Add initial alembic migration (#209)

* Add initial alembic migration

* Filter out alembic files from coverage

* Bump version

.coveragerc

@@ -0,0 +1,3 @@
+[run]
+omit =
+ rfhub2/alembic/*

DEVELOPMENT.md

@@ -92,3 +92,13 @@ black -t py36 rfhub2 tests
 
 You can consider adding a git hook or integrating it with your IDE for automated execution.
 
+### Database migrations
+When you introduce any changes to database schema, you should prepare Alembic revision reflecting these changes.
+
+To autogenerate revision file, make sure that SQLALCHEMY_DB_URI variable in config points to existing database instance
+containing database state from previous revision and execute
+
+```
+PYTHONPATH=. alembic -c rfhub2/alembic.ini revision --autogenerate -m "Your revision name"
+```
+Before commit, inspect generated file to make sure that revision contains only relevant changes to the schema.

requirements.txt

@@ -1,3 +1,4 @@
+alembic==1.4.2
 aiofiles==0.4.0
 Click==7.1.1
 dataclasses==0.6

rfhub2/alembic.ini

@@ -0,0 +1,82 @@
+# A generic, single database configuration.
+
+[alembic]
+# path to migration scripts
+script_location = %(here)s/alembic
+
+# template used to generate migration files
+# file_template = %%(rev)s_%%(slug)s
+
+# timezone to use when rendering the date
+# within the migration file as well as the filename.
+# 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 = true
+
+# 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
+version_locations = %(here)s/alembic/versions
+
+# the output encoding used when revision files
+# are written from script.py.mako
+# output_encoding = utf-8
+
+[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
+
+# 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

rfhub2/alembic/env.py

@@ -0,0 +1,75 @@
+from logging.config import fileConfig
+
+from sqlalchemy import engine_from_config
+from sqlalchemy import pool
+
+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)
+
+# add your model's MetaData object here
+# for 'autogenerate' support
+from rfhub2.db.base import *
+
+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.
+from rfhub2.config import SQLALCHEMY_DB_URI
+
+
+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.
+
+    """
+    context.configure(
+        url=SQLALCHEMY_DB_URI,
+        target_metadata=target_metadata,
+        literal_binds=True,
+        dialect_opts={"paramstyle": "named"},
+    )
+
+    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.
+
+    """
+    configuration = config.get_section(config.config_ini_section)
+    configuration["sqlalchemy.url"] = SQLALCHEMY_DB_URI
+    connectable = engine_from_config(
+        configuration, 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()

rfhub2/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():
+    ${upgrades if upgrades else "pass"}
+
+
+def downgrade():
+    ${downgrades if downgrades else "pass"}

rfhub2/alembic/versions/c54a916ec6c8_initial_model.py

@@ -0,0 +1,69 @@
+"""Initial model
+
+Revision ID: c54a916ec6c8
+Revises: 
+Create Date: 2020-04-01 21:02:20.117380
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = "c54a916ec6c8"
+down_revision = None
+branch_labels = None
+depends_on = None
+
+
+def upgrade():
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.create_table(
+        "collection",
+        sa.Column("id", sa.Integer(), nullable=False),
+        sa.Column("name", sa.Text(), nullable=True),
+        sa.Column("type", sa.Text(), nullable=True),
+        sa.Column("version", sa.Text(), nullable=True),
+        sa.Column("scope", sa.Text(), nullable=True),
+        sa.Column("named_args", sa.Text(), nullable=True),
+        sa.Column("path", sa.Text(), nullable=True),
+        sa.Column("doc", sa.Text(), nullable=True),
+        sa.Column("doc_format", sa.Text(), nullable=True),
+        sa.PrimaryKeyConstraint("id"),
+    )
+    op.create_index(op.f("ix_collection_name"), "collection", ["name"], unique=False)
+    op.create_table(
+        "keywordstatistics",
+        sa.Column("collection", sa.Text(), nullable=False),
+        sa.Column("keyword", sa.Text(), nullable=False),
+        sa.Column("execution_time", sa.DateTime(timezone=True), nullable=False),
+        sa.Column("times_used", sa.Integer(), nullable=True),
+        sa.Column("total_elapsed", sa.Integer(), nullable=True),
+        sa.Column("min_elapsed", sa.Integer(), nullable=True),
+        sa.Column("max_elapsed", sa.Integer(), nullable=True),
+        sa.PrimaryKeyConstraint("collection", "keyword", "execution_time"),
+    )
+    op.create_table(
+        "keyword",
+        sa.Column("id", sa.Integer(), nullable=False),
+        sa.Column("name", sa.Text(), nullable=True),
+        sa.Column("doc", sa.Text(), nullable=True),
+        sa.Column("args", sa.Text(), nullable=True),
+        sa.Column("collection_id", sa.Integer(), nullable=False),
+        sa.ForeignKeyConstraint(
+            ["collection_id"], ["collection.id"], ondelete="CASCADE"
+        ),
+        sa.PrimaryKeyConstraint("id"),
+    )
+    op.create_index(op.f("ix_keyword_name"), "keyword", ["name"], unique=False)
+    # ### end Alembic commands ###
+
+
+def downgrade():
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.drop_index(op.f("ix_keyword_name"), table_name="keyword")
+    op.drop_table("keyword")
+    op.drop_table("keywordstatistics")
+    op.drop_index(op.f("ix_collection_name"), table_name="collection")
+    op.drop_table("collection")
+    # ### end Alembic commands ###

rfhub2/db/migrate.py

@@ -0,0 +1,27 @@
+from alembic.config import Config
+from alembic.runtime.migration import MigrationContext
+from alembic import command
+from sqlalchemy.engine import Connection, Engine
+from sqlalchemy.engine.reflection import Inspector
+
+
+def has_tables(connection: Connection) -> bool:
+    inspector = Inspector(connection)
+    tables = inspector.get_table_names()
+    return len(tables) > 0
+
+
+def has_revision(connection: Connection) -> bool:
+    context = MigrationContext.configure(connection)
+    current_rev = context.get_current_revision()
+    return current_rev is not None
+
+
+def migrate_db(engine: Engine) -> None:
+    alembic_cfg = Config("rfhub2/alembic.ini")
+    with engine.begin() as connection:
+        # check if database has not been migrated yet with alembic
+        if has_tables(connection) and not has_revision(connection):
+            # stamp database with the initial revision id, representing pre-alembic database schema
+            command.stamp(alembic_cfg, "c54a916ec6c8")
+        command.upgrade(alembic_cfg, "head")

rfhub2/main.py

@@ -1,6 +1,6 @@
 from rfhub2.app import create_app
-from rfhub2.db.init_db import init_db
-from rfhub2.db.session import db_session
+from rfhub2.db.migrate import migrate_db
+from rfhub2.db.session import engine
 
-init_db(db_session)
+migrate_db(engine)
 app = create_app()

rfhub2/version.py

@@ -1 +1 @@
-version = "0.15"
+version = "0.16"

setup.py

@@ -17,6 +17,7 @@
     zip_safe=True,
     include_package_data=True,
     install_requires=[
+        'alembic>=1.2.0',
         'aiofiles>=0.4.0',
         'Click>=7.0',
         'fastapi>=0.46.0',

tests/unit/api/endpoints/base_endpoint_tests.py

@@ -3,9 +3,9 @@
 
 from rfhub2 import config
 from rfhub2.app import create_app
-from rfhub2.db.init_db import init_db
-from rfhub2.db.sample_data import recreate_data
-from rfhub2.db.session import db_session
+from rfhub2.db.migrate import migrate_db
+from rfhub2.db.session import db_session, engine
+from tests.unit.sample_data import recreate_data
 
 
 class BaseApiEndpointTest(unittest.TestCase):
@@ -234,10 +234,13 @@ class BaseApiEndpointTest(unittest.TestCase):
         "max_elapsed": 1000,
     }
 
+    @classmethod
+    def setUpClass(cls) -> None:
+        migrate_db(engine)
+
     def setUp(self) -> None:
         self.app = create_app()
         db_session.rollback()
-        init_db(db_session)
         recreate_data(db_session)
         self.client: TestClient = TestClient(self.app)
         self.auth_client: TestClient = TestClient(self.app)

tests/unit/db/base_repo_tests.py

@@ -1,16 +1,16 @@
 import unittest
 
 from rfhub2.db.base import Collection, Keyword
-from rfhub2.db.init_db import init_db
+from rfhub2.db.migrate import migrate_db
 from rfhub2.db.repository.collection_repository import CollectionRepository
 from rfhub2.db.repository.keyword_repository import KeywordRepository
-from rfhub2.db.session import db_session
+from rfhub2.db.session import db_session, engine
 
 
 class BaseRepositoryTest(unittest.TestCase):
     @classmethod
     def setUpClass(cls) -> None:
-        init_db(db_session)
+        migrate_db(engine)
 
     def setUp(self) -> None:
         db_session.rollback()