ocr-document-classification - npm Package Compare versions

Comparing version 1.0.3 to 1.0.4

dist/index.js

@@ -65,2 +65,14 @@ "use strict";
   const documentDictionary = { ...defaultDocumentDictionary, ...customDocumentDictionary };
+  let progress = 0;
+  const worker = await Tesseract.createWorker("nor+eng", 2, {
+    logger: (m) => {
+      if (m.status === "recognizing text") {
+        progress = m.progress * 0.8;
+        if (onProgress) onProgress(progress);
+      }
+    }
+  });
+  await worker.setParameters({
+    tessedit_pageseg_mode: Tesseract.PSM.AUTO_OSD
+  });
   const reader = new FileReader();
@@ -71,11 +83,5 @@ return new Promise((resolve, reject) => {
       try {
-        let progress = 0;
         if (onProgress) onProgress(progress);
-        const { data: { text } } = await Tesseract.recognize(imageDataUrl, "nor+eng", {
-          logger: (m) => {
-            if (m.status === "recognizing text") {
-              progress = m.progress * 0.8;
-              if (onProgress) onProgress(progress);
-            }
-          }
+        const { data: { text } } = await worker.recognize(imageDataUrl, {
+          rotateAuto: true
         });
@@ -82,0 +88,0 @@ const targetWords = Array.from(new Set(Object.values(documentDictionary).flat(2)));

package.json

 {
   "name": "ocr-document-classification",
-  "version": "1.0.3",
+  "version": "1.0.4",
   "description": "Document classification using tesseract.js and string-similarity-js.",
@@ -5,0 +5,0 @@ "main": "./dist/index.js",

README.md

@@ -44,14 +44,12 @@ # OCR Document Classification
 ```javascript
-const defaultDocumentDictionary: documentDictionary = {
-  'BEVIS PÅ FØRSTEGANGSTJENESTE': [
-    ['førstegangstjeneste', 'bevis', 'avtjent'],
-    ['attest', 'førstegangstjeneste'],
-  ],
-  POLITIATTEST: [
-    ['politiattest', 'politidistrikt'],
-    ['police certificate'],
-  ],
-  KOMPETANSEBEVIS: [['omfatter', 'opplæring', 'utdanningsprogram']],
-  LEGEERKLÆRING: [['legeerklæring', 'fødselsnummer']],
-};
+const defaultDocumentDictionary: documentDictionary  = {
+    BEVISPAFORSTEGANGSTJENESTE: [
+      ['førstegangstjeneste', 'bevis', 'avtjent'],
+      ['attest', 'førstegangstjeneste'],
+      ['fullført', 'førstegangstjeneste'],
+    ],
+    POLITIATTEST: [['politiattest', 'politidistrikt'], ['police certificate']],
+    KOMPETANSEBEVIS: [['omfatter', 'opplæring', 'utdanningsprogram']],
+    LEGEERKLERING: [['legeerklæring', 'fødselsnummer']],
+  }
 ```
@@ -58,0 +56,0 @@

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

12411

increased by2.42%

Lines of code

197

increased by6.49%

Worsened metrics

Number of lines in readme file

128

decreased by-1.54%

No dependency changes