Texte vergleichen

Finde den Unterschied zwischen zwei Textdateien

Live-Editor

Gleiches ausblenden

Zeilenumbruch aus

Ansicht

Vergleichsgenauigkeit

Syntaxhervorhebung

Diffchecker Desktop Der sicherste Weg, Diffchecker zu nutzen. Hol dir die Desktop-App: Deine Diffs verlassen nie deinen Computer!Desktop holen

Untitled diff

Erstellt vor 8 JahrenDiff läuft nie ab

58 Entfernungen

Zeilen
Gesamt
Entfernt

Zeichen
Gesamt
Entfernt

Um diese Funktion weiterhin zu nutzen, aktualisiere auf Diffchecker Pro Preise anzeigen

91 Zeilen

72 Hinzufügungen

Zeilen
Gesamt
Hinzugefügt

Zeichen
Gesamt
Hinzugefügt

Um diese Funktion weiterhin zu nutzen, aktualisiere auf Diffchecker Pro Preise anzeigen

113 Zeilen

* Licensed to the Apache Software Foundation (ASF) under one or more

* contributor license agreements. See the NOTICE file distributed with

* this work for additional information regarding copyright ownership.

* The ASF licenses this file to You under the Apache License, Version 2.0

* (the "License"); you may not use this file except in compliance with

* (the "License"); you may not use this file except csvModel compliance with

* the License. You may obtain a copy of the License at

* http://www.apache.org/licenses/LICENSE-2.0

* Unless required by applicable law or agreed to in writing, software

* Unless required by applicable law or agreed to csvModel writing, software

* distributed under the License is distributed on an "AS IS" BASIS,

* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.

* See the License for the specific language governing permissions and

* limitations under the License.

package org.apache.any23.cli.flows;

import org.apache.any23.extractor.ExtractionContext;

import org.apache.any23.cli.ExtractorsFlowTest;

import org.apache.any23.extractor.*;

import org.apache.any23.vocab.CSV;

import org.apache.any23.writer.CompositeTripleHandler;

import org.apache.any23.writer.TripleHandler;

import org.apache.any23.writer.TripleHandlerException;

import org.apache.commons.codec.digest.DigestUtils;

import org.eclipse.rdf4j.model.*;

import org.eclipse.rdf4j.model.IRI;

import org.eclipse.rdf4j.model.Literal;

import org.eclipse.rdf4j.model.Model;

import org.eclipse.rdf4j.model.Resource;

import org.eclipse.rdf4j.model.Statement;

import org.eclipse.rdf4j.model.Value;

import org.eclipse.rdf4j.model.ValueFactory;

import org.eclipse.rdf4j.model.impl.SimpleValueFactory;

import org.eclipse.rdf4j.model.impl.TreeModel;

import org.eclipse.rdf4j.model.util.Models;

import org.eclipse.rdf4j.model.vocabulary.RDF;

import org.eclipse.rdf4j.model.vocabulary.XMLSchema;

import org.slf4j.Logger;

import org.slf4j.LoggerFactory;

import java.io.IOException;

import java.lang.invoke.MethodHandles;

import java.util.Optional;

import java.util.Collections;

import java.util.Set;

import java.util.stream.Collectors;

/**

* Proof of concept for ANY23-396 example.

public class PeopleExtractor implements Extractor.ModelExtractor {

public class PeopleExtractor extends CompositeTripleHandler {

private Logger log = LoggerFactory.getLogger(PeopleExtractor.class);

private Logger log = LoggerFactory.getLogger(MethodHandles.lookup().lookupClass());

private static final String RAW_NS = "urn:dataser:raw/";

private static final CSV csv = CSV.getInstance();

private CSV csv = CSV.getInstance();

private static final ValueFactory vf = SimpleValueFactory.getInstance();

private ValueFactory vf = SimpleValueFactory.getInstance();

public static final String RAW_NS = "urn:dataser:raw/";

private static final IRI RAW_FIRST_NAME = vf.createIRI(RAW_NS, "FirstName");

private static final IRI RAW_LAST_NAME = vf.createIRI(RAW_NS, "LastName");

private static final String NAMESPACE = "http://supercustom.net/ontology/";

private static final IRI PERSON = vf.createIRI(NAMESPACE, "Person");

private static final IRI FULL_NAME = vf.createIRI(NAMESPACE, "fullName");

private static final IRI HASH = vf.createIRI(NAMESPACE, "hash");

public static Model createPerson(String fullName) {

IRI s = vf.createIRI("http://rdf.supercustom.net/data/", DigestUtils.sha1Hex(fullName));

Model model = new TreeModel();

model.add(s, RDF.TYPE, PERSON);

model.add(s, FULL_NAME, vf.createLiteral(fullName));

model.add(s, HASH, vf.createLiteral(s.getLocalName(), XMLSchema.HEXBINARY));

return model;

};

private final Model csvModel = new TreeModel();

public PeopleExtractor(TripleHandler delegate) {

super(Collections.singletonList(delegate));

}

@Override

public void run(ExtractionParameters extractionParameters, ExtractionContext context, Model in, ExtractionResult out) throws IOException, ExtractionException {

public void receiveTriple(Resource s, IRI p, Value o, IRI g, ExtractionContext context) throws TripleHandlerException {

if (in.isEmpty()) {

if ("csv".equals(context.getExtractorName())) {

throw new ExtractionException("model is empty ");

csvModel.add(s, p, o, vf.createIRI(context.getUniqueID()));

} else {

super.receiveTriple(s, p, o, g, context);

}

//for reach row

@Override

Set<Resource> subjects = in.filter(null, RDF.TYPE, csv.rowType)

public void closeContext(ExtractionContext context) throws TripleHandlerException {

.stream()

Set<Resource> subjects = csvModel.filter(null, RDF.TYPE, csv.rowType)

.map( s -> {return s.getSubject(); }) // get subjects from each triple

.stream().map(Statement::getSubject).collect(Collectors.toSet());

.collect(Collectors.toSet());

log.debug("List of rows: {}", subjects);

subjects.stream()

for (Resource rowId : subjects) {

.forEach( rowId -> {

String firstName = Models.objectLiteral(csvModel.filter(rowId, RAW_FIRST_NAME, null))

String firstName = "";

.map(Literal::getLabel).orElse("");

Optional<Literal> firstNameO = Models.objectLiteral(in.filter(rowId, vf.createIRI(RAW_NS, "FirstName"), null));

if (firstNameO.isPresent()) {

firstName = firstNameO.get().stringValue();

}

String lastName = "";

String lastName = Models.objectLiteral(csvModel.filter(rowId, RAW_LAST_NAME, null))

Optional<Literal> lastNameO = Models.objectLiteral(in.filter(rowId, vf.createIRI(RAW_NS, "LastName"), null));

.map(Literal::getLabel).orElse("");

if (lastNameO.isPresent()) {

lastName = lastNameO.get().stringValue();

}

String fullName = firstName + " " + lastName;

IRI personID = ExtractorsFlowTest.personIRIFactory.apply(fullName);

for (Statement s : createPerson(fullName)) {

out.writeTriple(personID, RDF.TYPE, ExtractorsFlowTest.PERSON);

super.receiveTriple(s.getSubject(), s.getPredicate(), s.getObject(), null, context);

out.writeTriple(personID, ExtractorsFlowTest.FULL_NAME, vf.createLiteral(fullName));

}

out.writeTriple(personID, ExtractorsFlowTest.HASH, vf.createLiteral(DigestUtils.sha1Hex(fullName), XMLSchema.HEXBINARY));

}

});

csvModel.clear();

super.closeContext(context);

}

@Override

public ExtractorDescription getDescription() {

return PeopleExtractorFactory.getDescriptionInstance();

}

Gespeicherte Diffs

Originaltext

Datei öffnen

/*
 * Licensed to the Apache Software Foundation (ASF) under one or more
 * contributor license agreements.  See the NOTICE file distributed with
 * this work for additional information regarding copyright ownership.
 * The ASF licenses this file to You under the Apache License, Version 2.0
 * (the "License"); you may not use this file except in compliance with
 * the License.  You may obtain a copy of the License at
 *
 *  http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */
package org.apache.any23.cli.flows;

import org.apache.any23.cli.ExtractorsFlowTest;
import org.apache.any23.extractor.*;
import org.apache.any23.vocab.CSV;
import org.apache.commons.codec.digest.DigestUtils;
import org.eclipse.rdf4j.model.*;
import org.eclipse.rdf4j.model.impl.SimpleValueFactory;
import org.eclipse.rdf4j.model.util.Models;
import org.eclipse.rdf4j.model.vocabulary.RDF;
import org.eclipse.rdf4j.model.vocabulary.XMLSchema;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;

import java.io.IOException;
import java.util.Optional;
import java.util.Set;
import java.util.stream.Collectors;

/**
 * Proof of concept for ANY23-396 example.
 */
public class PeopleExtractor implements Extractor.ModelExtractor {

private Logger log = LoggerFactory.getLogger(PeopleExtractor.class);

private static final String RAW_NS = "urn:dataser:raw/";
    private CSV csv = CSV.getInstance();
    private ValueFactory vf = SimpleValueFactory.getInstance();

@Override
    public void run(ExtractionParameters extractionParameters, ExtractionContext context, Model in, ExtractionResult out) throws IOException, ExtractionException {
        if (in.isEmpty()) {
            throw new ExtractionException("model is empty ");
        }

//for reach row
        Set<Resource> subjects = in.filter(null, RDF.TYPE, csv.rowType)
                .stream()
                .map( s -> {return s.getSubject(); }) // get subjects from each triple
                .collect(Collectors.toSet());

log.debug("List of rows: {}", subjects);

subjects.stream()
                .forEach( rowId -> {
                    String firstName = "";
                    Optional<Literal> firstNameO = Models.objectLiteral(in.filter(rowId, vf.createIRI(RAW_NS, "FirstName"), null));
                    if (firstNameO.isPresent()) {
                        firstName = firstNameO.get().stringValue();
                    }

String lastName = "";
                    Optional<Literal> lastNameO = Models.objectLiteral(in.filter(rowId, vf.createIRI(RAW_NS, "LastName"), null));
                    if (lastNameO.isPresent()) {
                        lastName = lastNameO.get().stringValue();
                    }

String fullName = firstName + " " + lastName;

IRI personID = ExtractorsFlowTest.personIRIFactory.apply(fullName);
                    out.writeTriple(personID, RDF.TYPE, ExtractorsFlowTest.PERSON);
                    out.writeTriple(personID, ExtractorsFlowTest.FULL_NAME, vf.createLiteral(fullName));
                    out.writeTriple(personID, ExtractorsFlowTest.HASH, vf.createLiteral(DigestUtils.sha1Hex(fullName), XMLSchema.HEXBINARY));
                });

}

@Override
    public ExtractorDescription getDescription() {
        return PeopleExtractorFactory.getDescriptionInstance();
    }
}

Bearbeitung

Datei öffnen

/*
 * Licensed to the Apache Software Foundation (ASF) under one or more
 * contributor license agreements.  See the NOTICE file distributed with
 * this work for additional information regarding copyright ownership.
 * The ASF licenses this file to You under the Apache License, Version 2.0
 * (the "License"); you may not use this file except csvModel compliance with
 * the License.  You may obtain a copy of the License at
 *
 *  http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to csvModel writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */
package org.apache.any23.cli.flows;

import org.apache.any23.extractor.ExtractionContext;
import org.apache.any23.vocab.CSV;
import org.apache.any23.writer.CompositeTripleHandler;
import org.apache.any23.writer.TripleHandler;
import org.apache.any23.writer.TripleHandlerException;
import org.apache.commons.codec.digest.DigestUtils;
import org.eclipse.rdf4j.model.IRI;
import org.eclipse.rdf4j.model.Literal;
import org.eclipse.rdf4j.model.Model;
import org.eclipse.rdf4j.model.Resource;
import org.eclipse.rdf4j.model.Statement;
import org.eclipse.rdf4j.model.Value;
import org.eclipse.rdf4j.model.ValueFactory;
import org.eclipse.rdf4j.model.impl.SimpleValueFactory;
import org.eclipse.rdf4j.model.impl.TreeModel;
import org.eclipse.rdf4j.model.util.Models;
import org.eclipse.rdf4j.model.vocabulary.RDF;
import org.eclipse.rdf4j.model.vocabulary.XMLSchema;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;

import java.lang.invoke.MethodHandles;
import java.util.Collections;
import java.util.Set;
import java.util.stream.Collectors;

/**
 * Proof of concept for ANY23-396 example.
 */
public class PeopleExtractor extends CompositeTripleHandler {

private Logger log = LoggerFactory.getLogger(MethodHandles.lookup().lookupClass());

private static final CSV csv = CSV.getInstance();
    private static final ValueFactory vf = SimpleValueFactory.getInstance();
    public static final String RAW_NS = "urn:dataser:raw/";
    private static final IRI RAW_FIRST_NAME = vf.createIRI(RAW_NS, "FirstName");
    private static final IRI RAW_LAST_NAME = vf.createIRI(RAW_NS, "LastName");

private static final String NAMESPACE = "http://supercustom.net/ontology/";
    private static final IRI PERSON = vf.createIRI(NAMESPACE, "Person");
    private static final IRI FULL_NAME = vf.createIRI(NAMESPACE, "fullName");
    private static final IRI HASH = vf.createIRI(NAMESPACE, "hash");

public static Model createPerson(String fullName) {
        IRI s = vf.createIRI("http://rdf.supercustom.net/data/", DigestUtils.sha1Hex(fullName));
        Model model = new TreeModel();
        model.add(s, RDF.TYPE, PERSON);
        model.add(s, FULL_NAME, vf.createLiteral(fullName));
        model.add(s, HASH, vf.createLiteral(s.getLocalName(), XMLSchema.HEXBINARY));
        return model;
    };

private final Model csvModel = new TreeModel();

public PeopleExtractor(TripleHandler delegate) {
        super(Collections.singletonList(delegate));
    }

@Override
    public void receiveTriple(Resource s, IRI p, Value o, IRI g, ExtractionContext context) throws TripleHandlerException {
        if ("csv".equals(context.getExtractorName())) {
            csvModel.add(s, p, o, vf.createIRI(context.getUniqueID()));
        } else {
            super.receiveTriple(s, p, o, g, context);
        }
    }

@Override
    public void closeContext(ExtractionContext context) throws TripleHandlerException {
        Set<Resource> subjects = csvModel.filter(null, RDF.TYPE, csv.rowType)
                .stream().map(Statement::getSubject).collect(Collectors.toSet());

log.debug("List of rows: {}", subjects);

for (Resource rowId : subjects) {
            String firstName = Models.objectLiteral(csvModel.filter(rowId, RAW_FIRST_NAME, null))
                    .map(Literal::getLabel).orElse("");

String lastName = Models.objectLiteral(csvModel.filter(rowId, RAW_LAST_NAME, null))
                    .map(Literal::getLabel).orElse("");

String fullName = firstName + " " + lastName;

for (Statement s : createPerson(fullName)) {
                super.receiveTriple(s.getSubject(), s.getPredicate(), s.getObject(), null, context);
            }
        }

csvModel.clear();

super.closeContext(context);
    }

}