Try out Alembic

src/egon/data/airflow/docker-compose.yml

@@ -15,4 +15,3 @@ services:
       POSTGRES_PASSWORD: data
     volumes:
     - $HOME/docker/volumes/postgres/egon-data:/var/lib/postgresql/data
-    - ./entrypoints:/docker-entrypoint-initdb.d/

src/egon/data/airflow/tasks.py

@@ -1,10 +1,13 @@
 import os.path
 import subprocess
 
+import egon.data
+
 
 def initdb():
     """ Initialize the local database used for data processing. """
     subprocess.run(
         ["docker-compose", "up", "-d", "--build"],
         cwd=os.path.dirname(__file__),
     )
+    subprocess.run(["alembic", "upgrade", "head"], cwd=egon.data.__path__[0])

src/egon/data/alembic.ini

@@ -0,0 +1,88 @@
+# A generic, single database configuration.
+
+[alembic]
+# path to migration scripts
+script_location = alembic
+
+# template used to generate migration files
+file_template = %%(year)d-%%(month).2d-%%(day).2dT%%(hour).2d:%%(minute).2d.%%(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 = UTC
+
+# max length of characters to apply to the
+# "slug" field
+truncate_slug_length = 53
+
+# 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/bar %(here)s/bat alembic/versions
+
+# 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 = fixup, isort, black, sequentialize
+fixup.type = fixup
+black.type = console_scripts
+black.entrypoint = black
+isort.type = console_scripts
+isort.entrypoint = isort
+sequentialize.type = sequentialize
+
+# 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

src/egon/data/alembic/README

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

src/egon/data/alembic/env.py

@@ -0,0 +1,135 @@
+from fileinput import FileInput
+from logging.config import fileConfig
+from pathlib import Path
+import re
+
+from alembic import context
+from alembic.script import ScriptDirectory, write_hooks
+
+from egon.data.db import engine
+from egon.data.orm.openstreetmap import metadata
+
+# 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 myapp import mymodel
+# target_metadata = mymodel.Base.metadata
+target_metadata = 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.
+
+
+@write_hooks.register("fixup")
+def fix_minor_issues(filename, options):
+    """Fix minor issues like grammar in comments or trailing whitespace."""
+    fixes = []
+    with FileInput(filename, inplace=True) as script:
+        for line in script:
+            if re.match(r"# revision identifiers, used by Alembic\.", line):
+                print("# Revision identifiers, used by Alembic.")
+                fixes.append('"# revision ..." -> "# Revision ..."')
+            else:
+                print(line, end="")
+    for fix in fixes:
+        print(f"Fixed: {fix}.")
+
+
+def script(filename=None, revision=None):
+    """Return the script object matching the parameters.
+
+    Either the script object having the given :py:obj:`filename` or having
+    the given :py:obj:`revision`, is returned. If both are given, both have
+    to match.
+
+    Supplying at least one is mandatory.
+    """
+    assert filename is not None or revision is not None
+    scripts = ScriptDirectory.from_config(config)
+    return [
+        s
+        for s in scripts.walk_revisions()
+        if (filename is None or s.path == filename)
+        and (revision is None or s.revision == revision)
+    ][0]
+
+
+@write_hooks.register("sequentialize")
+def assign_sequential_version_number(filename, options):
+    """Prefix the migration script's name with a sequential version number.
+
+    The version number is generated by incrementing the version number of
+    the down revision by one. Since the intention is to get a sequential
+    ordering when sorting the migration scripts alphabetically, this
+    sequential number is right aligned and padded with zeroes to a length of
+    three characters.
+    """
+
+    current = script(filename=filename)
+    path = Path(filename)
+    down = (
+        "-001."  # Gets incremented to 0 in the line below.
+        if current.down_revision is None
+        else Path(script(revision=current.down_revision).path).name
+    )
+    version = int(re.match(r"^(-?\d{3})\..*", down)[1]) + 1
+    prefix = f"{version:0>3}."
+    path.rename(path.parent / (prefix + path.name))
+    print(f'Prefixed new migration script with "{prefix}".')
+
+
+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=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.
+
+    """
+    connectable = engine()
+
+    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()

src/egon/data/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"}

src/egon/data/alembic/versions/000.2021-01-08T16:37.9b9584efcefd.do_nothing_for_the_base_migration.py

@@ -0,0 +1,25 @@
+"""Do nothing for the base migration
+
+This migration intentionally does nothing. Downgrading to this revision
+should reset the database to a clean state or at least undo everything
+done via Alembic.
+
+Revision ID: 9b9584efcefd
+Revises:
+Create Date: 2021-01-08 16:37:31.238609+00:00
+
+"""
+
+# Revision identifiers, used by Alembic.
+revision = "9b9584efcefd"
+down_revision = None
+branch_labels = None
+depends_on = None
+
+
+def upgrade():
+    pass
+
+
+def downgrade():
+    pass

src/egon/data/alembic/versions/001.2021-01-08T18:50.79833aa6bc04.create_the_hstore_and_postgis_database_extensions.py

@@ -0,0 +1,24 @@
+"""Create the hstore and postgis database extensions
+
+Revision ID: 79833aa6bc04
+Revises: 9b9584efcefd
+Create Date: 2021-01-08 18:50:07.951487+00:00
+
+"""
+from alembic import op
+
+# Revision identifiers, used by Alembic.
+revision = "79833aa6bc04"
+down_revision = "9b9584efcefd"
+branch_labels = None
+depends_on = None
+
+
+def upgrade():
+    op.execute("CREATE EXTENSION IF NOT EXISTS hstore;")
+    op.execute("CREATE EXTENSION IF NOT EXISTS postgis;")
+
+
+def downgrade():
+    op.execute("DROP EXTENSION IF EXISTS postgis;")
+    op.execute("DROP EXTENSION IF EXISTS hstore;")