#!/bin/perl -w use strict; use Benchmark( 'cmpthese'); use Encode; use Text::Iconv; use Unicode::Map8; use Unicode::String qw(utf8); use utf8; my $enc= 'latin1'; my $convert_iconv = Text::Iconv->new( 'utf8', $enc); my $convert_unicode = Unicode::Map8->new ($enc); my $text= ; chomp $text; # lets just check the output! print "Encode : ", encode("iso-8859-1", $text), "\n"; print "Text::Iconv : ", $convert_iconv->convert( $text), "\n"; print "Unicode::Map8 : ", $convert_unicode->to8 (utf8($text)->ucs2), "\n"; print "regexp : ", latin1( $text), "\n"; # now benchmark cmpthese( 500000, { 'Encode' => sub { encode("iso-8859-1", $text); }, 'Text::Iconv' => sub { $convert_iconv->convert( $text); }, 'Unicode::Map8' => sub { $convert_unicode->to8 (utf8($text)->ucs2); }, 'regexp' => sub { latin1( $text); }, }); sub latin1 { my $text=shift; $text=~s{([\xc0-\xc3])(.)}{ my $hi = ord($1); my $lo = ord($2); chr((($hi & 0x03) <<6) | ($lo & 0x3F)) }ge; return $text; } __DATA__ texte soupçonné d'être plein de caractÚres accentués #### Encode : texte soupçonné d'être plein de caractères accentués Text::Iconv : texte soupçonné d'être plein de caractères accentués Unicode::Map8 : texte soupçonné d'être plein de caractères accentués regexp : texte soupçonné d'être plein de caractères accentués Benchmark: timing 500000 iterations of Encode, Text::Iconv, Unicode::Map8, regexp... Encode: 6 wallclock secs ( 4.91 usr + 0.02 sys = 4.93 CPU) @ 101419.88/s (n=500000) Text::Iconv: 2 wallclock secs ( 2.20 usr + 0.00 sys = 2.20 CPU) @ 227272.73/s (n=500000) Unicode::Map8: 7 wallclock secs ( 7.66 usr + 0.00 sys = 7.66 CPU) @ 65274.15/s (n=500000) regexp: 6 wallclock secs ( 5.65 usr + 0.01 sys = 5.66 CPU) @ 88339.22/s (n=500000) Rate Unicode::Map8 regexp Encode Text::Iconv Unicode::Map8 65274/s -- -26% -36% -71% regexp 88339/s 35% -- -13% -61% Encode 101420/s 55% 15% -- -55% Text::Iconv 227273/s 248% 157% 124% --