feat: implement database migration system with Alembic

- Added Alembic configuration and migration scripts to facilitate database schema changes.
- Implemented a run_migrations function to execute migrations during application startup.
- Created migration scripts to transfer data from the old public schema to the new pad_ws schema, ensuring data integrity and consistency.
- Updated requirements.txt to include Alembic as a dependency for migration management.

Author: atyrode

src/backend/database/alembic.ini

@@ -0,0 +1,123 @@
+# A generic, single database configuration.
+
+[alembic]
+# path to migration scripts
+# Use forward slashes (/) also on windows to provide an os agnostic path
+script_location = migrations
+
+# Use a more descriptive file template that includes date and time
+file_template = %%(year)d_%%(month).2d_%%(day).2d_%%(hour).2d%%(minute).2d-%%(rev)s_%%(slug)s
+
+# 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 migrations/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:migrations/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
+
+# The SQLAlchemy connection URL is set in env.py from environment variables
+sqlalchemy.url = postgresql://postgres:postgres@localhost/pad
+
+
+[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 = check --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

src/backend/database/database.py

@@ -3,13 +3,17 @@
 """
 
 import os
+import asyncio
 from typing import AsyncGenerator
 from urllib.parse import quote_plus as urlquote
+from pathlib import Path
 
 from sqlalchemy.ext.asyncio import create_async_engine, AsyncSession
 from sqlalchemy.orm import sessionmaker
 from sqlalchemy.schema import CreateSchema
 from fastapi import Depends
+from alembic.config import Config
+from alembic import command
 
 from .models import Base, SCHEMA_NAME
 
@@ -35,8 +39,41 @@
     engine, class_=AsyncSession, expire_on_commit=False
 )
 
+async def run_migrations() -> None:
+    """Run database migrations using Alembic"""
+    # Get the path to the alembic.ini file
+    alembic_ini_path = Path(__file__).parent / "alembic.ini"
+    
+    # Create Alembic configuration
+    alembic_cfg = Config(str(alembic_ini_path))
+    
+    # Set the script_location to the correct path
+    # This ensures Alembic finds the migrations directory
+    alembic_cfg.set_main_option('script_location', str(Path(__file__).parent / "migrations"))
+    
+    # Define a function to run in a separate thread
+    def run_upgrade():
+        # Import the command module here to avoid import issues
+        from alembic import command
+        
+        # Set attributes that env.py might need
+        import sys
+        from pathlib import Path
+        
+        # Add the database directory to sys.path
+        db_dir = Path(__file__).parent
+        if str(db_dir) not in sys.path:
+            sys.path.insert(0, str(db_dir))
+        
+        # Run the upgrade command
+        command.upgrade(alembic_cfg, "head")
+    
+    # Run the migrations in a separate thread to avoid blocking the event loop
+    await asyncio.to_thread(run_upgrade)
+
 async def init_db() -> None:
     """Initialize the database with required tables"""
+    # Create schema and tables
     async with engine.begin() as conn:
         await conn.execute(CreateSchema(SCHEMA_NAME, if_not_exists=True))
         await conn.run_sync(Base.metadata.create_all)

src/backend/database/migrations/env.py

@@ -0,0 +1,106 @@
+from logging.config import fileConfig
+import os
+import sys
+from pathlib import Path
+
+from sqlalchemy import engine_from_config
+from sqlalchemy import pool
+from sqlalchemy.engine import URL
+
+from alembic import context
+from dotenv import load_dotenv
+
+# Add the parent directory to sys.path
+sys.path.append(str(Path(__file__).parent.parent.parent.parent))
+
+# Load environment variables from .env file
+load_dotenv()
+
+# 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)
+
+# Import the Base metadata from the models
+# We need to handle imports differently to avoid module not found errors
+import importlib.util
+import os
+
+# Get the absolute path to the models module
+models_path = os.path.join(os.path.dirname(os.path.dirname(os.path.abspath(__file__))), "models", "__init__.py")
+
+# Load the module dynamically
+spec = importlib.util.spec_from_file_location("models", models_path)
+models = importlib.util.module_from_spec(spec)
+spec.loader.exec_module(models)
+
+# Get Base and SCHEMA_NAME from the loaded module
+Base = models.Base
+SCHEMA_NAME = models.SCHEMA_NAME
+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.
+
+
+# Get database connection details from environment variables
+DB_USER = os.getenv('POSTGRES_USER', 'postgres')
+DB_PASSWORD = os.getenv('POSTGRES_PASSWORD', 'postgres')
+DB_NAME = os.getenv('POSTGRES_DB', 'pad')
+DB_HOST = os.getenv('POSTGRES_HOST', 'localhost')
+DB_PORT = os.getenv('POSTGRES_PORT', '5432')
+
+# Override sqlalchemy.url in alembic.ini
+config.set_main_option('sqlalchemy.url', f"postgresql://{DB_USER}:{DB_PASSWORD}@{DB_HOST}:{DB_PORT}/{DB_NAME}")
+
+def run_migrations_offline() -> None:
+    """Run migrations in 'offline' mode."""
+    url = config.get_main_option("sqlalchemy.url")
+    context.configure(
+        url=url,
+        target_metadata=target_metadata,
+        literal_binds=True,
+        dialect_opts={"paramstyle": "named"},
+        include_schemas=True,
+        version_table_schema=SCHEMA_NAME,
+    )
+
+    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,
+            include_schemas=True,
+            version_table_schema=SCHEMA_NAME
+        )
+
+        with context.begin_transaction():
+            context.run_migrations()
+
+
+if context.is_offline_mode():
+    run_migrations_offline()
+else:
+    run_migrations_online()

src/backend/database/migrations/script.py.mako

@@ -0,0 +1,28 @@
+"""${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:
+    """Upgrade schema."""
+    ${upgrades if upgrades else "pass"}
+
+
+def downgrade() -> None:
+    """Downgrade schema."""
+    ${downgrades if downgrades else "pass"}