Lingua-TT
view release on metacpan or search on metacpan
TT/Document.pm view on Meta::CPAN
##-- contiguous mode
my $oi = 0;
my $osize = $doc->nTokens / ($n || 1);
my ($sent);
foreach $sent (@$doc) {
push(@{$odocs[$oi]}, $sent);
$osizes[$oi] += scalar(@$sent);
++$oi if ($osizes[$oi] >= $osize);
}
} else {
##-- best-split mode
my ($sent,$oi,$oi_min);
foreach $sent (@$doc) {
##-- find smallest @odoc
$oi_min = 0;
foreach $oi (1..$#odocs) {
$oi_min = $oi if ($osizes[$oi] < $osizes[$oi_min]);
}
push(@{$odocs[$oi_min]}, $sent);
$osizes[$oi_min] += scalar(@$sent);
}
( run in 1.605 second using v1.01-cache-2.11-cpan-71847e10f99 )