Changeset 37047 for main/trunk/greenstone2/perllib/plugins/CSVPlugin.pm

Timestamp:

2022-12-23T10:24:09+13:00 (17 months ago)

Author:

davidb

Message:

Introduction of 'metadata_separate_fields', a plugin option that controls which fields get the value separation split applied to. By default all fields get split when the value split character is specified, however you can get situations where you want to split on (say) ',' for a Keyword field but not in a Abstract field that happens to use commas

File:

• main/trunk/greenstone2/perllib/plugins/CSVPlugin.pm (modified) (2 diffs)

main/trunk/greenstone2/perllib/plugins/CSVPlugin.pm

@@ -193 +193 @@
     }
 
+    my $md_sep_fields = $self->{'metadata_separate_fields'};
+    undef $md_sep_fields if ($md_sep_fields eq "");
+
+    my $md_sep_fields_lookup = undef;
+    if (defined $md_sep_fields) {
+    $md_sep_fields_lookup = {};
+
+    my @md_fields = split(/\s*,\s*/,$md_sep_fields);
+
+    for my $md_field (@md_fields) {
+        $md_sep_fields_lookup->{$md_field} = 1;
+    }
+    }
+
     my $csv = Text::CSV->new();
     $csv->sep_char($separate_char);
@@ -247 +261 @@
         my $md_name = $csv_file_fields[$i];
         $csv_line_metadata{$md_name} = [];
-        if (defined $md_val_sep) {          
+
+        my $needs_md_val_sep = 0;
+        if (defined $md_val_sep) {
+            # Default coming in is 'no' (0)
+            # => Check to see if any conditions met to turn this into a 'yes' (1)
             
+            # check to see if md_sep_fields is in play, and if it is
+            # => determine if this $md_name is one of the ones in $md_sep_fields_lookup
+            
+            if (defined $md_sep_fields_lookup) {
+            if ($md_sep_fields_lookup->{$md_name}) {
+                $needs_md_val_sep = 1;
+            }
+            }
+            else {
+            # if not set, then we apply the md_val_sep to all metadata fields
+            $needs_md_val_sep = 1;
+            }
+        }
+        
+        if ($needs_md_val_sep) {            
+            
             my @within_md_vals = split(/${md_val_sep}/,$md_val);