/**
* Describe the vocabularies which are in use in the KB based on the predicate partition
* statistics.
*
* @param predicateParitionCounts The predicate partition statistics.
*/
protected void describeVocabularies(final IVCount[] predicatePartitionCounts) {
// Find the distinct vocabularies in use.
final Set<String> namespaces = new LinkedHashSet<String>();
{
// property partitions.
for (IVCount tmp : predicatePartitionCounts) {
final URI p = (URI) tmp.getValue();
String namespace = p.getNamespace();
if (namespace.endsWith("#")) {
// Strip trailing '#' per VoID specification.
namespace = namespace.substring(0, namespace.length() - 1);
}
namespaces.add(namespace);
}
}
// Sort into dictionary order.
final String[] a = namespaces.toArray(new String[namespaces.size()]);
Arrays.sort(a);
for (String namespace : a) {
g.add(aDataset, VoidVocabularyDecl.vocabulary, f.createURI(namespace));
}
}
/**
* Describe a named or default graph.
*
* @param graph The named graph.
* @param predicatePartitionCounts The predicate partition statistics for that graph.
* @param classPartitionCounts The class partition statistics for that graph.
*/
protected void describeGraph(
final Resource graph,
final IVCount[] predicatePartitionCounts,
final IVCount[] classPartitionCounts) {
// The graph is a Graph.
g.add(graph, RDF.TYPE, SD.Graph);
// #of triples in the default graph
g.add(graph, VoidVocabularyDecl.triples, f.createLiteral(tripleStore.getStatementCount()));
// #of entities in the default graph.
g.add(graph, VoidVocabularyDecl.entities, f.createLiteral(tripleStore.getURICount()));
// #of distinct predicates in the default graph.
g.add(graph, VoidVocabularyDecl.properties, f.createLiteral(predicatePartitionCounts.length));
// #of distinct classes in the default graph.
g.add(graph, VoidVocabularyDecl.classes, f.createLiteral(classPartitionCounts.length));
// property partition statistics.
for (IVCount tmp : predicatePartitionCounts) {
final BNode propertyPartition = f.createBNode();
final URI p = (URI) tmp.getValue();
g.add(graph, VoidVocabularyDecl.propertyPartition, propertyPartition);
g.add(propertyPartition, VoidVocabularyDecl.property, p);
g.add(propertyPartition, VoidVocabularyDecl.triples, f.createLiteral(tmp.count));
}
// class partition statistics.
{
// per class partition statistics.
for (IVCount tmp : classPartitionCounts) {
final BNode classPartition = f.createBNode();
final BigdataValue cls = tmp.getValue();
g.add(graph, VoidVocabularyDecl.classPartition, classPartition);
g.add(classPartition, VoidVocabularyDecl.class_, cls);
g.add(classPartition, VoidVocabularyDecl.triples, f.createLiteral(tmp.count));
}
} // end class partition statistics.
}
/**
* Describe the default data set (the one identified by the namespace associated with the {@link
* AbstractTripleStore}.
*
* @param describeStatistics When <code>true</code>, the VoID description will include the {@link
* VoidVocabularyDecl#vocabulary} declarations, the property partition statistics, and the
* class partition statistics.
* @param describeNamedGraphs When <code>true</code>, each named graph will also be described in
* in the same level of detail as the default graph. Otherwise only the default graph will be
* described.
*/
public void describeDataSet(final boolean describeStatistics, final boolean describeNamedGraphs) {
final String namespace = tripleStore.getNamespace();
// This is a VoID data set.
g.add(aDataset, RDF.TYPE, VoidVocabularyDecl.Dataset);
// The namespace is used as a title for the data set.
g.add(aDataset, DCTermsVocabularyDecl.title, f.createLiteral(namespace));
// Also present the namespace in an unambiguous manner.
g.add(aDataset, SD.KB_NAMESPACE, f.createLiteral(namespace));
/**
* Service end point for this namespace.
*
* @see <a href="https://sourceforge.net/apps/trac/bigdata/ticket/689" > Missing URL encoding in
* RemoteRepositoryManager </a>
*/
for (String uri : serviceURI) {
g.add(
aDataset,
VoidVocabularyDecl.sparqlEndpoint,
f.createURI(uri + "/" + ConnectOptions.urlEncode(namespace) + "/sparql"));
}
// any URI is considered to be an entity.
g.add(aDataset, VoidVocabularyDecl.uriRegexPattern, f.createLiteral("^.*"));
if (!describeStatistics) {
// No statistics.
return;
}
// Frequency count of the predicates in the default graph.
final IVCount[] predicatePartitionCounts = predicateUsage(tripleStore);
// Frequency count of the classes in the default graph.
final IVCount[] classPartitionCounts = classUsage(tripleStore);
// Describe vocabularies based on the predicate partitions.
describeVocabularies(predicatePartitionCounts);
// defaultGraph description.
{
// Default graph in the default data set.
g.add(aDataset, SD.defaultGraph, aDefaultGraph);
// Describe the default graph using statistics.
describeGraph(aDefaultGraph, predicatePartitionCounts, classPartitionCounts);
} // end defaultGraph
// sb.append("termCount\t = " + tripleStore.getTermCount() + "\n");
//
// sb.append("uriCount\t = " + tripleStore.getURICount() + "\n");
//
// sb.append("literalCount\t = " + tripleStore.getLiteralCount() +
// "\n");
//
// /*
// * Note: The blank node count is only available when using the told
// * bnodes mode.
// */
// sb
// .append("bnodeCount\t = "
// + (tripleStore.getLexiconRelation()
// .isStoreBlankNodes() ? ""
// + tripleStore.getBNodeCount() : "N/A")
// + "\n");
/*
* Report for each named graph.
*/
if (describeNamedGraphs && tripleStore.isQuads()) {
final SPORelation r = tripleStore.getSPORelation();
// the index to use for distinct term scan.
final SPOKeyOrder keyOrder = SPOKeyOrder.CSPO;
// visit distinct IVs for context position on that index.
@SuppressWarnings("rawtypes")
final IChunkedIterator<IV> itr = r.distinctTermScan(keyOrder);
// resolve IVs to terms efficiently during iteration.
final BigdataValueIterator itr2 =
new BigdataValueIteratorImpl(tripleStore /* resolveTerms */, itr);
try {
while (itr2.hasNext()) {
/*
* Describe this named graph.
*
* Note: This is using the predicate and class partition
* statistics from the default graph (RDF merge) to identify
* the set of all possible predicates and classes within
* each named graph. It then tests each predicate and class
* partition against the named graph and ignores those which
* are not present in a given named graph. This is being
* done because we do not have a CPxx index.
*/
final BigdataResource graph = (BigdataResource) itr2.next();
final IVCount[] predicatePartitionCounts2 =
predicateUsage(tripleStore, graph.getIV(), predicatePartitionCounts);
final IVCount[] classPartitionCounts2 =
classUsage(tripleStore, graph.getIV(), classPartitionCounts);
final BNode aNamedGraph = f.createBNode();
// Named graph in the default data set.
g.add(aDataset, SD.namedGraph, aNamedGraph);
// The name of that named graph.
g.add(aNamedGraph, SD.name, graph);
// Describe the named graph.
describeGraph(aNamedGraph, predicatePartitionCounts2, classPartitionCounts2);
}
} finally {
itr2.close();
}
}
}
/**
* Implementation using the json.org API.
*
* @param json The RDF/JSON string to be parsed and converted into a Sesame Graph.
* @return A Sesame Graph if successful, otherwise null.
*/
public static Graph rdfJsonToGraph(String json) {
Graph result = new GraphImpl();
ValueFactory vf = result.getValueFactory();
try {
JSONObject input = new JSONObject(json);
Iterator<String> subjects = input.keys();
while (subjects.hasNext()) {
String subjStr = subjects.next();
Resource subject = null;
subject =
subjStr.startsWith("_:") ? vf.createBNode(subjStr.substring(2)) : vf.createURI(subjStr);
JSONObject pObj = input.getJSONObject(subjStr);
Iterator<String> predicates = pObj.keys();
while (predicates.hasNext()) {
String predStr = predicates.next();
URI predicate = vf.createURI(predStr);
JSONArray predArr = pObj.getJSONArray(predStr);
for (int i = 0; i < predArr.length(); i++) {
Value object = null;
JSONObject obj = predArr.getJSONObject(i);
if (!obj.has("value")) {
continue;
}
String value = obj.getString("value");
if (!obj.has("type")) {
continue;
}
String type = obj.getString("type");
String lang = null;
if (obj.has("lang")) {
lang = obj.getString("lang");
}
String datatype = null;
if (obj.has("datatype")) {
datatype = obj.getString("datatype");
}
if ("literal".equals(type)) {
if (lang != null) {
object = vf.createLiteral(value, lang);
} else if (datatype != null) {
object = vf.createLiteral(value, vf.createURI(datatype));
} else {
object = vf.createLiteral(value);
}
} else if ("bnode".equals(type)) {
object = vf.createBNode(value.substring(2));
} else if ("uri".equals(type)) {
object = vf.createURI(value);
}
if (obj.has("graphs")) {
JSONArray a = obj.getJSONArray("graphs");
// System.out.println("a.length() = " + a.length());
for (int j = 0; j < a.length(); j++) {
// Note: any nulls here will result in statements in the default context.
String s = a.getString(j);
Resource context = s.equals("null") ? null : vf.createURI(s);
// System.out.println("context = " + context);
result.add(subject, predicate, object, context);
}
} else {
result.add(subject, predicate, object);
}
}
}
}
} catch (JSONException e) {
log.error(e.getMessage(), e);
return null;
}
return result;
}
