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 MARC::Record;
  22
  23 use utf8;
  24 use open ':std', ':encoding(utf8)';
  25
  26 BEGIN {
  27     use_ok('C4::Charset');
  28 }
  29
  30 my $string;
  31 ok(!defined(NormalizeString($string,undef,1)),'Uninitialized string case 1 normalizes to uninitialized string.');
  32
  33 $string = 'Sample';
  34 ok(defined(NormalizeString($string,undef,0)), 'Initialized string case 1 normalizes to some string.');
  35 ok(defined(NormalizeString($string,undef,1)), 'Initialized string case 2 normalizes to some string.');
  36 ok(defined(NormalizeString($string,1,0)),     'Initialized string case 3 normalizes to some string.');
  37 ok(defined(NormalizeString($string,1,1)),     'Initialized string case 4 normalizes to some string.');
  38
  39 my $octets = "abc";
  40 ok(IsStringUTF8ish($octets), "verify octets are valid UTF-8 (ASCII)");
  41
  42 $octets = "flamb\c3\a9";
  43 ok(!utf8::is_utf8($octets), "verify that string does not have Perl UTF-8 flag on");
  44 ok(IsStringUTF8ish($octets), "verify octets are valid UTF-8 (LATIN SMALL LETTER E WITH ACUTE)");
  45 ok(!utf8::is_utf8($octets), "verify that IsStringUTF8ish does not magically turn Perl UTF-8 flag on");
  46
  47 $octets = "a\xc2" . "c";
  48 ok(!IsStringUTF8ish($octets), "verify octets are not valid UTF-8");
  49
  50 ok( !SetUTF8Flag(), 'SetUTF8Flag returns undef if no record passed' );
  51
  52 my $record = MARC::Record->new();
  53 ok( !SetUTF8Flag($record), 'SetUTF8Flag returns undef if the record has no subfields' );
  54 # Add some fields/subfields
  55 $record->append_fields(
  56     MARC::Field->new('100', ' ', ' ', a => 'Julio Cortazar'),
  57     MARC::Field->new('245', ' ', ' ', a => 'Rayuela'),
  58 );
  59 # Verify our data serves its purpose
  60 ok( !utf8::is_utf8($record->subfield('100','a')) &&
  61     !utf8::is_utf8($record->subfield('245','a')),
  62     'Verify that the subfields are NOT set the UTF-8 flag yet' );
  63
  64 SetUTF8Flag($record);
  65
  66 ok( utf8::is_utf8($record->subfield('100','a')) &&
  67     utf8::is_utf8($record->subfield('245','a')),
  68     'SetUTF8Flag sets the UTF-8 flag to all subfields' );
  69
  70 is( nsb_clean("Le Moyen Âge"), "Le Moyen Âge", "nsb_clean removes  and " );
  71
  72 1;