Fix browser image reading issue

examples/file-input/basic.html

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

package-lock.json

@@ -2152,12 +2152,14 @@
         "balanced-match": {
           "version": "1.0.0",
           "bundled": true,
-          "dev": true
+          "dev": true,
+          "optional": true
         },
         "brace-expansion": {
           "version": "1.1.11",
           "bundled": true,
           "dev": true,
+          "optional": true,
           "requires": {
             "balanced-match": "^1.0.0",
             "concat-map": "0.0.1"
@@ -2172,17 +2174,20 @@
         "code-point-at": {
           "version": "1.1.0",
           "bundled": true,
-          "dev": true
+          "dev": true,
+          "optional": true
         },
         "concat-map": {
           "version": "0.0.1",
           "bundled": true,
-          "dev": true
+          "dev": true,
+          "optional": true
         },
         "console-control-strings": {
           "version": "1.1.0",
           "bundled": true,
-          "dev": true
+          "dev": true,
+          "optional": true
         },
         "core-util-is": {
           "version": "1.0.2",
@@ -2299,7 +2304,8 @@
         "inherits": {
           "version": "2.0.3",
           "bundled": true,
-          "dev": true
+          "dev": true,
+          "optional": true
         },
         "ini": {
           "version": "1.3.5",
@@ -2311,6 +2317,7 @@
           "version": "1.0.0",
           "bundled": true,
           "dev": true,
+          "optional": true,
           "requires": {
             "number-is-nan": "^1.0.0"
           }
@@ -2325,6 +2332,7 @@
           "version": "3.0.4",
           "bundled": true,
           "dev": true,
+          "optional": true,
           "requires": {
             "brace-expansion": "^1.1.7"
           }
@@ -2332,12 +2340,14 @@
         "minimist": {
           "version": "0.0.8",
           "bundled": true,
-          "dev": true
+          "dev": true,
+          "optional": true
         },
         "minipass": {
           "version": "2.2.4",
           "bundled": true,
           "dev": true,
+          "optional": true,
           "requires": {
             "safe-buffer": "^5.1.1",
             "yallist": "^3.0.0"
@@ -2356,6 +2366,7 @@
           "version": "0.5.1",
           "bundled": true,
           "dev": true,
+          "optional": true,
           "requires": {
             "minimist": "0.0.8"
           }
@@ -2436,7 +2447,8 @@
         "number-is-nan": {
           "version": "1.0.1",
           "bundled": true,
-          "dev": true
+          "dev": true,
+          "optional": true
         },
         "object-assign": {
           "version": "4.1.1",
@@ -2448,6 +2460,7 @@
           "version": "1.4.0",
           "bundled": true,
           "dev": true,
+          "optional": true,
           "requires": {
             "wrappy": "1"
           }
@@ -2569,6 +2582,7 @@
           "version": "1.0.2",
           "bundled": true,
           "dev": true,
+          "optional": true,
           "requires": {
             "code-point-at": "^1.0.0",
             "is-fullwidth-code-point": "^1.0.0",
@@ -4470,8 +4484,7 @@
     "resolve-url": {
       "version": "0.2.1",
       "resolved": "https://registry.npmjs.org/resolve-url/-/resolve-url-0.2.1.tgz",
-      "integrity": "sha1-LGN/53yJOv0qZj/iGqkIAGjiBSo=",
-      "dev": true
+      "integrity": "sha1-LGN/53yJOv0qZj/iGqkIAGjiBSo="
     },
     "restore-cursor": {
       "version": "2.0.0",

package.json

@@ -32,6 +32,7 @@
     "check-types": "^7.4.0",
     "is-url": "1.2.2",
     "node-fetch": "^1.7.3",
+    "resolve-url": "^0.2.1",
     "tesseract.js-core": "^2.0.0-beta.5",
     "tesseract.js-utils": "^1.0.0-beta.1"
   },

src/browser/index.js

@@ -1,27 +1,34 @@
-const isURL = require('is-url');
+const check = require('check-types');
+const resolveURL = require('resolve-url');
+const { version } = require('../../package.json');
 
 const defaultOptions = {
-  // workerPath: 'https://cdn.jsdelivr.net/gh/naptha/tesseract.js@0.2.0/dist/worker.js',
   corePath: `https://cdn.jsdelivr.net/gh/naptha/tesseract.js-core@v2.0.0-beta.5/tesseract-core${typeof WebAssembly === 'object' ? '' : '.asm'}.js`,
-  langPath: 'https://cdn.jsdelivr.net/gh/naptha/tessdata@gh-pages/4.0.0/',
+  langPath: 'https://cdn.jsdelivr.net/gh/naptha/tessdata@gh-pages/4.0.0',
 };
 
 if (process.env.NODE_ENV === 'development') {
   console.debug('Using Development Configuration');
-  // eslint-disable-next-line
-  const { protocol, host } = location;
-  defaultOptions.workerPath = `${protocol}//${host}/dist/worker.dev.js?nocache=${Math.random().toString(36).slice(3)}`;
+  defaultOptions.workerPath = resolveURL(`/dist/worker.dev.js?nocache=${Math.random().toString(36).slice(3)}`);
 } else {
-  const { version } = require('../../package.json');
-  defaultOptions.workerPath = `https://cdn.jsdelivr.net/gh/naptha/tesseract.js@${version}/dist/worker.js`;
+  defaultOptions.workerPath = `https://cdn.jsdelivr.net/gh/naptha/tesseract.js@${version}/dist/worker.min.js`;
 }
 
-const loadImage = (imageURI) => {
-  if (isURL(imageURI)) {
-    return fetch(imageURI)
+const loadImage = (image) => {
+  if (check.string(image)) {
+    return fetch(resolveURL(image))
       .then(resp => resp.arrayBuffer());
   }
-  return new Promise();
+  if (check.instance(image, File)) {
+    return new Promise((res) => {
+      const fileReader = new FileReader();
+      fileReader.onload = () => {
+        res(fileReader.result);
+      };
+      fileReader.readAsArrayBuffer(image);
+    });
+  }
+  return Promise.reject();
 };
 
 exports.defaultOptions = defaultOptions;