Added valid authors test + ran pre-commit

.github/workflows/pull_request.yml

@@ -3,7 +3,7 @@ name: Pull request checks
 on:
   pull_request:
     paths-ignore:
-      - 'webapp/**'
+      - "webapp/**"
 env:
   DUCKDB_PATH: github_contributions.duckdb
 

.github/workflows/webapp_ci.yml

@@ -3,7 +3,7 @@ name: Web-app CI
 on:
   pull_request:
     paths:
-      - 'webapp/**'
+      - "webapp/**"
 env:
   WORKING_DIRECTORY: ./webapp
 

models/marts/fct_pull_requests.sql

@@ -1,12 +1,15 @@
-with authors as (
-    select *
-    FROM (VALUES
-        {%- for author in var("authors") -%}
-            ('{{ author.name }}', '{{  author.organization }}')
-            {%- if not loop.last %}, {%- endif -%}
-        {%- endfor -%}
-    ) Author(name, organization)
-)
+with
+    authors as (
+        select *
+        from
+            (
+                values
+                    {%- for author in var("authors") -%}
+                        ('{{ author.name }}', '{{  author.organization }}')
+                        {%- if not loop.last %}, {%- endif -%}
+                    {%- endfor -%}
+            ) author(name, organization)
+    )
 
 select
     pull_requests.title,
@@ -26,8 +29,5 @@ select
     pull_requests.pull_request_merged_at as merged_at,
     pull_requests.reactions_total_count,
     pull_requests.html_url as url,
-from
-        {{ ref("int_pull_requests") }} AS pull_requests
-    left join
-         authors
-    ON pull_requests.user_login = authors.name
+from {{ ref("int_pull_requests") }} as pull_requests
+left join authors on pull_requests.user_login = authors.name

models/staging/stg_github_contributions.yml

@@ -8,10 +8,9 @@ models:
           - not_null
           - unique
       - name: user_login
-# TODO(anyone) temporarily disabled test because it keeps failing, debug and revert this later
-#        tests:
-#          - accepted_values:
-#              values: "{{ var('author_string').split(',') }}"
+        tests:
+          - only_valid_authors:
+              valid_authors: "{{ var('author_string').split(',') }}"
 
   - name: stg_repositories
     tests:

tests/generic/test_only_valid_authors.sql

@@ -0,0 +1,23 @@
+{% test only_valid_authors(model, column_name, valid_authors) %}
+
+with validation as (
+    select
+        distinct lower({{ column_name }}) as author
+    from {{ model }}
+),
+
+validation_errors as (
+    select
+        author
+    from validation
+    where author not in (
+        {%- for author in valid_authors -%}
+            '{{ author | lower }}'{% if not loop.last %},{% endif %}
+        {%- endfor -%}
+    )
+)
+
+select *
+from validation_errors
+
+{% endtest %}