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

@@ -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 +1,14 @@
+# dbt_apple_search_ads v0.3.0
+[PR #20](https://github.com/fivetran/dbt_apple_search_ads/pull/20) includes the following updates:
+## 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/blob/main/README.md#union-multiple-connectors) for more details.
+
+## Under the hood 🚘
+- In the source package, 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 and downstream model and applied the `fivetran_utils.source_relation` macro.
+  - The `source_relation` column is included in all joins in the transform package. 
+- Updated tests to account for the new `source_relation` column.
+
 # dbt_apple_search_ads v0.2.2
 ## Bugfix:
 - Updated the dbt_utils.unique_combination_of_columns test for the `apple_search_ads__search_term_report` to include the following fields. ([PR #18](https://github.com/fivetran/dbt_apple_search_ads/pull/18)):
@@ -66,4 +77,4 @@ Accidental Release
 # dbt_apple_search_ads v0.1.0
 
 ## Initial Release
-- This is the initial release of this package. For more information refer to the [README](/README.md).
+- This is the initial release of this package. For more information refer to the [README](/README.md).

README.md

@@ -51,7 +51,7 @@ Include the following apple_search_ads package version in your `packages.yml` fi
 ```yaml
 packages:
   - package: fivetran/apple_search_ads
-    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
 ```
 
 Do NOT include the `apple_search_ads_source` package in this file. The transformation package itself has a dependency on it and will install the source package as well.
@@ -68,7 +68,17 @@ 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.
 
 ### Adding passthrough 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:
@@ -129,8 +139,6 @@ 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>
 
@@ -145,7 +153,7 @@ This dbt package is dependent on the following dbt packages. Please be aware tha
 ```yml
 packages:
     - package: fivetran/apple_search_ads_source
-      version: [">=0.2.0", "<0.3.0"]
+      version: [">=0.3.0", "<0.4.0"]
 
     - package: fivetran/fivetran_utils
       version: [">=0.4.0", "<0.5.0"]

dbt_project.yml

@@ -1,5 +1,5 @@
 name: 'apple_search_ads'
-version: '0.2.2'
+version: '0.3.0'
 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: apple_search_ads_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_search_ads_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_integration_tests'
-version: '0.2.2'
+version: '0.3.0'
 
 profile: 'integration_tests' 
 

integration_tests/requirements.txt

@@ -4,4 +4,6 @@ dbt-redshift>=1.3.0,<2.0.0
 dbt-postgres>=1.3.0,<2.0.0
 dbt-spark>=1.3.0,<2.0.0
 dbt-spark[PyHive]>=1.3.0,<2.0.0
-dbt-databricks>=1.3.0,<2.0.0
+dbt-databricks>=1.3.0,<2.0.0
+
+oscrypto @ git+https://github.com/wbond/oscrypto.git@d5f3437

models/apple_search_ads.yml

@@ -6,11 +6,14 @@ models:
     tests: 
       - dbt_utils.unique_combination_of_columns:
           combination_of_columns:
+            - source_relation
             - organization_id
             - campaign_id
             - ad_group_id
             - date_day
     columns:
+      - name: source_relation
+        description: "{{ doc('source_relation') }}"
       - name: organization_id
         description: Organization ID associated with this record.
       - name: organization_name
@@ -55,12 +58,15 @@ models:
     tests: 
       - dbt_utils.unique_combination_of_columns:
           combination_of_columns:
+            - source_relation
             - organization_id
             - campaign_id
             - ad_group_id
             - ad_id
             - date_day
     columns:
+      - name: source_relation
+        description: "{{ doc('source_relation') }}"
       - name: organization_id
         description: Organization ID associated with this record.
       - name: organization_name
@@ -105,10 +111,13 @@ models:
     tests: 
       - dbt_utils.unique_combination_of_columns:
           combination_of_columns:
+            - source_relation
             - organization_id
             - campaign_id
             - date_day
     columns:
+      - name: source_relation
+        description: "{{ doc('source_relation') }}"
       - name: organization_id
         description: Organization ID associated with this record.
       - name: organization_name
@@ -149,12 +158,15 @@ models:
     tests: 
       - dbt_utils.unique_combination_of_columns:
           combination_of_columns:
+            - source_relation
             - organization_id
             - campaign_id
             - ad_group_id
             - keyword_id
             - date_day
     columns:
+      - name: source_relation
+        description: "{{ doc('source_relation') }}"
       - name: organization_id
         description: Organization ID associated with this record.
       - name: organization_name
@@ -201,9 +213,12 @@ models:
     tests: 
       - dbt_utils.unique_combination_of_columns:
           combination_of_columns:
+            - source_relation
             - organization_id
             - date_day
     columns:
+      - name: source_relation
+        description: "{{ doc('source_relation') }}"
       - name: organization_id
         description: Organization ID associated with this record.
         tests:
@@ -234,6 +249,7 @@ models:
     tests: 
       - dbt_utils.unique_combination_of_columns:
           combination_of_columns:
+            - source_relation
             - search_term_text
             - match_type
             - date_day
@@ -242,6 +258,8 @@ models:
             - campaign_id
             - organization_id
     columns:
+      - name: source_relation
+        description: "{{ doc('source_relation') }}"
       - name: organization_id
         description: Organization ID associated with this record.
       - name: organization_name

models/apple_search_ads__ad_group_report.sql

@@ -29,6 +29,7 @@ organization as (
 joined as (
 
     select 
+        report.source_relation,
         report.date_day,
         organization.organization_id,
         organization.organization_name,
@@ -51,11 +52,14 @@ joined as (
     from report
     join ad_group 
         on report.ad_group_id = ad_group.ad_group_id
+        and report.source_relation = ad_group.source_relation
     join campaign 
         on ad_group.campaign_id = campaign.campaign_id
+        and ad_group.source_relation = campaign.source_relation
     join organization 
         on ad_group.organization_id = organization.organization_id
-    {{ dbt_utils.group_by(11) }}
+        and ad_group.source_relation = organization.source_relation
+    {{ dbt_utils.group_by(12) }}
 )
 
 select * 

models/apple_search_ads__ad_report.sql

@@ -36,6 +36,7 @@ organization as (
 joined as (
 
     select 
+        report.source_relation,
         report.date_day,
         organization.organization_id,
         organization.organization_name,
@@ -58,13 +59,17 @@ joined as (
     from report
     join ad 
         on report.ad_id = ad.ad_id
+        and report.source_relation = ad.source_relation
     join ad_group 
         on report.ad_group_id = ad_group.ad_group_id
+        and report.source_relation = ad_group.source_relation
     join campaign 
         on report.campaign_id = campaign.campaign_id
+        and report.source_relation = campaign.source_relation
     join organization 
         on ad.organization_id = organization.organization_id
-    {{ dbt_utils.group_by(11) }}
+        and ad.source_relation = organization.source_relation
+    {{ dbt_utils.group_by(12) }}
 )
 
 select * 

models/apple_search_ads__campaign_report.sql

@@ -24,6 +24,7 @@ organization as (
 joined as (
 
     select 
+        report.source_relation,
         report.date_day,
         campaign.organization_id,
         organization.organization_name,
@@ -44,9 +45,11 @@ joined as (
     from report
     join campaign 
         on report.campaign_id = campaign.campaign_id
+        and report.source_relation = campaign.source_relation
     join organization 
         on campaign.organization_id = organization.organization_id
-    {{ dbt_utils.group_by(9) }}
+        and campaign.source_relation = organization.source_relation
+    {{ dbt_utils.group_by(10) }}
 )
 
 select * 

models/apple_search_ads__keyword_report.sql

@@ -36,6 +36,7 @@ organization as (
 joined as (
 
     select 
+        report.source_relation,
         report.date_day,
         organization.organization_id,
         organization.organization_name,
@@ -59,13 +60,17 @@ joined as (
     from report
     join keyword 
         on report.keyword_id = keyword.keyword_id
+        and report.source_relation = keyword.source_relation
     join ad_group 
         on keyword.ad_group_id = ad_group.ad_group_id
+        and keyword.source_relation = ad_group.source_relation
     join campaign 
         on ad_group.campaign_id = campaign.campaign_id
+        and ad_group.source_relation = campaign.source_relation
     join organization 
         on ad_group.organization_id = organization.organization_id
-    {{ dbt_utils.group_by(12) }}
+        and ad_group.source_relation = organization.source_relation
+    {{ dbt_utils.group_by(13) }}
 )
 
 select * 

models/apple_search_ads__organization_report.sql

@@ -22,6 +22,7 @@ organization as (
 joined as (
 
     select 
+        report.source_relation,
         report.date_day,
         organization.organization_id,
         organization.organization_name,
@@ -37,9 +38,11 @@ joined as (
     from report
     join campaign 
         on report.campaign_id = campaign.campaign_id
+        and report.source_relation = campaign.source_relation
     join organization 
         on campaign.organization_id = organization.organization_id
-    {{ dbt_utils.group_by(4) }}
+        and campaign.source_relation = organization.source_relation
+    {{ dbt_utils.group_by(5) }}
 )
 
 select * 

models/apple_search_ads__search_term_report.sql

@@ -22,6 +22,7 @@ organization as (
 joined as (
 
     select 
+        report.source_relation,
         report.date_day,
         organization.organization_id,
         organization.organization_name,
@@ -45,10 +46,12 @@ joined as (
     from report
     join campaign 
         on report.campaign_id = campaign.campaign_id
+        and report.source_relation = campaign.source_relation
     join organization 
         on campaign.organization_id = organization.organization_id
+        and campaign.source_relation = organization.source_relation
     where report.search_term_text is not null
-    {{ dbt_utils.group_by(12) }}
+    {{ dbt_utils.group_by(13) }}
 )
 
 select * 

packages.yml

@@ -1,3 +1,3 @@
 packages:
 - package: fivetran/apple_search_ads_source
-  version: [">=0.2.0", "<0.3.0"]
+  version: [">=0.3.0", "<0.4.0"]