Merge pull request #2 from katariina-jarvenmaki/refactoring_and_migrations

Refactoring and migrations
This commit is contained in:
Katariina Järvenmäki
2026-03-03 18:22:05 +00:00
committed by GitHub
25 changed files with 778 additions and 191 deletions
-1
View File
@@ -1 +0,0 @@
BASE_URL=http://localhost:8000
+4 -1
View File
@@ -1,3 +1,6 @@
app/__pycache__
__pycache__
.pytest_cache/
venv/
test.txt
test.txt
diff.txt
+9 -3
View File
@@ -10,7 +10,7 @@ source venv/bin/activate
## Run locally
```bash
uvicorn app.main:app --reload
python -m uvicorn app.main:app --reload --host 0.0.0.0 --port 8000
```
Then check:<br>
http://127.0.0.1:8000<br>
@@ -23,5 +23,11 @@ http://127.0.0.1:8000/shorten
```bash
PYTHONPATH=./ pytest
export PYTHONPATH=$(pwd)
pytest
```
python -m pytest --cov=app --cov-report=term-missing
```
## Running Alembic revision
```bash
cd /opt/kjc/int/URL-shortener
alembic revision --autogenerate -m "create urls table"
```
+118
View File
@@ -0,0 +1,118 @@
# A generic, single database configuration.
[alembic]
# path to migration scripts
# Use forward slashes (/) also on windows to provide an os agnostic path
script_location = alembic
# template used to generate migration file names; The default value is %%(rev)s_%%(slug)s
# Uncomment the line below if you want the files to be prepended with date and time
# see https://alembic.sqlalchemy.org/en/latest/tutorial.html#editing-the-ini-file
# for all available tokens
# file_template = %%(year)d_%%(month).2d_%%(day).2d_%%(hour).2d%%(minute).2d-%%(rev)s_%%(slug)s
# sys.path path, will be prepended to sys.path if present.
# defaults to the current working directory.
prepend_sys_path = .
# timezone to use when rendering the date within the migration file
# as well as the filename.
# If specified, requires the python>=3.9 or backports.zoneinfo library and tzdata library.
# Any required deps can installed by adding `alembic[tz]` to the pip requirements
# string value is passed to ZoneInfo()
# leave blank for localtime
# timezone =
# max length of characters to apply to the "slug" field
# truncate_slug_length = 40
# set to 'true' to run the environment during
# the 'revision' command, regardless of autogenerate
# revision_environment = false
# set to 'true' to allow .pyc and .pyo files without
# a source .py file to be detected as revisions in the
# versions/ directory
# sourceless = false
# version location specification; This defaults
# to alembic/versions. When using multiple version
# directories, initial revisions must be specified with --version-path.
# The path separator used here should be the separator specified by "version_path_separator" below.
# version_locations = %(here)s/bar:%(here)s/bat:alembic/versions
# version path separator; As mentioned above, this is the character used to split
# version_locations. The default within new alembic.ini files is "os", which uses os.pathsep.
# If this key is omitted entirely, it falls back to the legacy behavior of splitting on spaces and/or commas.
# Valid values for version_path_separator are:
#
# version_path_separator = :
# version_path_separator = ;
# version_path_separator = space
# version_path_separator = newline
#
# Use os.pathsep. Default configuration used for new projects.
version_path_separator = os
# set to 'true' to search source files recursively
# in each "version_locations" directory
# new in Alembic version 1.10
# recursive_version_locations = false
# the output encoding used when revision files
# are written from script.py.mako
# output_encoding = utf-8
sqlalchemy.url = sqlite:///./test.db
[post_write_hooks]
# post_write_hooks defines scripts or Python functions that are run
# on newly generated revision scripts. See the documentation for further
# detail and examples
# format using "black" - use the console_scripts runner, against the "black" entrypoint
# hooks = black
# black.type = console_scripts
# black.entrypoint = black
# black.options = -l 79 REVISION_SCRIPT_FILENAME
# lint with attempts to fix using "ruff" - use the exec runner, execute a binary
# hooks = ruff
# ruff.type = exec
# ruff.executable = %(here)s/.venv/bin/ruff
# ruff.options = --fix REVISION_SCRIPT_FILENAME
# Logging configuration
[loggers]
keys = root,sqlalchemy,alembic
[handlers]
keys = console
[formatters]
keys = generic
[logger_root]
level = WARNING
handlers = console
qualname =
[logger_sqlalchemy]
level = WARNING
handlers =
qualname = sqlalchemy.engine
[logger_alembic]
level = INFO
handlers =
qualname = alembic
[handler_console]
class = StreamHandler
args = (sys.stderr,)
level = NOTSET
formatter = generic
[formatter_generic]
format = %(levelname)-5.5s [%(name)s] %(message)s
datefmt = %H:%M:%S
+1
View File
@@ -0,0 +1 @@
Generic single-database configuration.
+82
View File
@@ -0,0 +1,82 @@
from alembic import context
from sqlalchemy import engine_from_config, pool
from logging.config import fileConfig
from app.db.base import Base
from app.db import models
from app.core.config import settings
target_metadata = Base.metadata
# this is the Alembic Config object, which provides
# access to the values within the .ini file in use.
config = context.config
# Interpret the config file for Python logging.
# This line sets up loggers basically.
if config.config_file_name is not None:
fileConfig(config.config_file_name)
# add your model's MetaData object here
# for 'autogenerate' support
# from myapp import mymodel
# target_metadata = mymodel.Base.metadata
target_metadata = Base.metadata
# other values from the config, defined by the needs of env.py,
# can be acquired:
# my_important_option = config.get_main_option("my_important_option")
# ... etc.
def run_migrations_offline() -> None:
"""Run migrations in 'offline' mode.
This configures the context with just a URL
and not an Engine, though an Engine is acceptable
here as well. By skipping the Engine creation
we don't even need a DBAPI to be available.
Calls to context.execute() here emit the given string to the
script output.
"""
config.set_main_option("sqlalchemy.url", settings.database_url)
context.configure(
url=url,
target_metadata=target_metadata,
literal_binds=True,
dialect_opts={"paramstyle": "named"},
)
with context.begin_transaction():
context.run_migrations()
def run_migrations_online() -> None:
"""Run migrations in 'online' mode.
In this scenario we need to create an Engine
and associate a connection with the context.
"""
connectable = engine_from_config(
config.get_section(config.config_ini_section, {}),
prefix="sqlalchemy.",
poolclass=pool.NullPool,
)
with connectable.connect() as connection:
context.configure(
connection=connection, target_metadata=target_metadata
)
with context.begin_transaction():
context.run_migrations()
if context.is_offline_mode():
run_migrations_offline()
else:
run_migrations_online()
+26
View File
@@ -0,0 +1,26 @@
"""${message}
Revision ID: ${up_revision}
Revises: ${down_revision | comma,n}
Create Date: ${create_date}
"""
from typing import Sequence, Union
from alembic import op
import sqlalchemy as sa
${imports if imports else ""}
# revision identifiers, used by Alembic.
revision: str = ${repr(up_revision)}
down_revision: Union[str, None] = ${repr(down_revision)}
branch_labels: Union[str, Sequence[str], None] = ${repr(branch_labels)}
depends_on: Union[str, Sequence[str], None] = ${repr(depends_on)}
def upgrade() -> None:
${upgrades if upgrades else "pass"}
def downgrade() -> None:
${downgrades if downgrades else "pass"}
@@ -0,0 +1,30 @@
"""create urls table
Revision ID: 0132ba841ec5
Revises:
Create Date: 2026-03-02 09:13:50.764599
"""
from typing import Sequence, Union
from alembic import op
import sqlalchemy as sa
# revision identifiers, used by Alembic.
revision: str = '0132ba841ec5'
down_revision: Union[str, None] = None
branch_labels: Union[str, Sequence[str], None] = None
depends_on: Union[str, Sequence[str], None] = None
def upgrade() -> None:
# ### commands auto generated by Alembic - please adjust! ###
pass
# ### end Alembic commands ###
def downgrade() -> None:
# ### commands auto generated by Alembic - please adjust! ###
pass
# ### end Alembic commands ###
+70
View File
@@ -0,0 +1,70 @@
# app/api/routes.py
from fastapi import APIRouter, Depends, HTTPException, status
from fastapi.responses import RedirectResponse
from sqlalchemy.orm import Session
from app.db.session import get_db
from app.schemas.url import (
URLCreate,
URLResponse,
URLStatsResponse,
MessageResponse,
)
from app.services import url_service
router = APIRouter()
@router.get("/", response_model=MessageResponse)
def home():
return {"message": "URL Shortener API"}
@router.post("/shorten", response_model=URLResponse)
def shorten_url(
request: URLCreate,
db: Session = Depends(get_db),
):
short_url = url_service.create_short_url(db, str(request.url))
return {"short_url": short_url}
@router.get("/{short_code}")
def redirect_to_url(
short_code: str,
db: Session = Depends(get_db),
):
original_url = url_service.get_original_url(db, short_code)
if not original_url:
raise HTTPException(
status_code=status.HTTP_404_NOT_FOUND,
detail="Shortened URL not found",
)
url_service.increment_clicks(db, short_code)
return RedirectResponse(url=original_url)
@router.get("/stats/{short_code}", response_model=URLStatsResponse)
def get_url_stats(
short_code: str,
db: Session = Depends(get_db),
):
stats = url_service.get_stats(db, short_code)
if not stats:
raise HTTPException(
status_code=status.HTTP_404_NOT_FOUND,
detail="URL stats not found",
)
return stats
@router.get("/health", response_model=MessageResponse)
def health_check():
return {"message": "healthy"}
+38
View File
@@ -0,0 +1,38 @@
# app/core/config.py
from functools import lru_cache
from pydantic_settings import BaseSettings
from typing import List
class Settings(BaseSettings):
app_name: str = "URL Shortener"
allowed_hosts: List[str] = ["*"]
database_url: str
# Server settings
host: str = "0.0.0.0"
port: int = 8000
base_url: str = "http://localhost:8000"
# Debug flag
debug: bool = True
# Optional future extensions
rate_limit_per_minute: int = 60
class Config:
env_file = ".env"
env_file_encoding = "utf-8"
case_sensitive = False
extra = "ignore"
# Cached singleton-style access
@lru_cache()
def get_settings() -> Settings:
return Settings()
# Global settings instance
settings = get_settings()
+6
View File
@@ -0,0 +1,6 @@
# app/db/base.py
from sqlalchemy.orm import DeclarativeBase
class Base(DeclarativeBase):
pass
+57
View File
@@ -0,0 +1,57 @@
# app/db/models.py
from sqlalchemy import String, Integer, DateTime, func, Index
from sqlalchemy.orm import Mapped, mapped_column
from datetime import datetime
from app.db.base import Base
from typing import Optional
class URL(Base):
__tablename__ = "urls"
id: Mapped[int] = mapped_column(
Integer,
primary_key=True,
index=True
)
short_code: Mapped[str] = mapped_column(
String(10),
unique=True,
nullable=False,
index=True
)
original_url: Mapped[str] = mapped_column(
String(2048),
nullable=False,
index=True
)
clicks: Mapped[int] = mapped_column(
Integer,
default=0,
nullable=False
)
created_at: Mapped[datetime] = mapped_column(
DateTime(timezone=True),
server_default=func.now(),
nullable=False
)
last_accessed: Mapped[Optional[datetime]] = mapped_column(
DateTime(timezone=True),
nullable=True
)
# Additional compound index for faster lookups
__table_args__ = (
Index("idx_short_original", "short_code", "original_url"),
)
def __repr__(self) -> str:
return (
f"<URL(id={self.id}, short_code='{self.short_code}', "
f"original_url='{self.original_url}', clicks={self.clicks})>"
)
+26
View File
@@ -0,0 +1,26 @@
# app/db/session.py
from sqlalchemy import create_engine
from sqlalchemy.orm import sessionmaker
from app.core.config import settings
# Create SQLAlchemy engine
engine = create_engine(
settings.database_url,
pool_pre_ping=True, # helps prevent stale connections
)
# Session factory
SessionLocal = sessionmaker(
autocommit=False,
autoflush=False,
bind=engine,
)
# Dependency for FastAPI
def get_db():
db = SessionLocal()
try:
yield db
finally:
db.close()
+17 -113
View File
@@ -1,124 +1,28 @@
from fastapi import FastAPI, HTTPException
from fastapi.responses import RedirectResponse
# app/main.py
from fastapi import FastAPI
from contextlib import asynccontextmanager
from app.utils import generate_short_code
from pydantic import BaseModel, HttpUrl
from pydantic_settings import BaseSettings
import sqlite3
import logging
from app.core.config import settings
from app.db.session import engine
from app.db.base import Base
from app.api.routes import router
class AppSettings(BaseSettings):
base_url: str = "http://localhost:8000"
database_url: str = "urls.db"
settings = AppSettings() # Load environment variables
# Set up logging configuration
logging.basicConfig(level=logging.INFO,
format="%(asctime)s - %(levelname)s - %(message)s")
logger = logging.getLogger(__name__)
# Database connection setup
@asynccontextmanager
async def lifespan(app: FastAPI):
conn = sqlite3.connect(settings.database_url)
conn.execute("""
CREATE TABLE IF NOT EXISTS urls (
id INTEGER PRIMARY KEY,
short_code TEXT UNIQUE,
original_url TEXT NOT NULL,
clicks INTEGER DEFAULT 0
);
""")
conn.execute("""
CREATE INDEX IF NOT EXISTS idx_short_code ON urls(short_code);
""")
conn.commit()
logger.info("Database initialized or already exists.")
Base.metadata.create_all(bind=engine)
yield
conn.close()
logger.info("Database connection closed.")
app = FastAPI(lifespan=lifespan)
def get_db_connection():
return sqlite3.connect(settings.database_url, check_same_thread=False)
class URLRequest(BaseModel):
url: HttpUrl
@app.get("/")
def home():
logger.info("Home endpoint accessed.")
return {"message": "URL Shortener API"}
@app.post("/shorten")
def shorten_url(request: URLRequest):
conn = get_db_connection()
existing = conn.execute(
"SELECT short_code FROM urls WHERE original_url = ?",
(str(request.url),)
).fetchone()
if existing:
conn.close()
return {"short_url": f"{settings.base_url}/{existing[0]}"}
short_code = generate_short_code()
while conn.execute(
"SELECT 1 FROM urls WHERE short_code = ?",
(short_code,)
).fetchone():
short_code = generate_short_code()
conn.execute(
"INSERT INTO urls (short_code, original_url, clicks) VALUES (?, ?, 0)",
(short_code, str(request.url))
def create_app() -> FastAPI:
app = FastAPI(
title=settings.app_name,
debug=settings.debug,
)
conn.commit()
conn.close()
return {"short_url": f"{settings.base_url}/{short_code}"}
app.include_router(router)
@app.get("/{short_code}")
def redirect_to_url(short_code: str):
conn = get_db_connection()
url_data = conn.execute(
"SELECT original_url FROM urls WHERE short_code = ?",
(short_code,)
).fetchone()
return app
if url_data is None:
conn.close()
raise HTTPException(status_code=404, detail="Shortened URL not found")
original_url = url_data[0]
conn.execute(
"UPDATE urls SET clicks = clicks + 1 WHERE short_code = ?",
(short_code,)
)
conn.commit()
conn.close()
return RedirectResponse(url=original_url)
@app.get("/stats/{short_code}")
def get_url_stats(short_code: str):
logger.info(f"Stats request received for short_code: {short_code}")
conn = get_db_connection()
url_data = conn.execute("SELECT original_url, clicks FROM urls WHERE short_code = ?", (short_code,)).fetchone()
if url_data is None:
logger.warning(f"Stats not found for {short_code}.")
conn.close()
raise HTTPException(status_code=404, detail="URL stats not found")
original_url, clicks = url_data
conn.close()
logger.info(f"Returning stats for {original_url}. Total clicks: {clicks}")
return {"original_url": original_url, "clicks": clicks}
app = create_app()
app.router.lifespan_context = lifespan
+24
View File
@@ -0,0 +1,24 @@
# app/schemas/url.py
from pydantic import BaseModel, HttpUrl
from datetime import datetime
from typing import Optional
class URLCreate(BaseModel):
url: HttpUrl
class URLResponse(BaseModel):
short_url: str
class URLStatsResponse(BaseModel):
original_url: HttpUrl
clicks: int
created_at: datetime
last_accessed: Optional[datetime] = None
class MessageResponse(BaseModel):
message: str
+103
View File
@@ -0,0 +1,103 @@
# app/services/url_service.py
from sqlalchemy.orm import Session
from sqlalchemy import select
from datetime import datetime
from typing import Optional
from app.db.models import URL
from app.utils.short_code import generate_short_code
from app.core.config import settings
SHORT_CODE_LENGTH = 6
MAX_GENERATION_ATTEMPTS = 5
def create_short_url(db: Session, original_url: str) -> str:
"""
Create a shortened URL or return existing one if already present.
"""
# 1️⃣ Check if URL already exists
existing = db.execute(
select(URL).where(URL.original_url == original_url)
).scalar_one_or_none()
if existing:
return f"{settings.base_url}/{existing.short_code}"
# 2️⃣ Generate unique short code with collision handling
for _ in range(MAX_GENERATION_ATTEMPTS):
short_code = generate_short_code(SHORT_CODE_LENGTH)
collision = db.execute(
select(URL).where(URL.short_code == short_code)
).scalar_one_or_none()
if not collision:
new_url = URL(
short_code=short_code,
original_url=original_url,
)
db.add(new_url)
db.commit()
db.refresh(new_url)
return f"{settings.base_url}/{new_url.short_code}"
# If we somehow fail multiple times
raise RuntimeError("Failed to generate unique short code")
def get_original_url(db: Session, short_code: str) -> Optional[str]:
"""
Retrieve original URL for redirection.
"""
url_entry = db.execute(
select(URL).where(URL.short_code == short_code)
).scalar_one_or_none()
if not url_entry:
return None
return url_entry.original_url
def increment_clicks(db: Session, short_code: str) -> bool:
"""
Increment click counter and update last_accessed timestamp.
"""
url_entry = db.execute(
select(URL).where(URL.short_code == short_code)
).scalar_one_or_none()
if not url_entry:
return False
url_entry.clicks += 1
url_entry.last_accessed = datetime.utcnow()
db.commit()
return True
def get_stats(db: Session, short_code: str) -> Optional[dict]:
"""
Return URL statistics.
"""
url_entry = db.execute(
select(URL).where(URL.short_code == short_code)
).scalar_one_or_none()
if not url_entry:
return None
return {
"original_url": url_entry.original_url,
"clicks": url_entry.clicks,
"created_at": url_entry.created_at,
"last_accessed": url_entry.last_accessed,
}
-7
View File
@@ -1,7 +0,0 @@
# app/settings.py
import os
# Example configuration
database_url = os.getenv("DATABASE_URL", "sqlite:///default.db")
debug = os.getenv("DEBUG", "True") == "True"
-66
View File
@@ -1,66 +0,0 @@
from fastapi.testclient import TestClient
import sys
import os
sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), '..')))
from app.main import app
from app import settings
import tempfile
import pytest
@pytest.fixture
def test_client():
with tempfile.NamedTemporaryFile() as tmp:
settings.database_url = tmp.name
with TestClient(app) as c:
yield c
@pytest.fixture
def use_temp_db():
with tempfile.NamedTemporaryFile() as tmp:
settings.database_url = tmp.name
yield
def test_home(test_client):
response = test_client.get("/")
assert response.status_code == 200
assert response.json() == {"message": "URL Shortener API"}
def test_shorten_url(test_client):
response = test_client.post("/shorten", json={"url": "https://google.com"})
assert response.status_code == 200
data = response.json()
assert "short_url" in data
short_url = data["short_url"]
assert short_url.startswith("http://localhost:8000/")
def test_redirect(test_client):
response = test_client.post("/shorten", json={"url": "https://google.com"})
short_url = response.json()["short_url"]
code = short_url.split("/")[-1]
redirect = test_client.get(f"/{code}", follow_redirects=False)
assert redirect.status_code == 307
def test_duplicate_url_returns_same_code(test_client):
r1 = test_client.post("/shorten", json={"url": "https://example.com"})
r2 = test_client.post("/shorten", json={"url": "https://example.com"})
assert r1.status_code == 200
assert r2.status_code == 200
assert r1.json()["short_url"] == r2.json()["short_url"]
def test_stats_endpoint(test_client):
response = test_client.post("/shorten", json={"url": "https://stats-test.com"})
code = response.json()["short_url"].split("/")[-1]
test_client.get(f"/{code}", follow_redirects=False)
stats = test_client.get(f"/stats/{code}")
assert stats.status_code == 200
data = stats.json()
assert data["clicks"] == 1
def test_redirect_404(test_client):
response = test_client.get("/nonexistent", follow_redirects=False)
assert response.status_code == 404
+64
View File
@@ -0,0 +1,64 @@
# app/tests/conftest.py
import pytest
from sqlalchemy import create_engine
from sqlalchemy.orm import sessionmaker
from fastapi.testclient import TestClient
from app.main import app
from app.db.base import Base
from app.db.session import get_db
# Use in-memory SQLite for tests
TEST_DATABASE_URL = "sqlite+pysqlite:///:memory:"
@pytest.fixture(scope="function")
def db_session():
"""
Creates a new database session for a test.
Rolls back everything after test finishes.
"""
engine = create_engine(
TEST_DATABASE_URL,
connect_args={"check_same_thread": False},
)
TestingSessionLocal = sessionmaker(
autocommit=False,
autoflush=False,
bind=engine,
)
# Create tables
Base.metadata.create_all(bind=engine)
db = TestingSessionLocal()
try:
yield db
finally:
db.close()
Base.metadata.drop_all(bind=engine)
@pytest.fixture(scope="function")
def client(db_session):
"""
Overrides get_db dependency to use test database.
"""
def override_get_db():
try:
yield db_session
finally:
pass
app.dependency_overrides[get_db] = override_get_db
with TestClient(app) as c:
yield c
app.dependency_overrides.clear()
+93
View File
@@ -0,0 +1,93 @@
# app/tests/test_routes.py
import pytest
def test_home(client):
response = client.get("/")
assert response.status_code == 200
assert response.json() == {"message": "URL Shortener API"}
def test_health(client):
response = client.get("/health")
assert response.status_code == 200
assert response.json() == {"message": "healthy"}
def test_shorten_url(client):
response = client.post(
"/shorten",
json={"url": "https://google.com"},
)
assert response.status_code == 200
data = response.json()
assert "short_url" in data
assert data["short_url"].startswith("http://")
def test_shorten_invalid_url(client):
response = client.post(
"/shorten",
json={"url": "not-a-valid-url"},
)
assert response.status_code == 422 # Pydantic validation error
def test_duplicate_url_returns_same_code(client):
r1 = client.post("/shorten", json={"url": "https://example.com"})
r2 = client.post("/shorten", json={"url": "https://example.com"})
assert r1.status_code == 200
assert r2.status_code == 200
assert r1.json()["short_url"] == r2.json()["short_url"]
def test_redirect_success(client):
shorten = client.post(
"/shorten",
json={"url": "https://redirect-test.com"},
)
short_url = shorten.json()["short_url"]
code = short_url.split("/")[-1]
response = client.get(f"/{code}", follow_redirects=False)
assert response.status_code in (302, 307)
def test_redirect_404(client):
response = client.get("/nonexistent", follow_redirects=False)
assert response.status_code == 404
def test_stats_success(client):
shorten = client.post(
"/shorten",
json={"url": "https://stats-test.com"},
)
short_url = shorten.json()["short_url"]
code = short_url.split("/")[-1]
# Trigger one click
client.get(f"/{code}", follow_redirects=False)
stats = client.get(f"/stats/{code}")
assert stats.status_code == 200
data = stats.json()
assert data["original_url"] == "https://stats-test.com"
assert data["clicks"] == 1
assert "created_at" in data
def test_stats_404(client):
response = client.get("/stats/doesnotexist")
assert response.status_code == 404
+2
View File
@@ -1,3 +1,5 @@
# app/utils.py
import string
import random
View File
+8
View File
@@ -0,0 +1,8 @@
# app/utils/short_code.py
import string
import random
def generate_short_code(length: int = 6) -> str:
"""Generate a random alphanumeric short code."""
chars = string.ascii_letters + string.digits
return ''.join(random.choices(chars, k=length))
BIN
View File
Binary file not shown.
BIN
View File
Binary file not shown.