Update README

README.md

@@ -73,27 +73,38 @@ log_ingest --threads 1 --from 2026/01/01 --to 2026/01/31 ...
 
 ## Database Schema
 
+The schema uses normalized lookup tables to minimize disk usage for large datasets.
+
 ```sql
+-- Lookup tables for low-cardinality text columns
+CREATE TABLE apps (id INTEGER PRIMARY KEY, name TEXT NOT NULL UNIQUE);
+CREATE TABLE versions (id INTEGER PRIMARY KEY, name TEXT NOT NULL UNIQUE);
+CREATE TABLE models (id INTEGER PRIMARY KEY, name TEXT NOT NULL UNIQUE);
+CREATE TABLE devices (id INTEGER PRIMARY KEY, name TEXT NOT NULL UNIQUE);
+CREATE TABLE os_versions (id INTEGER PRIMARY KEY, name TEXT NOT NULL UNIQUE);
+CREATE TABLE app_names (id INTEGER PRIMARY KEY, name TEXT NOT NULL UNIQUE);
+
+-- Main table with foreign keys and millisecond timestamp
 CREATE TABLE signature_entries (
-    id INTEGER PRIMARY KEY AUTOINCREMENT,
     session_id TEXT NOT NULL,
-    timestamp TEXT NOT NULL,
+    timestamp_ms INTEGER NOT NULL,  -- Unix epoch milliseconds
-    app TEXT NOT NULL,
+    app_id INTEGER NOT NULL REFERENCES apps(id),
-    version TEXT NOT NULL,
+    version_id INTEGER NOT NULL REFERENCES versions(id),
-    offline_login_usage INTEGER NOT NULL,
+    offline_login_usage INTEGER,
-    is_password_autofill_enabled INTEGER NOT NULL,
+    is_password_autofill_enabled INTEGER,
-    camera_roll_usage INTEGER NOT NULL,
+    camera_roll_usage INTEGER,
-    os TEXT NOT NULL,
+    os_id INTEGER REFERENCES os_versions(id),
-    app_name TEXT NOT NULL,
+    app_name_id INTEGER REFERENCES app_names(id),
-    touch_id INTEGER NOT NULL,
+    touch_id INTEGER,
-    is_offline_login_enabled INTEGER NOT NULL,
+    is_offline_login_enabled INTEGER,
-    model TEXT NOT NULL,
+    model_id INTEGER REFERENCES models(id),
-    device TEXT NOT NULL,
+    device_id INTEGER REFERENCES devices(id),
-    password_autofill_usage INTEGER NOT NULL
+    password_autofill_usage INTEGER,
-);
+    PRIMARY KEY (session_id, timestamp_ms)
+) WITHOUT ROWID;
 
 CREATE INDEX idx_session_id ON signature_entries(session_id);
-CREATE INDEX idx_version ON signature_entries(version);
+CREATE INDEX idx_version ON signature_entries(version_id);
 ```
 
 ## Example Queries
@@ -105,15 +116,24 @@ SELECT
 FROM signature_entries;
 
 -- Count by app version
-SELECT version, COUNT(*) as cnt
+SELECT v.name as version, COUNT(*) as cnt
-FROM signature_entries
+FROM signature_entries se
-GROUP BY version
+JOIN versions v ON se.version_id = v.id
+GROUP BY v.name
 ORDER BY cnt DESC;
 
 -- Device breakdown
-SELECT device, COUNT(*) as cnt
+SELECT d.name as device, COUNT(*) as cnt
+FROM signature_entries se
+JOIN devices d ON se.device_id = d.id
+GROUP BY d.name;
+
+-- Convert timestamp_ms to readable datetime
+SELECT
+    datetime(timestamp_ms / 1000, 'unixepoch') as timestamp,
+    session_id
 FROM signature_entries
-GROUP BY device;
+LIMIT 10;
 ```
 
 ## Development