and a benchmark. The solution with the lookahead on each character does much better than I expected:qr %<p>([^<]*(?:<(?!b>|/p>)[^<]*)*)</p>%i;
#!/usr/bin/perl use strict; use warnings; use Benchmark qw /cmpthese/; our $abigail = qr %<p>([^<]*(?:<(?!b>|/p>)[^<]*)*)</p>%i; our $bart = qr %<P>((?:(?!<b>).)+?)</P>%is; our $corion = qr %<p>((?:[^<]*|<(?!b>)[^>]+>)*?)</p>%i; my @names = qw /abigail bart corion/; our @data = <DATA>; my @correct = ('Just another perl hacker', 'this should match', 'What about <a href="http://www.example.com">this</a>?' +, 'And <p>this'); cmpthese -1 => {map {$_ => "\@$_ = map {/\$$_/g} \@data"} @names}; no strict 'refs'; "@$_" eq "@correct" or die ucfirst for @names; __DATA__ <P>Just another perl hacker</P> <P>Just <b>another</b> perl hacker</P> <p>this should match</p> <p>This should <b>not</b> match</p> <p>What about <a href="http://www.example.com">this</a>?</p> <p>And <p>this</p> malformed piece?</p> Rate corion bart abigail corion 6457/s -- -68% -72% bart 19910/s 208% -- -14% abigail 23209/s 259% 17% --
Abigail
In reply to Re: Regular expression matching
by Abigail-II
in thread Regular expression matching
by murugu
| For: | Use: | ||
| & | & | ||
| < | < | ||
| > | > | ||
| [ | [ | ||
| ] | ] |