diff --git a/.env.dist b/.env.dist new file mode 100644 index 0000000..5632e56 --- /dev/null +++ b/.env.dist @@ -0,0 +1,5 @@ +POSTGRES_HOST=localhost +POSTGRES_PORT=5432 +POSTGRES_DB=rollup +POSTGRES_USER=rollup +POSTGRES_PASSWORD=rollup diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..7e9210d --- /dev/null +++ b/.gitignore @@ -0,0 +1,217 @@ +.env +.venv/ + + + + + + + + + + + + + + +# Byte-compiled / optimized / DLL files +__pycache__/ +*.py[codz] +*$py.class + +# C extensions +*.so + +# Distribution / packaging +.Python +build/ +develop-eggs/ +dist/ +downloads/ +eggs/ +.eggs/ +lib/ +lib64/ +parts/ +sdist/ +var/ +wheels/ +share/python-wheels/ +*.egg-info/ +.installed.cfg +*.egg +MANIFEST + +# PyInstaller +# Usually these files are written by a python script from a template +# before PyInstaller builds the exe, so as to inject date/other infos into it. +*.manifest +*.spec + +# Installer logs +pip-log.txt +pip-delete-this-directory.txt + +# Unit test / coverage reports +htmlcov/ +.tox/ +.nox/ +.coverage +.coverage.* +.cache +nosetests.xml +coverage.xml +*.cover +*.py,cover +.hypothesis/ +.pytest_cache/ +cover/ + +# Translations +*.mo +*.pot + +# Django stuff: +*.log +local_settings.py +db.sqlite3 +db.sqlite3-journal + +# Flask stuff: +instance/ +.webassets-cache + +# Scrapy stuff: +.scrapy + +# Sphinx documentation +docs/_build/ + +# PyBuilder +.pybuilder/ +target/ + +# Jupyter Notebook +.ipynb_checkpoints + +# IPython +profile_default/ +ipython_config.py + +# pyenv +# For a library or package, you might want to ignore these files since the code is +# intended to run in multiple environments; otherwise, check them in: +# .python-version + +# pipenv +# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control. +# However, in case of collaboration, if having platform-specific dependencies or dependencies +# having no cross-platform support, pipenv may install dependencies that don't work, or not +# install all needed dependencies. +#Pipfile.lock + +# UV +# Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control. +# This is especially recommended for binary packages to ensure reproducibility, and is more +# commonly ignored for libraries. +#uv.lock + +# poetry +# Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control. +# This is especially recommended for binary packages to ensure reproducibility, and is more +# commonly ignored for libraries. +# https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control +#poetry.lock +#poetry.toml + +# pdm +# Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control. +#pdm.lock +# pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it +# in version control. +# https://pdm.fming.dev/latest/usage/project/#working-with-version-control +.pdm.toml +.pdm-python +.pdm-build/ + +# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm +__pypackages__/ + +# Celery stuff +celerybeat-schedule +celerybeat.pid + +# SageMath parsed files +*.sage.py + +# Environments +.env +.envrc +.venv +env/ +venv/ +ENV/ +env.bak/ +venv.bak/ + +# Spyder project settings +.spyderproject +.spyproject + +# Rope project settings +.ropeproject + +# mkdocs documentation +/site + +# mypy +.mypy_cache/ +.dmypy.json +dmypy.json + +# Pyre type checker +.pyre/ + +# pytype static type analyzer +.pytype/ + +# Cython debug symbols +cython_debug/ + +# PyCharm +# JetBrains specific template is maintained in a separate JetBrains.gitignore that can +# be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore +# and can be added to the global gitignore or merged into this file. For a more nuclear +# option (not recommended) you can uncomment the following to ignore the entire idea folder. +#.idea/ + +# Abstra +# Abstra is an AI-powered process automation framework. +# Ignore directories containing user credentials, local state, and settings. +# Learn more at https://abstra.io/docs +.abstra/ + +# Visual Studio Code +# Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore +# that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore +# and can be added to the global gitignore or merged into this file. However, if you prefer, +# you could uncomment the following to ignore the entire vscode folder +# .vscode/ + +# Ruff stuff: +.ruff_cache/ + +# PyPI configuration file +.pypirc + +# Cursor +# Cursor is an AI-powered code editor. `.cursorignore` specifies files/directories to +# exclude from AI features like autocomplete and code analysis. Recommended for sensitive data +# refer to https://docs.cursor.com/context/ignore-files +.cursorignore +.cursorindexingignore + +# Marimo +marimo/_static/ +marimo/_lsp/ +__marimo__/ diff --git a/.vscode/settings.json b/.vscode/settings.json new file mode 100644 index 0000000..c8b28e2 --- /dev/null +++ b/.vscode/settings.json @@ -0,0 +1,6 @@ +{"[python]": { + "editor.formatOnSave": true, + "editor.defaultFormatter": "ms-python.black-formatter" +}, +"python.experiments.enabled": false +} \ No newline at end of file diff --git a/alembic.ini b/alembic.ini new file mode 100644 index 0000000..54f756d --- /dev/null +++ b/alembic.ini @@ -0,0 +1,141 @@ +# A generic, single database configuration. + +[alembic] +# path to migration scripts. +# this is typically a path given in POSIX (e.g. forward slashes) +# format, relative to the token %(here)s which refers to the location of this +# ini file +script_location = %(here)s/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. for multiple paths, the path separator +# is defined by "path_separator" below. +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 /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 "path_separator" +# below. +# version_locations = %(here)s/bar:%(here)s/bat:%(here)s/alembic/versions + +# path_separator; This indicates what character is used to split lists of file +# paths, including version_locations and prepend_sys_path within configparser +# files such as alembic.ini. +# The default rendered in new alembic.ini files is "os", which uses os.pathsep +# to provide os-dependent path splitting. +# +# Note that in order to support legacy alembic.ini files, this default does NOT +# take place if path_separator is not present in alembic.ini. If this +# option is omitted entirely, fallback logic is as follows: +# +# 1. Parsing of the version_locations option falls back to using the legacy +# "version_path_separator" key, which if absent then falls back to the legacy +# behavior of splitting on spaces and/or commas. +# 2. Parsing of the prepend_sys_path option falls back to the legacy +# behavior of splitting on spaces, commas, or colons. +# +# Valid values for path_separator are: +# +# path_separator = : +# path_separator = ; +# path_separator = space +# path_separator = newline +# +# Use os.pathsep. Default configuration used for new projects. +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 + +# database URL. This is consumed by the user-maintained env.py script only. +# other means of configuring database URLs may be customized within the env.py +# file. +sqlalchemy.url = driver://user:pass@localhost/dbname + + +[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. This is also consumed by the user-maintained +# env.py script only. +[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 diff --git a/alembic/README b/alembic/README new file mode 100644 index 0000000..98e4f9c --- /dev/null +++ b/alembic/README @@ -0,0 +1 @@ +Generic single-database configuration. \ No newline at end of file diff --git a/alembic/env.py b/alembic/env.py new file mode 100644 index 0000000..a595681 --- /dev/null +++ b/alembic/env.py @@ -0,0 +1,85 @@ +import os +from logging.config import fileConfig +from dotenv import load_dotenv +from sqlalchemy import engine_from_config, pool +from alembic import context + + +load_dotenv() + + +db_url = f"postgresql://{os.getenv('POSTGRES_USER')}:{os.getenv('POSTGRES_PASSWORD')}@{os.getenv('POSTGRES_HOST')}:{os.getenv('POSTGRES_PORT')}/{os.getenv('POSTGRES_DB')}" + + +# this is the Alembic Config object, which provides +# access to the values within the .ini file in use. +config = context.config +config.set_main_option("sqlalchemy.url", db_url) + +# 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 = None + +# 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. + + """ + url = config.get_main_option("sqlalchemy.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() diff --git a/alembic/script.py.mako b/alembic/script.py.mako new file mode 100644 index 0000000..480b130 --- /dev/null +++ b/alembic/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"} diff --git a/alembic/versions/394542f24f6c_add_projection_table.py b/alembic/versions/394542f24f6c_add_projection_table.py new file mode 100644 index 0000000..151ba22 --- /dev/null +++ b/alembic/versions/394542f24f6c_add_projection_table.py @@ -0,0 +1,106 @@ +"""add projection table + +Revision ID: 394542f24f6c +Revises: abfbb3d96037 +Create Date: 2025-06-14 23:57:39.301255 + +""" + +from typing import Sequence, Union + +from alembic import op +import sqlalchemy as sa + + +# revision identifiers, used by Alembic. +revision: str = "394542f24f6c" +down_revision: Union[str, None] = "abfbb3d96037" +branch_labels: Union[str, Sequence[str], None] = None +depends_on: Union[str, Sequence[str], None] = None + + +def upgrade() -> None: + """Upgrade schema.""" + op.create_table( + "users", + sa.Column( + "id", + sa.UUID(as_uuid=True), + nullable=False, + ), + sa.Column("created_at", sa.DateTime(timezone=True), nullable=False), + sa.Column("updated_at", sa.DateTime(timezone=True), nullable=False), + sa.Column("deleted_at", sa.DateTime(timezone=True)), + sa.Column("last_event_id", sa.UUID(as_uuid=True), nullable=False, unique=True), + sa.Column( + "last_event_sequence", + sa.Integer(), + nullable=False, + autoincrement=True, + unique=True, + ), + sa.Column("name", sa.String(), nullable=False), + sa.Column("age", sa.Integer(), nullable=False), + sa.Column("hair_color", sa.String(), nullable=False), + sa.PrimaryKeyConstraint("id"), + ) + + op.execute( + """ + create or replace function fn_project_user_created(event_id uuid, event_sequence integer, event_timestamp timestamptz, event jsonb) returns uuid + security definer + language plpgsql as $$ + declare result uuid; + begin + insert into users( + id, + created_at, + updated_at, + last_event_id, + last_event_sequence, + name, + age, + hair_color + ) + values( + cast(event->'event_payload'->>'id' as UUID), + event_timestamp, + event_timestamp, + event_id, + event_sequence, + event->'event_payload'->>'name', + cast(event->'event_payload'->>'age' as INTEGER), + event->'event_payload'->>'hair_color' + ) + returning id into result; + return result; + end; + $$; + + create or replace function fn_trigger_user_created() returns trigger + security definer + language plpgsql + as $$ + begin + perform fn_project_user_created( + new.id, + new.sequence, + new.created_at, + new.event_payload + ); + return new; + end; + $$; + + create trigger event_insert_user_created + after insert on user_events + for each row + when ((new.event_payload->>'event_type') = 'user_created') + execute procedure fn_trigger_user_created(); + """ + ) + + +def downgrade() -> None: + """Downgrade schema.""" + op.drop_table("users") diff --git a/alembic/versions/abfbb3d96037_create_user_event_table.py b/alembic/versions/abfbb3d96037_create_user_event_table.py new file mode 100644 index 0000000..2b97e8a --- /dev/null +++ b/alembic/versions/abfbb3d96037_create_user_event_table.py @@ -0,0 +1,49 @@ +"""create user event table + +Revision ID: abfbb3d96037 +Revises: +Create Date: 2025-06-14 22:22:48.407239 + +""" + +from typing import Sequence, Union + +from alembic import op +import sqlalchemy as sa +import sqlalchemy.dialects.postgresql as psql + +# revision identifiers, used by Alembic. +revision: str = "abfbb3d96037" +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: + """Upgrade schema.""" + + op.execute("CREATE EXTENSION IF NOT EXISTS pgcrypto;") + + op.create_table( + "user_events", + sa.Column( + "id", + sa.UUID(as_uuid=True), + nullable=False, + server_default=sa.text("gen_random_uuid()"), + ), + sa.Column("sequence", sa.Integer(), nullable=False, autoincrement=True), + sa.Column("event_payload", psql.JSONB, nullable=False), + sa.Column( + "created_at", + sa.DateTime(timezone=True), + nullable=False, + server_default=sa.text("NOW()"), + ), + sa.PrimaryKeyConstraint("id", "sequence"), + ) + + +def downgrade() -> None: + """Downgrade schema.""" + op.drop_table("user_events") diff --git a/create_events.py b/create_events.py new file mode 100644 index 0000000..fb3314e --- /dev/null +++ b/create_events.py @@ -0,0 +1,147 @@ +import os +from dotenv import load_dotenv +import psycopg2 +import uuid +import json + +load_dotenv() + +conn_params = { + "host": os.getenv("POSTGRES_HOST"), + "port": os.getenv("POSTGRES_PORT"), + "dbname": os.getenv("POSTGRES_DB"), + "user": os.getenv("POSTGRES_USER"), + "password": os.getenv("POSTGRES_PASSWORD"), +} + + +class User: + + def __init__(self, cursor, name, age, hair_color): + self.cursor = cursor + self.id = uuid.uuid4() + self.name = name + self.age = age + self.hair_color = hair_color + + self._fire_created_user_event() + + def update_user_details(self, name=None, age=None, hair_color=None): + if name: + self.name = name + if age: + self.age = age + if hair_color: + self.hair_color = hair_color + + self._fire_updated_user_event() + + def delete_user(self): + self._fire_deleted_user_event() + + def _fire_created_user_event(self): + event = CreateUserEvent(self) + self._fire_event(event) + + def _fire_updated_user_event(self): + event = UpdateUserEvent(self) + self._fire_event(event) + + def _fire_deleted_user_event(self): + event = DeleteUserEvent(self) + self._fire_event(event) + + def _fire_event(self, event): + query = f"INSERT INTO user_events (event_payload) VALUES ('{event.to_json()}')" + self.cursor.execute(query) + + +class CreateUserEvent: + + def __init__(self, user): + self._user = user + + def to_json(self): + return json.dumps( + { + "event_type": "user_created", + "event_payload": { + "id": self._user.id, + "name": self._user.name, + "age": self._user.age, + "hair_color": self._user.hair_color, + }, + }, + default=str, + ) + + +class UpdateUserEvent: + def __init__(self, user): + self._user = user + + def to_json(self): + return json.dumps( + { + "event_type": "user_updated", + "event_payload": { + "id": self._user.id, + "name": self._user.name, + "age": self._user.age, + "hair_color": self._user.hair_color, + }, + }, + default=str, + ) + + +class DeleteUserEvent: + def __init__(self, user): + self._user = user + + def to_json(self): + return json.dumps( + { + "event_type": "user_deleted", + "event_payload": {"id": self._user.id}, + }, + default=str, + ) + + +def main(): + + try: + # Connect to PostgreSQL + conn = psycopg2.connect(**conn_params) + cur = conn.cursor() + + my_user = User(cursor=cur, name="John", age=95, hair_color="Gray") + my_user.update_user_details(age=96) + my_user.delete_user() + + my_other_user = User(cursor=cur, name="Jane", age=3, hair_color="Fire Red") + my_other_user.update_user_details(age=15, hair_color="Golden Blonde") + my_other_user.update_user_details(age=35, hair_color="Touches of gray") + + my_immutable_user = User( + cursor=cur, name="The Dude", age=33, hair_color="Muffin Orange" + ) + + # Commit the transaction + conn.commit() + + print("Done") + + except Exception as e: + print("Error:", e) + + finally: + if cur: + cur.close() + if conn: + conn.close() + + +if __name__ == "__main__": + main() diff --git a/docker-compose.yml b/docker-compose.yml new file mode 100644 index 0000000..6195456 --- /dev/null +++ b/docker-compose.yml @@ -0,0 +1,11 @@ +version: '3.8' + +services: + postgres: + image: postgres:17 + environment: + POSTGRES_DB: ${POSTGRES_DB} + POSTGRES_USER: ${POSTGRES_USER} + POSTGRES_PASSWORD: ${POSTGRES_PASSWORD} + ports: + - "${POSTGRES_PORT}:${POSTGRES_PORT}" \ No newline at end of file diff --git a/requirements.txt b/requirements.txt new file mode 100644 index 0000000..cdeae21 --- /dev/null +++ b/requirements.txt @@ -0,0 +1,3 @@ +alembic +python-dotenv +psycopg2-binary \ No newline at end of file diff --git a/run_show.sh b/run_show.sh new file mode 100644 index 0000000..aa56cdd --- /dev/null +++ b/run_show.sh @@ -0,0 +1,7 @@ +docker compose down +docker compose up -d +sleep 2s +echo "Running migrations" +alembic upgrade head +echo "Creating events" +python3 create_events.py