t/Charset.t

   1 #!/usr/bin/perl
   2
   3 # This file is part of Koha.
   4 #
   5 # Koha is free software; you can redistribute it and/or modify it
   6 # under the terms of the GNU General Public License as published by
   7 # the Free Software Foundation; either version 3 of the License, or
   8 # (at your option) any later version.
   9 #
  10 # Koha is distributed in the hope that it will be useful, but
  11 # WITHOUT ANY WARRANTY; without even the implied warranty of
  12 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
  13 # GNU General Public License for more details.
  14 #
  15 # You should have received a copy of the GNU General Public License
  16 # along with Koha; if not, see <http://www.gnu.org/licenses>.
  17
  18 use Modern::Perl;
  19
  20 use Test::More tests => 16;
  21 use Encode qw( is_utf8 );
  22
  23 use MARC::Record;
  24
  25 use utf8;
  26 use open ':std', ':encoding(utf8)';
  27
  28 BEGIN {
  29     use_ok('C4::Charset');
  30 }
  31
  32 my $string;
  33 ok(!defined(NormalizeString($string,undef,1)),'Uninitialized string case 1 normalizes to uninitialized string.');
  34
  35 $string = 'Sample';
  36 ok(defined(NormalizeString($string,undef,0)), 'Initialized string case 1 normalizes to some string.');
  37 ok(defined(NormalizeString($string,undef,1)), 'Initialized string case 2 normalizes to some string.');
  38 ok(defined(NormalizeString($string,1,0)),     'Initialized string case 3 normalizes to some string.');
  39 ok(defined(NormalizeString($string,1,1)),     'Initialized string case 4 normalizes to some string.');
  40
  41 my $octets = "abc";
  42 ok(IsStringUTF8ish($octets), "verify octets are valid UTF-8 (ASCII)");
  43
  44 $octets = "flamb\xc3\xa9";
  45 ok(!Encode::is_utf8($octets), "verify that string does not have Perl UTF-8 flag on");
  46 ok(IsStringUTF8ish($octets), "verify octets are valid UTF-8 (LATIN SMALL LETTER E WITH ACUTE)");
  47 ok(!Encode::is_utf8($octets), "verify that IsStringUTF8ish does not magically turn Perl UTF-8 flag on");
  48
  49 $octets = "a\xc2" . "c";
  50 ok(!IsStringUTF8ish($octets), "verify octets are not valid UTF-8");
  51
  52 ok( !SetUTF8Flag(), 'SetUTF8Flag returns undef if no record passed' );
  53
  54 my $record = MARC::Record->new();
  55 ok( !SetUTF8Flag($record), 'SetUTF8Flag returns undef if the record has no subfields' );
  56 # Add some fields/subfields
  57 $record->append_fields(
  58     MARC::Field->new('100', ' ', ' ', a => 'Julio Cortazar'),
  59     MARC::Field->new('245', ' ', ' ', a => 'Rayuela'),
  60 );
  61 # Verify our data serves its purpose
  62 ok( !Encode::is_utf8($record->subfield('100','a')) &&
  63     !Encode::is_utf8($record->subfield('245','a')),
  64     'Verify that the subfields are NOT set the UTF-8 flag yet' );
  65
  66 SetUTF8Flag($record);
  67
  68 ok( Encode::is_utf8($record->subfield('100','a')) &&
  69     Encode::is_utf8($record->subfield('245','a')),
  70     'SetUTF8Flag sets the UTF-8 flag to all subfields' );
  71
  72 is( nsb_clean("Le Moyen Âge"), "Le Moyen Âge", "nsb_clean removes  and " );