use strict; use locale; my $entrees; my %formes; my %cats; my %lemmes; while (my $ligne = ){ chomp($ligne); my ($forme, $lemme, $cat) = split(/\t/, $ligne); $entrees ++; $formes{$forme} = 1; $cats{$cat} = 1; $lemmes{$lemme . "\t" . substr($cat, 0, 1)} = 1; } print "entrées : ", $entrees, "\n"; my @cles_formes = keys %formes; print "formes : ", $#cles_formes + 1, "\n"; my @cles_lemmes = keys %lemmes; print "lemmes : ", $#cles_lemmes + 1, "\n"; my @cles_cats = keys %cats; print "catégories : ", $#cles_cats + 1, "\n"; print "ratio entrées/lemmes : ", sprintf ("%.2f", $entrees / ($#cles_lemmes + 1)), "\n";