#!/usr/bin/perl -w
#
# based on kernighan and pike's markov chain program
# in _the practice of programming_, chapter 3
# (http://cm.bell-labs.com/cm/cs/tpop/markov.pl)
#
# Usage: markov.pl [prefix length] [max words to print] <infile
use strict;
my @words; # a line of text
my %wordlist; # key: prefix, value: array of suffixes
my $pref_len = shift @ARGV || 2;
my $maxwords = shift @ARGV || 10000;
# build word list
#
# 'Blessed is the man that walketh not in the counsel'
# %wordlist = ( 'blessed is' => [ 'the', ],
# 'is the' => [ 'man', ],
# 'the man' => [ 'that', ],
# );
while (<>) {
push @words, split;
while ( @words > $pref_len ) {
# build prefix of $pref_len words
# join(' ', @array) is faster than qq(@array) or "@array"
#
my $pref = join(' ', @words[0..($pref_len-1)]);
# add suffix to list
#
push @{ $wordlist{$pref} }, $words[$pref_len];
shift @words; # next word on this line
}
}
# starting point
#
my $pref = (keys %wordlist)[rand keys %wordlist];
print "$pref";
# dump out listings
#
for (0..($maxwords-1)) {
last if not defined($wordlist{$pref});
my $index = rand @{ $wordlist{$pref} };
my $suf = $wordlist{$pref}[$index];
print ' '. $suf;
print "\n" if ( $_ % 10 == 0);
# skip past first word in prefix
#
#$pref = (split(' ', $pref))[1..$pref_len-1] . ' ' . $suf;
$pref =~ s/^[^ ]+ (.+)$/$1 $suf/;
}
__END__
two good samples generated from the book of psalms:
"For, lo, thine enemies, and the horn of David the son of
thine house hath eaten me up"
"His mouth is full of troubles"
-
Are you posting in the right place? Check out Where do I post X? to know for sure.
-
Posts may use any of the Perl Monks Approved HTML tags. Currently these include the following:
<code> <a> <b> <big>
<blockquote> <br /> <dd>
<dl> <dt> <em> <font>
<h1> <h2> <h3> <h4>
<h5> <h6> <hr /> <i>
<li> <nbsp> <ol> <p>
<small> <strike> <strong>
<sub> <sup> <table>
<td> <th> <tr> <tt>
<u> <ul>
-
Snippets of code should be wrapped in
<code> tags not
<pre> tags. In fact, <pre>
tags should generally be avoided. If they must
be used, extreme care should be
taken to ensure that their contents do not
have long lines (<70 chars), in order to prevent
horizontal scrolling (and possible janitor
intervention).
-
Want more info? How to link
or How to display code and escape characters
are good places to start.
|