Created deal_duplicate_files.py

deal_duplicate_files.py

@@ -0,0 +1,43 @@
+import pathlib
+import argparse
+from numpy import source
+import pandas as pd
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(description='Deal with duplicate files in synology')
+
+    parser.add_argument('-s', '--source',
+                        type=str,
+                        
+                        help='csv file to the directory to be de-duplicate')
+    
+    parser.add_argument('-t', '--target',
+                        type=str,
+                        help='csv file to the directory that be compared')
+
+    args = parser.parse_args()
+    csv_source = args.source
+    csv_target = args.target
+
+    df_source = pd.DataFrame(pd.read_csv(csv_source, index_col='Index', dtype={'NumberOfLinks':'int', 'inode':'int'}))
+    df_target = pd.DataFrame(pd.read_csv(csv_target, index_col='Index', dtype={'NumberOfLinks':'int', 'inode':'int'}))
+
+    df_filtered = pd.DataFrame()
+    for index, row in df_source.iterrows():
+        checksum = row['CheckSum']
+        print(checksum)
+        for yrow in df_target.CheckSum:
+            if checksum == yrow:
+                print(row)
+                df_filtered = df_filtered.append(row)
+    
+    print("Found Duplicate")
+    print(df_filtered)
+    print("Source Directory")
+    print(df_source)
+    print("Target")
+    print(df_target)
+
+    for row in df_filtered.Path:
+        p = pathlib.Path(row)
+        print(str(p) + ": " + str(p.exists()))