Created
March 14, 2015 13:54
-
-
Save qlkzy/23b35484812653268776 to your computer and use it in GitHub Desktop.
Hacky Markov Chains over ZNC logs
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| #!/usr/bin/env perl | |
| use strict; | |
| use warnings; | |
| use Getopt::Long; | |
| use List::Util qw/shuffle/; | |
| my $n = 2; | |
| my $count = 1; | |
| my $nickfile; | |
| GetOptions('n=i' => \$n, | |
| 'count|c=i' => \$count, | |
| 'nickfile|k=s' => \$nickfile); | |
| my @nickmap; | |
| if ($nickfile) { | |
| open (my $nh, '<', $nickfile) or die; | |
| my $curr; | |
| while (<$nh>) { | |
| chomp; | |
| next if /^\s*$/; | |
| if (m/^\S/) { | |
| s/\s+//g; | |
| $curr = $_; | |
| } else { | |
| s/\s+//g; | |
| push(@nickmap, [$_, $curr]); | |
| } | |
| } | |
| } | |
| my %ngrams; | |
| while (<>) { | |
| if (m/^[^<]*<([^>]+)>\s+(.*)$/) { | |
| my $name = fixnick($1); | |
| my $msg = $2; | |
| my @words = split /\s+/, $msg; | |
| for (0 .. $#words-$n) { | |
| push(@{$ngrams{$name}{lc(join(' ', @words[$_ .. ($_+$n-1)]))}}, $words[$_+$n]); | |
| } | |
| } | |
| } | |
| while (my $name = prompt()) { | |
| $name =~ s/\s//g; | |
| next unless exists $ngrams{$name}; | |
| for (1..$count) { | |
| my @words = split / /, (shuffle(keys %{$ngrams{$name}}))[0]; | |
| while ($#words < 16) { | |
| my $next = (shuffle(@{$ngrams{$name}{lc(join(' ', @words[$#words-$n+1 .. $#words]))}}))[0]; | |
| if (!(defined $next)) { | |
| last; | |
| } | |
| push @words, $next; | |
| } | |
| print "@words\n"; | |
| } | |
| } | |
| sub prompt { | |
| print "> "; | |
| return <STDIN>; | |
| } | |
| sub fixnick { | |
| local $_ = shift; | |
| s/_*$//; | |
| for my $pat (@nickmap) { | |
| s/.*@$pat[0].*/@$pat[1]/i; | |
| } | |
| return $_; | |
| } |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment