Add global timeout #30. Thanks @Gill-Bates

ConfigExamples/fullConfig.yaml

@@ -8,9 +8,10 @@ collect:  # Settings determining which audit logs to collect and how to do it
     Audit.Exchange: True
     Audit.SharePoint: True
     DLP.All: True
-  rustEngine: True  # Use False to revert to the old Python engine. If running from python instead of executable, make sure to install the python wheel in the RustEngineWheels folder
+  rustEngine: True  # Use False to revert to the old Python engine. If running from python instead of executable, make sure to install the Rust enginej python wheel in the RustEngineWheels folder
 # schedule: 0 1 0  # How often to run in days/hours/minutes. Program will never exit and run on the schedule. Uncomment to use.
   maxThreads: 50  # Maximum number of simultaneous threads retrieving logs
+  globalTimeout: 0  # Number of minutes before the process is forced to exit if still running (0 = no timeout). If you run e.g. every hour you could set this to 59, ensuring there will only be 1 active process.
   retries: 3  # Times to retry retrieving a content blob if it fails
   retryCooldown: 3  # Seconds to wait before retrying retrieving a content blob
   autoSubscribe: True  # Automatically subscribe to collected content types. Never unsubscribes from anything.

Source/AuditLogCollector.py

@@ -80,6 +80,11 @@ def run_once(self):
             self.receive_results_from_rust_engine()
             self._stop_interfaces(force=False)
         else:
+            logging.warning(
+                "WARNING: The Python engine is deprecated; it will be removed in a future version as it has been "
+                "replaced by the Rust engine. Consider removing the 'rustEngine: False' line in your config. If you "
+                "are experiencing issues with the Rust engine, please consider creating an issue on the GitHub repo so "
+                "it can be fixed (https://github.com/ddbnl/office365-audit-log-collector/issues)")
             self._start_monitoring()
             self._get_all_available_content()
             while self.monitor_thread.is_alive():
@@ -95,8 +100,12 @@ def receive_results_from_rust_engine(self):
                                 self.config['collect', 'retries'] or 3)
         engine.run_once()
         last_received = datetime.datetime.now()
+        timeout = self.config['collect', 'globalTimeout']
         while True:
             try:
+                if timeout and datetime.datetime.now() - self.run_started >= datetime.timedelta(minutes=timeout):
+                    logging.error("Global timeout reached, killing process.")
+                    sys.exit(-1)
                 result = engine.get_result()
             except ValueError:  # RustEngine throws this error when no logs are in the results recv queue
                 now = datetime.datetime.now()