#!/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"

[download]

In reply to Markov Chain Program by sacked

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!
  • Titles consisting of a single word are discouraged, and in most cases are disallowed outright.
  • 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, details, 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, summary, 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.