1*0Sstevel@tonic-gate# 2*0Sstevel@tonic-gate# $Id: jperl.t,v 1.25 2002/10/06 03:27:02 dankogai Exp $ 3*0Sstevel@tonic-gate# 4*0Sstevel@tonic-gate# This script is written in euc-jp 5*0Sstevel@tonic-gate 6*0Sstevel@tonic-gateBEGIN { 7*0Sstevel@tonic-gate require Config; import Config; 8*0Sstevel@tonic-gate if ($Config{'extensions'} !~ /\bEncode\b/) { 9*0Sstevel@tonic-gate print "1..0 # Skip: Encode was not built\n"; 10*0Sstevel@tonic-gate exit 0; 11*0Sstevel@tonic-gate } 12*0Sstevel@tonic-gate unless (find PerlIO::Layer 'perlio') { 13*0Sstevel@tonic-gate print "1..0 # Skip: PerlIO was not built\n"; 14*0Sstevel@tonic-gate exit 0; 15*0Sstevel@tonic-gate } 16*0Sstevel@tonic-gate if (ord("A") == 193) { 17*0Sstevel@tonic-gate print "1..0 # Skip: EBCDIC\n"; 18*0Sstevel@tonic-gate exit 0; 19*0Sstevel@tonic-gate } 20*0Sstevel@tonic-gate $| = 1; 21*0Sstevel@tonic-gate} 22*0Sstevel@tonic-gate 23*0Sstevel@tonic-gateno utf8; # we have raw Japanese encodings here 24*0Sstevel@tonic-gate 25*0Sstevel@tonic-gateuse strict; 26*0Sstevel@tonic-gate#use Test::More tests => 18; 27*0Sstevel@tonic-gateuse Test::More tests => 15; # black magic tests commented out 28*0Sstevel@tonic-gatemy $Debug = shift; 29*0Sstevel@tonic-gate 30*0Sstevel@tonic-gateno encoding; # ensure 31*0Sstevel@tonic-gatemy $Enamae = "\xbe\xae\xbb\xf4\x20\xc3\xc6"; # euc-jp, with \x escapes 32*0Sstevel@tonic-gateuse encoding "euc-jp"; 33*0Sstevel@tonic-gate 34*0Sstevel@tonic-gatemy $Namae = "���� ��"; # in Japanese, in euc-jp 35*0Sstevel@tonic-gatemy $Name = "Dan Kogai"; # in English 36*0Sstevel@tonic-gate# euc-jp in \x format but after the pragma. But this one will be converted! 37*0Sstevel@tonic-gatemy $Ynamae = "\xbe\xae\xbb\xf4\x20\xc3\xc6"; 38*0Sstevel@tonic-gate 39*0Sstevel@tonic-gate 40*0Sstevel@tonic-gatemy $str = $Namae; $str =~ s/���� ��/Dan Kogai/o; 41*0Sstevel@tonic-gateis($str, $Name, q{regex}); 42*0Sstevel@tonic-gate$str = $Namae; $str =~ s/$Namae/Dan Kogai/o; 43*0Sstevel@tonic-gateis($str, $Name, q{regex - with variable}); 44*0Sstevel@tonic-gateis(length($Namae), 4, q{utf8:length}); 45*0Sstevel@tonic-gate{ 46*0Sstevel@tonic-gate use bytes; 47*0Sstevel@tonic-gate # converted to UTF-8 so 3*3+1 48*0Sstevel@tonic-gate is(length($Namae), 10, q{bytes:length}); 49*0Sstevel@tonic-gate # 50*0Sstevel@tonic-gate is(length($Enamae), 7, q{euc:length}); # 2*3+1 51*0Sstevel@tonic-gate is ($Namae, $Ynamae, q{literal conversions}); 52*0Sstevel@tonic-gate isnt($Enamae, $Ynamae, q{before and after}); 53*0Sstevel@tonic-gate is($Enamae, Encode::encode('euc-jp', $Namae)); 54*0Sstevel@tonic-gate} 55*0Sstevel@tonic-gate# let's test the scope as well. Must be in utf8 realm 56*0Sstevel@tonic-gateis(length($Namae), 4, q{utf8:length}); 57*0Sstevel@tonic-gate 58*0Sstevel@tonic-gate{ 59*0Sstevel@tonic-gate no encoding; 60*0Sstevel@tonic-gate ok(! defined(${^ENCODING}), q{no encoding;}); 61*0Sstevel@tonic-gate} 62*0Sstevel@tonic-gate# should've been isnt() but no scoping is suported -- yet 63*0Sstevel@tonic-gateok(! defined(${^ENCODING}), q{not scoped yet}); 64*0Sstevel@tonic-gate 65*0Sstevel@tonic-gate# 66*0Sstevel@tonic-gate# The following tests are commented out to accomodate 67*0Sstevel@tonic-gate# Inaba-San's patch to make tr/// work w/o eval qq{} 68*0Sstevel@tonic-gate#{ 69*0Sstevel@tonic-gate# # now let's try some real black magic! 70*0Sstevel@tonic-gate# local(${^ENCODING}) = Encode::find_encoding("euc-jp"); 71*0Sstevel@tonic-gate# my $str = "\xbe\xae\xbb\xf4\x20\xc3\xc6"; 72*0Sstevel@tonic-gate# is (length($str), 4, q{black magic:length}); 73*0Sstevel@tonic-gate# is ($str, $Enamae, q{black magic:eq}); 74*0Sstevel@tonic-gate#} 75*0Sstevel@tonic-gate#ok(! defined(${^ENCODING}), q{out of black magic}); 76*0Sstevel@tonic-gateuse bytes; 77*0Sstevel@tonic-gateis (length($Namae), 10); 78*0Sstevel@tonic-gate 79*0Sstevel@tonic-gate# 80*0Sstevel@tonic-gate# now something completely different! 81*0Sstevel@tonic-gate# 82*0Sstevel@tonic-gate{ 83*0Sstevel@tonic-gate use encoding "euc-jp", Filter=>1; 84*0Sstevel@tonic-gate ok(1, "Filter on"); 85*0Sstevel@tonic-gate use utf8; 86*0Sstevel@tonic-gate no strict 'vars'; # fools 87*0Sstevel@tonic-gate # doesn't work w/ "my" as of this writing. 88*0Sstevel@tonic-gate # because of buggy strict.pm and utf8.pm 89*0Sstevel@tonic-gate our $�� = 2; 90*0Sstevel@tonic-gate # ^^U+4eba, "human" in CJK ideograph 91*0Sstevel@tonic-gate $��++; # a child is born 92*0Sstevel@tonic-gate *people = \$��; 93*0Sstevel@tonic-gate is ($people, 3, "Filter:utf8 identifier"); 94*0Sstevel@tonic-gate no encoding; 95*0Sstevel@tonic-gate ok(1, "Filter off"); 96*0Sstevel@tonic-gate} 97*0Sstevel@tonic-gate 98*0Sstevel@tonic-gate1; 99*0Sstevel@tonic-gate__END__ 100*0Sstevel@tonic-gate 101*0Sstevel@tonic-gate 102