You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@stanbol.apache.org by re...@apache.org on 2016/05/17 22:20:55 UTC
svn commit: r1744328 [8/24] - in /stanbol/trunk: ./
commons/indexedgraph/src/main/java/org/apache/stanbol/commons/indexedgraph/
commons/indexedgraph/src/test/java/org/apache/stanbol/commons/indexedgraph/
commons/installer/bundleprovider/src/main/java/o...
Modified: stanbol/trunk/enhancement-engines/htmlextractor/src/test/java/org/apache/stanbol/enhancer/engines/htmlextractor/TestHtmlExtractor.java
URL: http://svn.apache.org/viewvc/stanbol/trunk/enhancement-engines/htmlextractor/src/test/java/org/apache/stanbol/enhancer/engines/htmlextractor/TestHtmlExtractor.java?rev=1744328&r1=1744327&r2=1744328&view=diff
==============================================================================
--- stanbol/trunk/enhancement-engines/htmlextractor/src/test/java/org/apache/stanbol/enhancer/engines/htmlextractor/TestHtmlExtractor.java (original)
+++ stanbol/trunk/enhancement-engines/htmlextractor/src/test/java/org/apache/stanbol/enhancer/engines/htmlextractor/TestHtmlExtractor.java Tue May 17 22:20:49 2016
@@ -24,11 +24,11 @@ import java.io.IOException;
import java.io.InputStream;
import java.util.Set;
-import org.apache.clerezza.rdf.core.MGraph;
-import org.apache.clerezza.rdf.core.NonLiteral;
-import org.apache.clerezza.rdf.core.Triple;
-import org.apache.clerezza.rdf.core.UriRef;
-import org.apache.clerezza.rdf.core.impl.SimpleMGraph;
+import org.apache.clerezza.commons.rdf.Graph;
+import org.apache.clerezza.commons.rdf.BlankNodeOrIRI;
+import org.apache.clerezza.commons.rdf.Triple;
+import org.apache.clerezza.commons.rdf.IRI;
+import org.apache.clerezza.commons.rdf.impl.utils.simple.SimpleGraph;
import org.apache.stanbol.enhancer.engines.htmlextractor.impl.ClerezzaRDFUtils;
import org.apache.stanbol.enhancer.engines.htmlextractor.impl.ExtractorException;
import org.apache.stanbol.enhancer.engines.htmlextractor.impl.HtmlExtractionRegistry;
@@ -78,7 +78,7 @@ public class TestHtmlExtractor {
@Test
public void testRdfaExtraction() throws Exception {
HtmlExtractor extractor = new HtmlExtractor(registry, parser);
- MGraph model = new SimpleMGraph();
+ Graph model = new SimpleGraph();
String testFile = "test-rdfa.html";
// extract text from RDFa annotated html
InputStream in = getResourceAsStream(testFile);
@@ -91,7 +91,7 @@ public class TestHtmlExtractor {
LOG.debug("RDFa triples: {}",tripleCounter);
printTriples(model);
assertEquals(8, tripleCounter);
- ClerezzaRDFUtils.makeConnected(model, new UriRef("file://" + testFile), new UriRef(NIE_NS+"contains"));
+ ClerezzaRDFUtils.makeConnected(model, new IRI("file://" + testFile), new IRI(NIE_NS+"contains"));
}
/** This tests some Microformat extraction
@@ -102,7 +102,7 @@ public class TestHtmlExtractor {
@Test
public void testMFExtraction() throws Exception {
HtmlExtractor extractor = new HtmlExtractor(registry, parser);
- MGraph model = new SimpleMGraph();
+ Graph model = new SimpleGraph();
String testFile = "test-MF.html";
// extract text from RDFa annotated html
@@ -116,7 +116,7 @@ public class TestHtmlExtractor {
LOG.debug("Microformat triples: {}",tripleCounter);
printTriples(model);
assertEquals(127, tripleCounter);
- ClerezzaRDFUtils.makeConnected(model, new UriRef("file://" + testFile), new UriRef(NIE_NS+"contains"));
+ ClerezzaRDFUtils.makeConnected(model, new IRI("file://" + testFile), new IRI(NIE_NS+"contains"));
}
/** This test some extraction of microdata from an HTML-5 document
@@ -126,7 +126,7 @@ public class TestHtmlExtractor {
@Test
public void testMicrodataExtraction() throws Exception {
HtmlExtractor extractor = new HtmlExtractor(registry, parser);
- MGraph model = new SimpleMGraph();
+ Graph model = new SimpleGraph();
String testFile = "test-microdata.html";
// extract text from RDFa annotated html
@@ -140,7 +140,7 @@ public class TestHtmlExtractor {
LOG.debug("Microdata triples: {}",tripleCounter);
printTriples(model);
assertEquals(91, tripleCounter);
- ClerezzaRDFUtils.makeConnected(model, new UriRef("file://" + testFile), new UriRef(NIE_NS+"contains"));
+ ClerezzaRDFUtils.makeConnected(model, new IRI("file://" + testFile), new IRI(NIE_NS+"contains"));
}
/** This tests the merging of disconnected graphs under a single root
@@ -150,7 +150,7 @@ public class TestHtmlExtractor {
@Test
public void testRootExtraction() throws Exception {
HtmlExtractor extractor = new HtmlExtractor(registry, parser);
- MGraph model = new SimpleMGraph();
+ Graph model = new SimpleGraph();
String testFile = "test-MultiRoot.html";
// extract text from RDFa annotated html
@@ -163,9 +163,9 @@ public class TestHtmlExtractor {
int tripleCounter = model.size();
LOG.debug("Triples: {}",tripleCounter);
printTriples(model);
- Set<NonLiteral> roots = ClerezzaRDFUtils.findRoots(model);
+ Set<BlankNodeOrIRI> roots = ClerezzaRDFUtils.findRoots(model);
assertTrue(roots.size() > 1);
- ClerezzaRDFUtils.makeConnected(model, new UriRef("file://" + testFile), new UriRef(NIE_NS+"contains"));
+ ClerezzaRDFUtils.makeConnected(model, new IRI("file://" + testFile), new IRI(NIE_NS+"contains"));
roots = ClerezzaRDFUtils.findRoots(model);
assertEquals(1,roots.size());
}
@@ -175,7 +175,7 @@ public class TestHtmlExtractor {
testResultFile);
}
- private void printTriples(MGraph model) {
+ private void printTriples(Graph model) {
for (Triple t: model) {
LOG.debug(t.toString());
}
Modified: stanbol/trunk/enhancement-engines/keywordextraction/src/main/java/org/apache/stanbol/enhancer/engines/keywordextraction/engine/KeywordLinkingEngine.java
URL: http://svn.apache.org/viewvc/stanbol/trunk/enhancement-engines/keywordextraction/src/main/java/org/apache/stanbol/enhancer/engines/keywordextraction/engine/KeywordLinkingEngine.java?rev=1744328&r1=1744327&r2=1744328&view=diff
==============================================================================
--- stanbol/trunk/enhancement-engines/keywordextraction/src/main/java/org/apache/stanbol/enhancer/engines/keywordextraction/engine/KeywordLinkingEngine.java (original)
+++ stanbol/trunk/enhancement-engines/keywordextraction/src/main/java/org/apache/stanbol/enhancer/engines/keywordextraction/engine/KeywordLinkingEngine.java Tue May 17 22:20:49 2016
@@ -30,13 +30,13 @@ import java.util.Map;
import java.util.Map.Entry;
import java.util.Set;
-import org.apache.clerezza.rdf.core.Language;
-import org.apache.clerezza.rdf.core.Literal;
+import org.apache.clerezza.commons.rdf.Language;
+import org.apache.clerezza.commons.rdf.Literal;
import org.apache.clerezza.rdf.core.LiteralFactory;
-import org.apache.clerezza.rdf.core.MGraph;
-import org.apache.clerezza.rdf.core.UriRef;
-import org.apache.clerezza.rdf.core.impl.PlainLiteralImpl;
-import org.apache.clerezza.rdf.core.impl.TripleImpl;
+import org.apache.clerezza.commons.rdf.Graph;
+import org.apache.clerezza.commons.rdf.IRI;
+import org.apache.clerezza.commons.rdf.impl.utils.PlainLiteralImpl;
+import org.apache.clerezza.commons.rdf.impl.utils.TripleImpl;
import org.apache.commons.lang.StringUtils;
import org.apache.felix.scr.annotations.Activate;
import org.apache.felix.scr.annotations.Component;
@@ -350,7 +350,7 @@ public class KeywordLinkingEngine
if(isOfflineMode() && !entitySearcher.supportsOfflineMode()){
throw new EngineException("Offline mode is not supported by the Component used to lookup Entities");
}
- Entry<UriRef,Blob> contentPart = ContentItemHelper.getBlob(ci, SUPPORTED_MIMETYPES);
+ Entry<IRI,Blob> contentPart = ContentItemHelper.getBlob(ci, SUPPORTED_MIMETYPES);
if(contentPart == null){
throw new IllegalStateException("No ContentPart with a supported Mime Type"
+ "found for ContentItem "+ci.getUri()+"(supported: '"
@@ -416,12 +416,12 @@ public class KeywordLinkingEngine
if(language != null && !language.isEmpty()){
languageObject = new Language(language);
}
- MGraph metadata = ci.getMetadata();
+ Graph metadata = ci.getMetadata();
for(LinkedEntity linkedEntity : linkedEntities){
- Collection<UriRef> textAnnotations = new ArrayList<UriRef>(linkedEntity.getOccurrences().size());
+ Collection<IRI> textAnnotations = new ArrayList<IRI>(linkedEntity.getOccurrences().size());
//first create the TextAnnotations for the Occurrences
for(Occurrence occurrence : linkedEntity.getOccurrences()){
- UriRef textAnnotation = EnhancementEngineHelper.createTextEnhancement(ci, this);
+ IRI textAnnotation = EnhancementEngineHelper.createTextEnhancement(ci, this);
textAnnotations.add(textAnnotation);
metadata.add(new TripleImpl(textAnnotation,
Properties.ENHANCER_START,
@@ -438,14 +438,14 @@ public class KeywordLinkingEngine
metadata.add(new TripleImpl(textAnnotation,
Properties.ENHANCER_CONFIDENCE,
literalFactory.createTypedLiteral(linkedEntity.getScore())));
- for(UriRef dcType : linkedEntity.getTypes()){
+ for(IRI dcType : linkedEntity.getTypes()){
metadata.add(new TripleImpl(
textAnnotation, Properties.DC_TYPE, dcType));
}
}
//now the EntityAnnotations for the Suggestions
for(Suggestion suggestion : linkedEntity.getSuggestions()){
- UriRef entityAnnotation = EnhancementEngineHelper.createEntityEnhancement(ci, this);
+ IRI entityAnnotation = EnhancementEngineHelper.createEntityEnhancement(ci, this);
//should we use the label used for the match, or search the
//representation for the best label ... currently its the matched one
Text label = suggestion.getBestLabel(linkerConfig.getNameField(),language);
@@ -457,21 +457,21 @@ public class KeywordLinkingEngine
new Language(label.getLanguage()))));
metadata.add(new TripleImpl(entityAnnotation,
Properties.ENHANCER_ENTITY_REFERENCE,
- new UriRef(suggestion.getRepresentation().getId())));
+ new IRI(suggestion.getRepresentation().getId())));
Iterator<Reference> suggestionTypes = suggestion.getRepresentation().getReferences(linkerConfig.getTypeField());
while(suggestionTypes.hasNext()){
metadata.add(new TripleImpl(entityAnnotation,
- Properties.ENHANCER_ENTITY_TYPE, new UriRef(suggestionTypes.next().getReference())));
+ Properties.ENHANCER_ENTITY_TYPE, new IRI(suggestionTypes.next().getReference())));
}
metadata.add(new TripleImpl(entityAnnotation,
Properties.ENHANCER_CONFIDENCE, literalFactory.createTypedLiteral(suggestion.getScore())));
- for(UriRef textAnnotation : textAnnotations){
+ for(IRI textAnnotation : textAnnotations){
metadata.add(new TripleImpl(entityAnnotation,
Properties.DC_RELATION, textAnnotation));
}
//add the name of the ReferencedSite providing this suggestion
metadata.add(new TripleImpl(entityAnnotation,
- new UriRef(RdfResourceEnum.site.getUri()),
+ new IRI(RdfResourceEnum.site.getUri()),
new PlainLiteralImpl(referencedSiteName)));
//in case dereferencing of Entities is enabled we need also to
//add the RDF data for entities
@@ -493,7 +493,7 @@ public class KeywordLinkingEngine
private String extractLanguage(ContentItem ci) {
String lang = EnhancementEngineHelper.getLanguage(ci);
// if(lang != null){
-// MGraph metadata = ci.getMetadata();
+// Graph metadata = ci.getMetadata();
// Iterator<Triple> langaugeEnhancementCreatorTriples =
// metadata.filter(null, Properties.DC_CREATOR, LANG_ID_ENGINE_NAME);
// if(langaugeEnhancementCreatorTriples.hasNext()){
@@ -867,14 +867,14 @@ public class KeywordLinkingEngine
sourceTypes[0],o);
continue configs;
}
- UriRef targetUri = new UriRef(targetType);
+ IRI targetUri = new IRI(targetType);
for(String sourceType : sourceTypes){
if(!sourceType.isEmpty()){
sourceType = NamespaceMappingUtils.getConfiguredUri(
nsPrefixService,TYPE_MAPPINGS,sourceType.trim()); //support for ns:localName
try { //validate
new URI(sourceType);
- UriRef old = linkerConfig.setTypeMapping(sourceType, targetUri);
+ IRI old = linkerConfig.setTypeMapping(sourceType, targetUri);
if(old == null){
log.info(" > add type mapping {} > {}", sourceType,targetType);
} else {
Modified: stanbol/trunk/enhancement-engines/keywordextraction/src/main/java/org/apache/stanbol/enhancer/engines/keywordextraction/impl/EntityLinker.java
URL: http://svn.apache.org/viewvc/stanbol/trunk/enhancement-engines/keywordextraction/src/main/java/org/apache/stanbol/enhancer/engines/keywordextraction/impl/EntityLinker.java?rev=1744328&r1=1744327&r2=1744328&view=diff
==============================================================================
--- stanbol/trunk/enhancement-engines/keywordextraction/src/main/java/org/apache/stanbol/enhancer/engines/keywordextraction/impl/EntityLinker.java (original)
+++ stanbol/trunk/enhancement-engines/keywordextraction/src/main/java/org/apache/stanbol/enhancer/engines/keywordextraction/impl/EntityLinker.java Tue May 17 22:20:49 2016
@@ -27,7 +27,7 @@ import java.util.List;
import java.util.Map;
import java.util.Set;
-import org.apache.clerezza.rdf.core.UriRef;
+import org.apache.clerezza.commons.rdf.IRI;
import org.apache.stanbol.commons.opennlp.TextAnalyzer.AnalysedText.Token;
import org.apache.stanbol.enhancer.engines.keywordextraction.impl.EntityLinkerConfig.RedirectProcessingMode;
import org.apache.stanbol.enhancer.engines.keywordextraction.impl.Suggestion.MATCH;
@@ -205,17 +205,17 @@ public class EntityLinker {
* @param conceptTypes The list of suggestions
* @return the types values for the {@link LinkedEntity}
*/
- private Set<UriRef> getLinkedEntityTypes(Collection<Suggestion> suggestions){
+ private Set<IRI> getLinkedEntityTypes(Collection<Suggestion> suggestions){
Collection<String> conceptTypes = new HashSet<String>();
for(Suggestion suggestion : suggestions){
for(Iterator<Reference> types =
suggestion.getRepresentation().getReferences(config.getTypeField());
types.hasNext();conceptTypes.add(types.next().getReference()));
}
- Map<String,UriRef> typeMappings = config.getTypeMappings();
- Set<UriRef> dcTypes = new HashSet<UriRef>();
+ Map<String,IRI> typeMappings = config.getTypeMappings();
+ Set<IRI> dcTypes = new HashSet<IRI>();
for(String conceptType : conceptTypes){
- UriRef dcType = typeMappings.get(conceptType);
+ IRI dcType = typeMappings.get(conceptType);
if(dcType != null){
dcTypes.add(dcType);
}
Modified: stanbol/trunk/enhancement-engines/keywordextraction/src/main/java/org/apache/stanbol/enhancer/engines/keywordextraction/impl/EntityLinkerConfig.java
URL: http://svn.apache.org/viewvc/stanbol/trunk/enhancement-engines/keywordextraction/src/main/java/org/apache/stanbol/enhancer/engines/keywordextraction/impl/EntityLinkerConfig.java?rev=1744328&r1=1744327&r2=1744328&view=diff
==============================================================================
--- stanbol/trunk/enhancement-engines/keywordextraction/src/main/java/org/apache/stanbol/enhancer/engines/keywordextraction/impl/EntityLinkerConfig.java (original)
+++ stanbol/trunk/enhancement-engines/keywordextraction/src/main/java/org/apache/stanbol/enhancer/engines/keywordextraction/impl/EntityLinkerConfig.java Tue May 17 22:20:49 2016
@@ -25,7 +25,7 @@ import java.util.Set;
import opennlp.tools.chunker.Chunker;
import opennlp.tools.postag.POSTagger;
-import org.apache.clerezza.rdf.core.UriRef;
+import org.apache.clerezza.commons.rdf.IRI;
import org.apache.stanbol.commons.opennlp.TextAnalyzer.AnalysedText;
import org.apache.stanbol.commons.opennlp.TextAnalyzer.AnalysedText.Chunk;
import org.apache.stanbol.commons.opennlp.TextAnalyzer.AnalysedText.Token;
@@ -95,10 +95,10 @@ public class EntityLinkerConfig {
* Default mapping for Concept types to dc:type values added for
* TextAnnotations.
*/
- public static final Map<String,UriRef> DEFAULT_ENTITY_TYPE_MAPPINGS;
+ public static final Map<String,IRI> DEFAULT_ENTITY_TYPE_MAPPINGS;
static { //the default mappings for the three types used by the Stanbol Enhancement Structure
- Map<String,UriRef> mappings = new HashMap<String,UriRef>();
+ Map<String,IRI> mappings = new HashMap<String,IRI>();
mappings.put(OntologicalClasses.DBPEDIA_ORGANISATION.getUnicodeString(),
OntologicalClasses.DBPEDIA_ORGANISATION);
mappings.put("http://dbpedia.org/ontology/Newspaper", OntologicalClasses.DBPEDIA_ORGANISATION);
@@ -120,22 +120,22 @@ public class EntityLinkerConfig {
mappings.put(OntologicalClasses.DBPEDIA_ORGANISATION.getUnicodeString(),
OntologicalClasses.DBPEDIA_ORGANISATION);
-// UriRef DRUG = new UriRef(NamespaceEnum.drugbank+"drugs");
+// IRI DRUG = new IRI(NamespaceEnum.drugbank+"drugs");
// mappings.put(DRUG.getUnicodeString(), DRUG);
// mappings.put(NamespaceEnum.dbpediaOnt+"Drug", DRUG);
// mappings.put(NamespaceEnum.dailymed+"drugs", DRUG);
// mappings.put(NamespaceEnum.sider+"drugs", DRUG);
// mappings.put(NamespaceEnum.tcm+"Medicine", DRUG);
//
-// UriRef DISEASE = new UriRef(NamespaceEnum.diseasome+"diseases");
+// IRI DISEASE = new IRI(NamespaceEnum.diseasome+"diseases");
// mappings.put(DISEASE.getUnicodeString(), DISEASE);
// mappings.put(NamespaceEnum.linkedct+"condition", DISEASE);
// mappings.put(NamespaceEnum.tcm+"Disease", DISEASE);
//
-// UriRef SIDE_EFFECT = new UriRef(NamespaceEnum.sider+"side_effects");
+// IRI SIDE_EFFECT = new IRI(NamespaceEnum.sider+"side_effects");
// mappings.put(SIDE_EFFECT.getUnicodeString(), SIDE_EFFECT);
//
-// UriRef INGREDIENT = new UriRef(NamespaceEnum.dailymed+"ingredients");
+// IRI INGREDIENT = new IRI(NamespaceEnum.dailymed+"ingredients");
// mappings.put(INGREDIENT.getUnicodeString(), INGREDIENT);
DEFAULT_ENTITY_TYPE_MAPPINGS = Collections.unmodifiableMap(mappings);
@@ -198,8 +198,8 @@ public class EntityLinkerConfig {
* Holds the mappings of rdf:type used by concepts to dc:type values used
* by TextAnnotations.
*/
- private Map<String,UriRef> typeMappings;
- private Map<String, UriRef> unmodTypeMappings;
+ private Map<String,IRI> typeMappings;
+ private Map<String, IRI> unmodTypeMappings;
/**
* The mode on how to process redirect for Entities.
*/
@@ -207,7 +207,7 @@ public class EntityLinkerConfig {
/**
* the default DC Type
*/
- private UriRef defaultDcType;
+ private IRI defaultDcType;
private String nameField;
private String redirectField;
private String typeField;
@@ -265,7 +265,7 @@ public class EntityLinkerConfig {
setMaxSuggestions(DEFAULT_SUGGESTIONS);
setMaxSearchTokens(DEFAULT_MAX_SEARCH_TOKENS);
setRedirectProcessingMode(DEFAULT_REDIRECT_PROCESSING_MODE);
- typeMappings = new HashMap<String,UriRef>(DEFAULT_ENTITY_TYPE_MAPPINGS);
+ typeMappings = new HashMap<String,IRI>(DEFAULT_ENTITY_TYPE_MAPPINGS);
unmodTypeMappings = Collections.unmodifiableMap(typeMappings);
setDefaultDcType(typeMappings.remove(null));
setNameField(DEFAULT_NAME_FIELD);
@@ -445,23 +445,23 @@ public class EntityLinkerConfig {
* @return the previously mapped dc:type value or <code>null</code> if
* no mapping for the parsed concept type was present
*/
- public UriRef removeTypeMapping(String conceptType){
+ public IRI removeTypeMapping(String conceptType){
return typeMappings.remove(conceptType);
}
/**
*
* @param conceptType the type of the concept or <code>null</code> to
- * add the default dc:type mapping. See also {@link #setDefaultDcType(UriRef)}
+ * add the default dc:type mapping. See also {@link #setDefaultDcType(IRI)}
* @param dcType the dc:type for the parsed concept type
* @return the previously mapped dc:type value if an existing mapping
* was updated or <code>null</code> if a new mapping was added.
*/
- public UriRef setTypeMapping(String conceptType, UriRef dcType){
+ public IRI setTypeMapping(String conceptType, IRI dcType){
if(dcType == null) {
throw new IllegalArgumentException("The parsed dc:type URI MUST NOT be NULL!");
}
if(conceptType == null){ //handle setting of the default dc:type value
- UriRef oldDefault = getDefaultDcType();
+ IRI oldDefault = getDefaultDcType();
setDefaultDcType(dcType);
return oldDefault;
}
@@ -475,7 +475,7 @@ public class EntityLinkerConfig {
* cases.
* @param defaultDcType the defaultDcType to set
*/
- public void setDefaultDcType(UriRef defaultDcType) {
+ public void setDefaultDcType(IRI defaultDcType) {
this.defaultDcType = defaultDcType;
}
/**
@@ -484,7 +484,7 @@ public class EntityLinkerConfig {
* explicit mapping exists
* @return the defaultDcType
*/
- public UriRef getDefaultDcType() {
+ public IRI getDefaultDcType() {
return defaultDcType;
}
/**
@@ -505,7 +505,7 @@ public class EntityLinkerConfig {
* Getter for the read only mappings of type mappings
* @return the type mappings (read only)
*/
- public Map<String,UriRef> getTypeMappings() {
+ public Map<String,IRI> getTypeMappings() {
return unmodTypeMappings;
}
/**
Modified: stanbol/trunk/enhancement-engines/keywordextraction/src/main/java/org/apache/stanbol/enhancer/engines/keywordextraction/impl/LinkedEntity.java
URL: http://svn.apache.org/viewvc/stanbol/trunk/enhancement-engines/keywordextraction/src/main/java/org/apache/stanbol/enhancer/engines/keywordextraction/impl/LinkedEntity.java?rev=1744328&r1=1744327&r2=1744328&view=diff
==============================================================================
--- stanbol/trunk/enhancement-engines/keywordextraction/src/main/java/org/apache/stanbol/enhancer/engines/keywordextraction/impl/LinkedEntity.java (original)
+++ stanbol/trunk/enhancement-engines/keywordextraction/src/main/java/org/apache/stanbol/enhancer/engines/keywordextraction/impl/LinkedEntity.java Tue May 17 22:20:49 2016
@@ -24,7 +24,7 @@ import java.util.Set;
import opennlp.tools.util.Span;
-import org.apache.clerezza.rdf.core.UriRef;
+import org.apache.clerezza.commons.rdf.IRI;
import org.apache.stanbol.commons.opennlp.TextAnalyzer.AnalysedText;
/**
@@ -131,7 +131,7 @@ public class LinkedEntity {
}
}
private final String selectedText;
- private final Set<UriRef> types;
+ private final Set<IRI> types;
private final List<Suggestion> suggestions;
private final Collection<Occurrence> occurrences = new ArrayList<Occurrence>();
private final Collection<Occurrence> unmodOccurrences = Collections.unmodifiableCollection(occurrences);
@@ -141,7 +141,7 @@ public class LinkedEntity {
* @param suggestions the entity suggestions
* @param types the types of the linked entity.
*/
- protected LinkedEntity(String selectedText, List<Suggestion> suggestions, Set<UriRef> types) {
+ protected LinkedEntity(String selectedText, List<Suggestion> suggestions, Set<IRI> types) {
this.suggestions = Collections.unmodifiableList(suggestions);
this.selectedText = selectedText;
this.types = Collections.unmodifiableSet(types);
@@ -155,7 +155,7 @@ public class LinkedEntity {
* @param types the types of the linked entity.
*/
protected LinkedEntity(AnalysedText sentence,int startToken,int tokenSpan,
- List<Suggestion> suggestions, Set<UriRef> types) {
+ List<Suggestion> suggestions, Set<IRI> types) {
this(sentence.getText().substring(
sentence.getTokens().get(startToken).getStart(),
sentence.getTokens().get(tokenSpan).getEnd()),suggestions,types);
@@ -173,7 +173,7 @@ public class LinkedEntity {
* Getter for read only list of types
* @return the types
*/
- public Set<UriRef> getTypes() {
+ public Set<IRI> getTypes() {
return types;
}
/**
Modified: stanbol/trunk/enhancement-engines/keywordextraction/src/test/java/org/apache/stanbol/enhancer/engines/keywordextraction/engine/KeywordLinkingEngineTest.java
URL: http://svn.apache.org/viewvc/stanbol/trunk/enhancement-engines/keywordextraction/src/test/java/org/apache/stanbol/enhancer/engines/keywordextraction/engine/KeywordLinkingEngineTest.java?rev=1744328&r1=1744327&r2=1744328&view=diff
==============================================================================
--- stanbol/trunk/enhancement-engines/keywordextraction/src/test/java/org/apache/stanbol/enhancer/engines/keywordextraction/engine/KeywordLinkingEngineTest.java (original)
+++ stanbol/trunk/enhancement-engines/keywordextraction/src/test/java/org/apache/stanbol/enhancer/engines/keywordextraction/engine/KeywordLinkingEngineTest.java Tue May 17 22:20:49 2016
@@ -39,14 +39,13 @@ import java.util.Map;
import opennlp.tools.tokenize.SimpleTokenizer;
-import org.apache.clerezza.rdf.core.Literal;
+import org.apache.clerezza.commons.rdf.Literal;
import org.apache.clerezza.rdf.core.LiteralFactory;
-import org.apache.clerezza.rdf.core.Resource;
-import org.apache.clerezza.rdf.core.Triple;
-import org.apache.clerezza.rdf.core.TypedLiteral;
-import org.apache.clerezza.rdf.core.UriRef;
-import org.apache.clerezza.rdf.core.impl.PlainLiteralImpl;
-import org.apache.clerezza.rdf.core.impl.TripleImpl;
+import org.apache.clerezza.commons.rdf.RDFTerm;
+import org.apache.clerezza.commons.rdf.Triple;
+import org.apache.clerezza.commons.rdf.IRI;
+import org.apache.clerezza.commons.rdf.impl.utils.PlainLiteralImpl;
+import org.apache.clerezza.commons.rdf.impl.utils.TripleImpl;
import org.apache.stanbol.commons.opennlp.OpenNLP;
import org.apache.stanbol.commons.opennlp.TextAnalyzer.TextAnalyzerConfig;
import org.apache.stanbol.enhancer.contentitem.inmemory.InMemoryContentItemFactory;
@@ -168,7 +167,7 @@ public class KeywordLinkingEngineTest {
}
public static ContentItem getContentItem(final String id, final String text) throws IOException {
- return ciFactory.createContentItem(new UriRef(id),new StringSource(text));
+ return ciFactory.createContentItem(new IRI(id),new StringSource(text));
}
/**
* This tests the EntityLinker functionality (if the expected Entities
@@ -237,7 +236,7 @@ public class KeywordLinkingEngineTest {
//compute the enhancements
engine.computeEnhancements(ci);
//validate the enhancement results
- Map<UriRef,Resource> expectedValues = new HashMap<UriRef,Resource>();
+ Map<IRI,RDFTerm> expectedValues = new HashMap<IRI,RDFTerm>();
expectedValues.put(ENHANCER_EXTRACTED_FROM, ci.getUri());
expectedValues.put(DC_CREATOR,LiteralFactory.getInstance().createTypedLiteral(
engine.getClass().getName()));
@@ -251,18 +250,18 @@ public class KeywordLinkingEngineTest {
assertEquals("Five fise:EntityAnnotations are expected by this Test", 5, numEntityAnnotations);
}
/**
- * Similar to {@link EnhancementStructureHelper#validateAllEntityAnnotations(org.apache.clerezza.rdf.core.TripleCollection, Map)}
+ * Similar to {@link EnhancementStructureHelper#validateAllEntityAnnotations(org.apache.clerezza.commons.rdf.Graph, Map)}
* but in addition checks fise:confidence [0..1] and entityhub:site properties
* @param ci
* @param expectedValues
* @return
*/
- private static int validateAllEntityAnnotations(ContentItem ci, Map<UriRef,Resource> expectedValues){
+ private static int validateAllEntityAnnotations(ContentItem ci, Map<IRI,RDFTerm> expectedValues){
Iterator<Triple> entityAnnotationIterator = ci.getMetadata().filter(null,
RDF_TYPE, ENHANCER_ENTITYANNOTATION);
int entityAnnotationCount = 0;
while (entityAnnotationIterator.hasNext()) {
- UriRef entityAnnotation = (UriRef) entityAnnotationIterator.next().getSubject();
+ IRI entityAnnotation = (IRI) entityAnnotationIterator.next().getSubject();
// test if selected Text is added
validateEntityAnnotation(ci.getMetadata(), entityAnnotation, expectedValues);
//validate also that the confidence is between [0..1]
@@ -279,12 +278,12 @@ public class KeywordLinkingEngineTest {
// +"',entityAnnotation "+entityAnnotation+")",
// 0.0 <= confidence.doubleValue());
//Test the entityhub:site property (STANBOL-625)
- UriRef ENTITYHUB_SITE = new UriRef(RdfResourceEnum.site.getUri());
+ IRI ENTITYHUB_SITE = new IRI(RdfResourceEnum.site.getUri());
Iterator<Triple> entitySiteIterator = ci.getMetadata().filter(entityAnnotation,
ENTITYHUB_SITE, null);
assertTrue("Expected entityhub:site value is missing (entityAnnotation "
+entityAnnotation+")",entitySiteIterator.hasNext());
- Resource siteResource = entitySiteIterator.next().getObject();
+ RDFTerm siteResource = entitySiteIterator.next().getObject();
assertTrue("entityhub:site values MUST BE Literals", siteResource instanceof Literal);
assertEquals("'"+TEST_REFERENCED_SITE_NAME+"' is expected as "
+ "entityhub:site value", TEST_REFERENCED_SITE_NAME,
Modified: stanbol/trunk/enhancement-engines/keywordextraction/src/test/java/org/apache/stanbol/enhancer/engines/keywordextraction/impl/ClasspathDataFileProvider.java
URL: http://svn.apache.org/viewvc/stanbol/trunk/enhancement-engines/keywordextraction/src/test/java/org/apache/stanbol/enhancer/engines/keywordextraction/impl/ClasspathDataFileProvider.java?rev=1744328&r1=1744327&r2=1744328&view=diff
==============================================================================
--- stanbol/trunk/enhancement-engines/keywordextraction/src/test/java/org/apache/stanbol/enhancer/engines/keywordextraction/impl/ClasspathDataFileProvider.java (original)
+++ stanbol/trunk/enhancement-engines/keywordextraction/src/test/java/org/apache/stanbol/enhancer/engines/keywordextraction/impl/ClasspathDataFileProvider.java Tue May 17 22:20:49 2016
@@ -68,7 +68,7 @@ public class ClasspathDataFileProvider i
// load default OpenNLP models from classpath (embedded in the defaultdata bundle)
final String resourcePath = RESOURCE_BASE_PATH + filename;
final URL dataFile = getClass().getClassLoader().getResource(resourcePath);
- //log.debug("Resource {} found: {}", (in == null ? "NOT" : ""), resourcePath);
+ //log.debug("RDFTerm {} found: {}", (in == null ? "NOT" : ""), resourcePath);
return dataFile;
}
}
Modified: stanbol/trunk/enhancement-engines/kuromoji-nlp/src/main/java/org/apache/stanbol/enhancer/engines/kuromoji/impl/KuromojiNlpEngine.java
URL: http://svn.apache.org/viewvc/stanbol/trunk/enhancement-engines/kuromoji-nlp/src/main/java/org/apache/stanbol/enhancer/engines/kuromoji/impl/KuromojiNlpEngine.java?rev=1744328&r1=1744327&r2=1744328&view=diff
==============================================================================
--- stanbol/trunk/enhancement-engines/kuromoji-nlp/src/main/java/org/apache/stanbol/enhancer/engines/kuromoji/impl/KuromojiNlpEngine.java (original)
+++ stanbol/trunk/enhancement-engines/kuromoji-nlp/src/main/java/org/apache/stanbol/enhancer/engines/kuromoji/impl/KuromojiNlpEngine.java Tue May 17 22:20:49 2016
@@ -37,12 +37,12 @@ import java.util.Iterator;
import java.util.List;
import java.util.Map;
-import org.apache.clerezza.rdf.core.Language;
+import org.apache.clerezza.commons.rdf.Language;
import org.apache.clerezza.rdf.core.LiteralFactory;
-import org.apache.clerezza.rdf.core.MGraph;
-import org.apache.clerezza.rdf.core.UriRef;
-import org.apache.clerezza.rdf.core.impl.PlainLiteralImpl;
-import org.apache.clerezza.rdf.core.impl.TripleImpl;
+import org.apache.clerezza.commons.rdf.Graph;
+import org.apache.clerezza.commons.rdf.IRI;
+import org.apache.clerezza.commons.rdf.impl.utils.PlainLiteralImpl;
+import org.apache.clerezza.commons.rdf.impl.utils.TripleImpl;
import org.apache.commons.io.input.CharSequenceReader;
import org.apache.felix.scr.annotations.Activate;
import org.apache.felix.scr.annotations.Component;
@@ -185,7 +185,7 @@ public class KuromojiNlpEngine extends A
@Override
public int canEnhance(ContentItem ci) throws EngineException {
// check if content is present
- Map.Entry<UriRef,Blob> entry = NlpEngineHelper.getPlainText(this, ci, false);
+ Map.Entry<IRI,Blob> entry = NlpEngineHelper.getPlainText(this, ci, false);
if(entry == null || entry.getValue() == null) {
return CANNOT_ENHANCE;
}
@@ -323,12 +323,12 @@ public class KuromojiNlpEngine extends A
} catch (IOException e) {/* ignore */}
}
//finally write the NER annotations to the metadata of the ContentItem
- final MGraph metadata = ci.getMetadata();
+ final Graph metadata = ci.getMetadata();
ci.getLock().writeLock().lock();
try {
Language lang = new Language("ja");
for(NerData nerData : nerList){
- UriRef ta = EnhancementEngineHelper.createTextEnhancement(ci, this);
+ IRI ta = EnhancementEngineHelper.createTextEnhancement(ci, this);
metadata.add(new TripleImpl(ta, ENHANCER_SELECTED_TEXT, new PlainLiteralImpl(
at.getSpan().substring(nerData.start, nerData.end),lang)));
metadata.add(new TripleImpl(ta, DC_TYPE, nerData.tag.getType()));
Modified: stanbol/trunk/enhancement-engines/kuromoji-nlp/src/test/java/org/apache/stanbol/enhancer/engines/kuromoji/impl/ClasspathDataFileProvider.java
URL: http://svn.apache.org/viewvc/stanbol/trunk/enhancement-engines/kuromoji-nlp/src/test/java/org/apache/stanbol/enhancer/engines/kuromoji/impl/ClasspathDataFileProvider.java?rev=1744328&r1=1744327&r2=1744328&view=diff
==============================================================================
--- stanbol/trunk/enhancement-engines/kuromoji-nlp/src/test/java/org/apache/stanbol/enhancer/engines/kuromoji/impl/ClasspathDataFileProvider.java (original)
+++ stanbol/trunk/enhancement-engines/kuromoji-nlp/src/test/java/org/apache/stanbol/enhancer/engines/kuromoji/impl/ClasspathDataFileProvider.java Tue May 17 22:20:49 2016
@@ -73,7 +73,7 @@ public class ClasspathDataFileProvider i
// load default OpenNLP models from classpath (embedded in the defaultdata bundle)
final String resourcePath = RESOURCE_BASE_PATH + filename;
final URL dataFile = getClass().getClassLoader().getResource(resourcePath);
- //log.debug("Resource {} found: {}", (in == null ? "NOT" : ""), resourcePath);
+ //log.debug("RDFTerm {} found: {}", (in == null ? "NOT" : ""), resourcePath);
return dataFile;
}
}
Modified: stanbol/trunk/enhancement-engines/kuromoji-nlp/src/test/java/org/apache/stanbol/enhancer/engines/kuromoji/impl/TestKuromojiNlpEngine.java
URL: http://svn.apache.org/viewvc/stanbol/trunk/enhancement-engines/kuromoji-nlp/src/test/java/org/apache/stanbol/enhancer/engines/kuromoji/impl/TestKuromojiNlpEngine.java?rev=1744328&r1=1744327&r2=1744328&view=diff
==============================================================================
--- stanbol/trunk/enhancement-engines/kuromoji-nlp/src/test/java/org/apache/stanbol/enhancer/engines/kuromoji/impl/TestKuromojiNlpEngine.java (original)
+++ stanbol/trunk/enhancement-engines/kuromoji-nlp/src/test/java/org/apache/stanbol/enhancer/engines/kuromoji/impl/TestKuromojiNlpEngine.java Tue May 17 22:20:49 2016
@@ -24,10 +24,10 @@ import java.util.List;
import java.util.Map;
import org.apache.clerezza.rdf.core.LiteralFactory;
-import org.apache.clerezza.rdf.core.Resource;
-import org.apache.clerezza.rdf.core.UriRef;
-import org.apache.clerezza.rdf.core.impl.PlainLiteralImpl;
-import org.apache.clerezza.rdf.core.impl.TripleImpl;
+import org.apache.clerezza.commons.rdf.RDFTerm;
+import org.apache.clerezza.commons.rdf.IRI;
+import org.apache.clerezza.commons.rdf.impl.utils.PlainLiteralImpl;
+import org.apache.clerezza.commons.rdf.impl.utils.TripleImpl;
import org.apache.stanbol.commons.solr.utils.DataFileResourceLoader;
import org.apache.stanbol.commons.stanboltools.datafileprovider.DataFileProvider;
import org.apache.stanbol.enhancer.contentitem.inmemory.InMemoryContentItemFactory;
@@ -62,7 +62,7 @@ public class TestKuromojiNlpEngine {
private static ContentItemFactory contentItemFactory;
- private static UriRef id = new UriRef("http://www.example.org/contentItem1");
+ private static IRI id = new IRI("http://www.example.org/contentItem1");
/**
* Test text taken from the <a href ="http://ja.wikipedia.org/wiki/%E3%83%AD%E3%83%B3%E3%83%89%E3%83%B3">
* Japanese wikipedia side for London</a>.
@@ -107,7 +107,7 @@ public class TestKuromojiNlpEngine {
Assert.assertEquals(EnhancementEngine.ENHANCE_ASYNC, engine.canEnhance(contentItem));
engine.computeEnhancements(contentItem);
//assert the results
- Map<UriRef,Resource> expected = new HashMap<UriRef,Resource>();
+ Map<IRI,RDFTerm> expected = new HashMap<IRI,RDFTerm>();
expected.put(Properties.DC_CREATOR, lf.createTypedLiteral(engine.getClass().getName()));
expected.put(Properties.ENHANCER_EXTRACTED_FROM,contentItem.getUri());
Assert.assertEquals(16, EnhancementStructureHelper.validateAllTextAnnotations(
Modified: stanbol/trunk/enhancement-engines/langdetect/src/main/java/org/apache/stanbol/enhancer/engines/langdetect/LanguageDetectionEnhancementEngine.java
URL: http://svn.apache.org/viewvc/stanbol/trunk/enhancement-engines/langdetect/src/main/java/org/apache/stanbol/enhancer/engines/langdetect/LanguageDetectionEnhancementEngine.java?rev=1744328&r1=1744327&r2=1744328&view=diff
==============================================================================
--- stanbol/trunk/enhancement-engines/langdetect/src/main/java/org/apache/stanbol/enhancer/engines/langdetect/LanguageDetectionEnhancementEngine.java (original)
+++ stanbol/trunk/enhancement-engines/langdetect/src/main/java/org/apache/stanbol/enhancer/engines/langdetect/LanguageDetectionEnhancementEngine.java Tue May 17 22:20:49 2016
@@ -32,10 +32,10 @@ import java.util.Map.Entry;
import java.util.Set;
import org.apache.clerezza.rdf.core.LiteralFactory;
-import org.apache.clerezza.rdf.core.MGraph;
-import org.apache.clerezza.rdf.core.UriRef;
-import org.apache.clerezza.rdf.core.impl.PlainLiteralImpl;
-import org.apache.clerezza.rdf.core.impl.TripleImpl;
+import org.apache.clerezza.commons.rdf.Graph;
+import org.apache.clerezza.commons.rdf.IRI;
+import org.apache.clerezza.commons.rdf.impl.utils.PlainLiteralImpl;
+import org.apache.clerezza.commons.rdf.impl.utils.TripleImpl;
import org.apache.commons.io.IOUtils;
import org.apache.felix.scr.annotations.Component;
import org.apache.felix.scr.annotations.Properties;
@@ -201,7 +201,7 @@ public class LanguageDetectionEnhancemen
}
public void computeEnhancements(ContentItem ci) throws EngineException {
- Entry<UriRef,Blob> contentPart = ContentItemHelper.getBlob(ci, SUPPORTED_MIMTYPES);
+ Entry<IRI,Blob> contentPart = ContentItemHelper.getBlob(ci, SUPPORTED_MIMTYPES);
if(contentPart == null){
throw new IllegalStateException("No ContentPart with Mimetype '"
+ TEXT_PLAIN_MIMETYPE+"' found for ContentItem "+ci.getUri()
@@ -253,13 +253,13 @@ public class LanguageDetectionEnhancemen
// add language to metadata
if (languages != null) {
- MGraph g = ci.getMetadata();
+ Graph g = ci.getMetadata();
ci.getLock().writeLock().lock();
try {
for(int i=0;i<maxSuggestedLanguages && i<languages.size();i++){
// add a hypothesis
Language hypothesis = languages.get(i);
- UriRef textEnhancement = EnhancementEngineHelper.createTextEnhancement(ci, this);
+ IRI textEnhancement = EnhancementEngineHelper.createTextEnhancement(ci, this);
g.add(new TripleImpl(textEnhancement, DC_LANGUAGE, new PlainLiteralImpl(hypothesis.lang)));
g.add(new TripleImpl(textEnhancement, ENHANCER_CONFIDENCE, literalFactory.createTypedLiteral(hypothesis.prob)));
g.add(new TripleImpl(textEnhancement, DC_TYPE, DCTERMS_LINGUISTIC_SYSTEM));
Modified: stanbol/trunk/enhancement-engines/langdetect/src/test/java/org/apache/stanbol/enhancer/engines/langdetect/LanguageDetectionEngineTest.java
URL: http://svn.apache.org/viewvc/stanbol/trunk/enhancement-engines/langdetect/src/test/java/org/apache/stanbol/enhancer/engines/langdetect/LanguageDetectionEngineTest.java?rev=1744328&r1=1744327&r2=1744328&view=diff
==============================================================================
--- stanbol/trunk/enhancement-engines/langdetect/src/test/java/org/apache/stanbol/enhancer/engines/langdetect/LanguageDetectionEngineTest.java (original)
+++ stanbol/trunk/enhancement-engines/langdetect/src/test/java/org/apache/stanbol/enhancer/engines/langdetect/LanguageDetectionEngineTest.java Tue May 17 22:20:49 2016
@@ -30,8 +30,8 @@ import java.util.HashMap;
import org.apache.clerezza.rdf.core.LiteralFactory;
-import org.apache.clerezza.rdf.core.Resource;
-import org.apache.clerezza.rdf.core.UriRef;
+import org.apache.clerezza.commons.rdf.RDFTerm;
+import org.apache.clerezza.commons.rdf.IRI;
import org.apache.commons.io.IOUtils;
import org.apache.stanbol.enhancer.contentitem.inmemory.InMemoryContentItemFactory;
import org.apache.stanbol.enhancer.servicesapi.ContentItem;
@@ -119,7 +119,7 @@ public class LanguageDetectionEngineTest
langIdEngine.activate(context);
ContentItem ci = ciFactory.createContentItem(new StringSource(text));
langIdEngine.computeEnhancements(ci);
- HashMap<UriRef,Resource> expectedValues = new HashMap<UriRef,Resource>();
+ HashMap<IRI,RDFTerm> expectedValues = new HashMap<IRI,RDFTerm>();
expectedValues.put(Properties.ENHANCER_EXTRACTED_FROM, ci.getUri());
expectedValues.put(Properties.DC_CREATOR, LiteralFactory.getInstance().createTypedLiteral(
langIdEngine.getClass().getName()));
Modified: stanbol/trunk/enhancement-engines/langid/src/main/java/org/apache/stanbol/enhancer/engines/langid/LangIdEnhancementEngine.java
URL: http://svn.apache.org/viewvc/stanbol/trunk/enhancement-engines/langid/src/main/java/org/apache/stanbol/enhancer/engines/langid/LangIdEnhancementEngine.java?rev=1744328&r1=1744327&r2=1744328&view=diff
==============================================================================
--- stanbol/trunk/enhancement-engines/langid/src/main/java/org/apache/stanbol/enhancer/engines/langid/LangIdEnhancementEngine.java (original)
+++ stanbol/trunk/enhancement-engines/langid/src/main/java/org/apache/stanbol/enhancer/engines/langid/LangIdEnhancementEngine.java Tue May 17 22:20:49 2016
@@ -27,10 +27,10 @@ import java.util.Map;
import java.util.Map.Entry;
import java.util.Set;
-import org.apache.clerezza.rdf.core.MGraph;
-import org.apache.clerezza.rdf.core.UriRef;
-import org.apache.clerezza.rdf.core.impl.PlainLiteralImpl;
-import org.apache.clerezza.rdf.core.impl.TripleImpl;
+import org.apache.clerezza.commons.rdf.Graph;
+import org.apache.clerezza.commons.rdf.IRI;
+import org.apache.clerezza.commons.rdf.impl.utils.PlainLiteralImpl;
+import org.apache.clerezza.commons.rdf.impl.utils.TripleImpl;
import org.apache.felix.scr.annotations.Component;
import org.apache.felix.scr.annotations.Properties;
import org.apache.felix.scr.annotations.Property;
@@ -134,7 +134,7 @@ public class LangIdEnhancementEngine
}
public void computeEnhancements(ContentItem ci) throws EngineException {
- Entry<UriRef,Blob> contentPart = ContentItemHelper.getBlob(ci, SUPPORTED_MIMTYPES);
+ Entry<IRI,Blob> contentPart = ContentItemHelper.getBlob(ci, SUPPORTED_MIMTYPES);
if(contentPart == null){
throw new IllegalStateException("No ContentPart with Mimetype '"
+ TEXT_PLAIN_MIMETYPE+"' found for ContentItem "+ci.getUri()
@@ -164,10 +164,10 @@ public class LangIdEnhancementEngine
log.info("language identified as " + language);
// add language to metadata
- MGraph g = ci.getMetadata();
+ Graph g = ci.getMetadata();
ci.getLock().writeLock().lock();
try {
- UriRef textEnhancement = EnhancementEngineHelper.createTextEnhancement(ci, this);
+ IRI textEnhancement = EnhancementEngineHelper.createTextEnhancement(ci, this);
g.add(new TripleImpl(textEnhancement, DC_LANGUAGE, new PlainLiteralImpl(language)));
g.add(new TripleImpl(textEnhancement, DC_TYPE, DCTERMS_LINGUISTIC_SYSTEM));
} finally {
Modified: stanbol/trunk/enhancement-engines/langid/src/test/java/org/apache/stanbol/enhancer/engines/langid/LangIdEngineTest.java
URL: http://svn.apache.org/viewvc/stanbol/trunk/enhancement-engines/langid/src/test/java/org/apache/stanbol/enhancer/engines/langid/LangIdEngineTest.java?rev=1744328&r1=1744327&r2=1744328&view=diff
==============================================================================
--- stanbol/trunk/enhancement-engines/langid/src/test/java/org/apache/stanbol/enhancer/engines/langid/LangIdEngineTest.java (original)
+++ stanbol/trunk/enhancement-engines/langid/src/test/java/org/apache/stanbol/enhancer/engines/langid/LangIdEngineTest.java Tue May 17 22:20:49 2016
@@ -28,8 +28,8 @@ import java.util.HashMap;
import org.apache.clerezza.rdf.core.LiteralFactory;
-import org.apache.clerezza.rdf.core.Resource;
-import org.apache.clerezza.rdf.core.UriRef;
+import org.apache.clerezza.commons.rdf.RDFTerm;
+import org.apache.clerezza.commons.rdf.IRI;
import org.apache.commons.io.IOUtils;
import org.apache.stanbol.enhancer.contentitem.inmemory.InMemoryContentItemFactory;
import org.apache.stanbol.enhancer.engines.langid.LangIdEnhancementEngine;
@@ -98,7 +98,7 @@ public class LangIdEngineTest {
langIdEngine.activate(context);
ContentItem ci = ciFactory.createContentItem(new StringSource(text));
langIdEngine.computeEnhancements(ci);
- HashMap<UriRef,Resource> expectedValues = new HashMap<UriRef,Resource>();
+ HashMap<IRI,RDFTerm> expectedValues = new HashMap<IRI,RDFTerm>();
expectedValues.put(Properties.ENHANCER_EXTRACTED_FROM, ci.getUri());
expectedValues.put(Properties.DC_CREATOR, LiteralFactory.getInstance().createTypedLiteral(
langIdEngine.getClass().getName()));
Modified: stanbol/trunk/enhancement-engines/lucenefstlinking/src/main/java/org/apache/stanbol/enhancer/engines/lucenefstlinking/FstLinkingEngine.java
URL: http://svn.apache.org/viewvc/stanbol/trunk/enhancement-engines/lucenefstlinking/src/main/java/org/apache/stanbol/enhancer/engines/lucenefstlinking/FstLinkingEngine.java?rev=1744328&r1=1744327&r2=1744328&view=diff
==============================================================================
--- stanbol/trunk/enhancement-engines/lucenefstlinking/src/main/java/org/apache/stanbol/enhancer/engines/lucenefstlinking/FstLinkingEngine.java (original)
+++ stanbol/trunk/enhancement-engines/lucenefstlinking/src/main/java/org/apache/stanbol/enhancer/engines/lucenefstlinking/FstLinkingEngine.java Tue May 17 22:20:49 2016
@@ -39,14 +39,14 @@ import java.util.NavigableMap;
import java.util.Set;
import java.util.TreeMap;
-import org.apache.clerezza.rdf.core.Language;
-import org.apache.clerezza.rdf.core.Literal;
+import org.apache.clerezza.commons.rdf.Language;
+import org.apache.clerezza.commons.rdf.Literal;
import org.apache.clerezza.rdf.core.LiteralFactory;
-import org.apache.clerezza.rdf.core.MGraph;
-import org.apache.clerezza.rdf.core.Triple;
-import org.apache.clerezza.rdf.core.UriRef;
-import org.apache.clerezza.rdf.core.impl.PlainLiteralImpl;
-import org.apache.clerezza.rdf.core.impl.TripleImpl;
+import org.apache.clerezza.commons.rdf.Graph;
+import org.apache.clerezza.commons.rdf.Triple;
+import org.apache.clerezza.commons.rdf.IRI;
+import org.apache.clerezza.commons.rdf.impl.utils.PlainLiteralImpl;
+import org.apache.clerezza.commons.rdf.impl.utils.TripleImpl;
import org.apache.commons.io.input.CharSequenceReader;
import org.apache.commons.lang.StringUtils;
import org.apache.lucene.analysis.TokenStream;
@@ -89,9 +89,9 @@ public class FstLinkingEngine implements
private static final Map<String,Object> SERVICE_PROPERTIES = Collections.unmodifiableMap(Collections
.singletonMap(ServiceProperties.ENHANCEMENT_ENGINE_ORDERING, (Object) ENGINE_ORDERING));
- private static final UriRef ENHANCER_ENTITY_RANKING = new UriRef(NamespaceEnum.fise + "entity-ranking");
+ private static final IRI ENHANCER_ENTITY_RANKING = new IRI(NamespaceEnum.fise + "entity-ranking");
- public static final UriRef FISE_ORIGIN = new UriRef(NamespaceEnum.fise + "origin");
+ public static final IRI FISE_ORIGIN = new IRI(NamespaceEnum.fise + "origin");
private final LiteralFactory literalFactory = LiteralFactory.getInstance();
@@ -419,7 +419,7 @@ public class FstLinkingEngine implements
* @param neTypes the types of the named entity
* @return
*/
- private boolean filterByNamedEntityType(Iterator<UriRef> eTypes, Set<String> neTypes) {
+ private boolean filterByNamedEntityType(Iterator<IRI> eTypes, Set<String> neTypes) {
//first collect the allowed entity types
Set<String> entityTypes = new HashSet<String>();
for(String neType : neTypes){
@@ -440,7 +440,7 @@ public class FstLinkingEngine implements
}
//second check the actual entity types against the allowed
while(eTypes.hasNext()){
- UriRef typeUri = eTypes.next();
+ IRI typeUri = eTypes.next();
if(typeUri != null && entityTypes.contains(typeUri.getUnicodeString())){
return false; //we found an match .. do not filter
}
@@ -454,13 +454,13 @@ public class FstLinkingEngine implements
* @param entityTypes
* @return
*/
- private boolean filterEntityByType(Iterator<UriRef> entityTypes){
- Map<UriRef, Integer> whiteList = elConfig.getWhitelistedTypes();
- Map<UriRef, Integer> blackList = elConfig.getBlacklistedTypes();
+ private boolean filterEntityByType(Iterator<IRI> entityTypes){
+ Map<IRI, Integer> whiteList = elConfig.getWhitelistedTypes();
+ Map<IRI, Integer> blackList = elConfig.getBlacklistedTypes();
Integer w = null;
Integer b = null;
while(entityTypes.hasNext()){
- UriRef type = entityTypes.next();
+ IRI type = entityTypes.next();
Integer act = whiteList.get(type);
if(act != null){
if(w == null || act.compareTo(w) < 0){
@@ -670,20 +670,20 @@ public class FstLinkingEngine implements
languageObject = new Language(language);
}
- MGraph metadata = ci.getMetadata();
+ Graph metadata = ci.getMetadata();
for(Tag tag : tags){
- Collection<UriRef> textAnnotations = new ArrayList<UriRef>(tags.size());
+ Collection<IRI> textAnnotations = new ArrayList<IRI>(tags.size());
//first create the TextAnnotations for the Occurrences
Literal startLiteral = literalFactory.createTypedLiteral(tag.getStart());
Literal endLiteral = literalFactory.createTypedLiteral(tag.getEnd());
//search for existing text annotation
Iterator<Triple> it = metadata.filter(null, ENHANCER_START, startLiteral);
- UriRef textAnnotation = null;
+ IRI textAnnotation = null;
while(it.hasNext()){
Triple t = it.next();
if(metadata.filter(t.getSubject(), ENHANCER_END, endLiteral).hasNext() &&
metadata.filter(t.getSubject(), RDF_TYPE, ENHANCER_TEXTANNOTATION).hasNext()){
- textAnnotation = (UriRef)t.getSubject();
+ textAnnotation = (IRI)t.getSubject();
break;
}
}
@@ -710,20 +710,20 @@ public class FstLinkingEngine implements
new PlainLiteralImpl(this.getClass().getName())));
}
//add dc:types (even to existing)
- for(UriRef dcType : getDcTypes(tag.getSuggestions())){
+ for(IRI dcType : getDcTypes(tag.getSuggestions())){
metadata.add(new TripleImpl(
textAnnotation, Properties.DC_TYPE, dcType));
}
textAnnotations.add(textAnnotation);
//now the EntityAnnotations for the Suggestions
for(Match match : tag.getSuggestions()){
- UriRef entityAnnotation = EnhancementEngineHelper.createEntityEnhancement(ci, this);
+ IRI entityAnnotation = EnhancementEngineHelper.createEntityEnhancement(ci, this);
//should we use the label used for the match, or search the
//representation for the best label ... currently its the matched one
metadata.add(new TripleImpl(entityAnnotation, Properties.ENHANCER_ENTITY_LABEL, match.getMatchLabel()));
metadata.add(new TripleImpl(entityAnnotation,ENHANCER_ENTITY_REFERENCE,
- new UriRef(match.getUri())));
- for(UriRef type : match.getTypes()){
+ new IRI(match.getUri())));
+ for(IRI type : match.getTypes()){
metadata.add(new TripleImpl(entityAnnotation,
Properties.ENHANCER_ENTITY_TYPE, type));
}
@@ -736,8 +736,8 @@ public class FstLinkingEngine implements
metadata.add(new TripleImpl(entityAnnotation, FISE_ORIGIN, indexConfig.getOrigin()));
}
//TODO: add origin information of the EntiySearcher
-// for(Entry<UriRef,Collection<Resource>> originInfo : entitySearcher.getOriginInformation().entrySet()){
-// for(Resource value : originInfo.getValue()){
+// for(Entry<IRI,Collection<RDFTerm>> originInfo : entitySearcher.getOriginInformation().entrySet()){
+// for(RDFTerm value : originInfo.getValue()){
// metadata.add(new TripleImpl(entityAnnotation,
// originInfo.getKey(),value));
// }
@@ -773,11 +773,11 @@ public class FstLinkingEngine implements
* @param conceptTypes The list of suggestions
* @return the types values for the {@link LinkedEntity}
*/
- private Set<UriRef> getDcTypes(List<Match> matches){
+ private Set<IRI> getDcTypes(List<Match> matches){
if(matches == null || matches.isEmpty()){
return Collections.emptySet();
}
- Collection<UriRef> conceptTypes = new HashSet<UriRef>();
+ Collection<IRI> conceptTypes = new HashSet<IRI>();
double score = -1; //only consider types of the best ranked Entities
for(Match match : matches){
double actScore = match.getScore();
@@ -785,13 +785,13 @@ public class FstLinkingEngine implements
break;
}
score = actScore;
- for(Iterator<UriRef> types = match.getTypes().iterator();
+ for(Iterator<IRI> types = match.getTypes().iterator();
types.hasNext(); conceptTypes.add(types.next()));
}
- Map<UriRef,UriRef> typeMappings = elConfig.getTypeMappings();
- Set<UriRef> dcTypes = new HashSet<UriRef>();
- for(UriRef conceptType : conceptTypes){
- UriRef dcType = typeMappings.get(conceptType);
+ Map<IRI,IRI> typeMappings = elConfig.getTypeMappings();
+ Set<IRI> dcTypes = new HashSet<IRI>();
+ for(IRI conceptType : conceptTypes){
+ IRI dcType = typeMappings.get(conceptType);
if(dcType != null){
dcTypes.add(dcType);
}
Modified: stanbol/trunk/enhancement-engines/lucenefstlinking/src/main/java/org/apache/stanbol/enhancer/engines/lucenefstlinking/FstLinkingEngineComponent.java
URL: http://svn.apache.org/viewvc/stanbol/trunk/enhancement-engines/lucenefstlinking/src/main/java/org/apache/stanbol/enhancer/engines/lucenefstlinking/FstLinkingEngineComponent.java?rev=1744328&r1=1744327&r2=1744328&view=diff
==============================================================================
--- stanbol/trunk/enhancement-engines/lucenefstlinking/src/main/java/org/apache/stanbol/enhancer/engines/lucenefstlinking/FstLinkingEngineComponent.java (original)
+++ stanbol/trunk/enhancement-engines/lucenefstlinking/src/main/java/org/apache/stanbol/enhancer/engines/lucenefstlinking/FstLinkingEngineComponent.java Tue May 17 22:20:49 2016
@@ -48,10 +48,10 @@ import java.util.concurrent.ExecutorServ
import java.util.concurrent.Executors;
import java.util.concurrent.Future;
-import org.apache.clerezza.rdf.core.Literal;
-import org.apache.clerezza.rdf.core.Resource;
-import org.apache.clerezza.rdf.core.UriRef;
-import org.apache.clerezza.rdf.core.impl.PlainLiteralImpl;
+import org.apache.clerezza.commons.rdf.Literal;
+import org.apache.clerezza.commons.rdf.RDFTerm;
+import org.apache.clerezza.commons.rdf.IRI;
+import org.apache.clerezza.commons.rdf.impl.utils.PlainLiteralImpl;
import org.apache.commons.io.FileUtils;
import org.apache.commons.io.FilenameUtils;
import org.apache.commons.lang.StringUtils;
@@ -177,7 +177,7 @@ public class FstLinkingEngineComponent {
* The origin information for all Entities provided by the configured SolrCore and
* FST. Origin information are added to all <code>fise:EntityAnnotation</code>
* by using the <code>fise:origin</code> property. Configured values can be both
- * {@link UriRef URI}s or {@link Literal}s. Configured Strings are checked if
+ * {@link IRI URI}s or {@link Literal}s. Configured Strings are checked if
* they are valid {@link URI}s and {@link URI#isAbsolute() absolute}. If not
* a {@link Literal} is parsed.
*/
@@ -240,7 +240,7 @@ public class FstLinkingEngineComponent {
/**
* The origin information of Entities.
*/
- private Resource origin;
+ private RDFTerm origin;
/**
* used to resolve '{prefix}:{local-name}' used within the engines configuration
@@ -470,13 +470,13 @@ public class FstLinkingEngineComponent {
//(4) parse Origin information
value = properties.get(ORIGIN);
- if(value instanceof Resource){
- origin = (Resource)origin;
+ if(value instanceof RDFTerm){
+ origin = (RDFTerm)origin;
} else if (value instanceof String){
try {
URI originUri = new URI((String)value);
if(originUri.isAbsolute()){
- origin = new UriRef((String)value);
+ origin = new IRI((String)value);
} else {
origin = new PlainLiteralImpl((String)value);
}
@@ -485,7 +485,7 @@ public class FstLinkingEngineComponent {
}
log.info(" - origin: {}", origin);
} else if(value != null){
- log.warn("Values of the {} property MUST BE of type Resource or String "
+ log.warn("Values of the {} property MUST BE of type RDFTerm or String "
+ "(parsed: {} (type:{}))", new Object[]{ORIGIN,value,value.getClass()});
} //else no ORIGIN information provided
Modified: stanbol/trunk/enhancement-engines/lucenefstlinking/src/main/java/org/apache/stanbol/enhancer/engines/lucenefstlinking/IndexConfiguration.java
URL: http://svn.apache.org/viewvc/stanbol/trunk/enhancement-engines/lucenefstlinking/src/main/java/org/apache/stanbol/enhancer/engines/lucenefstlinking/IndexConfiguration.java?rev=1744328&r1=1744327&r2=1744328&view=diff
==============================================================================
--- stanbol/trunk/enhancement-engines/lucenefstlinking/src/main/java/org/apache/stanbol/enhancer/engines/lucenefstlinking/IndexConfiguration.java (original)
+++ stanbol/trunk/enhancement-engines/lucenefstlinking/src/main/java/org/apache/stanbol/enhancer/engines/lucenefstlinking/IndexConfiguration.java Tue May 17 22:20:49 2016
@@ -30,9 +30,9 @@ import java.util.concurrent.ExecutorServ
import java.util.concurrent.locks.ReadWriteLock;
import java.util.concurrent.locks.ReentrantReadWriteLock;
-import org.apache.clerezza.rdf.core.Literal;
-import org.apache.clerezza.rdf.core.Resource;
-import org.apache.clerezza.rdf.core.UriRef;
+import org.apache.clerezza.commons.rdf.Literal;
+import org.apache.clerezza.commons.rdf.RDFTerm;
+import org.apache.clerezza.commons.rdf.IRI;
import org.apache.commons.io.FileUtils;
import org.apache.commons.io.FilenameUtils;
import org.apache.commons.io.filefilter.WildcardFileFilter;
@@ -125,10 +125,10 @@ public class IndexConfiguration {
/**
* The origin is added to <code>fise:TextAnnotation</code> created for
* linked Entities. It is intended to be used for providing a reference to
- * dataset of the Entity. Both {@link UriRef URI}s and {@link Literal}s can
+ * dataset of the Entity. Both {@link IRI URI}s and {@link Literal}s can
* be used here
*/
- private Resource origin;
+ private RDFTerm origin;
/**
* If alternate tokens (<code>posInc == 0</code>) can be skipped or if such
@@ -421,7 +421,7 @@ public class IndexConfiguration {
this.fstDirectory = fstDirectory;
}
- public void setOrigin(Resource origin) {
+ public void setOrigin(RDFTerm origin) {
this.origin = origin;
}
/**
@@ -434,7 +434,7 @@ public class IndexConfiguration {
*
* @return the origin or <code>null</code> if none is configured
*/
- public Resource getOrigin() {
+ public RDFTerm getOrigin() {
return origin;
}
Modified: stanbol/trunk/enhancement-engines/lucenefstlinking/src/main/java/org/apache/stanbol/enhancer/engines/lucenefstlinking/Match.java
URL: http://svn.apache.org/viewvc/stanbol/trunk/enhancement-engines/lucenefstlinking/src/main/java/org/apache/stanbol/enhancer/engines/lucenefstlinking/Match.java?rev=1744328&r1=1744327&r2=1744328&view=diff
==============================================================================
--- stanbol/trunk/enhancement-engines/lucenefstlinking/src/main/java/org/apache/stanbol/enhancer/engines/lucenefstlinking/Match.java (original)
+++ stanbol/trunk/enhancement-engines/lucenefstlinking/src/main/java/org/apache/stanbol/enhancer/engines/lucenefstlinking/Match.java Tue May 17 22:20:49 2016
@@ -22,8 +22,8 @@ import java.util.Collections;
import java.util.Comparator;
import java.util.Map;
-import org.apache.clerezza.rdf.core.Literal;
-import org.apache.clerezza.rdf.core.UriRef;
+import org.apache.clerezza.commons.rdf.Literal;
+import org.apache.clerezza.commons.rdf.IRI;
import org.apache.stanbol.enhancer.engines.entitylinking.impl.Suggestion;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
@@ -77,11 +77,11 @@ public class Match {
return getValues(FieldType.label);
}
- public Collection<UriRef> getTypes(){
+ public Collection<IRI> getTypes(){
return getValues(FieldType.type);
}
- public Collection<UriRef> getRedirects(){
+ public Collection<IRI> getRedirects(){
return getValues(FieldType.redirect);
}
public Double getRanking(){
@@ -157,8 +157,8 @@ public class Match {
static enum FieldType {
id(String.class),
label(Literal.class, true),
- type(UriRef.class,true),
- redirect(UriRef.class,true),
+ type(IRI.class,true),
+ redirect(IRI.class,true),
ranking(Double.class);
Class<?> valueType;
Modified: stanbol/trunk/enhancement-engines/lucenefstlinking/src/main/java/org/apache/stanbol/enhancer/engines/lucenefstlinking/TaggingSession.java
URL: http://svn.apache.org/viewvc/stanbol/trunk/enhancement-engines/lucenefstlinking/src/main/java/org/apache/stanbol/enhancer/engines/lucenefstlinking/TaggingSession.java?rev=1744328&r1=1744327&r2=1744328&view=diff
==============================================================================
--- stanbol/trunk/enhancement-engines/lucenefstlinking/src/main/java/org/apache/stanbol/enhancer/engines/lucenefstlinking/TaggingSession.java (original)
+++ stanbol/trunk/enhancement-engines/lucenefstlinking/src/main/java/org/apache/stanbol/enhancer/engines/lucenefstlinking/TaggingSession.java Tue May 17 22:20:49 2016
@@ -33,10 +33,10 @@ import java.util.concurrent.Future;
import java.util.concurrent.TimeUnit;
import java.util.concurrent.TimeoutException;
-import org.apache.clerezza.rdf.core.Language;
-import org.apache.clerezza.rdf.core.Literal;
-import org.apache.clerezza.rdf.core.UriRef;
-import org.apache.clerezza.rdf.core.impl.PlainLiteralImpl;
+import org.apache.clerezza.commons.rdf.Language;
+import org.apache.clerezza.commons.rdf.Literal;
+import org.apache.clerezza.commons.rdf.IRI;
+import org.apache.clerezza.commons.rdf.impl.utils.PlainLiteralImpl;
import org.apache.commons.lang.StringUtils;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.document.Document;
@@ -572,17 +572,17 @@ public class TaggingSession implements C
values.put(FieldType.label, labels);
//load the types
if(typeField != null){
- Set<UriRef> types = new HashSet<UriRef>();
+ Set<IRI> types = new HashSet<IRI>();
for(String type : doc.getValues(typeField)){
- types.add(new UriRef(type));
+ types.add(new IRI(type));
}
values.put(FieldType.type, types);
}
//load the redirects
if(redirectField != null){
- Set<UriRef> redirects = new HashSet<UriRef>();
+ Set<IRI> redirects = new HashSet<IRI>();
for(String redirect : doc.getValues(redirectField)){
- redirects.add(new UriRef(redirect));
+ redirects.add(new IRI(redirect));
}
values.put(FieldType.redirect, redirects);
}
Modified: stanbol/trunk/enhancement-engines/lucenefstlinking/src/test/java/org/apache/stanbol/enhancer/engines/lucenefstlinking/FstLinkingEngineTest.java
URL: http://svn.apache.org/viewvc/stanbol/trunk/enhancement-engines/lucenefstlinking/src/test/java/org/apache/stanbol/enhancer/engines/lucenefstlinking/FstLinkingEngineTest.java?rev=1744328&r1=1744327&r2=1744328&view=diff
==============================================================================
--- stanbol/trunk/enhancement-engines/lucenefstlinking/src/test/java/org/apache/stanbol/enhancer/engines/lucenefstlinking/FstLinkingEngineTest.java (original)
+++ stanbol/trunk/enhancement-engines/lucenefstlinking/src/test/java/org/apache/stanbol/enhancer/engines/lucenefstlinking/FstLinkingEngineTest.java Tue May 17 22:20:49 2016
@@ -48,13 +48,13 @@ import java.util.concurrent.Future;
import java.util.concurrent.TimeUnit;
import java.util.concurrent.TimeoutException;
-import org.apache.clerezza.rdf.core.Literal;
+import org.apache.clerezza.commons.rdf.Literal;
import org.apache.clerezza.rdf.core.LiteralFactory;
-import org.apache.clerezza.rdf.core.Resource;
-import org.apache.clerezza.rdf.core.Triple;
-import org.apache.clerezza.rdf.core.UriRef;
-import org.apache.clerezza.rdf.core.impl.PlainLiteralImpl;
-import org.apache.clerezza.rdf.core.impl.TripleImpl;
+import org.apache.clerezza.commons.rdf.RDFTerm;
+import org.apache.clerezza.commons.rdf.Triple;
+import org.apache.clerezza.commons.rdf.IRI;
+import org.apache.clerezza.commons.rdf.impl.utils.PlainLiteralImpl;
+import org.apache.clerezza.commons.rdf.impl.utils.TripleImpl;
import org.apache.solr.client.solrj.SolrServer;
import org.apache.solr.client.solrj.embedded.EmbeddedSolrServer;
import org.apache.solr.core.SolrCore;
@@ -158,9 +158,9 @@ public class FstLinkingEngineTest {
* Used with the {@link EnhancementStructureHelper} to validate Enhancement
* results
*/
- private static Map<UriRef,Resource> EXPECTED_ENHANCEMENT_VALUES;
+ private static Map<IRI,RDFTerm> EXPECTED_ENHANCEMENT_VALUES;
static{
- EXPECTED_ENHANCEMENT_VALUES = new HashMap<UriRef,Resource>();
+ EXPECTED_ENHANCEMENT_VALUES = new HashMap<IRI,RDFTerm>();
EXPECTED_ENHANCEMENT_VALUES.put(DC_CREATOR, LiteralFactory.getInstance().createTypedLiteral(
FstLinkingEngine.class.getName()));
//adding null as expected for confidence makes it a required property
@@ -346,13 +346,13 @@ public class FstLinkingEngineTest {
//iterate over all fise:TextAnnotations
//NOTE this assumes all textAnnotations are from the FST linking engine
log.info(" ... validated fise:TextAnnotations:");
- Map<UriRef,Resource> expected = new HashMap<UriRef,Resource>(EXPECTED_ENHANCEMENT_VALUES);
+ Map<IRI,RDFTerm> expected = new HashMap<IRI,RDFTerm>(EXPECTED_ENHANCEMENT_VALUES);
expected.put(ENHANCER_EXTRACTED_FROM, ci.getUri());
int[] num = new int[]{0,0};
Iterator<Triple> textAnnotations = ci.getMetadata().filter(
null, Properties.RDF_TYPE, TechnicalClasses.ENHANCER_TEXTANNOTATION);
while(textAnnotations.hasNext()){
- UriRef textAnnotation = (UriRef)textAnnotations.next().getSubject();
+ IRI textAnnotation = (IRI)textAnnotations.next().getSubject();
//validate this test annotation against the Stanbol EnhancementStructure
EnhancementStructureHelper.validateTextAnnotation(
ci.getMetadata(), textAnnotation, content, expected);
@@ -374,11 +374,11 @@ public class FstLinkingEngineTest {
Iterator<Triple> entityAnnotations = ci.getMetadata().filter(
null, Properties.RDF_TYPE, TechnicalClasses.ENHANCER_ENTITYANNOTATION);
while(entityAnnotations.hasNext()){
- UriRef entityAnnotation = (UriRef)entityAnnotations.next().getSubject();
+ IRI entityAnnotation = (IRI)entityAnnotations.next().getSubject();
//validate this test annotation against the Stanbol EnhancementStructure
EnhancementStructureHelper.validateEntityAnnotation(
ci.getMetadata(), entityAnnotation, expected);
- UriRef entityUri = EnhancementEngineHelper.getReference(
+ IRI entityUri = EnhancementEngineHelper.getReference(
ci.getMetadata(), entityAnnotation, Properties.ENHANCER_ENTITY_REFERENCE);
log.info(" {}. {}",num[1]+1,entityUri);
Assert.assertNotNull(entityUri);
Modified: stanbol/trunk/enhancement-engines/metaxa/src/main/java/org/apache/stanbol/enhancer/engines/metaxa/MetaxaEngine.java
URL: http://svn.apache.org/viewvc/stanbol/trunk/enhancement-engines/metaxa/src/main/java/org/apache/stanbol/enhancer/engines/metaxa/MetaxaEngine.java?rev=1744328&r1=1744327&r2=1744328&view=diff
==============================================================================
--- stanbol/trunk/enhancement-engines/metaxa/src/main/java/org/apache/stanbol/enhancer/engines/metaxa/MetaxaEngine.java (original)
+++ stanbol/trunk/enhancement-engines/metaxa/src/main/java/org/apache/stanbol/enhancer/engines/metaxa/MetaxaEngine.java Tue May 17 22:20:49 2016
@@ -30,15 +30,15 @@ import java.util.HashSet;
import java.util.Map;
import java.util.Set;
-import org.apache.clerezza.rdf.core.BNode;
-import org.apache.clerezza.rdf.core.MGraph;
-import org.apache.clerezza.rdf.core.NonLiteral;
-import org.apache.clerezza.rdf.core.Resource;
-import org.apache.clerezza.rdf.core.Triple;
-import org.apache.clerezza.rdf.core.UriRef;
-import org.apache.clerezza.rdf.core.impl.PlainLiteralImpl;
-import org.apache.clerezza.rdf.core.impl.SimpleMGraph;
-import org.apache.clerezza.rdf.core.impl.TripleImpl;
+import org.apache.clerezza.commons.rdf.BlankNode;
+import org.apache.clerezza.commons.rdf.Graph;
+import org.apache.clerezza.commons.rdf.BlankNodeOrIRI;
+import org.apache.clerezza.commons.rdf.RDFTerm;
+import org.apache.clerezza.commons.rdf.Triple;
+import org.apache.clerezza.commons.rdf.IRI;
+import org.apache.clerezza.commons.rdf.impl.utils.PlainLiteralImpl;
+import org.apache.clerezza.commons.rdf.impl.utils.simple.SimpleGraph;
+import org.apache.clerezza.commons.rdf.impl.utils.TripleImpl;
import org.apache.clerezza.rdf.core.impl.TypedLiteralImpl;
import org.apache.commons.io.IOUtils;
import org.apache.felix.scr.annotations.Component;
@@ -98,7 +98,7 @@ public class MetaxaEngine
/**
* Plain text content of a content item.
*/
- public static final UriRef NIE_PLAINTEXTCONTENT = new UriRef(NamespaceEnum.nie + "plainTextContent");
+ public static final IRI NIE_PLAINTEXTCONTENT = new IRI(NamespaceEnum.nie + "plainTextContent");
private static final URIImpl NIE_PLAINTEXT_PROPERTY = new URIImpl(NIE_PLAINTEXTCONTENT.getUnicodeString());
/**
* The default value for the Execution of this Engine. Currently set to
@@ -230,7 +230,7 @@ public class MetaxaEngine
} finally {
ci.getLock().readLock().unlock();
}
- // Convert the RDF2go model to a Clerezza Graph and also extract
+ // Convert the RDF2go model to a Clerezza ImmutableGraph and also extract
// the extracted plain text from the model
if (null == m) {
log.debug("Unable to preocess ContentItem {} (mime type {}) with Metaxa",
@@ -245,14 +245,14 @@ public class MetaxaEngine
throw new EngineException("Unable to initialise Blob for storing" +
"the plain text content",e);
}
- HashMap<BlankNode, BNode> blankNodeMap = new HashMap<BlankNode, BNode>();
+ HashMap<BlankNode, BlankNode> blankNodeMap = new HashMap<BlankNode, BlankNode>();
RDF2GoUtils.urifyBlankNodes(m);
ClosableIterator<Statement> it = m.iterator();
BufferedWriter out = new BufferedWriter(new OutputStreamWriter(
plainTextSink.getOutputStream(), UTF8));
boolean textExtracted = false; //used to detect if some text was extracted
try {
- MGraph g = new SimpleMGraph(); //first add to a temporary graph
+ Graph g = new SimpleGraph(); //first add to a temporary graph
while (it.hasNext()) {
Statement oneStmt = it.next();
//we need to treat triples that provide the plain/text
@@ -271,16 +271,16 @@ public class MetaxaEngine
}
textExtracted = true;
if (includeText) {
- NonLiteral subject = (NonLiteral) asClerezzaResource(oneStmt.getSubject(), blankNodeMap);
- UriRef predicate = (UriRef) asClerezzaResource(oneStmt.getPredicate(), blankNodeMap);
- Resource object = asClerezzaResource(oneStmt.getObject(), blankNodeMap);
+ BlankNodeOrIRI subject = (BlankNodeOrIRI) asClerezzaResource(oneStmt.getSubject(), blankNodeMap);
+ IRI predicate = (IRI) asClerezzaResource(oneStmt.getPredicate(), blankNodeMap);
+ RDFTerm object = asClerezzaResource(oneStmt.getObject(), blankNodeMap);
g.add(new TripleImpl(subject, predicate, object));
}
}
} else { //add metadata to the metadata of the contentItem
- NonLiteral subject = (NonLiteral) asClerezzaResource(oneStmt.getSubject(), blankNodeMap);
- UriRef predicate = (UriRef) asClerezzaResource(oneStmt.getPredicate(), blankNodeMap);
- Resource object = asClerezzaResource(oneStmt.getObject(), blankNodeMap);
+ BlankNodeOrIRI subject = (BlankNodeOrIRI) asClerezzaResource(oneStmt.getSubject(), blankNodeMap);
+ IRI predicate = (IRI) asClerezzaResource(oneStmt.getPredicate(), blankNodeMap);
+ RDFTerm object = asClerezzaResource(oneStmt.getObject(), blankNodeMap);
if (null != subject && null != predicate && null != object) {
Triple t = new TripleImpl(subject, predicate, object);
@@ -304,7 +304,7 @@ public class MetaxaEngine
}
if(textExtracted){
//add plain text to the content item
- UriRef blobUri = new UriRef("urn:metaxa:plain-text:"+randomUUID());
+ IRI blobUri = new IRI("urn:metaxa:plain-text:"+randomUUID());
ci.addPart(blobUri, plainTextSink.getBlob());
}
}
@@ -313,22 +313,22 @@ public class MetaxaEngine
* Converts the given RDF2Go node into a corresponding Clerezza object.
*
* @param node a {@link Node}
- * @return a {@link Resource}
+ * @return a {@link RDFTerm}
*/
- public static Resource asClerezzaResource(Node node, HashMap<BlankNode, BNode> blankNodeMap) {
+ public static RDFTerm asClerezzaResource(Node node, HashMap<BlankNode, BlankNode> blankNodeMap) {
if (node instanceof URI) {
- return new UriRef(node.asURI().toString());
+ return new IRI(node.asURI().toString());
} else if (node instanceof BlankNode) {
- BNode bNode = blankNodeMap.get(node);
+ BlankNode bNode = blankNodeMap.get(node);
if (bNode == null) {
- bNode = new BNode();
+ bNode = new BlankNode();
blankNodeMap.put(node.asBlankNode(), bNode);
}
return bNode;
} else if (node instanceof DatatypeLiteral) {
DatatypeLiteral dtl = node.asDatatypeLiteral();
- return new TypedLiteralImpl(dtl.getValue(), new UriRef(dtl.getDatatype().asURI().toString()));
+ return new TypedLiteralImpl(dtl.getValue(), new IRI(dtl.getDatatype().asURI().toString()));
} else if (node instanceof PlainLiteral) {
return new PlainLiteralImpl(node.asLiteral().getValue());
}
Modified: stanbol/trunk/enhancement-engines/metaxa/src/main/java/org/apache/stanbol/enhancer/engines/metaxa/core/RDF2GoUtils.java
URL: http://svn.apache.org/viewvc/stanbol/trunk/enhancement-engines/metaxa/src/main/java/org/apache/stanbol/enhancer/engines/metaxa/core/RDF2GoUtils.java?rev=1744328&r1=1744327&r2=1744328&view=diff
==============================================================================
--- stanbol/trunk/enhancement-engines/metaxa/src/main/java/org/apache/stanbol/enhancer/engines/metaxa/core/RDF2GoUtils.java (original)
+++ stanbol/trunk/enhancement-engines/metaxa/src/main/java/org/apache/stanbol/enhancer/engines/metaxa/core/RDF2GoUtils.java Tue May 17 22:20:49 2016
@@ -27,7 +27,7 @@ import org.ontoware.rdf2go.model.impl.Di
import org.ontoware.rdf2go.model.impl.URIGenerator;
import org.ontoware.rdf2go.model.node.BlankNode;
import org.ontoware.rdf2go.model.node.Node;
-import org.ontoware.rdf2go.model.node.Resource;
+import org.ontoware.rdf2go.model.node.RDFTerm;
import org.ontoware.rdf2go.model.node.URI;
/**
@@ -45,7 +45,7 @@ public class RDF2GoUtils {
Model remove = RDF2Go.getModelFactory().createModel();
remove.open();
for (Statement stmt : model) {
- Resource subj = stmt.getSubject();
+ RDFTerm subj = stmt.getSubject();
URI pred = stmt.getPredicate();
Node obj = stmt.getObject();
boolean match = false;
Modified: stanbol/trunk/enhancement-engines/metaxa/src/main/java/org/apache/stanbol/enhancer/engines/metaxa/core/html/BundleURIResolver.java
URL: http://svn.apache.org/viewvc/stanbol/trunk/enhancement-engines/metaxa/src/main/java/org/apache/stanbol/enhancer/engines/metaxa/core/html/BundleURIResolver.java?rev=1744328&r1=1744327&r2=1744328&view=diff
==============================================================================
--- stanbol/trunk/enhancement-engines/metaxa/src/main/java/org/apache/stanbol/enhancer/engines/metaxa/core/html/BundleURIResolver.java (original)
+++ stanbol/trunk/enhancement-engines/metaxa/src/main/java/org/apache/stanbol/enhancer/engines/metaxa/core/html/BundleURIResolver.java Tue May 17 22:20:49 2016
@@ -55,7 +55,7 @@ public class BundleURIResolver implement
String path = baseURI.getPath();
resource = path.substring(1, path.lastIndexOf('/') + 1) + href;
newUrl = BUNDLE.getEntry(resource);
- LOG.debug("Resource: " + resource);
+ LOG.debug("RDFTerm: " + resource);
if (newUrl != null) {
return new StreamSource(newUrl.openStream(), newUrl.toString());
} else {
Modified: stanbol/trunk/enhancement-engines/metaxa/src/main/java/org/apache/stanbol/enhancer/engines/metaxa/core/mp3/MP3FileExtractor.java
URL: http://svn.apache.org/viewvc/stanbol/trunk/enhancement-engines/metaxa/src/main/java/org/apache/stanbol/enhancer/engines/metaxa/core/mp3/MP3FileExtractor.java?rev=1744328&r1=1744327&r2=1744328&view=diff
==============================================================================
--- stanbol/trunk/enhancement-engines/metaxa/src/main/java/org/apache/stanbol/enhancer/engines/metaxa/core/mp3/MP3FileExtractor.java (original)
+++ stanbol/trunk/enhancement-engines/metaxa/src/main/java/org/apache/stanbol/enhancer/engines/metaxa/core/mp3/MP3FileExtractor.java Tue May 17 22:20:49 2016
@@ -21,7 +21,7 @@ import java.io.IOException;
import java.nio.charset.Charset;
import org.ontoware.rdf2go.model.Model;
-import org.ontoware.rdf2go.model.node.Resource;
+import org.ontoware.rdf2go.model.node.RDFTerm;
import org.ontoware.rdf2go.model.node.URI;
import org.ontoware.rdf2go.vocabulary.RDF;
import org.semanticdesktop.aperture.extractor.AbstractFileExtractor;
@@ -112,7 +112,7 @@ public class MP3FileExtractor extends Ab
protected void addSimpleContact(URI property, String fullname, RDFContainer container) {
Model model = container.getModel();
- Resource resource = ModelUtil.generateRandomResource(model);
+ RDFTerm resource = ModelUtil.generateRandomResource(model);
model.addStatement(resource, RDF.type, NCO.Contact);
model.addStatement(resource, NCO.fullname, fullname);
model.addStatement(container.getDescribedUri(), property, resource);
Modified: stanbol/trunk/enhancement-engines/metaxa/src/test/java/org/apache/stanbol/enhancer/engines/metaxa/core/TestMetaxaCore.java
URL: http://svn.apache.org/viewvc/stanbol/trunk/enhancement-engines/metaxa/src/test/java/org/apache/stanbol/enhancer/engines/metaxa/core/TestMetaxaCore.java?rev=1744328&r1=1744327&r2=1744328&view=diff
==============================================================================
--- stanbol/trunk/enhancement-engines/metaxa/src/test/java/org/apache/stanbol/enhancer/engines/metaxa/core/TestMetaxaCore.java (original)
+++ stanbol/trunk/enhancement-engines/metaxa/src/test/java/org/apache/stanbol/enhancer/engines/metaxa/core/TestMetaxaCore.java Tue May 17 22:20:49 2016
@@ -20,12 +20,12 @@ import java.io.IOException;
import java.io.InputStream;
import java.util.HashMap;
-import org.apache.clerezza.rdf.core.BNode;
-import org.apache.clerezza.rdf.core.NonLiteral;
-import org.apache.clerezza.rdf.core.Resource;
-import org.apache.clerezza.rdf.core.Triple;
-import org.apache.clerezza.rdf.core.UriRef;
-import org.apache.clerezza.rdf.core.impl.TripleImpl;
+import org.apache.clerezza.commons.rdf.BlankNode;
+import org.apache.clerezza.commons.rdf.BlankNodeOrIRI;
+import org.apache.clerezza.commons.rdf.RDFTerm;
+import org.apache.clerezza.commons.rdf.Triple;
+import org.apache.clerezza.commons.rdf.IRI;
+import org.apache.clerezza.commons.rdf.impl.utils.TripleImpl;
import org.apache.commons.io.IOUtils;
import org.apache.stanbol.enhancer.engines.metaxa.MetaxaEngine;
import org.junit.BeforeClass;
@@ -187,15 +187,15 @@ public class TestMetaxaCore {
int tripleCounter = 0;
- HashMap<BlankNode, BNode> blankNodeMap = new HashMap<BlankNode, BNode>();
+ HashMap<BlankNode, BlankNode> blankNodeMap = new HashMap<BlankNode, BlankNode>();
ClosableIterator<Statement> it = m.iterator();
while (it.hasNext()) {
Statement oneStmt = it.next();
- NonLiteral subject = (NonLiteral) MetaxaEngine.asClerezzaResource(oneStmt.getSubject(), blankNodeMap);
- UriRef predicate = (UriRef) MetaxaEngine.asClerezzaResource(oneStmt.getPredicate(), blankNodeMap);
- Resource object = MetaxaEngine.asClerezzaResource(oneStmt.getObject(), blankNodeMap);
+ BlankNodeOrIRI subject = (BlankNodeOrIRI) MetaxaEngine.asClerezzaResource(oneStmt.getSubject(), blankNodeMap);
+ IRI predicate = (IRI) MetaxaEngine.asClerezzaResource(oneStmt.getPredicate(), blankNodeMap);
+ RDFTerm object = MetaxaEngine.asClerezzaResource(oneStmt.getObject(), blankNodeMap);
if (null != subject
&& null != predicate