|
|
| (22 intermediate revisions by 2 users not shown) |
| Line 1: |
Line 1: |
| − | This page proves an overview of the API calls you can use to access the data in a DataObj. The example framing this is that of an export plugin.
| + | #REDIRECT [[Accessing Metadata Fields]] |
| − | | |
| − | == The Plugin ==
| |
| − | | |
| − | Below is a very simple export plugin, which outputs a single eprint or list of eprints as Text citations.
| |
| − | | |
| − | <pre>
| |
| − | package EPrints::Plugin::Export::Text;
| |
| − | | |
| − | use EPrints::Plugin::Export::TextFile;
| |
| − | | |
| − | @ISA = ( "EPrints::Plugin::Export::TextFile" );
| |
| − | | |
| − | use strict;
| |
| − | | |
| − | sub new
| |
| − | {
| |
| − | my( $class, %opts ) = @_;
| |
| − | | |
| − | my $self = $class->SUPER::new( %opts );
| |
| − | | |
| − | $self->{name} = "ASCII Citation";
| |
| − | $self->{accept} = [ 'dataobj/eprint', 'list/eprint' ];
| |
| − | $self->{visible} = "all";
| |
| − | | |
| − | return $self;
| |
| − | }
| |
| − | | |
| − | | |
| − | sub output_dataobj
| |
| − | {
| |
| − | my( $plugin, $dataobj ) = @_;
| |
| − | | |
| − | my $cite = $dataobj->render_citation;
| |
| − | | |
| − | return EPrints::Utils::tree_to_utf8( $cite )."\n\n";
| |
| − | }
| |
| − | | |
| − | 1;
| |
| − | </pre>
| |
| − | | |
| − | Note the output_dataobj function. In an export plugin, this will be called on every item in the list that is being exported, and the results for all items aggregated and outputted.
| |
| − | | |
| − | There are two function calls of particular interest that aid in retrieving and managing data:
| |
| − | | |
| − | <pre>
| |
| − | my $cite = $dataobj->render_citation;
| |
| − | </pre>
| |
| − | | |
| − | This returns an HTML DOM object containing the citation of the dataobj as specified in the configuration files (see cfg/citations/eprint/default.xml). Given an HTML DOM object, the following call will convert it into a string:
| |
| − | | |
| − | <pre>
| |
| − | my $text = EPrints::Utils::tree_to_utf8( $html_dom )
| |
| − | </pre>
| |
| − | | |
| − | == Accessing Metadata ==
| |
| − | | |
| − | A number of functions exist to aid in accessing and rendering values in a dataobj.
| |
| − | | |
| − | <pre>
| |
| − | my $title = $dataobj->value('title');
| |
| − | </pre>
| |
| − | | |
| − | $title will now be a scalar containing the value stored in the title field of the dataobj. A function is provided to enable testing first:
| |
| − | | |
| − | <pre>
| |
| − | if ($dataobj->is_set('title'))
| |
| − | {
| |
| − | $title = $dataobj->value('title');
| |
| − | }
| |
| − | </pre>
| |
| − | | |
| − | It is also possible to find out the fields that an item does have by querying the item's dataset:
| |
| − | | |
| − | <pre>
| |
| − | my $ds = $dataobj->dataset;
| |
| − | my @fields = $ds->fields;
| |
| − | my %fieldvalues
| |
| − | foreach my $field (@field)
| |
| − | {
| |
| − | my $fieldname = $field->name;
| |
| − | if ($dataobj->is_set($fieldname))
| |
| − | {
| |
| − | $fieldvalues{$fieldname} = $dataobj->value($fieldname);
| |
| − | }
| |
| − | }
| |
| − | </pre>
| |
| − | | |
| − | == The Structure of Values ==
| |
| − | | |
| − | On an eprint, the title is generally a simple metadata field. When $dataobj->value is called, it returns a scalar value.
| |
| − | | |
| − | EPrints has two types of metadata field:
| |
| − | | |
| − | * Simple
| |
| − | * Compound
| |
| − | | |
| − | Both types can either be a single or multiple values. An example of a compound multiple field is the creators field:
| |
| − | | |
| − | <pre>
| |
| − | my $creators = $dataobj->value('creators');
| |
| − | use Data::Dumper;
| |
| − | print Dumper $creators;
| |
| − | </pre>
| |
| − | | |
| − | Data::Dumper is a very useful library that will output the a perl datastructure. In the above case, the output may look something like this:
| |
| − | | |
| − | <pre>
| |
| − | $VAR1 = [
| |
| − | {
| |
| − | 'name' => {
| |
| − | 'lineage' => '',
| |
| − | 'given' => 'Noura',
| |
| − | 'honourific' => '',
| |
| − | 'family' => 'Abbas'
| |
| − | },
| |
| − | 'id' => '10363'
| |
| − | },
| |
| − | {
| |
| − | 'name' => {
| |
| − | 'lineage' => '',
| |
| − | 'given' => 'Andrew',
| |
| − | 'honourific' => '',
| |
| − | 'family' => 'Gravell'
| |
| − | },
| |
| − | 'id' => '22'
| |
| − | },
| |
| − | {
| |
| − | 'name' => {
| |
| − | 'lineage' => '',
| |
| − | 'given' => 'Gary',
| |
| − | 'honourific' => '',
| |
| − | 'family' => 'Wills'
| |
| − | },
| |
| − | 'id' => '395'
| |
| − | }
| |
| − | ];
| |
| − | </pre>
| |
| − | | |
| − | The above output shows an array of hashes. The structure can be compared to the configuration of the creators field (see cfg/cfg.d/eprint_fields.pl):
| |
| − | | |
| − | <pre>
| |
| − | {
| |
| − | 'name' => 'creators',
| |
| − | 'type' => 'compound',
| |
| − | 'multiple' => 1,
| |
| − | 'fields' => [
| |
| − | {
| |
| − | 'sub_name' => 'name',
| |
| − | 'type' => 'name',
| |
| − | 'hide_honourific' => 1,
| |
| − | 'hide_lineage' => 1,
| |
| − | 'family_first' => 1,
| |
| − | },
| |
| − | {
| |
| − | 'sub_name' => 'id',
| |
| − | 'type' => 'text',
| |
| − | 'input_cols' => 20,
| |
| − | 'allow_null' => 1,
| |
| − | }
| |
| − | ],
| |
| − | 'input_boxes' => 4,
| |
| − | },
| |
| − | </pre>
| |
| − | | |
| − | Each element in the array consists of a hash that has a key for each sub field of the creator field. Note the structure of the name part of the data dump. The name datatype is also a hash.
| |
| − | | |
| − | To summarise:
| |
| − | | |
| − | <dl>
| |
| − | <dt>Simple</dt><dd>Usually a scalar value (though some datatypes return a hashref</dd>
| |
| − | <dt>Compund</dt><dd>A hashref containing a simple value for each subfield</dd>
| |
| − | <dt>Multiple</dt><dd>An arrayref containing simple or compound metadata fields</dd>
| |
| − | </dl>
| |
