private static String format(Writable key, DocumentWrapper documentWrapper) { StringBuilder sb = new StringBuilder(); sb.append("-------------------------------------------\n"); sb.append("key : ").append(key).append("\n"); sb.append("rowid : ").append(documentWrapper.getRowId()).append("\n"); sb.append("title0 : ").append(DocumentWrapperUtils.getMainTitle(documentWrapper.getDocumentMetadata())).append("\n"); sb.append("year : ").append(DocumentWrapperUtils.getPublicationYear(documentWrapper)).append("\n"); for (Author author : documentWrapper.getDocumentMetadata().getBasicMetadata().getAuthorList()) { sb.append(author.getPositionNumber()).append(". ").append(author.getName()).append(" ").append(author.getSurname()).append("\n"); } sb.append("\n"); return sb.toString(); }
, Bytes.toBytes(HBaseConstant.FAMILY_METADATA_DOCUMENT_QUALIFIER_PROTO)) != null) { DocumentMetadata dm = DocumentMetadata.parseFrom(scannerResult.value()); for(Author a : dm.getBasicMetadata().getAuthorList()){ names.add(a.getForenames() + " " + a.getSurname());
public Collection<SolrInputDocument> convert(DocumentWrapper dw) { Collection<SolrInputDocument> docs = new ArrayList<SolrInputDocument>(0); List<Author> contributions = dw.getDocumentMetadata() .getBasicMetadata().getAuthorList(); for (Author contribution : contributions) { SolrInputDocument doc = convertContribution(contribution); convertDocExtIds(dw, doc); convertDocYear(dw, doc); docs.add(doc); } return docs; }
for (Author a : dm.getBasicMetadata().getAuthorList()) { try { String sname = a.getSurname();
private static Pair<String[], Boolean> extractSurnames(DocumentProtos.DocumentMetadata doc) { RegexpParser authorParser = new RegexpParser("authorParser.properties", "author"); List<DocumentProtos.Author> authorList = doc.getBasicMetadata().getAuthorList(); String[] resultByPositionNb = new String[authorList.size()]; String[] resultByOrder = new String[authorList.size()]; for (DocumentProtos.Author author : doc.getBasicMetadata().getAuthorList()) { String surname; if (author.hasSurname()) {
List<Author> aths = dw.getDocumentMetadata().getBasicMetadata().getAuthorList();
private Tuple addDocumentMetatdataFields(DocumentMetadata metadata, Tuple output) throws ExecException { output.set(fieldNumberMap.get(C.KEY), metadata.getKey()); appendToOutput(output, C.TITLE, metadata.getBasicMetadata() .getTitleList()); appendToOutput(output, C.ABSTRACT_TEXT, metadata.getDocumentAbstractList()); List<String> al = new ArrayList<String>(); for (KeywordsList kl : metadata.getKeywordsList()) { for (String s : kl.getKeywordsList()) { al.add(removeAllPigUnfriendlySigns(s)); } } output.set(fieldNumberMap.get(C.KEYWORDS), listToDataBag(al)); List<String> authorKeys = new ArrayList<String>(); List<String> authorNames = new ArrayList<String>(); for (Author author : metadata.getBasicMetadata().getAuthorList()) { authorKeys.add(author.getKey()); authorNames.add(author.getName()); } output.set(fieldNumberMap.get(C.CONTRIBUTORS), listToDataBag(authorKeys, authorNames)); return output; }
private void convertPersonIds(DocumentWrapper dw, SolrInputDocument doc) { List<Author> authors = dw.getDocumentMetadata().getBasicMetadata() .getAuthorList(); for (Author author : authors) { List<KeyValue> extIds = author.getExtIdList(); for (KeyValue extId : extIds) { if (extId .getKey() .equals(CoansysModulesConstants.COANSYS_MODULE_ID_DISAMBIGUATION_AUTHOR)) { doc.addField(SolrIndexConstants.DOC_PERSONID_FIELD_NAME, extId.getValue()); } } } } }
/** * wrapper for documentWrapper.getDocumentMetadata().getBasicMetadata().getAuthorList(); Never returns null */ public static List<Author> getAuthors(DocumentWrapper documentWrapper) { List<Author> authors = documentWrapper.getDocumentMetadata().getBasicMetadata().getAuthorList(); if (authors==null) { authors = Lists.newArrayList(); } return authors; }
private void convertAuthors(DocumentWrapper dw, SolrInputDocument doc) { List<Author> authors = dw.getDocumentMetadata().getBasicMetadata() .getAuthorList(); for (Author author : authors) { doc.addField(SolrIndexConstants.DOC_AUTHOR_FIELD_NAME, author.getName()); } }