Create database schema and initial python package

Author: szapp

.env.example

@@ -0,0 +1,8 @@
+# Environment variables
+# Copy this file to `.env` and fill in the values
+# Do not commit `.env` to the repository
+DB_HOST_POOL=
+DB_DATABASE=
+DB_USER=
+DB_PASSWORD=
+CONTACT_EMAIL=

create_schema.py

@@ -0,0 +1,85 @@
+"""
+This script creates and fills the schema for the database with data.
+If the schema already exists, it will be overwritten (dropped and
+recreated). Any data in the tables will be lost.
+
+The schema is described in the file schema.sql. The data is loaded
+from the cleaned CSV files in the data folder.
+"""
+
+import pandas as pd
+from sqlalchemy.sql import text
+
+from mangoleaf.connection import Connection
+
+
+def main():
+    # Establish a connection to the database
+
+    db_engine = Connection().get()
+
+    # Create schema from SQL file
+    with open("schema.sql") as f:
+        sql_commands = f.read()
+
+    with db_engine.connect() as connection:
+        for command in sql_commands.split(";"):
+            if command.strip():
+                connection.execute(text(command))
+        connection.commit()
+
+    # Load cleaned data locally
+    books = pd.read_csv("data/books/clean/books.csv", dtype="object")
+    mangas = pd.read_csv("data/mangas/clean/mangas.csv", dtype="object")
+    books_ratings = pd.read_csv("data/books/clean/ratings.csv", dtype="object")
+    mangas_ratings = pd.read_csv("data/mangas/clean/ratings.csv", dtype="object")
+
+    # Fill the static data: Books
+    df = books[["ISBN", "Book-Title", "Book-Author", "Image-URL-M"]]
+    df = df.rename(
+        columns={
+            "ISBN": "item_id",
+            "Book-Title": "title",
+            "Book-Author": "author",
+            "Image-URL-M": "image",
+        }
+    )
+    df.to_sql("books", db_engine, if_exists="append", index=False)
+
+    # Fill the static data: Mangas
+    df = mangas[["anime_id", "English name", "Other name", "Image URL"]]
+    df = df.rename(
+        columns={
+            "anime_id": "item_id",
+            "English name": "title",
+            "Other name": "other_title",
+            "Image URL": "image",
+        }
+    )
+    df.to_sql("mangas", db_engine, if_exists="append", index=False)
+
+    # Create users
+    user_id = set(books_ratings["User-ID"].unique())
+    user_id |= set(mangas_ratings["user_id"].unique())
+    user_id = list(user_id)
+    usernames = [f"User {i}" for i in user_id]
+    passwords = [f"password{i}" for i in user_id]
+    df = pd.DataFrame(dict(user_id=user_id, username=usernames, password=passwords))
+    df.to_sql("users", db_engine, if_exists="append", index=False)
+
+    # Fill the ratings: Books
+    df = books_ratings.rename(
+        columns={"User-ID": "user_id", "ISBN": "item_id", "Book-Rating": "rating"}
+    )
+    df.to_sql("books_ratings", db_engine, if_exists="append", index=False)
+
+    # Fill the ratings: Mangas
+    df = mangas_ratings.rename(columns={"anime_id": "item_id"})
+    df.to_sql("mangas_ratings", db_engine, if_exists="append", index=False)
+
+    # Close the connection
+    db_engine.dispose()
+
+
+if __name__ == "__main__":
+    main()

mangoleaf/__init__.py

@@ -0,0 +1,8 @@
+"""
+Mango Leaf is a Python package providing the backend for the web
+application of the same name.
+"""
+
+__all__ = ["Connection"]
+
+from .connection import Connection

mangoleaf/connection.py

@@ -0,0 +1,60 @@
+"""
+Establish a connection to the database
+"""
+
+import os
+
+from dotenv import load_dotenv
+from sqlalchemy import create_engine
+from sqlalchemy.pool import QueuePool
+
+
+def singleton(class_):
+    """Source: https://stackoverflow.com/questions/6760685"""
+    instances = {}
+
+    def getinstance(*args, **kwargs):
+        if class_ not in instances:
+            instances[class_] = class_(*args, **kwargs)
+        return instances[class_]
+
+    return getinstance
+
+
+@singleton
+class Connection:
+    def __init__(self):
+        """Establish a connection to the Postgress database"""
+        print("Establishing a connection to the database")
+
+        load_dotenv()
+
+        self.connection_string = "{protocol}://{user}:{password}@{host}/{database}?{query}".format(
+            protocol="postgresql+psycopg2",
+            user=os.getenv("DB_USER"),
+            password=os.getenv("DB_PASSWORD"),
+            host=os.getenv("DB_HOST_POOL"),
+            database=os.getenv("DB_DATABASE"),
+            query="sslmode=require",
+        )
+
+        self.engine = create_engine(
+            self.connection_string,
+            poolclass=QueuePool,
+            pool_size=10,
+            max_overflow=20,
+            pool_timeout=30,
+            pool_recycle=1800,
+            pool_pre_ping=True,
+        )
+
+    def get(self):
+        """
+        Get the connection to the database
+
+        Returns
+        -------
+        sqlalchemy.engine.base.Engine
+            Connection to the database
+        """
+        return self.engine

pyproject.toml

@@ -0,0 +1,33 @@
+[build-system]
+requires = ["flit_core >=3.2,<4"]
+build-backend = "flit_core.buildapi"
+
+[project]
+name = "mangoleaf"
+version = "0.0.1"
+description = "Mango Leaf is a Python package providing the backend for the web application of the same name."
+authors = [
+  { name = "Max Yurchak" },
+  { name = "S\u00f6ren Zapp" },
+]
+license = { file = "LICENSE" }
+readme = "README.md"
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "License :: OSI Approved :: MIT License"
+]
+requires-python = "~=3.12"
+
+[tool.black]
+line-length = 99
+include = '\.pyi?$'
+exclude = '''
+/(
+    \.git
+  | \.venv
+)/
+'''
+
+[tool.ruff.lint.isort]
+known_first_party = ["mangoleaf"]
+force_sort_within_sections = true

schema.sql

@@ -0,0 +1,57 @@
+DROP TABLE IF EXISTS books_ratings CASCADE;
+DROP TABLE IF EXISTS mangas_ratings CASCADE;
+
+DROP TABLE IF EXISTS books_popular CASCADE;
+DROP TABLE IF EXISTS mangas_popular CASCADE;
+DROP TABLE IF EXISTS books_item_based CASCADE;
+DROP TABLE IF EXISTS mangas_item_based CASCADE;
+DROP TABLE IF EXISTS books_user_based CASCADE;
+DROP TABLE IF EXISTS mangas_user_based CASCADE;
+
+DROP TABLE IF EXISTS books CASCADE;
+DROP TABLE IF EXISTS mangas CASCADE;
+DROP TABLE IF EXISTS users CASCADE;
+
+-- User table (dynamic)
+
+CREATE TABLE users (
+  user_id INTEGER PRIMARY KEY,
+  username VARCHAR(50) NOT NULL UNIQUE,
+  password VARCHAR(255) NOT NULL
+);
+
+-- Book and manga tables (static)
+
+CREATE TABLE books (
+  item_id VARCHAR(20) PRIMARY KEY,
+  title VARCHAR(255) NOT NULL,
+  author VARCHAR(255),
+  image VARCHAR(255)
+);
+
+CREATE TABLE mangas (
+  item_id INTEGER PRIMARY KEY,
+  title VARCHAR(255) NOT NULL,
+  other_title VARCHAR(255),
+  image VARCHAR(255)
+);
+
+-- Ratings tables (semi-static)
+
+CREATE TABLE books_ratings (
+  user_id INTEGER NOT NULL,
+  item_id VARCHAR(20) NOT NULL,
+  rating INTEGER NOT NULL CHECK (rating >= 1 AND rating <= 10),
+  PRIMARY KEY (user_id, item_id),
+  FOREIGN KEY (user_id) REFERENCES users(user_id),
+  FOREIGN KEY (item_id) REFERENCES books(item_id)
+);
+
+CREATE TABLE mangas_ratings (
+  user_id INTEGER NOT NULL,
+  item_id INTEGER NOT NULL,
+  rating INTEGER NOT NULL CHECK (rating >= 1 AND rating <= 10),
+  PRIMARY KEY (user_id, item_id),
+  FOREIGN KEY (user_id) REFERENCES users(user_id),
+  FOREIGN KEY (item_id) REFERENCES mangas(item_id)
+);