Beefy Boxes and Bandwidth Generously Provided by pair Networks
Do you know where your variables are?
 
PerlMonks  

Comment on

( #3333=superdoc: print w/ replies, xml ) Need Help??

Ok. Here's a better version. While I haven't benchmarked it, my feeling are that it's a hog, but I bullet proofed several areas. It's less than a hog than my earlier post. I'm posting the new version for an easier compare.

#!/usr/bin/perl # string, min_len of pattern, min_num of patterns use strict; use warnings; my $string = "bookhelloworldhellohellohihellohiworldhihelloworldhihe +llobookpenbookpenworld"; get_pattern($string, 2, 2); exit; sub get_pattern { my ($string, $min_len, $min_num) = @_; my $str_len = length($string); my $srch_max = int($str_len/2); my %patterns; # First we find all patterns that are up to 1/2 the length of the stri +ng print "length : $str_len\n"; my %tmp_hash; foreach my $len ($min_len..$srch_max) { my $eol = $str_len - $len; foreach my $ind1 (0..$eol) { my $pat = substr($string, $ind1, $len); unless ( defined($tmp_hash{$pat}) ) { $tmp_hash{$pat} = 0; $tmp_hash{$pat}++ while ($string =~ /\Q$pat\E/g); $patterns{$pat} = $tmp_hash{$pat} if ($tmp_hash{$pat} >= $min_ +num); } } } undef %tmp_hash; print "Patterns: ", scalar (keys %patterns), "\n"; # We then go through the patterns by order and remove those # that are invalidated by better patterns # Longer strings that occur more often are considered better my $mod_str = $string; foreach my $key (sort { $patterns{$b} * (length($b)-1) <=> $patterns{$a} * (length($a)-1) or length($b) <=> length($a) } keys %patterns) { my $tstr = $mod_str; # We null out any area with pattern and count $patterns{$key} = ($tstr =~ s/\Q$key\E/\000/g); if ($patterns{$key} >= $min_num) { # If it hits threshold we keep $mod_str = $tstr; } else { # If not we toss pattern delete $patterns{$key}; } } print "Valid : ", scalar (keys %patterns), "\n"; # We finally print results foreach my $key (sort { $patterns{$b} * (length($b)-1) <=> $patterns{$a} * (length($a)-1) or length($b) <=> length($a) or $a cmp $b } keys %patterns) { (my $pat = $key) =~ s/\n/\\n/g; printf "%3d: (%s)\n", $patterns{$key}, $pat; } }

In reply to Re:^2 Pattern Finding by lemming
in thread Pattern Finding by artist

Title:
Use:  <p> text here (a paragraph) </p>
and:  <code> code here </code>
to format your post; it's "PerlMonks-approved HTML":



  • Posts are HTML formatted. Put <p> </p> tags around your paragraphs. Put <code> </code> tags around your code and data!
  • Read Where should I post X? if you're not absolutely sure you're posting in the right place.
  • Please read these before you post! —
  • Posts may use any of the Perl Monks Approved HTML tags:
    a, abbr, b, big, blockquote, br, caption, center, col, colgroup, dd, del, div, dl, dt, em, font, h1, h2, h3, h4, h5, h6, hr, i, ins, li, ol, p, pre, readmore, small, span, spoiler, strike, strong, sub, sup, table, tbody, td, tfoot, th, thead, tr, tt, u, ul, wbr
  • You may need to use entities for some characters, as follows. (Exception: Within code tags, you can put the characters literally.)
            For:     Use:
    & &amp;
    < &lt;
    > &gt;
    [ &#91;
    ] &#93;
  • Link using PerlMonks shortcuts! What shortcuts can I use for linking?
  • See Writeup Formatting Tips and other pages linked from there for more info.
  • Log In?
    Username:
    Password:

    What's my password?
    Create A New User
    Chatterbox?
    and the web crawler heard nothing...

    How do I use this? | Other CB clients
    Other Users?
    Others examining the Monastery: (5)
    As of 2015-07-08 01:28 GMT
    Sections?
    Information?
    Find Nodes?
    Leftovers?
      Voting Booth?

      The top three priorities of my open tasks are (in descending order of likelihood to be worked on) ...









      Results (93 votes), past polls