Add pre-commit with GiHub Action (#56)

* Update pyproject.toml

* add pre-commit

* Create .pre-commit-config.yaml

* Comment out ruff

* Update .pre-commit-config.yaml

* General formatting

* Create format-and-fail.yml

* Update ci.yml

* Add pre-commit to dev dependencies

* Update pyproject.toml

app/shared/aa_utils.py

@@ -1,11 +1,13 @@
 # TODO: code in this file should eventually be moved to the auto-archiver code base
 
 from typing import List
-from loguru import logger
+
 from auto_archiver.core import Media, Metadata
+from loguru import logger
 
 from app.shared.db import models
 
+
 def get_all_urls(result: Metadata) -> List[models.ArchiveUrl]:
     db_urls = []
     for m in result.media:
@@ -29,4 +31,3 @@ def convert_if_media(media):
         except Exception as e:
             logger.debug(f"error parsing {media} : {e}")
     return False
-

app/shared/business_logic.py

@@ -2,6 +2,7 @@
 
 
 import datetime
+
 from sqlalchemy.orm import Session
 
 from app.shared.db import worker_crud

app/shared/db/database.py

@@ -1,8 +1,14 @@
-from functools import lru_cache
-from sqlalchemy import Engine, create_engine, event, text
-from sqlalchemy.orm import sessionmaker
 from contextlib import asynccontextmanager, contextmanager
-from sqlalchemy.ext.asyncio import create_async_engine, AsyncSession, AsyncEngine, async_sessionmaker
+from functools import lru_cache
+
+from sqlalchemy import Engine, create_engine, event, text
+from sqlalchemy.ext.asyncio import (
+    AsyncEngine,
+    AsyncSession,
+    async_sessionmaker,
+    create_async_engine,
+)
+from sqlalchemy.orm import sessionmaker
 
 from app.shared.settings import get_settings
 

app/shared/db/models.py

@@ -1,8 +1,17 @@
-from sqlalchemy import Column, String, JSON, DateTime, Boolean, Table, ForeignKey
-from sqlalchemy.sql import func
-from sqlalchemy.orm import relationship, declarative_base
 import uuid
 
+from sqlalchemy import (
+    JSON,
+    Boolean,
+    Column,
+    DateTime,
+    ForeignKey,
+    String,
+    Table,
+)
+from sqlalchemy.orm import declarative_base, relationship
+from sqlalchemy.sql import func
+
 
 Base = declarative_base()
 

app/shared/db/worker_crud.py

@@ -1,8 +1,10 @@
-from sqlalchemy.orm import Session
 from datetime import datetime
 
-from app.shared.db import models
+from sqlalchemy.orm import Session
+
 from app.shared import schemas
+from app.shared.db import models
+
 
 # TODO: isolate database operations away from worker and into WEB
 # ONLY WORKER

app/shared/log.py

@@ -1,4 +1,5 @@
 import traceback
+
 from loguru import logger
 
 
@@ -6,7 +7,7 @@ from loguru import logger
 logger.add("logs/api_logs.log", retention="30 days")
 logger.add("logs/error_logs.log", retention="30 days", level="ERROR")
 
-    
+
 def log_error(e: Exception, traceback_str: str = None, extra:str = ""):
     if not traceback_str: traceback_str = traceback.format_exc()
     if extra: extra = f"{extra}\n"

app/shared/schemas.py

@@ -1,7 +1,8 @@
+from datetime import datetime
 from typing import Annotated
+
 from annotated_types import Len
 from pydantic import BaseModel
-from datetime import datetime
 
 
 class SubmitSheet(BaseModel):

app/shared/settings.py

@@ -1,14 +1,15 @@
 
-from functools import lru_cache
 import os
+from functools import lru_cache
+from typing import Annotated, Set
+
+from annotated_types import Len
 from fastapi_mail import ConnectionConfig
 from pydantic_settings import BaseSettings, SettingsConfigDict
-from typing import Annotated, Set
-from annotated_types import Len
 
 
 class Settings(BaseSettings):
-    
+
     model_config = SettingsConfigDict(env_file=os.environ.get("ENVIRONMENT_FILE") , env_file_encoding='utf-8', extra='ignore', str_strip_whitespace=True)
 
 	# general
@@ -37,14 +38,14 @@ class Settings(BaseSettings):
         if self.REDIS_PASSWORD:
             return f"redis://:{self.REDIS_PASSWORD}@{self.REDIS_HOSTNAME}:6379"
         return f"redis://{self.REDIS_HOSTNAME}:6379"
-    
+
     # cronjobs
     CRON_ARCHIVE_SHEETS: bool = False
     CRON_DELETE_STALE_SHEETS: bool = False
     DELETE_STALE_SHEETS_DAYS: int = 14
     CRON_DELETE_SCHEDULED_ARCHIVES: bool = False
     DELETE_SCHEDULED_ARCHIVES_CHECK_EVERY_N_DAYS: int = 7
-    
+
 	# observability
     REPEAT_COUNT_METRICS_SECONDS: int = 30
 
@@ -73,4 +74,4 @@ class Settings(BaseSettings):
 
 @lru_cache
 def get_settings():
-    return Settings()
+    return Settings()

app/shared/task_messaging.py

@@ -1,8 +1,9 @@
 
 from functools import lru_cache
-from celery import Celery
-import redis
 
+from celery import Celery
+
+import redis
 from app.shared.settings import get_settings
 
 

app/shared/user_groups.py

@@ -1,9 +1,16 @@
 import json
 import os
+from typing import Dict, List, Set
+
 import yaml
 from loguru import logger
-from pydantic import BaseModel, computed_field, field_validator, Field, model_validator
-from typing import Dict, List, Set
+from pydantic import (
+    BaseModel,
+    Field,
+    computed_field,
+    field_validator,
+    model_validator,
+)
 from typing_extensions import Self
 
 

app/shared/utils/misc.py

@@ -7,4 +7,4 @@ def fnv1a_hash_mod(s: str, modulo:int) -> int:
         hash ^= ord(char)
         hash *= fnv_prime
         hash &= 0xFFFFFFFF # Keep it 32-bit
-    return (hash if hash < 0x80000000 else hash - 0x100000000) % modulo
+    return (hash if hash < 0x80000000 else hash - 0x100000000) % modulo