Revision 9021
Added by ben leinfelder about 10 years ago
| metacat-index/src/main/java/edu/ucsb/nceas/metacat/index/annotation/RdfXmlSubprocessor.java | ||
|---|---|---|
| 43 | 43 |
import org.dataone.cn.indexer.annotation.SparqlField; |
| 44 | 44 |
import org.dataone.cn.indexer.annotation.TripleStoreService; |
| 45 | 45 |
import org.dataone.cn.indexer.convert.SolrDateConverter; |
| 46 |
import org.dataone.cn.indexer.parser.AbstractDocumentSubprocessor; |
|
| 47 | 46 |
import org.dataone.cn.indexer.parser.IDocumentSubprocessor; |
| 48 |
import org.dataone.cn.indexer.parser.ISolrField; |
|
| 47 |
import org.dataone.cn.indexer.parser.ISolrDataField;
|
|
| 49 | 48 |
import org.dataone.cn.indexer.solrhttp.SolrDoc; |
| 50 | 49 |
import org.dataone.cn.indexer.solrhttp.SolrElementField; |
| 51 | 50 |
import org.dataone.service.exceptions.NotFound; |
| ... | ... | |
| 78 | 77 |
* The solr doc of the RDF/XML object only has the system metadata information. |
| 79 | 78 |
* The solr docs of the science metadata doc and data file have the annotation information. |
| 80 | 79 |
*/ |
| 81 |
public class RdfXmlSubprocessor extends AbstractDocumentSubprocessor implements IDocumentSubprocessor {
|
|
| 80 |
public class RdfXmlSubprocessor implements IDocumentSubprocessor {
|
|
| 82 | 81 |
|
| 83 | 82 |
private static final String QUERY ="q=id:"; |
| 84 | 83 |
private static Log log = LogFactory.getLog(RdfXmlSubprocessor.class); |
| 84 |
|
|
| 85 |
/** |
|
| 86 |
* If xpath returns true execute the processDocument Method |
|
| 87 |
*/ |
|
| 88 |
private List<String> matchDocuments = null; |
|
| 89 |
private List<ISolrDataField> fieldList = new ArrayList<ISolrDataField>(); |
|
| 90 |
|
|
| 85 | 91 |
private static SolrServer solrServer = null; |
| 86 | 92 |
static {
|
| 87 | 93 |
try {
|
| ... | ... | |
| 90 | 96 |
log.error("RdfXmlSubprocessor - can't generate the SolrServer since - "+e.getMessage());
|
| 91 | 97 |
} |
| 92 | 98 |
} |
| 93 |
|
|
| 99 |
|
|
| 100 |
/** |
|
| 101 |
* Returns true if subprocessor should be run against object |
|
| 102 |
* |
|
| 103 |
* @param formatId the the document to be processed |
|
| 104 |
* @return true if this processor can parse the formatId |
|
| 105 |
*/ |
|
| 106 |
public boolean canProcess(String formatId) {
|
|
| 107 |
return matchDocuments.contains(formatId); |
|
| 108 |
} |
|
| 109 |
|
|
| 110 |
public List<String> getMatchDocuments() {
|
|
| 111 |
return matchDocuments; |
|
| 112 |
} |
|
| 113 |
|
|
| 114 |
public void setMatchDocuments(List<String> matchDocuments) {
|
|
| 115 |
this.matchDocuments = matchDocuments; |
|
| 116 |
} |
|
| 94 | 117 |
@Override |
| 95 | 118 |
public Map<String, SolrDoc> processDocument(String identifier, Map<String, SolrDoc> docs, InputStream is) throws Exception {
|
| 96 | 119 |
SolrDoc resourceMapDoc = docs.get(identifier); |
| ... | ... | |
| 130 | 153 |
|
| 131 | 154 |
// process each field query |
| 132 | 155 |
Map<String, SolrDoc> documentsToIndex = new HashMap<String, SolrDoc>(); |
| 133 |
for (ISolrField field: this.getFieldList()) {
|
|
| 156 |
for (ISolrDataField field: this.fieldList) {
|
|
| 134 | 157 |
String q = null; |
| 135 | 158 |
if (field instanceof SparqlField) {
|
| 136 | 159 |
q = ((SparqlField) field).getQuery(); |
Also available in: Unified diff
use ISolrDataField because RDF subprocessor uses the SparqlField subclass.