.md)
 * [Examples](./docs/examples.md)
-* [Image Format](./docs/image-format.md)
+* [Supported Image Formats](./docs/image-format.md)
 * [API](./docs/api.md)
 * [Local Installation](./docs/local-installation.md)
 * [FAQ](./docs/faq.md)
 
+## Major changes in v5
+Version 5 changes are documented in [this issue](https://github.com/naptha/tesseract.js/issues/820).  Highlights are below.
+
+ - Significantly smaller files by default (54% smaller for English, 73% smaller for Chinese)
+    - This results in a ~50% reduction in runtime for first-time users (who do not have the files cached yet)
+ - Significantly lower memory usage
+ - Compatible with iOS 17 (using default settings)
+ - Breaking changes:
+    - `createWorker` arguments changed
+       - Setting non-default language and OEM now happens in `createWorker`
+          - E.g. `createWorker("chi_sim", 1)`
+    - `worker.initialize` and `worker.loadLanguage` functions now do nothing and can be deleted from code
+    - See [this issue](https://github.com/naptha/tesseract.js/issues/820) for full list
+
+## Major changes in v4
+Version 4 includes many new features and bug fixes--see [this issue](https://github.com/naptha/tesseract.js/issues/662) for a full list.  Several highlights are below. 
+
+- Added rotation preprocessing options (including auto-rotate) for significantly better accuracy
+- Processed images (rotated, grayscale, binary) can now be retrieved
+- Improved support for parallel processing (schedulers)
+- Breaking changes:
+  - `createWorker` is now async
+  - `getPDF` function replaced by `pdf` recognize option
+
+## 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
+
+
 ## Use tesseract.js the way you like!
 
 - Electron Version: https://github.com/Balearica/tesseract.js-electron
@@ -167,7 +152,7 @@ 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.
+It will automatically rebuild `tesseract.min.js` and `worker.min.js` when you change files in the **src** folder.
 
 ### Online Setup with a single Click
 

benchmarks/browser/auto-rotate-benchmark.html

@@ -1,7 +1,7 @@
 <html>
 
 <head>
-  <script src="/dist/tesseract.dev.js"></script>
+  <script src="/dist/tesseract.min.js"></script>
   <style>
     .column {
       float: left;
@@ -37,15 +37,10 @@
 
       const element = document.getElementById("imgRow");
 
-      const worker = await Tesseract.createWorker({
+      const worker = await Tesseract.createWorker('eng', 0, {
         // corePath: '/tesseract-core-simd.wasm.js',
-        workerPath: "/dist/worker.dev.js"
+        workerPath: "/dist/worker.min.js"
       });
-      await worker.loadLanguage('eng');
-      await worker.initialize('eng');
-
-      await worker.initialize();
-
 
       const fileArr = ["../data/meditations.jpg", "../data/tyger.jpg", "../data/testocr.png"];
       let timeTotal = 0;

benchmarks/browser/speed-benchmark.html

@@ -1,6 +1,6 @@
 <html>
   <head>
-    <script src="/dist/tesseract.dev.js"></script>
+    <script src="/dist/tesseract.min.js"></script>
   </head>
   <body>
     <textarea id="message">Working...</textarea>
@@ -13,20 +13,21 @@
       const { createWorker } = Tesseract;
 
       (async () => {
-        const worker = await createWorker({
-          // corePath: '/tesseract-core-simd.wasm.js',
-          workerPath: "/dist/worker.dev.js"
+        const worker = await createWorker("eng", 1, {
+          corePath: '../../node_modules/tesseract.js-core',
+          workerPath: "/dist/worker.min.js",
         });
-        await worker.loadLanguage('eng');
-        await worker.initialize('eng');
 
         // The performance.measureUserAgentSpecificMemory function only runs under specific circumstances for security reasons.
         // See: https://developer.mozilla.org/en-US/docs/Web/API/Performance/measureUserAgentSpecificMemory#security_requirements
         // Launching a server using `npm start` and accessing via localhost on the same system should meet these conditions.
         const debugMemory = true;
         if (debugMemory && crossOriginIsolated) {
-          console.log("Memory utilization after initialization:");
-          console.log(await performance.measureUserAgentSpecificMemory());
+          const memObj = await performance.measureUserAgentSpecificMemory();
+          const memMb = memObj.breakdown.map((x) => {if(x.attribution?.[0]?.scope == "DedicatedWorkerGlobalScope") return x.bytes}).reduce((a, b) => (a || 0) + (b || 0), 0) / 1e6;
+
+          console.log(`Worker memory utilization after initialization: ${memMb} MB`);
+
         } else {
           console.log("Unable to run `performance.measureUserAgentSpecificMemory`: not crossOriginIsolated.")
         }
@@ -45,8 +46,11 @@
         }
 
         if (debugMemory && crossOriginIsolated) {
-          console.log("Memory utilization after recognition:");
-          console.log(await performance.measureUserAgentSpecificMemory());
+          const memObj = await performance.measureUserAgentSpecificMemory();
+          const memMb = memObj.breakdown.map((x) => {if(x.attribution?.[0]?.scope == "DedicatedWorkerGlobalScope") return x.bytes}).reduce((a, b) => (a || 0) + (b || 0), 0) / 1e6;
+
+          console.log(`Worker memory utilization after recognition: ${memMb} MB`);
+
         }
 
         document.getElementById('message').innerHTML += "\nTotal runtime: " + timeTotal + "s";

benchmarks/node/speed-benchmark.js

@@ -4,8 +4,6 @@ const { createWorker } = require('../../');
 
 (async () => {
   const worker = await createWorker();
-  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) {