Added SIMD-detection when corePath is manually specified per #735 (#745)

docs/local-installation.md

@@ -12,7 +12,7 @@ In Node.js environment, the only path you may want to customize is languages/lan
 Tesseract.recognize(image, langs, {
   workerPath: 'https://cdn.jsdelivr.net/npm/tesseract.js@v4.0.3/dist/worker.min.js',
   langPath: 'https://tessdata.projectnaptha.com/4.0.0',
-  corePath: 'https://cdn.jsdelivr.net/npm/tesseract.js-core@v4.0.3/tesseract-core.wasm.js',
+  corePath: 'https://cdn.jsdelivr.net/npm/tesseract.js-core@v4.0.3',
 })
 ```
 
@@ -22,7 +22,7 @@ Or
 const worker = await createWorker({
   workerPath: 'https://cdn.jsdelivr.net/npm/tesseract.js@v4.0.3/dist/worker.min.js',
   langPath: 'https://tessdata.projectnaptha.com/4.0.0',
-  corePath: 'https://cdn.jsdelivr.net/npm/tesseract.js-core@v4.0.3/tesseract-core.wasm.js',
+  corePath: 'https://cdn.jsdelivr.net/npm/tesseract.js-core@v4.0.3',
 });
 ```
 
@@ -33,4 +33,8 @@ A string specifying the location of the `worker.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://cdn.jsdelivr.net/npm/tesseract.js-core@v4.0.3/tesseract-core.wasm.js'.
+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/npm/tesseract.js-core@v4.0.3'.
+
+When `corePath` is a directory rather than specific `.js` file (e.g. `https://cdn.jsdelivr.net/npm/tesseract.js-core@v4.0.3`), Tesseract.js loads either `tesseract-core-simd.wasm.js` or `tesseract-core.wasm.js` depending on whether the users' device supports SIMD (see [https://webassembly.org/roadmap/](https://webassembly.org/roadmap/)).  Therefore, if self-hosting it is important that both these files are in the location you specify for `corePath`.  Having multiple files is necessary as the SIMD-enabled version is *significantly* faster (for the LSTM model [the default]), however is not yet supported on all devices. 
+
+When `corePath` is set to a specific `.js` file (e.g. `https://cdn.jsdelivr.net/npm/tesseract.js-core@v4.0.3/tesseract-core.wasm.js`), it will load that file regardless of whether the users' device supports SIMD or not.  This behavior exists to preserve backwards compatibility--specifying a directory that contains both files is strongly recommended.  Specifying a single file will either result in much slower performance (if `tesseract-core.wasm.js` is specified) or failure to run on certain devices (if `tesseract-core-simd.wasm.js` is specified). 

examples/browser/basic-efficient.html

@@ -12,7 +12,7 @@
       // every time the user uploads a new file.  
 
       const worker = await Tesseract.createWorker({
-          corePath: '../../node_modules/tesseract.js-core/tesseract-core.wasm.js',
+          corePath: '../../node_modules/tesseract.js-core',
           workerPath: "/dist/worker.dev.js",
           logger: function(m){console.log(m);}
         });

examples/browser/basic.html

@@ -13,7 +13,7 @@
 
       const recognize = async ({ target: { files }  }) => {
         const { data: { text } } = await Tesseract.recognize(files[0], 'eng', {
-          corePath: '../../node_modules/tesseract.js-core/tesseract-core.wasm.js',
+          corePath: '../../node_modules/tesseract.js-core',
           workerPath: "/dist/worker.dev.js",
           logger: m => console.log(m),
         });

examples/browser/demo.html

@@ -39,7 +39,7 @@ function progressUpdate(packet){
 
 async function recognizeFile(file) {
 	document.querySelector("#log").innerHTML = ''
-  const corePath = '../../node_modules/tesseract.js-core/tesseract-core.wasm.js';
+  const corePath = '../../node_modules/tesseract.js-core';
 
   const lang = document.querySelector('#langsel').value
   const data = await Tesseract.recognize(file, lang, {

examples/browser/download-pdf.html

@@ -11,7 +11,7 @@
     <script type="module">
       const { createWorker } = Tesseract;
       const worker = await createWorker({
-        corePath: '/node_modules/tesseract.js-core/tesseract-core.wasm.js',
+        corePath: '/node_modules/tesseract.js-core',
         workerPath: "/dist/worker.dev.js",
         logger: m => console.log(m),
       });

src/worker-script/browser/getCore.js

@@ -6,19 +6,27 @@ module.exports = async (corePath, res) => {
     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) {
+    // Otherwise, default to CDN
+    const corePathImport = corePath || `https://cdn.jsdelivr.net/npm/tesseract.js-core@v${dependencies['tesseract.js-core'].substring(1)}`;
+
+    // If a user specifies a specific JavaScript file, load that file.
+    // Otherwise, assume a directory has been provided, and load either
+    // tesseract-core.wasm.js or tesseract-core-simd.wasm.js depending
+    // on whether this device has SIMD support.
+    let corePathImportFile;
+    if (corePathImport.slice(-2) === 'js') {
+      corePathImportFile = corePathImport;
+    } else {
       const simdSupport = await simd();
       if (simdSupport) {
-        corePathImport = `https://cdn.jsdelivr.net/npm/tesseract.js-core@v${dependencies['tesseract.js-core'].substring(1)}/tesseract-core-simd.wasm.js`;
+        corePathImportFile = `${corePathImport.replace(/\/$/, '')}/tesseract-core-simd.wasm.js`;
       } else {
-        corePathImport = `https://cdn.jsdelivr.net/npm/tesseract.js-core@v${dependencies['tesseract.js-core'].substring(1)}/tesseract-core.wasm.js`;
+        corePathImportFile = `${corePathImport.replace(/\/$/, '')}/tesseract-core.wasm.js`;
       }
     }
 
     // Create a module named `global.TesseractCore`
-    global.importScripts(corePathImport);
+    global.importScripts(corePathImportFile);
 
     // Tesseract.js-core versions through 4.0.3 create a module named `global.TesseractCoreWASM`,
     // so we account for that here to preserve backwards compatibility.