I figured this code would be executed repeatedly, so performance would matter.
For strings with very few surrounding spaces,
length=300
Rate merlyn ikegami
merlyn 8132/s -- -80%
ikegami 41078/s 405% --
length=500
Rate merlyn ikegami
merlyn 1660/s -- -91%
ikegami 18224/s 998% --
length=1000
Rate merlyn ikegami
merlyn 488/s -- -92%
ikegami 6095/s 1149% --
I wrote a more comprehensive benchmark, but I'm getting inconsistent results at the moment. I'll run on it a more stable machine tomorrow.
use strict;
use warnings;
use Benchmark qw( cmpthese );
my %tests = (
ikegami11 => 's/^(.{256,}?)\s+\z/$1/s, s/^\s*(.{256}).*\z/$1/s
+ if length > 256;',
ikegami21 => 's/(?<=.{6})\s+\z//s, s/^\s*(.{256}).*\z/$1/s
+ if length > 256;',
ikegami31 => 's/.{6}\K\s+\z//s, s/^\s*(.{256}).*\z/$1/s
+ if length > 256;',
ikegami12 => 's/^(.{256,}?)\s+\z/$1/s, s/^\s+(?=.{6})//s, s/(?<=^.{
+6}).*\z//s if length > 256;',
ikegami22 => 's/(?<=.{6})\s+\z//s, s/^\s+(?=.{6})//s, s/(?<=^.{
+6}).*\z//s if length > 256;',
ikegami32 => 's/.{6}\K\s+\z//s, s/^\s+(?=.{6})//s, s/(?<=^.{
+6}).*\z//s if length > 256;',
ikegami13 => 's/^(.{256,}?)\s+\z/$1/s, s/^\s+(?=.{6})//s, s/(?<=.{6
+}).*\z//s if length > 256;',
ikegami23 => 's/(?<=.{6})\s+\z//s, s/^\s+(?=.{6})//s, s/(?<=.{6
+}).*\z//s if length > 256;',
ikegami33 => 's/.{6}\K\s+\z//s, s/^\s+(?=.{6})//s, s/(?<=.{6
+}).*\z//s if length > 256;',
ikegami14 => 's/^(.{256,}?)\s+\z/$1/s, s/^\s+(?=.{6})//s, s/^.{6}\K
+.*\z//s if length > 256;',
ikegami24 => 's/(?<=.{6})\s+\z//s, s/^\s+(?=.{6})//s, s/^.{6}\K
+.*\z//s if length > 256;',
ikegami34 => 's/.{6}\K\s+\z//s, s/^\s+(?=.{6})//s, s/^.{6}\K
+.*\z//s if length > 256;',
merlyn => 's/\s$// || s/^\s// || s/.$// while length > 256;',
);
$_ = 'use strict; use warnings; local $_ = our $pat;' . $_
for values(%tests);
for my $len (256, 260, 300, 500) {
for our $pat (
' ' x $len,
(' ' x ($len/2)) . ('x' x ($len/2)),
'x' x $len,
) {
printf("length=%u, pat=\"%s...%s\"\n", $len, substr($pat, 0, 5),
+ substr($pat, -5));
cmpthese(-1, \%tests);
print("\n");
}
}
|