Merge pull request #8475 from QualitativeDataRepository/IQSS/8474-poi…

…_update

Iqss/8474 poi/tika updates

pom.xml

@@ -23,6 +23,8 @@
         <flyway.version>5.2.4</flyway.version>
         <jhove.version>1.20.1</jhove.version>
         <jacoco.version>0.8.7</jacoco.version>
+        <poi.version>5.2.1</poi.version>
+        <tika.version>2.3.0</tika.version>
     </properties>
 
     <!-- Versions of dependencies used both directly and transitive are managed here.
@@ -293,17 +295,17 @@
         <dependency>
             <groupId>org.apache.poi</groupId>
             <artifactId>poi</artifactId>
-            <version>4.1.1</version>
+            <version>${poi.version}</version>
         </dependency>
         <dependency>
             <groupId>org.apache.poi</groupId>
             <artifactId>poi-ooxml</artifactId>
-            <version>4.1.1</version>
+            <version>${poi.version}</version>
         </dependency>
         <dependency>
             <groupId>org.apache.poi</groupId>
             <artifactId>poi-scratchpad</artifactId>
-            <version>4.1.1</version>
+            <version>${poi.version}</version>
         </dependency>
         <dependency>
             <groupId>org.openpreservation.jhove</groupId>
@@ -495,8 +497,13 @@
         <!--  Full text indexing -->
         <dependency>
             <groupId>org.apache.tika</groupId>
-            <artifactId>tika-parsers</artifactId>
-            <version>1.27</version>
+            <artifactId>tika-core</artifactId>
+            <version>${tika.version}</version>
+        </dependency>
+        <dependency>
+            <groupId>org.apache.tika</groupId>
+            <artifactId>tika-parsers-standard-package</artifactId>
+            <version>${tika.version}</version>
         </dependency>
         <!-- Named Entity Recognition -->
         <dependency>

src/main/java/edu/harvard/iq/dataverse/api/Datasets.java

@@ -1,6 +1,7 @@
 package edu.harvard.iq.dataverse.api;
 
 import edu.harvard.iq.dataverse.*;
+import edu.harvard.iq.dataverse.DatasetLock.Reason;
 import edu.harvard.iq.dataverse.actionlogging.ActionLogRecord;
 import edu.harvard.iq.dataverse.authorization.AuthenticationServiceBean;
 import edu.harvard.iq.dataverse.authorization.DataverseRole;
@@ -146,9 +147,6 @@
 import org.glassfish.jersey.media.multipart.FormDataContentDisposition;
 import org.glassfish.jersey.media.multipart.FormDataParam;
 import com.amazonaws.services.s3.model.PartETag;
-import com.beust.jcommander.Strings;
-
-import java.util.Map.Entry;
 
 @Path("datasets")
 public class Datasets extends AbstractApiBean {
@@ -2691,9 +2689,12 @@ public Response listLocks(@QueryParam("type") String lockType, @QueryParam("user
             try {
                 lockTypeValue = DatasetLock.Reason.valueOf(lockType);
             } catch (IllegalArgumentException iax) {
-                String validValues = Strings.join(",", DatasetLock.Reason.values());
+                StringJoiner reasonJoiner = new StringJoiner(", ");
+                for (Reason r: Reason.values()) {
+                    reasonJoiner.add(r.name());
+                };
                 String errorMessage = "Invalid lock type value: " + lockType + 
-                        "; valid lock types: " + validValues;
+                        "; valid lock types: " + reasonJoiner.toString();
                 return error(Response.Status.BAD_REQUEST, errorMessage);
             }
         }

src/main/java/edu/harvard/iq/dataverse/dataaccess/StoredOriginalFile.java

@@ -27,7 +27,8 @@
 import java.nio.channels.ReadableByteChannel;
 import java.util.logging.Logger;
 
-import org.apache.tika.io.IOUtils;
+import org.apache.commons.io.IOUtils;
+
 /**
  *
  * @author Leonid Andreev

src/main/java/edu/harvard/iq/dataverse/engine/command/impl/SetCurationStatusCommand.java

@@ -29,7 +29,6 @@
 
 import org.apache.solr.client.solrj.SolrServerException;
 
-import com.beust.jcommander.Strings;
 import com.google.api.LabelDescriptor;
 
 @RequiredPermissions(Permission.PublishDataset)

src/main/java/edu/harvard/iq/dataverse/ingest/tabulardata/impl/plugins/xlsx/XLSXFileReader.java

@@ -37,7 +37,7 @@
 
 import org.apache.poi.xssf.eventusermodel.XSSFReader;
 import org.apache.poi.xssf.usermodel.XSSFRichTextString;
-import org.apache.poi.xssf.model.SharedStringsTable;
+import org.apache.poi.xssf.model.SharedStrings;
 import org.apache.poi.openxml4j.opc.OPCPackage;
 import org.xml.sax.Attributes;
 import org.xml.sax.ContentHandler;
@@ -229,7 +229,7 @@ public void processSheet(InputStream inputStream, DataTable dataTable, PrintWrit
         dbglog.info("entering processSheet");
         OPCPackage pkg = OPCPackage.open(inputStream);
         XSSFReader r = new XSSFReader(pkg);
-        SharedStringsTable sst = r.getSharedStringsTable();
+        SharedStrings sst = r.getSharedStringsTable();
 
         XMLReader parser = fetchSheetParser(sst, dataTable, tempOut);
 
@@ -241,7 +241,7 @@ public void processSheet(InputStream inputStream, DataTable dataTable, PrintWrit
         sheet1.close();
     }
 
-    public XMLReader fetchSheetParser(SharedStringsTable sst, DataTable dataTable, PrintWriter tempOut) throws SAXException {
+    public XMLReader fetchSheetParser(SharedStrings sst, DataTable dataTable, PrintWriter tempOut) throws SAXException {
         // An attempt to use org.apache.xerces.parsers.SAXParser resulted 
         // in some weird conflict in the app; the default XMLReader obtained 
         // from the XMLReaderFactory (from xml-apis.jar) appears to be working
@@ -265,7 +265,7 @@ public XMLReader fetchSheetParser(SharedStringsTable sst, DataTable dataTable, P
     private static class SheetHandler extends DefaultHandler {
 
         private DataTable dataTable;
-        private SharedStringsTable sst;
+        private SharedStrings sst;
         private String cellContents;
         private boolean nextIsString;
         private boolean variableHeader;
@@ -277,11 +277,11 @@ private static class SheetHandler extends DefaultHandler {
         String[] dataRow; 
         PrintWriter tempOut; 
 
-        private SheetHandler(SharedStringsTable sst) {
+        private SheetHandler(SharedStrings sst) {
             this(sst, null, null);
         }
 
-        private SheetHandler(SharedStringsTable sst, DataTable dataTable, PrintWriter tempOut) {
+        private SheetHandler(SharedStrings sst, DataTable dataTable, PrintWriter tempOut) {
             this.sst = sst;
             this.dataTable = dataTable;
             this.tempOut = tempOut; 
@@ -410,7 +410,7 @@ public void endElement(String uri, String localName, String name)
             // Do it now, as characters() may be called more than once
             if (nextIsString) {
                 int idx = Integer.parseInt(cellContents);
-                cellContents = new XSSFRichTextString(sst.getEntryAt(idx)).toString();
+                cellContents = sst.getItemAt(idx).getString();
                 nextIsString = false;
             }
 

src/main/java/edu/harvard/iq/dataverse/search/IndexServiceBean.java

@@ -67,6 +67,8 @@
 import javax.json.JsonObject;
 import javax.persistence.EntityManager;
 import javax.persistence.PersistenceContext;
+
+import org.apache.commons.io.IOUtils;
 import org.apache.commons.lang3.StringUtils;
 import org.apache.solr.client.solrj.SolrClient;
 import org.apache.solr.client.solrj.SolrQuery;
@@ -80,7 +82,6 @@
 import org.apache.solr.common.SolrInputDocument;
 import org.apache.solr.common.params.CursorMarkParams;
 import org.apache.tika.parser.AutoDetectParser;
-import org.apache.tika.io.IOUtils;
 import org.apache.tika.metadata.Metadata;
 import org.apache.tika.parser.ParseContext;
 import org.apache.tika.sax.BodyContentHandler;