1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
|
# -*- coding:utf-8; mode:CPerl -*-
use 5.8.0;
use strict; use warnings; use Test;
print q[# //Time-stamp: "2014-06-17 18:52:58 MDT sburke@cpan.org"], "\n";
BEGIN { plan tests => 20; }
use utf8;
use Text::Unidecode;
ok 1; print "# ^-- Hello\n";
print "# Text::Unidecode v$Text::Unidecode::VERSION\n",
"# Perl $^V\n",
"# I am test file " . __FILE__ . "\n",
"# Starting tests...\n";
ok binmode(*STDOUT, ":utf8"); print "# ^-- Testing binmode on STDOUT\n";
ok binmode(*STDERR, ":utf8"); print "# ^-- Testing binmode on STDERR\n";
# Be super-sure that our universe is sane
print "# Testing string literals...\n";
ok "ගඎ", "ගඎ", "Failure in comparing identity!?!?";
ok "ගඎ" => 'ගඎ', "quoting operator brokenness!?";
ok "ගඎ" => q[ගඎ], "quoting operator brokenness!?";
ok "ගඎ" => qq[ගඎ], "quoting operator brokenness!?";
ok "ගඎ" => "\x{0d9c}\x{0d8e}", "quoting operator brokenness!?";
# Syntactic sugar for our calls to "ok"...
my $from;
my $be = sub { return unidecode($from); };
print "# Latin-1...\n";
ok $be, "AEneid", ($from= "Æneid");
ok $be, "etude", ($from= "étude");
print "# Chinese...\n";
ok $be, "Bei Jing ", ($from="北亰");
print "# Canadian syllabics...\n";
ok $be, "shanana", ($from= "ᔕᓇᓇ");
print "# Cherokee...\n";
ok $be, "taliqua", ($from="ᏔᎵᏆ");
print "# Syriac...\n";
ok $be, "ptu'i", ($from= "ܦܛܽܐܺ");
print "# Devanagari...\n";
ok $be, "abhijiit", ($from= "अभिजीत");
print "# Bengali...\n";
ok $be, "abhijiit", ($from= "অভিজীত");
print "# Malayalaam...\n";
ok $be, "abhijiit", ($from= "അഭിജീത");
ok $be, "mlyaalm", ($from= "മലയാലമ്");
# the Malayaalam word for "Malayaalam"
# Yes, if we were doing it right, that'd be "malayaalam", not "mlyaalm"
print "# Japanese, astonishingly unmangled...\n";
ok $be, "genmaiCha ", ($from="げんまい茶"); #
print "# Bye:\n";
ok 1;
|
