philfreo · September 29, 2021 13:46 · Jan 19, 2021 · Jan 19, 2021 · Jan 19, 2021 · Jan 14, 2021
diff --git a/3_workaround.py b/3_workaround.py
@@ -10,6 +10,7 @@ def hash(s):
 
 anonymous_id = '(This needs to be passed to your backend from the browser/JS)'
 
+# Then on any call to Segment where integrations['Google Analytics'] is not False...
 analytics.track(user_id, 'Test', {}, anonymous_id=anonymous_id, integrations={
     'Google Analytics': {
         # Segment ignores our custom clientId if it's not a string

diff --git a/3_workaround.py b/3_workaround.py
@@ -8,7 +8,7 @@ def hash(s):
         hash = (hash * 33) ^ c[0]
     return c_uint32(hash).value
 
-anonymous_id = '(This needs to be passed to your backend)'
+anonymous_id = '(This needs to be passed to your backend from the browser/JS)'
 
 analytics.track(user_id, 'Test', {}, anonymous_id=anonymous_id, integrations={
     'Google Analytics': {

diff --git a/2_workaround.js b/2_workaround.js
@@ -16,8 +16,8 @@ function hash(str) {
 // https://segment.com/docs/connections/sources/catalog/libraries/website/javascript/middleware/
 const segmentSourceMiddleware = function({ payload, next, integrations }) {
   payload.obj.integrations['Google Analytics'] = {
-    // Segment ignores our custom clientId if it's not a string...
-    clientId: ""+hash(analytics.user().anonymousId())
+    // Segment ignores our custom clientId if it's not a string
+    clientId: String(hash(analytics.user().anonymousId()))
   };
   next(payload);
 };

diff --git a/3_workaround.py b/3_workaround.py
@@ -7,5 +7,12 @@ def hash(s):
     for c in reversed(list(struct.iter_unpack('H', s.encode('utf-16le')))):
         hash = (hash * 33) ^ c[0]
     return c_uint32(hash).value
-
-# TODO
+
+anonymous_id = '(This needs to be passed to your backend)'
+
+analytics.track(user_id, 'Test', {}, anonymous_id=anonymous_id, integrations={
+    'Google Analytics': {
+        # Segment ignores our custom clientId if it's not a string
+        'clientId': str(hash(anonymous_id || user_id))
+    }
+}
diff --git a/2_workaround.js b/2_workaround.js
@@ -11,6 +11,9 @@ function hash(str) {
   return hash >>> 0;
 }
 
+// Segment Source Middleware helps us here so that we don't have to 
+// customize each and every track(), page() etc.
+// https://segment.com/docs/connections/sources/catalog/libraries/website/javascript/middleware/
 const segmentSourceMiddleware = function({ payload, next, integrations }) {
   payload.obj.integrations['Google Analytics'] = {
     // Segment ignores our custom clientId if it's not a string...

diff --git a/3_workaround.py b/3_workaround.py
@@ -1,10 +1,11 @@
 # This matches the same hash function that Segment uses on their server-side GA integration
 # Ported to Python from https://github.com/darkskyapp/string-hash/blob/master/index.js
 def hash(s):
+    import struct
     from ctypes import c_uint32
     hash = 5381
-    for i in range(len(s) - 1, -1, -1):
-        hash = (hash * 33) ^ ord(s[i])
+    for c in reversed(list(struct.iter_unpack('H', s.encode('utf-16le')))):
+        hash = (hash * 33) ^ c[0]
     return c_uint32(hash).value
 
 # TODO
diff --git a/3_workaround.py b/3_workaround.py
@@ -1,5 +1,5 @@
-# This is the same hash function that Segment uses on their server-side GA integration
-# Ported from https://github.com/darkskyapp/string-hash/blob/master/index.js
+# This matches the same hash function that Segment uses on their server-side GA integration
+# Ported to Python from https://github.com/darkskyapp/string-hash/blob/master/index.js
 def hash(s):
     from ctypes import c_uint32
     hash = 5381

diff --git a/2_workaround.js b/2_workaround.js
@@ -1,8 +1,7 @@
-// In browser code with analytics.js, even for Google Analytics in Cloud Mode
+// In browser code with analytics.js when using a Google Analytics Destination in Cloud Mode
 
-// In Segment's Google Analytics server-side integration they do this:
-// This is the same hash that Segment uses on their server-side, from here:
-// From https://github.com/darkskyapp/string-hash/blob/master/index.js
+// This is the same hash function that Segment uses on their server-side GA integration
+// from https://github.com/darkskyapp/string-hash/blob/master/index.js
 function hash(str) {
   var hash = 5381,
       i    = str.length;

diff --git a/3_workaround.py b/3_workaround.py
@@ -1 +1,10 @@
-# coming soon
+# This is the same hash function that Segment uses on their server-side GA integration
+# Ported from https://github.com/darkskyapp/string-hash/blob/master/index.js
+def hash(s):
+    from ctypes import c_uint32
+    hash = 5381
+    for i in range(len(s) - 1, -1, -1):
+        hash = (hash * 33) ^ ord(s[i])
+    return c_uint32(hash).value
+
+# TODO
diff --git a/2_workaround.js b/2_workaround.js
@@ -14,7 +14,8 @@ function hash(str) {
 
 const segmentSourceMiddleware = function({ payload, next, integrations }) {
   payload.obj.integrations['Google Analytics'] = {
-    clientId: hash(analytics.user().anonymousId())
+    // Segment ignores our custom clientId if it's not a string...
+    clientId: ""+hash(analytics.user().anonymousId())
   };
   next(payload);
 };

diff --git a/1. Segment Google Analytics Issue.md b/1. Segment Google Analytics Issue.md
@@ -12,13 +12,13 @@ This is a problem even if you carefully pass `anonymousId`, `userId`, web page U
 
 ## Cause
 
-In Segment's Google Analytics server-side integration they do this:
+In Segment's Google Analytics server-side integration they do this to compute the value passed to GA's `cid` ("Client ID") field:
 
 `let cid = hash(facade.userId() || facade.anonymousId())`
 
-Where `hash` uses the [string-hash npm package](https://www.npmjs.com/package/string-hash)
+The `hash` they use is the [string-hash npm package](https://www.npmjs.com/package/string-hash)
 
-But this makes it impossible to track users/sessions in GA from anonymous (marketing stie) to identified (signed up in product)
+But because they _change_ this value as soon as a visitor is given a `userId`, this makes it impossible to track users/sessions in GA from anonymous (marketing stie) to identified (signed up in product)
 
 Segment incorrectly prefers sending a `clientId`/`cid` to Google Analytics based on the Segment `userId` (if present) rather 
 than preferring their `anonymousId` which would fix that problem and more appropriately use the fields outlined by 
@@ -30,6 +30,8 @@ Segment needs to update their Google Analytics server-side integration to be lik
 
 `let cid = hash(facade.anonymousId() || facade.userId())`
 
+This would allow for consistent tracking in GA from anonymous to identified. There is already a _separate_ field/option to pass User ID directly to GA, so there's no reason to prefer `userId` here when both are passed.
+
 Segment has indicated that the more customers complain about this, the more likely they are to make this change. 
 Currently they haven't committed to making any change :(
 

diff --git a/3_workaround.py b/3_workaround.py
@@ -0,0 +1 @@
+# coming soon
diff --git a/1. Segment Google Analytics Issue.md b/1. Segment Google Analytics Issue.md
@@ -2,7 +2,13 @@
 
 ## Problem
 
-** more details about use case coming soon **
+If you use Segment's Google Analytics server-side integrations, even if you follow **all** of their documentation / recommendation, it is impossible to properly track your visitors/sessions in GA from anonymous through identified.
+
+This means that if you use Segment like this, you cannot do very basic things in GA like understanding attribution of your product's sign ups. In GA, a brand new session is created for the identified users, which is not correct.
+
+This problem applies to using Segment on the web with analytics.js when the Google Analytics Destination is set to Cloud Mode, _or_ when using a true server-side Source such as Python/Ruby/Node.
+
+This is a problem even if you carefully pass `anonymousId`, `userId`, web page URL/title, and user's IP from your frontend to your backend and then to Segment following all their recommendations.
 
 ## Cause
 

diff --git a/Background.md → 1. Segment Google Analytics Issue.md b/Background.md → 1. Segment Google Analytics Issue.md
@@ -1,10 +1,10 @@
-## Overview
+# Overview
 
-# Problem
+## Problem
 
 ** more details about use case coming soon **
 
-# Cause
+## Cause
 
 In Segment's Google Analytics server-side integration they do this:
 
@@ -18,15 +18,15 @@ Segment incorrectly prefers sending a `clientId`/`cid` to Google Analytics based
 than preferring their `anonymousId` which would fix that problem and more appropriately use the fields outlined by 
 [Google Analytics API documentation here](https://developers.google.com/analytics/devguides/collection/protocol/v1/parameters#user)
 
-# Solution
+## Solution
 
 Segment needs to update their Google Analytics server-side integration to be like this:
 
 `let cid = hash(facade.anonymousId() || facade.userId())`
 
 Segment has indicated that the more customers complain about this, the more likely they are to make this change. 
-Right now they haven't committed to making any change :(
+Currently they haven't committed to making any change :(
 
-# Workaround
+## Workaround
 
 See code snippets below.
diff --git a/example.js → 2_workaround.js b/example.js → 2_workaround.js
diff --git a/example.js b/example.js
@@ -20,3 +20,7 @@ const segmentSourceMiddleware = function({ payload, next, integrations }) {
 };
 
 analytics.addSourceMiddleware(segmentSourceMiddleware);
+
+// Then you can use analytics.js like normal:
+analytics.track('Test');
+
diff --git a/Background.md b/Background.md
@@ -0,0 +1,32 @@
+## Overview
+
+# Problem
+
+** more details about use case coming soon **
+
+# Cause
+
+In Segment's Google Analytics server-side integration they do this:
+
+`let cid = hash(facade.userId() || facade.anonymousId())`
+
+Where `hash` uses the [string-hash npm package](https://www.npmjs.com/package/string-hash)
+
+But this makes it impossible to track users/sessions in GA from anonymous (marketing stie) to identified (signed up in product)
+
+Segment incorrectly prefers sending a `clientId`/`cid` to Google Analytics based on the Segment `userId` (if present) rather 
+than preferring their `anonymousId` which would fix that problem and more appropriately use the fields outlined by 
+[Google Analytics API documentation here](https://developers.google.com/analytics/devguides/collection/protocol/v1/parameters#user)
+
+# Solution
+
+Segment needs to update their Google Analytics server-side integration to be like this:
+
+`let cid = hash(facade.anonymousId() || facade.userId())`
+
+Segment has indicated that the more customers complain about this, the more likely they are to make this change. 
+Right now they haven't committed to making any change :(
+
+# Workaround
+
+See code snippets below.
diff --git a/example.js b/example.js
@@ -0,0 +1,22 @@
+// In browser code with analytics.js, even for Google Analytics in Cloud Mode
+
+// In Segment's Google Analytics server-side integration they do this:
+// This is the same hash that Segment uses on their server-side, from here:
+// From https://github.com/darkskyapp/string-hash/blob/master/index.js
+function hash(str) {
+  var hash = 5381,
+      i    = str.length;
+  while(i) {
+    hash = (hash * 33) ^ str.charCodeAt(--i);
+  }
+  return hash >>> 0;
+}
+
+const segmentSourceMiddleware = function({ payload, next, integrations }) {
+  payload.obj.integrations['Google Analytics'] = {
+    clientId: hash(analytics.user().anonymousId())
+  };
+  next(payload);
+};
+
+analytics.addSourceMiddleware(segmentSourceMiddleware);
No results found