Added a parameter to reprocessing running processes.

nomad/cli/admin/admin.py

@@ -40,7 +40,8 @@ from nomad.normalizing.springer import update_springer_data
 
 
 def __run_processing(
-        uploads, parallel: int, process: Callable[[proc.Upload], None], label: str):
+        uploads, parallel: int, process: Callable[[proc.Upload], None], label: str,
+        reprocess_running: bool = False):
     if isinstance(uploads, (tuple, list)):
         uploads_count = len(uploads)
 
@@ -64,7 +65,7 @@ def __run_processing(
         logger.info('%s started' % label, upload_id=upload.upload_id)
 
         completed = False
-        if upload.process_running:
+        if upload.process_running and not reprocess_running:
             logger.warn(
                 'cannot trigger %s, since the upload is already/still processing' % label,
                 current_process=upload.current_process,

nomad/cli/admin/uploads.py

@@ -272,10 +272,13 @@ def msgpack(ctx, uploads):
 @uploads.command(help='Reprocess selected uploads.')
 @click.argument('UPLOADS', nargs=-1)
 @click.option('--parallel', default=1, type=int, help='Use the given amount of parallel processes. Default is 1.')
+@click.option('--reprocess-running', is_flag=True, help='Also reprocess already running processes.')
 @click.pass_context
-def re_process(ctx, uploads, parallel: int):
+def re_process(ctx, uploads, parallel: int, reprocess_running: bool):
     _, uploads = query_uploads(ctx, uploads)
-    __run_processing(uploads, parallel, lambda upload: upload.re_process_upload(), 're-processing')
+    __run_processing(
+        uploads, parallel, lambda upload: upload.re_process_upload(), 're-processing',
+        reprocess_running=reprocess_running)
 
 
 @uploads.command(help='Repack selected uploads.')

nomad/processing/data.py

@@ -98,8 +98,10 @@ class Calc(Proc):
             ('upload_id', 'process_status'),
             ('upload_id', 'metadata.nomad_version'),
             'parser',
+            'metadata.processed',
+            'metadata.last_processing',
             'metadata.published',
-            'metadata.datasets'
+            'metadata.datasets',
             'metadata.pid'
         ]
     }