Created
August 5, 2020 07:30
-
-
Save mmanylov-zz/51f210646756d27253e1d5a6d3f02cee to your computer and use it in GitHub Desktop.
Utilization of multiprocessing in processing large log files
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# see https://www.blopig.com/blog/2016/08/processing-large-files-using-python/ | |
import multiprocessing as mp | |
import os | |
import re | |
from datetime import datetime, timedelta | |
RESULT_FILENAME = 'result.csv' | |
FILENAME_TEMPLATE ='log-{date}' | |
CHUNK_SIZE = 1024*1024 | |
log_pattern = re.compile(r'^SEVERITY.*(?<=first param in quotes\s")(.*)(?=").*(?<=second param\s)(\w+).*?(third param)?$') | |
manager = mp.Manager() | |
result = manager.list() | |
def write_result_csv(result): | |
work_f = open(RESULT_FILENAME, "w") | |
work_f.write('="first param";="second param";="third param"\n') | |
for line in result: | |
result = map(lambda x: f'="{x}"', line) | |
work_f.write(';'.join(result)+"\n") | |
work_f.close() | |
def get_logfile_name(): | |
yesterday_str = datetime.strftime(datetime.now() - timedelta(1), '%Y%m%d') | |
name = FILENAME_TEMPLATE.format(date=yesterday_str) | |
return name | |
def process(line): | |
pass | |
def worker(filename, chunk_start, chunk_size): | |
with open(filename, 'r') as f: | |
f.seek(chunk_start) | |
lines = f.read(chunk_size).splitlines() | |
for line in lines: | |
process(line) | |
def chunkify(fname, size=CHUNK_SIZE): | |
file_end = os.path.getsize(fname) | |
with open(fname, 'rb') as f: | |
chunk_end = f.tell() | |
while True: | |
chunk_start = chunk_end | |
f.seek(size, 1) | |
f.readline() | |
chunk_end = f.tell() | |
yield chunk_start, chunk_end - chunk_start | |
if chunk_end > file_end: | |
break | |
pool = mp.Pool(mp.cpu_count()) | |
jobs = [] | |
filename = get_logfile_name() | |
for chunk_start, chunk_size in chunkify(filename): | |
jobs.append(pool.apply_async(worker, (filename, chunk_start, chunk_size))) | |
for job in jobs: | |
job.get() | |
pool.close() | |
pool.join() | |
write_result_csv(result) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment