tesseract.js - npm Package Compare versions

Comparing version 2.0.0-alpha.11 to 2.0.0-alpha.12

docs/examples.md

@@ -8,3 +8,4 @@ # Tesseract.js Examples
 - Offline version: https://github.com/jeromewu/tesseract.js-offline
-- With Vue (similar with React/Angular): https://github.com/jeromewu/tesseract-vue-app
+- 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
@@ -127,3 +128,3 @@
 
-### with pdf output (^2.0.0-alpha.7)
+### with pdf output (^2.0.0-alpha.12)
 
@@ -143,3 +144,3 @@ In this example, pdf file will be downloaded in browser and write to file system in Node.js
     {
-      'tessedit_create_pdf': '1',
+      'tessjs_create_pdf': '1',
     }
@@ -169,5 +170,5 @@ )
     {
-      'tessedit_create_pdf': '1',
-      'pdf_auto_download': false, // disable auto download
-      'pdf_bin': true,            // add pdf file bin array in result
+      'tessjs_create_pdf': '1',
+      'tessjs_pdf_auto_download': false, // disable auto download
+      'tessjs_pdf_bin': true,            // add pdf file bin array in result
     }
@@ -204,1 +205,29 @@ )
 ```
+
+### with only part of the image (^2.0.0-alpha.12)
+
+```javascript
+import Tesseract from 'tesseract.js';
+
+const { TesseractWorker } = Tesseract;
+const worker = new TesseractWorker();
+
+worker
+  .recognize(
+    'https://tesseract.projectnaptha.com/img/eng_bw.png',
+    'eng',
+    {
+      tessjs_image_rectangle_left: 0,
+      tessjs_image_rectangle_top: 0,
+      tessjs_image_rectangle_width: 500,
+      tessjs_image_rectangle_height: 250,
+    }
+  )
+  .progress((p) => {
+    console.log('progress', p);
+  })
+  .then(({ text }) => {
+    console.log(text);
+    worker.terminate();
+  });
+```

docs/tesseract_parameters.md

@@ -27,12 +27,15 @@ Tesseract.js Parameters
 | tessedit\_char\_whitelist | string | '' | setting white list characters makes the result only contains these characters, useful the content in image is limited |
-| tessedit\_create\_pdf | string | '0' | only 2 values, '0' or '1', when the value is '1', tesseract.js generates a pdf output |
-| tessedit\_create\_hocr | string | '1' | only 2 values, '0' or '1', when the value is '1', tesseract.js includes hocr in the result |
-| tessedit\_create\_tsv | string | '1' | only 2 values, '0' or '1', when the value is '1', tesseract.js includes tsv in the result |
-| tessedit\_create\_box | string | '0' | only 2 values, '0' or '1', when the value is '1', tesseract.js includes box in the result |
-| tessedit\_create\_unlv | string | '0' | only 2 values, '0' or '1', when the value is '1', tesseract.js includes unlv in the result |
-| tessedit\_create\_osd | string | '0' | only 2 values, '0' or '1', when the value is '1', tesseract.js includes osd in the result |
-| pdf\_name | string | 'tesseract.js-ocr-result' | the name of the generated pdf file |
-| pdf\_title | string | 'Tesseract.js OCR Result' | the title of the generated pdf file |
-| pdf\_auto\_download | boolean | true | If the value is true, tesseract.js will automatic download/writeFile pdf file |
-| pdf\_bin | boolean | false | whether to include pdf binary array in the result object (result.files.pdf) |
-
+| tessjs\_create\_pdf | string | '0' | only 2 values, '0' or '1', when the value is '1', tesseract.js generates a pdf output |
+| 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 |
+| tessjs\_pdf\_name | string | 'tesseract.js-ocr-result' | the name of the generated pdf file |
+| tessjs\_pdf\_title | string | 'Tesseract.js OCR Result' | the title of the generated pdf file |
+| tessjs\_pdf\_auto\_download | boolean | true | If the value is true, tesseract.js will automatic download/writeFile pdf file |
+| tessjs\_pdf\_bin | boolean | false | whether to include pdf binary array in the result object (result.files.pdf) |
+| tessjs\_image\_rectangle\_left | number | 0 | The left of the sub-rectangle of the image. |
+| tessjs\_image\_rectangle\_top | number | 0 | The top of the sub-rectangle of the image. |
+| tessjs\_image\_rectangle\_width | number | -1 | The width of the sub-rectangle of the image, -1 means auto width detection |
+| tessjs\_image\_rectangle\_height | number | -1 | The height of the sub-rectangle of the image, -1 means auto height detection |

package.json

 {
   "name": "tesseract.js",
-  "version": "2.0.0-alpha.11",
+  "version": "2.0.0-alpha.12",
   "description": "Pure Javascript Multilingual OCR",
@@ -19,3 +19,4 @@ "main": "src/index.js",
     "test:browser:recognize": "npm run test:browser-tpl -- -f ./tests/recognize.test.html",
-    "lint": "eslint src"
+    "lint": "eslint src",
+    "postinstall": "opencollective-postinstall || true"
   },
@@ -58,2 +59,3 @@ "browser": {
     "node-fetch": "^2.3.0",
+    "opencollective-postinstall": "^2.0.2",
     "resolve-url": "^0.2.1",
@@ -70,3 +72,7 @@ "tesseract.js-core": "^2.0.0-beta.10",
   },
-  "homepage": "https://github.com/naptha/tesseract.js"
+  "homepage": "https://github.com/naptha/tesseract.js",
+  "collective": {
+    "type": "opencollective",
+    "url": "https://opencollective.com/tesseractjs"
+  }
 }

README.md

@@ -6,3 +6,3 @@ <p align="center">
 [![Build Status](https://travis-ci.org/naptha/tesseract.js.svg?branch=master)](https://travis-ci.org/naptha/tesseract.js)
-[![npm version](https://badge.fury.io/js/tesseract.js.svg)](https://badge.fury.io/js/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)
@@ -26,3 +26,3 @@ [![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
 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/).
+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:
@@ -49,2 +49,3 @@
 - Supported image formats: png, jpg, bmp, pbm
+- Support WebAssembly (fallback to ASM.js when browser doesn't support)
 
@@ -110,2 +111,6 @@
 
+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.
+
+[![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)
+
 ### Building Static Files
@@ -117,1 +122,31 @@ To build the compiled static files just execute the following:
 This will output the files into the `dist` directory.
+
+## Contributors
+
+### Code Contributors
+
+This project exists thanks to all the people who contribute. [[Contribute](CONTRIBUTING.md)].
+<a href="https://github.com/naptha/tesseract.js/graphs/contributors"><img src="https://opencollective.com/tesseractjs/contributors.svg?width=890&button=false" /></a>
+
+### Financial Contributors
+
+Become a financial contributor and help us sustain our community. [[Contribute](https://opencollective.com/tesseractjs/contribute)]
+
+#### Individuals
+
+<a href="https://opencollective.com/tesseractjs"><img src="https://opencollective.com/tesseractjs/individuals.svg?width=890"></a>
+
+#### Organizations
+
+Support this project with your organization. Your logo will show up here with a link to your website. [[Contribute](https://opencollective.com/tesseractjs/contribute)]
+
+<a href="https://opencollective.com/tesseractjs/organization/0/website"><img src="https://opencollective.com/tesseractjs/organization/0/avatar.svg"></a>
+<a href="https://opencollective.com/tesseractjs/organization/1/website"><img src="https://opencollective.com/tesseractjs/organization/1/avatar.svg"></a>
+<a href="https://opencollective.com/tesseractjs/organization/2/website"><img src="https://opencollective.com/tesseractjs/organization/2/avatar.svg"></a>
+<a href="https://opencollective.com/tesseractjs/organization/3/website"><img src="https://opencollective.com/tesseractjs/organization/3/avatar.svg"></a>
+<a href="https://opencollective.com/tesseractjs/organization/4/website"><img src="https://opencollective.com/tesseractjs/organization/4/avatar.svg"></a>
+<a href="https://opencollective.com/tesseractjs/organization/5/website"><img src="https://opencollective.com/tesseractjs/organization/5/avatar.svg"></a>
+<a href="https://opencollective.com/tesseractjs/organization/6/website"><img src="https://opencollective.com/tesseractjs/organization/6/avatar.svg"></a>
+<a href="https://opencollective.com/tesseractjs/organization/7/website"><img src="https://opencollective.com/tesseractjs/organization/7/avatar.svg"></a>
+<a href="https://opencollective.com/tesseractjs/organization/8/website"><img src="https://opencollective.com/tesseractjs/organization/8/avatar.svg"></a>
+<a href="https://opencollective.com/tesseractjs/organization/9/website"><img src="https://opencollective.com/tesseractjs/organization/9/avatar.svg"></a>

scripts/webpack.config.dev.js

@@ -23,2 +23,5 @@ const path = require('path');
   ],
+  devServer: {
+      allowedHosts: ['localhost', '.gitpod.io'],
+  },
 });
@@ -25,0 +28,0 @@

src/common/dump.js

@@ -46,7 +46,7 @@ /**
 module.exports = (TessModule, api, {
-  tessedit_create_hocr,
-  tessedit_create_tsv,
-  tessedit_create_box,
-  tessedit_create_unlv,
-  tessedit_create_osd,
+  tessjs_create_hocr,
+  tessjs_create_tsv,
+  tessjs_create_box,
+  tessjs_create_unlv,
+  tessjs_create_osd,
 }) => {
@@ -187,7 +187,7 @@ const ri = api.GetIterator();
     text: api.GetUTF8Text(),
-    hocr: tessedit_create_hocr === '1' ? deindent(api.GetHOCRText()) : null,
-    tsv: tessedit_create_tsv === '1' ? api.GetTSVText() : null,
-    box: tessedit_create_box === '1' ? api.GetBoxText() : null,
-    unlv: tessedit_create_unlv === '1' ? api.GetUNLVText() : null,
-    osd: tessedit_create_osd === '1' ? api.GetOsdText() : null,
+    hocr: tessjs_create_hocr === '1' ? deindent(api.GetHOCRText()) : null,
+    tsv: tessjs_create_tsv === '1' ? api.GetTSVText() : null,
+    box: tessjs_create_box === '1' ? api.GetBoxText() : null,
+    unlv: tessjs_create_unlv === '1' ? api.GetUNLVText() : null,
+    osd: tessjs_create_osd === '1' ? api.GetOsdText() : null,
     confidence: api.MeanTextConf(),
@@ -194,0 +194,0 @@ blocks,

src/common/options.js

@@ -19,14 +19,18 @@ const { OEM, PSM } = require('./types');
     tessedit_char_whiltelist: '',
-    tessedit_create_pdf: '0',
-    tessedit_create_hocr: '1',
-    tessedit_create_tsv: '1',
-    tessedit_create_box: '0',
-    tessedit_create_unlv: '0',
-    tessedit_create_osd: '0',
-    textonly_pdf: '0',
-    pdf_name: 'tesseract.js-ocr-result',
-    pdf_title: 'Tesseract.js OCR Result',
-    pdf_auto_download: true,
-    pdf_bin: false,
+    tessjs_create_pdf: '0',
+    tessjs_create_hocr: '1',
+    tessjs_create_tsv: '1',
+    tessjs_create_box: '0',
+    tessjs_create_unlv: '0',
+    tessjs_create_osd: '0',
+    tessjs_textonly_pdf: '0',
+    tessjs_pdf_name: 'tesseract.js-ocr-result',
+    tessjs_pdf_title: 'Tesseract.js OCR Result',
+    tessjs_pdf_auto_download: true,
+    tessjs_pdf_bin: false,
+    tessjs_image_rectangle_left: 0,
+    tessjs_image_rectangle_top: 0,
+    tessjs_image_rectangle_width: -1,
+    tessjs_image_rectangle_height: -1,
   },
 };

src/common/TesseractJob.js

@@ -51,10 +51,10 @@ /**
   then(resolve, reject) {
-    if (this._resolve.push) {
-      this._resolve.push(resolve);
-    } else {
-      resolve(this._resolve);
-    }
-
-    if (reject) this.catch(reject);
-    return this;
+    return new Promise((res, rej) => {
+      if (!this._resolve.push) {
+        res(this._result);
+      } else {
+        this._resolve.push(res);
+      }
+      this.catch(rej);
+    }).then(resolve, reject);
   }
@@ -61,0 +61,0 @@

src/common/workerUtils.js

@@ -35,4 +35,10 @@ /**
  */
-const setImage = (image) => {
+const setImage = (image, params) => {
   const {
+    tessjs_image_rectangle_left: left,
+    tessjs_image_rectangle_top: top,
+    tessjs_image_rectangle_width: width,
+    tessjs_image_rectangle_height: height,
+  } = params;
+  const {
     w, h, bytesPerPixel, data, pix,
@@ -52,3 +58,8 @@ } = readImage(TessModule, Array.from(image));
   }
-  api.SetRectangle(0, 0, w, h);
+  api.SetRectangle(
+    (left < 0) ? 0 : left,
+    (top < 0) ? 0 : top,
+    (width < 0) ? w : width,
+    (height < 0) ? h : height,
+  );
   return data === null ? pix : data;
@@ -79,3 +90,5 @@ };
   Object.keys(params).forEach((key) => {
-    api.SetVariable(key, params[key]);
+    if (!key.startsWith('tessjs')) {
+      api.SetVariable(key, params[key]);
+    }
   });
@@ -95,8 +108,8 @@ };
   const {
-    tessedit_create_pdf,
-    textonly_pdf,
-    pdf_name,
-    pdf_title,
-    pdf_auto_download,
-    pdf_bin,
+    tessjs_create_pdf,
+    tessjs_textonly_pdf,
+    tessjs_pdf_name,
+    tessjs_pdf_title,
+    tessjs_pdf_auto_download,
+    tessjs_pdf_bin,
   } = {
@@ -107,5 +120,5 @@ ...defaultParams,
 
-  if (tessedit_create_pdf === '1') {
-    const pdfRenderer = new TessModule.TessPDFRenderer(pdf_name, '/', textonly_pdf === '1');
-    pdfRenderer.BeginDocument(pdf_title);
+  if (tessjs_create_pdf === '1') {
+    const pdfRenderer = new TessModule.TessPDFRenderer(tessjs_pdf_name, '/', tessjs_textonly_pdf === '1');
+    pdfRenderer.BeginDocument(tessjs_pdf_title);
     pdfRenderer.AddImage(api);
@@ -115,10 +128,10 @@ pdfRenderer.EndDocument();
 
-    const data = TessModule.FS.readFile(`/${pdf_name}.pdf`);
+    const data = TessModule.FS.readFile(`/${tessjs_pdf_name}.pdf`);
 
-    if (pdf_bin) {
+    if (tessjs_pdf_bin) {
       files = { pdf: data, ...files };
     }
 
-    if (pdf_auto_download) {
-      adapter.writeFile(`${pdf_name}.pdf`, data, 'application/pdf');
+    if (tessjs_pdf_auto_download) {
+      adapter.writeFile(`${tessjs_pdf_name}.pdf`, data, 'application/pdf');
     }
@@ -214,20 +227,24 @@ }
         .then(() => {
-          const progressUpdate = (progress) => {
-            res.progress({ status: 'initializing api', progress });
-          };
-          const params = {
-            ...defaultParams,
-            ...customParams,
-          };
-          progressUpdate(0);
-          handleParams(langs, params);
-          progressUpdate(0.5);
-          const ptr = setImage(image);
-          progressUpdate(1);
-          api.Recognize(null);
-          const files = handleOutput(params);
-          const result = dump(TessModule, api, params);
-          api.End();
-          TessModule._free(ptr);
-          res.resolve({ files, ...result });
+          try {
+            const progressUpdate = (progress) => {
+              res.progress({ status: 'initializing api', progress });
+            };
+            const params = {
+              ...defaultParams,
+              ...customParams,
+            };
+            progressUpdate(0);
+            handleParams(langs, params);
+            progressUpdate(0.5);
+            const ptr = setImage(image, params);
+            progressUpdate(1);
+            api.Recognize(null);
+            const files = handleOutput(params);
+            const result = dump(TessModule, api, params);
+            api.End();
+            TessModule._free(ptr);
+            res.resolve({ files, ...result });
+          } catch (err) {
+            res.reject({ err });
+          }
         })
@@ -250,3 +267,3 @@ ))
 const handleDetect = ({
-  image, langs, options,
+  image, langs, options, params: customParams,
 }, res) => (
@@ -259,4 +276,8 @@ handleInit(options, res)
           api.SetPageSegMode(TessModule.PSM_OSD_ONLY);
+          const params = {
+            ...defaultParams,
+            ...customParams,
+          };
 
-          const ptr = setImage(image);
+          const ptr = setImage(image, params);
           const results = new TessModule.OSResults();
@@ -263,0 +284,0 @@

New alerts

Install scripts

Supply chain risk

Install scripts are run when the package is installed. The majority of malware in npm is hidden in install scripts.

Found 1 instance in 1 package

Improved metrics

Total package byte prevSize

2055901

increased by3.64%

Number of package files

70

increased by2.94%

Lines of code

2361

increased by1.37%

Number of lines in readme file

148

increased by30.97%

Worsened metrics

Dependency count

8

increased by14.29%

Number of high supply chain risk alerts

1

increased byInfinity%

Dependency changes

• + Addedopencollective-postinstall@^2.0.2

• + Addedopencollective-postinstall@2.0.3(transitive)