removed duplicate script dna file reader

dna_file_reader.py

-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-"""
-Created on Fri Oct 23 09:26:22 2020
-
-@author: oboulle
-"""
-import os
-import sys
-
-
-def read_fasta(fasta_file_path):
-    """
-    :param fasta_file_path: path to the .fasta file
-    :return: a dictionary containing the name and the content of the sequences in the file
-    """
-    sequence_dict = {}
-    if not os.path.isfile(fasta_file_path):
-        return None
-    fasta_file = open(fasta_file_path)
-    line = fasta_file.readline()
-    while line != "":
-        if line.startswith(">"):
-            sequence_name = line[1:].replace("\n", "")
-            sequence = ""
-            line = fasta_file.readline()
-            while not line.startswith(">") and line != "":
-                sequence += line.replace("\n", "")
-                line = fasta_file.readline()
-            sequence_dict[sequence_name] = sequence
-        else:
-            print("fasta format error :",line)
-            exit(1)
-    fasta_file.close()
-    return sequence_dict
-
-
-def read_single_sequence_fasta(fasta_file_path):
-    """
-    :param fasta_file_path: path to the .fasta file
-    :return: the name and the value of the sequence in the file
-    """
-    if not os.path.isfile(fasta_file_path):
-        return None, None
-    fasta_file = open(fasta_file_path)
-    line = fasta_file.readline()
-    if line.startswith(">"):
-        sequence_name = line[1:].replace("\n", "")
-        sequence = ""
-        line = fasta_file.readline()
-        while not line.startswith(">") and line != "":
-            sequence += line.replace("\n", "")
-            line = fasta_file.readline()
-    else:
-        print("error, could not red the sequence from the file :",fasta_file_path)
-        sequence_name, sequence = "", ""
-    fasta_file.close()
-    return sequence_name, sequence
-    
-    
-def read_fastq(fastq_file_path):
-    """
-    :param fastq_file_path: path to the .fastq file
-    :return: a list containing the name, content, description and score of the sequences in the file
-    """
-    sequence_list = []
-    fastq_file = open(fastq_file_path)
-    line = fastq_file.readline()
-    while line != "":
-        if line.startswith("@"):
-            seq_name = line.replace("\n", "")
-            line = fastq_file.readline()
-            seq_value = line.replace("\n", "")
-            line = fastq_file.readline()
-            seq_description = line.replace("\n", "")
-            line = fastq_file.readline()
-            seq_score = line.replace("\n", "")
-            line = fastq_file.readline()
-            sequence_list.append([seq_name, seq_value, seq_description, seq_score])
-        else:
-            print("fastq format error :",line)
-            exit(1)
-    fastq_file.close()
-    return sequence_list
-
-
-def reverse_complement(sequence):
-    """
-    return the reverse complement of a dna sequence (AGTT -> AACT)
-    :param sequence: the input sequence
-    :return: the reverse complement of the input sequence
-    """
-    complement = {"A": "T", "T": "A", "C": "G", "G": "C"}
-    result = ""
-    for letter in sequence:
-        result = complement[letter] + result
-    return result
-
-
-def get_sequence_size(fasta_file_path):
-    """
-    :param fasta_file_path: path of the .fasta file
-    :return: the length of the dna sequence
-    """
-    fasta_file = open(fasta_file_path)
-    fasta_file.readline()  # skip the first line
-    line = fasta_file.readline()
-    return len(line)
-
-
-def fasta_to_fastq(fasta_file_path, output_path):
-    """
-    convert a fasta file into a fastq file
-    :param fasta_file_path: path of the .fasta file
-    :param output_path: path of the .fastq output
-    """
-    sequences = read_fasta(fasta_file_path)
-    file_output = open(output_path, "w+")
-    for name, value in sequences.items():
-        file_output.write("@"+name+"\n")
-        file_output.write(value+"\n")
-        file_output.write("+\n")
-        file_output.write("---\n")
-    file_output.close()
-
-
-# =================== main ======================= #
-if __name__ == '__main__':
-    input_path = sys.argv[1]  # file to read the sequences
-    output_path = sys.argv[2]  # file to save the sequences
-    fasta_to_fastq(input_path, output_path)

image_conversion.py

@@ -3,7 +3,6 @@ import numpy as np
 import random
 from PIL import Image
 
-import dna_file_reader as dfr
 
 """
 convert images to dna sequences
@@ -266,7 +265,6 @@ if __name__ == "__main__":
             pass
     matrix_to_png(mat2, 'RGB', "img_decoded.png")
     """
-    seq_path = sys.argv[1]
-    name, sequence = dfr.read_single_sequence_fasta(seq_path)
+    sequence = sys.argv[1]
     decode_png(sequence, "test.png", "RGB;118;106")
 

sequence_control.py

 import sys
 import math
-import dna_file_reader as dfr
 import hashing
 import source_encoding
 import source_decoding
@@ -165,9 +164,7 @@ if __name__ == '__main__':
         print("usage : sequence_control.py sequence_path")
         sys.exit(1)
 
-    sequence_path = sys.argv[1]
-
-    _, sequence = dfr.read_single_sequence_fasta(sequence_path)
+    sequence = sys.argv[1]
     
     #find_hash_keys(sequence)
     decode_sequence(sequence)

source_decoding.py

 import sys
 import os.path
-import hashing
+import inspect
 import argparse
+
+import hashing
 import image_conversion as img_conv
 import file_conversion as file_conv
+
+currentdir = os.path.dirname(os.path.abspath(inspect.getfile(inspect.currentframe())))
+sys.path.insert(0, os.path.dirname(currentdir)+"/synthesis_simulation")
 import dna_file_reader as dfr
 import dna_numbering as dnbr
 

source_encoding.py

 import sys
 import os.path
+import inspect
 import argparse
+
 import hashing
 import image_conversion as img_conv
 import file_conversion as file_conv
+
+currentdir = os.path.dirname(os.path.abspath(inspect.getfile(inspect.currentframe())))
+sys.path.insert(0, os.path.dirname(currentdir)+"/synthesis_simulation")
 import dna_file_reader as dfr
 import dna_numbering as dnbr