feat: add database migration support and connection utilities (#17)

Author: SparkZou

alembic.ini

@@ -0,0 +1,124 @@
+# A generic, single database configuration.
+
+[alembic]
+# path to migration scripts
+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
+# 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.
+# Any required deps can be 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 = os  # Use os.pathsep. Default configuration used for new projects.
+
+# 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
+
+# Database URL Configuration
+#
+# Note: This project reads the database URL from environment variables in alembic/env.py.
+# The sqlalchemy.url setting is intentionally left unset here.
+#
+# Supported environment variables (in priority order):
+# 1) DATABASE_URL - Full connection URL (e.g., postgresql+psycopg://user:pass@host:5432/db)
+# 2) Individual variables: DATABASE_HOST, DATABASE_PORT, DATABASE_USER, DATABASE_PASSWORD, DATABASE_NAME
+#
+# The env.py automatically normalizes URL schemes (postgres://, postgresql://, postgresql+asyncpg://)
+# to postgresql+psycopg:// for Alembic migrations.
+#
+# sqlalchemy.url =
+
+[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 = WARN
+handlers = console
+qualname =
+
+[logger_sqlalchemy]
+level = WARN
+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

alembic/env.py

@@ -0,0 +1,152 @@
+"""Alembic migration environment configuration."""
+
+import os
+
+# pylint: disable=no-member
+from logging.config import fileConfig
+from urllib.parse import quote
+
+from sqlalchemy import pool
+
+from alembic import context
+
+# Import Base metadata for autogenerate support
+# Note: We import from app.models.base which is side-effect free
+# (doesn't create database connections or read environment variables)
+from app.models.base import Base
+
+
+def get_sync_database_url() -> str:
+    """
+    Get synchronous database URL for Alembic migrations.
+
+    Alembic uses synchronous database connections, so we need to convert
+    the async URL (postgresql+asyncpg://) to sync format (postgresql+psycopg://).
+
+    Returns:
+        str: Synchronous database connection URL
+    """
+    # First try DATABASE_URL from environment
+    database_url = os.getenv("DATABASE_URL")
+    if database_url:
+        # Normalize common PostgreSQL DSNs to use the psycopg (sync) driver.
+        # Handle bare postgres:// and postgresql:// URLs that don't specify a driver.
+        if database_url.startswith("postgres://"):
+            # postgres://user:pass@host/db -> postgresql+psycopg://user:pass@host/db
+            database_url = "postgresql+psycopg://" + database_url[len("postgres://") :]
+        elif database_url.startswith("postgresql://") and not database_url.startswith("postgresql+"):
+            # postgresql://user:pass@host/db -> postgresql+psycopg://user:pass@host/db
+            database_url = "postgresql+psycopg://" + database_url[len("postgresql://") :]
+
+        # Convert async driver to sync driver if needed
+        # postgresql+asyncpg:// -> postgresql+psycopg://
+        if database_url.startswith("postgresql+asyncpg://"):
+            database_url = "postgresql+psycopg://" + database_url[len("postgresql+asyncpg://") :]
+
+        return database_url
+
+    # Construct from individual variables
+    db_host = os.getenv("DATABASE_HOST")
+    db_port = os.getenv("DATABASE_PORT", "5432")  # Default PostgreSQL port
+    db_user = os.getenv("DATABASE_USER")
+    db_pass = os.getenv("DATABASE_PASSWORD")
+    db_name = os.getenv("DATABASE_NAME")
+
+    # Validate required environment variables (consistent with app/database.py)
+    missing_vars = [
+        name
+        for name, value in [
+            ("DATABASE_HOST", db_host),
+            ("DATABASE_USER", db_user),
+            ("DATABASE_PASSWORD", db_pass),
+            ("DATABASE_NAME", db_name),
+        ]
+        if not value
+    ]
+
+    if missing_vars:
+        raise RuntimeError(
+            f"Database configuration is incomplete. Missing environment variables: {', '.join(missing_vars)}"
+        )
+
+    # At this point, we know these are not None
+    assert db_host is not None
+    assert db_user is not None
+    assert db_pass is not None
+    assert db_name is not None
+
+    # URL-encode username and password to handle special characters
+    # Use quote(..., safe="") instead of quote_plus() for URL userinfo section
+    db_user_encoded = quote(db_user, safe="")
+    db_pass_encoded = quote(db_pass, safe="")
+
+    # Use psycopg (sync) for Alembic migrations
+    return f"postgresql+psycopg://{db_user_encoded}:{db_pass_encoded}@{db_host}:{db_port}/{db_name}"
+
+
+# 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)
+
+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.
+
+    """
+    # Get URL from environment variables
+    url = get_sync_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.
+
+    """
+    from sqlalchemy import create_engine
+
+    # Get URL from environment variables and create engine directly
+    url = get_sync_database_url()
+    connectable = create_engine(url, 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()

alembic/script.py.mako

@@ -0,0 +1,24 @@
+"""${message}
+
+Revision ID: ${up_revision}
+Revises: ${down_revision | comma,n}
+Create Date: ${create_date}
+
+"""
+from alembic import op
+import sqlalchemy as sa
+${imports if imports else ""}
+
+# revision identifiers, used by Alembic.
+revision = ${repr(up_revision)}
+down_revision = ${repr(down_revision)}
+branch_labels = ${repr(branch_labels)}
+depends_on = ${repr(depends_on)}
+
+
+def upgrade() -> None:
+    ${upgrades if upgrades else "pass"}
+
+
+def downgrade() -> None:
+    ${downgrades if downgrades else "pass"}