in reply to Python regex faster than Perl?

Recently, I tried diffing two large files only for the UNIX diff command to choke the OS. That's because the diff utility slurps both files, requiring 2x memory consumption.

I thought to provide chunking variants and measure the time taken for a 99 MB file.

Perl

#!/usr/bin/env perl
#use v5.20;
#use feature qw(signatures);
#no warnings qw(experimental::signatures);

use v5.36;
use autodie;

exit 1 if not @ARGV;

sub read_file ($fh, $chunk_size=65536) {
    # Return the next chunk, including to the end of line.
    read($fh, my $chunk, $chunk_size);
    if (length($chunk) && substr($chunk, -1) ne "\n") {
        return $chunk if eof($fh);
        $chunk .= readline($fh);
    }
    return $chunk;
}

my $mul_pattern = 'mul\(\d{1,3},\d{1,3}\)';
my $filename = shift;
my $count = 0;

if (open(my $fh, '<', $filename)) {
    while (length(my $chunk = read_file($fh))) {
        $count += () = $chunk =~ m/$mul_pattern/g;
    }
}

print "Found $count matches.\n";

[download]

Python

#!/usr/bin/env python
import re, sys

if len(sys.argv) < 2: sys.exit(1)

def read_file (file, chunk_size=65536):
    """
    Lazy function generator to read a file in chunks,
    including to the end of line.
    """
    while True:
        chunk = file.read(chunk_size)
        if not chunk:
            break
        if not chunk.endswith('\n'):
            chunk += file.readline()
        yield chunk

mul_re = re.compile(r"mul\(\d{1,3},\d{1,3}\)")
filename = sys.argv[1]
count = 0

try:
    with open (filename, "r") as file:
        for chunk in read_file(file):
            count += len(mul_re.findall(chunk))
except Exception as e:
    print(e, file=sys.stderr)
    sys.exit(1)

print(f"Found {count} matches.")

[download]

Results

Perl   0.463s
Found 200246 matches.

Python 0.250s
Found 200246 matches.

[download]

Replies are listed 'Best First'.
Re^2: Python regex faster than Perl? - Chunking 1 GB
by marioroy (Prior) on Mar 27, 2025 at 07:53 UTC

    Here I try 10x the input size i.e. ~ 1 GB input file.

    # choroba's input generator, 990 MB
# https://perlmonks.org/?node_id=11164445
# perl gen_input.pl > big

use strict;
use warnings;

for (1..100_000_000) {
  print int(rand 2)
    ? "xyzabcd" 
    : ("mul(" . int(rand 5000) . "," . int(rand 5000) . ")");
  print "\n" unless int rand 10;
}

    [download]

    Non-chunking consumes greater than 1 GB of memory ~ 1.1 GB. Chunking consumes significantly less ~ 10 MB.

    Non-chunking: > 1 GB memory

    Perl   4.395s
Found 1999533 matches.

Python 2.262s
Found 1999533 matches.

    [download]

    Chunking: ~ 10 MB memory

    Perl   4.422s
Found 1999533 matches.

Python 2.247s
Found 1999533 matches.

    [download]
[reply]
[d/l]
[select]

      Perl parallel demonstration

      Seeing Python win by 2x made me consider a parallel variant using MCE. But more so to find out if this will scale increasing the number of workers.

      #!/usr/bin/env perl
# time NUM_THREADS=3 perl pcount.pl big

use v5.36;
use autodie;
use MCE;

exit 1 if not @ARGV;

my $mul_pattern = 'mul\(\d{1,3},\d{1,3}\)';
my $filename = shift;
my $count = 0;

sub reduce_count ($worker_count) {
    $count += $worker_count;
}

my $mce = MCE->new(
    max_workers => $ENV{NUM_THREADS} // MCE::Util::get_ncpu(),
    chunk_size => 65536*16,
    use_slurpio => 1,
    gather => \&reduce_count,
    user_func => sub {
        my ($mce, $slurp_ref, $chunk_id) = @_;
        my $count = () = $$slurp_ref =~ m/$mul_pattern/g;
        $mce->gather($count);
    }
)->spawn;

$mce->process({ input_data => $filename });
$mce->shutdown;

print "Found $count matches.\n";

      [download]

      This calls for slurpio for best performance. No line by line processing behind the scene. The MCE gather option is set to a reduce function to tally the counts. And, increased chunk_size to reduced IPC among the workers. The input file is read serially.

      Results

      Found 1999533 matches.

1: 4.420s
2: 2.263s  needs 2 workers to reach Python performance
3: 1.511s
4: 1.154s
5: 0.940s
6: 0.788s
7: 0.680s
8: 0.600s
9: 0.538s

      [download]

      Python parallel demonstration

      Now I wonder about parallel in Python. We can reuse the chunk function introduced in the prior example.

      #!/usr/bin/env python
# time NUM_THREADS=3 python pcount.py big

import os, re, sys
from multiprocessing import Pool, cpu_count

if len(sys.argv) < 2: sys.exit(1)

def read_file (file, chunk_size=65536*16):
    """
    Lazy function generator to read a file in chunks,
    including to the end of line.
    """
    while True:
        chunk = file.read(chunk_size)
        if not chunk:
            break
        if not chunk.endswith('\n'):
            chunk += file.readline()
        yield chunk

def process_chunk(chunk):
    """
    Worker function to process chunks in parallel.
    """
    count = len(mul_re.findall(chunk))
    return count

mul_re = re.compile(r"mul\(\d{1,3},\d{1,3}\)")
num_processes = int(os.getenv('NUM_THREADS') or cpu_count())
p = Pool(num_processes)
file_name = sys.argv[1]

try:
    with open (file_name, "r") as file:
        results = p.map(process_chunk, read_file(file))
    p.close()
    p.join()
except Exception as e:
    print(e, file=sys.stderr)
    sys.exit(1)

print(f"Found {sum(results)} matches.")

      [download]

      Results

      Found 1999533 matches.

1: 3.131s
2: 1.824s
3: 1.408s
4: 1.178s
5: 1.187s
6: 1.187s
7: 1.172s
8: 1.008s
9: 0.995s

      [download]
[reply]
[d/l]
[select]

        Yet, another attempt with MCE-like chunking for more apple-to-apple comparison. Workers seek to offset position and slurp the whole chunk.

        Last updated on March 28, 2025.

        Python parallel demonstration

        #!/usr/bin/env python
# time NUM_THREADS=3 python pcount2.py big

import os, re, sys

from concurrent.futures import ProcessPoolExecutor, as_completed
from multiprocessing import Pool, cpu_count, Lock

if len(sys.argv) < 2: sys.exit(1)

mul_re = re.compile(r"mul\(\d{1,3},\d{1,3}\)")
lock = Lock()

def process_chunk(params):
    """
    Worker function to process chunks in parallel.
    Read IO is serial to not cause a denial of service
    for SAN storage. Comment out locking for parallel IO.
    """
    file_name, chunk_start, chunk_end = params
    with open (file_name, "r") as f:
        f.seek(chunk_start)
 #      lock.acquire()
        chunk = f.read(chunk_end - chunk_start)
 #      lock.release()
        count = len(mul_re.findall(chunk))
        return count

def parallel_read(file_name):
    num_processes = int(os.getenv('NUM_THREADS') or cpu_count())

    def gen_offsets():
        # Emit next offset input [ file_name, chunk_start, chunk_end ]
        try:
            file_size = os.path.getsize(file_name)
        except Exception as e:
            print(e, file=sys.stderr);
            sys.exit(1)

        chunk_size = 65536 * 16
        position = 0

        with open(file_name, 'r') as f:
            while True:
                chunk_start = position
                if chunk_start > file_size - 1:
                    break
                if chunk_start + chunk_size <= file_size:
                    f.seek(chunk_start + chunk_size - 1)
                    if f.read(1) == '\n':
                        # Chunk ends with linefeed
                        chunk_end = chunk_start + chunk_size
                        position += chunk_size
                    else:
                        # Include the rest of line
                        length = len(f.readline())
                        chunk_end = chunk_start + chunk_size + length
                        position += chunk_size + length
                else:
                    position = chunk_end = file_size

                yield [ file_name, chunk_start, chunk_end ]

    # Run chunks in parallel and tally count

    count = 0

#   # Map possibly slower due to overhead preserving order
#   with Pool(num_processes) as p:
#       results = p.map(process_chunk, gen_offsets())
#       count = sum(results)

    # Try imap_unordered when ordered results unnecessary
    with Pool(num_processes) as p:
        results = list(p.imap_unordered(process_chunk, gen_offsets()))
        count = sum(results)

#   # Try also, concurrent.futures
#   with ProcessPoolExecutor(max_workers=num_processes) as executor:
#       futures = [executor.submit(process_chunk, params) \
#           for params in gen_offsets()]
#       for future in as_completed(futures):
#           count += future.result()

    return count

count = parallel_read(sys.argv[1])
print(f"Found {count} matches.")

        [download]

        Results

        Found 1999533 matches.

1: 2.628s
2: 1.342s
3: 0.914s
4: 0.703s
5: 0.571s
6: 0.482s
7: 0.423s
8: 0.375s
9: 0.339s

        [download]
[reply]
[d/l]
[select]

In Section Seekers of Perl Wisdom