mirror of
https://github.com/lrnselfreliance/wrolpi.git
synced 2026-10-26 19:01:39 -04:00
The database now lives at <media>/config/wrolpi.db so a library (files, configs, AND database) travels with the drive between WROLPi systems. Core: - wrolpi/db.py: lazy SQLite engine factory (WAL, busy_timeout=30s, foreign_keys=ON); get_db_curs yields a plain sqlite3.Cursor; native sqlite3 paramstyle everywhere (no compatibility shims); global sqlite3 adapters keep raw-SQL datetime formats identical to the ORM's. - wrolpi/fts.py: FTS5 external-content search replacing tsvector/GIN. Injection-proof websearch->FTS5 translator, bm25(10,4,2,1) reproducing A/B/C/D weighting, fast(abc)/deep column filtering, snippet headlines. Stemming contract pinned by dedicated tests (watch/watches/watched/ watching are interchangeable). - wrolpi/schema_ddl.py: SQLite triggers shared verbatim by the alembic baseline and test DBs; fixes the channel video_count DELETE/UPDATE bugs and a latent total_size bug (it used the video id as channel id). - wrolpi/db_bootstrap.py: startup auto-create/migrate; refuses databases written by a newer WROLPi (db_version_mismatch); SQLite 3.40 floor; network-filesystem refusal; never creates/migrates/trusts a database beneath an unmounted production media directory (shadow-DB guard). - Alembic: 85 Postgres-era migrations squashed into one baseline; revision ids are dates (2026_07_10_1350) so filenames self-sort and alembic_version says when a schema was created; render_as_batch=True. - All raw Postgres SQL rewritten (ANY->json_each IN, array_agg @> -> HAVING COUNT(DISTINCT), unnest->executemany/UPDATE..FROM, generate_series histograms->strftime GROUP BY, DISTINCT ON-> row_number(), writable CTEs->two statements, jsonb_*->json_*, explicit NULLS FIRST/LAST, LIMIT-before-OFFSET). Simple statements converted to SQLAlchemy instead (flag upsert, download retry/summary/tag checks, channel-by-tag estimate, Directory delete). - Config imports count skipped entries; background dumps are blocked after a lossy import so partial imports can never overwrite YAML configs (they are the sole source of truth for rebuilds now). - Search tolerates explicit JSON nulls for limit/offset (Postgres treated OFFSET NULL as 0; SQLite errors). - file_group.id/doc_section.id render as INTEGER PRIMARY KEY on SQLite (BIGINT is not a rowid alias; FTS5 content_rowid requires it). Ops teardown: docker-compose db service, CI postgres sidecars, initialize_api_db.sh, controller postgresql service, psycopg2-binary all removed. upgrade.sh stops/disables postgresql (data is NOT deleted; `systemctl enable --now postgresql` restores it); systemd units no longer Want postgresql.service. Existing-user upgrade: first boot creates+migrates the DB, configs import (tags recreate their FileGroups from disk), a refresh rebuilds the library index. QA'd on the 10.0.0.8 RPi: rebuild matched the Postgres baseline exactly; survived an uncontrolled hard reboot with clean integrity checks. Accepted behavior changes: FTS5 has no stopwords; bm25 length normalization shifts some rank orders; fast-path d_headline is un-highlighted; all-negative queries match nothing. Deferred: Debian/trixie package lists (incl. sqlite3 CLI), Cypress re-baseline, VACUUM INTO snapshots, exFAT/NTFS warning, auto-kicked rebuild refresh with progress UX. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
116 lines
4 KiB
Python
116 lines
4 KiB
Python
from logging.config import fileConfig
|
|
|
|
from alembic import context
|
|
|
|
# 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 wrolpi.common import Base
|
|
# Import all models so they are registered with the Base metadata
|
|
from wrolpi.files.models import FileGroup, Directory # noqa: F401
|
|
from modules.docs.models import Doc # noqa: F401
|
|
from wrolpi.tags import Tag # noqa: F401
|
|
from wrolpi.flags import WROLPiFlag # noqa: F401
|
|
from wrolpi.downloader import Download # noqa: F401
|
|
from wrolpi.collections.models import Collection, CollectionItem # noqa: F401
|
|
from modules.videos.models import Video, Channel # noqa: F401
|
|
from modules.archive.models import Archive # noqa: F401
|
|
from modules.zim.models import Zim, TagZimEntry, ZimSubscription # noqa: F401
|
|
|
|
target_metadata = Base.metadata
|
|
|
|
|
|
def get_url() -> str:
|
|
"""The database URL: from the ini/CLI when overridden, otherwise derived from the media directory."""
|
|
url = config.get_main_option('sqlalchemy.url')
|
|
if url and not url.startswith('sqlite:///CHANGEME'):
|
|
return url
|
|
from wrolpi.db import get_db_uri
|
|
return get_db_uri()
|
|
|
|
|
|
def include_object(object_, name, type_, reflected, compare_to):
|
|
"""Exclude tables Alembic must not manage from autogenerate/check.
|
|
|
|
The FTS5 virtual tables and their shadow tables (created by wrolpi.schema_ddl /
|
|
wrolpi.fts) plus SQLite internals would otherwise be proposed for DROP."""
|
|
if type_ == 'table':
|
|
from wrolpi.fts import FTS_TABLE_PREFIXES
|
|
if name == 'sqlite_sequence' or any(name.startswith(prefix) for prefix in FTS_TABLE_PREFIXES):
|
|
return False
|
|
return True
|
|
|
|
|
|
def process_revision_directives(context_, revision, directives):
|
|
"""New revisions get date ids (e.g. 2026_07_10_1350) instead of random hashes.
|
|
|
|
Filenames therefore self-sort chronologically, and the `alembic_version` value in a
|
|
database says when its schema was created. Underscores, not dashes: alembic forbids
|
|
`-` in revision identifiers (it is reserved for relative-revision syntax like `head-1`)."""
|
|
from datetime import datetime, timezone
|
|
script = directives[0]
|
|
script.rev_id = datetime.now(timezone.utc).strftime('%Y_%m_%d_%H%M')
|
|
|
|
|
|
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=get_url(),
|
|
target_metadata=target_metadata,
|
|
literal_binds=True,
|
|
dialect_opts={"paramstyle": "named"},
|
|
render_as_batch=True,
|
|
include_object=include_object,
|
|
process_revision_directives=process_revision_directives,
|
|
)
|
|
|
|
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.
|
|
|
|
"""
|
|
from wrolpi.db import create_wrolpi_engine
|
|
|
|
connectable = create_wrolpi_engine(get_url())
|
|
|
|
with connectable.connect() as connection:
|
|
context.configure(
|
|
connection=connection,
|
|
target_metadata=target_metadata,
|
|
# SQLite's limited ALTER TABLE requires batch mode for most column changes.
|
|
render_as_batch=True,
|
|
include_object=include_object,
|
|
process_revision_directives=process_revision_directives,
|
|
)
|
|
|
|
with context.begin_transaction():
|
|
context.run_migrations()
|
|
|
|
|
|
if context.is_offline_mode():
|
|
run_migrations_offline()
|
|
else:
|
|
run_migrations_online()
|