75 lines
3.3 KiB
Python
75 lines
3.3 KiB
Python
#!/usr/bin/env python3
|
|
import json
|
|
import os
|
|
from pathlib import Path
|
|
|
|
"""
|
|
This is a very simple python script, which only function is to "reduplicate" or rather restore the original
|
|
status of your files after wrongfully running rmlint.
|
|
|
|
Since rmlint deletes all files with a matching checksum BUT the original, it's possible to use the leftover rmlint.json file
|
|
to copy the original files back into their original destination.
|
|
|
|
There is only one value which you may technically need to edit, which is the path to your rmlint json down below this comment block
|
|
but, just in case give the document a read
|
|
"""
|
|
|
|
rmlint_file = "ENTER HERE THE PATH OF YOUR rmlint.json FILE!!!"
|
|
|
|
with open(rmlint_file, encoding="utf-8") as f:
|
|
json_data = json.load(f) # Load the data of the rmlint into a variable
|
|
|
|
|
|
def quote(line):
|
|
"""Add quotation marks to the file just to avoid errors"""
|
|
return '"' + line + '"'
|
|
|
|
|
|
def find_value(key, value):
|
|
"""
|
|
This function, will return the index number for the keys of all the twin files that have matching checksums
|
|
basically, it will be fed the value of a checksum, and go through the json data and find any files with the same
|
|
checksum and then return it on an list
|
|
"""
|
|
list_index = [] # declare empty list
|
|
for i, dic in enumerate(json_data):
|
|
if dic.get(key) == value: # if checksum == checksum
|
|
list_index.append(i) # append the index into the list to return
|
|
return list_index
|
|
|
|
|
|
for dic in json_data:
|
|
# This, is where the magic happens, it will separate the json into individual dictionaires
|
|
if dic.get("type") == "duplicate_file" and dic.get("is_original") == True:
|
|
# Looks for original files which belong to duplicated groups
|
|
checksum = dic.get("checksum")
|
|
twins = dic.get("twins")
|
|
# This calls the function, and stores the list of indexes
|
|
list_index = find_value("checksum", checksum)
|
|
original_file = dic.get("path")
|
|
missing_files = []
|
|
# Checks that the count of twins matches the amount of indexes found, should match
|
|
if dic.get("twins") == len(list_index):
|
|
for i in list_index:
|
|
# Now, it will list only files that were deleted
|
|
if json_data[i].get("is_original") == False:
|
|
# And append them to missing files
|
|
missing_files.append((json_data[i].get("path")))
|
|
"""
|
|
This is unnecesary, but just to make sure that it will ONLY attempt to copy if the original file still exists
|
|
in my case, I deleted a couple files, which when trying to copy them threw an error, this was a bit scary till I realize
|
|
those files I actually delted myself, this hopefully makes the experience more seamless for the user
|
|
"""
|
|
if Path(original_file).exists() == False:
|
|
print("ERROR!!! the original file is missing, perhaps you deleted it?")
|
|
print(original_file)
|
|
else:
|
|
# RESTORE THE FILES!!!!
|
|
print("Original file found:")
|
|
print(original_file)
|
|
print("Restoring to:")
|
|
for file in missing_files:
|
|
os.system("echo " + quote(file))
|
|
os.system("cp " + quote(str(original_file)) + " " + quote(str(file)))
|
|
print("______________________")
|