Release snowplow media player/0.9.1

CHANGELOG

@@ -1,3 +1,19 @@
+snowplow-media-player 0.9.1 (2024-10-23)
+---------------------------------------
+## Summary
+This patch release adds app_id as a new field in some of the derived tables and includes a bug fix related to user identification handling in ad_views.
+
+## Features
+- Introduced app_id field across some of the derived tables to improve application-level analytics
+
+## Fix
+- Optimized user_id aggregation, changed from GROUP BY to MAX(user_id) in queries in ad_view, because it could cause duplicates in an edge case.
+
+## Upgrading
+To upgrade, update the snowplow-media-player version in your `packages.yml` file. Please note:
+- The new app_id field will be populated for new data points automatically
+- Although this is a non-breaking change, historical data will require a [full refresh](https://docs.snowplow.io/docs/modeling-your-data/modeling-your-data-with-dbt/dbt-operation/full-or-partial-refreshes/) to include app_id values, if needed
+
 snowplow-media-player 0.9.0 (2024-10-15)
 ---------------------------------------
 ## Summary

dbt_project.yml

@@ -1,5 +1,5 @@
 name: 'snowplow_media_player'
-version: '0.9.0'
+version: '0.9.1'
 config-version: 2
 
 require-dbt-version: ['>=1.4.0', '<2.0.0']

integration_tests/dbt_project.yml

@@ -1,5 +1,5 @@
 name: 'snowplow_media_player_integration_tests'
-version: '0.9.0'
+version: '0.9.1'
 config-version: 2
 
 profile: 'integration_tests'

models/base/scratch/base_scratch.yml

@@ -42,6 +42,8 @@ models:
         description: '{{ doc("col_original_session_identifier") }}'
       - name: session_identifier
         description: '{{ doc("col_session_identifier") }}'
+      - name: app_id
+        description: '{{doc("col_app_id")}}'
       - name: user_identifier
         description: '{{ doc("col_user_identifier") }}'
       - name: media_identifier

models/media_ad_views/media_ad_views.yml

@@ -28,6 +28,8 @@ models:
         description: '{{ doc("col_user_id")}}'
       - name: session_identifier
         description: '{{ doc("col_session_identifier")}}'
+      - name: app_id
+        description: '{{doc("col_app_id")}}'
       - name: play_id
         description: '{{ doc("col_play_id")}}'
       - name: ad_break_id

models/media_ad_views/scratch/base_scratch.yml

@@ -27,6 +27,8 @@ models:
         description: '{{ doc("col_user_id")}}'
       - name: session_identifier
         description: '{{ doc("col_session_identifier")}}'
+      - name: app_id
+        description: '{{doc("col_app_id")}}'
       - name: domain_sessionid_array
         description: '{{ doc("col_domain_sessionid_array") }}'
       - name: play_id

models/media_ad_views/scratch/snowplow_media_player_media_ad_views_this_run.sql

@@ -39,7 +39,7 @@ events_this_run as (
     ,ev.media_identifier
     ,ev.user_identifier
     ,ev.session_identifier
-    ,ev.user_id
+    ,ev.app_id 
     ,ev.play_id
     ,ev.media_ad_break__break_id as ad_break_id
     ,ev.media_ad__ad_id as ad_id
@@ -57,7 +57,8 @@ events_this_run as (
       {%- endif -%}
       {% endfor -%}
     {%- endif %}
-
+
+    ,max(ev.user_id) as user_id
     ,max(ev.media_label) as media_label
     ,max(ev.media_ad_break__name) as ad_break_name
     ,max(ev.media_ad_break__break_type) as ad_break_type
@@ -80,9 +81,9 @@ events_this_run as (
     ,{{ snowplow_utils.get_string_agg('original_session_identifier', 'ev', is_distinct=True) }} as domain_sessionid_array
 
   from events_this_run as ev
-
   {{ dbt_utils.group_by(n=9+(var('snowplow__ad_views_passthroughs', [])|length)) }}
 
+
 )
 
 select
@@ -93,6 +94,7 @@ select
   ,p.media_label
   ,p.user_identifier
   ,p.session_identifier
+  ,p.app_id
   ,p.domain_sessionid_array
   ,p.user_id
   ,p.play_id

models/media_base/media_base.yml

@@ -24,6 +24,8 @@ models:
         description: '{{ doc("col_media_label") }}'
       - name: session_identifier
         description: '{{ doc("col_session_identifier") }}'
+      - name: app_id
+        description: '{{doc("col_app_id")}}'
       - name: domain_sessionid_array
         description: '{{ doc("col_domain_sessionid_array") }}'
       - name: user_identifier

models/media_base/scratch/base_scratch.yml

@@ -23,6 +23,8 @@ models:
         description: '{{ doc("col_media_label") }}'
       - name: session_identifier
         description: '{{ doc("col_session_identifier") }}'
+      - name: app_id
+        description: '{{doc("col_app_id")}}'
       - name: domain_sessionid_array
         description: '{{ doc("col_domain_sessionid_array") }}'
       - name: user_identifier

models/media_base/scratch/snowplow_media_player_base_this_run.sql

@@ -40,6 +40,7 @@ events_this_run as (
     ,i.player_id
     ,i.media_label
     ,i.session_identifier
+    ,i.app_id
     ,i.user_identifier
     ,i.user_id
     ,i.platform
@@ -86,7 +87,7 @@ events_this_run as (
 
   from events_this_run as i
 
-  {{ dbt_utils.group_by(n=17+(var('snowplow__base_passthroughs', [])|length)) }}
+  {{ dbt_utils.group_by(n=18+(var('snowplow__base_passthroughs', [])|length)) }}
 
 )
 
@@ -206,6 +207,7 @@ select
   d.player_id,
   d.media_label,
   d.session_identifier,
+  d.app_id,
   d.domain_sessionid_array,
   d.user_identifier,
   d.user_id,

models/media_plays/media_plays.yml

@@ -24,6 +24,8 @@ models:
         description: '{{ doc("col_media_label") }}'
       - name: session_identifier
         description: '{{ doc("col_session_identifier") }}'
+      - name: app_id
+        description: '{{doc("col_app_id")}}'
       - name: domain_sessionid_array
         description: '{{ doc("col_domain_sessionid_array") }}'
       - name: user_identifier