Пример #1
0
  public void test() throws IOException {
    assertTrue(dir != null);
    assertTrue(fieldInfos != null);
    IndexReader reader = DirectoryReader.open(dir);
    Document doc = reader.document(0);
    assertTrue(doc != null);
    assertTrue(doc.getField(DocHelper.TEXT_FIELD_1_KEY) != null);

    Field field = (Field) doc.getField(DocHelper.TEXT_FIELD_2_KEY);
    assertTrue(field != null);
    assertTrue(field.fieldType().storeTermVectors());

    assertFalse(field.fieldType().omitNorms());
    assertTrue(field.fieldType().indexOptions() == IndexOptions.DOCS_AND_FREQS_AND_POSITIONS);

    field = (Field) doc.getField(DocHelper.TEXT_FIELD_3_KEY);
    assertTrue(field != null);
    assertFalse(field.fieldType().storeTermVectors());
    assertTrue(field.fieldType().omitNorms());
    assertTrue(field.fieldType().indexOptions() == IndexOptions.DOCS_AND_FREQS_AND_POSITIONS);

    field = (Field) doc.getField(DocHelper.NO_TF_KEY);
    assertTrue(field != null);
    assertFalse(field.fieldType().storeTermVectors());
    assertFalse(field.fieldType().omitNorms());
    assertTrue(field.fieldType().indexOptions() == IndexOptions.DOCS);

    DocumentStoredFieldVisitor visitor = new DocumentStoredFieldVisitor(DocHelper.TEXT_FIELD_3_KEY);
    reader.document(0, visitor);
    final List<IndexableField> fields = visitor.getDocument().getFields();
    assertEquals(1, fields.size());
    assertEquals(DocHelper.TEXT_FIELD_3_KEY, fields.get(0).name());
    reader.close();
  }
  private List<Document> lookupDocs(Term term, final LoadFieldCallback lfc) throws IOException {
    final List<Document> documents = new ArrayList<Document>();
    final TermFilter tf = new TermFilter(term);
    try {
      for (AtomicReaderContext arc : searcher.getIndexReader().leaves()) {
        AtomicReader ar = arc.reader();
        Bits liveDocs = ar.getLiveDocs();
        DocIdSet docSet = tf.getDocIdSet(arc, liveDocs);
        if (docSet != null) {
          DocIdSetIterator disi = docSet.iterator();
          if (disi != null) {
            int docId;
            while ((docId = disi.nextDoc()) != DocIdSetIterator.NO_MORE_DOCS) {
              DocumentStoredFieldVisitor fv =
                  new DocumentStoredFieldVisitor() {
                    @Override
                    public StoredFieldVisitor.Status needsField(FieldInfo fieldInfo)
                        throws IOException {
                      if (lfc == null || lfc.loadField(fieldInfo.name)) {
                        return StoredFieldVisitor.Status.YES;
                      }
                      return StoredFieldVisitor.Status.NO;
                    }
                  };
              ar.document(docId, fv);
              documents.add(fv.getDocument());
            }
          }
        }
      }
    } catch (IOException io) {
      throw new IndexException(io);
    }

    return documents;
  }
 private StoredDocument retrieveDocument(final SchemaField uniqueField, int doc)
     throws IOException {
   DocumentStoredFieldVisitor visitor = new DocumentStoredFieldVisitor(uniqueField.getName());
   rb.req.getSearcher().doc(doc, visitor);
   return visitor.getDocument();
 }
Пример #4
0
  public static List<Element> handlePropertyName(
      String[] propertyNames,
      ServiceContext context,
      boolean freq,
      int maxRecords,
      String cswServiceSpecificConstraint,
      LuceneConfig luceneConfig)
      throws Exception {

    List<Element> domainValuesList = null;

    if (Log.isDebugEnabled(Geonet.CSW))
      Log.debug(
          Geonet.CSW,
          "Handling property names '"
              + Arrays.toString(propertyNames)
              + "' with max records of "
              + maxRecords);

    for (int i = 0; i < propertyNames.length; i++) {

      if (i == 0) domainValuesList = new ArrayList<Element>();

      // Initialize list of values element.
      Element listOfValues = null;

      // Generate DomainValues element
      Element domainValues = new Element("DomainValues", Csw.NAMESPACE_CSW);

      // FIXME what should be the type ???
      domainValues.setAttribute("type", "csw:Record");

      String property = propertyNames[i].trim();

      // Set propertyName in any case.
      Element pn = new Element("PropertyName", Csw.NAMESPACE_CSW);
      domainValues.addContent(pn.setText(property));

      GeonetContext gc = (GeonetContext) context.getHandlerContext(Geonet.CONTEXT_NAME);
      SearchManager sm = gc.getSearchmanager();

      IndexAndTaxonomy indexAndTaxonomy = sm.getNewIndexReader(null);
      try {
        GeonetworkMultiReader reader = indexAndTaxonomy.indexReader;
        BooleanQuery groupsQuery = (BooleanQuery) CatalogSearcher.getGroupsQuery(context);
        BooleanQuery query = null;

        // Apply CSW service specific constraint
        if (StringUtils.isNotEmpty(cswServiceSpecificConstraint)) {
          Query constraintQuery =
              CatalogSearcher.getCswServiceSpecificConstraintQuery(
                  cswServiceSpecificConstraint, luceneConfig);

          query = new BooleanQuery();

          BooleanClause.Occur occur = LuceneUtils.convertRequiredAndProhibitedToOccur(true, false);

          query.add(groupsQuery, occur);
          query.add(constraintQuery, occur);

        } else {
          query = groupsQuery;
        }

        List<Pair<String, Boolean>> sortFields =
            Collections.singletonList(Pair.read(Geonet.SearchResult.SortBy.RELEVANCE, true));
        Sort sort = LuceneSearcher.makeSort(sortFields, context.getLanguage(), false);
        CachingWrapperFilter filter = null;

        Pair<TopDocs, Element> searchResults =
            LuceneSearcher.doSearchAndMakeSummary(
                maxRecords,
                0,
                maxRecords,
                context.getLanguage(),
                null,
                reader,
                query,
                filter,
                sort,
                null,
                false,
                false,
                false,
                false // Scoring is useless for GetDomain operation
                );
        TopDocs hits = searchResults.one();

        try {
          // Get mapped lucene field in CSW configuration
          String indexField = CatalogConfiguration.getFieldMapping().get(property.toLowerCase());
          if (indexField != null) property = indexField;

          // check if params asked is in the index using getFieldNames ?
          FieldInfos fi = new SlowCompositeReaderWrapper(reader).getFieldInfos();
          if (fi.fieldInfo(property) == null) continue;

          boolean isRange = false;
          if (CatalogConfiguration.getGetRecordsRangeFields().contains(property)) isRange = true;

          if (isRange) listOfValues = new Element("RangeOfValues", Csw.NAMESPACE_CSW);
          else listOfValues = new Element("ListOfValues", Csw.NAMESPACE_CSW);

          Set<String> fields = new HashSet<String>();
          fields.add(property);
          fields.add("_isTemplate");

          // parse each document in the index
          String[] fieldValues;
          SortedSet<String> sortedValues = new TreeSet<String>();
          HashMap<String, Integer> duplicateValues = new HashMap<String, Integer>();
          for (int j = 0; j < hits.scoreDocs.length; j++) {
            DocumentStoredFieldVisitor selector = new DocumentStoredFieldVisitor(fields);
            reader.document(hits.scoreDocs[j].doc, selector);
            Document doc = selector.getDocument();

            // Skip templates and subTemplates
            String[] isTemplate = doc.getValues("_isTemplate");
            if (isTemplate[0] != null && !isTemplate[0].equals("n")) continue;

            // Get doc values for specified property
            fieldValues = doc.getValues(property);
            if (fieldValues == null) continue;

            addtoSortedSet(sortedValues, fieldValues, duplicateValues);
          }

          SummaryComparator valuesComparator =
              new SummaryComparator(SortOption.FREQUENCY, Type.STRING, context.getLanguage(), null);
          TreeSet<Map.Entry<String, Integer>> sortedValuesFrequency =
              new TreeSet<Map.Entry<String, Integer>>(valuesComparator);
          sortedValuesFrequency.addAll(duplicateValues.entrySet());

          if (freq) return createValuesByFrequency(sortedValuesFrequency);
          else listOfValues.addContent(createValuesElement(sortedValues, isRange));

        } finally {
          // any children means that the catalog was unable to determine
          // anything about the specified parameter
          if (listOfValues != null && listOfValues.getChildren().size() != 0)
            domainValues.addContent(listOfValues);

          // Add current DomainValues to the list
          domainValuesList.add(domainValues);
        }
      } finally {
        sm.releaseIndexReader(indexAndTaxonomy);
      }
    }
    return domainValuesList;
  }
Пример #5
0
 /**
  * Like {@link #document(int)} but only loads the specified fields. Note that this is simply sugar
  * for {@link DocumentStoredFieldVisitor#DocumentStoredFieldVisitor(Set)}.
  */
 public final Document document(int docID, Set<String> fieldsToLoad) throws IOException {
   final DocumentStoredFieldVisitor visitor = new DocumentStoredFieldVisitor(fieldsToLoad);
   document(docID, visitor);
   return visitor.getDocument();
 }
Пример #6
0
 // TODO: we need a separate StoredField, so that the
 // Document returned here contains that class not
 // IndexableField
 public final Document document(int docID) throws IOException {
   final DocumentStoredFieldVisitor visitor = new DocumentStoredFieldVisitor();
   document(docID, visitor);
   return visitor.getDocument();
 }