Merge pull request #45 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 +1,20 @@
+# dbt_apple_search_ads_source v0.3.0
+[PR #45](https://github.com/fivetran/dbt_apple_search_ads_source/pull/45) includes the following updates:
+## Breaking changes
+- Updated the source identifier format for consistency with their respective source names and compatibility with the `fivetran_utils.union_data` macro. If you are using the previous identifier, be sure to update to the current version! Identifiers now are:
+
+| current  | previous |
+|----------|----------|
+|apple_search_ads_ad_level_report_identifier | apple_search_ads_ad_report_identifier |
+
+## Feature update 🎉
+- Unioning capability! This adds the ability to union source data from multiple apple_search_ads connectors. Refer to the [Union Multiple Connectors README section](https://github.com/fivetran/dbt_apple_search_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_apple_search_ads_source v0.2.2
 ## Bug Fix
 - The `apple_search_ads__search_term_passthrough_metrics` variable was moved to be within the return call of the `get_search_term_report_columns` macro. The previous placement caused an issue where the passthrough metrics would not properly persist to downstream models. ([PR #42](https://github.com/fivetran/dbt_apple_search_ads_source/pull/42))

README.md

@@ -39,7 +39,7 @@ If you  are **not** using the [Apple Search Ads transformation package](https://
 ```yaml
 packages:
   - package: fivetran/apple_search_ads_source
-    version: [">=0.2.0", "<0.3.0"] # we recommend using ranges to capture non-breaking changes automatically
+    version: [">=0.3.0", "<0.4.0"] # we recommend using ranges to capture non-breaking changes automatically
 ```
 ## Step 3: Define database and schema variables
 By default, this package runs using your destination and the `apple_search_ads` schema. If this is not where your Apple Search Ads data is (for example, if your Apple Search Ads schema is named `apple_search_ads_fivetran`), add the following configuration to your root `dbt_project.yml` file:
@@ -51,7 +51,17 @@ vars:
 ```
 
 ## (Optional) Step 4: Additional configurations
-<details><summary>Expand for configurations</summary>
+### Union multiple connectors
+If you have multiple apple_search_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 `apple_search_ads_union_schemas` OR `apple_search_ads_union_databases` variables (cannot do both) in your root `dbt_project.yml` file:
+
+```yml
+vars:
+    apple_search_ads_union_schemas: ['apple_search_ads_usa','apple_search_ads_canada'] # use this if the data is in different schemas/datasets of the same database/project
+    apple_search_ads_union_databases: ['apple_search_ads_usa','apple_search_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:
@@ -108,8 +118,6 @@ vars:
     apple_search_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: 'apple_search_ads_source'
-version: '0.2.2'
+version: '0.3.0'
 
 config-version: 2
 require-dbt-version: [">=1.3.0", "<2.0.0"]

integration_tests/ci/sample.profiles.yml

@@ -45,10 +45,10 @@ integration_tests:
       schema: apple_ads_source_integrations_tests_1
       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: apple_ads_source_integrations_tests_1
-      threads: 2
+      threads: 8
       token: "{{ env_var('CI_DATABRICKS_DBT_TOKEN') }}"
       type: databricks

integration_tests/dbt_project.yml

@@ -1,7 +1,7 @@
 config-version: 2
 
 name: 'apple_search_ads_source_integration_tests'
-version: '0.2.2'
+version: '0.3.0'
 
 profile: 'integration_tests' 
 
@@ -13,7 +13,7 @@ vars:
   apple_search_ads_ad_group_history_identifier: "ad_group_history_data"
   apple_search_ads_ad_group_report_identifier: "ad_group_report_data"
   apple_search_ads_ad_history_identifier: "ad_history_data"
-  apple_search_ads_ad_report_identifier: "ad_report_data"
+  apple_search_ads_ad_level_report_identifier: "ad_report_data"
   apple_search_ads_keyword_history_identifier: "keyword_history_data"
   apple_search_ads_keyword_report_identifier: "keyword_report_data"
   apple_search_ads_search_term_report_identifier: "search_term_report_data"

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_apple_search_ads.yml

@@ -2,7 +2,7 @@
 version: 2
 
 sources:
-  - name: apple_search_ads
+  - name: apple_search_ads # This source will only be used if you are using a single apple_search_ads source connector. If multiple sources are being unioned, their tables will be directly referenced via adapter.get_relation.
     schema: "{{ var('apple_search_ads_schema', 'apple_search_ads') }}"
     database: "{% if target.type != 'spark' %}{{ var('apple_search_ads_database', target.database) }}{% endif %}"
 
@@ -82,7 +82,7 @@ sources:
 
       - name: ad_level_report
         description: Each record represents the daily performance of an ad in Apple Search Ads.
-        identifier: "{{ var('apple_search_ads_ad_report_identifier', 'ad_level_report') }}"
+        identifier: "{{ var('apple_search_ads_ad_level_report_identifier', 'ad_level_report') }}"
         columns:
           - name: date
             description: Date for daily report aggregation.

models/stg_apple_search_ads.yml

@@ -6,9 +6,12 @@ models:
     tests:
       - dbt_utils.unique_combination_of_columns:
           combination_of_columns:
+            - source_relation
             - ad_group_id
             - modified_at
     columns:
+      - name: source_relation
+        description: "{{ doc('source_relation') }}"
       - name: modified_at
         description: Timestamp of when the ad group object was last modified.
         tests:
@@ -37,9 +40,12 @@ models:
     tests:
       - dbt_utils.unique_combination_of_columns:
           combination_of_columns:
+            - source_relation
             - ad_group_id
             - date_day
     columns:
+      - name: source_relation
+        description: "{{ doc('source_relation') }}"
       - name: ad_group_id
         description: Ad group ID associated with the record.
         tests:
@@ -66,9 +72,12 @@ models:
     tests:
       - dbt_utils.unique_combination_of_columns:
           combination_of_columns:
+            - source_relation
             - ad_id
             - modified_at
     columns:
+      - name: source_relation
+        description: "{{ doc('source_relation') }}"
       - name: created_at
         description: Timestamp of when ad was created.
       - name: modified_at
@@ -95,10 +104,13 @@ models:
     tests:
       - dbt_utils.unique_combination_of_columns:
           combination_of_columns:
+            - source_relation
             - ad_id
             - date_day
             - ad_group_id
     columns:
+      - name: source_relation
+        description: "{{ doc('source_relation') }}"
       - name: date_day
         description: Date for daily report aggregation.
         tests:
@@ -131,9 +143,12 @@ models:
     tests:
       - dbt_utils.unique_combination_of_columns:
           combination_of_columns:
+            - source_relation
             - campaign_id
             - modified_at
     columns:
+      - name: source_relation
+        description: "{{ doc('source_relation') }}"
       - name: modified_at
         description: Timestamp of when the campaign object was last modified.
         tests:
@@ -160,9 +175,12 @@ models:
     tests:
       - dbt_utils.unique_combination_of_columns:
           combination_of_columns:
+            - source_relation
             - campaign_id
             - date_day
     columns:
+      - name: source_relation
+        description: "{{ doc('source_relation') }}"
       - name: campaign_id
         description: Campaign ID associated with the record.
         tests:
@@ -190,9 +208,12 @@ models:
     tests:
       - dbt_utils.unique_combination_of_columns:
           combination_of_columns:
+            - source_relation
             - keyword_id
             - modified_at
     columns:
+      - name: source_relation
+        description: "{{ doc('source_relation') }}"
       - name: modified_at
         description: Timestamp of when the keyword object was last modified.
         tests:
@@ -223,9 +244,12 @@ models:
     tests:
       - dbt_utils.unique_combination_of_columns:
           combination_of_columns:
+            - source_relation
             - keyword_id
             - date_day
     columns:
+      - name: source_relation
+        description: "{{ doc('source_relation') }}"
       - name: keyword_id
         description: Keyword ID associated with the record.
         tests:
@@ -252,8 +276,11 @@ models:
     tests:
       - dbt_utils.unique_combination_of_columns:
           combination_of_columns:
+            - source_relation
             - organization_id
     columns:
+      - name: source_relation
+        description: "{{ doc('source_relation') }}"
       - name: organization_id
         description: Organization ID associated with the record.
         tests:
@@ -272,9 +299,12 @@ models:
     tests:
       - dbt_utils.unique_combination_of_columns:
           combination_of_columns:
+            - source_relation
             - _fivetran_id
             - date_day
     columns:
+      - name: source_relation
+        description: "{{ doc('source_relation') }}"
       - name: _fivetran_id
         description: A Fivetran internal unique id that helps us avoid duplicate rows in primary keyless tables.
         tests:

models/stg_apple_search_ads__ad_group_history.sql

@@ -16,11 +16,19 @@ fields as (
             )
         }}
 
+
+        {{ fivetran_utils.source_relation(
+            union_schema_variable='apple_search_ads_union_schemas', 
+            union_database_variable='apple_search_ads_union_databases') 
+        }}
+
     from base
 ),
 
 final as (
-    select 
+
+    select
+        source_relation, 
         modification_time as modified_at,
         organization_id,
         campaign_id,
@@ -29,7 +37,7 @@ final as (
         status as ad_group_status,
         start_time as start_at,
         end_time as end_at,
-        row_number() over (partition by id order by modification_time desc) = 1 as is_most_recent_record
+        row_number() over (partition by source_relation, id order by modification_time desc) = 1 as is_most_recent_record
     from fields
 )
 

models/stg_apple_search_ads__ad_group_report.sql

@@ -15,12 +15,19 @@ fields as (
                 staging_columns=get_ad_group_report_columns()
             )
         }}
+
+        {{ fivetran_utils.source_relation(
+            union_schema_variable='apple_search_ads_union_schemas', 
+            union_database_variable='apple_search_ads_union_databases') 
+        }}
+
     from base
 ),
 
 final as (
-    
+
     select
+        source_relation,
         date as date_day, 
         ad_group_id,
         impressions,

models/stg_apple_search_ads__ad_history.sql

@@ -15,12 +15,19 @@ fields as (
                 staging_columns=get_ad_history_columns()
             )
         }}
+
+        {{ fivetran_utils.source_relation(
+            union_schema_variable='apple_search_ads_union_schemas', 
+            union_database_variable='apple_search_ads_union_databases') 
+        }}
+
     from base
 ),
 
 final as (
-
-    select 
+
+    select
+        source_relation, 
         creation_time as created_at,
         modification_time as modified_at,
         org_id as organization_id,
@@ -29,7 +36,7 @@ final as (
         name as ad_name,
         id as ad_id,
         status as ad_status, 
-        row_number() over (partition by id order by modification_time desc) = 1 as is_most_recent_record
+        row_number() over (partition by source_relation, id order by modification_time desc) = 1 as is_most_recent_record
     from fields
 )
 

models/stg_apple_search_ads__ad_report.sql

@@ -15,12 +15,19 @@ fields as (
                 staging_columns=get_ad_level_report_columns()
             )
         }}
+
+        {{ fivetran_utils.source_relation(
+            union_schema_variable='apple_search_ads_union_schemas', 
+            union_database_variable='apple_search_ads_union_databases') 
+        }}
+
     from base
 ),
 
 final as (
-
-    select 
+
+    select
+        source_relation, 
         date as date_day,
         campaign_id,
         ad_group_id,