Add warning to xfel-calibrate if configuration may cause result to not be reproducible

src/xfel_calibrate/calibrate.py

@@ -985,6 +985,34 @@ def run():
     caltype = args["type"].upper()
     sequential = args["no_cluster_job"]
 
+    # Pick out any arguments that may prevent reproducibility from
+    # working, sorted alphabetically and converted back to their
+    # canonical representation.
+    not_reproducible_args = sorted(
+        ('--' + x.replace('_', '-')
+         for x in ['skip_report', 'skip_env_freeze']
+         if args[x]))
+
+    # If any of these arguments are set, present a warning.
+    if not_reproducible_args:
+        print('WARNING: One or more command line arguments ({}) may prevent '
+              'this specific correction result from being reproducible based '
+              'on its metadata. It may not be possible to restore identical '
+              'output data files when they have been deleted or lost. Please '
+              'ensure that the data retention policy of the chosen storage '
+              'location is sufficient for your '
+              'needs.'.format(', '.join(not_reproducible_args)))
+
+        try:
+            input('Press ENTER to continue or CTRL+C to abort...')
+        except KeyboardInterrupt:
+            # Catch the interrupt and silently exit.
+            sys.exit(0)
+
+        reproducible = False
+    else:
+        reproducible = True
+
     try:
         nb_info = notebooks[detector][caltype]
     except KeyError:
@@ -1100,6 +1128,7 @@ def run():
     metadata["pycalibration-version"] = version
     metadata["report-path"] = f"{report_to}.pdf" if report_to \
         else '# REPORT SKIPPED #'
+    metadata['reproducible'] = reproducible
     metadata["concurrency"] = {
         'parameter': concurrency_par,
         'default': concurrency_defval,