[OSC-1291] add schema revision tool alembic (#20)

* add alembic

* update travis build

* updated pipenv

* updated readme

* rename schema to dpo

* bump version number up for next release

* pip -> pipenv

Author: seanbudd

Makefile

@@ -2,6 +2,7 @@
 install_deps:
 	pip install pipenv --upgrade
 	pipenv install --dev
+	alembic -c dpo/alembic.ini -x postgresql+psycopg2://postgres:travisci@localhost:5432/postgres upgrade head
 
 # Run unit tests
 test_unit:
@@ -10,4 +11,3 @@ test_unit:
 # Run integration tests
 test_integration:
 	./tests/integration/test_integration.sh
-	

Pipfile

@@ -12,6 +12,8 @@ autopep8 = "*"
 [packages]
 psycopg2-binary = "==2.7.7"
 SQLAlchemy = "==1.2.17"
+alembic = "==1.0.8"
+dpo = {path = "."}
 
 [requires]
 python_version = "3.7"

Pipfile.lock

@@ -0,0 +1,98 @@
+from __future__ import with_statement
+
+from logging.config import fileConfig
+
+from sqlalchemy import engine_from_config, create_engine
+from sqlalchemy import pool
+
+from alembic import context
+
+from dpo.Shared import BaseEntity
+from dpo.entities import ModelChecksumEntity
+from dpo.entities import DataPipelineExecutionEntity
+from dpo.Shared import Constants
+
+# 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 = BaseEntity.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.
+
+if not context.get_x_argument():
+    raise AttributeError(
+        "example usage `alembic -c dpo/alembic.ini -x postgresql+psycopg2://postgres:postgres@localhost/postgres downgrade -1`")
+
+url = context.get_x_argument()[0]
+
+
+def use_schema(object, name, type_, reflected, compare_to):
+    if type_ == 'table' and object.schema != Constants.DATA_PIPELINE_EXECUTION_SCHEMA_NAME:
+        return False
+    if (type_ == "column" and
+        not reflected and
+            object.info.get("skip_autogenerate", False)):
+        return False
+    if type_ == 'table' and name == 'alembic_version':
+        return False
+    return True
+
+
+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=url, target_metadata=target_metadata, literal_binds=True, include_schemas=True,
+        include_object=use_schema, version_table=f'alembic_version_{Constants.DATA_PIPELINE_EXECUTION_SCHEMA_NAME}'
+    )
+
+    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 = create_engine(
+        url,
+        poolclass=pool.NullPool,
+    )
+
+    with connectable.connect() as connection:
+        context.configure(
+            connection=connection, target_metadata=target_metadata, include_schemas=True,
+            include_object=use_schema, version_table=f'alembic_version_{Constants.DATA_PIPELINE_EXECUTION_SCHEMA_NAME}'
+        )
+
+        with context.begin_transaction():
+            context.run_migrations()
+
+
+if context.is_offline_mode():
+    run_migrations_offline()
+else:
+    run_migrations_online()

alembic-dpo/env.py

@@ -14,10 +14,6 @@ def __init__(self, db_engine, logger=None):
         self.db_engine = db_engine
         self.session_maker = sessionmaker(bind=self.db_engine)
 
-    def ensure_schema_exists(self):
-        self.db_engine.execute(f'CREATE SCHEMA IF NOT EXISTS {Constants.DATA_PIPELINE_EXECUTION_SCHEMA_NAME}')
-        Shared.BaseEntity.metadata.create_all(self.db_engine)
-
     def get_current_db_datetime_with_timezone(self):
         return self.db_engine.execute(select([func.now()])).fetchone()[0]
 

dpo/DataRepository.py

@@ -7,7 +7,7 @@
 
 class Constants:
     APP_NAME = 'data-pipeline-orchestrator'
-    DATA_PIPELINE_EXECUTION_SCHEMA_NAME = 'data_pipeline'
+    DATA_PIPELINE_EXECUTION_SCHEMA_NAME = 'dpo'
     NO_LAST_SUCCESSFUL_EXECUTION = 'NO_LAST_SUCCESSFUL_EXECUTION'
 
     class DataPipelineExecutionStatus:

dpo/Shared.py

@@ -0,0 +1,72 @@
+# 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 = 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 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
+
+
+# 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