ocr-document-classification - npm Package Compare versions

Comparing version 1.1.3 to 1.1.4

dist/index.js

@@ -40,3 +40,2 @@ "use strict";
 var Tesseract = __toESM(require("tesseract.js"));
-var pdfjsLib = __toESM(require("pdfjs-dist"));
 function findTargetWords(documentText, targetWords, threshold = 0.75) {
@@ -68,14 +67,2 @@ const foundTargetWords = [];
 };
-async function extractTextFromPDF(fileContent) {
-  pdfjsLib.GlobalWorkerOptions.workerSrc = `https://cdn.jsdelivr.net/npm/pdfjs-dist@4.4.168/+esm`;
-  const pdf = await pdfjsLib.getDocument({ data: fileContent }).promise;
-  let text = "";
-  for (let i = 0; i < pdf.numPages; i++) {
-    const page = await pdf.getPage(i + 1);
-    const content = await page.getTextContent();
-    const pageText = content.items.map((item) => item.str).join(" ");
-    text += pageText + "\n";
-  }
-  return text;
-}
 async function ocrImage(imageDataUrl, onProgress) {
@@ -93,3 +80,5 @@ const worker = await Tesseract.createWorker(["nor", "eng"], 1, {
   });
-  const { data: { text } } = await worker.recognize(imageDataUrl, {
+  const {
+    data: { text }
+  } = await worker.recognize(imageDataUrl, {
     rotateAuto: true
@@ -114,11 +103,6 @@ });
           console.log("Processing PDF file...");
-          text = await extractTextFromPDF(fileContent);
-          console.log("Text extracted from PDF:", text);
-          if (!text.trim()) {
-            console.log("Extracted text is empty, using OCR...");
-            const blob = new Blob([fileContent], { type: "application/pdf" });
-            const imageDataUrl = URL.createObjectURL(blob);
-            text = await ocrImage(imageDataUrl, onProgress);
-            console.log("Text extracted using OCR:", text);
-          }
+          const blob = new Blob([fileContent], { type: "application/pdf" });
+          const imageDataUrl = URL.createObjectURL(blob);
+          text = await ocrImage(imageDataUrl, onProgress);
+          console.log("Text extracted using OCR from pdf:", text);
           progress = 0.9;
@@ -125,0 +109,0 @@ } else {

package.json

 {
   "name": "ocr-document-classification",
-  "version": "1.1.3",
+  "version": "1.1.4",
   "description": "Document classification using tesseract.js and string-similarity-js.",
@@ -28,3 +28,2 @@ "main": "./dist/index.js",
   "dependencies": {
-    "pdfjs-dist": "^4.4.168",
     "string-similarity-js": "^2.1.4",
@@ -31,0 +30,0 @@ "tesseract.js": "^5.1.0",

No alert changes

Improved metrics

Dependency count

3

decreased by-25%

Worsened metrics

Total package byte prevSize

14612

decreased by-9.48%

Lines of code

279

decreased by-10.29%

Dependency changes

• - Removedpdfjs-dist@^4.4.168

• - Removed@napi-rs/canvas@0.1.67(transitive)

• - Removed@napi-rs/canvas-android-arm64@0.1.67(transitive)

• - Removed@napi-rs/canvas-darwin-arm64@0.1.67(transitive)

• - Removed@napi-rs/canvas-darwin-x64@0.1.67(transitive)

• - Removed@napi-rs/canvas-linux-arm-gnueabihf@0.1.67(transitive)

• - Removed@napi-rs/canvas-linux-arm64-gnu@0.1.67(transitive)

• - Removed@napi-rs/canvas-linux-arm64-musl@0.1.67(transitive)

• - Removed@napi-rs/canvas-linux-riscv64-gnu@0.1.67(transitive)

• - Removed@napi-rs/canvas-linux-x64-gnu@0.1.67(transitive)

• - Removed@napi-rs/canvas-linux-x64-musl@0.1.67(transitive)

• - Removed@napi-rs/canvas-win32-x64-msvc@0.1.67(transitive)

• - Removedpdfjs-dist@4.10.38(transitive)