work in progress: testing the impact of underlying buffer size when reading gzip fasta files

phagetermvirome/IData_handling.py

@@ -286,14 +286,15 @@ class ReadGetter:
 def totReads(filin):
     """Verify and retrieve the number of reads in the fastq file before alignment"""
     start_t=time.perf_counter_ns()
+    bufsize=102400
     if filin.endswith('.gz'):
         print(io.DEFAULT_BUFFER_SIZE)
         filein = gzip.open(filin, 'rb')
     else:
         filein = open(filin, 'r')
-
     line = 0
-    while filein.readline():
+    with io.BufferedReader(filein, buffer_size=bufsize) as buffered_f:
+    #while filein.readline():
         line += 1
     seq = float(round(line / 4))
     filein.close()