Merge pull request #11 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

@@ -1,3 +1,14 @@
+# dbt_amazon_ads v0.3.0
+[PR #11](https://github.com/fivetran/dbt_amazon_ads/pull/11) includes the following updates:
+## Feature update 🎉
+- Unioning capability! This adds the ability to union source data from multiple amazon_ads connectors. Refer to the [Union Multiple Connectors README section](https://github.com/fivetran/dbt_amazon_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_amazon_ads v0.2.0
 [PR #6](https://github.com/fivetran/dbt_amazon_ads/pull/6) includes the following updates:
 ## 🚨 Breaking changes

README.md

@@ -52,7 +52,7 @@ Include the following amazon_ads package version in your `packages.yml` file:
 ```yaml
 packages:
   - package: fivetran/amazon_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 `amazon_ads_source` package in this file. The transformation package itself has a dependency on it and will install the source package as well.
@@ -76,7 +76,17 @@ vars:
 ```
 
 ## (Optional) Step 5: Additional configurations
-<details><summary>Expand for configurations</summary>
+### Union multiple connectors
+If you have multiple amazon_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 `amazon_ads_union_schemas` OR `amazon_ads_union_databases` variables (cannot do both) in your root `dbt_project.yml` file:
+
+```yml
+vars:
+    amazon_ads_union_schemas: ['amazon_ads_usa','amazon_ads_canada'] # use this if the data is in different schemas/datasets of the same database/project
+    amazon_ads_union_databases: ['amazon_ads_usa','amazon_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 following configurations to your `dbt_project.yml` file. These variables allow the pass-through fields to be aliased (`alias`) if desired, but not required. Use the following format for declaring the respective pass-through variables:
@@ -122,8 +132,6 @@ If an individual source table has a different name than the package expects, add
 vars:
     amazon_ads_<default_source_table_name>_identifier: your_table_name 
 ```
-</details>
-
 ## (Optional) Step 6: Orchestrate your models with Fivetran Transformations for dbt Core™    
 <details><summary>Expand for more details</summary>
 
@@ -138,7 +146,7 @@ This dbt package is dependent on the following dbt packages. Be aware that these
 ```yml
 packages:
     - package: fivetran/amazon_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: 'amazon_ads'
-version: '0.2.0'
+version: '0.3.0'
 config-version: 2
 require-dbt-version: [">=1.3.0", "<2.0.0"]
 models:

integration_tests/ci/sample.profiles.yml

@@ -45,7 +45,7 @@ integration_tests:
       schema: amazon_ads_integration_tests_02
       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: amazon_ads_integration_tests_02

integration_tests/dbt_project.yml

@@ -1,7 +1,7 @@
 config-version: 2
 
 name: 'amazon_ads_integration_tests'
-version: '0.2.0'
+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/amazon_ads.yml

@@ -6,9 +6,12 @@ models:
     tests:     
       - dbt_utils.unique_combination_of_columns:
           combination_of_columns:
+            - source_relation
             - date_day
             - profile_id
     columns:
+      - name: source_relation
+        description: "{{ doc('source_relation') }}"
       - name: date_day
         description: "{{ doc('report_date') }}"
       - name: profile_id
@@ -35,9 +38,12 @@ models:
     tests:     
       - dbt_utils.unique_combination_of_columns:
           combination_of_columns:
+            - source_relation
             - date_day
             - ad_group_id
     columns:
+      - name: source_relation
+        description: "{{ doc('source_relation') }}"
       - name: date_day
         description: "{{ doc('report_date') }}"
       - name: account_id
@@ -82,9 +88,12 @@ models:
     tests:     
       - dbt_utils.unique_combination_of_columns:
           combination_of_columns:
+            - source_relation
             - date_day
             - ad_id
     columns:
+      - name: source_relation
+        description: "{{ doc('source_relation') }}"
       - name: date_day
         description: "{{ doc('report_date') }}"
       - name: account_id
@@ -137,9 +146,12 @@ models:
     tests:     
       - dbt_utils.unique_combination_of_columns:
           combination_of_columns:
+            - source_relation
             - date_day
             - campaign_id
     columns:
+      - name: source_relation
+        description: "{{ doc('source_relation') }}"
       - name: date_day
         description: "{{ doc('report_date') }}"
       - name: account_id
@@ -180,9 +192,12 @@ models:
     tests:     
       - dbt_utils.unique_combination_of_columns:
           combination_of_columns:
+            - source_relation
             - date_day
             - portfolio_id
     columns:
+      - name: source_relation
+        description: "{{ doc('source_relation') }}"
       - name: date_day
         description: "{{ doc('report_date') }}"
       - name: account_id
@@ -227,9 +242,12 @@ models:
     tests:     
       - dbt_utils.unique_combination_of_columns:
           combination_of_columns:
+            - source_relation
             - date_day
             - keyword_id
     columns:
+      - name: source_relation
+        description: "{{ doc('source_relation') }}"
       - name: date_day
         description: "{{ doc('report_date') }}"
       - name: account_id
@@ -280,10 +298,13 @@ models:
     tests:     
       - dbt_utils.unique_combination_of_columns:
           combination_of_columns:
+            - source_relation
             - date_day
             - search_term
             - keyword_id
     columns:
+      - name: source_relation
+        description: "{{ doc('source_relation') }}"
       - name: date_day
         description: "{{ doc('report_date') }}"
       - name: account_id

models/amazon_ads__account_report.sql

@@ -20,6 +20,7 @@ campaigns as (
 
 fields as (
     select
+        report.source_relation,
         report.date_day,
         account_info.account_name,
         account_info.account_id,
@@ -36,11 +37,13 @@ fields as (
 
     left join campaigns
         on campaigns.campaign_id = report.campaign_id
+        and campaigns.source_relation = report.source_relation
     left join account_info
         on account_info.profile_id = campaigns.profile_id
+        and account_info.source_relation = campaigns.source_relation
 
 
-    {{ dbt_utils.group_by(5) }}
+    {{ dbt_utils.group_by(6) }}
 )
 
 select *

models/amazon_ads__ad_group_report.sql

@@ -30,6 +30,7 @@ ad_groups as (
 
 fields as (
     select
+        report.source_relation,
         report.date_day,
         account_info.account_name,
         account_info.account_id,
@@ -55,14 +56,18 @@ fields as (
 
     left join ad_groups
         on ad_groups.ad_group_id = report.ad_group_id
+        and ad_groups.source_relation = report.source_relation
     left join campaigns
         on campaigns.campaign_id = ad_groups.campaign_id
+        and campaigns.source_relation = ad_groups.source_relation
     left join portfolios
         on portfolios.portfolio_id = campaigns.portfolio_id
+        and portfolios.source_relation = campaigns.source_relation
     left join account_info
         on account_info.profile_id = campaigns.profile_id
+        and account_info.source_relation = campaigns.source_relation
 
-    {{ dbt_utils.group_by(15) }}
+    {{ dbt_utils.group_by(16) }}
 )
 
 select *

models/amazon_ads__ad_report.sql

@@ -36,6 +36,7 @@ ads as (
 
 fields as (
     select
+        report.source_relation,
         report.date_day,
         account_info.account_name,
         account_info.account_id,
@@ -65,16 +66,21 @@ fields as (
 
     left join ads
         on ads.ad_id = report.ad_id
+        and ads.source_relation = report.source_relation
     left join ad_groups
         on ad_groups.ad_group_id = report.ad_group_id
+        and ad_groups.source_relation = report.source_relation
     left join campaigns
         on campaigns.campaign_id = report.campaign_id
+        and campaigns.source_relation = report.source_relation
     left join portfolios
-        on portfolios.portfolio_id = campaigns.portfolio_id 
+        on portfolios.portfolio_id = campaigns.portfolio_id
+        and portfolios.source_relation = campaigns.source_relation 
     left join account_info
-        on account_info.profile_id = campaigns.profile_id 
+        on account_info.profile_id = campaigns.profile_id
+        and account_info.source_relation = campaigns.source_relation 
 
-    {{ dbt_utils.group_by(19) }}
+    {{ dbt_utils.group_by(20) }}
 )
 
 select *

models/amazon_ads__campaign_report.sql

@@ -24,6 +24,7 @@ campaigns as (
 
 fields as (
     select
+        report.source_relation,
         report.date_day,
         account_info.account_name,
         account_info.account_id,
@@ -47,12 +48,15 @@ fields as (
 
     left join campaigns
         on campaigns.campaign_id = report.campaign_id
+        and campaigns.source_relation = report.source_relation
     left join portfolios
-        on portfolios.portfolio_id = campaigns.portfolio_id 
+        on portfolios.portfolio_id = campaigns.portfolio_id
+        and portfolios.source_relation = campaigns.source_relation 
     left join account_info
-        on account_info.profile_id = campaigns.profile_id 
+        on account_info.profile_id = campaigns.profile_id
+        and account_info.source_relation = campaigns.source_relation 
 
-    {{ dbt_utils.group_by(13) }}
+    {{ dbt_utils.group_by(14) }}
 )
 
 select *

models/amazon_ads__keyword_report.sql

@@ -36,6 +36,7 @@ keywords as (
 
 fields as (
     select
+        report.source_relation,
         report.date_day,
         account_info.account_name,
         account_info.account_id,
@@ -64,16 +65,21 @@ fields as (
 
     left join keywords
         on keywords.keyword_id = report.keyword_id
+        and keywords.source_relation = report.source_relation
     left join ad_groups
         on ad_groups.ad_group_id = report.ad_group_id
+        and ad_groups.source_relation = report.source_relation
     left join campaigns
         on campaigns.campaign_id = report.campaign_id
+        and campaigns.source_relation = report.source_relation
     left join portfolios
         on portfolios.portfolio_id = campaigns.portfolio_id
+        and portfolios.source_relation = campaigns.source_relation
     left join account_info
         on account_info.profile_id = campaigns.profile_id
+        and account_info.source_relation = campaigns.source_relation
 
-    {{ dbt_utils.group_by(18) }}
+    {{ dbt_utils.group_by(19) }}
 )
 
 select *

models/amazon_ads__portfolio_report.sql

@@ -26,6 +26,7 @@ campaigns as (
 
 fields as (
     select
+        report.source_relation,
         report.date_day,
         account_info.account_name,
         account_info.account_id,
@@ -52,12 +53,15 @@ fields as (
 
     left join campaigns
         on campaigns.portfolio_id = portfolios.portfolio_id
+        and campaigns.source_relation = portfolios.source_relation
     left join account_info
         on account_info.profile_id = campaigns.profile_id
+        and account_info.source_relation = campaigns.source_relation
     left join report
         on report.campaign_id = campaigns.campaign_id
+        and report.source_relation = campaigns.source_relation
 
-    {{ dbt_utils.group_by(15) }}
+    {{ dbt_utils.group_by(16) }}
 )
 
 select *