tesseract.js - npm Package Compare versions

Comparing version 2.0.0-alpha.9 to 2.0.0-alpha.10

docs/faq.md

@@ -15,1 +15,27 @@ FAQ
 For tesseract.js v1, check [Training Tesseract 3.03–3.05](https://github.com/tesseract-ocr/tesseract/wiki/Training-Tesseract-3.03%E2%80%933.05)
+
+## How can I get HOCR, TSV, Box, UNLV, OSD?
+
+Starting from 2.0.0-alpha.10, you can get all these information in the final result.
+
+```javascript
+import Tesseract from 'tesseract.js';
+
+const { TesseractWorker } = Tesseract;
+const worker = new TesseractWorker();
+
+worker
+  .recognize('https://tesseract.projectnaptha.com/img/eng_bw.png', 'eng', {
+    tessedit_create_box: '1',
+    tessedit_create_unlv: '1',
+    tessedit_create_osd: '1',
+  })
+  .then((result) => {
+    console.log(result.text);
+    console.log(result.hocr);
+    console.log(result.tsv);
+    console.log(result.box);
+    console.log(result.unlv);
+    console.log(result.osd);
+  });
+```

docs/local-installation.md

 ## Local Installation
 
-Check here for an example: https://github.com/jeromewu/tesseract.js-offline
+Check here for examples: https://github.com/naptha/tesseract.js/blob/master/docs/examples.md 
 
@@ -13,3 +13,3 @@ In browser environment, `tesseract.js` simply provides the API layer. Internally, it opens a WebWorker to handle requests. That worker itself loads code from the Emscripten-built `tesseract.js-core` which itself is hosted on a CDN. Then it dynamically loads language files hosted on another CDN.
 const worker = Tesseract.TesseractWorker({
-  workerPath: 'https://unpkg.com/tesseract.js@v2.0.0-alpha.8/dist/worker.min.js',
+  workerPath: 'https://unpkg.com/tesseract.js@v2.0.0-alpha.10/dist/worker.min.js',
   langPath: 'https://tessdata.projectnaptha.com/4.0.0',
@@ -27,4 +27,4 @@ corePath: 'https://unpkg.com/tesseract.js-core@v2.0.0-beta.10/tesseract-core.wasm.js',
 ### 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@v2.0.0-beta.8/tesseract-core.wasm.js' (fallback to tesseract-core.asm.js when WebAssembly is not available).
+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@v2.0.0-beta.10/tesseract-core.wasm.js' (fallback to tesseract-core.asm.js when WebAssembly is not available).
 
-Another WASM option is 'https://unpkg.com/tesseract.js-core@v2.0.0-beta.8/tesseract-core.js' which is a script that loads 'https://unpkg.com/tesseract.js-core@v2.0.0-beta.8/tesseract-core.wasm'. But it fails to fetch at this moment.
+Another WASM option is 'https://unpkg.com/tesseract.js-core@v2.0.0-beta.10/tesseract-core.js' which is a script that loads 'https://unpkg.com/tesseract.js-core@v2.0.0-beta.10/tesseract-core.wasm'. But it fails to fetch at this moment.

docs/tesseract_parameters.md

@@ -27,3 +27,8 @@ 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 will generate a pdf output |
+| 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 |
@@ -30,0 +35,0 @@ | pdf\_title | string | 'Tesseract.js OCR Result' | the title of the generated pdf file |

package.json

 {
   "name": "tesseract.js",
-  "version": "2.0.0-alpha.9",
+  "version": "2.0.0-alpha.10",
   "description": "Pure Javascript Multilingual OCR",
@@ -5,0 +5,0 @@ "main": "src/index.js",

README.md

@@ -42,3 +42,3 @@ # [Tesseract.js](http://tesseract.projectnaptha.com/)
 ```html
-<script src='https://unpkg.com/tesseract.js@v2.0.0-alpha.8/dist/tesseract.min.js'></script>
+<script src='https://unpkg.com/tesseract.js@v2.0.0-alpha.10/dist/tesseract.min.js'></script>
 ```
@@ -45,0 +45,0 @@

src/common/dump.js

@@ -45,3 +45,9 @@ /**
  */
-module.exports = (TessModule, api) => {
+module.exports = (TessModule, api, {
+  tessedit_create_hocr,
+  tessedit_create_tsv,
+  tessedit_create_box,
+  tessedit_create_unlv,
+  tessedit_create_osd,
+}) => {
   const ri = api.GetIterator();
@@ -181,3 +187,7 @@ const blocks = [];
     text: api.GetUTF8Text(),
-    html: deindent(api.GetHOCRText()),
+    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,
     confidence: api.MeanTextConf(),
@@ -184,0 +194,0 @@ blocks,

src/common/options.js

@@ -20,2 +20,7 @@ const { OEM, PSM } = require('./types');
     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',
@@ -22,0 +27,0 @@ pdf_name: 'tesseract.js-ocr-result',

src/common/workerUtils.js

@@ -70,10 +70,7 @@ /**
  */
-const handleParams = (langs, customParams) => {
+const handleParams = (langs, iParams) => {
   const {
     tessedit_ocr_engine_mode,
     ...params
-  } = {
-    ...defaultParams,
-    ...customParams,
-  };
+  } = iParams;
   api.Init(null, getLangsStr(langs), tessedit_ocr_engine_mode);
@@ -195,3 +192,3 @@ Object.keys(params).forEach((key) => {
 const handleRecognize = ({
-  image, langs, options, params,
+  image, langs, options, params: customParams,
 }, res) => (
@@ -216,2 +213,6 @@ handleInit(options, res)
           };
+          const params = {
+            ...defaultParams,
+            ...customParams,
+          };
           progressUpdate(0);
@@ -224,3 +225,3 @@ handleParams(langs, params);
           const files = handleOutput(params);
-          const result = dump(TessModule, api);
+          const result = dump(TessModule, api, params);
           api.End();
@@ -227,0 +228,0 @@ TessModule._free(ptr);

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

1769608

increased by0.23%

Lines of code

2307

increased by0.79%

No dependency changes