ADD : JSON2RDF

ADD : Data samples
master
Kevin Shehu 2020-09-28 16:48:54 +02:00
parent c4286cf81f
commit 561f61afe2
5 changed files with 244 additions and 0 deletions

23
pom.xml
View File

@ -7,6 +7,18 @@
<groupId>org.example</groupId>
<artifactId>GGD</artifactId>
<version>1.0-SNAPSHOT</version>
<build>
<plugins>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-compiler-plugin</artifactId>
<configuration>
<source>7</source>
<target>7</target>
</configuration>
</plugin>
</plugins>
</build>
<dependencies>
<dependency>
<groupId>org.apache.jena</groupId>
@ -25,6 +37,17 @@
<artifactId>jena-fuseki-main</artifactId>
<version>3.16.0</version>
</dependency>
<dependency>
<groupId>info.picocli</groupId>
<artifactId>picocli</artifactId>
<version>4.5.1</version>
</dependency>
<dependency>
<groupId>org.glassfish</groupId>
<artifactId>javax.json</artifactId>
<version>1.1.4</version>
</dependency>
</dependencies>

View File

@ -0,0 +1,28 @@
{
"desc" : "Distances between several cities, in kilometers.",
"updated" : "2014-02-04T18:50:45",
"uptodate": true,
"author" : null,
"cities" : {
"Brussels": [
{"to": "London", "distance": 322},
{"to": "Paris", "distance": 265},
{"to": "Amsterdam", "distance": 173}
],
"London": [
{"to": "Brussels", "distance": 322},
{"to": "Paris", "distance": 344},
{"to": "Amsterdam", "distance": 358}
],
"Paris": [
{"to": "Brussels", "distance": 265},
{"to": "London", "distance": 344},
{"to": "Amsterdam", "distance": 431}
],
"Amsterdam": [
{"to": "Brussels", "distance": 173},
{"to": "London", "distance": 358},
{"to": "Paris", "distance": 431}
]
}
}

View File

@ -0,0 +1,67 @@
package JSON2RDF;
import java.io.BufferedReader;
import java.io.BufferedWriter;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.io.OutputStream;
import java.io.OutputStreamWriter;
import java.io.Reader;
import java.net.URI;
import java.nio.charset.Charset;
import java.nio.charset.StandardCharsets;
import org.apache.jena.riot.system.StreamRDF;
import org.apache.jena.riot.system.StreamRDFLib;
import picocli.CommandLine;
@CommandLine.Command(name = "json2rdf")
public class JSON2RDF {
private final InputStream jsonIn;
private final OutputStream rdfOut;
@CommandLine.Parameters(paramLabel = "base", index = "0", description = "Base URI of the RDF output data\nExample: https://localhost/")
private URI baseURI;
@CommandLine.Option(names = { "--input-charset" }, description = "Input charset (default: ${DEFAULT-VALUE})")
private Charset inputCharset = StandardCharsets.UTF_8;
@CommandLine.Option(names = { "--output-charset" }, description = "Output charset (default: ${DEFAULT-VALUE})")
private Charset outputCharset = StandardCharsets.UTF_8;
public static void main(String[] args) throws IOException
{
JSON2RDF json2rdf = new JSON2RDF(System.in, System.out);
try
{
CommandLine.ParseResult parseResult = new CommandLine(json2rdf).parseArgs(args);
if (!CommandLine.printHelpIfRequested(parseResult)) json2rdf.convert();
}
catch (CommandLine.ParameterException ex)
{ // command line arguments could not be parsed
System.err.println(ex.getMessage());
ex.getCommandLine().usage(System.err);
}
}
public JSON2RDF(InputStream csvIn, OutputStream rdfOut)
{
this.jsonIn = csvIn;
this.rdfOut = rdfOut;
}
public void convert() throws IOException
{
if (jsonIn.available() == 0) throw new IllegalStateException("JSON input not provided");
try (Reader reader = new BufferedReader(new InputStreamReader(jsonIn, inputCharset)))
{
StreamRDF rdfStream = StreamRDFLib.writer(new BufferedWriter(new OutputStreamWriter(rdfOut, outputCharset)));
new JsonStreamRDFWriter(reader, rdfStream, baseURI.toString()).convert();
}
}
}

View File

@ -0,0 +1,124 @@
package JSON2RDF;
import java.io.InputStream;
import java.io.Reader;
import java.util.ArrayDeque;
import java.util.Deque;
import java.util.HashMap;
import java.util.Map;
import javax.json.Json;
import javax.json.stream.JsonParser;
import org.apache.jena.datatypes.xsd.XSDDatatype;
import org.apache.jena.graph.Node;
import org.apache.jena.graph.NodeFactory;
import org.apache.jena.graph.Triple;
import org.apache.jena.riot.system.IRIResolver;
import org.apache.jena.riot.system.StreamRDF;
public class JsonStreamRDFWriter
{
private final JsonParser parser;
private final StreamRDF rdfStream;
private final IRIResolver iriResolver;
public JsonStreamRDFWriter(Reader reader, StreamRDF rdfStream, String baseURI)
{
this(Json.createParser(reader), rdfStream, baseURI);
}
public JsonStreamRDFWriter(InputStream is, StreamRDF rdfStream, String baseURI)
{
this(Json.createParser(is), rdfStream, baseURI);
}
public JsonStreamRDFWriter(JsonParser parser, StreamRDF rdfStream, String baseURI)
{
this.parser = parser;
this.rdfStream = rdfStream;
this.iriResolver = IRIResolver.create(baseURI);
}
public void convert()
{
getStreamRDF().start();
write(getParser(), getStreamRDF(), getIRIResolver());
getStreamRDF().finish();
}
public static void write(JsonParser parser, StreamRDF rdfStream, IRIResolver iriResolver)
{
Deque<Node> subjectStack = new ArrayDeque<>();
Map<Node, Node> arrayProperties = new HashMap<>();
Node property = null;
while (parser.hasNext())
{
JsonParser.Event event = parser.next();
switch (event)
{
case START_ARRAY:
if (!subjectStack.isEmpty() && property != null) arrayProperties.put(subjectStack.getLast(), property);
break;
case END_ARRAY:
if (!subjectStack.isEmpty()) arrayProperties.remove(subjectStack.getLast());
break;
case START_OBJECT:
Node subject = NodeFactory.createBlankNode();
// add triple with current array property, if any
if (property != null && !subjectStack.isEmpty()) rdfStream.triple(new Triple(subjectStack.getLast(), property, subject));
subjectStack.addLast(subject);
break;
case END_OBJECT:
subjectStack.removeLast();
// restore previous array property, if there was any
if (!subjectStack.isEmpty() && arrayProperties.containsKey(subjectStack.getLast())) property = arrayProperties.get(subjectStack.getLast());
break;
case VALUE_FALSE:
rdfStream.triple(new Triple(subjectStack.getLast(), property, NodeFactory.createLiteralByValue(Boolean.FALSE, XSDDatatype.XSDboolean)));
break;
case VALUE_TRUE:
rdfStream.triple(new Triple(subjectStack.getLast(), property, NodeFactory.createLiteralByValue(Boolean.TRUE, XSDDatatype.XSDboolean)));
break;
case KEY_NAME:
property = NodeFactory.createURI(iriResolver.resolveToString("#" + parser.getString()));
break;
case VALUE_STRING:
if (property != null) rdfStream.triple(new Triple(subjectStack.getLast(), property, NodeFactory.createLiteral(parser.getString())));
break;
case VALUE_NUMBER:
try
{
rdfStream.triple(new Triple(subjectStack.getLast(), property,NodeFactory.createLiteralByValue(Integer.valueOf(parser.getString()), XSDDatatype.XSDint)));
}
catch (NumberFormatException ex)
{
rdfStream.triple(new Triple(subjectStack.getLast(), property,NodeFactory.createLiteralByValue(Float.valueOf(parser.getString()), XSDDatatype.XSDfloat)));
}
break;
case VALUE_NULL:
break;
}
}
}
protected JsonParser getParser()
{
return parser;
}
protected StreamRDF getStreamRDF()
{
return rdfStream;
}
protected IRIResolver getIRIResolver()
{
return iriResolver;
}
}

View File

@ -1,4 +1,5 @@
import JSON2RDF.JSON2RDF;
import org.apache.jena.rdf.model.*;
import org.apache.jena.vocabulary.*;
@ -44,5 +45,6 @@ public class main {
System.out.println(" .");
}
}
}