From 1f1f66cf3a3e9a28ff072947f92e5fc6d79d0a81 Mon Sep 17 00:00:00 2001
From: Srinivas-Saravanan <srinivas.saravanan@venbainfotech.com>
Date: Mon, 27 Jan 2025 10:58:47 +0530
Subject: [PATCH] FIX_EXCEL_SANTIZE_HELPER_IMPROVED

---
 app/Helpers/ExcelSanitizeHelper.php | 22 ++++++++--------------
 1 file changed, 8 insertions(+), 14 deletions(-)

diff --git a/app/Helpers/ExcelSanitizeHelper.php b/app/Helpers/ExcelSanitizeHelper.php
index 67aaa55e..5c2836a7 100644
--- a/app/Helpers/ExcelSanitizeHelper.php
+++ b/app/Helpers/ExcelSanitizeHelper.php
@@ -1,4 +1,5 @@
 <?php
+
 namespace App\Helpers;
 
 use PhpOffice\PhpSpreadsheet\Shared\StringHelper;
@@ -6,17 +7,11 @@ use PhpOffice\PhpSpreadsheet\Shared\StringHelper;
 class ExcelSanitizeHelper
 {
     /**
-     * Array of non-printable characters to be removed from strings.
-     *
-     * You can modify this array to include any characters you want to remove.
+     * Regex pattern for non-printable characters to be removed from strings.
+     * 
+     * This pattern includes control characters, zero-width characters, and Excel-specific codes
      */
-    private static $nonPrintableChars = [
-        "\x00", "\x01", "\x02", "\x03", "\x04", "\x05", "\x06", "\x07", "\x08", "\x09", 
-        "\x0A", "\x0B", "\x0C", "\x0D", "\x0E", "\x0F", "\x10", "\x11", "\x12", "\x13", 
-        "\x14", "\x15", "\x16", "\x17", "\x18", "\x19", "\x1A", "\x1B", "\x1C", "\x1D", 
-        "\x1E", "\x1F", "\x7F", "_x000D_", "_x000A_", "_x0009_", "_x0008_", "_x0007_", 
-        "_x0006_", "_x0005_", "_x0004_", "_x0003_", "_x0002_", "_x0001_","\u200C"
-    ];
+    private static $nonPrintablePattern = '/[\x00-\x1F\x7F\x{200B}\x{200C}]|_x[0-9A-F]{4}_/u';
 
     /**
      * Sanitizes array data by removing non-printable characters and trimming whitespace from strings.
@@ -24,22 +19,21 @@ class ExcelSanitizeHelper
      * @param array $data Input array containing data to sanitize
      * @return array Sanitized array with non-printable characters removed and leading/trailing whitespace trimmed
      */
-    public static function sanitizeArrayData(array $data): array 
+    public static function sanitizeArrayData(array $data): array
     {
         try {
             $cleanData = [];
-            
+
             foreach ($data as $key => $value) {
                 if (is_array($value)) {
                     $cleanData[$key] = self::sanitizeArrayData($value); // Recursive call for nested arrays
                 } elseif (is_string($value)) {
                     // Remove non-printable characters and trim whitespace from strings
-                    $cleanData[$key] = trim(str_replace(self::$nonPrintableChars, '', $value));
+                    $cleanData[$key] = trim(preg_replace(self::$nonPrintablePattern, '', $value));
                 } else {
                     $cleanData[$key] = $value; // Keep non-string/non-array data as is
                 }
             }
-            
             return $cleanData;
         } catch (\Exception $e) {
             // Log the error and the problematic data for debugging