Align backend data models with expanded paper schema (#9)

* Adapt models to new paper schema

* Normalize username identifier

* add DatabaseConstants

* Fix pylint warnings and migrate legacy users table

* add pylint ignore

* fix pylint GitHub workflow

* adapt encoding of .pylintrc

* introduce services and repositories and refactor code

* fix pylint issues

* adapt __init__.py files for services and repositories

* pylint

* adapt to code comments

* adapt backend-lint.yml to check return types

* fix backend-lint.yml

* add mypy to workflow

* add mypy.ini

* add missing return types

Author: MoSchmidt

.github/workflows/backend-lint.yml

@@ -0,0 +1,51 @@
+name: Backend Lint
+
+on: [push]
+
+jobs:
+  pylint:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v6
+        with:
+          python-version: "3.14"
+
+      - name: Install dependencies
+        working-directory: backend
+        run: |
+          python -m pip install --upgrade pip
+          pip install -r requirements.txt
+          pip install pylint
+
+      - name: Run Pylint
+        working-directory: backend
+        run: |
+          pylint --rcfile=../.pylintrc $(git ls-files '*.py')
+
+  mypy:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v6
+        with:
+          python-version: "3.14"
+
+      - name: Install MyPy and dependencies
+        working-directory: backend
+        run: |
+          python -m pip install --upgrade pip
+          pip install -r requirements.txt
+          pip install mypy
+
+      - name: Run MyPy
+        run: |
+          mypy backend

.github/workflows/pylint.yml

@@ -0,0 +1,13 @@
+[MASTER]
+ignore=inquiro-env, __pycache__, build, dist
+
+[MESSAGES CONTROL]
+disable =
+    too-few-public-methods,
+    not-callable,
+    missing-module-docstring,
+
+
+[TYPECHECK]
+ignored-modules =
+    sqlalchemy.sql.functions

.pylintrc

@@ -0,0 +1,20 @@
+"""Enumerations shared across database models."""
+
+from enum import Enum
+
+
+class PaperSource(Enum):
+    """Supported sources for fetching papers."""
+
+    ARXIV = "ARXIV"
+
+
+class PaperType(Enum):
+    """High-level classifications for scholarly papers."""
+
+    JOURNAL = "JOURNAL"
+    CONFERENCE = "CONFERENCE"
+    PREPRINT = "PREPRINT"
+    WORKSHOP = "WORKSHOP"
+    THESIS = "THESIS"
+    OTHER = "OTHER"

backend/app/constants/__init__.py

@@ -30,4 +30,4 @@ class Settings(BaseSettings):
     )
 
 
-settings = Settings()
+settings = Settings()  # type: ignore[call-arg]

backend/app/constants/database_constants.py

@@ -2,9 +2,10 @@
 
 import logging
 from importlib import import_module
+from typing import Any, Generator
 
 from sqlalchemy import create_engine
-from sqlalchemy.orm import declarative_base, sessionmaker
+from sqlalchemy.orm import declarative_base, sessionmaker, Session
 
 from app.core.config import settings
 
@@ -22,13 +23,20 @@
 
 def init_db() -> None:
     """Automatically create or update tables based on SQLAlchemy models."""
-    import_module("app.models.user")
+
+    for module in (
+            "app.models.user",
+            "app.models.project",
+            "app.models.paper",
+            "app.models.project_paper",
+    ):
+        import_module(module)
     logger.info("🔄 Creating / updating database schema...")
     Base.metadata.create_all(bind=engine)
     logger.info("✅ Database schema up to date.")
 
 
-def get_db():
+def get_db() -> Generator[Session, Any, None]:
     """Yield a database session for FastAPI routes."""
     db = SESSION_LOCAL()
     try:

backend/app/core/config.py

@@ -19,7 +19,7 @@ def create_access_token(data: Dict[str, Any], expires_delta: Optional[timedelta]
 
     to_encode = data.copy()
     expire = datetime.now(timezone.utc) + (
-        expires_delta or timedelta(minutes=settings.ACCESS_TOKEN_EXPIRE_MINUTES)
+            expires_delta or timedelta(minutes=settings.ACCESS_TOKEN_EXPIRE_MINUTES)
     )
     to_encode.update({"exp": expire})
     return jwt.encode(to_encode, settings.JWT_SECRET_KEY, algorithm=ALGORITHM)
@@ -30,7 +30,7 @@ def create_refresh_token(data: Dict[str, Any], expires_delta: Optional[timedelta
 
     to_encode = data.copy()
     expire = datetime.now(timezone.utc) + (
-        expires_delta or timedelta(days=settings.REFRESH_TOKEN_EXPIRE_DAYS)
+            expires_delta or timedelta(days=settings.REFRESH_TOKEN_EXPIRE_DAYS)
     )
     to_encode.update({"exp": expire, "type": "refresh"})
     return jwt.encode(to_encode, settings.JWT_SECRET_KEY, algorithm=ALGORITHM)

backend/app/core/database.py

@@ -1,7 +1,6 @@
-"""Application entry point for the Inquiro FastAPI service."""
-
 import logging
 from contextlib import asynccontextmanager
+from typing import Any, AsyncGenerator
 
 from fastapi import FastAPI
 from starlette.middleware.cors import CORSMiddleware
@@ -24,7 +23,7 @@
 # Lifespan Event Handlers (Modern FastAPI)
 # ---------------------------------------------------------
 @asynccontextmanager
-async def lifespan(_app: FastAPI):
+async def lifespan(_app: FastAPI) -> AsyncGenerator[None, Any]:
     """Initialize and tear down application resources."""
 
     logger.info("🚀 Starting Inquiro API in '%s' mode...", settings.ENVIRONMENT)
@@ -48,7 +47,6 @@ async def lifespan(_app: FastAPI):
     lifespan=lifespan,
 )
 
-
 # ---------------------------------------------------------
 # Development-only CORS configuration
 # ---------------------------------------------------------
@@ -65,7 +63,6 @@ async def lifespan(_app: FastAPI):
         allow_headers=["*"],
     )
 
-
 # ---------------------------------------------------------
 # Register Routers
 # ---------------------------------------------------------

backend/app/core/security.py

@@ -0,0 +1,15 @@
+"""Expose SQLAlchemy models for convenient imports."""
+
+from .paper import Paper, PaperSource, PaperType
+from .project import Project
+from .project_paper import ProjectPaper
+from .user import User
+
+__all__ = [
+    "Paper",
+    "PaperSource",
+    "PaperType",
+    "Project",
+    "ProjectPaper",
+    "User",
+]