moved filtering

binary_dna_conversion.py

@@ -265,22 +265,6 @@ def remove_ban_words_z_encoding(sequence: str, z_method_offset=0) -> str:
     return sequence_wo_bans
 
 
-def apply_binary_filter(binary_string: str) -> str:
-    """
-    apply a filter to the binary string
-    use the length of the string as a default hash key, so 2 files of different size have a different hash key
-    this is because some zip results starts with the same octets
-    we just need to use the same key for the un-hashing
-    """
-    filter = hashing.hash_string_to_formated_base2(str(len(binary_string)), len(binary_string))
-    filtered_binary_string = ""
-    for i in range(len(binary_string)):
-        filter_bit = int(filter[i]) # get filter bit of index i
-        filtered_binary_string += str((int(binary_string[i])+filter_bit) % 2) # get reverse binary string of index i and XOR it with the filter bit
-         
-    return filtered_binary_string
-
-
 # =================== main ======================= #
 if __name__ == '__main__':
     #doc_path = sys.argv[1]

file_to_dna.py

@@ -49,6 +49,22 @@ def compute_check_sum(binary_string: str) -> str:
         
     return bin_sum.zfill(CHECK_SUM_SIZE) # fill the beginning with 0 to get the correct size
 
+
+def apply_binary_filter(binary_string: str) -> str:
+    """
+    apply a filter to the binary string
+    use the length of the string as a default hash key, so 2 files of different size have a different hash key
+    this is because some zip results starts with the same octets
+    we just need to use the same key for the un-hashing
+    """
+    filter = hashing.hash_string_to_formated_base2(str(len(binary_string)), len(binary_string))
+    filtered_binary_string = ""
+    for i in range(len(binary_string)):
+        filter_bit = int(filter[i]) # get filter bit of index i
+        filtered_binary_string += str((int(binary_string[i])+filter_bit) % 2) # get reverse binary string of index i and XOR it with the filter bit
+         
+    return filtered_binary_string
+
   
 def convert_file_to_bits(input_path: str) -> str:
     """
@@ -192,7 +208,7 @@ def encode_file(input_path: str, output_path: str) -> None:
     
     # apply a filter to the binary string -> shuffle the data to avoid long rows of 0 or 1, and avoid rows repetitions 
     binary_string = binary_string[::-1] # reverse the binary string, because 2 files can have the same start with ziping methods
-    filtered_binary_string = bdc.apply_binary_filter(binary_string)
+    filtered_binary_string = apply_binary_filter(binary_string)
     
     
     # calculate and add the binary check_sum at the end
@@ -274,7 +290,7 @@ def decode_file(input_path: str, output_path: str) -> None:
         exit(1)
         
     # apply the same filter used in the encoding to the binary string to remove it  
-    binary_string = bdc.apply_binary_filter(binary_string)
+    binary_string = apply_binary_filter(binary_string)
     binary_string = binary_string[::-1] # reverse the binary string to get the original
 
     # case binaries length is not multiple of 8 -> remove the excess bits at the beginning that have been added in the encoding to get a round number of blocks