Merge pull request #6 from gwenwindflower/add-pre-commit

.github/workflows/ci.yml

@@ -10,14 +10,12 @@ jobs:
       - name: Checkout
         uses: actions/checkout@v4.1.0
       - name: Setup Python
-        uses: actions/setup-python@v4.7.0 
+        uses: actions/setup-python@v4.7.0
         with:
-          python-version: '3.10.x'
+          python-version: "3.10.x"
       - name: Install requirements
         run: python3 -m pip install -r requirements.txt
-      - name: Load data-test
+      - name: Run EL
         run: python3 el.py -lc
-      - name: Run transformations        
+      - name: Run T
         run: dbt deps && dbt build
-
-

.pre-commit-config.yaml

@@ -0,0 +1,28 @@
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v2.3.0
+    hooks:
+      - id: check-yaml
+        exclude: reports/evidence.plugins.yaml
+      - id: end-of-file-fixer
+      - id: trailing-whitespace
+      - id: requirements-txt-fixer
+  - repo: https://github.com/charliermarsh/ruff-pre-commit
+    rev: v0.0.291
+    hooks:
+      - id: ruff
+        args: [--fix, --exit-non-zero-on-fix]
+  - repo: https://github.com/PyCQA/isort
+    rev: 5.12.0
+    hooks:
+      - id: isort
+  - repo: https://github.com/psf/black
+    rev: 23.9.1
+    hooks:
+      - id: black
+  # - repo: https://github.com/sqlfluff/sqlfluff
+  #   rev: 2.3.2
+  #   hooks:
+  #     - id: sqlfluff-fix
+  #       additional_dependencies:
+  #         ["dbt-metricflow[duckdb]~=0.3.0", "sqlfluff-templater-dbt"]

.sqlfluff

@@ -1,8 +1,15 @@
 [sqlfluff]
 dialect = duckdb
+templater = dbt
+
+[sqlfluff:templater:dbt]
+profiles_dir = .
 
 [sqlfluff:indentation]
 tab_space_size = 4
 
 [sqlfluff:rules:capitalisation.keywords]
 capitalisation_policy = lower
+
+[sqlfluff:convention]
+select_trailing_comma = required

.sqlfluffignore

@@ -0,0 +1,3 @@
+target/
+dbt_packages/
+macros/

README.md

@@ -17,35 +17,35 @@ There are some basic tasks included using my preferred task runner [Task](https:
   <summary>macOS</summary>
   <br>
   Using Homebrew:
-  
+
   ```shell
   brew install go-task
   ```
 
 </details>
 <details>
-  
+
   <summary>Windows</summary>
   <br>
   Using Chocolatey:
-  
+
   ```shell
   choco install go-task
   ```
 
   Using Scoop:
-  
+
   ```shell
   scoop install task
   ```
 
 </details>
 <details>
-  
+
   <summary>Linux</summary>
   <br>
   Using Yay:
-  
+
   ```shell
   yay -S go-task-bin
   ```

el.py

@@ -1,10 +1,11 @@
 import argparse
 import os
-import requests
+from datetime import date, datetime, timedelta
+
 import duckdb
-from tqdm import tqdm
+import requests
 from halo import Halo
-from datetime import datetime, date, timedelta
+from tqdm import tqdm
 
 
 def validate_date(date_str):
@@ -65,18 +66,18 @@ def load_data():
     else:
         spinner_text = "🦆💾 Loading data into DuckDB..."
         connection = "./reports/github_archive.db"
-    
+
     spinner = Halo(text=spinner_text, spinner="dots")
     spinner.start()
-    
+
     con = duckdb.connect(database=connection, read_only=False)
     con.execute(
         """
         CREATE SCHEMA IF NOT EXISTS raw;
-        CREATE OR REPLACE TABLE raw.github_events AS 
+        CREATE OR REPLACE TABLE raw.github_events AS
         SELECT * FROM read_ndjson(
         """
-        "'" + data_path + '/*.json.gz' + "',"
+        "'" + data_path + "/*.json.gz" + "',"
         """
             columns={
                 'id': 'VARCHAR',
@@ -91,8 +92,8 @@ def load_data():
                 )',
                 'repo': 'STRUCT(id VARCHAR, name VARCHAR, url VARCHAR)',
                 'payload': 'JSON',
-                'public': 'BOOLEAN', 
-                'created_at': 'TIMESTAMP', 
+                'public': 'BOOLEAN',
+                'created_at': 'TIMESTAMP',
                 'org': 'STRUCT(
                     id VARCHAR,
                     login VARCHAR,

models/marts/pull_request_events.sql

@@ -50,7 +50,6 @@ unnest_json as (
         ->> '$.comments' as pull_request_comment_count,
         payload -> '$.pull_request' -> '$.user' ->> '$.login' as user_login,
         payload -> '$.pull_request' -> '$.user' ->> '$.id' as user_id,
-        payload -> '$.pull_request' -> '$.repo' ->> '$.id' as repo_id,
         payload
         -> '$.pull_request'
         -> '$.repo'

models/marts/repos.sql

@@ -11,7 +11,7 @@ distill_repos_from_events as (
         repo_id,
         repo_name,
         repo_url,
-        max(event_created_at) as repo_state_last_seen_at,
+        max(event_created_at) as repo_state_last_seen_at
 
     from {{ ref('stg_events') }}
 
@@ -28,8 +28,8 @@ rank_most_recent_repo_state as (
         row_number() over (
             partition by repo_id
             order by repo_state_last_seen_at desc
-        ) as repo_recency_rank,
- 
+        ) as repo_recency_rank
+
     from distill_repos_from_events
 
 ),
@@ -39,10 +39,10 @@ pull_most_recent_repo_state as (
     select
         repo_id,
         repo_name,
-        repo_url,
-    
+        repo_url
+
     from rank_most_recent_repo_state
-    
+
     where repo_recency_rank = 1
 
 )

models/marts/users.sql

@@ -3,23 +3,23 @@ with
 distill_user_states_from_events as (
 
     select
-        {{ 
+        {{
             dbt_utils.generate_surrogate_key([
                 'actor_id',
                 'actor_gravatar_id',
                 'actor_login',
                 'actor_display_login',
                 'actor_url',
                 'actor_avatar_url'
-            ]) 
+            ])
         }} as user_state_uuid,
         actor_id,
         actor_gravatar_id,
         actor_login,
         actor_display_login,
         actor_url,
         actor_avatar_url,
-        max(event_created_at) as user_state_last_seen_at,
+        max(event_created_at) as user_state_last_seen_at
 
     from {{ ref('stg_events') }}
 
@@ -37,10 +37,10 @@ rank_user_state_recency as (
         actor_url,
         actor_avatar_url,
         row_number() over (
-            partition by actor_id 
+            partition by actor_id
             order by user_state_last_seen_at desc
-        ) as user_state_recency_rank,
-    
+        ) as user_state_recency_rank
+
     from distill_user_states_from_events
 
 ),
@@ -53,7 +53,7 @@ pull_most_recent_user_state as (
         actor_login,
         actor_display_login,
         actor_url,
-        actor_avatar_url,
+        actor_avatar_url
 
     from rank_user_state_recency
 

models/staging/github/stg_events.sql

@@ -2,44 +2,43 @@ with
 
 source as (
 
-  select * from {{ source('github', 'github_events') }}
+    select * from {{ source('github', 'github_events') }}
 
 ),
 
 
 renamed as (
 
-  select
-    --- event
-    id as event_id,
-    type as event_type,
-    public as is_event_public,
-    created_at as event_created_at,
-
-    --- actor
-    actor.id as actor_id,
-    actor.gravatar_id as actor_gravatar_id,
-    actor.login as actor_login,
-    actor.display_login as actor_display_login,
-    actor.url as actor_url,
-    actor.avatar_url as actor_avatar_url,
-
-    --- repo
-    repo.id as repo_id,
-    repo.name as repo_name,
-    repo.url as repo_url,
-
-    --- org
-    org.id as org_id,
-    org.login as org_login,
-    org.gravatar_id as org_gravatar_id,
-    org.url as org_url,
-    org.avatar_url as org_avatar_url,
-
-    --- payload
-    payload
-
-  from source
+    select
+        --- event
+        id as event_id,
+        type as event_type,
+        public as is_event_public,
+        created_at as event_created_at,
+
+        payload,
+
+        --- actor
+        actor['id'] as actor_id,
+        actor['gravatar_id'] as actor_gravatar_id,
+        actor['login'] as actor_login,
+        actor['display_login'] as actor_display_login,
+        actor['url'] as actor_url,
+        actor['avatar_url'] as actor_avatar_url,
+
+        --- repo
+        repo['id'] as repo_id,
+        repo['name'] as repo_name,
+        repo['url'] as repo_url,
+
+        --- org
+        org['id'] as org_id,
+        org['login'] as org_login,
+        org['gravatar_id'] as org_gravatar_id,
+        org['url'] as org_url,
+        org['avatar_url'] as org_avatar_url
+
+    from source
 
 )
 

reports/.evidence/customization/custom-formatting.json

@@ -1,4 +1,4 @@
 {
   "version": "1.0",
   "customFormats": []
-}
+}

reports/.gitignore

@@ -6,4 +6,4 @@ node_modules
 .vscode/settings.json
 
 .duckdb
-.db
+.db

reports/.npmrc

@@ -1,3 +1,3 @@
 loglevel=error
 audit=false
-fund=false
+fund=false

reports/README.md

@@ -10,9 +10,9 @@ Check out the docs for [alternative install methods](https://docs.evidence.dev/g
 
 ```shell
 npx degit evidence-dev/template my-project
-cd my-project 
-npm install 
-npm run dev 
+cd my-project
+npm install
+npm run dev
 ```
 
 Once you've launched Evidence, this project includes a short tutorial to help you get started.

requirements.txt

@@ -1,5 +1,10 @@
+black~=23.9.1
 dbt-metricflow[duckdb]~=0.3.0
+halo~=0.0.31
+isort~=5.12.0
+pre-commit~=3.4.0
 requests~=2.31.0
+ruff~=0.0.291
+sqlfluff-templater-dbt~=2.3.2
+sqlfluff~=2.3.2
 tqdm~=4.66.1
-halo~=0.0.31
-sqlfluff~=2.3.0