horror/backend/app/db.py

import json
import sqlite3
from contextlib import contextmanager

from .config import DB_PATH

SCHEMA = """
CREATE TABLE IF NOT EXISTS movies (
    id            INTEGER PRIMARY KEY,
    title         TEXT NOT NULL,
    original_title TEXT,
    release_date  TEXT,
    year          INTEGER,
    overview      TEXT,
    teaser        TEXT,
    poster_path   TEXT,
    backdrop_path TEXT,
    vote_average  REAL,
    vote_count    INTEGER,
    runtime       INTEGER,
    genres        TEXT,
    images        TEXT,
    trailer_key   TEXT,
    imdb_id       TEXT,
    netflix_id    TEXT,
    netflix_url   TEXT,
    on_netflix    INTEGER DEFAULT 0,
    canon_group   INTEGER,
    canon_pos     INTEGER,
    collection_id   INTEGER,
    collection_name TEXT,
    synced_at     TEXT
);

CREATE TABLE IF NOT EXISTS meta (
    key   TEXT PRIMARY KEY,
    value TEXT
);

-- Fingerabdrücke der Backdrops, damit spätere Syncs die Bilder nicht
-- erneut herunterladen müssen
-- hash als BLOB: der dHash ist vorzeichenlos 64 Bit und passt nicht in
-- SQLites vorzeichenbehaftetes INTEGER
CREATE TABLE IF NOT EXISTS image_prints (
    file_path TEXT PRIMARY KEY,
    hash      BLOB NOT NULL,
    histogram BLOB NOT NULL
);
"""

JSON_FIELDS = ("genres", "images")


@contextmanager
def connect():
    DB_PATH.parent.mkdir(parents=True, exist_ok=True)
    conn = sqlite3.connect(DB_PATH)
    conn.row_factory = sqlite3.Row
    try:
        yield conn
        conn.commit()
    finally:
        conn.close()


def init():
    with connect() as conn:
        conn.executescript(SCHEMA)
        # Spalten, die erst später dazukamen — die Teaser in einer bestehenden
        # Datenbank sind zu teuer, um sie für ein Schema-Update wegzuwerfen
        existing = {row["name"] for row in conn.execute("PRAGMA table_info(movies)")}
        for column, kind in (
            ("collection_id", "INTEGER"),
            ("collection_name", "TEXT"),
            ("netflix_id", "TEXT"),
            ("imdb_id", "TEXT"),
            ("on_netflix", "INTEGER DEFAULT 0"),
            ("canon_group", "INTEGER"),
            ("canon_pos", "INTEGER"),
        ):
            if column not in existing:
                conn.execute(f"ALTER TABLE movies ADD COLUMN {column} {kind}")


def row_to_dict(row):
    movie = dict(row)
    for field in JSON_FIELDS:
        movie[field] = json.loads(movie[field] or "[]")
    return movie


def upsert(conn, movie):
    payload = dict(movie)
    for field in JSON_FIELDS:
        payload[field] = json.dumps(payload.get(field) or [], ensure_ascii=False)
    columns = ", ".join(payload)
    placeholders = ", ".join(f":{c}" for c in payload)
    conn.execute(
        f"INSERT OR REPLACE INTO movies ({columns}) VALUES ({placeholders})", payload
    )


def existing_teasers(conn):
    rows = conn.execute(
        "SELECT id, teaser FROM movies WHERE teaser IS NOT NULL AND teaser != ''"
    ).fetchall()
    return {row["id"]: row["teaser"] for row in rows}


def existing_netflix_ids(conn):
    rows = conn.execute(
        "SELECT id, netflix_id FROM movies WHERE netflix_id IS NOT NULL"
    ).fetchall()
    return {row["id"]: row["netflix_id"] for row in rows}


def drop_missing(conn, keep_ids):
    """Was weder auf Netflix läuft noch im Kanon steht, fliegt raus."""
    current = {r["id"] for r in conn.execute("SELECT id FROM movies").fetchall()}
    gone = current - set(keep_ids)
    if gone:
        conn.executemany("DELETE FROM movies WHERE id = ?", [(i,) for i in gone])
    return len(gone)


def all_movies():
    with connect() as conn:
        rows = conn.execute(
            "SELECT * FROM movies ORDER BY vote_count DESC, title ASC"
        ).fetchall()
        return [row_to_dict(r) for r in rows]


def get_movie(movie_id):
    with connect() as conn:
        row = conn.execute("SELECT * FROM movies WHERE id = ?", (movie_id,)).fetchone()
        return row_to_dict(row) if row else None


def known_prints(conn, paths):
    """SQLite begrenzt die Parameterzahl, also in Blöcken abfragen."""
    found = {}
    paths = list(paths)
    for start in range(0, len(paths), 500):
        chunk = paths[start : start + 500]
        marks = ", ".join("?" * len(chunk))
        rows = conn.execute(
            f"SELECT file_path, hash, histogram FROM image_prints "
            f"WHERE file_path IN ({marks})",
            chunk,
        ).fetchall()
        for row in rows:
            found[row["file_path"]] = (
                int.from_bytes(row["hash"], "big"),
                row["histogram"],
            )
    return found


def store_prints(conn, prints):
    conn.executemany(
        "INSERT OR REPLACE INTO image_prints (file_path, hash, histogram) "
        "VALUES (?, ?, ?)",
        [
            (path, value[0].to_bytes(8, "big"), value[1])
            for path, value in prints.items()
        ],
    )


def set_meta(conn, key, value):
    conn.execute(
        "INSERT OR REPLACE INTO meta (key, value) VALUES (?, ?)", (key, str(value))
    )


def get_meta(key):
    with connect() as conn:
        row = conn.execute("SELECT value FROM meta WHERE key = ?", (key,)).fetchone()
        return row["value"] if row else None