From 686581cfccc15ff3d15a444dea5d76b86f091850 Mon Sep 17 00:00:00 2001
From: sunil-lakshman <104969541+sunil-lakshman@users.noreply.github.com>
Date: Wed, 13 Nov 2024 16:44:50 +0530
Subject: [PATCH] chore: Fixed table cell merge issue

---
 CHANGELOG.md           |  3 +++
 package-lock.json      |  4 ++--
 package.json           |  2 +-
 src/helper/sanitize.ts | 21 ++++++++++++---------
 4 files changed, 18 insertions(+), 12 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 6e78677..b17d141 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,5 +1,8 @@
 # Changelog
 
+## [1.3.14](https://github.com/contentstack/contentstack-utils-javascript/tree/v1.3.14) (2024-11-18)
+ - Fix: Added Table cell merge in table tags
+
 ## [1.3.13](https://github.com/contentstack/contentstack-utils-javascript/tree/v1.3.13) (2024-10-22)
  - Enh: Node version bump
 
diff --git a/package-lock.json b/package-lock.json
index 9b29e97..d6fbce1 100644
--- a/package-lock.json
+++ b/package-lock.json
@@ -1,12 +1,12 @@
 {
   "name": "@contentstack/utils",
-  "version": "1.3.13",
+  "version": "1.3.14",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "@contentstack/utils",
-      "version": "1.3.13",
+      "version": "1.3.14",
       "license": "MIT",
       "devDependencies": {
         "@babel/preset-env": "^7.22.20",
diff --git a/package.json b/package.json
index 4c25fb7..6e6b2ad 100644
--- a/package.json
+++ b/package.json
@@ -1,6 +1,6 @@
 {
   "name": "@contentstack/utils",
-  "version": "1.3.13",
+  "version": "1.3.14",
   "description": "Contentstack utilities for Javascript",
   "main": "dist/index.es.js",
   "types": "dist/types/index.d.ts",
diff --git a/src/helper/sanitize.ts b/src/helper/sanitize.ts
index c413ff2..a94fa3e 100644
--- a/src/helper/sanitize.ts
+++ b/src/helper/sanitize.ts
@@ -1,19 +1,22 @@
 
-type AllowedTags = 'p' | 'a' | 'strong' | 'em' | 'ul' | 'ol' | 'li' | 'h1' | 'h2' | 'h3' | 'h4' | 'h5' | 'h6' | 'sub' | 'u' | 'table' | 'thead' | 'tbody' | 'tr' | 'th' | 'td' | 'span'|'fragment'|'strike'|'sup'|'br';
-type AllowedAttributes = 'href' | 'title' | 'target' | 'alt' | 'src' | 'class' | 'id' | 'style';
+type AllowedTags = 'p' | 'a' | 'strong' | 'em' | 'ul' | 'ol' | 'li' | 'h1' | 'h2' | 'h3' | 'h4' | 'h5' | 'h6' | 'sub' | 'u' | 'table' | 'thead' | 'tbody' | 'tr' | 'th' | 'td' | 'span' | 'fragment' | 'strike' | 'sup' | 'br';
+type AllowedAttributes = 'href' | 'title' | 'target' | 'alt' | 'src' | 'class' | 'id' | 'style' | 'colspan' | 'rowspan' | 'content-type-uid' | 'data-sys-asset-uid' | 'sys-style-type';
 
-export function sanitizeHTML(input: string, allowedTags: AllowedTags[] = ['p', 'a', 'strong', 'em', 'ul', 'ol', 'li', 'h1', 'h2', 'h3', 'h4', 'h5', 'h6', 'sub', 'u', 'table', 'thead', 'tbody', 'tr', 'th', 'td', 'span','fragment','sup','strike','br'], allowedAttributes: AllowedAttributes[] = ['href', 'title', 'target', 'alt', 'src', 'class', 'id', 'style']): string {
+export function sanitizeHTML(input: string, allowedTags: AllowedTags[] = ['p', 'a', 'strong', 'em', 'ul', 'ol', 'li', 'h1', 'h2', 'h3', 'h4', 'h5', 'h6', 'sub', 'u', 'table', 'thead', 'tbody', 'tr', 'th', 'td', 'span', 'fragment', 'sup', 'strike', 'br'], allowedAttributes: AllowedAttributes[] = ['href', 'title', 'target', 'alt', 'src', 'class', 'id', 'style', 'colspan', 'rowspan', 'content-type-uid', 'data-sys-asset-uid', 'sys-style-type']): string {
     // Regular expression to find and remove all HTML tags except the allowed ones
     const sanitized = input.replace(/<\/?([a-z][a-z0-9]*)\b[^<>]*>/gi, (match, tag) => {
         return allowedTags.includes(tag.toLowerCase()) ? match : '';
     });
 
     // Regular expression to remove all attributes except the allowed ones
-    const cleaned = sanitized.replace(/\s([a-z:]+)=['"][^'"]*['"]/gi
-    , (match, attribute) => {
-        return allowedAttributes.includes(attribute.toLowerCase()) ? match : '';
+    const cleaned = sanitized.replace(/<([a-z][a-z0-9]*)\b[^<>]*>/gi, (match, tag) => {
+        if (!allowedTags.includes(tag.toLowerCase())) {
+            return match; // Ignore tags not in allowedTags
+        }
+        // For each tag that is allowed, clean its attributes
+        return match.replace(/\s([a-z\-]+)=['"][^'"]*['"]/gi, (attributeMatch, attribute) => {
+            return allowedAttributes.includes(attribute.toLowerCase()) ? attributeMatch : '';
+        });
     });
-
     return cleaned;
-}
-
+}
\ No newline at end of file