feat: initial project setup

.editorconfig

@@ -0,0 +1,27 @@
+# EditorConfig is awesome: https://EditorConfig.org
+
+# top-most EditorConfig file
+root = true
+
+# Unix-style newlines with a newline ending every file
+[*]
+charset = utf-8
+end_of_line = lf
+insert_final_newline = true
+trim_trailing_whitespace = true
+
+# 2 space indentation for every file
+[*]
+indent_style = space
+indent_size = 2
+
+# 4 space indentation for python
+[*.py]
+indent_size = 4
+
+# allow trailing whitespace in markdown files
+[*.md]
+trim_trailing_whitespace = false
+
+[Makefile]
+indent_style = tab

.env.test

@@ -0,0 +1,2 @@
+DATABASE_URI="postgresql://felix@localhost:5432/whisper_api_test"
+ENVIRONMENT="development"

.flake8

@@ -0,0 +1,4 @@
+[flake8]
+max-line-length = 88
+extend-ignore = E203
+exclude = .git,__pycache__,__init__.py,.mypy_cache,.pytest_cache

.github/workflows/ci.yml

@@ -0,0 +1,41 @@
+name: CI
+on: push
+
+jobs:
+  fmt:
+    runs-on: ubuntu-latest
+    name: Fmt
+    steps:
+      - uses: actions/checkout@v3
+      - uses: actions/setup-python@v4
+        with:
+          python-version: '3.11'
+          cache: 'pip'
+      - pip install -e .[dev]
+      - black --check app
+      - isort --check app
+      - mypy app
+      - flake8 app
+  lint:
+    runs-on: ubuntu-latest
+    name: Lint
+    steps:
+      - uses: actions/checkout@v3
+      - uses: actions/setup-python@v4
+        with:
+          python-version: '3.11'
+          cache: 'pip'
+      - pip install -e .[dev]
+      - mypy app
+      - flake8 app
+  test:
+    runs-on: ubuntu-latest
+    name: Test
+    steps:
+      - uses: actions/checkout@v3
+      - uses: actions/setup-python@v4
+        with:
+          python-version: '3.11'
+          cache: 'pip'
+      - pip install -e .[dev]
+      - pytest

.gitignore

@@ -0,0 +1,163 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$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
+
+# 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
+
+# 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/#use-with-ide
+.pdm.toml
+
+# 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
+.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/
+
+# VS Code
+.vscode

Makefile

@@ -0,0 +1,17 @@
+
+dev:
+	uvicorn app.main:app --reload
+
+fmt:
+	black app --check
+	isort app
+
+test:
+	ENVIRONMENT=test pytest
+
+lint:
+	mypy app
+	flake8 app
+
+create_account:
+	python -m scripts.create_account ${name}

README.md

@@ -0,0 +1,7 @@
+# whisper-api
+
+### TODO
+
+- [ ] run alembic migrations before startup
+- [ ] dockerize
+- [ ] add celery queue

alembic.ini

@@ -0,0 +1,104 @@
+# A generic, single database configuration.
+
+[alembic]
+# path to migration scripts
+script_location = app/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.
+prepend_sys_path = .
+
+# timezone to use when rendering the date within the migration file
+# as well as the filename.
+# If specified, requires the python-dateutil library that can be
+# installed by adding `alembic[tz]` to the pip requirements
+# string value is passed to dateutil.tz.gettz()
+# 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 src/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:src/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.
+
+# the output encoding used when revision files
+# are written from script.py.mako
+# output_encoding = utf-8
+
+# 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
+
+# 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

app/alembic/README

@@ -0,0 +1 @@
+Generic single-database configuration.

app/alembic/env.py

@@ -0,0 +1,80 @@
+from logging.config import fileConfig
+
+from alembic import context
+from sqlalchemy import engine_from_config, pool
+
+from app.config import settings
+from app.db.models import Base
+
+# 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)
+
+config.set_main_option("sqlalchemy.url", settings.DATABASE_URI)
+
+# add your model's MetaData object here
+# for 'autogenerate' support
+# from myapp import mymodel
+# target_metadata = mymodel.Base.metadata
+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.
+
+    """
+    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()

app/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"}

app/alembic/versions/54824f17a11d_add_account_table.py

@@ -0,0 +1,46 @@
+"""add_account_table
+
+Revision ID: 54824f17a11d
+Revises:
+Create Date: 2022-12-18 17:51:09.172531
+
+"""
+import sqlalchemy as sa
+from alembic import op
+from sqlalchemy.dialects import postgresql
+
+# revision identifiers, used by Alembic.
+revision = "54824f17a11d"
+down_revision = None
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.create_table(
+        "accounts",
+        sa.Column("id", postgresql.UUID(as_uuid=True), nullable=False),
+        sa.Column(
+            "created_at",
+            sa.DateTime(),
+            server_default=sa.text("now()"),
+            nullable=False,
+        ),
+        sa.Column("updated_at", sa.DateTime(), nullable=True),
+        sa.Column("api_key", postgresql.UUID(as_uuid=True), nullable=True),
+        sa.Column("name", sa.String(length=256), nullable=True),
+        sa.PrimaryKeyConstraint("id"),
+        sa.UniqueConstraint("name"),
+    )
+    op.create_index(op.f("ix_accounts_api_key"), "accounts", ["api_key"], unique=False)
+    op.create_index(op.f("ix_accounts_id"), "accounts", ["id"], unique=False)
+    # ### end Alembic commands ###
+
+
+def downgrade() -> None:
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.drop_index(op.f("ix_accounts_id"), table_name="accounts")
+    op.drop_index(op.f("ix_accounts_api_key"), table_name="accounts")
+    op.drop_table("accounts")
+    # ### end Alembic commands ###

app/config.py

@@ -0,0 +1,18 @@
+import os
+
+from pydantic import BaseSettings
+
+
+class Settings(BaseSettings):
+    DATABASE_URI: str
+    ENVIRONMENT: str
+
+    class Config:
+        env_file = ".env"
+        env_file_encoding = "utf-8"
+
+
+if "ENVIRONMENT" in os.environ and os.environ["ENVIRONMENT"] == "test":
+    settings = Settings(_env_file=".env.test")  # type: ignore
+else:
+    settings = Settings()

app/db/base.py

@@ -0,0 +1,18 @@
+from typing import Generator
+
+from sqlalchemy import create_engine
+from sqlalchemy.orm import Session, sessionmaker
+
+from app.config import settings
+
+engine = create_engine(settings.DATABASE_URI)
+
+SessionLocal = sessionmaker(autocommit=False, autoflush=False, bind=engine)
+
+
+def get_db() -> Generator[Session, None, None]:
+    db = SessionLocal()
+    try:
+        yield db
+    finally:
+        db.close()

app/db/dtos.py

@@ -0,0 +1,23 @@
+from datetime import datetime
+from typing import Optional
+from uuid import UUID
+
+from pydantic import BaseModel
+
+
+class WithStandardFields(BaseModel):
+    id: UUID
+    created_at: datetime
+    updated_at: Optional[datetime]
+
+    class Config:
+        orm_mode = True
+
+
+class AccountBase(BaseModel):
+    api_key: UUID
+    name: str
+
+
+class Account(AccountBase, WithStandardFields):
+    pass

app/db/models.py

@@ -0,0 +1,31 @@
+from typing import Optional
+import uuid
+
+from sqlalchemy import Column, DateTime, String, func
+from sqlalchemy.dialects.postgresql import UUID
+from sqlalchemy.orm import declarative_mixin, declared_attr, Mapped
+from sqlalchemy.ext.declarative import declarative_base
+
+Base = declarative_base()
+
+
+@declarative_mixin
+class WithStandardFields:
+    @declared_attr
+    def created_at(cls) -> Mapped[DateTime]:
+        return Column(DateTime, server_default=func.now(), nullable=False)
+
+    @declared_attr
+    def updated_at(cls) -> Mapped[Optional[DateTime]]:
+        return Column(DateTime, onupdate=func.now())
+
+    @declared_attr
+    def id(cls) -> Mapped[UUID]:
+        return Column(UUID(as_uuid=True), primary_key=True, index=True, default=uuid.uuid4)
+
+
+class Account(Base, WithStandardFields):
+    __tablename__ = "accounts"
+
+    api_key = Column(UUID(as_uuid=True), index=True, default=uuid.uuid4)
+    name = Column(String(length=256), unique=True)

app/main.py

@@ -0,0 +1,37 @@
+from typing import Dict, List
+
+from fastapi import APIRouter, Depends, FastAPI
+
+from .security import authenticate_api_key
+
+app = FastAPI()
+
+api_router = APIRouter(prefix="/api/v1", dependencies=[Depends(authenticate_api_key)])
+
+
+@api_router.get("/")
+def api_root() -> Dict:
+    return {}
+
+
+@api_router.post("/transcripts")
+def create_transcript() -> None:
+    return None
+
+
+@api_router.get("/transcripts")
+def get_transcripts() -> List:
+    return []
+
+
+@api_router.get("/transcripts/{id}")
+def get_transcript() -> None:
+    return None
+
+
+@api_router.delete("/transcripts/{id}")
+def delete_transcript() -> None:
+    return None
+
+
+app.include_router(api_router)

app/security.py

@@ -0,0 +1,26 @@
+from uuid import UUID
+
+from fastapi import Depends, HTTPException
+from fastapi.security import OAuth2PasswordBearer
+from sqlalchemy.orm import Session
+from sqlalchemy.orm.exc import NoResultFound
+
+from .db.base import get_db
+from .db.models import Account
+
+oauth2_scheme = OAuth2PasswordBearer(tokenUrl="token")
+
+
+def authenticate_api_key(
+    db: Session = Depends(get_db),
+    api_key: str = Depends(oauth2_scheme),
+) -> Account:
+    try:
+        account = db.query(Account).filter(Account.api_key == UUID(api_key)).one()
+    except NoResultFound:
+        raise HTTPException(status_code=401)
+    except Exception as e:
+        print(e)
+        raise HTTPException(status_code=422)
+
+    return account

app/tests/conftest.py

@@ -0,0 +1,42 @@
+from typing import Generator
+
+import pytest
+from sqlalchemy.orm import Session
+from sqlalchemy_utils import create_database, database_exists, drop_database
+
+from app.db.base import SessionLocal, engine, get_db
+from app.db.models import Account, Base
+from app.main import app
+
+
+def pytest_configure() -> None:
+    if not database_exists(engine.url):
+        create_database(engine.url)
+        Base.metadata.create_all(engine)
+
+
+def pytest_unconfigure() -> None:
+    if database_exists(engine.url):
+        drop_database(engine.url)
+
+
+@pytest.fixture(name="db_session", scope="function", autouse=True)
+def db_session() -> Generator[Session, None, None]:
+    connection = engine.connect()
+    transaction = connection.begin()
+
+    with SessionLocal(bind=connection) as session:
+        app.dependency_overrides[get_db] = lambda: session
+        yield session
+        app.dependency_overrides.clear()
+        transaction.rollback()
+        connection.close()
+
+
+@pytest.fixture(scope="function")
+def test_account(db_session: Session) -> Account:
+    account = Account(name="test_account")
+    db_session.add(account)
+    db_session.commit()
+    db_session.refresh(account)
+    return account

app/tests/test_auth.py

@@ -0,0 +1,32 @@
+from typing import Dict
+
+from fastapi.testclient import TestClient
+
+from app.db.models import Account
+from app.main import app
+
+client = TestClient(app)
+
+
+def auth_header(s: str) -> Dict[str, str]:
+    return {"Authorization": f"Bearer {s}"}
+
+
+def test_authorization_header_missing() -> None:
+    res = client.get("/api/v1")
+    assert res.status_code == 401
+
+
+def test_authorization_header_malformed() -> None:
+    res = client.get("/api/v1", headers=auth_header("not_a_uuid"))
+    assert res.status_code == 422
+
+
+def test_inexistent_api_key(test_account: Account) -> None:
+    res = client.get("/api/v1", headers=auth_header(str(test_account.id)))
+    assert res.status_code == 401
+
+
+def test_existing_api_key(test_account: Account) -> None:
+    res = client.get("/api/v1", headers=auth_header(str(test_account.api_key)))
+    assert res.status_code == 200

mypy.ini

@@ -0,0 +1,4 @@
+[mypy]
+plugins = pydantic.mypy, sqlmypy, sqlalchemy.ext.mypy.plugin
+ignore_missing_imports = True
+disallow_untyped_defs = True

pyproject.toml

@@ -0,0 +1,33 @@
+[project]
+name = "whisper-api"
+description = ""
+version = "0.0.1"
+
+dependencies=[
+  "alembic ==1.9.0",
+  "fastapi ==0.88.0",
+  "psycopg2 ==2.9.5",
+  "python-dotenv ==0.21.0",
+  "sqlalchemy[mypy] == 1.4.45",
+  "uvicorn[standard] ==0.20.0"
+]
+
+[project.optional-dependencies]
+dev = [
+  # code formatting
+  "black",
+  "isort",
+
+  # linting
+  "flake8",
+  "mypy",
+
+  # tests
+  "httpx",
+  "sqlalchemy-stubs",
+  "sqlalchemy-utils",
+  "pytest"
+]
+
+[tool.isort]
+profile = "black"

scripts/create_account.py

@@ -0,0 +1,21 @@
+import argparse
+from dotenv import load_dotenv
+from app.db.base import get_db
+from app.db.models import Account
+
+load_dotenv()
+
+def create_account(name: str) -> Account:
+    db = get_db().__next__()
+    account = Account(name=name)
+    db.add(account)
+    db.commit()
+    db.refresh(account)
+    return account
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("name", type=str, nargs=1)
+    args = parser.parse_args()
+    create_account(args.name[0])