Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
149 changes: 149 additions & 0 deletions alembic.ini
Original file line number Diff line number Diff line change
@@ -0,0 +1,149 @@
# A generic, single database configuration.

[alembic]
# path to migration scripts.
# this is typically a path given in POSIX (e.g. forward slashes)
# format, relative to the token %(here)s which refers to the location of this
# ini file
script_location = %(here)s/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
# Or organize into date-based subdirectories (requires recursive_version_locations = true)
# file_template = %%(year)d/%%(month).2d/%%(day).2d_%%(hour).2d%%(minute).2d_%%(second).2d_%%(rev)s_%%(slug)s

# sys.path path, will be prepended to sys.path if present.
# defaults to the current working directory. for multiple paths, the path separator
# is defined by "path_separator" below.
prepend_sys_path = .


# timezone to use when rendering the date within the migration file
# as well as the filename.
# If specified, requires the tzdata library which can be 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 <script_location>/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 "path_separator"
# below.
# version_locations = %(here)s/bar:%(here)s/bat:%(here)s/alembic/versions

# path_separator; This indicates what character is used to split lists of file
# paths, including version_locations and prepend_sys_path within configparser
# files such as alembic.ini.
# The default rendered in new alembic.ini files is "os", which uses os.pathsep
# to provide os-dependent path splitting.
#
# Note that in order to support legacy alembic.ini files, this default does NOT
# take place if path_separator is not present in alembic.ini. If this
# option is omitted entirely, fallback logic is as follows:
#
# 1. Parsing of the version_locations option falls back to using the legacy
# "version_path_separator" key, which if absent then falls back to the legacy
# behavior of splitting on spaces and/or commas.
# 2. Parsing of the prepend_sys_path option falls back to the legacy
# behavior of splitting on spaces, commas, or colons.
#
# Valid values for path_separator are:
#
# path_separator = :
# path_separator = ;
# path_separator = space
# path_separator = newline
#
# Use os.pathsep. Default configuration used for new projects.
path_separator = os

# 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

# database URL. Archivist's env.py builds the URL from Settings
# (`get_settings().sqlalchemy_database_uri`) rather than reading it here, so
# this key is intentionally left unset.
# sqlalchemy.url =


[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 module runner, against the "ruff" module
# hooks = ruff
# ruff.type = module
# ruff.module = ruff
# ruff.options = check --fix REVISION_SCRIPT_FILENAME

# Alternatively, use the exec runner to execute a binary found on your PATH
# hooks = ruff
# ruff.type = exec
# ruff.executable = ruff
# ruff.options = check --fix REVISION_SCRIPT_FILENAME

# Logging configuration. This is also consumed by the user-maintained
# env.py script only.
[loggers]
keys = root,sqlalchemy,alembic

[handlers]
keys = console

[formatters]
keys = generic

[logger_root]
level = WARNING
handlers = console
qualname =

[logger_sqlalchemy]
level = WARNING
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
1 change: 1 addition & 0 deletions alembic/README
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
Generic single-database configuration.
67 changes: 67 additions & 0 deletions alembic/env.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,67 @@
"""Alembic environment for Archivist.

Wires Alembic to Archivist's settings-driven database configuration. The
target metadata is `database.Base.metadata`; importing `archivist.orm`
registers the `Manifest` / `ManifestEntry` / `Archive` tables on it. Mirrors
the sibling Librarian's `alembic/env.py`.
"""

# A hack so that `archivist` is importable when alembic is run from the repo
# root: the `src/` layout means the package lives under src/.
import sys

sys.path.insert(0, "src")

from logging.config import fileConfig

from alembic import context
from archivist import orm # noqa: F401 (registers ORM tables on Base.metadata)
from archivist.database import Base, get_engine
from archivist.settings import get_settings

# 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.
if config.config_file_name is not None:
fileConfig(config.config_file_name)

# Autogenerate compares this metadata against the live database.
target_metadata = Base.metadata


def run_migrations_offline() -> None:
"""Run migrations in 'offline' mode -- all we need is a URL."""
url = get_settings().sqlalchemy_database_uri
context.configure(
url=url,
target_metadata=target_metadata,
literal_binds=True,
dialect_opts={"paramstyle": "named"},
render_as_batch=True,
)

with context.begin_transaction():
context.run_migrations()


def run_migrations_online() -> None:
"""Run migrations in 'online' mode -- using the actual Archivist database
connection built from settings.
"""
with get_engine().connect() as connection:
context.configure(
connection=connection,
target_metadata=target_metadata,
render_as_batch=True,
)

with context.begin_transaction():
context.run_migrations()


if context.is_offline_mode():
run_migrations_offline()
else:
run_migrations_online()
28 changes: 28 additions & 0 deletions alembic/script.py.mako
Original file line number Diff line number Diff line change
@@ -0,0 +1,28 @@
"""${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, Sequence[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:
"""Upgrade schema."""
${upgrades if upgrades else "pass"}


def downgrade() -> None:
"""Downgrade schema."""
${downgrades if downgrades else "pass"}
Original file line number Diff line number Diff line change
@@ -0,0 +1,86 @@
"""baseline: manifest, manifest_entry, archive

Revision ID: ff34fa3fb15c
Revises:
Create Date: 2026-07-13 11:12:15.020976

"""

from typing import Sequence, Union

import sqlalchemy as sa

from alembic import op

# revision identifiers, used by Alembic.
revision: str = "ff34fa3fb15c"

down_revision: Union[str, Sequence[str], None] = None
branch_labels: Union[str, Sequence[str], None] = None
depends_on: Union[str, Sequence[str], None] = None


def upgrade() -> None:
"""Upgrade schema."""
# ### commands auto generated by Alembic - please adjust! ###
op.create_table(
"manifest",
sa.Column("id", sa.String(length=36), nullable=False),
sa.Column("librarian_name", sa.String(length=256), nullable=False),
sa.Column("created_time", sa.DateTime(), nullable=False),
sa.Column("total_size_bytes", sa.BigInteger(), nullable=False),
sa.Column("file_count", sa.Integer(), nullable=False),
sa.PrimaryKeyConstraint("id"),
)
op.create_table(
"archive",
sa.Column("id", sa.String(length=36), nullable=False),
sa.Column("created_time", sa.DateTime(), nullable=False),
sa.Column("retries", sa.Integer(), nullable=False),
sa.Column("manifest_id", sa.String(length=36), nullable=False),
sa.Column("archive_root", sa.String(length=512), nullable=False),
sa.Column("archive_path", sa.String(length=2048), nullable=True),
sa.Column("librarian_archive_id", sa.String(length=2048), nullable=True),
sa.Column("consumed", sa.Boolean(), nullable=True),
sa.Column("consumed_time", sa.DateTime(), nullable=True),
sa.Column("completed", sa.Boolean(), nullable=True),
sa.Column("completed_time", sa.DateTime(), nullable=True),
sa.Column("failed", sa.Boolean(), nullable=True),
sa.ForeignKeyConstraint(["manifest_id"], ["manifest.id"], ondelete="CASCADE"),
sa.PrimaryKeyConstraint("id"),
sa.UniqueConstraint("librarian_archive_id"),
sa.UniqueConstraint("manifest_id"),
)
op.create_table(
"manifest_entry",
sa.Column("id", sa.Integer(), nullable=False),
sa.Column("manifest_id", sa.String(length=36), nullable=False),
sa.Column("name", sa.String(length=1024), nullable=False),
sa.Column("create_time", sa.DateTime(), nullable=False),
sa.Column("size", sa.BigInteger(), nullable=False),
sa.Column("checksum", sa.String(length=256), nullable=False),
sa.Column("uploader", sa.String(length=256), nullable=False),
sa.Column("source", sa.String(length=256), nullable=False),
sa.Column("instance_path", sa.String(length=2048), nullable=False),
sa.Column("instance_create_time", sa.DateTime(), nullable=False),
sa.Column("instance_available", sa.Boolean(), nullable=False),
sa.Column("outgoing_transfer_id", sa.Integer(), nullable=False),
sa.ForeignKeyConstraint(["manifest_id"], ["manifest.id"], ondelete="CASCADE"),
sa.PrimaryKeyConstraint("id"),
)
with op.batch_alter_table("manifest_entry", schema=None) as batch_op:
batch_op.create_index(batch_op.f("ix_manifest_entry_manifest_id"), ["manifest_id"], unique=False)

# ### end Alembic commands ###


def downgrade() -> None:
"""Downgrade schema."""
# ### commands auto generated by Alembic - please adjust! ###
with op.batch_alter_table("manifest_entry", schema=None) as batch_op:
batch_op.drop_index(batch_op.f("ix_manifest_entry_manifest_id"))

op.drop_table("manifest_entry")
op.drop_table("archive")
op.drop_table("manifest")
# ### end Alembic commands ###
2 changes: 2 additions & 0 deletions pyproject.toml
Original file line number Diff line number Diff line change
Expand Up @@ -25,6 +25,7 @@ dependencies = [
"loguru",
"uvicorn",
"requests>=2.32.5",
"alembic>=1.18.5",
]

[project.urls]
Expand All @@ -39,6 +40,7 @@ dev = [
"coveralls>=4.0.1",
"httpx>=0.28.1",
"hypothesis>=6.141.1",
"ipython>=9.15.0",
"isort>=6.1.0",
"pre-commit>=4.3.0",
"pytest>=8.4.2",
Expand Down
2 changes: 1 addition & 1 deletion src/archivist/__init__.py
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,6 @@
"""Archive tools for data."""

from ._version import __version__
from .core.archive import Archive
from .core.archive_job import ArchiveJob
from .core.registry import RegistryLibrarian, RegistrySqlite
from .storage import StorageDisk, StorageHPSS
Loading