Bug 17302: Add Koha::Util::Normalize for normalization functions

This patch introduces Koha::Util::Normalize, which includes the following normalization routines
that need no explanation:

- remove_spaces
- upper_case
- lower_case

and it also includes:

- legacy_default: which basically does what C4::Matcher::_normalize does.

All routines functionality are fully tested with the included in the included tests.

To test:
- Apply the patch
- Run:
  $ prove t/Koha/Util/Normalize.t
=> SUCCESS: All tests pass
- Sign off :-D

Edit: Added Exporter to explicitly export the routines.

Signed-off-by: Marcel de Rooy <m.de.rooy@rijksmuseum.nl>

Signed-off-by: Katrin Fischer  <katrin.fischer@bsz-bw.de>

Signed-off-by: Kyle M Hall <kyle@bywatersolutions.com>

Koha/Util/Normalize.pm

@@ -0,0 +1,105 @@
+package Koha::Util::Normalize;
+
+# Copyright 2016 Koha Development Team
+#
+# This file is part of Koha.
+#
+# Koha is free software; you can redistribute it and/or modify it under the
+# terms of the GNU General Public License as published by the Free Software
+# Foundation; either version 3 of the License, or (at your option) any later
+# version.
+#
+# Koha is distributed in the hope that it will be useful, but WITHOUT ANY
+# WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR
+# A PARTICULAR PURPOSE.  See the GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License along
+# with Koha; if not, write to the Free Software Foundation, Inc.,
+# 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
+
+use Modern::Perl;
+
+use parent qw( Exporter );
+
+our @EXPORT = qw(
+  legacy_default
+  remove_spaces
+  upper_case
+  lower_case
+);
+
+=head1 NAME
+
+Koha::Util::Normalize - utility class with string normalization routines
+
+=head1 METHODS
+
+=head2 legacy_default
+
+Default normalization function
+
+=cut
+
+sub legacy_default {
+
+    my $string = uc shift;
+
+    $string =~ s/[.;:,\]\[\)\(\/'"]//g;
+    $string =~ s/^\s+//;
+    $string =~ s/\s+$//;
+    $string =~ s/\s+/ /g;
+
+    return $string;
+}
+
+=head2 remove_spaces
+
+Normalization function removing spaces
+
+=cut
+
+sub remove_spaces {
+
+    my $string = shift;
+
+    $string =~ s/\s+//g;
+
+    return $string;
+}
+
+=head2 upper_case
+
+Normalization function converting characters into upper-case
+
+=cut
+
+sub upper_case {
+
+    my $string = uc shift;
+
+    return $string;
+}
+
+=head2 lower_case
+
+Normalization function converting characters into lower-case
+
+=cut
+
+sub lower_case {
+
+    my $string = lc shift;
+
+    return $string;
+}
+
+1;
+__END__
+
+=head1 AUTHOR
+
+Koha Development Team <http://koha-community.org/>
+
+Tomas Cohen Arazi <tomascohen@theke.io>
+
+=cut

t/Koha/Util/Normalize.t

@@ -0,0 +1,67 @@
+#!/usr/bin/perl
+
+# This file is part of Koha.
+#
+# Koha is free software; you can redistribute it and/or modify it
+# under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 3 of the License, or
+# (at your option) any later version.
+#
+# Koha is distributed in the hope that it will be useful, but
+# WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with Koha; if not, see <http://www.gnu.org/licenses>.
+
+use Modern::Perl;
+
+use Test::More tests => 5;
+
+BEGIN {
+    use_ok('Koha::Util::Normalize');
+}
+
+subtest 'legacy_default() normalizer' => sub {
+
+    plan tests => 1;
+
+    my $string = '  .; kY[]:,  (l)/E\'"';
+
+    is( Koha::Util::Normalize::legacy_default( $string ), 'KY LE',
+        'The \'legacy_default\' normalizer removes: .;:,][)(/\'" and shifts characters upper-case.
+         Also removes spaces from the beginning and ending, and replaces multiple spaces with a single one.' );
+};
+
+subtest 'remove_spaces() normalizer' => sub {
+
+    plan tests => 1;
+
+    my $string = '  .; kY[]:,  (l)/E\'"';
+
+    is( Koha::Util::Normalize::remove_spaces( $string ), '.;kY[]:,(l)/E\'"',
+        'The \'remove_spaces\' normalizer removes all spaces' );
+};
+
+subtest 'upper_case() normalizer' => sub {
+
+    plan tests => 1;
+
+    my $string = '  .; kY[]:,  (l)/E\'"';
+
+    is( Koha::Util::Normalize::upper_case( $string ), '  .; KY[]:,  (L)/E\'"',
+        'The \'upper_case\' normalizer only makes characters upper-case' );
+};
+
+subtest 'lower_case() normalizer' => sub {
+
+    plan tests => 1;
+
+    my $string = '  .; kY[]:,  (l)/E\'"';
+
+    is( Koha::Util::Normalize::lower_case( $string ), '  .; ky[]:,  (l)/e\'"',
+        'The \'lower_case\' normalizer only makes characters lower-case' );
+};
+
+1;