Merge branch 'master' of code-repo.d4science.org:D-Net/dnet-hadoop

dhp-common/src/main/java/eu/dnetlib/dhp/common/PacePerson.java

@@ -16,6 +16,13 @@ import com.google.common.collect.Iterables;
 import com.google.common.collect.Lists;
 import com.google.common.hash.Hashing;
 
+/**
+* PacePerson tries to derive information from the fullname string of an author.
+* Such informations are Names, Surnames an Fullname split into terms. It provides also an additional field for
+* the original data.
+* The calculation of the names and the surnames is not always possible. When it is impossible to assert which are the
+* names and the surnames, the lists are empty.
+* */
 public class PacePerson {
 
 	private static final String UTF8 = "UTF-8";
@@ -26,10 +33,19 @@ public class PacePerson {
 
 	private static Set<String> particles = null;
 
+	/**
+	* Capitalizes a string
+	 *
+	 * @param s the string to capitalize
+	 * @return the input string with capital letter
+	* */
 	public static final String capitalize(final String s) {
 		return WordUtils.capitalize(s.toLowerCase(), ' ', '-');
 	}
 
+	/**
+	* Adds a dot to a string with length equals to 1
+	* */
 	public static final String dotAbbreviations(final String s) {
 		return s.length() == 1 ? s + "." : s;
 	}
@@ -46,6 +62,12 @@ public class PacePerson {
 		return h;
 	}
 
+	/**
+	* The constructor of the class. It fills the fields of the class basing on the input fullname.
+	 *
+	 * @param s the input string (fullname of the author)
+	 * @param aggressive set the string normalization type
+	* */
 	public PacePerson(String s, final boolean aggressive) {
 		original = s;
 		s = Normalizer.normalize(s, Normalizer.Form.NFD);
@@ -64,6 +86,7 @@ public class PacePerson {
 			// s = s.replaceAll("[\\W&&[^,-]]", "");
 		}
 
+		//if the string contains a comma, it can derive surname and name by splitting on it
 		if (s.contains(",")) {
 			final String[] arr = s.split(",");
 			if (arr.length == 1) {
@@ -74,21 +97,23 @@ public class PacePerson {
 				fullname.addAll(surname);
 				fullname.addAll(name);
 			}
-		} else {
+		} else {  //otherwise, it should rely on CAPS terms and short terms
 			fullname = splitTerms(s);
 
 			int lastInitialPosition = fullname.size();
 			boolean hasSurnameInUpperCase = false;
 
+			//computes lastInitialPosition and hasSurnameInUpperCase
 			for (int i = 0; i < fullname.size(); i++) {
 				final String term = fullname.get(i);
 				if (term.length() == 1) {
-					lastInitialPosition = i;
+					lastInitialPosition = i; //first word in the name longer than 1 (to avoid name with dots)
 				} else if (term.equals(term.toUpperCase())) {
-					hasSurnameInUpperCase = true;
+					hasSurnameInUpperCase = true; //if one of the words is CAPS
 				}
 			}
 
+			//manages particular cases of fullnames
 			if (lastInitialPosition < fullname.size() - 1) { // Case: Michele G. Artini
 				name = fullname.subList(0, lastInitialPosition + 1);
 				surname = fullname.subList(lastInitialPosition + 1, fullname.size());

dhp-common/src/test/java/eu/dnetlib/dhp/common/PacePersonTest.java

@@ -0,0 +1,26 @@
+package eu.dnetlib.dhp.common;
+
+import org.junit.jupiter.api.Test;
+
+import static org.junit.jupiter.api.Assertions.*;
+
+public class PacePersonTest {
+
+    @Test
+    public void pacePersonTest1(){
+
+        PacePerson p = new PacePerson("Artini, Michele", false);
+        assertEquals("Artini",p.getSurnameString());
+        assertEquals("Michele", p.getNameString());
+        assertEquals("Artini, Michele", p.getNormalisedFullname());
+    }
+
+    @Test
+    public void pacePersonTest2(){
+        PacePerson p = new PacePerson("Michele G. Artini", false);
+        assertEquals("Artini, Michele G.", p.getNormalisedFullname());
+        assertEquals("Michele G", p.getNameString());
+        assertEquals("Artini", p.getSurnameString());
+    }
+
+}

dhp-workflows/dhp-graph-provision/src/main/java/eu/dnetlib/dhp/oa/provision/utils/XmlRecordFactory.java

@@ -896,6 +896,9 @@ public class XmlRecordFactory implements Serializable {
 				if (p.getContracttype() != null) {
 					metadata.add(XmlSerializationUtils.mapQualifier("contracttype", p.getContracttype()));
 				}
+				if (p.getOamandatepublications() != null) {
+					metadata.add(XmlSerializationUtils.asXmlElement("oamandatepublications", p.getOamandatepublications().getValue()));
+				}
 				if (p.getEcsc39() != null) {
 					metadata.add(XmlSerializationUtils.asXmlElement("ecsc39", p.getEcsc39().getValue()));
 				}