Introducing --output parameter

Change-Id: Ibeb1bb625f9ef30ccb6207d8c4d20d4c0d0c9056

Changes

@@ -1,3 +1,6 @@
+2.6.0 2023-06-06
+        - Add -o parameter.
+
 2.5.0 2023-01-24
         - Upgrade minimal Perl version to 5.36 to improve
           unicode handling.

lib/KorAP/XML/TEI/Tokenizer/KorAP.pm

@@ -4,7 +4,7 @@ use strict;
 use warnings;
 use File::Share ':all';
 
-our $VERSION = '2.5.0';
+our $VERSION = '2.6.0';
 my $MIN_JAVA_VERSION = 17;
 
 use constant {

lib/KorAP/XML/TEI/Zipper.pm

@@ -33,7 +33,7 @@ sub new {
     $root_dir =~ s/^\.?\/+//;
   };
 
-  bless [$out // '-', undef, $root_dir // ''], $class;
+  bless [$out || '-', undef, $root_dir // ''], $class;
 };
 
 

lib/Test/KorAP/XML/TEI.pm

@@ -181,6 +181,41 @@ sub stderr_unlike {
   );
 };
 
+# Check for stdout equality
+sub stdout_is {
+  my ($self, $value, $desc) = @_;
+  return $self->_test(
+    'is',
+    $self->{stdout},
+    $value,
+    _desc($desc, 'exact match for stdout')
+  );
+};
+
+
+# Check for stdout similarity
+sub stdout_like {
+  my ($self, $value, $desc) = @_;
+  return $self->_test(
+    'like',
+    $self->{stdout},
+    $value,
+    _desc($desc, 'similar to stdout')
+  );
+};
+
+
+# Check for stdout non-similarity
+sub stdout_unlike {
+  my ($self, $value, $desc) = @_;
+  return $self->_test(
+    'unlike',
+    $self->{stdout},
+    $value,
+    _desc($desc, 'not similar to stdout')
+  );
+};
+
 
 # Check if a zip exists
 sub file_exists {

script/tei2korapxml

@@ -24,7 +24,7 @@ use KorAP::XML::TEI::Zipper;
 use KorAP::XML::TEI::Header;
 use KorAP::XML::TEI::Inline;
 
-our $VERSION = '2.5.0';
+our $VERSION = '2.6.0';
 
 our $VERSION_MSG = "\ntei2korapxml - v$VERSION\n";
 
@@ -44,6 +44,7 @@ my $inline_tokens_exclusive = 0;
 GetOptions(
   'root|r=s'              => \(my $root_dir    = '.'),
   'input|i=s'             => \(my $input_fname = ''),
+  'output|o=s'            => \(my $output_fname = ''),
   'tokenizer-call|tc=s'   => \(my $tokenizer_call),
   'tokenizer-korap|tk'    => \(my $tokenizer_korap),
   'tokenizer-internal|ti' => \(my $tokenizer_intern),
@@ -166,7 +167,7 @@ if (index($_tokens_dir, '!') == 0) {
 };
 
 # Initialize zipper
-my $zipper = KorAP::XML::TEI::Zipper->new($root_dir);
+my $zipper = KorAP::XML::TEI::Zipper->new($root_dir, $output_fname);
 
 # text directory (below $root_dir)
 my $dir = '';
@@ -563,6 +564,10 @@ Minimum requirement for L<KorAP::XML::TEI> is Perl 5.16.
 The input file to process. If no specific input is defined and a single
 dash C<-> is passed as an argument, data is read from C<STDIN>.
 
+=item B<--output|-o>
+
+The output zip file to be created. If no specific output is defined,
+data is written to C<STDOUT>.
 
 =item B<--root|-r>
 

t/script.t

@@ -829,4 +829,37 @@ subtest 'Handling of whitespace at linebreaks' => sub {
       ;
 };
 
+subtest 'Write to output' => sub {
+
+  my $temp_out = korap_tempfile('out');
+
+  my $t = test_tei2korapxml(
+    file => catfile($f, 'data', 'stadigmer.p5.xml'),
+    tmp => 'script_out',
+    param => '-s -ti -o "' . $temp_out . '"',
+    )->stderr_like(qr!tei2korapxml:.*? text_id=NO_000\.00000!)
+      ->stdout_is('');
+
+  my $content;
+  open(X, '<' . $temp_out);
+  binmode(X);
+  $content .= <X> while !eof(X);
+  close(X);
+  $t->{stdout} = $content;
+
+  $t->unzip_xml('NO/000/00000/data.xml')
+      ->content_like(qr/har lurt/)
+      ->content_like(qr/etter at/)
+      ->content_like(qr/en stund/)
+      ->content_like(qr/skjønner med/)
+      ->content_like(qr/og det/)
+      ->content_like(qr/stadig mer/)
+      ->content_like(qr/sitt, og/)
+      ->content_like(qr/tenkt å bli/)
+      ->content_like(qr/er både/)
+      ;
+
+  unlink $temp_out;
+};
+
 done_testing;