Fix: include CID when filtering in mc-rows-from-mrva-list

This commit is contained in:
Michael Hohn
2024-08-22 13:58:07 -07:00
committed by =Michael Hohn
parent 0d3f4c5e40
commit 7d27b910cd

View File

@@ -19,9 +19,11 @@ Script to list full details for a mrva-list file
]
}
2. reads a pandas dataframe stored in a csv file
3. selects all rows from 2. that contain the 'owner' column matching
the string before the slash from 1. and the 'name' column matching
the string between the slash and the marker 'ctsj'
3. selects all rows from 2. that
- contain the 'owner' column matching the string before the slash from 1. and
- the 'name' column matching the string between the slash and the marker
'ctsj' and
- the 'CID' column matching the string after the marker 'ctsj'
"""
import argparse
@@ -49,7 +51,8 @@ parsed_mirva_list = []
for item in mirva_list:
owner_name = item.split('/')[0]
repo_name = item.split('/')[1].split('ctsj')[0]
parsed_mirva_list.append((owner_name, repo_name))
cid = item.split('/')[1].split('ctsj')[1]
parsed_mirva_list.append((owner_name, repo_name, cid))
#* Step 2: Read the CSV file into a pandas dataframe
import pandas as pd
@@ -58,7 +61,7 @@ df = pd.read_csv(args.info_csv)
#* Step 3: Filter the dataframe based on the parsed "mirva-list"
filtered_df = df[
df.apply(lambda row:
(row['owner'], row['name']) in parsed_mirva_list, axis=1)]
(row['owner'], row['name'], row['CID']) in parsed_mirva_list, axis=1)]
# Optionally, you can save the filtered dataframe to a new CSV file
filtered_df.to_csv(sys.stdout, index=False)