Add mc-db-unique as default single-(owner,repo) selector

client/qldbtools/README.md

@@ -67,6 +67,6 @@ import qldbtools as ql
 
     ./bin/mc-db-view-info < db-info-2.csv 
     
-    
+    ./bin/mc-db-unique < db-info-2.csv > db-info-3.csv
     
         

client/qldbtools/bin/mc-db-unique

@@ -0,0 +1,43 @@
+#!/usr/bin/env python
+""" Read a table of CodeQL DB information, 
+    group entries by (owner,name),  sort each group by
+    creationTime and keep only the top (newest) element.
+"""
+import argparse
+import logging
+
+#
+#* Configure logger
+# 
+logging.basicConfig(level=logging.INFO, format='%(asctime)s %(message)s')
+# Overwrite log level set by minio
+root_logger = logging.getLogger()
+root_logger.setLevel(logging.INFO)
+
+#
+#* Process command line
+#
+parser = argparse.ArgumentParser(
+    description=""" Read a table of CodeQL DB information, 
+    group entries by (owner,name),  sort each group by
+    creationTime and keep only the top (newest) element.
+    """)
+
+args = parser.parse_args()
+#
+#* Collect the information and select subset
+#
+import pandas as pd
+import sys
+
+df0 = pd.read_csv(sys.stdin)
+
+df_sorted = df0.sort_values(by=['owner', 'name', 'creationTime'])
+df_unique = df_sorted.groupby(['owner', 'name']).first().reset_index()
+
+df_unique.to_csv(sys.stdout, index=False)
+
+
+# Local Variables:
+# python-shell-virtualenv-root: "~/work-gh/mrva/mrvacommander/client/qldbtools/venv/"
+# End:

client/qldbtools/qldbtools/session-4-unique.py

@@ -0,0 +1,16 @@
+# Experimental work with utils.py, to be merged into it.
+from utils import *
+from pprint import pprint
+
+#* Reload gzipped CSV file to continue work
+df2 = pd.read_csv('db-info-2.csv')
+
+
+df_sorted = df2.sort_values(by=['owner', 'name', 'creationTime'])
+df_unique = df_sorted.groupby(['owner', 'name']).first().reset_index()
+
+# 
+# Local Variables:
+# python-shell-virtualenv-root: "~/work-gh/mrva/mrvacommander/client/qldbtools/venv/"
+# End:
+#