chore: modular monolith folder split (no behavior change)

app/seismo/services/backup_scheduler.py

@@ -0,0 +1,145 @@
+"""
+Automatic Database Backup Scheduler
+Handles scheduled automatic backups of the database
+"""
+
+import schedule
+import time
+import threading
+from datetime import datetime
+from typing import Optional
+import logging
+
+from backend.services.database_backup import DatabaseBackupService
+
+logger = logging.getLogger(__name__)
+
+
+class BackupScheduler:
+    """Manages automatic database backups on a schedule"""
+
+    def __init__(self, db_path: str = "./data/seismo_fleet.db", backups_dir: str = "./data/backups"):
+        self.backup_service = DatabaseBackupService(db_path=db_path, backups_dir=backups_dir)
+        self.scheduler_thread: Optional[threading.Thread] = None
+        self.is_running = False
+
+        # Default settings
+        self.backup_interval_hours = 24  # Daily backups
+        self.keep_count = 10  # Keep last 10 backups
+        self.enabled = False
+
+    def configure(self, interval_hours: int = 24, keep_count: int = 10, enabled: bool = True):
+        """
+        Configure backup scheduler settings
+
+        Args:
+            interval_hours: Hours between automatic backups
+            keep_count: Number of backups to retain
+            enabled: Whether automatic backups are enabled
+        """
+        self.backup_interval_hours = interval_hours
+        self.keep_count = keep_count
+        self.enabled = enabled
+
+        logger.info(f"Backup scheduler configured: interval={interval_hours}h, keep={keep_count}, enabled={enabled}")
+
+    def create_automatic_backup(self):
+        """Create an automatic backup and cleanup old ones"""
+        if not self.enabled:
+            logger.info("Automatic backups are disabled, skipping")
+            return
+
+        try:
+            timestamp = datetime.utcnow().strftime("%Y-%m-%d %H:%M UTC")
+            description = f"Automatic backup - {timestamp}"
+
+            logger.info("Creating automatic backup...")
+            snapshot = self.backup_service.create_snapshot(description=description)
+
+            logger.info(f"Automatic backup created: {snapshot['filename']} ({snapshot['size_mb']} MB)")
+
+            # Cleanup old backups
+            cleanup_result = self.backup_service.cleanup_old_snapshots(keep_count=self.keep_count)
+            if cleanup_result['deleted'] > 0:
+                logger.info(f"Cleaned up {cleanup_result['deleted']} old snapshots")
+
+            return snapshot
+
+        except Exception as e:
+            logger.error(f"Automatic backup failed: {str(e)}")
+            return None
+
+    def start(self):
+        """Start the backup scheduler in a background thread"""
+        if self.is_running:
+            logger.warning("Backup scheduler is already running")
+            return
+
+        if not self.enabled:
+            logger.info("Backup scheduler is disabled, not starting")
+            return
+
+        logger.info(f"Starting backup scheduler (every {self.backup_interval_hours} hours)")
+
+        # Clear any existing scheduled jobs
+        schedule.clear()
+
+        # Schedule the backup job
+        schedule.every(self.backup_interval_hours).hours.do(self.create_automatic_backup)
+
+        # Also run immediately on startup
+        self.create_automatic_backup()
+
+        # Start the scheduler thread
+        self.is_running = True
+        self.scheduler_thread = threading.Thread(target=self._run_scheduler, daemon=True)
+        self.scheduler_thread.start()
+
+        logger.info("Backup scheduler started successfully")
+
+    def _run_scheduler(self):
+        """Internal method to run the scheduler loop"""
+        while self.is_running:
+            schedule.run_pending()
+            time.sleep(60)  # Check every minute
+
+    def stop(self):
+        """Stop the backup scheduler"""
+        if not self.is_running:
+            logger.warning("Backup scheduler is not running")
+            return
+
+        logger.info("Stopping backup scheduler...")
+        self.is_running = False
+        schedule.clear()
+
+        if self.scheduler_thread:
+            self.scheduler_thread.join(timeout=5)
+
+        logger.info("Backup scheduler stopped")
+
+    def get_status(self) -> dict:
+        """Get current scheduler status"""
+        next_run = None
+        if self.is_running and schedule.jobs:
+            next_run = schedule.jobs[0].next_run.isoformat() if schedule.jobs[0].next_run else None
+
+        return {
+            "enabled": self.enabled,
+            "running": self.is_running,
+            "interval_hours": self.backup_interval_hours,
+            "keep_count": self.keep_count,
+            "next_run": next_run
+        }
+
+
+# Global scheduler instance
+_scheduler_instance: Optional[BackupScheduler] = None
+
+
+def get_backup_scheduler() -> BackupScheduler:
+    """Get or create the global backup scheduler instance"""
+    global _scheduler_instance
+    if _scheduler_instance is None:
+        _scheduler_instance = BackupScheduler()
+    return _scheduler_instance

app/seismo/services/database_backup.py

@@ -0,0 +1,192 @@
+"""
+Database Backup and Restore Service
+Handles full database snapshots, restoration, and remote synchronization
+"""
+
+import os
+import shutil
+import sqlite3
+from datetime import datetime
+from pathlib import Path
+from typing import List, Dict, Optional
+import json
+
+
+class DatabaseBackupService:
+    """Manages database backup operations"""
+
+    def __init__(self, db_path: str = "./data/seismo_fleet.db", backups_dir: str = "./data/backups"):
+        self.db_path = Path(db_path)
+        self.backups_dir = Path(backups_dir)
+        self.backups_dir.mkdir(parents=True, exist_ok=True)
+
+    def create_snapshot(self, description: Optional[str] = None) -> Dict:
+        """
+        Create a full database snapshot using SQLite backup API
+        Returns snapshot metadata
+        """
+        if not self.db_path.exists():
+            raise FileNotFoundError(f"Database not found at {self.db_path}")
+
+        # Generate snapshot filename with timestamp
+        timestamp = datetime.utcnow().strftime("%Y%m%d_%H%M%S")
+        snapshot_name = f"snapshot_{timestamp}.db"
+        snapshot_path = self.backups_dir / snapshot_name
+
+        # Get database size before backup
+        db_size = self.db_path.stat().st_size
+
+        try:
+            # Use SQLite backup API for safe backup (handles concurrent access)
+            source_conn = sqlite3.connect(str(self.db_path))
+            dest_conn = sqlite3.connect(str(snapshot_path))
+
+            # Perform the backup
+            with dest_conn:
+                source_conn.backup(dest_conn)
+
+            source_conn.close()
+            dest_conn.close()
+
+            # Create metadata
+            metadata = {
+                "filename": snapshot_name,
+                "created_at": timestamp,
+                "created_at_iso": datetime.utcnow().isoformat(),
+                "description": description or "Manual snapshot",
+                "size_bytes": snapshot_path.stat().st_size,
+                "size_mb": round(snapshot_path.stat().st_size / (1024 * 1024), 2),
+                "original_db_size_bytes": db_size,
+                "type": "manual"
+            }
+
+            # Save metadata as JSON sidecar file
+            metadata_path = self.backups_dir / f"{snapshot_name}.meta.json"
+            with open(metadata_path, 'w') as f:
+                json.dump(metadata, f, indent=2)
+
+            return metadata
+
+        except Exception as e:
+            # Clean up partial snapshot if it exists
+            if snapshot_path.exists():
+                snapshot_path.unlink()
+            raise Exception(f"Snapshot creation failed: {str(e)}")
+
+    def list_snapshots(self) -> List[Dict]:
+        """
+        List all available snapshots with metadata
+        Returns list sorted by creation date (newest first)
+        """
+        snapshots = []
+
+        for db_file in sorted(self.backups_dir.glob("snapshot_*.db"), reverse=True):
+            metadata_file = self.backups_dir / f"{db_file.name}.meta.json"
+
+            if metadata_file.exists():
+                with open(metadata_file, 'r') as f:
+                    metadata = json.load(f)
+            else:
+                # Fallback for legacy snapshots without metadata
+                stat_info = db_file.stat()
+                metadata = {
+                    "filename": db_file.name,
+                    "created_at": datetime.fromtimestamp(stat_info.st_mtime).strftime("%Y%m%d_%H%M%S"),
+                    "created_at_iso": datetime.fromtimestamp(stat_info.st_mtime).isoformat(),
+                    "description": "Legacy snapshot",
+                    "size_bytes": stat_info.st_size,
+                    "size_mb": round(stat_info.st_size / (1024 * 1024), 2),
+                    "type": "manual"
+                }
+
+            snapshots.append(metadata)
+
+        return snapshots
+
+    def delete_snapshot(self, filename: str) -> bool:
+        """Delete a snapshot and its metadata"""
+        snapshot_path = self.backups_dir / filename
+        metadata_path = self.backups_dir / f"{filename}.meta.json"
+
+        if not snapshot_path.exists():
+            raise FileNotFoundError(f"Snapshot {filename} not found")
+
+        snapshot_path.unlink()
+        if metadata_path.exists():
+            metadata_path.unlink()
+
+        return True
+
+    def restore_snapshot(self, filename: str, create_backup_before_restore: bool = True) -> Dict:
+        """
+        Restore database from a snapshot
+        Creates a safety backup before restoring if requested
+        """
+        snapshot_path = self.backups_dir / filename
+
+        if not snapshot_path.exists():
+            raise FileNotFoundError(f"Snapshot {filename} not found")
+
+        if not self.db_path.exists():
+            raise FileNotFoundError(f"Database not found at {self.db_path}")
+
+        backup_info = None
+
+        # Create safety backup before restore
+        if create_backup_before_restore:
+            backup_info = self.create_snapshot(description="Auto-backup before restore")
+
+        try:
+            # Replace database file
+            shutil.copy2(str(snapshot_path), str(self.db_path))
+
+            return {
+                "message": "Database restored successfully",
+                "restored_from": filename,
+                "restored_at": datetime.utcnow().isoformat(),
+                "backup_created": backup_info["filename"] if backup_info else None
+            }
+
+        except Exception as e:
+            raise Exception(f"Restore failed: {str(e)}")
+
+    def get_database_stats(self) -> Dict:
+        """Get statistics about the current database"""
+        if not self.db_path.exists():
+            return {"error": "Database not found"}
+
+        conn = sqlite3.connect(str(self.db_path))
+        cursor = conn.cursor()
+
+        # Get table counts
+        cursor.execute("SELECT name FROM sqlite_master WHERE type='table' AND name NOT LIKE 'sqlite_%'")
+        tables = cursor.fetchall()
+
+        table_stats = {}
+        total_rows = 0
+
+        for (table_name,) in tables:
+            cursor.execute(f"SELECT COUNT(*) FROM {table_name}")
+            count = cursor.fetchone()[0]
+            table_stats[table_name] = count
+            total_rows += count
+
+        conn.close()
+
+        db_size = self.db_path.stat().st_size
+
+        return {
+            "database_path": str(self.db_path),
+            "size_bytes": db_size,
+            "size_mb": round(db_size / (1024 * 1024), 2),
+            "total_rows": total_rows,
+            "tables": table_stats,
+            "last_modified": datetime.fromtimestamp(self.db_path.stat().st_mtime).isoformat()
+        }
+
+    def download_snapshot(self, filename: str) -> Path:
+        """Get the file path for downloading a snapshot"""
+        snapshot_path = self.backups_dir / filename
+        if not snapshot_path.exists():
+            raise FileNotFoundError(f"Snapshot {filename} not found")
+        return snapshot_path

app/seismo/services/snapshot.py

@@ -0,0 +1,191 @@
+from datetime import datetime, timezone
+from sqlalchemy.orm import Session
+
+from backend.database import get_db_session
+from backend.models import Emitter, RosterUnit, IgnoredUnit
+
+
+def ensure_utc(dt):
+    if dt is None:
+        return None
+    if dt.tzinfo is None:
+        return dt.replace(tzinfo=timezone.utc)
+    return dt.astimezone(timezone.utc)
+
+
+def format_age(last_seen):
+    if not last_seen:
+        return "N/A"
+    last_seen = ensure_utc(last_seen)
+    now = datetime.now(timezone.utc)
+    diff = now - last_seen
+    hours = diff.total_seconds() // 3600
+    mins = (diff.total_seconds() % 3600) // 60
+    return f"{int(hours)}h {int(mins)}m"
+
+
+def calculate_status(last_seen, status_ok_threshold=12, status_pending_threshold=24):
+    """
+    Calculate status based on how long ago the unit was last seen.
+
+    Args:
+        last_seen: datetime of last seen (UTC)
+        status_ok_threshold: hours before status becomes Pending (default 12)
+        status_pending_threshold: hours before status becomes Missing (default 24)
+
+    Returns:
+        "OK", "Pending", or "Missing"
+    """
+    if not last_seen:
+        return "Missing"
+
+    last_seen = ensure_utc(last_seen)
+    now = datetime.now(timezone.utc)
+    hours_ago = (now - last_seen).total_seconds() / 3600
+
+    if hours_ago > status_pending_threshold:
+        return "Missing"
+    elif hours_ago > status_ok_threshold:
+        return "Pending"
+    else:
+        return "OK"
+
+
+def emit_status_snapshot():
+    """
+    Merge roster (what we *intend*) with emitter data (what is *actually happening*).
+    Status is recalculated based on current time to ensure accuracy.
+    """
+
+    db = get_db_session()
+    try:
+        # Get user preferences for status thresholds
+        from backend.models import UserPreferences
+        prefs = db.query(UserPreferences).filter_by(id=1).first()
+        status_ok_threshold = prefs.status_ok_threshold_hours if prefs else 12
+        status_pending_threshold = prefs.status_pending_threshold_hours if prefs else 24
+
+        roster = {r.id: r for r in db.query(RosterUnit).all()}
+        emitters = {e.id: e for e in db.query(Emitter).all()}
+        ignored = {i.id for i in db.query(IgnoredUnit).all()}
+
+        units = {}
+
+        # --- Merge roster entries first ---
+        for unit_id, r in roster.items():
+            e = emitters.get(unit_id)
+            if r.retired:
+                # Retired units get separated later
+                status = "Retired"
+                age = "N/A"
+                last_seen = None
+                fname = ""
+            else:
+                if e:
+                    last_seen = ensure_utc(e.last_seen)
+                    # RECALCULATE status based on current time, not stored value
+                    status = calculate_status(last_seen, status_ok_threshold, status_pending_threshold)
+                    age = format_age(last_seen)
+                    fname = e.last_file
+                else:
+                    # Rostered but no emitter data
+                    status = "Missing"
+                    last_seen = None
+                    age = "N/A"
+                    fname = ""
+
+                units[unit_id] = {
+                    "id": unit_id,
+                    "status": status,
+                    "age": age,
+                    "last": last_seen.isoformat() if last_seen else None,
+                    "fname": fname,
+                "deployed": r.deployed,
+                "note": r.note or "",
+                "retired": r.retired,
+                # Device type and type-specific fields
+                "device_type": r.device_type or "seismograph",
+                "last_calibrated": r.last_calibrated.isoformat() if r.last_calibrated else None,
+                "next_calibration_due": r.next_calibration_due.isoformat() if r.next_calibration_due else None,
+                "deployed_with_modem_id": r.deployed_with_modem_id,
+                "ip_address": r.ip_address,
+                "phone_number": r.phone_number,
+                    "hardware_model": r.hardware_model,
+                    # Location for mapping
+                    "location": r.location or "",
+                    "address": r.address or "",
+                    "coordinates": r.coordinates or "",
+                }
+
+        # --- Add unexpected emitter-only units ---
+        for unit_id, e in emitters.items():
+            if unit_id not in roster:
+                last_seen = ensure_utc(e.last_seen)
+                # RECALCULATE status for unknown units too
+                status = calculate_status(last_seen, status_ok_threshold, status_pending_threshold)
+                units[unit_id] = {
+                    "id": unit_id,
+                    "status": status,
+                    "age": format_age(last_seen),
+                    "last": last_seen.isoformat(),
+                    "fname": e.last_file,
+                    "deployed": False,            # default
+                    "note": "",
+                    "retired": False,
+                    # Device type and type-specific fields (defaults for unknown units)
+                    "device_type": "seismograph",  # default
+                    "last_calibrated": None,
+                    "next_calibration_due": None,
+                    "deployed_with_modem_id": None,
+                    "ip_address": None,
+                    "phone_number": None,
+                    "hardware_model": None,
+                    # Location fields
+                    "location": "",
+                    "address": "",
+                    "coordinates": "",
+                }
+
+        # Separate buckets for UI
+        active_units = {
+            uid: u for uid, u in units.items()
+            if not u["retired"] and u["deployed"] and uid not in ignored
+        }
+
+        benched_units = {
+            uid: u for uid, u in units.items()
+            if not u["retired"] and not u["deployed"] and uid not in ignored
+        }
+
+        retired_units = {
+            uid: u for uid, u in units.items()
+            if u["retired"]
+        }
+
+        # Unknown units - emitters that aren't in the roster and aren't ignored
+        unknown_units = {
+            uid: u for uid, u in units.items()
+            if uid not in roster and uid not in ignored
+        }
+
+        return {
+            "timestamp": datetime.utcnow().isoformat(),
+            "units": units,
+            "active": active_units,
+            "benched": benched_units,
+            "retired": retired_units,
+            "unknown": unknown_units,
+            "summary": {
+                "total": len(active_units) + len(benched_units),
+                "active": len(active_units),
+                "benched": len(benched_units),
+                "retired": len(retired_units),
+                "unknown": len(unknown_units),
+                # Status counts only for deployed units (active_units)
+                "ok": sum(1 for u in active_units.values() if u["status"] == "OK"),
+                "pending": sum(1 for u in active_units.values() if u["status"] == "Pending"),
+                "missing": sum(1 for u in active_units.values() if u["status"] == "Missing"),
+            }
+        }
+    finally:
+        db.close()