cast as int bug

.gitignore

@@ -1,6 +1,7 @@
-
 target/
 dbt_modules/
 logs/
-
-dbt_packages/
+env/
+dbt_packages/
+.DS_Store
+package-lock.yml

CHANGELOG.md

@@ -1,3 +1,12 @@
+# dbt_hubspot v0.17.1
+[PR #140](https://github.com/fivetran/dbt_hubspot/pull/140) includes the following updates:
+
+## Under the Hood
+- In `int_hubspot__contact_merge_adjust`, updates casting of `vid_to_merge` as `{{ dbt.type_int() }}` to `{{ dbt.type_string() }}` in the join of `contact_merge_audit` to `contacts`. Previously, casting only to `int` caused model failures resulting from integer fields that exceeded the range allowed in certain warehouses. In addition, for the case where the `contact_merge_audit` table is not present, the parsed `calculated_merged_vids` from the contact table are outputted as strings, therefore requiring the titular datatype cast in the join.
+
+For context, the [Nov 2022 release of the Hubspot connector](https://fivetran.com/docs/connectors/applications/hubspot/changelog#november2022) should not have the `contact_merge_audit` table as that was deprecated in place of storing `property_hs_calculated_merged_vids` in the `contact` table.
+
+
 # dbt_hubspot v0.17.0
 [PR #137](https://github.com/fivetran/dbt_hubspot/pull/137) includes the following updates:
 

dbt_project.yml

@@ -1,5 +1,5 @@
 name: 'hubspot'
-version: '0.17.0'
+version: '0.17.1'
 
 config-version: 2
 require-dbt-version: [">=1.3.0", "<2.0.0"]

integration_tests/.gitignore

@@ -4,4 +4,5 @@ dbt_modules/
 logs/
 .DS_Store
 dbt_packages/
-env/
+env/
+package-lock.yml

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_integration_tests_11
+      schema: hubspot_integration_tests_55
       threads: 8
     bigquery:
       type: bigquery
       method: service-account-json
       project: 'dbt-package-testing'
-      schema: hubspot_integration_tests_11
+      schema: hubspot_integration_tests_55
       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_integration_tests_11
+      schema: hubspot_integration_tests_55
       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_integration_tests_11
+      schema: hubspot_integration_tests_55
       threads: 8
     databricks:
       catalog: "{{ env_var('CI_DATABRICKS_DBT_CATALOG') }}"
       host: "{{ env_var('CI_DATABRICKS_DBT_HOST') }}"
       http_path: "{{ env_var('CI_DATABRICKS_DBT_HTTP_PATH') }}"
-      schema: hubspot_integration_tests_11
+      schema: hubspot_integration_tests_55
       threads: 8
       token: "{{ env_var('CI_DATABRICKS_DBT_TOKEN') }}"
       type: databricks

integration_tests/dbt_project.yml

@@ -1,10 +1,11 @@
 name: 'hubspot_integration_tests'
-version: '0.17.0'
+version: '0.17.1'
 
 profile: 'integration_tests'
 config-version: 2
 vars:
-  hubspot_schema: hubspot_integration_tests_11
+  hubspot_schema: hubspot_integration_tests_55
+  # hubspot_contact_merge_audit_enabled: true
   hubspot_source:
     hubspot_service_enabled: true
     hubspot_sales_enabled: true # enable when generating docs
@@ -64,6 +65,9 @@ vars:
 seeds:
   hubspot_integration_tests:
     +quote_columns: "{{ true if target.type == 'redshift' else false }}"
+    contact_merge_audit_data:
+      +column_types:
+        vid_to_merge: "{{ 'int64' if target.type == 'bigquery' else 'bigint' }}"
     owner_data:
       +column_types:
         owner_id: "{{ 'int64' if target.type == 'bigquery' else 'bigint' }}"

integration_tests/requirements.txt

@@ -4,4 +4,4 @@ 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,<1.7.13

integration_tests/seeds/contact_merge_audit_data.csv

@@ -1,5 +1,5 @@
 canonical_vid,contact_id,vid_to_merge,_fivetran_synced,entity_id,first_name,last_name,num_properties_moved,timestamp,user_id
-5555,5555,11111,2020-12-30 11:20:31,json,,,2,2019-10-08 15:50:57,
+5555,5555,2147483648,2020-12-30 11:20:31,json,,,2,2019-10-08 15:50:57,
 4444,4444,7777,2021-01-09 11:16:00,json,,,2,2019-09-03 15:39:29,
 3333,3333,8888,2020-12-29 11:16:02,json,,,2,2019-11-20 20:17:59,
 2222,2222,9999,2020-12-30 11:16:58,json,,,2,2019-12-10 18:14:34,

models/marketing/intermediate/int_hubspot__contact_merge_adjust.sql

@@ -19,7 +19,7 @@ with contacts as (
     from contacts
 
     left join contact_merge_audit
-        on contacts.contact_id = cast(contact_merge_audit.vid_to_merge as {{ dbt.type_int() }})
+        on cast(contacts.contact_id as {{ dbt.type_string() }}) = cast(contact_merge_audit.vid_to_merge as {{ dbt.type_string() }})
 
     where contact_merge_audit.vid_to_merge is null
 )