tesseract.js - npm Package Compare versions

Comparing version 4.0.3 to 4.0.4

docs/local-installation.md

@@ -13,5 +13,5 @@ ## Local Installation
 Tesseract.recognize(image, langs, {
-  workerPath: 'https://unpkg.com/tesseract.js@v4.0.1/dist/worker.min.js',
+  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://unpkg.com/tesseract.js-core@v4.0.1/tesseract-core.wasm.js',
+  corePath: 'https://cdn.jsdelivr.net/npm/tesseract.js-core@v4.0.3',
 })
@@ -24,5 +24,5 @@ ```
 const worker = await createWorker({
-  workerPath: 'https://unpkg.com/tesseract.js@v4.0.1/dist/worker.min.js',
+  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://unpkg.com/tesseract.js-core@v4.0.1/tesseract-core.wasm.js',
+  corePath: 'https://cdn.jsdelivr.net/npm/tesseract.js-core@v4.0.3',
 });
@@ -32,3 +32,3 @@ ```
 ### workerPath
-A string specifying the location of the [worker.js](./dist/worker.min.js) file.
+A string specifying the location of the `worker.js` file.
 
@@ -39,4 +39,6 @@ ### langPath
 ### 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@v4.0.1/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'.
 
-Another WASM option is 'https://unpkg.com/tesseract.js-core@v4.0.1/tesseract-core.js' which is a script that loads 'https://unpkg.com/tesseract.js-core@v4.0.1/tesseract-core.wasm'. But it fails to fetch at this moment.
+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). 

package.json

 {
   "name": "tesseract.js",
-  "version": "4.0.3",
+  "version": "4.0.4",
   "description": "Pure Javascript Multilingual OCR",
@@ -11,3 +11,3 @@ "main": "src/index.js",
     "start": "node scripts/server.js",
-    "build": "rimraf dist && webpack --config scripts/webpack.config.prod.js && rollup -c scripts/rollup.esm.js",
+    "build": "rimraf dist && webpack --config scripts/webpack.config.prod.js && rollup -c scripts/rollup.esm.mjs",
     "profile:tesseract": "webpack-bundle-analyzer dist/tesseract-stats.json",
@@ -39,38 +39,38 @@ "profile:worker": "webpack-bundle-analyzer dist/worker-stats.json",
   "devDependencies": {
-    "@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",
+    "@babel/core": "^7.21.4",
+    "@babel/eslint-parser": "^7.21.3",
+    "@babel/preset-env": "^7.21.4",
+    "@rollup/plugin-commonjs": "^24.1.0",
+    "acorn": "^8.8.2",
+    "babel-loader": "^9.1.2",
     "buffer": "^6.0.3",
     "cors": "^2.8.5",
-    "eslint": "^7.2.0",
-    "eslint-config-airbnb-base": "^14.2.0",
-    "eslint-plugin-import": "^2.22.1",
+    "eslint": "^7.32.0",
+    "eslint-config-airbnb-base": "^14.2.1",
+    "eslint-plugin-import": "^2.27.5",
     "expect.js": "^0.3.1",
-    "express": "^4.17.1",
-    "mocha": "^10.0.0",
+    "express": "^4.18.2",
+    "mocha": "^10.2.0",
     "mocha-headless-chrome": "^4.0.0",
     "npm-run-all": "^4.1.5",
     "nyc": "^15.1.0",
-    "rimraf": "^2.7.1",
-    "rollup": "^2.79.0",
-    "wait-on": "^3.3.0",
-    "webpack": "^5.74.0",
-    "webpack-bundle-analyzer": "^4.6.0",
-    "webpack-cli": "^4.10.0",
-    "webpack-dev-middleware": "^5.3.3"
+    "rimraf": "^5.0.0",
+    "rollup": "^3.20.7",
+    "wait-on": "^7.0.1",
+    "webpack": "^5.79.0",
+    "webpack-bundle-analyzer": "^4.8.0",
+    "webpack-cli": "^5.0.1",
+    "webpack-dev-middleware": "^6.0.2"
   },
   "dependencies": {
-    "babel-eslint": "^10.1.0",
     "bmp-js": "^0.1.0",
-    "file-type": "^12.4.1",
-    "idb-keyval": "^3.2.0",
-    "is-electron": "^2.2.0",
+    "file-type": "^12.4.2",
+    "idb-keyval": "^6.2.0",
+    "is-electron": "^2.2.2",
     "is-url": "^1.2.4",
-    "node-fetch": "^2.6.0",
-    "opencollective-postinstall": "^2.0.2",
+    "node-fetch": "^2.6.9",
+    "opencollective-postinstall": "^2.0.3",
     "regenerator-runtime": "^0.13.3",
     "resolve-url": "^0.2.1",
-    "tesseract.js-core": "^4.0.3",
+    "tesseract.js-core": "^4.0.4",
     "wasm-feature-detect": "^1.2.11",
@@ -77,0 +77,0 @@ "zlibjs": "^0.3.1"

README.md

@@ -105,3 +105,3 @@ <p align="center">
 <!-- v4 -->
-<script src='https://unpkg.com/tesseract.js@4.0.2/dist/tesseract.min.js'></script>
+<script src='https://cdn.jsdelivr.net/npm/tesseract.js@4/dist/tesseract.min.js'></script>
 ```
@@ -108,0 +108,0 @@ After including the script the `Tesseract` variable will be globally available.

scripts/webpack.config.dev.js

@@ -11,2 +11,3 @@ const path = require('path');
   mode: 'development',
+  devtool: 'source-map',
   entry,
@@ -13,0 +14,0 @@ output: {

src/worker-script/browser/getCore.js

@@ -9,18 +9,30 @@ const { simd } = require('wasm-feature-detect');
     // 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${dependencies['tesseract.js-core'].substring(1)}`;
+
+    // If a user specifies a specific JavaScript file, load that file.
+    // Otherwise, assume a directory has been provided, and load either
+    // tesseract-core.wasm.js or tesseract-core-simd.wasm.js depending
+    // on whether this device has SIMD support.
+    let corePathImportFile;
+    if (corePathImport.slice(-2) === 'js') {
+      corePathImportFile = corePathImport;
+    } else {
       const simdSupport = await simd();
       if (simdSupport) {
-        corePathImport = `https://unpkg.com/tesseract.js-core@v${dependencies['tesseract.js-core'].substring(1)}/tesseract-core-simd.wasm.js`;
+        corePathImportFile = `${corePathImport.replace(/\/$/, '')}/tesseract-core-simd.wasm.js`;
       } else {
-        corePathImport = `https://unpkg.com/tesseract.js-core@v${dependencies['tesseract.js-core'].substring(1)}/tesseract-core.wasm.js`;
+        corePathImportFile = `${corePathImport.replace(/\/$/, '')}/tesseract-core.wasm.js`;
       }
     }
 
-    global.importScripts(corePathImport);
+    // Create a module named `global.TesseractCore`
+    global.importScripts(corePathImportFile);
 
-    if (typeof global.TesseractCoreWASM !== 'undefined' && typeof WebAssembly === 'object') {
+    // Tesseract.js-core versions through 4.0.3 create a module named `global.TesseractCoreWASM`,
+    // so we account for that here to preserve backwards compatibility.
+    // This part can be removed when Tesseract.js-core v4.0.3 becomes incompatible for other reasons
+    if (typeof global.TesseractCore === 'undefined' && typeof global.TesseractCoreWASM !== 'undefined' && typeof WebAssembly === 'object') {
       global.TesseractCore = global.TesseractCoreWASM;
-    } else {
+    } else if (typeof global.TesseractCore === 'undefined') {
       throw Error('Failed to load TesseractCore');
@@ -27,0 +39,0 @@ }

src/worker-script/index.js

@@ -309,4 +309,8 @@ /**
       api.FindLines();
-      const rotateRadiansCalc = api.GetAngle();
 
+      // The function GetAngle will be replaced with GetGradient in 4.0.4,
+      // but for now we want to maintain compatibility.
+      // We can switch to only using GetGradient in v5.
+      const rotateRadiansCalc = api.GetGradient ? api.GetGradient() : api.GetAngle();
+
       // Restore user-provided PSM setting
@@ -313,0 +317,0 @@ if (psmEdit) {

src/worker/browser/defaultOptions.js

@@ -12,3 +12,3 @@ const resolveURL = require('resolve-url');
     ? resolveURL(`/dist/worker.dev.js?nocache=${Math.random().toString(36).slice(3)}`)
-    : `https://unpkg.com/tesseract.js@v${version}/dist/worker.min.js`,
+    : `https://cdn.jsdelivr.net/npm/tesseract.js@v${version}/dist/worker.min.js`,
   /*
@@ -15,0 +15,0 @@ * If browser doesn't support WebAssembly,

No alert changes

Improved metrics

Dependency count

12

decreased by-7.69%

Lines of code

3391

increased by1.8%

Worsened metrics

Total package byte prevSize

27357814

decreased by-25.69%

Dev dependency count

24

increased by4.35%

Dependency changes

• + Addedidb-keyval@6.2.1(transitive)

• - Removedbabel-eslint@^10.1.0

• - Removed@babel/code-frame@7.24.6(transitive)

• - Removed@babel/generator@7.24.6(transitive)

• - Removed@babel/helper-environment-visitor@7.24.6(transitive)

• - Removed@babel/helper-function-name@7.24.6(transitive)

• - Removed@babel/helper-hoist-variables@7.24.6(transitive)

• - Removed@babel/helper-split-export-declaration@7.24.6(transitive)

• - Removed@babel/helper-string-parser@7.24.6(transitive)

• - Removed@babel/helper-validator-identifier@7.24.6(transitive)

• - Removed@babel/highlight@7.24.6(transitive)

• - Removed@babel/parser@7.24.6(transitive)

• - Removed@babel/template@7.24.6(transitive)

• - Removed@babel/traverse@7.24.6(transitive)

• - Removed@babel/types@7.24.6(transitive)

• - Removed@eslint-community/eslint-utils@4.4.0(transitive)

• - Removed@eslint-community/regexpp@4.10.0(transitive)

• - Removed@eslint/eslintrc@3.1.0(transitive)

• - Removed@eslint/js@9.3.0(transitive)

• - Removed@humanwhocodes/config-array@0.13.0(transitive)

• - Removed@humanwhocodes/module-importer@1.0.1(transitive)

• - Removed@humanwhocodes/object-schema@2.0.3(transitive)

• - Removed@humanwhocodes/retry@0.3.0(transitive)

• - Removed@jridgewell/gen-mapping@0.3.5(transitive)

• - Removed@jridgewell/resolve-uri@3.1.2(transitive)

• - Removed@jridgewell/set-array@1.2.1(transitive)

• - Removed@jridgewell/sourcemap-codec@1.4.15(transitive)

• - Removed@jridgewell/trace-mapping@0.3.25(transitive)

• - Removed@nodelib/fs.scandir@2.1.5(transitive)

• - Removed@nodelib/fs.stat@2.0.5(transitive)

• - Removed@nodelib/fs.walk@1.2.8(transitive)

• - Removedacorn@8.11.3(transitive)

• - Removedacorn-jsx@5.3.2(transitive)

• - Removedajv@6.12.6(transitive)

• - Removedansi-regex@5.0.1(transitive)

• - Removedansi-styles@3.2.14.3.0(transitive)

• - Removedargparse@2.0.1(transitive)

• - Removedbabel-eslint@10.1.0(transitive)

• - Removedbalanced-match@1.0.2(transitive)

• - Removedbrace-expansion@1.1.11(transitive)

• - Removedcallsites@3.1.0(transitive)

• - Removedchalk@2.4.24.1.2(transitive)

• - Removedcolor-convert@1.9.32.0.1(transitive)

• - Removedcolor-name@1.1.31.1.4(transitive)

• - Removedconcat-map@0.0.1(transitive)

• - Removedcross-spawn@7.0.3(transitive)

• - Removeddebug@4.3.5(transitive)

• - Removeddeep-is@0.1.4(transitive)

• - Removedescape-string-regexp@1.0.54.0.0(transitive)

• - Removedeslint@9.3.0(transitive)

• - Removedeslint-scope@8.0.1(transitive)

• - Removedeslint-visitor-keys@1.3.03.4.34.0.0(transitive)

• - Removedespree@10.0.1(transitive)

• - Removedesquery@1.5.0(transitive)

• - Removedesrecurse@4.3.0(transitive)

• - Removedestraverse@5.3.0(transitive)

• - Removedesutils@2.0.3(transitive)

• - Removedfast-deep-equal@3.1.3(transitive)

• - Removedfast-json-stable-stringify@2.1.0(transitive)

• - Removedfast-levenshtein@2.0.6(transitive)

• - Removedfastq@1.17.1(transitive)

• - Removedfile-entry-cache@8.0.0(transitive)

• - Removedfind-up@5.0.0(transitive)

• - Removedflat-cache@4.0.1(transitive)

• - Removedflatted@3.3.1(transitive)

• - Removedfunction-bind@1.1.2(transitive)

• - Removedglob-parent@6.0.2(transitive)

• - Removedglobals@11.12.014.0.0(transitive)

• - Removedhas-flag@3.0.04.0.0(transitive)

• - Removedhasown@2.0.2(transitive)

• - Removedidb-keyval@3.2.0(transitive)

• - Removedignore@5.3.1(transitive)

• - Removedimport-fresh@3.3.0(transitive)

• - Removedimurmurhash@0.1.4(transitive)

• - Removedis-core-module@2.13.1(transitive)

• - Removedis-extglob@2.1.1(transitive)

• - Removedis-glob@4.0.3(transitive)

• - Removedis-path-inside@3.0.3(transitive)

• - Removedisexe@2.0.0(transitive)

• - Removedjs-tokens@4.0.0(transitive)

• - Removedjs-yaml@4.1.0(transitive)

• - Removedjsesc@2.5.2(transitive)

• - Removedjson-buffer@3.0.1(transitive)

• - Removedjson-schema-traverse@0.4.1(transitive)

• - Removedjson-stable-stringify-without-jsonify@1.0.1(transitive)

• - Removedkeyv@4.5.4(transitive)

• - Removedlevn@0.4.1(transitive)

• - Removedlocate-path@6.0.0(transitive)

• - Removedlodash.merge@4.6.2(transitive)

• - Removedminimatch@3.1.2(transitive)

• - Removedms@2.1.2(transitive)

• - Removednatural-compare@1.4.0(transitive)

• - Removedoptionator@0.9.4(transitive)

• - Removedp-limit@3.1.0(transitive)

• - Removedp-locate@5.0.0(transitive)

• - Removedparent-module@1.0.1(transitive)

• - Removedpath-exists@4.0.0(transitive)

• - Removedpath-key@3.1.1(transitive)

• - Removedpath-parse@1.0.7(transitive)

• - Removedpicocolors@1.0.1(transitive)

• - Removedprelude-ls@1.2.1(transitive)

• - Removedpunycode@2.3.1(transitive)

• - Removedqueue-microtask@1.2.3(transitive)

• - Removedresolve@1.22.8(transitive)

• - Removedresolve-from@4.0.0(transitive)

• - Removedreusify@1.0.4(transitive)

• - Removedrun-parallel@1.2.0(transitive)

• - Removedshebang-command@2.0.0(transitive)

• - Removedshebang-regex@3.0.0(transitive)

• - Removedstrip-ansi@6.0.1(transitive)

• - Removedstrip-json-comments@3.1.1(transitive)

• - Removedsupports-color@5.5.07.2.0(transitive)

• - Removedsupports-preserve-symlinks-flag@1.0.0(transitive)

• - Removedtext-table@0.2.0(transitive)

• - Removedto-fast-properties@2.0.0(transitive)

• - Removedtype-check@0.4.0(transitive)

• - Removeduri-js@4.4.1(transitive)

• - Removedwhich@2.0.2(transitive)

• - Removedword-wrap@1.2.5(transitive)

• - Removedyocto-queue@0.1.0(transitive)

• Updatedfile-type@^12.4.2

• Updatedidb-keyval@^6.2.0

• Updatedis-electron@^2.2.2

• Updatednode-fetch@^2.6.9

• Updatedopencollective-postinstall@^2.0.3

• Updatedtesseract.js-core@^4.0.4