#!/usr/bin/perl -w
use strict;
use Benchmark;
my $string = "<<HTML>;nbsp dont_strip_me</HTML>> <xyzfdgfghgf> ;strip_
+me";
sub reversed {
my $reverse = reverse(shift);
$reverse =~ s| \w* ; \s* > |>|x;
return scalar reverse $reverse;
}
sub greedy {
my $line = shift;
$line =~ s|^ (.*>) \s* ; \w* |$1|x;
return $line;
}
print "Reversed: ", reversed($string), "\n";
print "Greedy: ", greedy($string), "\n";
timethese( -10,{
reversed => sub { reversed( $string ) },
greedy => sub { greedy( $string ) },
} );
Output:
Reversed: <<HTML>;nbsp dont_strip_me</HTML>> <xyzfdgfghgf>
Greedy: <<HTML>;nbsp dont_strip_me</HTML>> <xyzfdgfghgf>
Benchmark: running greedy, reversed, each for at least 10 CPU seconds...
greedy: 10 wallclock secs ( 9.98 usr + 0.02 sys = 10.00 CPU) @ 78480.80/s (n=784808)
reversed: 11 wallclock secs (10.46 usr + 0.00 sys = 10.46 CPU) @ 167660.04/s (n=1753724)
As you can see, it's over twice the speed. On longer strings, the difference would be even greater.
Also, your regex is wrong. Read through perldoc:perlre (specifically, the section marked 'Warning on \1 vs $1') to discover why.
|