ENGCOM-4533: Remove all marketing get params on Varnish to minimize the cache objects #21818

Author: sidolov

app/code/Magento/PageCache/etc/varnish4.vcl

@@ -91,10 +91,11 @@ sub vcl_recv {
         }
     }
 
-    # Remove Google gclid parameters to minimize the cache objects
-    set req.url = regsuball(req.url,"\?gclid=[^&]+$",""); # strips when QS = "?gclid=AAA"
-    set req.url = regsuball(req.url,"\?gclid=[^&]+&","?"); # strips when QS = "?gclid=AAA&foo=bar"
-    set req.url = regsuball(req.url,"&gclid=[^&]+",""); # strips when QS = "?foo=bar&gclid=AAA" or QS = "?foo=bar&gclid=AAA&bar=baz"
+    # Remove all marketing get parameters to minimize the cache objects
+    if (req.url ~ "(\?|&)(gclid|cx|ie|cof|siteurl|zanpid|origin|mc_[a-z]+|utm_[a-z]+)=") {
+        set req.url = regsuball(req.url, "(gclid|cx|ie|cof|siteurl|zanpid|origin|mc_[a-z]+|utm_[a-z]+)=[-_A-z0-9+()%.]+&?", "");
+        set req.url = regsub(req.url, "[?|&]+$", "");
+    }
 
     # Static files caching
     if (req.url ~ "^/(pub/)?(media|static)/") {

app/code/Magento/PageCache/etc/varnish5.vcl

@@ -92,10 +92,11 @@ sub vcl_recv {
         }
     }
 
-    # Remove Google gclid parameters to minimize the cache objects
-    set req.url = regsuball(req.url,"\?gclid=[^&]+$",""); # strips when QS = "?gclid=AAA"
-    set req.url = regsuball(req.url,"\?gclid=[^&]+&","?"); # strips when QS = "?gclid=AAA&foo=bar"
-    set req.url = regsuball(req.url,"&gclid=[^&]+",""); # strips when QS = "?foo=bar&gclid=AAA" or QS = "?foo=bar&gclid=AAA&bar=baz"
+    # Remove all marketing get parameters to minimize the cache objects
+    if (req.url ~ "(\?|&)(gclid|cx|ie|cof|siteurl|zanpid|origin|mc_[a-z]+|utm_[a-z]+)=") {
+        set req.url = regsuball(req.url, "(gclid|cx|ie|cof|siteurl|zanpid|origin|mc_[a-z]+|utm_[a-z]+)=[-_A-z0-9+()%.]+&?", "");
+        set req.url = regsub(req.url, "[?|&]+$", "");
+    }
 
     # Static files caching
     if (req.url ~ "^/(pub/)?(media|static)/") {