find hash keys

sequence_control.py

 import sys
 import dna_file_reader as dfr
+import hashing
+import source_encoding
+from numpy import source
 
 
 def check_homopolymere(sequence, max_h):
@@ -64,21 +67,47 @@ def check_loop(sequence, loop_size, window_size):
     return loop_nbr
 
 
-def sequence_check(sequence, window_size):
-    h_max = check_homopolymere(sequence, 3)
-    print("number of homopolymere larger than",3,":",h_nbr)
+def sequence_check(sequence, window_size, verbose=False):
+    h_nbr = check_homopolymere(sequence, 3)
+    if verbose: print("number of homopolymere larger than",3,":",h_nbr)
     min_GC_percent, max_GC_percent = check_GC(sequence, window_size)
-    print("GC percentage :",min_GC_percent,"% to",max_GC_percent,"%")
+    if verbose: print("GC percentage :",min_GC_percent,"% to",max_GC_percent,"%")
     loop_nbr = check_loop(sequence, 6, window_size)
-    print("number of potential loop :",loop_nbr)
+    if verbose: print("number of potential loop :",loop_nbr)
     
-    if h_max == 0 and min_GC_percent > 40 and max_GC_percent < 55 and loop_nbr == 0:
-        print("sequence is correct")
+    if h_nbr == 0 and min_GC_percent > 40 and max_GC_percent < 55 and loop_nbr == 0:
+        if verbose: print("sequence is correct")
         return True
     else:
-        print("sequence is not correct")
+        if verbose: print("sequence is not correct")
         return False
     
+    
+def hash_until_correct(sequence, start_key=0):
+    
+    hash_key = start_key
+    hash_filter = hashing.hash_string_to_formated_number(str(hash_key), len(sequence), 4)
+    hashed_sequence = source_encoding.apply_filter(sequence, hash_filter)
+    while not sequence_check(hashed_sequence, 60):
+        hash_key += 1
+        hash_filter = hashing.hash_string_to_formated_number(str(hash_key), len(sequence), 4)
+        hashed_sequence = source_encoding.apply_filter(sequence, hash_filter)
+    
+    return hash_key
+    
+    
+def find_hash_keys(sequence):
+    tot_hash = ""
+    for i in range(5):
+        sub_seq = sequence[200*i:200*(i+1)]
+        hash_key = hash_until_correct(sub_seq)
+        hash_filter = hashing.hash_string_to_formated_number(str(hash_key), 200, 4)
+        hashed_sub_seq = source_encoding.apply_filter(sub_seq, hash_filter)
+        tot_hash += hashed_sub_seq
+        print(hash_key)
+    print(tot_hash)
+    sequence_check(tot_hash, 60, True)
+    
 # =================== main ======================= #
 if __name__ == '__main__':
      
@@ -89,4 +118,5 @@ if __name__ == '__main__':
     sequence_path = sys.argv[1]
 
     _, sequence = dfr.read_single_sequence_fasta(sequence_path)
-    sequence_check(sequence)
+    
\ No newline at end of file
+