#1319 - Generic support for PubAnnotation

dkpro-core-io-pubannotation-asl/pom.xml

@@ -84,5 +84,10 @@
       <artifactId>dkpro-core-api-ner-asl</artifactId>
       <scope>test</scope>
     </dependency>
+    <dependency>
+      <groupId>de.tudarmstadt.ukp.dkpro.core</groupId>
+      <artifactId>de.tudarmstadt.ukp.dkpro.core.io.conll-asl</artifactId>
+      <scope>test</scope>
+    </dependency>
   </dependencies>
 </project>

dkpro-core-io-pubannotation-asl/src/main/java/org/dkpro/core/io/pubannotation/GenericPubAnnotationReader.java

@@ -0,0 +1,127 @@
+/*
+ * Licensed to the Technische Universität Darmstadt under one
+ * or more contributor license agreements.  See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership.  The Technische Universität Darmstadt 
+ * 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.
+ *  
+ * 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.dkpro.core.io.pubannotation;
+
+import java.io.BufferedInputStream;
+import java.io.IOException;
+import java.io.InputStream;
+
+import org.apache.uima.UimaContext;
+import org.apache.uima.collection.CollectionException;
+import org.apache.uima.fit.descriptor.ConfigurationParameter;
+import org.apache.uima.fit.descriptor.MimeTypeCapability;
+import org.apache.uima.fit.descriptor.ResourceMetaData;
+import org.apache.uima.fit.descriptor.TypeCapability;
+import org.apache.uima.jcas.JCas;
+import org.apache.uima.resource.ResourceInitializationException;
+import org.dkpro.core.io.pubannotation.internal.GenericPubAnnotation2DKPro;
+import org.dkpro.core.io.pubannotation.internal.model.PADocument;
+
+import com.fasterxml.jackson.core.JsonParser;
+import com.fasterxml.jackson.databind.ObjectMapper;
+
+import de.tudarmstadt.ukp.dkpro.core.api.io.JCasResourceCollectionReader_ImplBase;
+import de.tudarmstadt.ukp.dkpro.core.api.metadata.type.DocumentMetaData;
+import de.tudarmstadt.ukp.dkpro.core.api.parameter.MimeTypes;
+
+/**
+ * Reader for the PubAnnotation format.
+ * 
+ * Since the PubAnnotation format only associates spans/relations with simple values and since
+ * annotations are not typed, it is necessary to define target types and features via
+ * {@link #PARAM_SPAN_TYPE} and {@link #PARAM_SPAN_LABEL_FEATURE}. In PubAnnotation, every
+ * annotation has an ID. If the target type has a suitable feature to retain the ID, it can be
+ * configured via {@link #PARAM_SPAN_ID_FEATURE}.
+ * 
+ * The {@code sourcedb} and {@code sourceid} from the PubAnnotation document are imported as
+ * {@link DocumentMetaData#setCollectionId(String) collectionId} and
+ * {@link DocumentMetaData#setDocumentId(String) documentId} respectively. If present, also the
+ * {@code target} is imported as {@link DocumentMetaData#setDocumentUri(String) documentUri}. The
+ * {@link DocumentMetaData#setDocumentBaseUri(String) documentBaseUri} is cleared in this case.
+ * 
+ * Currently supports only span annotations, i.e. no relations or modifications. Discontinuous
+ * segments are also not supported.
+ * 
+ * @see <a href="http://www.pubannotation.org/docs/annotation-format/">PubAnnotation format</a>
+ */
+@ResourceMetaData(name = "PubAnnotation Reader")
+@MimeTypeCapability({MimeTypes.APPLICATION_X_PUB_ANNOTATION_JSON})
+@TypeCapability(
+        outputs = { 
+                "de.tudarmstadt.ukp.dkpro.core.api.metadata.type.DocumentMetaData" })
+public class GenericPubAnnotationReader
+    extends JCasResourceCollectionReader_ImplBase
+{
+    /**
+     * The span annotation type to which the PubAnnotation spans are mapped.
+     */
+    public static final String PARAM_SPAN_TYPE = "spanType";
+    @ConfigurationParameter(name = PARAM_SPAN_TYPE, mandatory = true)
+    private String spanType;
+
+    /**
+     * The feature on the span annotation type which receives the ID.
+     */
+    public static final String PARAM_SPAN_ID_FEATURE = "spanIdFeature";
+    @ConfigurationParameter(name = PARAM_SPAN_ID_FEATURE, mandatory = false)
+    private String spanIdFeature;
+
+    /**
+     * The feature on the span annotation type which receives the label.
+     */
+    public static final String PARAM_SPAN_LABEL_FEATURE = "spanLabelFeature";
+    @ConfigurationParameter(name = PARAM_SPAN_LABEL_FEATURE, mandatory = false)
+    private String spanLabelFeature;
+
+    /**
+     * The feature on the span annotation type which receives the label.
+     */
+    public static final String PARAM_RESOLVE_NAMESPACES = "resolveNamespaces";
+    @ConfigurationParameter(name = PARAM_RESOLVE_NAMESPACES, mandatory = true, defaultValue = "false")
+    private boolean resolveNamespaces;
+
+    private ObjectMapper mapper;
+
+    @Override
+    public void initialize(UimaContext aContext)
+        throws ResourceInitializationException
+    {
+        super.initialize(aContext);
+
+        mapper = new ObjectMapper();
+        // Hack because LXF dumper presently creates invalid JSON
+        mapper.configure(JsonParser.Feature.ALLOW_SINGLE_QUOTES, true);
+    }
+
+    @Override
+    public void getNext(JCas aCAS)
+        throws IOException, CollectionException
+    {
+        Resource res = nextFile();
+        initCas(aCAS, res);
+
+        GenericPubAnnotation2DKPro converter = new GenericPubAnnotation2DKPro();
+        converter.setSpanMapping(spanType, spanIdFeature, spanLabelFeature);
+        converter.setResolveNamespaces(resolveNamespaces);
+
+        try (InputStream is = new BufferedInputStream(res.getInputStream())) {
+            PADocument doc = mapper.readValue(is, PADocument.class);
+            converter.convert(doc, aCAS);
+        }
+    }
+}

dkpro-core-io-pubannotation-asl/src/main/java/org/dkpro/core/io/pubannotation/GenericPubAnnotationWriter.java

@@ -0,0 +1,96 @@
+/*
+ * Licensed to the Technische Universität Darmstadt under one
+ * or more contributor license agreements.  See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership.  The Technische Universität Darmstadt 
+ * 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.
+ *  
+ * 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.dkpro.core.io.pubannotation;
+
+import java.io.OutputStream;
+
+import org.apache.uima.UimaContext;
+import org.apache.uima.analysis_engine.AnalysisEngineProcessException;
+import org.apache.uima.fit.descriptor.ConfigurationParameter;
+import org.apache.uima.fit.descriptor.MimeTypeCapability;
+import org.apache.uima.fit.descriptor.ResourceMetaData;
+import org.apache.uima.fit.descriptor.TypeCapability;
+import org.apache.uima.jcas.JCas;
+import org.apache.uima.resource.ResourceInitializationException;
+import org.dkpro.core.io.pubannotation.internal.GenericDKPro2PubAnnotation;
+import org.dkpro.core.io.pubannotation.internal.model.PADocument;
+
+import com.fasterxml.jackson.databind.ObjectMapper;
+
+import de.tudarmstadt.ukp.dkpro.core.api.io.JCasFileWriter_ImplBase;
+import de.tudarmstadt.ukp.dkpro.core.api.metadata.type.DocumentMetaData;
+import de.tudarmstadt.ukp.dkpro.core.api.parameter.ComponentParameters;
+import de.tudarmstadt.ukp.dkpro.core.api.parameter.MimeTypes;
+
+/**
+ * Writer for the PubAnnotation format.
+ * 
+ * The {@code sourcedb} and {@code sourceid} from the PubAnnotation document are exported from
+ * {@link DocumentMetaData#setCollectionId(String) collectionId} and
+ * {@link DocumentMetaData#setDocumentId(String) documentId} respectively. The {@code target} is
+ * exported from {@link DocumentMetaData#setDocumentUri(String) documentUri}.
+ * 
+ * Currently supports only span annotations, i.e. no relations or modifications. Discontinuous
+ * segments are also not supported.
+ * 
+ * @see <a href="http://www.pubannotation.org/docs/annotation-format/">PubAnnotation format</a>
+ */
+@ResourceMetaData(name = "PubAnnotation Writer")
+@MimeTypeCapability({MimeTypes.APPLICATION_X_PUB_ANNOTATION_JSON})
+@TypeCapability(
+        inputs = { 
+                "de.tudarmstadt.ukp.dkpro.core.api.metadata.type.DocumentMetaData" })
+public class GenericPubAnnotationWriter
+    extends JCasFileWriter_ImplBase
+{
+    /**
+     * Specify the suffix of output files. Default value <code>.json</code>. If the suffix is not
+     * needed, provide an empty string as value.
+     */
+    public static final String PARAM_FILENAME_EXTENSION = 
+            ComponentParameters.PARAM_FILENAME_EXTENSION;
+    @ConfigurationParameter(name = PARAM_FILENAME_EXTENSION, mandatory = true, defaultValue = ".json")
+    private String filenameSuffix;
+
+    private ObjectMapper mapper;
+
+    @Override
+    public void initialize(UimaContext aContext)
+        throws ResourceInitializationException
+    {
+        super.initialize(aContext);
+
+        mapper = new ObjectMapper();
+    }
+
+    @Override
+    public void process(JCas aJCas)
+        throws AnalysisEngineProcessException
+    {
+        PADocument doc = new PADocument();
+
+        GenericDKPro2PubAnnotation converter = new GenericDKPro2PubAnnotation();
+        converter.convert(aJCas, doc);
+
+        try (OutputStream docOS = getOutputStream(aJCas, filenameSuffix)) {
+            mapper.writerWithDefaultPrettyPrinter().writeValue(docOS, doc);
+        }
+        catch (Exception e) {
+            throw new AnalysisEngineProcessException(e);
+        }
+    }
+}