created_at and updated_at columns (#121)

* created_at and updated_at columns

* add test

* more testing

* alembic logic integrated in code

* style and type-check

* import init_database

* add default value

---------

Co-authored-by: Alessio Siniscalchi <[email protected]>

Author: malmans2

README.md

@@ -104,6 +104,25 @@ Before pushing to GitHub, run the following commands:
 1. Run the static type checker: `make type-check`
 1. Build the documentation (see [Sphinx tutorial](https://www.sphinx-doc.org/en/master/tutorial/)): `make docs-build`
 
+### Instructions for database updating
+
+In case of database structure upgrade, developers must follow these steps:
+
+1. Update the new database structure modifying [/cacholote/database.py](/cacholote/database.py), using
+   [SQLAlchemy ORM technologies](https://docs.sqlalchemy.org/en/latest/orm/)
+1. Execute from the cacholote work folder:
+   ```
+   alembic revision -m "message about the db modification"
+   ```
+1. The last command will create a new python file inside [/alembic/versions](/alembic/versions). Fill the `upgrade`
+   function with the operations that must be executed to migrate the database from the old structure to the new one.
+   Keep in mind both DDL (structure modification) and DML (data modification) instructions. For reference,
+   use https://alembic.sqlalchemy.org/en/latest/ops.html#ops.
+   Similarly, do the same with the `downgrade` function.
+1. Commit and push the modifications and the new file.
+
+For details about the alembic migration tool, see the [Alembic tutorial](https://alembic.sqlalchemy.org/en/latest/tutorial.html).
+
 ## License
 
 ```

alembic.ini

@@ -0,0 +1,122 @@
+# A generic, single database configuration.
+
+[alembic]
+# path to migration scripts
+# Use forward slashes (/) also on windows to provide an os agnostic path
+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>=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 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
+
+drivername =
+username =
+password =
+host =
+port =
+database =
+sqlalchemy.url = %(drivername)s://%(username)s:%(password)s@%(host)s:%(port)s/%(database)s
+
+
+[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 +1,65 @@
+"""module for entry points."""
+
+import sqlalchemy as sa
+
+import alembic.context
+import cacholote
+
+config = alembic.context.config
+
+
+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_props = dict()
+    for prop in ["drivername", "username", "password", "host", "port", "database"]:
+        url_props[prop] = config.get_main_option(prop)
+    url_props["port"] = url_props["port"] and int(url_props["port"]) or None  # type: ignore
+    url = sa.engine.URL.create(**url_props)  # type: ignore
+    alembic.context.configure(
+        url=url,
+        target_metadata=cacholote.database.Base.metadata,
+        literal_binds=True,
+        dialect_opts={"paramstyle": "named"},
+    )
+    with alembic.context.begin_transaction():
+        alembic.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.
+
+    """
+    url_props = dict()
+    for prop in ["drivername", "username", "password", "host", "port", "database"]:
+        url_props[prop] = config.get_main_option(prop)
+    url_props["port"] = url_props["port"] and int(url_props["port"]) or None  # type: ignore
+    url = sa.engine.URL.create(**url_props)  # type: ignore
+    engine = sa.create_engine(url, poolclass=sa.pool.NullPool)
+    with engine.connect() as connection:
+        alembic.context.configure(
+            connection=connection,
+            target_metadata=cacholote.database.Base.metadata,
+            version_table="alembic_version_cacholote",
+        )
+
+        with alembic.context.begin_transaction():
+            alembic.context.run_migrations()
+
+
+if alembic.context.is_offline_mode():
+    run_migrations_offline()
+else:
+    run_migrations_online()

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"}

alembic/versions/a38663d192e5_add_created_at_and_rename_timestamp_.py

@@ -0,0 +1,35 @@
+"""add created_at and rename timestamp column.
+
+Revision ID: a38663d192e5
+Revises:
+Create Date: 2024-07-24 15:53:43.989464
+
+"""
+
+from typing import Sequence, Union
+
+import sqlalchemy as sa
+
+import cacholote
+from alembic import op
+
+# revision identifiers, used by Alembic.
+revision: str = "a38663d192e5"
+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:
+    op.add_column(
+        "cache_entries",
+        sa.Column("created_at", sa.DateTime, default=cacholote.utils.utcnow),
+    )
+    op.execute(f"UPDATE cache_entries SET created_at='{cacholote.utils.utcnow()!s}'")
+
+    op.alter_column("cache_entries", "timestamp", new_column_name="updated_at")
+
+
+def downgrade() -> None:
+    op.drop_column("cache_entries", "created_at")
+    op.alter_column("cache_entries", "updated_at", new_column_name="timestamp")

cacholote/__init__.py

@@ -23,6 +23,7 @@
     delete,
     expire_cache_entries,
 )
+from .database import init_database
 from .decode import loads
 from .encode import dumps
 
@@ -47,6 +48,7 @@
     "dumps",
     "expire_cache_entries",
     "extra_encoders",
+    "init_database",
     "loads",
     "utils",
 ]

cacholote/cache.py

@@ -76,7 +76,7 @@ def wrapper(*args: Any, **kwargs: Any) -> Any:
                 for cache_entry in session.scalars(
                     sa.select(database.CacheEntry)
                     .filter(*filters)
-                    .order_by(database.CacheEntry.timestamp.desc())
+                    .order_by(database.CacheEntry.updated_at.desc())
                 ):
                     try:
                         return _decode_and_update(session, cache_entry, settings)

cacholote/clean.py

@@ -196,9 +196,13 @@ def _get_method_sorters(
     ) -> list[sa.orm.InstrumentedAttribute[Any]]:
         sorters: list[sa.orm.InstrumentedAttribute[Any]] = []
         if method == "LRU":
-            sorters.extend([database.CacheEntry.timestamp, database.CacheEntry.counter])
+            sorters.extend(
+                [database.CacheEntry.updated_at, database.CacheEntry.counter]
+            )
         elif method == "LFU":
-            sorters.extend([database.CacheEntry.counter, database.CacheEntry.timestamp])
+            sorters.extend(
+                [database.CacheEntry.counter, database.CacheEntry.updated_at]
+            )
         else:
             raise ValueError(f"{method=}")
         sorters.append(database.CacheEntry.expiration)
@@ -368,9 +372,9 @@ def expire_cache_entries(
     if tags is not None:
         filters.append(database.CacheEntry.tag.in_(tags))
     if before is not None:
-        filters.append(database.CacheEntry.timestamp < before)
+        filters.append(database.CacheEntry.created_at < before)
     if after is not None:
-        filters.append(database.CacheEntry.timestamp > after)
+        filters.append(database.CacheEntry.created_at > after)
 
     count = 0
     with config.get().instantiated_sessionmaker() as session: