diff --git a/post_processing.py b/post_processing.py
index 03c3afa8f4e0f3c1f18f78c3e098d8a4e5348645..72339c292e99e38c381d1eaed4469ccfe8a438a0 100755
--- a/post_processing.py
+++ b/post_processing.py
@@ -12,6 +12,12 @@ do the opposite of pre_processing.py
take dna sequences and convert them into files
"""
+def compressed_name(file_path):
+ return file_path+".gz"
+
+def uncompressed_name(file_path):
+ return file_path.replace(".gz", "")
+
def convert_to_binary(input_dir_path, compressed_dir_path):
"""
@@ -20,7 +26,7 @@ def convert_to_binary(input_dir_path, compressed_dir_path):
for filename in os.listdir(input_dir_path):
file_path = os.path.join(input_dir_path, filename)
- result_file_path = os.path.join(compressed_dir_path, filename)+".gz"
+ result_file_path = os.path.join(compressed_dir_path, compressed_name(filename))
# checking if it is a file
if os.path.isfile(file_path):
@@ -38,14 +44,14 @@ def uncompress_files(compressed_dir_path, uncompressed_dir_path):
"""
for filename in os.listdir(compressed_dir_path):
file_path = os.path.join(compressed_dir_path, filename)
- result_file_path = os.path.join(uncompressed_dir_path, filename.replace(".gz",""))
+ result_file_path = os.path.join(uncompressed_dir_path, uncompressed_name(filename))
# checking if it is a file
if os.path.isfile(file_path):
pre_processing.unzip_file(file_path)
# move the unzipped file
- os.replace(file_path.replace(".gz", ""), result_file_path)
+ os.replace(uncompressed_name(file_path), result_file_path)
elif os.path.isdir(file_path):
print("error post processing (uncompress_files) : directory found in compressed_dir_path", filename)
diff --git a/pre_processing.py b/pre_processing.py
index bae60193ecc4d86d40cf01447e86698927316a36..dfbc2640c08912c832bff01b05eb545cbcab995a 100755
--- a/pre_processing.py
+++ b/pre_processing.py
@@ -33,6 +33,13 @@ def unzip_file(file_path):
subprocess.run('/bin/bash -c "$COMMAND"', shell=True, env={'COMMAND': decompression_command})
+def compressed_name(file_path):
+ return file_path+".gz"
+
+def uncompressed_name(file_path):
+ return file_path.replace(".gz", "")
+
+
def insert_path_in_files(input_dir_path: str, rearanged_files_dir_path: str) -> None:
"""
copy all files from a directory and paste them at the same level in output directory, with their relative path written before first line
@@ -90,7 +97,7 @@ def compress_and_split(rearanged_files_dir_path: str, compressed_dir_path: str)
exit(0)
# get binary size of the compressed file
- binary_len = len(file_to_dna.convert_file_to_bits(compressed_file_path+".gz"))
+ binary_len = len(file_to_dna.convert_file_to_bits(compressed_name(compressed_file_path)))
if binary_len <= max_binary_length: # if acceptable length, it's perfect
files_compressed_size[filename] = binary_len # save the compressed size for this file
@@ -98,7 +105,7 @@ def compress_and_split(rearanged_files_dir_path: str, compressed_dir_path: str)
else:
# file too large, nedd to split it
- os.remove(compressed_file_path+".gz") # delete the compressed file
+ os.remove(compressed_name(compressed_file_path)) # delete the compressed file
# read the original file as bytes
with open(file_path, "rb") as input_file:
@@ -143,7 +150,7 @@ def compress_and_split(rearanged_files_dir_path: str, compressed_dir_path: str)
# compress the split_file to the compressed directory
zip_file(split_file_path, compressed_file_path + split_file_footer)
- compressed_subfile_path = compressed_file_path + split_file_footer + ".gz"
+ compressed_subfile_path = compressed_name(compressed_file_path + split_file_footer)
# check the size of the subfile
binary_len = len(file_to_dna.convert_file_to_bits(compressed_subfile_path))
@@ -197,7 +204,7 @@ def compress_and_split(rearanged_files_dir_path: str, compressed_dir_path: str)
# add the merged file path to the bis dict with it's compressed size
zip_file(merged_file_path, compressed_merged_file_path)
- merged_binary_len = len(file_to_dna.convert_file_to_bits(compressed_merged_file_path+".gz"))
+ merged_binary_len = len(file_to_dna.convert_file_to_bits(compressed_name(compressed_merged_file_path)))
if merged_binary_len >= max_binary_length:
print("error merging result too large", compressed_merged_file_path)
@@ -207,8 +214,8 @@ def compress_and_split(rearanged_files_dir_path: str, compressed_dir_path: str)
files_compressed_size[merged_file_name] = merged_binary_len
# remove the 2 compressed files of the 2 files
- os.remove(os.path.join(compressed_dir_path, filename)+".gz")
- os.remove(os.path.join(compressed_dir_path, filename_2)+".gz")
+ os.remove(os.path.join(compressed_dir_path, compressed_name(filename)))
+ os.remove(os.path.join(compressed_dir_path, compressed_name(filename_2)))
# set the compressed size of the 2 files to a too high number to avoid them to be reused for merging
files_compressed_size[filename] = 2*max_binary_length
@@ -238,7 +245,7 @@ def convert_to_sequence(compressed_dir_path, payload_fragments_dir_path):
# checking if it is a file
if os.path.isfile(file_path):
- output_file_path = os.path.join(payload_fragments_dir_path, filename.replace(".gz", ""))
+ output_file_path = os.path.join(payload_fragments_dir_path, uncompressed_name(filename))
dna_sequence = file_to_dna.encode_file(file_path, output_file_path) # convert binaries into a dna sequence and save result in the output file