ocr-document-classification - npm Package Compare versions

Comparing version 1.1.2 to 1.1.3

dist/index.js

		@@ -110,12 +110,18 @@ "use strict";
		if (file.type === "application/pdf") {
		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);
		}
		progress = 0.9;
		} else {
		console.log("Processing image file...");
		const imageDataUrl = URL.createObjectURL(file);
		text = await ocrImage(imageDataUrl, onProgress);
		console.log("Text extracted from image using OCR:", text);
		progress = 0.9;
		@@ -136,5 +142,10 @@ }
		} catch (err) {
		console.error("Error processing document:", err);
		reject(err);
		}
		};
		reader.onerror = (err) => {
		console.error("FileReader error:", err);
		reject(err);
		};
		if (file.type === "application/pdf") {
		@@ -141,0 +152,0 @@ reader.readAsArrayBuffer(file);

package.json

		{
		"name": "ocr-document-classification",
		"version": "1.1.2",
		"version": "1.1.3",
		"description": "Document classification using tesseract.js and string-similarity-js.",
		@@ -5,0 +5,0 @@ "main": "./dist/index.js",

dist/index.mjs

Sorry, the diff of this file is not supported yet

New alerts