Last active
August 29, 2015 13:58
-
-
Save bldewolf/10227630 to your computer and use it in GitHub Desktop.
Script that mangles input by replacing words with "equivalents" found via dictd/moby-thesaurus
This file contains 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/perl | |
use strict; | |
use warnings; | |
use IO::Socket; | |
my %options; | |
my %words; | |
my $sock; | |
# preserve uc/ucfirst/lc-ness in replacement word | |
sub save_case { | |
my $orig = shift; | |
my $new = shift; | |
return $orig if $new eq $orig; | |
return ucfirst $new if $orig =~ /^[A-Z][a-z]*$/; | |
return uc $new if $orig =~ /^[A-Z]*$/; | |
return $new; | |
} | |
# RAAAAAAAAAAAAAAAANDO | |
sub rando { | |
my $word = shift; | |
my @opts = @{$options{lc $word}}; | |
if(@opts == 0) { | |
return $word; | |
} | |
return $opts[rand @opts]; | |
@opts = sort { length($a) <=> length($b) } @opts; | |
return $opts[0]; | |
} | |
sub lookup { | |
my $sock = IO::Socket::INET->new( | |
Proto => "tcp", | |
PeerAddr => "localhost", | |
PeerPort => "2628", | |
) or die "Failed to open socket"; | |
# dictd supports pipelining, so we shove all the words at it at once | |
my @order = keys %words; | |
for my $word (@order) { | |
$options{$word} = []; | |
print $sock "define moby-thesaurus $word\r\n"; | |
# print ">define moby-thesaurus $word\r\n"; | |
} | |
# then we loosely parse the results | |
while(my $word = shift @order) { | |
# print "=$word\n"; | |
while(<$sock>) { | |
# print "<$_"; | |
chomp; | |
last if(/^250 ok|^552 no/); | |
next if(!/^ /); | |
s/^\s*//; | |
s/\s*$//; | |
for my $opt (split /, ?/, lc $_) { | |
push(@{$options{$word}}, $opt); | |
} | |
} | |
} | |
close($sock) | |
or die "oh no sock"; | |
} | |
my @lines; | |
# collect lines and words to lookup | |
while(my $l = <>) { | |
push @lines, $l; | |
for my $word ($l =~ m/[[:alpha:]]+/g) { | |
$words{lc $word} = undef; | |
} | |
} | |
# populate %options | |
lookup(); | |
# do replacements | |
for my $l (@lines) { | |
$l =~ s/([[:alpha:]]+)/save_case($1, rando($1))/eg; | |
print $l; | |
} | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment