Revision 8805
Added by ben leinfelder over 10 years ago
| metacat-index/src/main/java/edu/ucsb/nceas/metacat/index/annotation/RdfXmlSubprocessor.java | ||
|---|---|---|
| 107 | 107 |
for (SolrDoc processedDoc : processedDocs) {
|
| 108 | 108 |
processedDocsMap.put(processedDoc.getIdentifier(), processedDoc); |
| 109 | 109 |
} |
| 110 |
return processedDocsMap; |
|
| 110 |
// make sure to merge any docs that are currently being processed |
|
| 111 |
Map<String, SolrDoc> mergedDocuments = mergeDocs(docs, processedDocsMap); |
|
| 112 |
return mergedDocuments; |
|
| 111 | 113 |
} |
| 112 | 114 |
|
| 113 | 115 |
private InputStream toInputStream(Document doc) throws TransformerConfigurationException, TransformerException, TransformerFactoryConfigurationError {
|
| ... | ... | |
| 213 | 215 |
return list; |
| 214 | 216 |
} |
| 215 | 217 |
|
| 216 |
private Map<String, SolrDoc> mergeDocs(Map<String, SolrDoc> pending, Map<String, SolrDoc> existing) {
|
|
| 218 |
private Map<String, SolrDoc> mergeDocs(Map<String, SolrDoc> pending, Map<String, SolrDoc> existing) throws Exception {
|
|
| 219 |
IndexSchema indexSchema = SolrQueryServiceController.getInstance().getSchema(); |
|
| 220 |
|
|
| 217 | 221 |
Map<String, SolrDoc> merged = new HashMap<String, SolrDoc>(); |
| 218 | 222 |
Iterator<String> pendingIter = pending.keySet().iterator(); |
| 219 | 223 |
while (pendingIter.hasNext()) {
|
| ... | ... | |
| 233 | 237 |
if (field.getName().equals(SolrElementField.FIELD_ID) && mergedDoc.hasField(SolrElementField.FIELD_ID)) {
|
| 234 | 238 |
continue; |
| 235 | 239 |
} |
| 236 |
mergedDoc.addField(field); |
|
| 237 |
|
|
| 240 |
// don't transfer the copyTo fields, otherwise there are errors |
|
| 241 |
if (indexSchema.isCopyFieldTarget(indexSchema.getField(field.getName()))) {
|
|
| 242 |
continue; |
|
| 243 |
} |
|
| 244 |
// only add if we don't already have it |
|
| 245 |
if (!mergedDoc.hasFieldWithValue(field.getName(), field.getValue())) {
|
|
| 246 |
mergedDoc.addField(field); |
|
| 247 |
} |
|
| 238 | 248 |
} |
| 239 | 249 |
|
| 240 | 250 |
// include in results |
Also available in: Unified diff
handle multiple subprocessors (RDF and ORE) before the object gets indexed by making sure to merge the solr doc map before submitting to the index.