PED test

dhp-workflows/dhp-bmuse/src/test/java/eu/dnetlib/dhp/bmuse/bioschema/Html2TriplesTest.java

@@ -0,0 +1,45 @@
+
+package eu.dnetlib.dhp.bmuse.bioschema;
+
+import java.io.IOException;
+import java.io.InputStream;
+import java.nio.charset.StandardCharsets;
+
+import org.apache.any23.Any23;
+import org.apache.any23.extractor.ExtractionException;
+import org.apache.any23.source.DocumentSource;
+import org.apache.any23.source.StringDocumentSource;
+import org.apache.any23.writer.NTriplesWriter;
+import org.apache.any23.writer.TripleHandler;
+import org.apache.any23.writer.TripleHandlerException;
+import org.apache.commons.io.IOUtils;
+import org.apache.commons.io.output.ByteArrayOutputStream;
+import org.junit.jupiter.api.Test;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+public class Html2TriplesTest {
+
+	static Logger logger = LoggerFactory.getLogger(Html2TriplesTest.class);
+
+	@Test
+//	@Disabled
+	void conversionTest() throws Exception {
+		InputStream is = Html2TriplesTest.class.getResourceAsStream("/eu/dnetlib/dhp/bmuse/bioschema/ped.html");
+		String page = IOUtils.toString(is, StandardCharsets.UTF_8.name());
+		DocumentSource source = new StringDocumentSource(page, "https://proteinensemble.org/PED00001");
+		Any23 runner = new Any23();
+		try (ByteArrayOutputStream out = new ByteArrayOutputStream();
+			TripleHandler handler = new NTriplesWriter(out);) {
+			runner.extract(source, handler);
+			logger.info(out.toString("UTF-8"));
+		} catch (ExtractionException e) {
+			logger.error("Cannot extract triples", e);
+		} catch (IOException e1) {
+			logger.error(" IO error whilst extracting triples", e1);
+		} catch (TripleHandlerException e2) {
+			logger.error("TripleHanderException", e2);
+		}
+
+	}
+}