tesseract.js - npm Package Compare versions

Comparing version 2.0.0-alpha.10 to 2.0.0-alpha.11

docs/examples.md

@@ -21,4 +21,8 @@ # Tesseract.js Examples
   .recognize('https://tesseract.projectnaptha.com/img/eng_bw.png')
-  .then((result) => {
-    console.log(result);
+  .progress((p) => {
+    console.log('progress', p);
+  })
+  .then(({ text }) => {
+    console.log(text);
+    worker.terminate();
   });
@@ -40,4 +44,5 @@ ```
   })
-  .then((result) => {
-    console.log(result);
+  .then(({ text }) => {
+    console.log(text);
+    worker.terminate();
   });
@@ -62,4 +67,5 @@ ```
   })
-  .then((result) => {
-    console.log(result);
+  .then(({ text }) => {
+    console.log(text);
+    worker.terminate();
   });
@@ -90,4 +96,5 @@ ```
   })
-  .then((result) => {
-    console.log(result);
+  .then(({ text }) => {
+    console.log(text);
+    worker.terminate();
   });
@@ -117,4 +124,5 @@ ```
   })
-  .then((result) => {
-    console.log(result);
+  .then(({ text }) => {
+    console.log(text);
+    worker.terminate();
   });
@@ -144,4 +152,5 @@ ```
   })
-  .then((result) => {
-    console.log(result);
+  .then(({ text }) => {
+    console.log(text);
+    worker.terminate();
   });
@@ -171,5 +180,27 @@ ```
   })
-  .then((result) => {
-    console.log(result.files.pdf); // You can access pdf binary array here.
+  .then(({ files: { pdf } }) => {
+    console.log(Object.values(pdf)); // As pdf is an array-like object, you need to do a little convertion first.
+    worker.terminate();
   });
 ```
+
+### with preload language data
+
+```javascript
+const Tesseract = require('tesseract.js');
+
+const { TesseractWorker, utils: { loadLang } } = Tesseract;
+const worker = new TesseractWorker();
+
+loadLang({ langs: 'eng', langPath: worker.options.langPath })
+  .then(() => {
+    worker
+      .recognize('https://tesseract.projectnaptha.com/img/eng_bw.png')
+      .progress(p => console.log(p))
+      .then(({ text }) => {
+        console.log(text);
+        worker.terminate();
+      });
+  });
+
+```

docs/image-format.md

@@ -11,4 +11,7 @@ # Image Format
 - a path or URL to an accessible image
+- a base64 encoded image fits `data:image\/([a-zA-Z]*);base64,([^"]*)` regexp
 
 In Node.js, an image can be
 - a path to a local image
+- a Buffer storing binary image 
+- a base64 encoded image fits `data:image\/([a-zA-Z]*);base64,([^"]*)` regexp

docs/local-installation.md

@@ -13,3 +13,3 @@ ## Local Installation
 const worker = Tesseract.TesseractWorker({
-  workerPath: 'https://unpkg.com/tesseract.js@v2.0.0-alpha.10/dist/worker.min.js',
+  workerPath: 'https://unpkg.com/tesseract.js@v2.0.0-alpha.11/dist/worker.min.js',
   langPath: 'https://tessdata.projectnaptha.com/4.0.0',
@@ -16,0 +16,0 @@ corePath: 'https://unpkg.com/tesseract.js-core@v2.0.0-beta.10/tesseract-core.wasm.js',

docs/tesseract_lang_list.md

@@ -5,69 +5,105 @@ # Tesseract Languages
 
-| `lang`    | Language              | 
-|-----------|-----------------------| 
-| 'afr'     | Afrikaans             | 
-| 'ara'     | Arabic                | 
-| 'aze'     | Azerbaijani           | 
-| 'bel'     | Belarusian            | 
-| 'ben'     | Bengali               | 
-| 'bul'     | Bulgarian             | 
-| 'cat'     | Catalan               | 
-| 'ces'     | Czech                 | 
-| 'chi_sim' | Chinese               | 
-| 'chi_tra' | Traditional Chinese   | 
-| 'chr'     | Cherokee              | 
-| 'dan'     | Danish                | 
-| 'deu'     | German                | 
-| 'ell'     | Greek                 | 
-| 'eng'     | English                | 
-| 'enm'     | English (Old)         | 
-| 'epo'     | Esperanto             | 
-| 'epo_alt' | Esperanto alternative | 
-| 'equ'     | Math                  | 
-| 'est'     | Estonian              | 
-| 'eus'     | Basque                | 
-| 'fas'     |Persian (Farsi)        |
-| 'fin'     | Finnish               | 
-| 'fra'     | French                | 
-| 'frk'     | Frankish              | 
-| 'frm'     | French (Old)          | 
-| 'glg'     | Galician              | 
-| 'grc'     | Ancient Greek         | 
-| 'heb'     | Hebrew                | 
-| 'hin'     | Hindi                 | 
-| 'hrv'     | Croatian              | 
-| 'hun'     | Hungarian             | 
-| 'ind'     | Indonesian            | 
-| 'isl'     | Icelandic             | 
-| 'ita'     | Italian               | 
-| 'ita_old' | Italian (Old)         | 
-| 'jpn'     | Japanese              | 
-| 'kan'     | Kannada               | 
-| 'kor'     | Korean                | 
-| 'lav'     | Latvian               | 
-| 'lit'     | Lithuanian            | 
-| 'mal'     | Malayalam             | 
-| 'mkd'     | Macedonian            | 
-| 'mlt'     | Maltese               | 
-| 'msa'     | Malay                 | 
-| 'nld'     | Dutch                 | 
-| 'nor'     | Norwegian             | 
-| 'pol'     | Polish                | 
-| 'por'     | Portuguese            | 
-| 'ron'     | Romanian              | 
-| 'rus'     | Russian               | 
-| 'slk'     | Slovakian             | 
-| 'slv'     | Slovenian             | 
-| 'spa'     | Spanish               | 
-| 'spa_old' | Old Spanish           | 
-| 'sqi'     | Albanian              | 
-| 'srp'     | Serbian (Latin)       | 
-| 'swa'     | Swahili               | 
-| 'swe'     | Swedish               | 
-| 'tam'     | Tamil                 | 
-| 'tel'     | Telugu                | 
-| 'tgl'     | Tagalog               | 
-| 'tha'     | Thai                  | 
-| 'tur'     | Turkish               | 
-| 'ukr'     | Ukrainian             | 
-| 'vie'     | Vietnamese            | 
+Lang Code | Language | 4.0 traineddata
+:---------| :------- | :---------------
+afr | Afrikaans | [afr.traineddata.gz](https://tessdata.projectnaptha.com/4.00/afr.traineddata.gz)
+amh | Amharic | [amh.traineddata.gz](https://tessdata.projectnaptha.com/4.00/amh.traineddata.gz)
+ara | Arabic | [ara.traineddata.gz](https://tessdata.projectnaptha.com/4.00/ara.traineddata.gz)
+asm | Assamese | [asm.traineddata.gz](https://tessdata.projectnaptha.com/4.00/asm.traineddata.gz)
+aze | Azerbaijani | [aze.traineddata.gz](https://tessdata.projectnaptha.com/4.00/aze.traineddata.gz)
+aze_cyrl | Azerbaijani - Cyrillic | [aze_cyrl.traineddata.gz](https://tessdata.projectnaptha.com/4.00/aze_cyrl.traineddata.gz)
+bel | Belarusian | [bel.traineddata.gz](https://tessdata.projectnaptha.com/4.00/bel.traineddata.gz)
+ben | Bengali | [ben.traineddata.gz](https://tessdata.projectnaptha.com/4.00/ben.traineddata.gz)
+bod | Tibetan | [bod.traineddata.gz](https://tessdata.projectnaptha.com/4.00/bod.traineddata.gz)
+bos | Bosnian | [bos.traineddata.gz](https://tessdata.projectnaptha.com/4.00/bos.traineddata.gz)
+bul | Bulgarian | [bul.traineddata.gz](https://tessdata.projectnaptha.com/4.00/bul.traineddata.gz)
+cat | Catalan; Valencian | [cat.traineddata.gz](https://tessdata.projectnaptha.com/4.00/cat.traineddata.gz)
+ceb | Cebuano | [ceb.traineddata.gz](https://tessdata.projectnaptha.com/4.00/ceb.traineddata.gz)
+ces | Czech | [ces.traineddata.gz](https://tessdata.projectnaptha.com/4.00/ces.traineddata.gz)
+chi_sim | Chinese - Simplified | [chi_sim.traineddata.gz](https://tessdata.projectnaptha.com/4.00/chi_sim.traineddata.gz)
+chi_tra | Chinese - Traditional | [chi_tra.traineddata.gz](https://tessdata.projectnaptha.com/4.00/chi_tra.traineddata.gz)
+chr | Cherokee | [chr.traineddata.gz](https://tessdata.projectnaptha.com/4.00/chr.traineddata.gz)
+cym | Welsh | [cym.traineddata.gz](https://tessdata.projectnaptha.com/4.00/cym.traineddata.gz)
+dan | Danish | [dan.traineddata.gz](https://tessdata.projectnaptha.com/4.00/dan.traineddata.gz)
+deu | German | [deu.traineddata.gz](https://tessdata.projectnaptha.com/4.00/deu.traineddata.gz)
+dzo | Dzongkha | [dzo.traineddata.gz](https://tessdata.projectnaptha.com/4.00/dzo.traineddata.gz)
+ell | Greek, Modern (1453-) | [ell.traineddata.gz](https://tessdata.projectnaptha.com/4.00/ell.traineddata.gz)
+eng | English | [eng.traineddata.gz](https://tessdata.projectnaptha.com/4.00/eng.traineddata.gz)
+enm | English, Middle (1100-1500) | [enm.traineddata.gz](https://tessdata.projectnaptha.com/4.00/enm.traineddata.gz)
+epo | Esperanto | [epo.traineddata.gz](https://tessdata.projectnaptha.com/4.00/epo.traineddata.gz)
+est | Estonian | [est.traineddata.gz](https://tessdata.projectnaptha.com/4.00/est.traineddata.gz)
+eus | Basque | [eus.traineddata.gz](https://tessdata.projectnaptha.com/4.00/eus.traineddata.gz)
+fas | Persian | [fas.traineddata.gz](https://tessdata.projectnaptha.com/4.00/fas.traineddata.gz)
+fin | Finnish | [fin.traineddata.gz](https://tessdata.projectnaptha.com/4.00/fin.traineddata.gz)
+fra | French | [fra.traineddata.gz](https://tessdata.projectnaptha.com/4.00/fra.traineddata.gz)
+frk | Frankish | [frk.traineddata.gz](https://tessdata.projectnaptha.com/4.00/frk.traineddata.gz)
+frm | French, Middle (ca. 1400-1600) | [frm.traineddata.gz](https://tessdata.projectnaptha.com/4.00/frm.traineddata.gz)
+gle | Irish | [gle.traineddata.gz](https://tessdata.projectnaptha.com/4.00/gle.traineddata.gz)
+glg | Galician | [glg.traineddata.gz](https://tessdata.projectnaptha.com/4.00/glg.traineddata.gz)
+grc | Greek, Ancient (-1453) | [grc.traineddata.gz](https://tessdata.projectnaptha.com/4.00/grc.traineddata.gz)
+guj | Gujarati | [guj.traineddata.gz](https://tessdata.projectnaptha.com/4.00/guj.traineddata.gz)
+hat | Haitian; Haitian Creole | [hat.traineddata.gz](https://tessdata.projectnaptha.com/4.00/hat.traineddata.gz)
+heb | Hebrew | [heb.traineddata.gz](https://tessdata.projectnaptha.com/4.00/heb.traineddata.gz)
+hin | Hindi | [hin.traineddata.gz](https://tessdata.projectnaptha.com/4.00/hin.traineddata.gz)
+hrv | Croatian | [hrv.traineddata.gz](https://tessdata.projectnaptha.com/4.00/hrv.traineddata.gz)
+hun | Hungarian | [hun.traineddata.gz](https://tessdata.projectnaptha.com/4.00/hun.traineddata.gz)
+iku | Inuktitut | [iku.traineddata.gz](https://tessdata.projectnaptha.com/4.00/iku.traineddata.gz)
+ind | Indonesian | [ind.traineddata.gz](https://tessdata.projectnaptha.com/4.00/ind.traineddata.gz)
+isl | Icelandic | [isl.traineddata.gz](https://tessdata.projectnaptha.com/4.00/isl.traineddata.gz)
+ita | Italian | [ita.traineddata.gz](https://tessdata.projectnaptha.com/4.00/ita.traineddata.gz)
+ita_old | Italian - Old | [ita_old.traineddata.gz](https://tessdata.projectnaptha.com/4.00/ita_old.traineddata.gz)
+jav | Javanese | [jav.traineddata.gz](https://tessdata.projectnaptha.com/4.00/jav.traineddata.gz)
+jpn | Japanese | [jpn.traineddata.gz](https://tessdata.projectnaptha.com/4.00/jpn.traineddata.gz)
+kan | Kannada | [kan.traineddata.gz](https://tessdata.projectnaptha.com/4.00/kan.traineddata.gz)
+kat | Georgian | [kat.traineddata.gz](https://tessdata.projectnaptha.com/4.00/kat.traineddata.gz)
+kat_old | Georgian - Old | [kat_old.traineddata.gz](https://tessdata.projectnaptha.com/4.00/kat_old.traineddata.gz)
+kaz | Kazakh | [kaz.traineddata.gz](https://tessdata.projectnaptha.com/4.00/kaz.traineddata.gz)
+khm | Central Khmer | [khm.traineddata.gz](https://tessdata.projectnaptha.com/4.00/khm.traineddata.gz)
+kir | Kirghiz; Kyrgyz | [kir.traineddata.gz](https://tessdata.projectnaptha.com/4.00/kir.traineddata.gz)
+kor | Korean | [kor.traineddata.gz](https://tessdata.projectnaptha.com/4.00/kor.traineddata.gz)
+kur | Kurdish | [kur.traineddata.gz](https://tessdata.projectnaptha.com/4.00/kur.traineddata.gz)
+lao | Lao | [lao.traineddata.gz](https://tessdata.projectnaptha.com/4.00/lao.traineddata.gz)
+lat | Latin | [lat.traineddata.gz](https://tessdata.projectnaptha.com/4.00/lat.traineddata.gz)
+lav | Latvian | [lav.traineddata.gz](https://tessdata.projectnaptha.com/4.00/lav.traineddata.gz)
+lit | Lithuanian | [lit.traineddata.gz](https://tessdata.projectnaptha.com/4.00/lit.traineddata.gz)
+mal | Malayalam | [mal.traineddata.gz](https://tessdata.projectnaptha.com/4.00/mal.traineddata.gz)
+mar | Marathi | [mar.traineddata.gz](https://tessdata.projectnaptha.com/4.00/mar.traineddata.gz)
+mkd | Macedonian | [mkd.traineddata.gz](https://tessdata.projectnaptha.com/4.00/mkd.traineddata.gz)
+mlt | Maltese | [mlt.traineddata.gz](https://tessdata.projectnaptha.com/4.00/mlt.traineddata.gz)
+msa | Malay | [msa.traineddata.gz](https://tessdata.projectnaptha.com/4.00/msa.traineddata.gz)
+mya | Burmese | [mya.traineddata.gz](https://tessdata.projectnaptha.com/4.00/mya.traineddata.gz)
+nep | Nepali | [nep.traineddata.gz](https://tessdata.projectnaptha.com/4.00/nep.traineddata.gz)
+nld | Dutch; Flemish | [nld.traineddata.gz](https://tessdata.projectnaptha.com/4.00/nld.traineddata.gz)
+nor | Norwegian | [nor.traineddata.gz](https://tessdata.projectnaptha.com/4.00/nor.traineddata.gz)
+ori | Oriya | [ori.traineddata.gz](https://tessdata.projectnaptha.com/4.00/ori.traineddata.gz)
+pan | Panjabi; Punjabi | [pan.traineddata.gz](https://tessdata.projectnaptha.com/4.00/pan.traineddata.gz)
+pol | Polish | [pol.traineddata.gz](https://tessdata.projectnaptha.com/4.00/pol.traineddata.gz)
+por | Portuguese | [por.traineddata.gz](https://tessdata.projectnaptha.com/4.00/por.traineddata.gz)
+pus | Pushto; Pashto | [pus.traineddata.gz](https://tessdata.projectnaptha.com/4.00/pus.traineddata.gz)
+ron | Romanian; Moldavian; Moldovan | [ron.traineddata.gz](https://tessdata.projectnaptha.com/4.00/ron.traineddata.gz)
+rus | Russian | [rus.traineddata.gz](https://tessdata.projectnaptha.com/4.00/rus.traineddata.gz)
+san | Sanskrit | [san.traineddata.gz](https://tessdata.projectnaptha.com/4.00/san.traineddata.gz)
+sin | Sinhala; Sinhalese | [sin.traineddata.gz](https://tessdata.projectnaptha.com/4.00/sin.traineddata.gz)
+slk | Slovak | [slk.traineddata.gz](https://tessdata.projectnaptha.com/4.00/slk.traineddata.gz)
+slv | Slovenian | [slv.traineddata.gz](https://tessdata.projectnaptha.com/4.00/slv.traineddata.gz)
+spa | Spanish; Castilian | [spa.traineddata.gz](https://tessdata.projectnaptha.com/4.00/spa.traineddata.gz)
+spa_old | Spanish; Castilian - Old | [spa_old.traineddata.gz](https://tessdata.projectnaptha.com/4.00/spa_old.traineddata.gz)
+sqi | Albanian | [sqi.traineddata.gz](https://tessdata.projectnaptha.com/4.00/sqi.traineddata.gz)
+srp | Serbian | [srp.traineddata.gz](https://tessdata.projectnaptha.com/4.00/srp.traineddata.gz)
+srp_latn | Serbian - Latin | [srp_latn.traineddata.gz](https://tessdata.projectnaptha.com/4.00/srp_latn.traineddata.gz)
+swa | Swahili | [swa.traineddata.gz](https://tessdata.projectnaptha.com/4.00/swa.traineddata.gz)
+swe | Swedish | [swe.traineddata.gz](https://tessdata.projectnaptha.com/4.00/swe.traineddata.gz)
+syr | Syriac | [syr.traineddata.gz](https://tessdata.projectnaptha.com/4.00/syr.traineddata.gz)
+tam | Tamil | [tam.traineddata.gz](https://tessdata.projectnaptha.com/4.00/tam.traineddata.gz)
+tel | Telugu | [tel.traineddata.gz](https://tessdata.projectnaptha.com/4.00/tel.traineddata.gz)
+tgk | Tajik | [tgk.traineddata.gz](https://tessdata.projectnaptha.com/4.00/tgk.traineddata.gz)
+tgl | Tagalog | [tgl.traineddata.gz](https://tessdata.projectnaptha.com/4.00/tgl.traineddata.gz)
+tha | Thai | [tha.traineddata.gz](https://tessdata.projectnaptha.com/4.00/tha.traineddata.gz)
+tir | Tigrinya | [tir.traineddata.gz](https://tessdata.projectnaptha.com/4.00/tir.traineddata.gz)
+tur | Turkish | [tur.traineddata.gz](https://tessdata.projectnaptha.com/4.00/tur.traineddata.gz)
+uig | Uighur; Uyghur | [uig.traineddata.gz](https://tessdata.projectnaptha.com/4.00/uig.traineddata.gz)
+ukr | Ukrainian | [ukr.traineddata.gz](https://tessdata.projectnaptha.com/4.00/ukr.traineddata.gz)
+urd | Urdu | [urd.traineddata.gz](https://tessdata.projectnaptha.com/4.00/urd.traineddata.gz)
+uzb | Uzbek | [uzb.traineddata.gz](https://tessdata.projectnaptha.com/4.00/uzb.traineddata.gz)
+uzb_cyrl | Uzbek - Cyrillic | [uzb_cyrl.traineddata.gz](https://tessdata.projectnaptha.com/4.00/uzb_cyrl.traineddata.gz)
+vie | Vietnamese | [vie.traineddata.gz](https://tessdata.projectnaptha.com/4.00/vie.traineddata.gz)
+yid | Yiddish | [yid.traineddata.gz](https://tessdata.projectnaptha.com/4.00/yid.traineddata.gz)

docs/tesseract_parameters.md

@@ -16,3 +16,3 @@ Tesseract.js Parameters
   .recognize(image, 'eng', {
-    tessedit_ocr_engine_mode: OEM.TESSERACT_LSTM_COMBINED,
+    tessedit_ocr_engine_mode: OEM.LSTM_ONLY,
     tessedit_pageseg_mode: PSM.SINGLE_BLOCK,
@@ -25,3 +25,3 @@ })
 | ---- | ---- | ------------- | ----------- |
-| tessedit\_ocr\_engine\_mode | enum | OEM.TESSERACT\_LSTM\_COMBINED | Check [HERE](https://github.com/tesseract-ocr/tesseract/blob/4.0.0/src/ccstruct/publictypes.h#L268) for definition of each mode | 
+| tessedit\_ocr\_engine\_mode | enum | OEM.LSTM\_ONLY | Check [HERE](https://github.com/tesseract-ocr/tesseract/blob/4.0.0/src/ccstruct/publictypes.h#L268) for definition of each mode | 
 | tessedit\_pageseg\_mode | enum | PSM.SINGLE\_BLOCK | Check [HERE](https://github.com/tesseract-ocr/tesseract/blob/4.0.0/src/ccstruct/publictypes.h#L163) for definition of each mode |
@@ -28,0 +28,0 @@ | tessedit\_char\_whitelist | string | '' | setting white list characters makes the result only contains these characters, useful the content in image is limited |

package.json

 {
   "name": "tesseract.js",
-  "version": "2.0.0-alpha.10",
+  "version": "2.0.0-alpha.11",
   "description": "Pure Javascript Multilingual OCR",
   "main": "src/index.js",
+  "unpkg": "dist/tesseract.min.js",
+  "jsdelivr": "dist/tesseract.min.js",
   "scripts": {
@@ -7,0 +9,0 @@ "start": "node scripts/server.js",

README.md

@@ -1,14 +0,20 @@
-# [Tesseract.js](http://tesseract.projectnaptha.com/)
+<p align="center">
+<a href="https://tesseract.projectnaptha.com/"><img alt="Tesseract.js" src="https://tesseract.projectnaptha.com/img/logo_small.png"></a>
+</p>
 
+[![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)
+[![Maintenance](https://img.shields.io/badge/Maintained%3F-yes-green.svg)](https://github.com/naptha/tesseract.js/graphs/commit-activity)
 [![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
 [![Code Style](https://badgen.net/badge/code%20style/airbnb/ff5a5f?icon=airbnb)](https://github.com/airbnb/javascript)
-[![Maintenance](https://img.shields.io/badge/Maintained%3F-yes-green.svg)](https://github.com/naptha/tesseract.js/graphs/commit-activity)
-
-[![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)
 [![Downloads Total](https://img.shields.io/npm/dt/tesseract.js.svg)](https://www.npmjs.com/package/tesseract.js)
 [![Downloads Month](https://img.shields.io/npm/dm/tesseract.js.svg)](https://www.npmjs.com/package/tesseract.js)
 
-**Tesseract.js v2 is now available and under development in master branch, check [support/1.x](https://github.com/naptha/tesseract.js/tree/support/1.x) branch for v1.**
+<h3 align="center">
+  Version 2 is now available and under development in the master branch<br>
+  Check the <a href="https://github.com/naptha/tesseract.js/tree/support/1.x">support/1.x</a> branch for version 1
+</h3>
 
+<br>
+
 Tesseract.js is a javascript library that gets words in [almost any language](./docs/tesseract_lang_list.md) out of images. ([Demo](http://tesseract.projectnaptha.com/))
@@ -18,3 +24,5 @@
 
-Tesseract.js works with script tags, [webpack](https://webpack.js.org/), and [Node.js](https://nodejs.org/en/). [After you install it](#installation), using it is as simple as
+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/).
+After you [install it](#installation), using it is as simple as:
 
@@ -26,55 +34,49 @@ ```javascript
 worker.recognize(myImage)
-  .progress((p) => { console.log('progress', p);    })
-  .then((result) => { console.log('result', result); });
+  .progress(progress => {
+    console.log('progress', progress);
+  }).then(result => {
+    console.log('result', result);
+  });
 ```
 
-[Check out the docs](#docs) for a full treatment of the API.
+[Check out the docs](#docs) for a full explanation of the API.
 
-## Provenance
-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.
 
+## Major changes in v2
+- Upgrade to tesseract v4
+- Support multiple languages at the same time, eg: eng+chi_tra for English and Traditional Chinese
+- Supported image formats: png, jpg, bmp, pbm
 
-# Installation
-Tesseract.js works with a `<script>` tag via local copy or CDN, with webpack via `npm`, and on Node.js via `npm`. [Check out the docs](#docs) for a full treatment of the API.
 
-## CDN 
+## Installation
+Tesseract.js works with a `<script>` tag via local copy or CDN, with webpack via `npm` and on Node.js with `npm/yarn`.
 
-You can simply include Tesseract.js with a CDN like this:
+
+### CDN
 ```html
-<script src='https://unpkg.com/tesseract.js@v2.0.0-alpha.10/dist/tesseract.min.js'></script>
+<!-- v2 -->
+<script src='https://unpkg.com/tesseract.js@v2.0.0-alpha.11/dist/tesseract.min.js'></script>
+
+<!-- v1 -->
+<script src='https://unpkg.com/tesseract.js@1.0.19/src/index.js'></script>
 ```
+After including the script the `Tesseract` variable will be globally available.
 
-After including your scripts, the `Tesseract` variable will be defined globally!
 
-## npm
+### Node.js
 
-### 2.x
+**Tesseract.js currently requires Node.js v6.8.0 or higher**
 
-Major Changes
-
-- Upgrade to tesseract v4
-- Support multiple languages, ex: eng+chi_tra
-- Support image formats: png, jpg, bmp, pbm
-
 ```shell
-> yarn add tesseract.js@next
-```
-or
-```
-> npm install tesseract.js@next --save
-```
+# For v2
+npm install tesseract.js@next
+yarn add tesseract.js@next
 
-### 1.x
-
-```shell
-> yarn add tesseract.js
+# For v1
+npm install tesseract.js
+yarn add tesseract.js
 ```
-or
-```
-> npm install tesseract.js --save
-```
 
-> Note: Tesseract.js currently requires Node.js v6.8.0 or higher.
 
-# Documentation
+## Documentation
 
@@ -87,31 +89,27 @@ * [Examples](./docs/examples.md)
 
-# Contributing
 
-## Development
-To run a development copy of tesseract.js, first clone this repo.
-```shell
-> git clone https://github.com/naptha/tesseract.js.git
-```
+## Contributing
 
-Then, `cd tesseract.js && npm install && npm start`
+### Development
+To run a development copy of Tesseract.js do the following:
 ```shell
-> cd tesseract.js
-> npm install && npm start
+# First we clone the repository
+git clone https://github.com/naptha/tesseract.js.git
+cd tesseract.js
 
-  ... a bunch of npm stuff ...
+# Then we install the dependencies
+npm install
 
-  Starting up http-server, serving ./
-  Available on:
-    http://127.0.0.1:3000
-    http://[your ip]:3000
-
+# And finally we start the development server
+npm start
 ```
 
-Then open `http://localhost:3000/examples/browser/demo.html` in your favorite browser. The devServer automatically rebuilds `tesseract.dev.js` and `worker.min.js` when you change files in the src folder.
+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.min.js` when you change files in the src folder.
 
-## Building Static Files
-After you've cloned the repo and run `npm install` as described in the [Development Section](#development), you can build static library files in the dist folder with
-
+### Building Static Files
+To build the compiled static files just execute the following:
 ```shell
-> npm run build
+npm run build
 ```
+This will output the files into the `dist` directory.

scripts/test-helper.js

 global.expect = require('expect.js');
-global.fetch = require('node-fetch');
+global.fs = require('fs');
+global.path = require('path');
 global.Tesseract = require('../src');

src/browser/index.js

@@ -13,2 +13,3 @@ /**
 const axios = require('axios');
+const b64toU8Array = require('./b64toU8Array');
 const { defaultOptions } = require('../common/options');
@@ -42,2 +43,3 @@ const { version } = require('../../package.json');
  *   string: URL string, can be relative path
+ *   string: base64 image
  *   img HTMLElement: extract image source from src attribute
@@ -51,2 +53,7 @@ *   video HTMLElement: extract image source from poster attribute
   if (check.string(image)) {
+    // Base64 Image
+    if (/data:image\/([a-zA-Z]*);base64,([^"]*)/.test(image)) {
+      return Promise.resolve(b64toU8Array(image.split(',')[1]));
+    }
+    // Image URL
     return axios.get(resolveURL(image), {
@@ -104,3 +111,3 @@ responseType: 'arraybuffer',
   ...defaultOptions,
-  workerPath: process.env.TESS_ENV === 'development'
+  workerPath: (typeof process !== 'undefined' && process.env.TESS_ENV === 'development')
     ? resolveURL(`/dist/worker.dev.js?nocache=${Math.random().toString(36).slice(3)}`)
@@ -107,0 +114,0 @@ : `https://unpkg.com/tesseract.js@v${version}/dist/worker.min.js`,

src/browser/worker.js

@@ -13,2 +13,3 @@ /**
 const workerUtils = require('../common/workerUtils');
+const b64toU8Array = require('./b64toU8Array');
 
@@ -46,3 +47,3 @@ /*
   },
-  b64toU8Array: s => new Uint8Array(atob(s).split('').map(c => c.charCodeAt(0))),
+  b64toU8Array,
   writeFile: (path, data, type) => {
@@ -49,0 +50,0 @@ postMessage({

src/common/options.js

@@ -16,3 +16,3 @@ const { OEM, PSM } = require('./types');
   defaultParams: {
-    tessedit_ocr_engine_mode: OEM.TESSERACT_LSTM_COMBINED,
+    tessedit_ocr_engine_mode: OEM.LSTM_ONLY,
     tessedit_pageseg_mode: PSM.SINGLE_BLOCK,
@@ -19,0 +19,0 @@ tessedit_char_whiltelist: '',

src/common/TesseractWorker.js

@@ -11,3 +11,3 @@ /**
 const check = require('check-types');
-const resolveURL = process.browser ? require('resolve-url') : s => s;
+const resolveURL = (typeof window !== 'undefined' && typeof window.document !== 'undefined') ? require('resolve-url') : s => s;
 const adapter = require('../node');
@@ -14,0 +14,0 @@ const circularize = require('./circularize');

src/node/index.js

@@ -16,2 +16,3 @@ /**
 const path = require('path');
+const b64toU8Array = require('./b64toU8Array');
 const { defaultOptions } = require('../common/options');
@@ -29,2 +30,4 @@
  *   string: URL string or file path
+ *   string: base64 image
+ *   buffer: image buffer
  * @returns {array} binary image in array format
@@ -39,2 +42,11 @@ */
   }
+
+  if (/data:image\/([a-zA-Z]*);base64,([^"]*)/.test(image)) {
+    return Promise.resolve(b64toU8Array(image.split(',')[1]));
+  }
+
+  if (Buffer.isBuffer(image)) {
+    return Promise.resolve(image);
+  }
+
   return readFile(image);
@@ -41,0 +53,0 @@ };

src/node/worker.js

@@ -13,2 +13,3 @@ /**
 const workerUtils = require('../common/workerUtils');
+const b64toU8Array = require('./b64toU8Array');
 
@@ -37,3 +38,3 @@ let TesseractCore = null;
   },
-  b64toU8Array: s => Buffer.from(s, 'base64'),
+  b64toU8Array,
   writeFile: (path, data) => {
@@ -40,0 +41,0 @@ const fs = require('fs');

New alerts

License Policy Violation

License

This package is not allowed per your license policy. Review the package's license to ensure compliance.

Found 1 instance in 1 package

Fixed alerts

License Policy Violation

License

This package is not allowed per your license policy. Review the package's license to ensure compliance.

Found 1 instance in 1 package

Improved metrics

Total package byte prevSize

1983721

increased by12.1%

Number of package files

68

increased by13.33%

Lines of code

2329

increased by0.95%

Worsened metrics

Number of lines in readme file

113

decreased by-1.74%

Number of low supply chain risk alerts

4

increased by33.33%

No dependency changes