@adobe/spacecat-shared-utils 1.94.0 → 1.95.0

package/CHANGELOG.md

@@ -1,3 +1,10 @@
+# [@adobe/spacecat-shared-utils-v1.95.0](https://github.com/adobe/spacecat-shared/compare/@adobe/spacecat-shared-utils-v1.94.0...@adobe/spacecat-shared-utils-v1.95.0) (2026-02-12)
+
+
+### Features
+
+* add canonicalizeUrl utility for consistent URL comparison ([#1334](https://github.com/adobe/spacecat-shared/issues/1334)) ([eb15132](https://github.com/adobe/spacecat-shared/commit/eb1513228e5d2e1701211b6aaf36108bd1642d68))
+
 # [@adobe/spacecat-shared-utils-v1.94.0](https://github.com/adobe/spacecat-shared/compare/@adobe/spacecat-shared-utils-v1.93.0...@adobe/spacecat-shared-utils-v1.94.0) (2026-02-11)
 
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@adobe/spacecat-shared-utils",
-  "version": "1.94.0",
+  "version": "1.95.0",
   "description": "Shared modules of the Spacecat Services - utils",
   "type": "module",
   "exports": {

package/src/index.d.ts

@@ -133,6 +133,20 @@ export declare function stripTrailingSlash(url: string): string;
  */
 export declare function stripWWW(url: string): string;
 
+/**
+ * Canonicalizes a URL by removing protocol, www prefix, and trailing slash
+ * for comparison and matching purposes.
+ * Optionally strips query parameters and fragments.
+ * @param url - URL to canonicalize
+ * @param options - Canonicalization options
+ * @param options.stripQuery - Whether to strip query parameters and fragments
+ * @returns Canonicalized URL
+ */
+export declare function canonicalizeUrl(
+  url: string,
+  options?: { stripQuery?: boolean }
+): string;
+
 /**
  * Composes a base URL by applying a series of transformations to the given domain.
  * @param domain - The domain to compose the base URL from.

package/src/index.js

@@ -55,6 +55,7 @@ export { logWrapper } from './log-wrapper.js';
 export { instrumentAWSClient, getTraceId, addTraceIdHeader } from './xray.js';
 
 export {
+  canonicalizeUrl,
   composeBaseURL,
   composeAuditURL,
   prependSchema,

package/src/url-helpers.js

@@ -318,6 +318,40 @@ async function wwwUrlResolver(site, rumApiClient, log) {
   return fallback;
 }
 
+/**
+ * Canonicalizes a URL by removing protocol, www prefix, and trailing slash
+ * for comparison and matching purposes.
+ * Optionally strips query parameters and fragments.
+ * @param {string} url - URL to canonicalize
+ * @param {object} options - Canonicalization options
+ * @param {boolean} options.stripQuery - Whether to strip query parameters and fragments
+ * @returns {string} Canonicalized URL
+ */
+export function canonicalizeUrl(url, { stripQuery = false } = {}) {
+  if (!url || typeof url !== 'string') {
+    return '';
+  }
+
+  let canonicalized = url
+    .toLowerCase() // Case insensitive
+    .trim()
+    .replace(/^https?:\/\//, '') // Remove protocol
+    .replace(/^www\d*\./, '') // Remove www, www2, www3, etc.
+    .replace(/\/$/, ''); // Remove trailing slash
+
+  // Optionally strip query parameters and fragments
+  if (stripQuery) {
+    const queryIndex = canonicalized.search(/[?#]/);
+    if (queryIndex !== -1) {
+      canonicalized = canonicalized.substring(0, queryIndex);
+    }
+    // Remove any trailing slash that may have been revealed
+    canonicalized = canonicalized.replace(/\/$/, '');
+  }
+
+  return canonicalized;
+}
+
 export {
   ensureHttps,
   getSpacecatRequestHeaders,