Newer
Older
package fr.emse.gitlab.saref.jobs;
import java.io.File;
import java.io.FileInputStream;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.nio.charset.Charset;
import java.nio.charset.MalformedInputException;
import java.text.SimpleDateFormat;
import java.util.HashMap;
import java.util.HashSet;
import org.apache.jena.atlas.RuntimeIOException;
import org.apache.jena.datatypes.xsd.XSDDatatype;
import org.apache.jena.query.Dataset;
import org.apache.jena.query.QueryExecution;
import org.apache.jena.query.QueryExecutionFactory;
import org.apache.jena.query.QuerySolution;
import org.apache.jena.query.ReadWrite;
import org.apache.jena.query.ResultSet;
import org.apache.jena.rdf.model.Literal;
import org.apache.jena.rdf.model.Model;
import org.apache.jena.rdf.model.ModelFactory;
import org.apache.jena.rdf.model.NodeIterator;
import org.apache.jena.rdf.model.RDFNode;
import org.apache.jena.rdf.model.ResIterator;
import org.apache.jena.rdf.model.Resource;
import org.apache.jena.rdf.model.ResourceFactory;
import org.apache.jena.riot.Lang;
import org.apache.jena.vocabulary.DCTerms;
import org.apache.jena.vocabulary.OWL2;
import org.apache.jena.vocabulary.RDF;
import org.apache.jena.vocabulary.RDFS;
import org.topbraid.jenax.util.JenaUtil;
import org.topbraid.shacl.validation.ValidationUtil;
import org.topbraid.shacl.vocabulary.SH;
import fr.emse.gitlab.saref.Constants;
import fr.emse.gitlab.saref.SAREFPipelineException;
import fr.emse.gitlab.saref.entities.git.ReleaseVersion;
import fr.emse.gitlab.saref.entities.git.Version;
import fr.emse.gitlab.saref.vocabs.EX;
import fr.emse.gitlab.saref.vocabs.RDFP;
import fr.emse.gitlab.saref.vocabs.VANN;
public class ReadOntology extends JobRunner {
static final String SHACL_WARNING = "http://www.w3.org/ns/shacl#Warning";
static final String SHACL_VIOLATION = "http://www.w3.org/ns/shacl#Violation";
static final String SOURCE_ERROR = "There shall be exactly one annotation dcterms:source that points to the ETSI Technical Specification URL `http://www.etsi.org/deliver/etsi_ts/...`.";
static final String SELECT_VIOLATION = "PREFIX sh: <http://www.w3.org/ns/shacl#>\n"
+ "SELECT ?focusNode ?resultMessage ?resultPath ?value ?severity\n" + "WHERE { \n"
+ " ?violation sh:focusNode ?focusNode .\n" + " ?violation sh:resultMessage ?resultMessage .\n"
+ " ?violation sh:resultSeverity ?severity .\n"
+ " OPTIONAL { ?violation sh:resultPath ?resultPath . }\n"
+ " OPTIONAL { ?violation sh:value ?value . } \n" + "}"
+ "ORDER BY ?severity ?resultMessage ?focusNode ";
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
static final Map<String, String> PREFIXES = new HashMap<String, String>();
static {
PREFIXES.put("owl", "http://www.w3.org/2002/07/owl#");
PREFIXES.put("rdfs", "http://www.w3.org/2000/01/rdf-schema#");
PREFIXES.put("xsd", "http://www.w3.org/2001/XMLSchema#");
PREFIXES.put("dcterms", "http://purl.org/dc/terms/");
PREFIXES.put("vann", "http://purl.org/vocab/vann/");
PREFIXES.put("schema", "http://schema.org/");
PREFIXES.put("rdf", "http://www.w3.org/1999/02/22-rdf-syntax-ns#");
PREFIXES.put("voaf", "http://purl.org/vocommons/voaf#");
PREFIXES.put("dce", "http://purl.org/dc/elements/1.1/");
PREFIXES.put("dct", "http://purl.org/dc/terms/");
PREFIXES.put("xml", "http://www.w3.org/XML/1998/namespace/");
PREFIXES.put("saref", "https://saref.etsi.org/core/");
}
private static final SimpleDateFormat SIMPLE_DATE_FORMAT = new SimpleDateFormat("yyyy-MM-dd");
private static final Resource ETSI_URL = ResourceFactory.createResource("https://www.etsi.org/");
private static final Resource ETSI_LICENSE = ResourceFactory
.createResource("https://forge.etsi.org/etsi-software-license");
public ReadOntology(String testSuiteName) {
super(testSuiteName);
}
public void doJob(Dataset dataset, Version version) throws SAREFPipelineException {
String repoName = version.getRepositoryName();
String ontologyName = repoName.equals("saref-core") ? "saref.ttl" : repoName + ".ttl";
File ontologyFile = new File(version.getRepository().getDirectory(), "ontology/" + ontologyName);
Model model = ModelFactory.createDefaultModel();
try (FileInputStream input = new FileInputStream(ontologyFile)) {
model.read(input, Constants.BASE, Lang.TTL.getLabel());
} catch (Exception ex) {
if (ex instanceof RuntimeIOException && ex.getCause() instanceof MalformedInputException) {
try (InputStreamReader input2 = new InputStreamReader(new FileInputStream(ontologyFile),
Charset.defaultCharset())) {
model.read(input2, Constants.BASE, Lang.TTL.getLabel());
} catch (Exception ex2) {
logger.error("Exception while reading the ontology file", ex2);
throw new SAREFPipelineException("Exception while reading the ontology file", ex2);
}
} else {
logger.error("Exception while reading the ontology file", ex);
throw new SAREFPipelineException("Exception while reading the ontology file", ex);
}
}
checkPrefixes(model);
checkShapes(model, version);
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
// how does the TDB model work? documentation is not precise.
dataset.begin(ReadWrite.WRITE);
Model config = getNamedModel(dataset, Constants.CONFIG);
updateOntologyMetadata(version, model);
dataset.addNamedModel(version.getUri(), model);
augmentTermGraphs(dataset, version, model, config);
dataset.commit();
}
private void checkPrefixes(Model model) {
final Map<String, String> prefixes = model.getNsPrefixMap();
for (String s : PREFIXES.keySet()) {
if (prefixes.containsKey(s)) {
if (!prefixes.get(s).equals(PREFIXES.get(s))) {
logger.warn(String.format(
"Prefix `%s:` in the ontology file is expected to be equal to `<%s>`. Got: `<%s>`", s,
PREFIXES.get(s), prefixes.get(s)));
}
}
}
for (Map.Entry<String, String> entry : prefixes.entrySet()) {
String s = entry.getKey();
String l = entry.getValue();
if (l.contains("saref")) {
if (!l.matches(Constants.REGEX_ONTO_SERIES_URI)) {
logger.warn(String.format(
"Prefix `%s:` in the ontology file contains string \"saref\", but does not seem to match the official SAREF ontologies namespaces: `\\\\%s\\\\`. Got: `<%s>`",
s, Constants.REGEX_ONTO_SERIES_URI, l));
}
}
}
}
private void checkShapes(Model model, Version version) throws SAREFPipelineException {
Model shapeModel = JenaUtil.createDefaultModel();
try (InputStream in = ReadOntology.class.getClassLoader().getResourceAsStream("sarefShape.ttl")) {
shapeModel.read(in, Constants.BASE, "TTL");
} catch (Exception ex) {
logger.error("Exception while reading the shape file", ex);
throw new SAREFPipelineException("Exception while reading the shape file", ex);
}
Resource reportResource = ValidationUtil.validateModel(model, shapeModel, true);
boolean conforms = reportResource.getProperty(SH.conforms).getBoolean();
if (!conforms) {
Model reportModel = reportResource.getModel();
reportModel.setNsPrefixes(PREFIXES);
reportModel.setNsPrefix("sh", "http://www.w3.org/ns/shacl#");
try (QueryExecution exec = QueryExecutionFactory.create(SELECT_VIOLATION, reportModel);) {
Resource previousSeverity = null;
Literal previousResultMessage = null;
List<Resource> previousFocusNodes = new ArrayList<>();
List<RDFNode> previousvalues = new ArrayList<>();
for (ResultSet resultSet = exec.execSelect(); resultSet.hasNext();) {
QuerySolution sol = resultSet.next();
Resource severity = sol.getResource("severity");
Literal resultMessage = sol.getLiteral("resultMessage");
Resource focusNode = sol.get("focusNode").asResource();
if (severity != null && severity.equals(previousSeverity) && resultMessage != null
&& resultMessage.equals(previousResultMessage)) {
previousFocusNodes.add(focusNode);
previousvalues.add(value);
if (previousSeverity != null) {
String message = String.format("%s: %s", previousResultMessage,
String.join(" - ", previousFocusNodes.stream().map(Object::toString)
.collect(Collectors.toList()).toArray(new String[1])));
if (severity.getURI().equals(SHACL_VIOLATION)) {
logger.error(message);
} else {
logger.warn(message);
}
}
previousSeverity = severity;
previousResultMessage = resultMessage;
previousFocusNodes = new ArrayList<>();
previousvalues = new ArrayList<>();
}
}
if (!previousFocusNodes.isEmpty()) {
String message = String.format("%s: %s", previousResultMessage,
String.join(" - ", previousFocusNodes.stream().map(Object::toString)
.collect(Collectors.toList()).toArray(new String[1])));
if (previousSeverity != null && previousSeverity.getURI().equals(SHACL_VIOLATION)) {
logger.error(message);
} else {
logger.warn(message);
for (ResIterator it = model.listSubjectsWithProperty(RDF.type, OWL2.Ontology); it.hasNext();) {
logger.error("There shall be only one owl:Ontology");
}
// if(version instanceof ReleaseVersion) {
// int source = 0;
// NodeIterator its = model.listObjectsOfProperty(ontology, DCTerms.source);
// if(!its.hasNext()) {
// logger.warn(SOURCE_ERROR);
// }
// while(its.hasNext()) {
// if(source++>1) {
// logger.warn(SOURCE_ERROR);
// }
// RDFNode s = its.next();
// if(!s.isURIResource() || !s.asResource().getURI().startsWith("http://www.etsi.org/deliver/etsi_ts/")) {
// logger.warn(SOURCE_ERROR);
// }
// }
// }
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
}
}
/**
* for each term, add: some triples in the default graph (used to detect naming
* clashes), and some triples in the named graph of the term (used to display
* the page of the term)
*
* @param dataset
* @param version
* @param model
*/
private void augmentTermGraphs(Dataset dataset, Version version, Model model, Model config) {
Set<Resource> definedTerms = new HashSet<>();
Set<Resource> usedTerms = new HashSet<>();
computeTerms(version, model, definedTerms, usedTerms);
config.add(version.getRepository().getResource(), EX.hasVersion, version.getResource());
config.add(version.getResource(), RDF.type, EX.OntologyVersion);
config.add(version.getResource(), EX.repositoryName, version.getRepositoryName());
config.add(version.getResource(), EX.versionInfo, version.getVersionName());
if (version.getPriorVersion() != null) {
config.add(version.getResource(), EX.priorVersion, version.getPriorVersion().getResource());
}
for (Resource t : definedTerms) {
Model termModel = getNamedModel(dataset, t.getURI());
termModel.add(t, RDF.type, RDFS.Resource);
String localName = t.getURI().substring(version.getRepository().getNamespace().length());
termModel.add(t, RDFS.isDefinedBy, version.getResource());
// keep the most recent definition of the term
if (version.getNextVersion() == null) {
termModel.add(DCTerms.modified, RDF.type, OWL.AnnotationProperty);
termModel.add(t, DCTerms.modified, SIMPLE_DATE_FORMAT.format(version.getIssued()), XSDDatatype.XSDdate);
try (QueryExecution exec = QueryExecutionFactory.create("DESCRIBE <" + t.getURI() + ">", model)) {
termModel.add(exec.execDescribe());
}
}
config.add(t, RDF.type, RDFP.Resource);
config.add(t, EX.localName, localName);
config.add(t, RDFS.isDefinedBy, version.getResource());
}
for (Resource t : usedTerms) {
Model termModel = getNamedModel(dataset, t.getURI());
termModel.add(t, EX.isUsedBy, version.getResource());
config.add(t, RDF.type, RDFP.Resource);
config.add(t, EX.isUsedBy, version.getResource());
}
}
private void updateOntologyMetadata(Version version, Model model) {
Resource ontologySeries = version.getRepository().getResource();
model.add(ontologySeries, RDF.type, OWL2.Ontology);
model.removeAll(ontologySeries, OWL2.versionIRI, null);
model.add(ontologySeries, OWL2.versionIRI, version.getResource());
model.removeAll(ontologySeries, OWL2.versionInfo, null);
model.add(ontologySeries, OWL2.versionInfo, version.getVersionName());
model.removeAll(ontologySeries, OWL2.priorVersion, null);
if (version.getPriorVersion() != null) {
model.add(ontologySeries, OWL2.priorVersion, version.getPriorVersion().getResource());
}
model.removeAll(ontologySeries, DCTerms.publisher, null);
model.add(ontologySeries, DCTerms.publisher, ETSI_URL);
model.removeAll(ontologySeries, DCTerms.license, null);
model.add(ontologySeries, DCTerms.license, ETSI_LICENSE);
model.add(VANN.preferredNamespaceUri, RDF.type, OWL.AnnotationProperty);
model.add(VANN.preferredNamespacePrefix, RDF.type, OWL.AnnotationProperty);
model.add(DCTerms.title, RDF.type, OWL.AnnotationProperty);
model.add(DCTerms.title, RDF.type, OWL.AnnotationProperty);
model.add(DCTerms.title, RDF.type, OWL.AnnotationProperty);
model.add(DCTerms.abstract_, RDF.type, OWL.AnnotationProperty);
model.add(DCTerms.description, RDF.type, OWL.AnnotationProperty);
model.add(DCTerms.creator, RDF.type, OWL.AnnotationProperty);
model.add(DCTerms.contributor, RDF.type, OWL.AnnotationProperty);
model.add(DCTerms.publisher, RDF.type, OWL.AnnotationProperty);
model.add(DCTerms.issued, RDF.type, OWL.AnnotationProperty);
model.add(DCTerms.modified, RDF.type, OWL.AnnotationProperty);
model.add(DCTerms.license, RDF.type, OWL.AnnotationProperty);
model.add(SCHEMA.Person, RDF.type, OWL.Class);
model.add(SCHEMA.Organization, RDF.type, OWL.Class);
model.add(SCHEMA.affiliation, RDF.type, OWL.ObjectProperty);
model.add(SCHEMA.familyName, RDF.type, OWL.DatatypeProperty);
model.add(SCHEMA.givenName, RDF.type, OWL.DatatypeProperty);
model.add(SCHEMA.name, RDF.type, OWL.DatatypeProperty);
// // list of contributors
// Set<Contributor> contributors = new HashSet<>();
// for (Iterator<RevCommit> it = git.log().add(version.ref.getObjectId()).call().iterator(); it.hasNext();) {
// RevCommit commit = it.next();
// Contributor contributor = new Contributor(commit.getCommitterIdent());
// contributors.add(contributor);
// }
// for (Contributor contributor : contributors) {
// // git can only provide name + email.
// // would need to maintain some list of mapping email -> url in the future.
// Resource anon = onto.createResource();
// onto.add(repo.resource, DCTerms.contributor, anon);
// onto.add(anon, FOAF.name, contributor.getName());
// onto.add(anon, FOAF.mbox, contributor.getEmailAddress());
// }
model.removeAll(ontologySeries, VANN.preferredNamespacePrefix, null);
model.removeAll(ontologySeries, VANN.preferredNamespaceUri, null);
model.add(ontologySeries, VANN.preferredNamespacePrefix, version.getRepository().getPrefix());
model.add(ontologySeries, VANN.preferredNamespaceUri, version.getRepository().getNamespace(),
XSDDatatype.XSDanyURI);
model.removeAll(ontologySeries, DCTerms.issued, null);
model.add(ontologySeries, DCTerms.issued, SIMPLE_DATE_FORMAT.format(version.getIssued()), XSDDatatype.XSDdate);
}
private void computeTerms(Version version, Model model, Set<Resource> definedTerms, Set<Resource> usedTerms) {
model.listStatements().forEachRemaining(stmt -> {
Resource s = stmt.getSubject();
Resource p = stmt.getPredicate();
Resource o = stmt.getObject().isResource() ? (Resource) stmt.getObject() : null;
computeTerms(version, s, definedTerms, usedTerms);
computeTerms(version, p, definedTerms, usedTerms);
computeTerms(version, o, definedTerms, usedTerms);
});
}
private void computeTerms(Version version, Resource t, Set<Resource> definedTerms, Set<Resource> usedTerms) {
if (t == null || !t.isURIResource() || !t.getURI().startsWith(Constants.BASE) || t.getURI().endsWith("/")) {
return;
}
String uri = t.getURI();
if (uri.startsWith(version.getRepository().getNamespace())) {
definedTerms.add(t);
} else {
usedTerms.add(t);
}
}
private Model getNamedModel(Dataset dataset, String uri) {
if (!dataset.containsNamedModel(uri)) {
dataset.addNamedModel(uri, ModelFactory.createDefaultModel());
}
return dataset.getNamedModel(uri);
}
}