EvaDB Catalog Table Migration with Alembic

README_alembic.md

@@ -0,0 +1,24 @@
+## Integration of Alembic with EvaDB
+Alembic works with the “change management scripts” to manage table schemas through `upgrade` and `downgrade` functions while tracking revisions. Therefore, it could be helpful in migrating the seven metadata table schemas whenever a newer version of EvaDB is released with changes to them.
+
+## DEMO
+### Migration Scripts
+In `alembic/versions` two example migration scripts can be found:
+- `b0ecb091fa7b_edit_a_column_in_table_catalog.py`
+- `e6dc73b305fe_first_migration_adding_a_new_column_to_.py`
+
+These scripts are created using the command `alembic revision -m <description for this revision>`. In the scripts we define two functions `upgrade` to make desired changes to tables or databases, and `downgrade` to revert the changes. The followins are some of the common commands for managing revisions:
+
+- Display the current revision for a database: `alembic current`
+- View migrations history: `alembic history --verbose`
+- Revert all migrations: `alembic downgrade base`
+- Apply all migrations: `alembic upgrade head`
+- Apply specified revisionL `alembic upgrade <revision ID>`
+- Reset the database: `alembic downgrade base && alembic upgrade head`
+
+### Automigration Scripts
+In the scenario where we would like to update the catalog tables along with the new release of EvaDB, the migration is expected to be done automatically. Therefore, `alembic_automigration.py` is provided to detect any newer revision and update accordingly. This script can be triggered either in `setup.py` or other release management tools.
+
+## License
+Copyright (c) [Georgia Tech Database Group](http://db.cc.gatech.edu/).
+Licensed under an [Apache License](LICENSE.txt).

alembic.ini

@@ -0,0 +1,116 @@
+# A generic, single database configuration.
+
+[alembic]
+# path to migration scripts
+script_location = 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 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: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.
+
+# 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
+
+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 = --fix 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

alembic/README

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

alembic/env.py

@@ -0,0 +1,80 @@
+from logging.config import fileConfig
+
+from sqlalchemy import engine_from_config
+from sqlalchemy import pool
+
+from alembic import context
+import evadb
+from pathlib import Path
+# 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', evadb.database.get_default_db_uri(Path('evadb_data')))
+
+# 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()

alembic/script.py.mako

@@ -0,0 +1,27 @@
+"""${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:
+    ${upgrades if upgrades else "pass"}
+
+
+def downgrade() -> None:
+    ${downgrades if downgrades else "pass"}
+

alembic/versions/b0ecb091fa7b_edit_a_column_in_table_catalog.py

@@ -0,0 +1,28 @@
+"""edit a column in table_catalog
+
+Revision ID: b0ecb091fa7b
+Revises: e6dc73b305fe
+Create Date: 2023-11-20 19:01:31.602478
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision: str = 'b0ecb091fa7b'
+down_revision: Union[str, None] = 'e6dc73b305fe'
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    with op.batch_alter_table("table_catalog") as batch_op:
+        batch_op.alter_column("TEST", new_column_name="TEST1")
+
+
+def downgrade() -> None:
+    with op.batch_alter_table("table_catalog") as batch_op:
+        batch_op.alter_column("TEST1", new_column_name="TEST")

alembic/versions/e6dc73b305fe_first_migration_adding_a_new_column_to_.py

@@ -0,0 +1,29 @@
+"""first migration: adding a new column to catalog_table
+
+Revision ID: e6dc73b305fe
+Revises: 
+Create Date: 2023-11-19 23:28:29.655424
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision: str = 'e6dc73b305fe'
+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:
+    with op.batch_alter_table("table_catalog") as batch_op:
+        batch_op.add_column(sa.Column("TEST", sa.String()))
+
+
+def downgrade() -> None:
+    with op.batch_alter_table("table_catalog") as batch_op:
+        batch_op.drop_column("TEST")
+

alembic_automigration.py

@@ -0,0 +1,35 @@
+from alembic.config import Config
+from alembic import command
+from alembic.script import ScriptDirectory
+from alembic.migration import MigrationContext
+from sqlalchemy import create_engine
+from pathlib import Path
+import evadb
+
+
+def get_current_revision(db_uri):
+    engine = create_engine(db_uri)
+    conn = engine.connect()
+    context = MigrationContext.configure(conn)
+    return context.get_current_revision()
+
+def get_latest_revision(config):
+    script = ScriptDirectory.from_config(config)
+    return script.get_heads()[-1]
+
+def run_migrations():
+    # Set up database connnection
+    db_uri = evadb.database.get_default_db_uri(Path('evadb_data'))
+    alembic_cfg = Config('./alembic.ini')
+    alembic_cfg.set_main_option('sqlalchemy.url', db_uri)
+
+    # Get current local revision and lastest revision available
+    current_revision = get_current_revision(db_uri)
+    latest_revision = get_latest_revision(alembic_cfg)
+
+    # If newer revision found, upgrade to the lastest revision
+    if current_revision and current_revision != latest_revision:
+        command.upgrade(alembic_cfg, latest_revision)
+
+if __name__ == "__main__":
+    run_migrations()

docs/requirements.txt

@@ -25,7 +25,7 @@ mock>=1.0.1
 pillow>=9.0.1
 readthedocs-sphinx-ext>1.1
 autodoc_pydantic
-
+alembic
 # MyST
 myst-parser
 myst-nb

test/third_party_tests/__init__.py

@@ -0,0 +1,14 @@
+# coding=utf-8
+# Copyright 2018-2023 EvaDB
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.