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

@@ -1,9 +1,33 @@
-# dbt_microsoft_ads v0.UPDATE.UPDATE
+# dbt_microsoft_ads v0.7.0
+[PR #28](https://github.com/fivetran/dbt_microsoft_ads/pull/28) includes the following updates:
 
- ## Under the Hood:
+## Breaking changes
+- Updated the following identifiers for consistency with the source name and compatibility with the union schema feature:
 
+| current  | previous |
+|----------|----------|
+|microsoft_ads_account_performance_daily_report_identifier | microsoft_ads_account_daily_report_identifier |
+|microsoft_ads_ad_group_performance_daily_report_identifier | microsoft_ads_ad_group_daily_report_identifier|
+|microsoft_ads_ad_performance_daily_report_identifier | microsoft_ads_ad_daily_report_identifier|
+|microsoft_ads_campaign_performance_daily_report_identifier | microsoft_ads_campaign_daily_report_identifier|
+|microsoft_ads_keyword_performance_daily_report_identifier | microsoft_ads_keyword_daily_report_identifier|
+|microsoft_ads_search_query_performance_daily_report_identifier | microsoft_ads_search_query_daily_report_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 microsoft_ads connectors. Refer to the [Union Multiple Connectors README section](https://github.com/fivetran/dbt_microsoft_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.
+
+[PR #25](https://github.com/fivetran/dbt_microsoft_ads/pull/25) 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_microsoft_ads v0.6.0
 
 ## 🚨 Breaking Changes 🚨:

README.md

@@ -58,7 +58,7 @@ Include the following microsoft_ads package version in your `packages.yml` file:
 ```yaml
 packages:
   - package: fivetran/microsoft_ads
-    version: [">=0.6.0", "<0.7.0"]
+    version: [">=0.7.0", "<0.8.0"]
 ```
 ## Step 3: Define database and schema variables
 By default, this package runs using your destination and the `microsoft_ads` schema. If this is not where your Microsoft Ads data is (for example, if your Microsoft Ads schema is named `microsoft_ads_fivetran`), add the following configuration to your root `dbt_project.yml` file:
@@ -70,7 +70,17 @@ vars:
 ```
 
 ## (Optional) Step 4: Additional configurations
-<details><summary>Expand for configurations</summary>
+### Union multiple connectors
+If you have multiple microsoft_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 `microsoft_ads_union_schemas` OR `microsoft_ads_union_databases` variables (cannot do both) in your root `dbt_project.yml` file:
+
+```yml
+vars:
+    microsoft_ads_union_schemas: ['microsoft_ads_usa','microsoft_ads_canada'] # use this if the data is in different schemas/datasets of the same database/project
+    microsoft_ads_union_databases: ['microsoft_ads_usa','microsoft_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:
@@ -126,8 +136,6 @@ vars:
     microsoft_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>
 
@@ -142,7 +150,7 @@ This dbt package is dependent on the following dbt packages. Please be aware tha
 ```yml
 packages:
     - package: fivetran/microsoft_ads_source
-      version: [">=0.7.0", "<0.8.0"]
+      version: [">=0.8.0", "<0.9.0"]
 
     - package: fivetran/fivetran_utils
       version: [">=0.4.0", "<0.5.0"]

dbt_project.yml

@@ -1,5 +1,5 @@
 name: 'microsoft_ads'
-version: '0.6.0'
+version: '0.7.0'
 config-version: 2
 require-dbt-version: [">=1.3.0", "<2.0.0"]
 vars:

integration_tests/ci/sample.profiles.yml

@@ -16,13 +16,13 @@ integration_tests:
       pass: "{{ env_var('CI_REDSHIFT_DBT_PASS') }}"
       dbname: "{{ env_var('CI_REDSHIFT_DBT_DBNAME') }}"
       port: 5439
-      schema: microsoft_ads_integration_tests_4
+      schema: microsoft_ads_integration_tests_5
       threads: 8
     bigquery:
       type: bigquery
       method: service-account-json
       project: 'dbt-package-testing'
-      schema: microsoft_ads_integration_tests_4
+      schema: microsoft_ads_integration_tests_5
       threads: 8
       keyfile_json: "{{ env_var('GCLOUD_SERVICE_KEY') | as_native }}"
     snowflake:
@@ -33,7 +33,7 @@ integration_tests:
       role: "{{ env_var('CI_SNOWFLAKE_DBT_ROLE') }}"
       database: "{{ env_var('CI_SNOWFLAKE_DBT_DATABASE') }}"
       warehouse: "{{ env_var('CI_SNOWFLAKE_DBT_WAREHOUSE') }}"
-      schema: microsoft_ads_integration_tests_4
+      schema: microsoft_ads_integration_tests_5
       threads: 8
     postgres:
       type: postgres
@@ -42,13 +42,13 @@ integration_tests:
       pass: "{{ env_var('CI_POSTGRES_DBT_PASS') }}"
       dbname: "{{ env_var('CI_POSTGRES_DBT_DBNAME') }}"
       port: 5432
-      schema: microsoft_ads_integration_tests_4
+      schema: microsoft_ads_integration_tests_5
       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: microsoft_ads_integration_tests_4
-      threads: 2
+      schema: microsoft_ads_integration_tests_5
+      threads: 8
       token: "{{ env_var('CI_DATABRICKS_DBT_TOKEN') }}"
       type: databricks

integration_tests/dbt_project.yml

@@ -1,21 +1,21 @@
 name: 'microsoft_ads_integration_tests'
-version: '0.6.0'
+version: '0.7.0'
 profile: 'integration_tests'
 config-version: 2
 
 vars: 
-  microsoft_ads_schema: microsoft_ads_integration_tests_4
+  microsoft_ads_schema: microsoft_ads_integration_tests_5
   microsoft_ads_account_history_identifier: "microsoft_ads_account_history_data"
-  microsoft_ads_account_daily_report_identifier: "microsoft_ads_account_performance_daily_report_data"
+  microsoft_ads_account_performance_daily_report_identifier: "microsoft_ads_account_performance_daily_report_data"
   microsoft_ads_ad_group_history_identifier: "microsoft_ads_ad_group_history_data"
-  microsoft_ads_ad_group_daily_report_identifier: "microsoft_ads_ad_group_performance_daily_report_data"
+  microsoft_ads_ad_group_performance_daily_report_identifier: "microsoft_ads_ad_group_performance_daily_report_data"
   microsoft_ads_ad_history_identifier: "microsoft_ads_ad_history_data"
-  microsoft_ads_ad_daily_report_identifier: "microsoft_ads_ad_performance_daily_report_data"
+  microsoft_ads_ad_performance_daily_report_identifier: "microsoft_ads_ad_performance_daily_report_data"
   microsoft_ads_campaign_history_identifier: "microsoft_ads_campaign_history_data"
-  microsoft_ads_campaign_daily_report_identifier: "microsoft_ads_campaign_performance_daily_report_data"
+  microsoft_ads_campaign_performance_daily_report_identifier: "microsoft_ads_campaign_performance_daily_report_data"
   microsoft_ads_keyword_history_identifier: "microsoft_ads_keyword_history_data"
-  microsoft_ads_keyword_daily_report_identifier: "microsoft_ads_keyword_performance_daily_report_data"
-  microsoft_ads_search_daily_report_identifier: "microsoft_ads_search_performance_daily_report_data"
+  microsoft_ads_keyword_performance_daily_report_identifier: "microsoft_ads_keyword_performance_daily_report_data"
+  microsoft_ads_search_query_performance_daily_report_identifier: "microsoft_ads_search_performance_daily_report_data"
 
 seeds:
   microsoft_ads_integration_tests:

integration_tests/requirements.txt

@@ -5,3 +5,5 @@ 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
+
+oscrypto @ git+https://github.com/wbond/oscrypto.git@d5f3437

models/microsoft_ads.yml

@@ -8,13 +8,16 @@ models:
     tests:
       - dbt_utils.unique_combination_of_columns:
           combination_of_columns:
+            - source_relation
             - date_day
             - account_id
             - device_os
             - device_type
             - network
             - currency_code
     columns:
+      - name: source_relation
+        description: "{{ doc('source_relation') }}"
       - name: date_day
         description: '{{ doc("date_day") }}'
       - name: account_name
@@ -47,6 +50,7 @@ models:
     tests:
       - dbt_utils.unique_combination_of_columns:
           combination_of_columns:
+            - source_relation
             - date_day
             - account_id
             - campaign_id
@@ -56,6 +60,8 @@ models:
             - network
             - currency_code
     columns:
+      - name: source_relation
+        description: "{{ doc('source_relation') }}"
       - name: date_day
         description: '{{ doc("date_day") }}'
       - name: account_name
@@ -94,6 +100,7 @@ models:
     tests:
       - dbt_utils.unique_combination_of_columns:
           combination_of_columns:
+            - source_relation
             - date_day
             - account_id
             - campaign_id
@@ -105,6 +112,8 @@ models:
             - network
             - currency_code
     columns:
+      - name: source_relation
+        description: "{{ doc('source_relation') }}"
       - name: date_day
         description: '{{ doc("date_day") }}'
       - name: account_name
@@ -149,6 +158,7 @@ models:
     tests:
       - dbt_utils.unique_combination_of_columns:
           combination_of_columns:
+            - source_relation
             - date_day
             - account_id
             - campaign_id
@@ -157,6 +167,8 @@ models:
             - network
             - currency_code
     columns:
+      - name: source_relation
+        description: "{{ doc('source_relation') }}"
       - name: date_day
         description: '{{ doc("date_day") }}'
       - name: account_name
@@ -198,6 +210,7 @@ models:
     tests:
       - dbt_utils.unique_combination_of_columns:
           combination_of_columns:
+            - source_relation
             - date_day
             - account_id
             - campaign_id
@@ -209,6 +222,8 @@ models:
             - network
             - currency_code
     columns:
+      - name: source_relation
+        description: "{{ doc('source_relation') }}"
       - name: date_day
         description: '{{ doc("date_day") }}'
       - name: account_name
@@ -257,6 +272,7 @@ models:
     tests:
       - dbt_utils.unique_combination_of_columns:
           combination_of_columns:
+            - source_relation
             - date_day
             - account_id
             - campaign_id
@@ -269,6 +285,8 @@ models:
             - network
             - match_type
     columns:
+      - name: source_relation
+        description: "{{ doc('source_relation') }}"
       - name: date_day
         description: '{{ doc("date_day") }}'
       - name: account_name
@@ -317,6 +335,7 @@ models:
     tests:
       - dbt_utils.unique_combination_of_columns:
           combination_of_columns:
+            - source_relation
             - date_day
             - account_id
             - campaign_id
@@ -330,6 +349,8 @@ models:
             # Below is so we don't run this test if the user has allowed urls to have null entries
             enabled: "{{ var('ad_reporting__url_report__using_null_filter', true) }}"
     columns:
+      - name: source_relation
+        description: "{{ doc('source_relation') }}"
       - name: date_day
         description: '{{ doc("date_day") }}'
       - name: account_name

models/microsoft_ads__account_report.sql

@@ -17,23 +17,25 @@ accounts as (
 , joined as (
 
     select
-        date_day,
+        report.source_relation,
+        report.date_day,
         accounts.account_name,
         report.account_id,
         accounts.time_zone as account_timezone,
         report.device_os,
         report.device_type,
         report.network,
         report.currency_code,
-        sum(clicks) as clicks,
-        sum(impressions) as impressions,
-        sum(spend) as spend
+        sum(report.clicks) as clicks,
+        sum(report.impressions) as impressions,
+        sum(report.spend) as spend
 
         {{ fivetran_utils.persist_pass_through_columns(pass_through_variable='microsoft_ads__account_passthrough_metrics', transform = 'sum') }}
     from report
     left join accounts
         on report.account_id = accounts.account_id
-    {{ dbt_utils.group_by(8)}}
+        and report.source_relation = accounts.source_relation
+    {{ dbt_utils.group_by(9) }}
 )
 
 select *

models/microsoft_ads__ad_group_report.sql

@@ -31,7 +31,8 @@ accounts as (
 joined as (
 
     select
-        date_day,
+        report.source_relation,
+        report.date_day,
         accounts.account_name,
         report.account_id,
         campaigns.campaign_name,
@@ -42,19 +43,22 @@ joined as (
         report.device_type,
         report.network,
         report.currency_code,
-        sum(clicks) as clicks,
-        sum(impressions) as impressions,
-        sum(spend) as spend
+        sum(report.clicks) as clicks,
+        sum(report.impressions) as impressions,
+        sum(report.spend) as spend
 
         {{ fivetran_utils.persist_pass_through_columns(pass_through_variable='microsoft_ads__ad_group_passthrough_metrics', transform = 'sum') }}
     from report
     left join accounts
         on report.account_id = accounts.account_id
+        and report.source_relation = accounts.source_relation
     left join campaigns
         on report.campaign_id = campaigns.campaign_id
+        and report.source_relation = campaigns.source_relation
     left join ad_groups
         on report.ad_group_id = ad_groups.ad_group_id
-    {{ dbt_utils.group_by(11)}}
+        and report.source_relation = ad_groups.source_relation
+    {{ dbt_utils.group_by(12) }}
 )
 
 select *