Merge pull request #20 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

@@ -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

@@ -1,8 +1,16 @@
-# dbt_snapchat_ads_source v0.UPDATE.UPDATE
+# dbt_snapchat_ads_source v0.6.0
+[PR #20](https://github.com/fivetran/dbt_snapchat_ads_source/pull/20) includes the following updates:
+## Feature update 🎉
+- Unioning capability! This adds the ability to union source data from multiple snapchat_ads connectors. Refer to the [Union Multiple Connectors README section](https://github.com/fivetran/dbt_snapchat_ads_source/blob/main/README.md#union-multiple-connectors) for more details.
 
-## Under the Hood:
-- Incorporated the new `fivetran_utils.drop_schemas_automation` macro into the end of each Buildkite integration test job. ([#17](https://github.com/fivetran/dbt_snapchat_ads_source/pull/17))
-- Updated the pull request [templates](/.github). ([#17](https://github.com/fivetran/dbt_snapchat_ads_source/pull/17))
+## 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.
+
+[PR #17](https://github.com/fivetran/dbt_snapchat_ads_source/pull/17) includes the following updates:
+- Incorporated the new `fivetran_utils.drop_schemas_automation` macro into the end of each Buildkite integration test job.
+- Updated the pull request [templates](/.github).
 
 # dbt_snapchat_ads_source v0.5.0
 ## 🚨 Breaking Changes 🚨:

README.md

@@ -40,7 +40,7 @@ If you  are **not** using the [Snapchat Ads transformation package](https://gith
 ```yaml
 packages:
   - package: fivetran/snapchat_ads_source
-    version: [">=0.5.0", "<0.6.0"] # we recommend using ranges to capture non-breaking changes automatically
+    version: [">=0.6.0", "<0.7.0"] # we recommend using ranges to capture non-breaking changes automatically
 ```
 ## Step 3: Configure your variables
 
@@ -54,7 +54,17 @@ vars:
 ```
 
 ## (Optional) Step 4: Additional configurations
-<details><summary>Expand for configurations</summary>
+### Union multiple connectors
+If you have multiple snapchat_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 `snapchat_ads_union_schemas` OR `snapchat_ads_union_databases` variables (cannot do both) in your root `dbt_project.yml` file:
+
+```yml
+vars:
+    snapchat_ads_union_schemas: ['snapchat_ads_usa','snapchat_ads_canada'] # use this if the data is in different schemas/datasets of the same database/project
+    snapchat_ads_union_databases: ['snapchat_ads_usa','snapchat_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:
@@ -91,8 +101,6 @@ models:
       +schema: my_new_schema_name # leave blank for just the target_schema
 ```
 
-</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: 'snapchat_ads_source'
-version: '0.5.0'
+version: '0.6.0'
 config-version: 2
 require-dbt-version: [">=1.3.0", "<2.0.0"]
 vars:

integration_tests/ci/sample.profiles.yml

@@ -45,10 +45,10 @@ integration_tests:
       schema: snapchat_ads_source_integration_tests
       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: snapchat_ads_source_integration_tests
-      threads: 2
+      threads: 8
       token: "{{ env_var('CI_DATABRICKS_DBT_TOKEN') }}"
       type: databricks

integration_tests/dbt_project.yml

@@ -1,6 +1,6 @@
 name: 'snapchat_ads_source_integration_tests'
 
-version: '0.5.0'
+version: '0.6.0'
 profile: 'integration_tests'
 config-version: 2
 

models/docs.md

@@ -1,3 +1,7 @@
 {% docs _fivetran_synced -%} When the record was last synced by Fivetran. {%- enddocs %}
 
-{% docs is_most_recent_record %} Boolean representing whether a record is the most recent version of that record. {% enddocs %}
+{% docs is_most_recent_record %} Boolean representing whether a record is the most recent version of that record. {% enddocs %}
+
+{% 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_snapchat.yml

@@ -1,7 +1,7 @@
 version: 2
 
 sources:
-  - name: snapchat_ads
+  - name: snapchat_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.
     schema: "{{ var('snapchat_ads_schema', 'snapchat_ads') }}"
     database: "{% if target.type != 'spark'%}{{ var('snapchat_ads_database', target.database) }}{% endif %}"
     loader: Fivetran

models/stg_snapchat.yml

@@ -6,9 +6,12 @@ models:
     tests:
       - dbt_utils.unique_combination_of_columns:
           combination_of_columns:
+            - source_relation
             - ad_account_id
             - _fivetran_synced 
     columns:
+      - name: source_relation
+        description: "{{ doc('source_relation') }}"
       - name: _fivetran_synced
         description: "{{ doc('_fivetran_synced') }}"
         tests:
@@ -37,9 +40,12 @@ models:
     tests:
       - dbt_utils.unique_combination_of_columns:
           combination_of_columns:
+            - source_relation
             - ad_id
             - _fivetran_synced 
     columns:
+      - name: source_relation
+        description: "{{ doc('source_relation') }}"
       - name: _fivetran_synced
         description: "{{ doc('_fivetran_synced') }}"
         tests:
@@ -66,9 +72,12 @@ models:
     tests:
       - dbt_utils.unique_combination_of_columns:
           combination_of_columns:
+            - source_relation
             - ad_id
             - date_hour 
     columns:
+      - name: source_relation
+        description: "{{ doc('source_relation') }}"
       - name: ad_id
         description: The ID of the ad that the report relates to in Snapchat.
         tests:
@@ -117,9 +126,12 @@ models:
     tests:
       - dbt_utils.unique_combination_of_columns:
           combination_of_columns:
+            - source_relation
             - ad_squad_id
             - _fivetran_synced 
     columns:
+      - name: source_relation
+        description: "{{ doc('source_relation') }}"
       - name: _fivetran_synced
         description: "{{ doc('_fivetran_synced') }}"
         tests:
@@ -144,9 +156,12 @@ models:
     tests:
       - dbt_utils.unique_combination_of_columns:
           combination_of_columns:
+            - source_relation
             - ad_squad_id
             - date_hour 
     columns:
+      - name: source_relation
+        description: "{{ doc('source_relation') }}"
       - name: ad_squad_id
         description: ID of the ad squad.
         tests:
@@ -195,9 +210,12 @@ models:
     tests:
       - dbt_utils.unique_combination_of_columns:
           combination_of_columns:
+            - source_relation
             - campaign_id
             - _fivetran_synced 
     columns:
+      - name: source_relation
+        description: "{{ doc('source_relation') }}"
       - name: _fivetran_synced
         description: "{{ doc('_fivetran_synced') }}"
         tests:
@@ -222,9 +240,12 @@ models:
     tests:
       - dbt_utils.unique_combination_of_columns:
           combination_of_columns:
+            - source_relation
             - campaign_id
             - date_hour 
     columns:
+      - name: source_relation
+        description: "{{ doc('source_relation') }}"
       - name: campaign_id
         description: ID of campaign
         tests:
@@ -273,9 +294,12 @@ models:
     tests:
       - dbt_utils.unique_combination_of_columns:
           combination_of_columns:
+            - source_relation
             - creative_id
             - _fivetran_synced 
     columns:
+      - name: source_relation
+        description: "{{ doc('source_relation') }}"
       - name: _fivetran_synced
         description: "{{ doc('_fivetran_synced') }}"
         tests:
@@ -302,10 +326,13 @@ models:
     tests:
       - dbt_utils.unique_combination_of_columns:
           combination_of_columns:
+            - source_relation
             - creative_id
             - param_key
             - updated_at
     columns:
+      - name: source_relation
+        description: "{{ doc('source_relation') }}"
       - name: creative_id
         description: The ID of the related creative in Snapchat.
         tests:

models/stg_snapchat_ads__ad_account_history.sql

@@ -15,12 +15,19 @@ fields as (
                 staging_columns=get_ad_account_history_columns()
             )
         }}
+
+        {{ fivetran_utils.source_relation(
+            union_schema_variable='snapchat_ads_union_schemas', 
+            union_database_variable='snapchat_ads_union_databases') 
+        }}
+
     from base
 ),
 
 final as (
-
-    select 
+
+    select
+        source_relation, 
         id as ad_account_id,
         name as ad_account_name,
         cast (created_at as {{ dbt.type_timestamp() }}) as created_at,
@@ -29,7 +36,7 @@ final as (
         timezone,
         cast (_fivetran_synced as {{ dbt.type_timestamp() }}) as _fivetran_synced,
         cast (updated_at as {{ dbt.type_timestamp() }}) as updated_at,
-        row_number() over (partition by id order by _fivetran_synced desc) = 1 as is_most_recent_record
+        row_number() over (partition by source_relation, id order by _fivetran_synced desc) = 1 as is_most_recent_record
     from fields
 )
 

models/stg_snapchat_ads__ad_history.sql

@@ -15,20 +15,27 @@ fields as (
                 staging_columns=get_ad_history_columns()
             )
         }}
+
+        {{ fivetran_utils.source_relation(
+            union_schema_variable='snapchat_ads_union_schemas', 
+            union_database_variable='snapchat_ads_union_databases') 
+        }}
+
     from base
 ),
 
 final as (
-
-    select 
+
+    select
+        source_relation, 
         id as ad_id,
         name as ad_name,
         cast (created_at as {{ dbt.type_timestamp() }}) as created_at,
         ad_squad_id,
         creative_id,
         cast (_fivetran_synced as {{ dbt.type_timestamp() }}) as _fivetran_synced,
         cast (updated_at as {{ dbt.type_timestamp() }}) as updated_at,
-        row_number() over (partition by id order by _fivetran_synced desc) = 1 as is_most_recent_record
+        row_number() over (partition by source_relation, id order by _fivetran_synced desc) = 1 as is_most_recent_record
     from fields
 )
 

models/stg_snapchat_ads__ad_hourly_report.sql

@@ -15,12 +15,19 @@ fields as (
                 staging_columns=get_ad_hourly_report_columns()
             )
         }}        
+
+        {{ fivetran_utils.source_relation(
+            union_schema_variable='snapchat_ads_union_schemas', 
+            union_database_variable='snapchat_ads_union_databases') 
+        }}
+
     from base
 ),
 
 final as (
-
-    select 
+
+    select
+        source_relation, 
         ad_id,
         cast (date as {{ dbt.type_timestamp() }}) as date_hour,
         attachment_quartile_1,

models/stg_snapchat_ads__ad_squad_history.sql

@@ -15,19 +15,26 @@ fields as (
                 staging_columns=get_ad_squad_history_columns()
             )
         }}
+
+        {{ fivetran_utils.source_relation(
+            union_schema_variable='snapchat_ads_union_schemas', 
+            union_database_variable='snapchat_ads_union_databases') 
+        }}
+
     from base
 ),
 
 final as (
 
-    select 
+    select
+        source_relation, 
         id as ad_squad_id,
         name as ad_squad_name,
         cast (created_at as {{ dbt.type_timestamp() }}) as created_at,
         campaign_id,
         cast (_fivetran_synced as {{ dbt.type_timestamp() }}) as _fivetran_synced,
         cast (updated_at as {{ dbt.type_timestamp() }}) as updated_at,
-        row_number() over (partition by id order by _fivetran_synced desc) = 1 as is_most_recent_record
+        row_number() over (partition by source_relation, id order by _fivetran_synced desc) = 1 as is_most_recent_record
     from fields
 )
 

models/stg_snapchat_ads__ad_squad_hourly_report.sql

@@ -15,12 +15,19 @@ fields as (
                 staging_columns=get_ad_squad_hourly_report_columns()
             )
         }}        
+
+        {{ fivetran_utils.source_relation(
+            union_schema_variable='snapchat_ads_union_schemas', 
+            union_database_variable='snapchat_ads_union_databases') 
+        }}
+
     from base
 ),
 
 final as (
-
-    select 
+
+    select
+        source_relation, 
         ad_squad_id,
         cast (date as {{ dbt.type_timestamp() }}) as date_hour,
         attachment_quartile_1,