GeezerVison

"""Microbenchmark re.findall / split / sub / subn (result-list building)."""
import re
import pyperf

WORDS = "the quick brown fox jumps over the lazy dog " * 2000
CSVISH = "field1,field2,field3,field4,field5,field6,field7,field8\n" * 3000

word_re = re.compile(r"\w+")
group_re = re.compile(r"(\w)(\w+)")
split_re = re.compile(r"[,\n]")
sub_re = re.compile(r"\w+")


def b_findall():        return word_re.findall(WORDS)
def b_findall_groups(): return group_re.findall(WORDS)   # list of tuples
def b_sub():            return sub_re.sub("X", WORDS)
def b_subn():           return sub_re.subn("X", WORDS)


if __name__ == "__main__":
    runner = pyperf.Runner()
    runner.bench_func("re_findall", b_findall)
    runner.bench_func("re_findall_groups", b_findall_groups)
    runner.bench_func("re_sub", b_sub)
    runner.bench_func("re_subn", b_subn)