Modern UTM & Referral Cookie Replicator

script.js

<script id="gtm-modern-cookie-replicator">
  /**
   * Modern UTM & Referral Cookie Replicator
   *
   * Inspired from the UTMZ cookie replicator, 
   * whose goal was to makes a generally faithful representation 
   * of the old __utmz cookie from Classic Analytics. ;
   *
   * the "Modern" cookie replicator
   * - stores and decodes the cookie as/from JSON format
   * - stores raw UTM parameters along with google "friendly" equivalents using prefixes
   * - stores the time at which utm of ga referral variables were updated
   * - stores the first and last visited hosts
   * - stores the first referrer
   * - generates a unique visit ID
   *
   * Its goal is to be 
   * - data warehouse friendly (keep all raw data)
   * - session friendly (you know exactly when the UTM were first set or updated)
   * 
   * Stores the data in a cookie named cookieName (default `__cookie_utms`).
   * Also sets a session cookie named sessionCookieName (default `__cookie_utms_ses`).
   *
   * Data is stored in the cookie_utms cookie in JSON format 
   * brackets indicate optional data:
   *
   * { 
   *   ga_source: SOURCE
   *   ga_medium: MEDIUM
   *   ga_campaign: CAMPAIGN
   *   saved_at: CAMPAIGN
   *   first_visited_host: HOST
   *   last_visited_host: HOST
   *   referrer: STRING | null
   *   visit_id: STRING
   *   [|utm_campaign: UTM_CAMPAIGN]
   *   [|utm_medium: UTM_MEDIUM]
   *   [|utm_source: UTM_CAMPAIGN]
   *   [|utm_content: UTM_CONTENT]
   *   [|utm_term: UTM_TERM]
   *   [|utm_keyword: UTM_KEYWORD]
   * }
   */
  (function(document) {
    var referrer = document.referrer;
    var gaReferral = {
      'ga_source': '(direct)',
      'ga_medium': '(none)',
      'ga_campaign': '(not set)'
    };
    var cookieName = '__cookie_utms'
    var sessionCookieName = '__cookie_utms_ses'
    var thisHostname = document.location.hostname;
    var thisDomain = getDomain_(thisHostname);
    var referringDomain = getDomain_(document.referrer);
    var sessionCookie = getCookie_(sessionCookieName);
    // Expiration 4 hours from UTM registration
    var cookieExpiration = new Date(Date.now() + 4 * (60 * 60 * 1000) );
    var qs = document.location.search.replace('?', '');
    var hash = document.location.hash.replace('#', '');
    var gaParams = parseGoogleParams(qs + '#' + hash);
    var referringInfo = parseGaReferrer(referrer);
    var storedVals = getCookie_(cookieName);
    var referralOrUTMChanged = false
    var newCookieVals = {};
    var key;

    // Always rewrite previous values 
    // (we need to extend the cookie expiration)
    if (storedVals) {
      for (key in storedVals) {
        if (typeof storedVals[key] !== 'undefined') {
          newCookieVals[key] = storedVals[key];
        }
      }
    } else {
      for (key in gaReferral) {
        if (typeof gaReferral[key] !== 'undefined') {
          newCookieVals[key] = gaReferral[key];
        }
      }
      newCookieVals['visit_id'] = generateId()
      newCookieVals['referrer'] = referrer
    }

    // Do not erase existing stuff when browsing same domain
    if (sessionCookie && referringDomain === thisDomain) {
      gaParams = null;
      referringInfo = null;
    }

    if (gaParams && (gaParams.utm_source || gaParams.gclid || gaParams.dclid)) {
      referralOrUTMChanged = true 

      // Override ga_ with actual UTM values
      for (key in gaParams) {
        if (typeof gaParams[key] !== 'undefined') {
          gaReferral[key] = gaParams[key];
        }
      }

      // Google stuff
      if (gaParams.gclid || gaParams.dclid) {
        gaReferral.ga_source = 'google';
        gaReferral.ga_medium = gaReferral.ga_utmgclid ? 'cpc' : 'cpm';
      }

    } else if (referringInfo) {
      referralOrUTMChanged = true 

      // Override ga_ with actual referring info values
      gaReferral.ga_source = referringInfo.source;
      gaReferral.ga_medium = referringInfo.medium;
      if (referringInfo.term) {
        gaReferral.ga_term = referringInfo.term
      }
    }

    if (!storedVals || !storedVals.first_visited_host) {
      newCookieVals.first_visited_host = thisHostname
    }
    newCookieVals.last_visited_host = thisHostname

    if (referralOrUTMChanged) {
      for (key in gaReferral) {
        if (typeof gaReferral[key] !== 'undefined') {
          newCookieVals[key] = gaReferral[key];
        }
      }
      newCookieVals.saved_at = new Date().toISOString();
    }

    writeCookie_(cookieName, newCookieVals, cookieExpiration, '/', thisDomain);
    writeCookie_(sessionCookieName, 1, null, '/', thisDomain);

    function parseGoogleParams(str) {
      var campaignParams = ['source', 'medium', 'campaign', 'term', 'content', 'keyword'];
      var regex = new RegExp('(utm_(' + campaignParams.join('|') + ')|(d|g)clid)=.*?([^&#]*|$)', 'gi');
      var gaParams = str.match(regex);
      var paramsObj,
        vals,
        len,
        i;

      if (gaParams) {
        paramsObj = {};
        len = gaParams.length;

        for (i = 0; i < len; i++) {
          vals = gaParams[i].split('=');

          if (vals) {
            paramsObj[vals[0]] = vals[1];
          }
        }
      }
      return paramsObj;
    }

    function parseGaReferrer(referrer) {
      if (!referrer) return;

      var searchEngines = {
        'daum.net': {
          'p': 'q',
          'n': 'daum'
        },
        'eniro.se': {
          'p': 'search_word',
          'n': 'eniro '
        },
        'naver.com': {
          'p': 'query',
          'n': 'naver '
        },
        'yahoo.com': {
          'p': 'p',
          'n': 'yahoo'
        },
        'msn.com': {
          'p': 'q',
          'n': 'msn'
        },
        'bing.com': {
          'p': 'q',
          'n': 'live'
        },
        'aol.com': {
          'p': 'q',
          'n': 'aol'
        },
        'lycos.com': {
          'p': 'q',
          'n': 'lycos'
        },
        'ask.com': {
          'p': 'q',
          'n': 'ask'
        },
        'altavista.com': {
          'p': 'q',
          'n': 'altavista'
        },
        'search.netscape.com': {
          'p': 'query',
          'n': 'netscape'
        },
        'cnn.com': {
          'p': 'query',
          'n': 'cnn'
        },
        'about.com': {
          'p': 'terms',
          'n': 'about'
        },
        'mamma.com': {
          'p': 'query',
          'n': 'mama'
        },
        'alltheweb.com': {
          'p': 'q',
          'n': 'alltheweb'
        },
        'voila.fr': {
          'p': 'rdata',
          'n': 'voila'
        },
        'search.virgilio.it': {
          'p': 'qs',
          'n': 'virgilio'
        },
        'baidu.com': {
          'p': 'wd',
          'n': 'baidu'
        },
        'alice.com': {
          'p': 'qs',
          'n': 'alice'
        },
        'yandex.com': {
          'p': 'text',
          'n': 'yandex'
        },
        'najdi.org.mk': {
          'p': 'q',
          'n': 'najdi'
        },
        'seznam.cz': {
          'p': 'q',
          'n': 'seznam'
        },
        'search.com': {
          'p': 'q',
          'n': 'search'
        },
        'wp.pl': {
          'p': 'szukaj ',
          'n': 'wirtulana polska'
        },
        'online.onetcenter.org': {
          'p': 'qt',
          'n': 'o*net'
        },
        'szukacz.pl': {
          'p': 'q',
          'n': 'szukacz'
        },
        'yam.com': {
          'p': 'k',
          'n': 'yam'
        },
        'pchome.com': {
          'p': 'q',
          'n': 'pchome'
        },
        'kvasir.no': {
          'p': 'q',
          'n': 'kvasir'
        },
        'sesam.no': {
          'p': 'q',
          'n': 'sesam'
        },
        'ozu.es': {
          'p': 'q',
          'n': 'ozu '
        },
        'terra.com': {
          'p': 'query',
          'n': 'terra'
        },
        'mynet.com': {
          'p': 'q',
          'n': 'mynet'
        },
        'ekolay.net': {
          'p': 'q',
          'n': 'ekolay'
        },
        'rambler.ru': {
          'p': 'words',
          'n': 'rambler'
        },
        'google': {
          'p': 'q',
          'n': 'google'
        }
      };
      var a = document.createElement('a');
      var values = {};
      var searchEngine,
        termRegex,
        term;

      a.href = referrer;

      // Shim for the billion google search engines
      if (a.hostname.indexOf('google') > -1) {
        referringDomain = 'google';
      }

      if (searchEngines[referringDomain]) {
        searchEngine = searchEngines[referringDomain];
        termRegex = new RegExp(searchEngine.p + '=.*?([^&#]*|$)', 'gi');
        term = a.search.match(termRegex);

        values.source = searchEngine.n;
        values.medium = 'organic';

        values.term = (term ? term[0].split('=')[1] : '') || '(not provided)';
      } else if (referringDomain !== thisDomain) {
        values.source = a.hostname;
        values.medium = 'referral';
      }

      return values;
    }

    function writeCookie_(name, value, expiration, path, domain) {
      var str = name + '=' + JSON.stringify(value) + '; SameSite=Lax; Secure';
      if (expiration) str += 'Expires=' + expiration.toGMTString() + ';';
      if (path) str += 'Path=' + path + ';';
      if (domain) str += 'Domain=' + domain + ';';

      document.cookie = str;
    }

    function getCookie_(cname) {
      var matchingCookie = document.cookie.split('; ').find(function (row) {
        return row.startsWith(cname + '=');
      })
      if(!matchingCookie) { return null; }

      var cookie = matchingCookie.split('=')[1]

      if (cookie.startsWith('{')) {
        return JSON.parse(cookie);
      } else {
        return null;
      }
    }

    function getDomain_(url) {
      if (!url) return;

      var a = document.createElement('a');
      a.href = url;

      try {
        return a.hostname.match(/[^.]*\.[^.]{2,3}(?:\.[^.]{2,3})?$/)[0];
      } catch(squelch) {}
    }

    // https://stackoverflow.com/a/2117523/1177228
    function generateId() {
      return ([1e7] + -1e3 + -4e3 + -8e3 + -1e11).replace(/[018]/g, function (c) {
        return (c ^ crypto.getRandomValues(new Uint8Array(1))[0] & 15 >> c / 4).toString(16);
      });
    }
  })(document);
</script>