Added order by CheckSum

mv_unique_files.py

@@ -3,6 +3,7 @@ import os
 import argparse
 from typing import List
 import pandas as pd
+import hashlib
 import csv
 
 from pandas.core.series import Series
@@ -27,6 +28,13 @@ def view_unqiue_files(p: pathlib.Path, min_size):
                 str(p.lstat().st_size/1024/1024) + 
                 "MB with number of links: " + str(p.lstat().st_nlink))
 
+def get_file_checksum(p: pathlib.Path):
+    m = hashlib.md5()
+    with open(p, 'rb') as f: 
+        while chunk := f.read(8192):
+            m.update(chunk)
+    return m.hexdigest()
+
 if __name__ == "__main__":
     parser = argparse.ArgumentParser(description='convert hardlink to symlink in download folder')
 
@@ -50,7 +58,7 @@ if __name__ == "__main__":
     parser.add_argument('--order',
                         type=str,
                         help='order exported csv by name or inode',
-                        choices=['inode','name'])
+                        choices=['inode','name','checksum'])
     
     parser.add_argument('--csv_path',
                         type=str,
@@ -71,18 +79,21 @@ if __name__ == "__main__":
 
     if args.csv == "True":
         csv_path = "result.csv"
-        df_csv = pd.DataFrame(columns=['FileName', 'Path', 'inode', 'NumberOfLinks'])
+        df_csv = pd.DataFrame(columns=['FileName', 'Path', 'inode', 'NumberOfLinks', 'CheckSum'])
         for x in paths:
             if x.lstat().st_size > min_file_size * 1024 * 1024:
                 new_row = {'FileName': x.name,
                             'Path': str(x),
                             'inode': x.lstat().st_ino,
-                            'NumberOfLinks': x.lstat().st_nlink}
+                            'NumberOfLinks': x.lstat().st_nlink,
+                            'CheckSum': get_file_checksum(x)}
                 df_csv = df_csv.append(new_row, ignore_index=True)
         if args.order == "inode":
             df_csv = df_csv.sort_values(by="inode")
         elif args.order == "name":
             df_csv = df_csv.sort_values(by="FileName")
+        elif args.order == "checksum":
+            df_csv = df_csv.sort_values(by="CheckSum")
         
         if args.csv_path:
             csv_path = args.csv_path