@adobe/spacecat-shared-rum-api-client 2.28.1 → 2.30.0

package/CHANGELOG.md

@@ -1,3 +1,17 @@
+# [@adobe/spacecat-shared-rum-api-client-v2.30.0](https://github.com/adobe/spacecat-shared/compare/@adobe/spacecat-shared-rum-api-client-v2.29.0...@adobe/spacecat-shared-rum-api-client-v2.30.0) (2025-06-25)
+
+
+### Features
+
+* SITES-32914 implement `startDate` and `endDate` in RUM client ([#819](https://github.com/adobe/spacecat-shared/issues/819)) ([1520465](https://github.com/adobe/spacecat-shared/commit/15204653ca7a1c3f04b1df30afc1a72f74d2b254))
+
+# [@adobe/spacecat-shared-rum-api-client-v2.29.0](https://github.com/adobe/spacecat-shared/compare/@adobe/spacecat-shared-rum-api-client-v2.28.1...@adobe/spacecat-shared-rum-api-client-v2.29.0) (2025-06-20)
+
+
+### Features
+
+* high organic low ctr detection using traffic instead of thresholds ([#815](https://github.com/adobe/spacecat-shared/issues/815)) ([54569fb](https://github.com/adobe/spacecat-shared/commit/54569fb5d9b5fbe8400da0aadbae148380866fda))
+
 # [@adobe/spacecat-shared-rum-api-client-v2.28.1](https://github.com/adobe/spacecat-shared/compare/@adobe/spacecat-shared-rum-api-client-v2.28.0...@adobe/spacecat-shared-rum-api-client-v2.28.1) (2025-05-31)
 
 

package/README.md

@@ -46,6 +46,21 @@ const result = await rumApiClient.query('cwv', opts);
 console.log(`Query result: ${result}`);
 ```
 
+**Using startTime and endTime for precise date ranges:**
+
+```js
+const opts = {
+  domain: 'www.aem.live',
+  domainkey: '<domain-key>',
+  granularity: 'daily',
+  startTime: '2024-01-01T00:00:00Z',
+  endTime: '2024-01-31T23:59:59Z'
+};
+
+const result = await rumApiClient.query('cwv', opts);
+console.log(`Query result: ${result}`);
+```
+
 **Note**: All query names must be lowercase.
 
 ### Query Options: the 'opts' object
@@ -54,8 +69,10 @@ console.log(`Query result: ${result}`);
 |-------------|----------|---------|----------------------------------------------------------|
 | domain      | yes      |         | The domain for which to fetch data.                      |
 | domainkey   | no       |         | Provide directly or omit to auto-fetch using `RUM_ADMIN_KEY`. |
-| interval    | no       | 7       | Interval in days (integer).                              |
+| interval    | no       | 7       | Interval in days (integer). Ignored when startTime/endTime are provided. |
 | granularity | no       | daily   | 'daily' or 'hourly'.                                     |
+| startTime   | no       |         | Start time in ISO 8601 format (e.g., "2024-01-01T00:00:00Z"). Must be before endTime. Format `YYYY-MM-DD` or `YYYY-MM-DDTHH:MM:SSZ` |
+| endTime     | no       |         | End time in ISO 8601 format (e.g., "2024-01-31T23:59:59Z"). Must be after startTime.  Format `YYYY-MM-DD` or `YYYY-MM-DDTHH:MM:SSZ` |
 
 
 ### Retrieving and Caching the Domainkey

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@adobe/spacecat-shared-rum-api-client",
-  "version": "2.28.1",
+  "version": "2.30.0",
   "description": "Shared modules of the Spacecat Services - Rum API client",
   "type": "module",
   "engines": {

package/src/common/rum-bundler-client.js

@@ -22,6 +22,24 @@ const ONE_DAY = ONE_HOUR * HOURS_IN_DAY;
 
 const CHUNK_SIZE = 31;
 
+/**
+ * Parses a date string and returns a Date object.
+ * Supports both ISO 8601 format (e.g., "2024-01-01T00:00:00Z")
+ * and simple date format (e.g., "2024-01-01").
+ * For simple date strings, assumes UTC timezone.
+ * @param {string} dateString - The date string to parse
+ * @returns {Date} The parsed Date object
+ */
+function parseDate(dateString) {
+  // If it's a simple date string (YYYY-MM-DD), convert to ISO format
+  if (/^\d{4}-\d{2}-\d{2}$/.test(dateString)) {
+    return new Date(`${dateString}T00:00:00.000Z`);
+  }
+
+  // Otherwise, let the Date constructor handle it (ISO 8601, etc.)
+  return new Date(dateString);
+}
+
 function isBotTraffic(bundle) {
   return bundle?.userAgent?.includes('bot');
 }
@@ -54,6 +72,24 @@ function getUrlChunks(urls, chunkSize) {
     .map((_, index) => urls.slice(index * chunkSize, (index + 1) * chunkSize));
 }
 
+function generateUrlsForDateRange(startDate, endDate, domain, granularity, domainkey) {
+  const urls = [];
+  const currentDate = parseDate(startDate);
+  const endDateTime = parseDate(endDate);
+
+  while (currentDate < endDateTime) {
+    urls.push(constructUrl(domain, currentDate, granularity, domainkey));
+
+    if (granularity.toUpperCase() === GRANULARITY.HOURLY) {
+      currentDate.setUTCHours(currentDate.getUTCHours() + 1);
+    } else {
+      currentDate.setUTCDate(currentDate.getUTCDate() + 1);
+    }
+  }
+
+  return urls;
+}
+
 /* c8 ignore start */
 /*
  * throw-away code for a single customer who customized the experimentation engine
@@ -165,23 +201,46 @@ async function fetchBundles(opts, log) {
     granularity = GRANULARITY.DAILY,
     checkpoints = [],
     filterBotTraffic = true,
+    startTime,
+    endTime,
   } = opts;
 
   if (!hasText(domain) || !hasText(domainkey)) {
     throw new Error('Missing required parameters');
   }
 
-  const multiplier = granularity.toUpperCase() === GRANULARITY.HOURLY ? ONE_HOUR : ONE_DAY;
-  const range = granularity.toUpperCase() === GRANULARITY.HOURLY
-    ? interval * HOURS_IN_DAY
-    : interval + 1;
+  // Validate startTime and endTime if provided
+  if (startTime && endTime) {
+    const start = parseDate(startTime);
+    const end = parseDate(endTime);
 
-  const urls = [];
-  const currentDate = new Date();
+    if (Number.isNaN(start.getTime()) || Number.isNaN(end.getTime())) {
+      throw new Error('Invalid startTime or endTime format. Use ISO 8601 format (e.g., "2024-01-01T00:00:00Z") or simple date format (e.g., "2024-01-01")');
+    }
 
-  for (let i = 0; i < range; i += 1) {
-    const date = new Date(currentDate.getTime() - i * multiplier);
-    urls.push(constructUrl(domain, date, granularity, domainkey));
+    if (start >= end) {
+      throw new Error('startTime must be before endTime');
+    }
+  }
+
+  let urls = [];
+
+  if (startTime && endTime) {
+    // Use custom date range
+    urls = generateUrlsForDateRange(startTime, endTime, domain, granularity, domainkey);
+  } else {
+    // Use existing interval-based logic
+    const multiplier = granularity.toUpperCase() === GRANULARITY.HOURLY ? ONE_HOUR : ONE_DAY;
+    const range = granularity.toUpperCase() === GRANULARITY.HOURLY
+      ? interval * HOURS_IN_DAY
+      : interval + 1;
+
+    const currentDate = new Date();
+
+    for (let i = 0; i < range; i += 1) {
+      const date = new Date(currentDate.getTime() - i * multiplier);
+      urls.push(constructUrl(domain, date, granularity, domainkey));
+    }
   }
 
   const chunks = getUrlChunks(urls, CHUNK_SIZE);
@@ -197,7 +256,6 @@ async function fetchBundles(opts, log) {
       return response;
     }));
     const bundles = await Promise.all(responses.map((response) => response.json()));
-
     bundles.forEach((b) => {
       b.rumBundles
         .filter((bundle) => !filterBotTraffic || !isBotTraffic(bundle))

package/src/functions/opportunities/high-organic-low-ctr.js

@@ -13,16 +13,15 @@
 import trafficAcquisition from '../traffic-acquisition.js';
 import { getCTRByUrlAndVendor, getSiteAvgCTR } from '../../common/aggregateFns.js';
 
-const DAILY_EARNED_THRESHOLD = 1000;
-const CTR_THRESHOLD_RATIO = 0.95;
-const DAILY_PAGEVIEW_THRESHOLD = 1000;
 const VENDORS_TO_CONSIDER = 5;
+const MAX_OPPORTUNITIES = 10;
 
 const MAIN_TYPES = ['paid', 'earned', 'owned'];
 
 function convertToOpportunity(traffic) {
   const {
-    url, total, ctr, paid, owned, earned, sources, siteAvgCTR, ctrByUrlAndVendor, pageOnTime,
+    url, total, ctr, paid, percentileScore, owned, earned,
+    sources, siteAvgCTR, ctrByUrlAndVendor, pageOnTime,
   } = traffic;
 
   const vendors = sources.reduce((acc, { type, views }) => {
@@ -51,6 +50,7 @@ function convertToOpportunity(traffic) {
     trackedKPISiteAverage: siteAvgCTR,
     pageViews: total,
     samples: total, // todo: get the actual number of samples
+    percentileScore,
     metrics: [{
       type: 'traffic',
       vendor: '*',
@@ -106,33 +106,48 @@ function convertToOpportunity(traffic) {
   return opportunity;
 }
 
-function hasHighOrganicTraffic(interval, traffic) {
-  const { earned } = traffic;
-  return earned >= DAILY_EARNED_THRESHOLD * interval;
-}
+/**
+ * Sort pages by earned AND overall traffic using percentile scoring.
+ * @param {Array} pages - List of { url, total, earned }
+ * @returns {Array} List of pages sorted by joint strength
+ */
+function sortPagesByEarnedAndOverallTraffic(pages) {
+  if (!Array.isArray(pages) || pages.length === 0) return [];
 
-function hasLowerCTR(ctr, siteAvgCTR) {
-  return ctr < CTR_THRESHOLD_RATIO * siteAvgCTR;
-}
+  const sortedOverall = [...pages].sort((a, b) => a.total - b.total);
+  const sortedEarned = [...pages].sort((a, b) => {
+    if (a.earned === b.earned) {
+      return a.total - b.total;
+    }
+    return a.earned - b.earned;
+  });
+  const n = pages.length;
+
+  const percentiles = pages.map((p) => {
+    const totalPercentile = sortedOverall.findIndex((x) => x.url === p.url) / (n - 1);
+    const earnedPercentile = sortedEarned.findIndex((x) => x.url === p.url) / (n - 1);
+    const percentileScore = totalPercentile * earnedPercentile;
+    return { ...p, percentileScore };
+  });
 
-function handler(bundles, opts = {}) {
-  const { interval = 7 } = opts;
+  return percentiles.sort((a, b) => b.percentileScore - a.percentileScore);
+}
 
+function handler(bundles) {
   const trafficByUrl = trafficAcquisition.handler(bundles);
   const ctrByUrlAndVendor = getCTRByUrlAndVendor(bundles);
   const siteAvgCTR = getSiteAvgCTR(bundles);
+  const pagesSortedByEarnedAndOverallTraffic = sortPagesByEarnedAndOverallTraffic(
+    trafficByUrl,
+  ).slice(0, MAX_OPPORTUNITIES);
 
-  return trafficByUrl.filter((traffic) => traffic.total > interval * DAILY_PAGEVIEW_THRESHOLD)
-    .filter(hasHighOrganicTraffic.bind(null, interval))
-    .filter((traffic) => hasLowerCTR(ctrByUrlAndVendor[traffic.url].value, siteAvgCTR))
-    .map((traffic) => ({
-      ...traffic,
-      ctr: ctrByUrlAndVendor[traffic.url].value,
-      siteAvgCTR,
-      ctrByUrlAndVendor: ctrByUrlAndVendor[traffic.url].vendors,
-      pageOnTime: traffic.maxTimeDelta,
-    }))
-    .map(convertToOpportunity);
+  return pagesSortedByEarnedAndOverallTraffic.map((traffic) => ({
+    ...traffic,
+    ctr: ctrByUrlAndVendor[traffic.url].value,
+    siteAvgCTR,
+    ctrByUrlAndVendor: ctrByUrlAndVendor[traffic.url].vendors,
+    pageOnTime: traffic.maxTimeDelta,
+  })).map(convertToOpportunity);
 }
 
 export default {

package/src/functions/traffic-acquisition.js

@@ -47,7 +47,7 @@ function formatTraffic(row) {
     url, weight, type, category, vendor, events = [],
   } = row;
 
-  const maxTimeDelta = events.reduce((max, e) => Math.max(max, e.timeDelta), 0);
+  const maxTimeDelta = events.reduce((max, e) => Math.max(max, e.timeDelta || 0), 0);
 
   return {
     url,

package/src/index.d.ts

@@ -28,6 +28,16 @@ export interface RUMAPIOptions {
    */
   interval?: number;
 
+  /**
+   * Start Date
+   */
+  startDate?: string;
+
+  /**
+   * End Date
+   */
+  endDate?: string;
+
   /**
    * Granularity can be 'hourly' or 'daily'.
    * @default 'daily'