OMM: Bring in SQLAlchemy, get database working

open-media-match/.devcontainer/devcontainer.json

@@ -50,5 +50,5 @@
   "mounts": [
     "source=python-threatexchange-cmdhistory,target=/commandhistory,type=volume"
   ],
-  "postAttachCommand": "OMM_CONFIG=/workspace/.devcontainer/omm_config.py flask --app OpenMediaMatch run --debug"
+  "postAttachCommand": "/workspace/.devcontainer/startup.sh"
 }

open-media-match/.devcontainer/omm_config.py

@@ -1,9 +1,9 @@
 # Database configuration
 PRODUCTION = False
-DBUSER = 'media_match'
-DBPASS = 'hunter2'
-DBHOST = 'db'
-DBNAME = 'media_match'
+DBUSER = "media_match"
+DBPASS = "hunter2"
+DBHOST = "db"
+DBNAME = "media_match"
 DATABASE_URI = f"postgresql+psycopg2://{DBUSER}:{DBPASS}@{DBHOST}/{DBNAME}"
 
 ROLE_HASHER = True

open-media-match/.devcontainer/startup.sh

@@ -0,0 +1,5 @@
+#!/bin/bash
+set -e
+export OMM_CONFIG=/workspace/.devcontainer/omm_config.py
+flask --app OpenMediaMatch db upgrade --directory src/openMediaMatch/migrations
+flask --app OpenMediaMatch run --debug

open-media-match/pyproject.toml

@@ -17,6 +17,9 @@ classifiers = [
 ]
 dependencies = [
     "flask",
+    "flask_sqlalchemy",
+    "flask_migrate",
+    "psycopg2",
 ]
 
 [project.optional-dependencies]

open-media-match/src/OpenMediaMatch/__init__.py

@@ -2,16 +2,27 @@
 
 import os
 import flask
+import flask_migrate
+import flask_sqlalchemy
 
 from .blueprints import hashing, matching, curation
 
+database = flask_sqlalchemy.SQLAlchemy()
+migrate = flask_migrate.Migrate()
+
 
 def create_app():
     """
     Create and configure the Flask app
     """
     app = flask.Flask(__name__)
     app.config.from_envvar("OMM_CONFIG")
+    app.config.update(
+        SQLALCHEMY_DATABASE_URI=app.config.get("DATABASE_URI"),
+        SQLALCHEMY_TRACK_MODIFICATIONS=False,
+    )
+    database.init_app(app)
+    migrate.init_app(app, database)
 
     @app.route("/")
     def index():
@@ -41,4 +52,14 @@ def status():
     if app.config.get("ROLE_MATCHER", False):
         app.register_blueprint(curation.bp, url_prefix="/c")
 
+    from . import models
+
+    @app.cli.command("seed")
+    def seed_data():
+        # TODO: This is a placeholder for where some useful seed data can be loaded;
+        # particularly important for development
+        bank = models.Bank(name="bad_stuff", enabled=True)
+        database.session.add(bank)
+        database.session.commit()
+
     return app

open-media-match/src/OpenMediaMatch/app.py

@@ -0,0 +1,3 @@
+from OpenMediaMatch import create_app
+
+app = create_app()

open-media-match/src/OpenMediaMatch/migrations/README

@@ -0,0 +1 @@
+Single-database configuration for Flask.

open-media-match/src/OpenMediaMatch/migrations/alembic.ini

@@ -0,0 +1,50 @@
+# A generic, single database configuration.
+
+[alembic]
+# template used to generate migration files
+# file_template = %%(rev)s_%%(slug)s
+
+# set to 'true' to run the environment during
+# the 'revision' command, regardless of autogenerate
+# revision_environment = false
+
+
+# Logging configuration
+[loggers]
+keys = root,sqlalchemy,alembic,flask_migrate
+
+[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
+
+[logger_flask_migrate]
+level = INFO
+handlers =
+qualname = flask_migrate
+
+[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

open-media-match/src/OpenMediaMatch/migrations/env.py

@@ -0,0 +1,107 @@
+import logging
+from logging.config import fileConfig
+
+from flask import current_app
+
+from alembic import context
+
+# 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.
+fileConfig(config.config_file_name)
+logger = logging.getLogger("alembic.env")
+
+
+def get_engine():
+    try:
+        # this works with Flask-SQLAlchemy<3 and Alchemical
+        return current_app.extensions["migrate"].db.get_engine()
+    except TypeError:
+        # this works with Flask-SQLAlchemy>=3
+        return current_app.extensions["migrate"].db.engine
+
+
+def get_engine_url():
+    try:
+        return get_engine().url.render_as_string(hide_password=False).replace("%", "%%")
+    except AttributeError:
+        return str(get_engine().url).replace("%", "%%")
+
+
+# add your model's MetaData object here
+# for 'autogenerate' support
+# from myapp import mymodel
+# target_metadata = mymodel.Base.metadata
+config.set_main_option("sqlalchemy.url", get_engine_url())
+target_db = current_app.extensions["migrate"].db
+
+# 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 get_metadata():
+    if hasattr(target_db, "metadatas"):
+        return target_db.metadatas[None]
+    return target_db.metadata
+
+
+def run_migrations_offline():
+    """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.
+
+    """
+    url = config.get_main_option("sqlalchemy.url")
+    context.configure(url=url, target_metadata=get_metadata(), literal_binds=True)
+
+    with context.begin_transaction():
+        context.run_migrations()
+
+
+def run_migrations_online():
+    """Run migrations in 'online' mode.
+
+    In this scenario we need to create an Engine
+    and associate a connection with the context.
+
+    """
+
+    # this callback is used to prevent an auto-migration from being generated
+    # when there are no changes to the schema
+    # reference: http://alembic.zzzcomputing.com/en/latest/cookbook.html
+    def process_revision_directives(context, revision, directives):
+        if getattr(config.cmd_opts, "autogenerate", False):
+            script = directives[0]
+            if script.upgrade_ops.is_empty():
+                directives[:] = []
+                logger.info("No changes in schema detected.")
+
+    connectable = get_engine()
+
+    with connectable.connect() as connection:
+        context.configure(
+            connection=connection,
+            target_metadata=get_metadata(),
+            process_revision_directives=process_revision_directives,
+            **current_app.extensions["migrate"].configure_args,
+        )
+
+        with context.begin_transaction():
+            context.run_migrations()
+
+
+if context.is_offline_mode():
+    run_migrations_offline()
+else:
+    run_migrations_online()

open-media-match/src/OpenMediaMatch/migrations/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():
+    ${upgrades if upgrades else "pass"}
+
+
+def downgrade():
+    ${downgrades if downgrades else "pass"}

open-media-match/src/OpenMediaMatch/migrations/versions/b44643ee7ef0_.py

@@ -0,0 +1,42 @@
+"""empty message
+
+Revision ID: b44643ee7ef0
+Revises: 
+Create Date: 2023-08-29 11:09:14.206946
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = "b44643ee7ef0"
+down_revision = None
+branch_labels = None
+depends_on = None
+
+
+def upgrade():
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.create_table(
+        "banks",
+        sa.Column("id", sa.Integer(), autoincrement=True, nullable=False),
+        sa.Column("name", sa.String(length=255), nullable=False),
+        sa.Column("enabled", sa.Boolean(), nullable=False),
+        sa.PrimaryKeyConstraint("id"),
+    )
+    op.create_table(
+        "hashes",
+        sa.Column("id", sa.Integer(), autoincrement=True, nullable=False),
+        sa.Column("enabled", sa.Boolean(), nullable=False),
+        sa.Column("value", sa.LargeBinary(), nullable=False),
+        sa.PrimaryKeyConstraint("id"),
+    )
+    # ### end Alembic commands ###
+
+
+def downgrade():
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.drop_table("hashes")
+    op.drop_table("banks")
+    # ### end Alembic commands ###

open-media-match/src/OpenMediaMatch/models.py

@@ -0,0 +1,17 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+
+from . import database as db
+
+
+class Bank(db.Model):
+    __tablename__ = "banks"
+    id = db.Column(db.Integer, primary_key=True, autoincrement=True)
+    name = db.Column(db.String(255), nullable=False)
+    enabled = db.Column(db.Boolean, nullable=False)
+
+
+class Hash(db.Model):
+    __tablename__ = "hashes"
+    id = db.Column(db.Integer, primary_key=True, autoincrement=True)
+    enabled = db.Column(db.Boolean, nullable=False)
+    value = db.Column(db.LargeBinary, nullable=False)