From 9d746b0d319c1b3f23c7c9c6d68f49d191dae63b Mon Sep 17 00:00:00 2001
From: Veronique Legrand <vlegrand@pasteur.fr>
Date: Wed, 26 Mar 2025 16:38:58 +0100
Subject: [PATCH] work in progress: testing the impact of underlying buffer
size when reading gzip fasta files
---
phagetermvirome/IData_handling.py | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/phagetermvirome/IData_handling.py b/phagetermvirome/IData_handling.py
index dc7d31a..b75abe5 100755
--- a/phagetermvirome/IData_handling.py
+++ b/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()
--
GitLab