gh-150942: Speed up re.split result building - #155940

"""Microbenchmark re.split (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
CSVISH_BYTES = CSVISH.encode()

split_re = re.compile(r"[,\n]")
group_re = re.compile(r"([,\n])")
ws_re = re.compile(r"\s+")
bytes_re = re.compile(rb"[,\n]")
nomatch_re = re.compile(r"[;|]")


def b_split():         return split_re.split(CSVISH)
def b_split_groups():  return group_re.split(CSVISH)
def b_split_ws():      return ws_re.split(WORDS)
def b_split_bytes():   return bytes_re.split(CSVISH_BYTES)
def b_split_nomatch(): return nomatch_re.split(CSVISH)
def b_str_split():     return CSVISH.split(",")


if __name__ == "__main__":
    runner = pyperf.Runner()
    runner.bench_func("re_split", b_split)
    runner.bench_func("re_split_groups", b_split_groups)
    runner.bench_func("re_split_ws", b_split_ws)
    runner.bench_func("re_split_bytes", b_split_bytes)
    runner.bench_func("re_split_nomatch", b_split_nomatch)
    runner.bench_func("str_split_control", b_str_split)