Merge pull request #12 from fivetran/MagicBot/add-union-schema

Feature: Union schema compatibility

.buildkite/hooks/pre-command

@@ -21,4 +21,5 @@ export CI_SNOWFLAKE_DBT_USER=$(gcloud secrets versions access latest --secret="C
 export CI_SNOWFLAKE_DBT_WAREHOUSE=$(gcloud secrets versions access latest --secret="CI_SNOWFLAKE_DBT_WAREHOUSE" --project="dbt-package-testing-363917")
 export CI_DATABRICKS_DBT_HOST=$(gcloud secrets versions access latest --secret="CI_DATABRICKS_DBT_HOST" --project="dbt-package-testing-363917")
 export CI_DATABRICKS_DBT_HTTP_PATH=$(gcloud secrets versions access latest --secret="CI_DATABRICKS_DBT_HTTP_PATH" --project="dbt-package-testing-363917")
-export CI_DATABRICKS_DBT_TOKEN=$(gcloud secrets versions access latest --secret="CI_DATABRICKS_DBT_TOKEN" --project="dbt-package-testing-363917")
+export CI_DATABRICKS_DBT_TOKEN=$(gcloud secrets versions access latest --secret="CI_DATABRICKS_DBT_TOKEN" --project="dbt-package-testing-363917")
+export CI_DATABRICKS_DBT_CATALOG=$(gcloud secrets versions access latest --secret="CI_DATABRICKS_DBT_CATALOG" --project="dbt-package-testing-363917")

.buildkite/pipeline.yml

@@ -58,7 +58,7 @@ steps:
     commands: |
       bash .buildkite/scripts/run_models.sh redshift
 
-  - label: ":bricks: Run Tests - Databricks"
+  - label: ":databricks: Run Tests - Databricks"
     key: "run_dbt_databricks"
     plugins:
       - docker#v3.13.0:
@@ -69,5 +69,6 @@ steps:
             - "CI_DATABRICKS_DBT_HOST"
             - "CI_DATABRICKS_DBT_HTTP_PATH"
             - "CI_DATABRICKS_DBT_TOKEN"
+            - "CI_DATABRICKS_DBT_CATALOG"
     commands: |
       bash .buildkite/scripts/run_models.sh databricks

CHANGELOG.md

@@ -1,3 +1,28 @@
+# dbt_tiktok_ads_source v0.5.0
+[PR #12](https://github.com/fivetran/dbt_tiktok_ads_source/pull/12) includes the following updates:
+## Breaking changes
+- Updated the source identifier format for consistency with other packages and for compatibility with the `fivetran_utils.union_data` macro. Identifiers now are:
+
+| current  | previous |
+|----------|----------|
+|tiktok_ads_adgroup_history_identifier | tiktok_ads__ad_group_history_identifier |
+|tiktok_ads_ad_history_identifier | tiktok_ads__ad_history_identifier
+|tiktok_ads_advertiser_identifier | tiktok_ads__advertiser_identifier|
+|tiktok_ads_campaign_history_identifier | tiktok_ads__campaign_history_identifier|
+|tiktok_ads_ad_report_hourly_identifier | tiktok_ads__ad_report_hourly_identifier|
+|tiktok_ads_adgroup_report_hourly_identifier | tiktok_ads__ad_group_report_hourly_identifier|
+|tiktok_ads_campaign_report_hourly_identifier | tiktok_ads__campaign_report_hourly_identifier|
+
+- If you are using the previous identifier, be sure to update to the current version!
+
+## Feature update 🎉
+- Unioning capability! This adds the ability to union source data from multiple tiktok_ads connectors. Refer to the [Union Multiple Connectors README section](https://github.com/fivetran/dbt_tiktok_ads_source/blob/main/README.md#union-multiple-connectors) for more details.
+
+## Under the hood 🚘
+- Updated tmp models to union source data using the `fivetran_utils.union_data` macro. 
+- To distinguish which source each field comes from, added `source_relation` column in each staging model and applied the `fivetran_utils.source_relation` macro.
+- Updated tests to account for the new `source_relation` column.
+
 # dbt_tiktok_ads_source v0.4.0
 [PR #10](https://github.com/fivetran/dbt_tiktok_ads_source/pull/10) applies the following updates:
 ## 🚨 Breaking Changes 🚨

README.md

@@ -40,7 +40,7 @@ If you  are **not** using the [Tiktok transformation package](https://github.com
 ```yaml
 packages:
   - package: fivetran/tiktok_ads_source
-    version: [">=0.4.0", "<0.5.0"]
+    version: [">=0.5.0", "<0.6.0"]
 ```
 
 ## Step 3: Define database and schema variables
@@ -53,7 +53,17 @@ vars:
 ```
 
 ## (Optional) Step 4: Additional configurations
-<details><summary>Expand for configurations</summary>
+### Union multiple connectors
+If you have multiple tiktok_ads connectors in Fivetran and would like to use this package on all of them simultaneously, we have provided functionality to do so. The package will union all of the data together and pass the unioned table into the transformations. You will be able to see which source it came from in the `source_relation` column of each model. To use this functionality, you will need to set either the `tiktok_ads_union_schemas` OR `tiktok_ads_union_databases` variables (cannot do both) in your root `dbt_project.yml` file:
+
+```yml
+vars:
+    tiktok_ads_union_schemas: ['tiktok_ads_usa','tiktok_ads_canada'] # use this if the data is in different schemas/datasets of the same database/project
+    tiktok_ads_union_databases: ['tiktok_ads_usa','tiktok_ads_canada'] # use this if the data is in different databases/projects but uses the same schema name
+```
+Please be aware that the native `source.yml` connection set up in the package will not function when the union schema/database feature is utilized. Although the data will be correctly combined, you will not observe the sources linked to the package models in the Directed Acyclic Graph (DAG). This happens because the package includes only one defined `source.yml`.
+
+To connect your multiple schema/database sources to the package models, follow the steps outlined in the [Union Data Defined Sources Configuration](https://github.com/fivetran/dbt_fivetran_utils/tree/releases/v0.4.latest#union_data-source) section of the Fivetran Utils documentation for the union_data macro. This will ensure a proper configuration and correct visualization of connections in the DAG.
 
 ### Passing Through Additional Metrics
 By default, this package will select `clicks`, `impressions`, and `cost` from the source reporting tables to store into the staging models. If you would like to pass through additional metrics to the staging models, add the below configurations to your `dbt_project.yml` file. These variables allow for the pass-through fields to be aliased (`alias`) if desired, but not required. Use the below format for declaring the respective pass-through variables:
@@ -93,8 +103,6 @@ vars:
     tiktok_ads_<default_source_table_name>_identifier: your_table_name 
 ```
 
-</details>
-
 ## (Optional) Step 5: Orchestrate your models with Fivetran Transformations for dbt Core™
 <details><summary>Expand for more details</summary>
 

dbt_project.yml

@@ -1,5 +1,5 @@
 name: 'tiktok_ads_source'
-version: '0.4.0'
+version: '0.5.0'
 config-version: 2
 require-dbt-version: [">=1.3.0", "<2.0.0"]
 models:

integration_tests/ci/sample.profiles.yml

@@ -45,10 +45,10 @@ integration_tests:
       schema: tiktok_ads_source_integration_tests_2
       threads: 8
     databricks:
-      catalog: null
+      catalog: "{{ env_var('CI_DATABRICKS_DBT_CATALOG') }}"
       host: "{{ env_var('CI_DATABRICKS_DBT_HOST') }}"
       http_path: "{{ env_var('CI_DATABRICKS_DBT_HTTP_PATH') }}"
       schema: tiktok_ads_source_integration_tests_2
-      threads: 2
+      threads: 8
       token: "{{ env_var('CI_DATABRICKS_DBT_TOKEN') }}"
       type: databricks

integration_tests/dbt_project.yml

@@ -1,18 +1,18 @@
 name: 'tiktok_ads_source_integration_tests'
-version: '0.4.0'
+version: '0.5.0'
 profile: 'integration_tests'
 config-version: 2
 
 vars: 
   tiktok_ads_source:
     tiktok_ads_schema: tiktok_ads_source_integration_tests_2
-    tiktok_ads__ad_group_history_identifier: "tiktok_adgroup_history_data"
-    tiktok_ads__ad_history_identifier: "tiktok_ad_history_data"
-    tiktok_ads__advertiser_identifier: "tiktok_advertiser_data"
-    tiktok_ads__campaign_history_identifier: "tiktok_campaign_history_data"
-    tiktok_ads__ad_report_hourly_identifier: "tiktok_ad_report_hourly_data"
-    tiktok_ads__ad_group_report_hourly_identifier: "tiktok_adgroup_report_hourly_data"
-    tiktok_ads__campaign_report_hourly_identifier: "tiktok_campaign_report_hourly_data"
+    tiktok_ads_adgroup_history_identifier: "tiktok_adgroup_history_data"
+    tiktok_ads_ad_history_identifier: "tiktok_ad_history_data"
+    tiktok_ads_advertiser_identifier: "tiktok_advertiser_data"
+    tiktok_ads_campaign_history_identifier: "tiktok_campaign_history_data"
+    tiktok_ads_ad_report_hourly_identifier: "tiktok_ad_report_hourly_data"
+    tiktok_ads_adgroup_report_hourly_identifier: "tiktok_adgroup_report_hourly_data"
+    tiktok_ads_campaign_report_hourly_identifier: "tiktok_campaign_report_hourly_data"
 
 
 seeds:

models/docs.md

@@ -0,0 +1,3 @@
+{% docs source_relation %}
+The source of the record if the unioning functionality is being used. If not this field will be empty.
+{% enddocs %}

models/src_tiktok_ads.yml

@@ -1,7 +1,7 @@
 version: 2
 
 sources:
-  - name: tiktok_ads
+  - name: tiktok_ads # This source will only be used if you are using a single tiktok_ads source connector. If multiple sources are being unioned, their tables will be directly referenced via adapter.get_relation.
     database: "{% if target.type != 'spark' %}{{var('tiktok_ads_database', target.database)}}{% endif %}"
     schema: "{{var('tiktok_ads_schema', 'tiktok_ads')}}"
 
@@ -17,7 +17,7 @@ sources:
 
     tables:
       - name: advertiser
-        identifier: "{{ var('tiktok_ads__advertiser_identifier', 'advertiser') }}"
+        identifier: "{{ var('tiktok_ads_advertiser_identifier', 'advertiser') }}"
         description: Each record represents data for one advertiser.
         columns:
           - name: id
@@ -82,7 +82,7 @@ sources:
             description: Timestamp of when Fivetran synced a record. 
 
       - name: campaign_history
-        identifier: "{{ var('tiktok_ads__campaign_history_identifier', 'campaign_history') }}"
+        identifier: "{{ var('tiktok_ads_campaign_history_identifier', 'campaign_history') }}"
         description: Each record represents a version of a TikTok campaign.
         columns:
           - name: campaign_id
@@ -113,7 +113,7 @@ sources:
             description: Split Test variables. Optional values; TARGETING, BIDDING_OPTIMIZATION , CREATIVE.
 
       - name: adgroup_history
-        identifier: "{{ var('tiktok_ads__ad_group_history_identifier', 'adgroup_history') }}"
+        identifier: "{{ var('tiktok_ads_adgroup_history_identifier', 'adgroup_history') }}"
         description: Each record represents a version of a TikTok ad group.
         columns:
           - name: adgroup_id
@@ -272,7 +272,7 @@ sources:
             description: Whether users can download your video ads on TikTok(cannot be updated once created). 
 
       - name: ad_history
-        identifier: "{{ var('tiktok_ads__ad_history_identifier', 'ad_history') }}"
+        identifier: "{{ var('tiktok_ads_ad_history_identifier', 'ad_history') }}"
         description: Each record represents a version of a TikTok ad.
         columns:
           - name: ad_id
@@ -327,7 +327,7 @@ sources:
             description: The video ID.
 
       - name: ad_report_hourly
-        identifier: "{{ var('tiktok_ads__ad_report_hourly_identifier', 'ad_report_hourly') }}"
+        identifier: "{{ var('tiktok_ads_ad_report_hourly_identifier', 'ad_report_hourly') }}"
         description: Each record represents data for each ad for each hour.
         columns:
           - name: ad_id
@@ -445,7 +445,7 @@ sources:
             description: Timestamp of when Fivetran synced a record. 
 
       - name: campaign_report_hourly
-        identifier: "{{ var('tiktok_ads__campaign_report_hourly_identifier', 'campaign_report_hourly') }}"
+        identifier: "{{ var('tiktok_ads_campaign_report_hourly_identifier', 'campaign_report_hourly') }}"
         description: Each record represents data for each campaign for each hour.
         columns:
           - name: campaign_id
@@ -565,7 +565,7 @@ sources:
             description: Timestamp of when Fivetran synced a record. 
 
       - name: adgroup_report_hourly
-        identifier: "{{ var('tiktok_ads__ad_group_report_hourly_identifier', 'adgroup_report_hourly') }}"
+        identifier: "{{ var('tiktok_ads_adgroup_report_hourly_identifier', 'adgroup_report_hourly') }}"
         description: Each record represents data for each ad group for each hour.
         columns:
           - name: adgroup_id

models/stg_tiktok_ads.yml

@@ -1,15 +1,19 @@
-
-
 version: 2
 
 models:
   - name: stg_tiktok_ads__advertiser
     description: Each record represents data for each advertiser.
+    tests:
+      - dbt_utils.unique_combination_of_columns:
+          combination_of_columns:
+            - source_relation
+            - advertiser_id
     columns:
+      - name: source_relation
+        description: "{{ doc('source_relation') }}"
       - name: advertiser_id
         description: Advertiser ID
         tests:
-          - unique
           - not_null
       - name: address
         description: Advertiser address information
@@ -52,9 +56,12 @@ models:
     tests:
       - dbt_utils.unique_combination_of_columns:
           combination_of_columns:
+            - source_relation
             - ad_group_id
             - updated_at 
     columns:
+      - name: source_relation
+        description: "{{ doc('source_relation') }}"
       - name: ad_group_id
         description: Ad group ID
         tests:
@@ -103,9 +110,12 @@ models:
     tests:
       - dbt_utils.unique_combination_of_columns:
           combination_of_columns:
+            - source_relation
             - ad_id
             - updated_at
     columns:
+      - name: source_relation
+        description: "{{ doc('source_relation') }}"
       - name: ad_id
         description: Ad ID
         tests:
@@ -153,9 +163,12 @@ models:
     tests:
       - dbt_utils.unique_combination_of_columns:
           combination_of_columns:
+            - source_relation
             - campaign_id
             - updated_at
     columns:
+      - name: source_relation
+        description: "{{ doc('source_relation') }}"
       - name: campaign_id
         description: Campaign ID
         tests:
@@ -179,9 +192,12 @@ models:
     tests:
       - dbt_utils.unique_combination_of_columns:
           combination_of_columns:
+            - source_relation
             - ad_id
             - stat_time_hour
     columns:
+      - name: source_relation
+        description: "{{ doc('source_relation') }}"
       - name: ad_id
         description: Ad id
         tests:
@@ -254,9 +270,12 @@ models:
     tests:
       - dbt_utils.unique_combination_of_columns:
           combination_of_columns:
+            - source_relation
             - ad_group_id
             - stat_time_hour
     columns:
+      - name: source_relation
+        description: "{{ doc('source_relation') }}"
       - name: ad_group_id
         description: Ad group id
         tests:
@@ -329,9 +348,12 @@ models:
     tests:
       - dbt_utils.unique_combination_of_columns:
           combination_of_columns:
+            - source_relation
             - campaign_id
             - stat_time_hour
     columns:
+      - name: source_relation
+        description: "{{ doc('source_relation') }}"
       - name: campaign_id
         description: Campaign id
         tests:

models/stg_tiktok_ads__ad_group_history.sql

@@ -16,12 +16,19 @@ fields as (
             )
         }}
 
+
+        {{ fivetran_utils.source_relation(
+            union_schema_variable='tiktok_ads_union_schemas', 
+            union_database_variable='tiktok_ads_union_databases') 
+        }}
+
     from base
 ), 
 
 final as (
 
     select
+        source_relation,
         adgroup_id as ad_group_id,
         cast(updated_at as {{ dbt.type_timestamp() }}) as updated_at,
         advertiser_id,
@@ -40,7 +47,7 @@ final as (
         gender,
         languages, 
         landing_page_url,
-        row_number() over (partition by adgroup_id order by updated_at desc) = 1 as is_most_recent_record
+        row_number() over (partition by source_relation, adgroup_id order by updated_at desc) = 1 as is_most_recent_record
     from fields
 )
 

models/stg_tiktok_ads__ad_group_report_hourly.sql

@@ -15,12 +15,19 @@ fields as (
                 staging_columns=get_ad_group_report_hourly_columns()
             )
         }}
+
+        {{ fivetran_utils.source_relation(
+            union_schema_variable='tiktok_ads_union_schemas', 
+            union_database_variable='tiktok_ads_union_databases') 
+        }}
+
     from base
 ), 
 
 final as (
 
-    select  
+    select
+        source_relation,  
         adgroup_id as ad_group_id,
         cast(stat_time_hour as {{ dbt.type_timestamp() }}) as stat_time_hour, 
         cpc, 

models/stg_tiktok_ads__ad_history.sql

@@ -16,12 +16,19 @@ fields as (
             )
         }}
 
+
+        {{ fivetran_utils.source_relation(
+            union_schema_variable='tiktok_ads_union_schemas', 
+            union_database_variable='tiktok_ads_union_databases') 
+        }}
+
     from base
 ), 
 
 final as (
 
-    select  
+    select
+        source_relation,  
         ad_id,
         cast(updated_at as {{ dbt.type_timestamp() }}) as updated_at,
         adgroup_id as ad_group_id,
@@ -40,7 +47,7 @@ final as (
         {{ dbt_utils.get_url_parameter('landing_page_url', 'utm_content') }} as utm_content,
         {{ dbt_utils.get_url_parameter('landing_page_url', 'utm_term') }} as utm_term,
         landing_page_url,
-        row_number() over (partition by ad_id order by updated_at desc) = 1 as is_most_recent_record
+        row_number() over (partition by source_relation, ad_id order by updated_at desc) = 1 as is_most_recent_record
     from fields
 )