Merge pull request #10790 from vera/fix/perma-exporters-and-citations

fix: issues in exporters and citations for PermaLink/non-DOI PIDs

Author: ofahimIQSS

doc/release-notes/10790-fix pid handling in exporters and citations.md

@@ -0,0 +1,16 @@
+### Improvements to PID formatting in exports and citations
+
+Multiple small issues with the formatting of PIDs in the
+DDI exporters, and EndNote and BibTeX citation formats have
+been addressed. These should improve the ability to import
+Dataverse citations into reference managers and fix potential
+issues harvesting datasets using PermaLinks.
+
+Backward Incompatibility
+
+Changes to PID formatting occur in the DDI/DDI Html export formats
+and the EndNote and BibTex citation formats. These changes correct
+errors and improve conformance with best practices but could break
+parsing of these formats.
+ 
+For more information, see #10790.

doc/sphinx-guides/source/installation/config.rst

@@ -581,6 +581,7 @@ Note:
 
 - If you configure ``base-url``, it should include a "/" after the hostname like this: ``https://demo.dataverse.org/``.
 - When using multiple PermaLink providers, you should avoid ambiguous authority/separator/shoulder combinations that would result in the same overall prefix.
+- Configuring PermaLink providers differing only by their separator values is not supported.
 - In general, PermaLink authority/shoulder values should be alphanumeric. For other cases, admins may need to consider the potential impact of special characters in S3 storage identifiers, resolver URLs, exports, etc.
 
 .. _dataverse.pid.*.handlenet:

src/main/java/edu/harvard/iq/dataverse/DataCitation.java

@@ -38,6 +38,10 @@
 import org.apache.commons.text.StringEscapeUtils;
 import org.apache.commons.lang3.StringUtils;
 
+import static edu.harvard.iq.dataverse.pidproviders.doi.AbstractDOIProvider.DOI_PROTOCOL;
+import static edu.harvard.iq.dataverse.pidproviders.handle.HandlePidProvider.HDL_PROTOCOL;
+import static edu.harvard.iq.dataverse.pidproviders.perma.PermaLinkPidProvider.PERMA_PROTOCOL;
+
 /**
  *
  * @author gdurand, qqmyers
@@ -293,11 +297,13 @@ public void writeAsBibtexCitation(OutputStream os) throws IOException {
         out.write("version = {");
         out.write(version);
         out.write("},\r\n");
-        out.write("doi = {");
-        out.write(persistentId.getAuthority());
-        out.write("/");
-        out.write(persistentId.getIdentifier());
-        out.write("},\r\n");
+        if("doi".equals(persistentId.getProtocol())) {
+            out.write("doi = {");
+            out.write(persistentId.getAuthority());
+            out.write("/");
+            out.write(persistentId.getIdentifier());
+            out.write("},\r\n");
+        }
         out.write("url = {");
         out.write(persistentId.asURL());
         out.write("}\r\n");
@@ -595,11 +601,21 @@ private void createEndNoteXML(XMLStreamWriter xmlw) throws XMLStreamException {
         }
 
         xmlw.writeStartElement("urls");
-        xmlw.writeStartElement("related-urls");
-        xmlw.writeStartElement("url");
-        xmlw.writeCharacters(getPersistentId().asURL());
-        xmlw.writeEndElement(); // url
-        xmlw.writeEndElement(); // related-urls
+        if (persistentId != null) {
+            if (PERMA_PROTOCOL.equals(persistentId.getProtocol()) || HDL_PROTOCOL.equals(persistentId.getProtocol())) {
+                xmlw.writeStartElement("web-urls");
+                xmlw.writeStartElement("url");
+                xmlw.writeCharacters(getPersistentId().asURL());
+                xmlw.writeEndElement(); // url
+                xmlw.writeEndElement(); // web-urls
+            } else if (DOI_PROTOCOL.equals(persistentId.getProtocol())) {
+                xmlw.writeStartElement("related-urls");
+                xmlw.writeStartElement("url");
+                xmlw.writeCharacters(getPersistentId().asURL());
+                xmlw.writeEndElement(); // url
+                xmlw.writeEndElement(); // related-urls
+            }
+        }
         xmlw.writeEndElement(); // urls
 
         // a DataFile citation also includes the filename and (for Tabular
@@ -617,10 +633,9 @@ private void createEndNoteXML(XMLStreamWriter xmlw) throws XMLStreamException {
                     xmlw.writeEndElement(); // custom2
             }
         }
-        if (persistentId != null) {
+        if (persistentId != null && "doi".equals(persistentId.getProtocol())) {
             xmlw.writeStartElement("electronic-resource-num");
-            String electResourceNum = persistentId.getProtocol() + "/" + persistentId.getAuthority() + "/"
-                    + persistentId.getIdentifier();
+            String electResourceNum = persistentId.asRawIdentifier();
             xmlw.writeCharacters(electResourceNum);
             xmlw.writeEndElement();
         }

src/main/java/edu/harvard/iq/dataverse/DvObject.java

@@ -143,12 +143,14 @@ public String visit(DataFile df) {
     @Column(insertable = false, updatable = false) private String dtype;
 
     /*
-    * Add DOI related fields
+    * Add PID related fields
     */
 
     private String protocol;
     private String authority;
 
+    private String separator;
+
     @Temporal(value = TemporalType.TIMESTAMP)
     private Date globalIdCreateTime;
 
@@ -323,6 +325,16 @@ public void setAuthority(String authority) {
         globalId=null;
     }
 
+    public String getSeparator() {
+        return separator;
+    }
+
+    public void setSeparator(String separator) {
+        this.separator = separator;
+        //Remove cached value
+        globalId=null;
+    }
+
     public Date getGlobalIdCreateTime() {
         return globalIdCreateTime;
     }
@@ -353,11 +365,13 @@ public void setGlobalId( GlobalId pid ) {
         if ( pid == null ) {
             setProtocol(null);
             setAuthority(null);
+            setSeparator(null);
             setIdentifier(null);
         } else {
             //These reset globalId=null
             setProtocol(pid.getProtocol());
             setAuthority(pid.getAuthority());
+            setSeparator(pid.getSeparator());
             setIdentifier(pid.getIdentifier());
         }
     }

src/main/java/edu/harvard/iq/dataverse/GlobalId.java

@@ -63,6 +63,10 @@ public String getAuthority() {
         return authority;
     }
 
+    public String getSeparator() {
+        return separator;
+    }
+
     public String getIdentifier() {
         return identifier;
     }

src/main/java/edu/harvard/iq/dataverse/api/dto/DatasetDTO.java

@@ -12,6 +12,7 @@ public class DatasetDTO implements java.io.Serializable {
         private String identifier;
         private String protocol;
         private String authority;
+        private String separator;
         private String globalIdCreateTime;
         private String publisher;
         private String publicationDate;
@@ -51,6 +52,14 @@ public void setAuthority(String authority) {
         this.authority = authority;
     }
 
+    public String getSeparator() {
+        return separator;
+    }
+
+    public void setSeparator(String separator) {
+        this.separator = separator;
+    }
+
     public String getGlobalIdCreateTime() {
         return globalIdCreateTime;
     }
@@ -94,7 +103,7 @@ public void setPublicationDate(String publicationDate) {
 
     @Override
     public String toString() {
-        return "DatasetDTO{" + "id=" + id + ", identifier=" + identifier + ", protocol=" + protocol + ", authority=" + authority + ", globalIdCreateTime=" + globalIdCreateTime + ", datasetVersion=" + datasetVersion + ", dataFiles=" + dataFiles + '}';
+        return "DatasetDTO{" + "id=" + id + ", identifier=" + identifier + ", protocol=" + protocol + ", authority=" + authority + ", separator=" + separator + ", globalIdCreateTime=" + globalIdCreateTime + ", datasetVersion=" + datasetVersion + ", dataFiles=" + dataFiles + '}';
     }
 
     public void setMetadataLanguage(String metadataLanguage) {