ocr-document-classification - npm Package Compare versions

Comparing version 1.3.1 to 1.3.2

dist/index.js

@@ -8,10 +8,10 @@ // src/functions.ts
 pdfjsLib.GlobalWorkerOptions.workerSrc = "https://cdn.jsdelivr.net/npm/pdfjs-dist@4.4.168/build/pdf.worker.min.mjs";
-async function convert(pdfPath) {
+async function convert(pdfPath, maxNumPages) {
   try {
     const loadingTask = pdfjsLib.getDocument(pdfPath);
     const doc = await loadingTask.promise;
-    const numPages = doc.numPages;
+    const totalPages = Math.min(pdf.numPages, maxNumPages);
     let blobArray = [];
     console.log(`PDF loaded with ${numPages} pages`);
-    for (let i = 1; i <= numPages; i++) {
+    for (let i = 1; i <= totalPages; i++) {
       const page = await doc.getPage(i);
@@ -89,3 +89,3 @@ const viewport = page.getViewport({ scale: 1.5 });
     const pdfPath = URL.createObjectURL(file);
-    BlobArray = await convert(pdfPath);
+    BlobArray = await convert(pdfPath, maxNumPages);
     console.log("Blob to read set by convert function");
@@ -98,3 +98,3 @@ } else if (file.type.startsWith("image/")) {
   let progress = 0;
-  const totalBlobs = BlobArray.length;
+  const totalBlobs = Math.min(BlobArray.length, maxNumPages);
   let fullText = "";
@@ -106,5 +106,2 @@ const targetWords = Array.from(
     for (let i = 0; i < totalBlobs; i++) {
-      if (i >= maxNumPages - 1) {
-        break;
-      }
       const text = await ocrBlob(BlobArray[i]);
@@ -111,0 +108,0 @@ fullText += text;

package.json

 {
   "name": "ocr-document-classification",
-  "version": "1.3.1",
+  "version": "1.3.2",
   "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

Worsened metrics

Total package byte prevSize

37617

decreased by-0.11%

Lines of code

373

decreased by-1.58%

No dependency changes