pdf-parser-client-side - npm Package Compare versions

Comparing version 1.0.1 to 1.0.2

index.js

@@ -14,3 +14,3 @@ /* ---------------------------------------------
 
-module.exports = extractTextFromPDF = async (file) => {
+module.exports = extractTextFromPDF = async (file, variant) => {
   try {
@@ -35,2 +35,22 @@ // Create a blob URL for the PDF file
     if (extractedText.length > 0) {
+      // variant check
+      if (variant === "clean") {
+        extractedText = extractedText.replaceAll(
+          /[^\x00-\x7F]+\ *(?:[^\x00-\x7F]| )*/g,
+          " "
+        );
+      }
+      if (variant === "alphanumeric") {
+        extractedText = extractedText.replaceAll(/[^a-zA-Z0-9]+/g, " ");
+      }
+      if (variant === "alphanumericwithspace") {
+        extractedText = extractedText.replaceAll(/[^a-zA-Z0-9 ]+/g, " ");
+      }
+      if (variant === "alphanumericwithspaceandpunctuation") {
+        extractedText = extractedText.replaceAll(/[^a-zA-Z0-9 .,!?]+/g, " ");
+      }
+      if (variant === "alphanumericwithspaceandpunctuationandnewline") {
+        extractedText = extractedText.replaceAll(/[^a-zA-Z0-9 .,!?]+/g, " ");
+      }
+
       return extractedText;
@@ -37,0 +57,0 @@ }

package.json

 {
   "name": "pdf-parser-client-side",
-  "version": "1.0.1",
+  "version": "1.0.2",
   "description": "A lightweight easy to use package to parse text from PDF files on client side without any server dependency.",
@@ -5,0 +5,0 @@ "main": "index.js",

README.md

@@ -12,5 +12,7 @@ <div align="center">
 ## PDF Parser Client Side
+
 A lightweight easy to use package to parse text from PDF files on client side without any server dependency.
 
 ## How to Install ?
+
 Use npm or yarn to install this npm package
@@ -21,3 +23,5 @@
 ```
+
 or
+
 ```js
@@ -61,3 +65,46 @@ yarn add pdf-parser-client-side
 }
+```
 
+#### `variant` Parameter
+
+The `variant` parameter is used to specify the type of text extraction and replacement to be performed on the `extractedText`. Depending on the value of the `variant` parameter, different types of characters will be removed or retained.
+
+| `variant` Value                                 | Description                                                                            | Regular Expression                 | Retained Characters        |
+| ----------------------------------------------- | -------------------------------------------------------------------------------------- | ---------------------------------- | -------------------------- | --------------------- |
+| `clean`                                         | Removes all non-ASCII characters and any spaces that follow them.                      | `/[^\x00-\x7F]+\ \*(?:[^\x00-\x7F] | )\*/g`                     | ASCII characters only |
+| `alphanumeric`                                  | Retains only alphanumeric characters (letters and numbers).                            | `/[^a-zA-Z0-9]+/g`                 | A-Z, a-z, 0-9              |
+| `alphanumericwithspace`                         | Retains alphanumeric characters and spaces.                                            | `/[^a-zA-Z0-9 ]+/g`                | A-Z, a-z, 0-9, space       |
+| `alphanumericwithspaceandpunctuation`           | Retains alphanumeric characters, spaces, and basic punctuation marks (.,!?,).          | `/[^a-zA-Z0-9 .,!?]+/g`            | A-Z, a-z, 0-9, space, .,!? |
+| `alphanumericwithspaceandpunctuationandnewline` | Retains alphanumeric characters, spaces, basic punctuation marks (.,!?), and newlines. | `/[^a-zA-Z0-9 .,!?]+/g`            | A-Z, a-z, 0-9, space, .,!? |
+
+#### Example Usage
+
+```javascript
+import React from "react";
+import extractTextFromPDF from "pdf-parser-client-side";
+
+let extractedText = "Example text with special characters: !@#$%^&*()_+";
+
+export default function Test() {
+  return (
+    <div>
+      <input
+        type="file"
+        name=""
+        id="file-selector"
+        accept=".pdf"
+        onChange={(e) => {
+          // Selecting the first file
+          const file = e.target.files[0];
+          //   If file exists then we will call our function
+          if (file) {
+            extractTextFromPDF(file, "clean").then((data) => {
+              console.log(data);
+            });
+          }
+        }}
+      />
+    </div>
+  );
+}
 ```
@@ -64,0 +111,0 @@

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

14701

increased by28.88%

Lines of code

78

increased by32.2%

Number of lines in readme file

118

increased by66.2%

No dependency changes