Merge pull request #58 from fivetran/release/v0.8.1

fivetran-avinash · web-flow · commit 7b41b31ce8be · 2024-10-23T13:35:40.000-07:00
[Release] Version 0.8.1: Current_timestamp macro updates, pull request join fix
diff --git a/.gitignore b/.gitignore
@@ -5,4 +5,6 @@ logs/
 keyfile.json
 .DS_Store
 develop/
-dbt_packages/
+dbt_packages/
+env/
+package-lock.yml
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -1,5 +1,18 @@
+# dbt_github v0.8.1  
+This release contains the following updates:
+
+## Bug Fixes 
+- Replaced the deprecated `dbt_current_timestamp.backcompat()` macro with the up-to-date `dbt_current_timestamp`. The deprecated macro occasionally returned the system timezone instead of the expected UTC timestamp, leading to incorrect downstream metrics like negative values for `days_issue_open`. [PR #58](https://github.com/fivetran/dbt_github/pull/58)
+- Updated the join type in `int_github__pull_request_times` to ensure pull requests without explicitly requested reviewers are no longer dropped. [PR #57](https://github.com/fivetran/dbt_github/pull/57)
+
+## Under the Hood:
+- Added consistency tests for `github__issues` and `github__pull_requests` to ensure new changes don't change the output of either model. (Some measures are omitted from the comparison tests, since they're measures based on the `current_timestamp`, which differs between validation test runs). [PR #58](https://github.com/fivetran/dbt_github/pull/58)
+
+## Contributors
+- [@samkessaram](https://github.com/samkessaram) ([PR #57](https://github.com/fivetran/dbt_github/pull/57))
+
 # dbt_github v0.8.0
-[PR #53](https://github.com/fivetran/dbt_jira/dbt_github/53) contains the following updates:
+[PR #53](https://github.com/fivetran/dbt_github/pull/53) contains the following updates:
 
 ## 🚨 Breaking Change 🚨
 - For consistency with other Fivetran packages, added default target schemas in `dbt_project.yml`. This is a breaking change since the model outputs will now be stored in a schema called `<your target schema>_github` by default. You will need to update any of your downstream use cases to point to the new schema.
@@ -80,6 +93,7 @@
 
 ## Contributors
 - [@jackiexsun](https://github.com/jackiexsun) ([#31](https://github.com/fivetran/dbt_github/pull/31))
+
 # dbt_github v0.5.0
 ## 🚨 Breaking Changes 🚨
 - The addition of the `label` source model results in the reference within `int_github__issue_label` to break. As a result, with the addition of upstream changes within `dbt_github_source` and the new `int_github__issue_label_join` model this issue has been resolved. ([#26](https://github.com/fivetran/dbt_github/pull/26))
diff --git a/dbt_project.yml b/dbt_project.yml
@@ -1,6 +1,6 @@
 config-version: 2
 name: 'github'
-version: '0.8.0'
+version: '0.8.1'
 require-dbt-version: [">=1.3.0", "<2.0.0"]
 models:
   github:
diff --git a/docs/catalog.json b/docs/catalog.json
diff --git a/docs/index.html b/docs/index.html
diff --git a/docs/manifest.json b/docs/manifest.json
diff --git a/docs/run_results.json b/docs/run_results.json
diff --git a/integration_tests/ci/sample.profiles.yml b/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: github_integration_tests
+      schema: github_integration_tests_1
       threads: 8
     bigquery:
       type: bigquery
       method: service-account-json
       project: 'dbt-package-testing'
-      schema: github_integration_tests
+      schema: github_integration_tests_1
       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: github_integration_tests
+      schema: github_integration_tests_1
       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: github_integration_tests
+      schema: github_integration_tests_1
       threads: 8
     databricks:
       catalog: null
       host: "{{ env_var('CI_DATABRICKS_DBT_HOST') }}"
       http_path: "{{ env_var('CI_DATABRICKS_DBT_HTTP_PATH') }}"
-      schema: github_integration_tests
+      schema: github_integration_tests_1
       threads: 2
       token: "{{ env_var('CI_DATABRICKS_DBT_TOKEN') }}"
       type: databricks
diff --git a/integration_tests/dbt_project.yml b/integration_tests/dbt_project.yml
@@ -1,10 +1,10 @@
 name: 'github_integration_tests'
-version: '0.8.0'
+version: '0.8.1'
 config-version: 2
 profile: 'integration_tests'
 vars:
   github_source:
-    github_schema: github_integration_tests
+    github_schema: github_integration_tests_1
     github_issue_assignee_identifier: "github_issue_assignee_data"
     github_issue_closed_history_identifier: "github_issue_closed_history_data"
     github_issue_comment_identifier: "github_issue_comment_data"
@@ -19,6 +19,10 @@ vars:
     github_requested_reviewer_history_identifier: "github_requested_reviewer_history_data"
     github_team_identifier: "github_team_data"
     github_user_identifier: "github_user_data"
+
+models:
+  +schema: "github_{{ var('directed_schema','dev') }}"
+
 seeds:
   github_integration_tests:
     +quote_columns: "{{ true if target.type == 'redshift' else false }}"
diff --git a/integration_tests/packages.yml b/integration_tests/packages.yml
@@ -1,2 +1,2 @@
 packages:
-  - local: ../
+  - local: ../
diff --git a/integration_tests/tests/consistency_issues.sql b/integration_tests/tests/consistency_issues.sql
@@ -0,0 +1,48 @@
+{{ config(
+    tags="fivetran_validations",
+    enabled=var('fivetran_validation_tests_enabled', false)
+) }}
+
+-- this test ensures the github__issues end model matches the prior version
+with prod as (
+    select * except(days_issue_open, labels, repository_team_names, assignees)  --the differences in prod/dev run times will lead to discrepancies because it leverages current_timestamp, and string aggs don't always have the same order
+    from {{ target.schema }}_github_prod.github__issues
+    where date(updated_at) < date({{ dbt.current_timestamp() }})
+),
+
+dev as (
+    select * except(days_issue_open, labels, repository_team_names, assignees)   --the differences in prod/dev run times will lead to slight discrepancies because it leverages current_timestamp, and string aggs don't always order the same
+    from {{ target.schema }}_github_dev.github__issues
+    where date(updated_at) < date({{ dbt.current_timestamp() }})
+),
+
+prod_not_in_dev as (
+    -- rows from prod not found in dev
+    select * from prod
+    except distinct
+    select * from dev
+),
+
+dev_not_in_prod as (
+    -- rows from dev not found in prod
+    select * from dev
+    except distinct
+    select * from prod
+),
+
+final as (
+    select
+        *,
+        'from prod' as source
+    from prod_not_in_dev
+
+    union all -- union since we only care if rows are produced
+
+    select
+        *,
+        'from dev' as source
+    from dev_not_in_prod
+)
+
+select *
+from final
diff --git a/integration_tests/tests/consistency_issues_counts.sql b/integration_tests/tests/consistency_issues_counts.sql
@@ -0,0 +1,33 @@
+{{ config(
+    tags="fivetran_validations",
+    enabled=var('fivetran_validation_tests_enabled', false)
+) }}
+
+with prod as (
+    select 
+        1 as join_key,
+        count(*) as total_prod_pr_count
+    from {{ target.schema }}_github_prod.github__issues
+    group by 1
+),
+
+dev as (
+    select 
+        1 as join_key,
+        count(*) as total_dev_pr_count
+    from {{ target.schema }}_github_dev.github__issues
+    group by 1
+),
+
+final as (
+    select
+        total_prod_pr_count,
+        total_dev_pr_count
+    from prod
+    full outer join dev
+        on dev.join_key = prod.join_key
+)
+
+select *
+from final
+where total_dev_pr_count != total_prod_pr_count
diff --git a/integration_tests/tests/consistency_pull_requests.sql b/integration_tests/tests/consistency_pull_requests.sql
@@ -0,0 +1,48 @@
+{{ config(
+    tags="fivetran_validations",
+    enabled=var('fivetran_validation_tests_enabled', false)
+) }}
+
+-- this test ensures the github__pull_requests end model matches the prior version
+with prod as (
+    select * except(days_issue_open, hours_request_review_to_first_review, hours_request_review_to_first_action, hours_request_review_to_merge)  --the differences in prod/dev run times will lead to discrepancies because these fields leverages current_timestamp
+    from {{ target.schema }}_github_prod.github__pull_requests    
+    where date(updated_at) < date({{ dbt.current_timestamp() }})
+),
+
+dev as (
+    select * except(days_issue_open, hours_request_review_to_first_review, hours_request_review_to_first_action, hours_request_review_to_merge)  --the differences in prod/dev run times will lead to discrepancies because these fields leverages current_timestamp
+    from {{ target.schema }}_github_prod.github__pull_requests  
+    where date(updated_at) < date({{ dbt.current_timestamp() }})
+),
+
+prod_not_in_dev as (
+    -- rows from prod not found in dev
+    select * from prod
+    except distinct
+    select * from dev
+),
+
+dev_not_in_prod as (
+    -- rows from dev not found in prod
+    select * from dev
+    except distinct
+    select * from prod
+),
+
+final as (
+    select
+        *,
+        'from prod' as source
+    from prod_not_in_dev
+
+    union all -- union since we only care if rows are produced
+
+    select
+        *,
+        'from dev' as source
+    from dev_not_in_prod
+)
+
+select *
+from final
diff --git a/integration_tests/tests/consistency_pull_requests_counts.sql b/integration_tests/tests/consistency_pull_requests_counts.sql
@@ -0,0 +1,33 @@
+{{ config(
+    tags="fivetran_validations",
+    enabled=var('fivetran_validation_tests_enabled', false)
+) }}
+
+with prod as (
+    select 
+        1 as join_key,
+        count(*) as total_prod_pr_count
+    from {{ target.schema }}_github_prod.github__pull_requests   
+    group by 1
+),
+
+dev as (
+    select 
+        1 as join_key,
+        count(*) as total_dev_pr_count
+    from {{ target.schema }}_github_dev.github__pull_requests  
+    group by 1
+),
+
+final as (
+    select
+        total_prod_pr_count,
+        total_dev_pr_count
+    from prod
+    full outer join dev
+        on dev.join_key = prod.join_key
+)
+
+select *
+from final
+where total_dev_pr_count != total_prod_pr_count
diff --git a/models/intermediate/int_github__issue_open_length.sql b/models/intermediate/int_github__issue_open_length.sql
@@ -26,7 +26,7 @@ close_events_with_timestamps as (
   select
     issue_id,
     updated_at as valid_starting,
-    coalesce(lead(updated_at) over (partition by issue_id order by updated_at), {{ dbt.current_timestamp_backcompat() }}) as valid_until,
+    coalesce(lead(updated_at) over (partition by issue_id order by updated_at), {{ dbt.current_timestamp() }}) as valid_until,
     is_closed
   from close_events_stacked
 )
diff --git a/models/intermediate/int_github__pull_request_times.sql b/models/intermediate/int_github__pull_request_times.sql
@@ -39,7 +39,7 @@ first_request_time as (
       min(requested_reviewer_history.created_at) as time_of_first_request,
       min(pull_request_review.submitted_at) as time_of_first_review_post_request
     from pull_request
-    join requested_reviewer_history on requested_reviewer_history.pull_request_id = pull_request.pull_request_id
+    left join requested_reviewer_history on requested_reviewer_history.pull_request_id = pull_request.pull_request_id
     left join pull_request_review on pull_request_review.pull_request_id = pull_request.pull_request_id
       and pull_request_review.submitted_at > requested_reviewer_history.created_at
     group by 1, 2
@@ -50,14 +50,14 @@ select
   issue_merged.merged_at,
   {{ dbt.datediff(
                         'time_of_first_request', 
-                        "coalesce(time_of_first_review_post_request, " ~ dbt.current_timestamp_backcompat() ~ ")", 
+                        "coalesce(time_of_first_review_post_request, " ~ dbt.current_timestamp() ~ ")", 
                         'second') 
   }}/ 60/60 as hours_request_review_to_first_review,
   {{ dbt.datediff(
                         'time_of_first_request', 
                         "least(
-                            coalesce(time_of_first_requested_reviewer_review, " ~ dbt.current_timestamp_backcompat() ~ "),
-                            coalesce(issue.closed_at, " ~ dbt.current_timestamp_backcompat() ~ "))", 
+                            coalesce(time_of_first_requested_reviewer_review, " ~ dbt.current_timestamp() ~ "),
+                            coalesce(issue.closed_at, " ~ dbt.current_timestamp() ~ "))", 
                         'second') 
   }} / 60/60 as hours_request_review_to_first_action,
   {{ dbt.datediff('time_of_first_request', 'merged_at', 'second') }}/ 60/60 as hours_request_review_to_merge

Original file line number	Diff line number	Diff line change
`@@ -1,2 +1,2 @@`
`1`	`1`	`packages:`
`2`		`- - local: ../`
	`2`	`+ - local: ../`