Files
pluto 052f019075 feat: add database schema with WAL mode and FTS5 triggers
SQLite database layer with thread-local connections, WAL journal mode,
foreign key enforcement, and FTS5 full-text search on utterances via
content-table triggers. TDD: 5 tests written first, all passing.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-28 10:28:05 -05:00

89 lines
3.3 KiB
Python

import sqlite3
import threading
from pathlib import Path
from app.shared.config import Settings
_local = threading.local()
def get_db(settings: Settings) -> sqlite3.Connection:
if not hasattr(_local, "conn") or _local.conn is None:
conn = sqlite3.connect(settings.db_path, check_same_thread=False)
conn.row_factory = sqlite3.Row
conn.execute("PRAGMA journal_mode=WAL")
conn.execute("PRAGMA foreign_keys=ON")
_local.conn = conn
return _local.conn
def init_schema(settings: Settings) -> None:
Path(settings.clips_dir).mkdir(parents=True, exist_ok=True)
db = get_db(settings)
db.executescript("""
CREATE TABLE IF NOT EXISTS rooms (
id INTEGER PRIMARY KEY,
name TEXT NOT NULL UNIQUE,
device_label TEXT,
is_active BOOLEAN DEFAULT 0,
last_seen DATETIME,
created_at DATETIME DEFAULT CURRENT_TIMESTAMP
);
CREATE TABLE IF NOT EXISTS speakers (
id INTEGER PRIMARY KEY,
name TEXT NOT NULL,
created_at DATETIME DEFAULT CURRENT_TIMESTAMP,
updated_at DATETIME DEFAULT CURRENT_TIMESTAMP
);
CREATE TABLE IF NOT EXISTS voice_embeddings (
id INTEGER PRIMARY KEY,
speaker_id INTEGER NOT NULL REFERENCES speakers(id) ON DELETE CASCADE,
embedding BLOB NOT NULL,
audio_sample BLOB,
created_at DATETIME DEFAULT CURRENT_TIMESTAMP
);
CREATE TABLE IF NOT EXISTS utterances (
id INTEGER PRIMARY KEY,
room_id INTEGER NOT NULL REFERENCES rooms(id),
speaker_id INTEGER REFERENCES speakers(id),
transcript TEXT NOT NULL,
embedding BLOB,
match_status TEXT NOT NULL DEFAULT 'unreviewed',
match_confidence REAL,
start_time DATETIME NOT NULL,
end_time DATETIME NOT NULL,
audio_clip_path TEXT,
livekit_room TEXT,
created_at DATETIME DEFAULT CURRENT_TIMESTAMP
);
CREATE VIRTUAL TABLE IF NOT EXISTS utterances_fts USING fts5(
transcript, content=utterances, content_rowid=id
);
CREATE TRIGGER IF NOT EXISTS utterances_ai AFTER INSERT ON utterances BEGIN
INSERT INTO utterances_fts(rowid, transcript) VALUES (new.id, new.transcript);
END;
CREATE TRIGGER IF NOT EXISTS utterances_au AFTER UPDATE OF transcript ON utterances BEGIN
INSERT INTO utterances_fts(utterances_fts, rowid, transcript)
VALUES ('delete', old.id, old.transcript);
INSERT INTO utterances_fts(rowid, transcript) VALUES (new.id, new.transcript);
END;
CREATE TRIGGER IF NOT EXISTS utterances_ad AFTER DELETE ON utterances BEGIN
INSERT INTO utterances_fts(utterances_fts, rowid, transcript)
VALUES ('delete', old.id, old.transcript);
END;
CREATE TABLE IF NOT EXISTS daily_summaries (
id INTEGER PRIMARY KEY,
date DATE NOT NULL UNIQUE,
summary_text TEXT NOT NULL,
generated_at DATETIME DEFAULT CURRENT_TIMESTAMP
);
""")
db.commit()