We need to ensure when a BatchingTelemetryMessenger stops, all remaining
telemetries in its queue are sent. The existing logic does this, but
this commit improves the readability and intent of the code, as well as
adds a test for this condition.
On Windows, git will normalize the line endings of .txt (and other)
files to crlf instead of lf. This is useful for many files, but the
ransomware_target files need unmodified when they are checked out.
By adding an exception in .gitattributes, the files in
monkey/tests/data_for_tests/ransomware_targets are not modified on
windows.
Ransomware will soon do more than just encrypt files. We should give the
telemetry that's related to encrypting files a more descriptive name
that better describes what it is reporting.
My original plan was to start a thread in __init__() and stop the thread
when __del__() was called. Since the running thread (object) contains a
reference to the BatchingTelemetryMessenger object that launched it, the
destructor will not be called until the thread is stopped. This
resulted in adding a stop() method (fadd978) followed by adding a
start() method (1d066c8e).
By using an inner class to run the thread, we enable the class to be
used as originally intended, reducing the burden on the user of this
class. The thread is now started on construction and stopped on
destruction. The user can remain blissfully unaware that anything
resembling threading is going in, and can use the
BatchingTelemetryMessenger just like any other ITelemetryMessenger.
My original plan was to start a thread in __init__() and stop the thread
when __del__() was called. Since the running thread (object) contains a
reference to the BatchingTelemetryMessenger object that launched it, the
destructor will not be called until the thread is stopped. Therefore, a
stop() was added to allow the BatchingTelemetryMessenger to be stopped.
Since it has an explicit stop, it should also have an explicit start,
rather than starting the thread in the constructor.