ocr-document-classification - npm Package Compare versions

Comparing version 1.3.4 to 1.3.5

dist/index.d.ts

@@ -5,3 +5,8 @@ type documentDictionary = {
 
-declare function classifyDocument(file: File, onProgress?: (progress: number) => void, customDocumentDictionary?: documentDictionary, maxNumPages?: number): Promise<{
+type ClassifyDocumentOptions = {
+    onProgress?: (progress: number) => void;
+    customDocumentDictionary?: documentDictionary;
+    maxNumPages?: number;
+};
+declare function classifyDocument(file: File, options?: ClassifyDocumentOptions): Promise<{
     classification: string;
@@ -8,0 +13,0 @@ text: string;

dist/index.js

@@ -84,3 +84,9 @@ // src/functions.ts
 };
-async function classifyDocument(file, onProgress, customDocumentDictionary, maxNumPages = Infinity) {
+async function classifyDocument(file, options = {}) {
+  const {
+    onProgress,
+    customDocumentDictionary,
+    maxNumPages = Infinity
+    // Default value if not provided
+  } = options;
   const documentDictionary = {
@@ -87,0 +93,0 @@ ...defaultDocumentDictionary,

package.json

 {
   "name": "ocr-document-classification",
-  "version": "1.3.4",
+  "version": "1.3.5",
   "description": "Document classification using tesseract.js and string-similarity-js.",
@@ -5,0 +5,0 @@ "main": "./dist/index.cjs",

README.md

@@ -30,5 +30,7 @@ # OCR Document Classification
 
-- `file`: The image file (File object) of the document to be classified.
-- `onProgress` (optional): A callback function to receive progress updates. It accepts a number between 0 and 1.
-- `customDocumentDictionary` (optional): An object containing custom document types and their associated target words.
+- file: The image file (File object) of the document to be classified.
+- options (optional): An object containing the following optional properties:
+  - onProgress: A callback function to receive progress updates. It accepts a number between 0 and 100.
+  - customDocumentDictionary: An object containing custom document types and their associated target words.
+  - maxNumPages: A number specifying the maximum number of pages to process. Defaults to Infinity.
 
@@ -43,3 +45,3 @@ #### Returns
 ### Classes
-There exists a couple of default classes that can be useful to classify the most common documents. As you can see there exists multiple arrays for each key. This means that every word of **only ONE** of the arrays needs to be found in the document after OCR. You can also add your own class my creating a customDocumentDictionary
+There exists a couple of default classes that can be useful to classify the most common documents. As you can see there exists multiple arrays for each key. This means that every word of **only ONE** of the arrays needs to be found in the document after OCR. You can also add your own class my creating a customDocumentDictionary.
 ```javascript
@@ -68,57 +70,67 @@ const defaultDocumentDictionary: documentDictionary = {
 ```jsx
+import React, { useState, useEffect } from "react";
+import { classifyDocument } from "ocr-document-classification";
+
 function UploadClassification() {
-  const [documentFile, setDocumentFile] = useState<File | null>(null)
-  const [classification, setClassification] = useState('')
-  const [outputText, setOutputText] = useState('')
-  const [progress, setProgress] = useState(0)
+  const [documentFile, setDocumentFile] = useState<File | null>(null);
+  const [classification, setClassification] = useState("");
+  const [outputText, setOutputText] = useState("");
+  const [progress, setProgress] = useState(0);
 
   const handleFileChange = (event: React.ChangeEvent<HTMLInputElement>) => {
-    const file = event.target.files && event.target.files[0]
-    setDocumentFile(file)
-  }
+    const file = event.target.files && event.target.files[0];
+    setDocumentFile(file);
+  };
 
   const customDocumentDictionary = {
-    Jobbsøknad: [['søknad', 'stilling', 'ledig']],
-  }
+    Jobbsøknad: [["søknad", "stilling", "ledig"]],
+  };
 
-    useEffect(() => {
-    console.log('Progress: ', progress)
-  }, [progress])
+  useEffect(() => {
+    console.log("Progress: ", progress);
+  }, [progress]);
 
   useEffect(() => {
     if (documentFile) {
-      classifyDocument(documentFile, setProgress, customDocumentDictionary)
+      classifyDocument(documentFile, {
+        onProgress: setProgress,
+        customDocumentDictionary: customDocumentDictionary,
+      })
         .then(({ classification, text }) => {
-          setClassification(classification)
-          setOutputText(text)
+          setClassification(classification);
+          setOutputText(text);
         })
         .catch((err) => {
-          console.error(err)
-          setOutputText('Error during OCR processing')
-        })
+          console.error(err);
+          setOutputText("Error during OCR processing");
+        });
     }
-    resetOCR()
-  }, [documentFile])
+    resetOCR();
+  }, [documentFile]);
 
   function resetOCR() {
-    setClassification('')
-    setOutputText('')
-    setImageSrc('')
-    setProgress(0)
+    setClassification("");
+    setOutputText("");
+    setProgress(0);
   }
 
-return (
+  return (
     <>
-    <input
+      <input
         accept="image/jpeg, image/png"
         type="file"
         onChange={handleFileChange}
-    />
-    <div>
+      />
+      <div>
         <h3>Resultat av OCR</h3>
-        <p>{classification ? outputText : 'Laster inn ...'}</p>
+        <p>{classification ? outputText : "Laster inn ..."}</p>
         <h1>{classification}</h1>
-    </div>
-)}
+      </div>
+    </>
+  );
+}
 
+export default UploadClassification;
+
+
 ```
@@ -132,2 +144,3 @@
 - `tesseract.js`: For performing OCR on the document image.
+- `pdfjs-dist`: For handling PDFs
 
@@ -134,0 +147,0 @@ ## LICENSE

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

39428

increased by3.44%

Lines of code

398

increased by4.46%

Number of lines in readme file

146

increased by9.77%

No dependency changes