added unredact function. Currently debugging file not found error

Author: rootware

.gitignore

@@ -6,6 +6,7 @@ redacted_*
 ip_test.txt
 multiredact
 manhours*
+hashshadow*
 .hashshadow*
 *.txt
 .vscode

.vscode/launch.json

@@ -10,7 +10,7 @@
       "request": "launch",
       "module": "pyredactkit",
       "justMyCode": true,
-      "args": ["test/test.txt"]
+      "args": ["redacted_attempts.log", "-u", ".hashshadow_attempts.log.json"]
     }
   ]
 }

pyredactkit/pyredactkit.py

@@ -5,9 +5,9 @@
 
 import argparse
 from pyredactkit.redact import Redactor
+from pyredactkit.unredact import Unredactor
 import os
 import glob
-# lintertest
 
 banner = """
     ______       ______         _            _     _   ___ _   
@@ -35,8 +35,17 @@ def main():
         formatter_class=argparse.ArgumentDefaultsHelpFormatter
     )
     parser.add_argument(
-        "file", nargs="+",
-        help="Path of a file or a directory of files"
+        "file",
+        nargs="+",
+        help="""Path of a file or a directory of files"""
+    )
+    parser.add_argument(
+        "-u",
+        "--unredact",
+        help="""
+        Option to unredact masked data.
+        pyredactkit [redactedfile] -u [.hashshadow.json]
+        """
     )
     parser.add_argument(
         "-t", "--redactiontype",
@@ -82,13 +91,16 @@ def main():
 
     # redact file
     redact_obj = Redactor()
+    unredact_obj = Unredactor()
 
     for file in files:
         if args.redactiontype:
             redact_obj.process_file(file, args.redactiontype)
         elif args.dirout:
             redact_obj.process_file(file, args.redactiontype, args.dirout)
             redact_obj.process_report(file, args.dirout)
+        elif args.unredact:
+            unredact_obj.unredact(args.unredact, file)
         else:
             redact_obj.process_file(file)
             redact_obj.process_report(file)

pyredactkit/redact.py

@@ -5,7 +5,6 @@
 import sys
 import re
 import math
-import hashlib
 import json
 import uuid
 
@@ -82,7 +81,15 @@ def allowed_file(self, file):
             return False
         return mimetypes.guess_type(file)[0] in self.get_allowed_files()
 
-    def write_hashmap(self, hash_map, filename):
+    def write_hashmap(self, hash_map=dict, filename=str):
+        """Function that writes a .hashshadow_file.txt.json to os directory.
+        Args:
+            hash_map (dictionary): dictionary object to be written to file.
+            filename (str): name of supplied file
+
+        Returns:
+            Writes .hashshadow_file.txt.json to os directory
+        """
         with open(f".hashshadow_{os.path.basename(filename)}.json", "w", encoding="utf-8") as file:
             json.dump(hash_map, file)
             print(
@@ -106,6 +113,7 @@ def redact_specific(self, line=str, option=str, filename=str):
         Args:
             line (str) : line to be supplied to redact
             option (str): (optional) choice for redaction
+            filename (str): name of supplied file
 
         Returns:
             line (str): redacted line

pyredactkit/unredact.py

@@ -0,0 +1,55 @@
+import json
+import sys
+
+
+class Unredactor:
+    """Redactor class
+    Class containing all methods to support un-redaction
+    of masked data
+
+    """
+
+    def __init__(self):
+        """
+        Class Initialization
+        Args:
+            None
+
+        Returns:
+            None
+        """
+
+    def replace_all(self, text, dictionary):
+        """Function to replace all the text from string
+        Args:
+            text (str): A line of text in string format
+            dictionary (dict): A key value pair of masked data and original data
+
+        Returns:
+            text (str): A line of text after replacing masked data with original data
+        """
+        for k, v in dictionary.items():
+            text = text.replace(k, v)
+        return text
+
+    def unredact(self, lookup_file, redacted_file):
+        """Function to unredact masked data and produces original unredacted data.
+        Args:
+            lookup_file (str): Name of the file to look up key value map of masked data and original data.
+            redacted_file (str): Name of the redacted file
+
+        Returns:
+            Writes unredacted_file.txt with original unmasked data.
+        """
+        with open(redacted_file, encoding="utf-8") as redacted_target:
+            try:
+                with open(lookup_file, encoding="utf-8") as lookup_target:
+                    with open(f"unredacted_{redacted_file}", "w", encoding="utf-8") as write_file:
+                        content = json.load(lookup_target)
+                        for line in redacted_target:
+                            line = self.replace_all(line, content)
+                            write_file.write(line)
+            except FileNotFoundError:
+                sys.exit(f"[ - ] {lookup_file} file was not found")
+            except json.JSONDecodeError:
+                sys.exit(f"[ - ] Issue decoding {lookup_file} file")

test/unredact.py

@@ -3,6 +3,7 @@
 import json
 import os
 import sys
+import fileinput
 
 
 def unredact(lookup_file, redacted_file):
@@ -11,17 +12,27 @@ def unredact(lookup_file, redacted_file):
             with open(lookup_file, encoding="utf-8") as lookup_target:
                 with open("unredacted_file.txt", "w", encoding="utf-8") as write_file:
                     content = json.load(lookup_target)
-                    for key, value in content.items():
-                        for line in redacted_target:
-                            if key in line:
-                                print(line)
-                            # print(line)
-                            # line = line.replace(key, value)
-                            # write_file.write(line)
+                    for line in redacted_target:
+                        line = replace_all(line, content)
+                        write_file.write(line)
         except FileNotFoundError:
             sys.exit(f"[ - ] {lookup_file} file was not found")
         except json.JSONDecodeError:
             sys.exit(f"[ - ] Issue decoding {lookup_file} file")
 
 
+def replace_all(text, dictionary):
+    for k, v in dictionary.items():
+        text = text.replace(k, v)
+    return text
+
+
 unredact(".hashshadow.json", "redacted_test.txt")
+
+
+# with fileinput.FileInput("redacted_test.txt", inplace=True, backup='.bak') as file:
+#     for line in file:
+#         line.replace("c9b72036-172d-461a-ab87-b1098ad5649d",
+#                      "www.linkedin.com")
+
+#     file.write(line)