[Hubspot] Add sanitizeValue function to Trim Whitespace and Remove Invisible Characters (#812)

* Sanitize values
- Add function to sanitize values
- Add function to trim whitespaces and remove invisible characters
- Add unit test cases

* update hubspot version in package json

---------

Co-authored-by: Arijit Ray <[email protected]>

Author: harsh-joshi99

integrations/hubspot/lib/index.js

@@ -70,6 +70,45 @@ HubSpot.prototype.loaded = function() {
   return libLoaded && !!(window.hbspt && window.hbspt.forms);
 };
 
+/**
+ * Trims whitespace and invisible characters from a string.
+ *
+ * @param {string} str - The string to trim.
+ * @returns {string} - The trimmed string.
+ */
+function trimWhitespaceAndInvisibleChars(str) {
+  // This regular expression matches leading and trailing whitespace characters,
+  // as well as invisible characters such as zero-width spaces and non-breaking spaces.
+  return str.replace(
+    /^[\s\u200B-\u200D\uFEFF]+|[\s\u200B-\u200D\uFEFF]+$/g,
+    ''
+  );
+}
+
+/**
+ * Recursively sanitizes the values of an object or array by trimming whitespace
+ * and invisible characters from string values, and preserving the structure of
+ * functions, arrays, and nested objects.
+ *
+ * @param {Object|Array} msg - The object or array to sanitize.
+ * @returns {Object|Array} - The sanitized object or array.
+ */
+function sanitizeValue(msg) {
+  if (typeof msg === 'object' && msg !== null) {
+    Object.keys(msg).forEach(function(key) {
+      var value = msg[key];
+      if (typeof value === 'string') {
+        msg[key] = trimWhitespaceAndInvisibleChars(value);
+      } else if (Array.isArray(value)) {
+        msg[key] = value.map(sanitizeValue);
+      } else if (typeof value === 'object') {
+        msg[key] = sanitizeValue(value);
+      }
+    });
+  }
+  return msg;
+}
+
 /**
  * Page.
  *
@@ -89,6 +128,7 @@ HubSpot.prototype.page = function() {
  */
 
 HubSpot.prototype.identify = function(identify) {
+  sanitizeValue(identify);
   // use newer version of Identify to have access to `companyName`
   var newIdentify = new Identify({
     traits: identify.traits(),
@@ -121,6 +161,7 @@ HubSpot.prototype.identify = function(identify) {
  */
 
 HubSpot.prototype.track = function(track) {
+  sanitizeValue(track);
   // Hubspot expects properties.id to be the name of the .track() event
   // Ref: http://developers.hubspot.com/docs/methods/enterprise_events/javascript_api
   var props = convertDates(track.properties({ id: '_id', revenue: 'value' }));

integrations/hubspot/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@segment/analytics.js-integration-hubspot",
   "description": "The Hubspot analytics.js integration.",
-  "version": "2.2.4",
+  "version": "2.2.5",
   "keywords": [
     "analytics.js",
     "analytics.js-integration",

integrations/hubspot/test/index.test.js

@@ -251,6 +251,22 @@ describe('HubSpot', function() {
           }
         ]);
       });
+
+      it('should sanitize values in identify method', function() {
+        analytics.identify({
+          email: '   [email protected]    ',
+          company: {
+            name: '    Example Company     '
+          }
+        });
+        analytics.called(window._hsq.push, [
+          'identify',
+          {
+            email: '[email protected]',
+            company: 'Example Company'
+          }
+        ]);
+      });
     });
 
     describe('#track', function() {
@@ -314,6 +330,18 @@ describe('HubSpot', function() {
           { id: 'Did Something Valuable', _id: '12345', value: 13 }
         ]);
       });
+
+      it('should sanitize values in track method', function() {
+        analytics.track('   Did Something Valuable  ', {
+          id: '   12345 ',
+          revenue: 13
+        });
+        analytics.called(window._hsq.push, [
+          'trackEvent',
+          'Did Something Valuable',
+          { id: 'Did Something Valuable', _id: '12345', value: 13 }
+        ]);
+      });
     });
 
     describe('#page', function() {