Merge branch 'main' into basic-interface

* main:
  docs: Changelog
  chore: Fix mypy
  test: Fix tests
  chore: Fix mypy
  feat: validate database urls
  chore: Update configuration
  feat: Add sqlalchemy and alembic
  docs: Changelog
  chore: Fix tests
  test: Add tests for the ref package
  feat: Add a config subcommands
  feat: Add a ref package

.github/workflows/ci.yaml

@@ -74,6 +74,7 @@ jobs:
           make fetch-test-data
       - name: Run tests
         run: |
+          uv run --package ref pytest packages/ref -r a -v --doctest-modules --cov=packages/ref/src --cov-report=term
           uv run --package ref-core pytest packages/ref-core -r a -v --doctest-modules --cov=packages/ref-core/src --cov-report=term
           uv run --package ref-metrics-example pytest packages/ref-metrics-example -r a -v --doctest-modules --cov=packages/ref-metrics-example/src --cov-report=term --cov-append
           uv run coverage xml

.gitignore

@@ -148,3 +148,6 @@ dmypy.json
 
 # Esgpull
 .esgpull
+
+# Generated output
+out

Makefile

@@ -30,13 +30,20 @@ pre-commit:  ## run all the linting checks of the codebase
 .PHONY: mypy
 mypy:  ## run mypy on the codebase
 	MYPYPATH=stubs uv run --package ref-core mypy packages/ref-core
+	MYPYPATH=stubs uv run --package ref mypy packages/ref
 	MYPYPATH=stubs uv run --package ref-metrics-example mypy packages/ref-metrics-example
 
 .PHONY: ruff-fixes
 ruff-fixes:  ## fix the code using ruff
 	uv run ruff check --fix
 	uv run ruff format
 
+.PHONY: test-ref
+test-ref:  ## run the tests
+	uv run --package ref \
+		pytest packages/ref \
+		-r a -v --doctest-modules --cov=packages/ref/src
+
 .PHONY: test-core
 test-core:  ## run the tests
 	uv run --package ref-core \
@@ -56,7 +63,7 @@ test-integration:  ## run the integration tests
 		-r a -v
 
 .PHONY: test
-test: test-core test-metrics-example test-integration ## run the tests
+test: test-core test-ref test-metrics-example test-integration ## run the tests
 
 # Note on code coverage and testing:
 # If you want to debug what is going on with coverage, we have found

alembic.ini

@@ -0,0 +1,114 @@
+# A generic, single database configuration.
+
+[alembic]
+# path to migration scripts
+# Use forward slashes (/) also on windows to provide an os agnostic path
+script_location = %(here)s/packages/ref/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>=3.9 or backports.zoneinfo library.
+# Any required deps can installed by adding `alembic[tz]` to the pip requirements
+# string value is passed to ZoneInfo()
+# 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 packages/ref/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:packages/ref/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 = newline
+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
+
+
+[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
+
+# lint with attempts to fix using "ruff"
+hooks = ruff-fix, ruff-format
+
+ruff-fix.type = exec
+ruff-fix.executable = %(here)s/.venv/bin/ruff
+ruff-fix.options = check -q --fix REVISION_SCRIPT_FILENAME
+
+ruff-format.type = exec
+ruff-format.executable = %(here)s/.venv/bin/ruff
+ruff-format.options = format -q 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

changelog/11.feature.md

@@ -0,0 +1 @@
+Add `SqlAlchemy` as an ORM for the database alongside `alembic` for managing database migrations.

changelog/8.feature.md

@@ -0,0 +1 @@
+Adds the `ref` package with a basic CLI interface that will allow for users to interact with the database of jobs.

packages/ref-core/src/ref_core/exceptions.py

@@ -0,0 +1,4 @@
+class RefException(Exception):
+    """Base class for exceptions related to REF operations"""
+
+    pass

packages/ref/README.md

@@ -0,0 +1,10 @@
+# ref
+
+The `ref` package orchestrates the tracking and execution of model benchmarking metrics
+against CMIP data.
+
+
+## Usage
+
+The `ref` package exposes a command line interface (CLI) that can be used to
+interact with the

packages/ref/alembic/README

@@ -0,0 +1,22 @@
+# Alembic
+
+Alembic is a database migration tool.
+It interoperates with SqlAlchemy to determine how the currently declared models differ from what the database
+expects and generates a migration to apply the changes.
+
+The migrations are applied at run-time automatically (see [ref.database.Database]()).
+
+## Generating migrations
+
+To generate a migration,
+you can use the `uv run` command with the `alembic` package and the `revision` command.
+The `--rev-id` flag is used to specify the revision id.
+If it is omitted the revision id will be generated automatically.
+
+```
+uv run --package ref alembic revision --rev-id 0.1.0 --message "initial table" --autogenerate
+```
+
+How we name and manage these migrations is still a work in progress.
+It might be nice to have a way to automatically generate the revision id based on the version of the package.
+This would allow us to easily track which migrations have been applied to the database.

packages/ref/alembic/env.py

@@ -0,0 +1,73 @@
+from logging.config import fileConfig
+
+from alembic import context
+
+from ref.config import Config
+from ref.database import Database
+from ref.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)
+
+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 = config.attributes.get("connection", None)
+
+    if connectable is None:
+        db = Database.from_config(Config(), run_migrations=False)
+        connectable = db._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()

packages/ref/alembic/script.py.mako

@@ -0,0 +1,26 @@
+"""${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"}

packages/ref/alembic/versions/0.1.0_initial_table.py

@@ -0,0 +1,41 @@
+"""initial table
+
+Revision ID: 0.1.0
+Revises:
+Create Date: 2024-11-08 11:21:55.995923
+
+"""
+
+from collections.abc import Sequence
+from typing import Union
+
+import sqlalchemy as sa
+from alembic import op
+
+# revision identifiers, used by Alembic.
+revision: str = "0.1.0"
+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:
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.create_table(
+        "dataset",
+        sa.Column("dataset_id", sa.String(), nullable=False),
+        sa.Column("instance_id", sa.String(), nullable=False),
+        sa.Column("master_id", sa.String(), nullable=False),
+        sa.Column("version", sa.String(), nullable=False),
+        sa.Column("data_node", sa.String(), nullable=False),
+        sa.Column("size", sa.Integer(), nullable=False),
+        sa.Column("number_of_files", sa.Integer(), nullable=False),
+        sa.PrimaryKeyConstraint("dataset_id"),
+    )
+    # ### end Alembic commands ###
+
+
+def downgrade() -> None:
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.drop_table("dataset")
+    # ### end Alembic commands ###

packages/ref/conftest.py

@@ -0,0 +1,20 @@
+import pytest
+
+from ref.config import Config
+
+# Ignore the alembic folder
+collect_ignore = ["alembic"]
+
+
+@pytest.fixture
+def config(tmp_path, monkeypatch) -> Config:
+    monkeypatch.setenv("REF_CONFIGURATION", str(tmp_path / "ref"))
+
+    # Uses the default configuration
+    cfg = Config.load(tmp_path / "ref" / "ref.toml")
+
+    # Use a SQLite in-memory database for testing
+    cfg.db.database_url = "sqlite:///:memory:"
+    cfg.save()
+
+    return cfg