ocr-document-classification - npm Package Compare versions

Comparing version 1.3.0 to 1.3.1

dist/index.d.ts

@@ -5,3 +5,3 @@ type documentDictionary = {
 
-declare function classifyDocument(file: File, onProgress?: (progress: number) => void, customDocumentDictionary?: documentDictionary): Promise<{
+declare function classifyDocument(file: File, onProgress?: (progress: number) => void, customDocumentDictionary?: documentDictionary, maxNumPages?: number): Promise<{
     classification: string;
@@ -8,0 +8,0 @@ text: string;

dist/index.js

@@ -80,3 +80,3 @@ // src/functions.ts
 };
-async function classifyDocument(file, onProgress, customDocumentDictionary) {
+async function classifyDocument(file, onProgress, customDocumentDictionary, maxNumPages = Infinity) {
   const documentDictionary = {
@@ -99,19 +99,29 @@ ...defaultDocumentDictionary,
   let fullText = "";
-  for (let i = 0; i < totalBlobs; i++) {
-    const text = await ocrBlob(BlobArray[i]);
-    fullText += text + "\n";
-    progress = Math.round((i + 1) / totalBlobs * 100);
-    if (onProgress) {
-      onProgress(progress);
-    }
-  }
   const targetWords = Array.from(
     new Set(Object.values(documentDictionary).flat(2))
   );
-  const targetWordsFound = findTargetWords(fullText, targetWords);
-  const classification = determineClassification(
-    targetWordsFound,
-    documentDictionary
-  );
-  return { classification, text: fullText };
+  try {
+    for (let i = 0; i < totalBlobs; i++) {
+      if (i >= maxNumPages - 1) {
+        break;
+      }
+      const text = await ocrBlob(BlobArray[i]);
+      fullText += text;
+      progress = Math.round((i + 1) / totalBlobs * 100);
+      if (onProgress) {
+        onProgress(progress);
+      }
+      const targetWordsFound = findTargetWords(text, targetWords);
+      const classification = determineClassification(
+        targetWordsFound,
+        documentDictionary
+      );
+      if (classification !== "UKJENT") {
+        return { classification, text: fullText };
+      }
+    }
+  } catch (error) {
+    console.log("Error in ocr process: ", error);
+  }
+  return { classification: "UKJENT", text: fullText };
 }
@@ -137,3 +147,2 @@ function determineClassification(targetWordsFound, documentDictionary) {
       }
-      console.log(m);
     }
@@ -140,0 +149,0 @@ });

package.json

 {
   "name": "ocr-document-classification",
-  "version": "1.3.0",
+  "version": "1.3.1",
   "description": "Document classification using tesseract.js and string-similarity-js.",
@@ -5,0 +5,0 @@ "main": "./dist/index.cjs",

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

37657

increased by4.59%

Lines of code

379

increased by4.99%

No dependency changes