Parses the section from the XML returned from PubMed that contains information about an article.

Parameters

$xml: The XML to parse

$pub: The publication object to which additional details will be added

Related topics

File

tripal_pub/includes/importers/tripal_pub.PMID.inc, line 500

This file provides support for importing and parsing of results from the NCBI PubMed database. The functions here are used by both the publication importer setup form and the publication importer.

Code

function tripal_pub_PMID_parse_article($xml, &$pub) {

  while ($xml->read()) {
    // get this element name
    $element = $xml->name;

    // if we're at the </Article> element then we're done with the article...
    if ($xml->nodeType == XMLReader::END_ELEMENT and $element == 'Article') {
      return;
    }
    if ($xml->nodeType == XMLReader::ELEMENT) {
      switch ($element) {
        case 'Journal':
          tripal_pub_PMID_parse_journal($xml, $pub);
          break;
        case 'ArticleTitle':
          $xml->read();
          // remoave any trailing period from the title
          $pub['Title'] = trim(preg_replace('/\.$/', '', $xml->value));
          break;
        case 'Abstract':
          tripal_pub_PMID_parse_abstract($xml, $pub);
          break;
        case 'Pagination':
          tripal_pub_PMID_parse_pagination($xml, $pub);
          break;
        case 'ELocationID':
          $type = $xml->getAttribute('EIdType');
          $valid = $xml->getAttribute('ValidYN');
          $xml->read();
          $elocation = $xml->value;
          if ($type == 'doi' and $valid == 'Y') {
            $pub['DOI'] = $elocation;
          }
          if ($type == 'pii' and $valid == 'Y') {
            $pub['PII'] = $elocation;
          }
          $pub['Elocation'] = $elocation;
          break;
        case 'Affiliation':
          // the affiliation tag at this level is meant solely for the first author
          $xml->read();
          $pub['Author List'][0]['Affiliation'] = $xml->value;
          break;
        case 'AuthorList':
          $complete = $xml->getAttribute('CompleteYN');
          tripal_pub_PMID_parse_authorlist($xml, $pub);
          break;
        case 'InvestigatorList':
          // TODO: perhaps handle this one day.  The investigator list is to list the names of people who
          // are members of a collective or corporate group that is an author in the paper.
          break;
        case 'Language':
          $xml->read();
          $lang_abbr = $xml->value;
          // there may be multiple languages so we store these in an array
          $pub['Language'][] = tripal_pub_remote_search_get_language($lang_abbr);
          $pub['Language Abbr'][] = $lang_abbr;
          break;
        case 'DataBankList':
          // TODO: handle this case
          break;
        case 'GrantList':
          // TODO: handle this case
          break;
        case 'PublicationTypeList':
          tripal_pub_PMID_parse_publication_type($xml, $pub);
          break;
        case 'VernacularTitle':
          $xml->read();
          $pub['Vernacular Title'][] = $xml->value;
          break;
        case 'ArticleDate':
          // TODO: figure out what to do with this element. We already have the
          // published date in the <PubDate> field, but this date should be in numeric
          // form and may have more information.
          break;
        default:
          break;
      }
    }
  }
}