v0.11.0 release branch

.buildkite/scripts/run_models.sh

@@ -20,7 +20,7 @@ dbt seed --target "$db" --full-refresh
 dbt run --target "$db" --full-refresh
 dbt test --target "$db"
 ## UPDATE FOR VARS HERE, IF NO VARS, PLEASE REMOVE
-dbt run --vars '{marketo__enable_campaigns: true, marketo__enable_programs: true, marketo__activity_delete_lead_enabled: false}' --target "$db" --full-refresh
-dbt test --target "$db"
+dbt run --vars '{lead_history_columns: ['first_name', 'lead_status', 'urgency', 'priority', 'relative_score', 'relative_urgency', 'demographic_score_marketing', 'behavior_score_marketing'], marketo__enable_campaigns: true, marketo__enable_programs: true, marketo__activity_delete_lead_enabled: false}' --target "$db" --full-refresh
+dbt test --target "$db" --vars '{lead_history_columns: ['first_name', 'lead_status', 'urgency', 'priority', 'relative_score', 'relative_urgency', 'demographic_score_marketing', 'behavior_score_marketing'], marketo__enable_campaigns: true, marketo__enable_programs: true, marketo__activity_delete_lead_enabled: false}' --target "$db"
 ### END VARS CHUNK, REMOVE IF NOT USING
 dbt run-operation fivetran_utils.drop_schemas_automation --target "$db"

.github/PULL_REQUEST_TEMPLATE/maintainer_pull_request_template.md

@@ -4,48 +4,27 @@
 **This PR will result in the following new package version:**
 <!--- Please add details around your decision for breaking vs non-breaking version upgrade. If this is a breaking change, were backwards-compatible options explored? -->
 
-**Please detail what change(s) this PR introduces and any additional information that should be known during the review of this PR:**
+**Please provide the finalized CHANGELOG entry which details the relevant changes included in this PR:**
+<!--- Copy/paste the CHANGELOG for this version below. -->
 
 ## PR Checklist
 ### Basic Validation
 Please acknowledge that you have successfully performed the following commands locally:
-- [ ] dbt compile
-- [ ] dbt run –full-refresh
-- [ ] dbt run
-- [ ] dbt test
-- [ ] dbt run –vars (if applicable)
+- [ ] dbt run –full-refresh && dbt test
+- [ ] dbt run (if incremental models are present) && dbt test
 
 Before marking this PR as "ready for review" the following have been applied:
-- [ ] The appropriate issue has been linked and tagged
-- [ ] You are assigned to the corresponding issue and this PR
+- [ ] The appropriate issue has been linked, tagged, and properly assigned
+- [ ] All necessary documentation and version upgrades have been applied
+    <!--- Be sure to update the package version in the dbt_project.yml, integration_tests/dbt_project.yml, and README if necessary. -->
+- [ ] docs were regenerated (unless this PR does not include any code or yml updates)
 - [ ] BuildKite integration tests are passing
+- [ ] Detailed validation steps have been provided below
 
 ### Detailed Validation
-Please acknowledge that the following validation checks have been performed prior to marking this PR as "ready for review":
-- [ ] You have validated these changes and assure this PR will address the respective Issue/Feature.
-- [ ] You are reasonably confident these changes will not impact any other components of this package or any dependent packages.
-- [ ] You have provided details below around the validation steps performed to gain confidence in these changes.
+Please share any and all of your validation steps:
 <!--- Provide the steps you took to validate your changes below. -->
 
-### Standard Updates
-Please acknowledge that your PR contains the following standard updates:
-- Package versioning has been appropriately indexed in the following locations:
-    - [ ] indexed within dbt_project.yml
-    - [ ] indexed within integration_tests/dbt_project.yml
-- [ ] CHANGELOG has individual entries for each respective change in this PR
-    <!--- If there is a parallel upstream change, remember to reference the corresponding CHANGELOG as an individual entry.  -->
-- [ ] README updates have been applied (if applicable)
-    <!--- Remember to check the following README locations for common updates. →
-        <!--- Suggested install range (needed for breaking changes) →
-        <!--- Dependency matrix is appropriately updated (if applicable) →
-        <!--- New variable documentation (if applicable) -->
-- [ ] DECISIONLOG updates have been updated (if applicable)
-- [ ] Appropriate yml documentation has been added (if applicable)
-
-### dbt Docs
-Please acknowledge that after the above were all completed the below were applied to your branch:
-- [ ] docs were regenerated (unless this PR does not include any code or yml updates)
-
 ### If you had to summarize this PR in an emoji, which would it be?
 <!--- For a complete list of markdown compatible emojis check our this git repo (https://gist.github.com/rxaviers/7360908)  --> 
-:dancer:
+:dancer:

.github/workflows/auto-release.yml

@@ -0,0 +1,13 @@
+name: 'auto release'
+on:
+  pull_request:
+    types:
+      - closed
+    branches:
+      - main
+
+jobs:
+  call-workflow-passing-data:
+    if: github.event.pull_request.merged
+    uses: fivetran/dbt_package_automations/.github/workflows/auto-release.yml@main
+    secrets: inherit

.gitignore

@@ -2,5 +2,5 @@
 target/
 dbt_modules/
 logs/
-
+package-lock.yml
 dbt_packages/

CHANGELOG.md

@@ -1,3 +1,54 @@
+# dbt_marketo v0.11.0
+
+[PR #33](https://github.com/fivetran/dbt_marketo/pull/33) includes the following updates:
+## Bug Fix
+- Removed the use of `ignore nulls` statements in `marketo__lead_history` and `marketo__change_data_scd`, which was incompatible with PostgreSQL and Databricks Runtime. The logic has been updated with a new approach but produces the same results as before.
+- Updated model `marketo__change_data_pivot` to use the `activity_id` as a tie-breaker to remove randomness when ordering events having the same `activity_timestamp`. 
+  - Previously if two events happened at the same timestamp, results would be inconsistent, which propagated to downstream models. Now, this model will produce consistent results.
+
+## Under the hood
+- Added additional variable configurations to integration tests to account for a wider range of situations.
+
+---
+
+[PR #32](https://github.com/fivetran/dbt_marketo/pull/32) and Marketo Source [PR #35](https://github.com/fivetran/dbt_marketo_source/pull/35) include the following updates:
+
+## Feature Updates (includes 🚨 breaking changes 🚨)
+- Ensures that `stg_marketo__lead` (and therefore `marketo__leads`) has and documents the below columns, all [standard](https://developers.marketo.com/rest-api/lead-database/fields/list-of-standard-fields/) fields from Marketo. Previously, peristed all fields found in your `LEAD` source table but only _ensured_ that the `id`, `created_at`, `updated_at`, `email`, `first_name`, `last_name`, and `_fivetran_synced` fields were included. If any of the following default columns are missing from your `LEAD` table, `stg_marketo__lead` will create a NULL version with the proper data type:
+  - `phone`
+  - `main_phone`
+  - `mobile_phone`
+  - `company`
+  - `inferred_company`
+  - `address_lead`
+  - `address`
+  - `city`
+  - `state`
+  - `state_code`
+  - `country`
+  - `country_code`
+  - `postal_code`
+  - `billing_street`
+  - `billing_city`
+  - `billing_state`
+  - `billing_state_code`
+  - `billing_country`
+  - `billing_country_code`
+  - `billing_postal_code`
+  - `inferred_city`
+  - `inferred_state_region`
+  - `inferred_country`
+  - `inferred_postal_code`
+  - `inferred_phone_area_code`
+  - `anonymous_ip`
+  - `unsubscribed` -> aliased as `is_unsubscribed` (🚨 breaking change 🚨)
+  - `email_invalid` -> aliased as `is_email_invalid` (🚨 breaking change 🚨)
+  - `do_not_call`
+
+## Under the Hood
+- Updated the maintainer PR template to resemble the most up to date format.
+- Included auto-releaser GitHub Actions workflow to automate future releases.
+
 # dbt_marketo v0.10.0
 
 ## 🚨 Breaking Changes 🚨  (recommend --full-refresh):

README.md

@@ -59,7 +59,7 @@ Include the following Marketo package version in your `packages.yml` file.
 ```yml
 packages:
   - package: fivetran/marketo
-    version: [">=0.10.0", "<0.11.0"]
+    version: [">=0.11.0", "<0.12.0"]
 ```
 Do **NOT** include the `marketo_source` package in this file. The transformation package itself has a dependency on it and will install the source package as well. 
 
@@ -89,7 +89,7 @@ vars:
     marketo__activity_delete_lead_enabled:  false     # Disable if you do not have the activity_delete_lead table 
 ```
 ## (Optional) Step 5: Additional configurations
-<details><summary>Expand for details</summary>
+<details open><summary>Expand/Collapse details</summary>
 <br>
 
 ### Passing Through Additional Columns
@@ -152,7 +152,7 @@ This dbt package is dependent on the following dbt packages. Please be aware tha
 ```yml
 packages:
     - package: fivetran/marketo_source
-      version: [">=0.10.0", "<0.11.0"]
+      version: [">=0.11.0", "<0.12.0"]
 
     - package: fivetran/fivetran_utils
       version: [">=0.4.0", "<0.5.0"]

dbt_project.yml

@@ -1,5 +1,5 @@
 name: 'marketo'
-version: '0.10.0'
+version: '0.11.0'
 config-version: 2
 require-dbt-version: [">=1.3.0", "<2.0.0"]
 on-run-start: "{{ lead_history_columns_warning() }}"

integration_tests/dbt_project.yml

@@ -1,5 +1,5 @@
 name: 'marketo_integration_tests'
-version: '0.10.0'
+version: '0.11.0'
 profile: 'integration_tests'
 config-version: 2
 

models/intermediate/marketo__change_data_pivot.sql

@@ -43,7 +43,7 @@ with change_data as (
         *,
         row_number() over (
             partition by cast(activity_timestamp as date), lead_id, primary_attribute_value_id
-            order by activity_timestamp asc
+            order by activity_timestamp asc, activity_id desc -- In the case that events come in the exact same time, we will rely on the activity_id to prove the order
             ) as row_num
     from joined
 

models/intermediate/marketo__change_data_scd.sql

@@ -9,9 +9,14 @@
 }}
 
 {%- set lead_columns = adapter.get_columns_in_relation(ref('int_marketo__lead')) -%}
+{% set filtered_lead_columns = [] %}
+{% for col in lead_columns if col.name|lower not in ['lead_id','_fivetran_synced'] and col.name|lower in var('lead_history_columns') %}
+    {% set filtered_lead_columns = filtered_lead_columns.append(col) %}
+{% endfor %}
+
 {%- set change_data_columns = adapter.get_columns_in_relation(ref('marketo__change_data_pivot')) -%}
 {%- set change_data_columns_xf = change_data_columns|map(attribute='name')|list %}
-    
+
 with change_data as (
 
     select *
@@ -45,51 +50,63 @@ with change_data as (
             ) 
     }}
 
+), field_partitions as (
+
+    select
+        coalesce(unioned.date_day, current_date) as valid_to,
+        unioned.date_day,
+        unioned.lead_id
+
+        {% for col in filtered_lead_columns %}
+        {% if col.name not in change_data_columns_xf %}
+        , unioned.{{ col.name }}
+        , null as {{ col.name }}_partition
+
+        {% else %}
+        , unioned.{{ col.name }}
+        , sum(case when unioned.{{ col.name }} is null and not coalesce(details.{{ col.name }}, true) then 0
+            else 1 end) over (
+                partition by unioned.lead_id
+                order by coalesce(unioned.date_day, current_date) desc 
+                rows between unbounded preceding and current row)
+            as {{ col.name }}_partition
+
+        {% endif %}
+        {% endfor %}
+
+    from unioned
+    left join details
+        on unioned.date_day = details.date_day
+        and unioned.lead_id = details.lead_id
+
 ), today as (
 
-    -- For each day where a change occurred for each lead, we backfill the values from the subsequent change, 
-    -- going back in time. In order to account for changes that occur to or from null values, we need to do a coalesce
-    -- with dummy values, which we nullif() at the end.
+    -- For each day where a change occurred for each lead, we backfill the values from the subsequent change, going back in time.
     -- The 'details' table is joined in for exactly this purpose. It tells us, even if a value is null, whether that null
     -- value is because no change occurred on that day, or because there was a change and the change involved the null value.
 
     select 
-        coalesce(unioned.date_day, current_date) as valid_to, 
-        unioned.lead_id
-        {% for col in lead_columns if col.name|lower not in ['lead_id','_fivetran_synced'] and col.name|lower in var('lead_history_columns') %} 
-        ,
-        {% if col.name not in change_data_columns_xf %}
+        field_partitions.valid_to, 
+        field_partitions.lead_id
 
+        {% for col in filtered_lead_columns %} 
+        {% if col.name not in change_data_columns_xf %}
         {# If the column does not exist in the change data, grab the value from the current state of the record. #}
-        last_value(unioned.{{ col.name }}) over (
-            partition by unioned.lead_id 
-            order by unioned.date_day asc 
+        , last_value(field_partitions.{{ col.name }}) over (
+            partition by field_partitions.lead_id 
+            order by field_partitions.date_day asc 
             rows between unbounded preceding and current row) as {{ col.name }}
 
         {% else %}
-
-        case
-
-            {# if there was a change on the day, as specified by the details table, use that value #}
-            when coalesce(details.{{ col.name }}, True) then unioned.{{ col.name }}
-
-            {# otherwise, grab the most recent value from a day where a change did occur #} 
-            else nullif(
-
-                first_value(case when coalesce(details.{{ col.name }}, True) then coalesce(unioned.{{ col.name}}, {{ fivetran_utils.dummy_coalesce_value(col) }}) end ignore nulls) over (
-                    partition by unioned.lead_id 
-                    order by coalesce(unioned.date_day, current_date) asc 
-                    rows between 1 following and unbounded following), 
-
-                    {{ fivetran_utils.dummy_coalesce_value(col) }})
-        end as {{ col.name }}
+        , first_value(field_partitions.{{ col.name }}) over (
+            partition by field_partitions.lead_id, field_partitions.{{ col.name }}_partition 
+            order by field_partitions.valid_to desc
+            rows between unbounded preceding and current row)
+            as {{ col.name }}
         {% endif %}
         {% endfor %}
 
-    from unioned
-    left join details
-        on unioned.date_day = details.date_day
-        and unioned.lead_id = details.lead_id
+    from field_partitions
 
 ), surrogate_key as (