Update/crm api v3 - contact merge audit removed

CHANGELOG.md

@@ -1,3 +1,22 @@
+# dbt_hubspot_source v0.9.0
+
+## 🚨 Breaking Changes 🚨
+In [November 2022](https://fivetran.com/docs/applications/hubspot/changelog#november2022), the Fivetran Hubspot connector switched to v3 of the Hubspot CRM API, which deprecated the `CONTACT_MERGE_AUDIT` table and stored merged contacts in a field in the `CONTACT` table. **This has not been rolled out to BigQuery warehouses yet.** BigQuery connectors with the `CONTACT_MERGE_AUDIT` table enabled will continue to sync this table until the new `CONTACT.property_hs_calculated_merged_vids` field and API version becomes available to them.
+
+This release introduces breaking changes around how contacts are merged in order to align with the above connector changes. It is, however, backwards-compatible.
+
+[PR #98](https://github.com/fivetran/dbt_hubspot_source/pull/98) applies the following changes:
+- Updates logic around the recently deprecated `CONTACT_MERGE_AUDIT` table.
+  - The package now brings in the new `property_hs_calculated_merged_vids` field (and removes the `property_hs_` prefix) for all customers, including those on BigQuery (the field will just be `null`).
+  - **Backwards-compatibility:** the package will only reference the old `CONTACT_MERGE_AUDIT` table and create `stg_hubspot__contact_merge_audit` if `hubspot_contact_merge_audit_enabled` is explicitly set to `true` in your root `dbt_project.yml` file.
+
+## Under the Hood
+[PR #98](https://github.com/fivetran/dbt_hubspot_source/pull/98) applies the following changes:
+- Updates seed data to test new merging paradigm.
+- Ensures that all timestamp fields are explicitly cast as timestamps without timezone, as recent API changes also introduced inconsistent timestamp formats.
+
+See the transform package [CHANEGLOG](https://github.com/fivetran/dbt_hubspot/blob/main/CHANGELOG.md) for updates made to end models in `dbt_hubspot v0.9.0`.
+
 # dbt_hubspot_source v0.8.0
 
 ## 🚨 Breaking Changes 🚨:

README.md

@@ -38,13 +38,13 @@ dispatch:
     search_order: ['spark_utils', 'dbt_utils']
 ```
 
-## Step 2: Install the package
+## Step 2: Install the package (skip if also using the `hubspot` transformation package)
 Include the following hubspot_source package version in your `packages.yml` file.
 > TIP: Check [dbt Hub](https://hub.getdbt.com/) for the latest installation instructions or [read the dbt docs](https://docs.getdbt.com/docs/package-management) for more information on installing packages.
 ```yaml
 packages:
   - package: fivetran/hubspot_source
-    version: [">=0.7.0", "<0.8.0"]
+    version: [">=0.9.0", "<0.10.0"]
 ```
 ## Step 3: Define database and schema variables
 By default, this package runs using your destination and the `hubspot` schema. If this is not where your HubSpot data is (for example, if your HubSpot schema is named `hubspot_fivetran`), add the following configuration to your root `dbt_project.yml` file:
@@ -57,7 +57,6 @@ vars:
 ## Step 4: Disable models for non-existent sources
 When setting up your Hubspot connection in Fivetran, it is possible that not every table this package expects will be synced. This can occur because you either don't use that functionality in Hubspot or have actively decided to not sync some tables. Therefore we have added enable/disable configs in the `src.yml` to allow you to disable certain sources not present. Downstream models are automatically disabled as well. In order to disable the relevant functionality in the package, you will need to add the relevant variables in your root `dbt_project.yml`. By default, all variables are assumed to be `true` (with exception of `hubspot_service_enabled`, `hubspot_ticket_deal_enabled`, and `hubspot_contact_merge_audit_enabled`). You only need to add variables for the tables different from default:
 
-
 ```yml
 # dbt_project.yml
 vars:
@@ -82,8 +81,9 @@ vars:
   hubspot_email_event_spam_report_enabled: false
   hubspot_email_event_status_change_enabled: false
 
-  hubspot_contact_merge_audit_enabled: true               # Enables contact merge auditing to be applied to final models (removes any merged contacts that are still persisting in the contact table)
-
+  hubspot_contact_merge_audit_enabled: true               # Enables the use of the CONTACT_MERGE_AUDIT table (deprecated by Hubspot v3 API) for removing merged contacts in the final models.
+                                                          # If false, ~~~contacts will still be merged~~~, but using the CONTACT.property_hs_calculated_merged_vids field (introduced in v3 of the Hubspot CRM API)
+                                                          # Default = false
   # Sales
 
   hubspot_sales_enabled: false                            # Disables all sales models

dbt_project.yml

@@ -1,5 +1,5 @@
 name: 'hubspot_source'
-version: '0.8.0'
+version: '0.9.0'
 config-version: 2
 require-dbt-version: [">=1.3.0", "<2.0.0"]
 models:

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: hubspot_source_integration_tests_1
+      schema: hubspot_source_integration_tests_2
       threads: 8
     bigquery:
       type: bigquery
       method: service-account-json
       project: 'dbt-package-testing'
-      schema: hubspot_source_integration_tests_1
+      schema: hubspot_source_integration_tests_2
       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: hubspot_source_integration_tests_1
+      schema: hubspot_source_integration_tests_2
       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: hubspot_source_integration_tests_1
+      schema: hubspot_source_integration_tests_2
       threads: 8
     databricks:
       catalog: null
       host: "{{ env_var('CI_DATABRICKS_DBT_HOST') }}"
       http_path: "{{ env_var('CI_DATABRICKS_DBT_HTTP_PATH') }}"
-      schema: hubspot_source_integration_tests_1
+      schema: hubspot_source_integration_tests_2
       threads: 2
       token: "{{ env_var('CI_DATABRICKS_DBT_TOKEN') }}"
       type: databricks

integration_tests/dbt_project.yml

@@ -1,12 +1,12 @@
 name: 'hubspot_source_integration_tests'
-version: '0.8.0'
+version: '0.9.0'
 profile: 'integration_tests'
 config-version: 2
 models:
   hubspot_source:
     +schema:
 vars:
-  hubspot_schema: hubspot_source_integration_tests_1
+  hubspot_schema: hubspot_source_integration_tests_2
   hubspot_source:
     hubspot_service_enabled: true
     hubspot_company_property_history_identifier: "company_property_history_data"
@@ -59,62 +59,67 @@ seeds:
     +quote_columns: "{{ true if target.type == 'redshift' else false }}"
     owner_data:
       +column_types:
-        owner_id: "{{ 'int64' if target.name == 'bigquery' else 'bigint' }}"
+        owner_id: "{{ 'int64' if target.type == 'bigquery' else 'bigint' }}"
     company_data:
       +column_types:
-        id: "{{ 'int64' if target.name == 'bigquery' else 'bigint' }}"
+        id: "{{ 'int64' if target.type == 'bigquery' else 'bigint' }}"
     deal_data:
       +column_types:
-        deal_id: "{{ 'int64' if target.name == 'bigquery' else 'bigint' }}"
-        owner_id: "{{ 'int64' if target.name == 'bigquery' else 'bigint' }}"
+        deal_id: "{{ 'int64' if target.type == 'bigquery' else 'bigint' }}"
+        owner_id: "{{ 'int64' if target.type == 'bigquery' else 'bigint' }}"
+        _fivetran_synced: timestamp
+        property_closedate: timestamp
+        property_createdate: timestamp
     deal_contact_data:
       +column_types:
-        contact_id: "{{ 'int64' if target.name == 'bigquery' else 'bigint' }}"
-        deal_id: "{{ 'int64' if target.name == 'bigquery' else 'bigint' }}"
+        contact_id: "{{ 'int64' if target.type == 'bigquery' else 'bigint' }}"
+        deal_id: "{{ 'int64' if target.type == 'bigquery' else 'bigint' }}"
     deal_stage_data:
       +column_types:
-        deal_id: "{{ 'int64' if target.name == 'bigquery' else 'bigint' }}"
+        deal_id: "{{ 'int64' if target.type == 'bigquery' else 'bigint' }}"
     company_property_history_data:
       +column_types:
-        company_id: "{{ 'int64' if target.name == 'bigquery' else 'bigint' }}"
+        company_id: "{{ 'int64' if target.type == 'bigquery' else 'bigint' }}"
     email_campaign_data:
       +column_types:
-        id: "{{ 'int64' if target.name == 'bigquery' else 'bigint' }}"
-        content_id: "{{ 'int64' if target.name == 'bigquery' else 'bigint' }}"
+        id: "{{ 'int64' if target.type == 'bigquery' else 'bigint' }}"
+        content_id: "{{ 'int64' if target.type == 'bigquery' else 'bigint' }}"
     deal_property_history_data:
       +column_types:
-        deal_id: "{{ 'int64' if target.name == 'bigquery' else 'bigint' }}"
+        deal_id: "{{ 'int64' if target.type == 'bigquery' else 'bigint' }}"
     engagement_call_data:
       +column_types:
-        engagement_id: "{{ 'int64' if target.name == 'bigquery' else 'bigint' }}"
+        engagement_id: "{{ 'int64' if target.type == 'bigquery' else 'bigint' }}"
     engagement_company_data:
       +column_types:
-        engagement_id: "{{ 'int64' if target.name == 'bigquery' else 'bigint' }}"
-        company_id: "{{ 'int64' if target.name == 'bigquery' else 'bigint' }}"
+        engagement_id: "{{ 'int64' if target.type == 'bigquery' else 'bigint' }}"
+        company_id: "{{ 'int64' if target.type == 'bigquery' else 'bigint' }}"
     engagement_contact_data:
       +column_types:
-        engagement_id: "{{ 'int64' if target.name == 'bigquery' else 'bigint' }}"
-        contact_id: "{{ 'int64' if target.name == 'bigquery' else 'bigint' }}"
+        engagement_id: "{{ 'int64' if target.type == 'bigquery' else 'bigint' }}"
+        contact_id: "{{ 'int64' if target.type == 'bigquery' else 'bigint' }}"
     engagement_deal_data:
       +column_types:
-        engagement_id: "{{ 'int64' if target.name == 'bigquery' else 'bigint' }}"
-        deal_id: "{{ 'int64' if target.name == 'bigquery' else 'bigint' }}"
+        engagement_id: "{{ 'int64' if target.type == 'bigquery' else 'bigint' }}"
+        deal_id: "{{ 'int64' if target.type == 'bigquery' else 'bigint' }}"
     engagement_data:
       +column_types:
-        id: "{{ 'int64' if target.name == 'bigquery' else 'bigint' }}"
+        id: "{{ 'int64' if target.type == 'bigquery' else 'bigint' }}"
     engagement_meeting_data:
       +column_types:
-        engagement_id: "{{ 'int64' if target.name == 'bigquery' else 'bigint' }}"
+        engagement_id: "{{ 'int64' if target.type == 'bigquery' else 'bigint' }}"
     engagement_email_data:
       +column_types:
-        engagement_id: "{{ 'int64' if target.name == 'bigquery' else 'bigint' }}"
+        engagement_id: "{{ 'int64' if target.type == 'bigquery' else 'bigint' }}"
+        _fivetran_synced: timestamp
+        email_send_event_id_created: timestamp
     engagement_task_data:
       +column_types:
-        engagement_id: "{{ 'int64' if target.name == 'bigquery' else 'bigint' }}"
+        engagement_id: "{{ 'int64' if target.type == 'bigquery' else 'bigint' }}"
         completion_date: "{{ 'varchar(100)'  if target.type in ('redshift','postgres') else 'string'}}"
     engagement_note_data:
       +column_types:
-        engagement_id: "{{ 'int64' if target.name == 'bigquery' else 'bigint' }}"
+        engagement_id: "{{ 'int64' if target.type == 'bigquery' else 'bigint' }}"
     deal_pipeline_data:
       +column_types:
         pipeline_id: "{{ 'varchar(100)'  if target.type in ('redshift','postgres') else 'string'}}"
@@ -137,6 +142,13 @@ seeds:
       +enabled: "{{ true if target.type != 'postgres' else false }}"
     contact_list_data_postgres:
       +enabled: "{{ true if target.type == 'postgres' else false }}"
+    email_event_data: 
+      +column_types:
+        _fivetran_synced: timestamp
+        caused_by_created: timestamp
+        created: timestamp
+        obsoleted_by_created: timestamp
+        sent_by_created: timestamp
 
 dispatch:
   - macro_namespace: dbt_utils