ocr-document-classification - npm Package Compare versions

Comparing version 1.0.9 to 1.0.10

dist/index.js

@@ -45,3 +45,6 @@ "use strict";
     targetWords.forEach((targetWord) => {
-      const similarity = (0, import_string_similarity_js.stringSimilarity)(docWord.toLowerCase(), targetWord.toLowerCase());
+      const similarity = (0, import_string_similarity_js.stringSimilarity)(
+        docWord.toLowerCase(),
+        targetWord.toLowerCase()
+      );
       if (similarity >= threshold) {
@@ -55,3 +58,3 @@ foundTargetWords.push(targetWord);
 var defaultDocumentDictionary = {
-  BEVISPAFORSTEGANGSTJENESTE: [
+  "BEVIS P\xC5 F\xD8RSTEGANGSTJENESTE": [
     ["f\xF8rstegangstjeneste", "bevis", "avtjent"],
@@ -63,6 +66,9 @@ ["attest", "f\xF8rstegangstjeneste"],
   KOMPETANSEBEVIS: [["omfatter", "oppl\xE6ring", "utdanningsprogram"]],
-  LEGEERKLERING: [["legeerkl\xE6ring", "f\xF8dselsnummer"]]
+  LEGEERKL\u00C6RING: [["legeerkl\xE6ring", "f\xF8dselsnummer"]]
 };
 async function classifyDocument(file, onProgress, customDocumentDictionary) {
-  const documentDictionary = { ...defaultDocumentDictionary, ...customDocumentDictionary };
+  const documentDictionary = {
+    ...defaultDocumentDictionary,
+    ...customDocumentDictionary
+  };
   let progress = 0;
@@ -86,10 +92,17 @@ const worker = await Tesseract.createWorker(["noreng"], 1, {
         if (onProgress) onProgress(progress);
-        const { data: { text } } = await worker.recognize(imageDataUrl, {
+        const {
+          data: { text }
+        } = await worker.recognize(imageDataUrl, {
           rotateAuto: true
         });
-        const targetWords = Array.from(new Set(Object.values(documentDictionary).flat(2)));
+        const targetWords = Array.from(
+          new Set(Object.values(documentDictionary).flat(2))
+        );
         const targetWordsFound = findTargetWords(text, targetWords);
         progress = 0.9;
         if (onProgress) onProgress(progress);
-        const classification = determineClassification(targetWordsFound, documentDictionary);
+        const classification = determineClassification(
+          targetWordsFound,
+          documentDictionary
+        );
         progress = 1;
@@ -106,3 +119,5 @@ if (onProgress) onProgress(progress);
 function determineClassification(targetWordsFound, documentDictionary) {
-  for (const [classification, targetWordSets] of Object.entries(documentDictionary)) {
+  for (const [classification, targetWordSets] of Object.entries(
+    documentDictionary
+  )) {
     for (const targetWords of targetWordSets) {
@@ -114,3 +129,3 @@ if (targetWords.every((word) => targetWordsFound.includes(word))) {
   }
-  return "UNKNOWN";
+  return "UKJENT";
 }
@@ -117,0 +132,0 @@ // Annotate the CommonJS export names for ESM import in node:

package.json

 {
   "name": "ocr-document-classification",
-  "version": "1.0.9",
+  "version": "1.0.10",
   "description": "Document classification using tesseract.js and string-similarity-js.",
@@ -5,0 +5,0 @@ "main": "./dist/index.js",

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

12662

increased by2.01%

Lines of code

227

increased by15.23%

No dependency changes