MediaShelf/mediashelf/db.py
Jess Hallsworth 6a557bcdd9
Implement MediaShelf v1
The application the design describes: Flask + SQLite, Plex for library data,
Tautulli for watch history, report-only.

Structure follows the design's seams. providers/ splits MediaProvider from
HistoryProvider, because on this network library data and watch data live on
different machines and Jellyfin later will have no Tautulli equivalent.
scoring.py implements the reclaim score twice - as a SQL expression for the
live grid (weights change on every slider drag, so storing it would mean
rewriting thousands of rows per drag) and in Python for CSV export and tests,
with a property test over 500 generated rows asserting the two agree.
rules.py compiles saved views to parameterized SQL through a field/operator
whitelist; nothing user-supplied is ever interpolated.

Three properties are enforced by test rather than asserted in prose:

- Ingest is idempotent. Three consecutive full scans leave every count and
  every byte total unchanged. A scanner that double-counts produces a report
  that looks plausible and is wrong.
- Keep marks survive Plex reassigning every rating key in the library. They
  are keyed on content GUID, scoped per library so the Movies and 4K Movies
  copies of the same film mark independently.
- Every config variable the app reads is declared in docker-compose.yml, so
  a variable set in Portainer can never silently do nothing.

Also found and fixed while verifying against a fake Plex+Tautulli pair:
executescript() commits the pending transaction, so migrations needed their
BEGIN/COMMIT inside the script; replaceChildren() renders null as the literal
text "null"; a hash-only URL change does not reload the document, so deep
links needed a hashchange listener; and SQLite ROUND rounds half away from
zero where Python rounds half to even.

73 tests, no live server required.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01GVbG48GAXfCZatcmX123Ra
2026-09-07 14:59:03 +00:00

158 lines
5.4 KiB
Python

"""SQLite access and migrations.
One writer (the scan job), many readers. WAL mode makes that work without
readers blocking. Migrations are plain numbered .sql files applied in order at
startup and tracked in schema_version — no ORM migration framework (§5).
"""
from __future__ import annotations
import logging
import os
import sqlite3
import threading
from pathlib import Path
log = logging.getLogger(__name__)
MIGRATIONS_DIR = Path(__file__).parent / "migrations"
_local = threading.local()
def connect(path: str, *, read_only: bool = False) -> sqlite3.Connection:
"""Open a tuned connection. Callers own the connection lifecycle."""
if path != ":memory:":
os.makedirs(os.path.dirname(os.path.abspath(path)) or ".", exist_ok=True)
conn = sqlite3.connect(path, timeout=30.0, isolation_level=None)
conn.row_factory = sqlite3.Row
conn.execute("PRAGMA journal_mode=WAL")
conn.execute("PRAGMA foreign_keys=ON")
conn.execute("PRAGMA synchronous=NORMAL")
conn.execute("PRAGMA busy_timeout=30000")
conn.execute("PRAGMA temp_store=MEMORY")
if read_only:
conn.execute("PRAGMA query_only=ON")
return conn
def migrate(conn: sqlite3.Connection) -> int:
"""Apply any unapplied migrations. Returns the resulting version."""
conn.execute(
"CREATE TABLE IF NOT EXISTS schema_version ("
" version INTEGER PRIMARY KEY, applied_at INTEGER NOT NULL)"
)
row = conn.execute("SELECT COALESCE(MAX(version), 0) AS v FROM schema_version").fetchone()
current = row["v"]
files = sorted(MIGRATIONS_DIR.glob("*.sql"))
applied = current
for f in files:
try:
version = int(f.name.split("_", 1)[0])
except ValueError:
log.warning("skipping unnumbered migration %s", f.name)
continue
if version <= current:
continue
log.info("applying migration %s", f.name)
sql = f.read_text()
# Migrations contain triggers with internal semicolons, so the whole file
# runs as a script rather than being split on ';'. executescript() commits
# any pending transaction before it runs, so the BEGIN/COMMIT must live
# inside the script itself for the migration to be atomic.
script = (
"BEGIN;\n"
+ sql
+ f"\nINSERT INTO schema_version (version, applied_at)"
f" VALUES ({version}, strftime('%s','now'));\nCOMMIT;"
)
try:
conn.executescript(script)
except Exception:
if conn.in_transaction:
conn.execute("ROLLBACK")
raise
applied = version
return applied
class Database:
"""Thin wrapper giving each thread its own connection.
Flask serves requests on multiple threads and the scheduler runs on its own,
and sqlite3 connections are not shareable across threads.
"""
def __init__(self, path: str):
self.path = path
@property
def conn(self) -> sqlite3.Connection:
c = getattr(_local, "conn", None)
if c is None or getattr(_local, "path", None) != self.path:
c = connect(self.path)
_local.conn = c
_local.path = self.path
return c
def close(self) -> None:
c = getattr(_local, "conn", None)
if c is not None:
c.close()
_local.conn = None
# ── convenience ──────────────────────────────────────────────────────
def query(self, sql: str, params: tuple | dict = ()) -> list[sqlite3.Row]:
return self.conn.execute(sql, params).fetchall()
def one(self, sql: str, params: tuple | dict = ()) -> sqlite3.Row | None:
return self.conn.execute(sql, params).fetchone()
def scalar(self, sql: str, params: tuple | dict = ()):
row = self.conn.execute(sql, params).fetchone()
return None if row is None else row[0]
def execute(self, sql: str, params: tuple | dict = ()) -> sqlite3.Cursor:
return self.conn.execute(sql, params)
def executemany(self, sql: str, seq) -> sqlite3.Cursor:
return self.conn.executemany(sql, seq)
def migrate(self) -> int:
return migrate(self.conn)
# ── settings ─────────────────────────────────────────────────────────
def get_setting(self, key: str, default=None):
row = self.one("SELECT value FROM setting WHERE key = ?", (key,))
return default if row is None else row["value"]
def set_setting(self, key: str, value: str) -> None:
self.execute(
"INSERT INTO setting (key, value) VALUES (?, ?) "
"ON CONFLICT(key) DO UPDATE SET value = excluded.value",
(key, str(value)),
)
class transaction:
"""Context manager for an explicit write transaction.
isolation_level is None (autocommit), so transactions are explicit here.
"""
def __init__(self, db: Database):
self.db = db
def __enter__(self) -> sqlite3.Connection:
self.db.conn.execute("BEGIN IMMEDIATE")
return self.db.conn
def __exit__(self, exc_type, exc, tb) -> bool:
if exc_type is None:
self.db.conn.execute("COMMIT")
else:
self.db.conn.execute("ROLLBACK")
return False