[Port to dtq-dev] Log unparsable-PDF filter-media errors as WARN, not ERROR

dspace-api/src/main/java/org/dspace/app/mediafilter/PDFBoxThumbnail.java

@@ -8,6 +8,7 @@
 package org.dspace.app.mediafilter;
 
 import java.awt.image.BufferedImage;
+import java.io.IOException;
 import java.io.InputStream;
 
 import org.apache.logging.log4j.Logger;
@@ -79,6 +80,13 @@ public InputStream getDestinationStream(Item currentItem, InputStream source, bo
         } catch (InvalidPasswordException ex) {
             log.error("PDF is encrypted. Cannot create thumbnail (item: {})", currentItem::getHandle);
             return null;
+        } catch (IOException ex) {
+            // A malformed/non-standard PDF (bad %PDF- header, missing xref, truncated file, etc.)
+            // is a data-quality issue in the source bitstream, not a DSpace fault. Skip the
+            // thumbnail instead of failing the whole filter-media run.
+            log.warn("PDF could not be parsed by PDFBox. Cannot create thumbnail (item: {}): {}",
+                    currentItem::getHandle, ex::getMessage);
+            return null;
         }
 
         // Generate thumbnail derivative and return as IO stream.

dspace-api/src/main/java/org/dspace/app/mediafilter/TikaTextExtractionFilter.java

@@ -85,10 +85,13 @@ public InputStream getDestinationStream(Item currentItem, InputStream source, bo
             tika.setMaxStringLength(maxChars); // Tell Tika the maximum number of characters to extract
             extractedText = tika.parseToString(source);
         } catch (IOException e) {
-            System.err.format("Unable to extract text from bitstream in Item %s%n", currentItem.getID().toString());
-            e.printStackTrace(System.err);
-            log.error("Unable to extract text from bitstream in Item {}", currentItem.getID().toString(), e);
-            throw e;
+            // A malformed/non-standard source file (e.g. a PDF with a corrupt header, missing
+            // xref, or truncated content) is a data-quality issue in the bitstream, not a
+            // DSpace fault. Skip text extraction for it instead of failing the whole
+            // filter-media run.
+            log.warn("Unable to extract text from bitstream in Item {}: {}",
+                    currentItem.getHandle(), e.getMessage());
+            return null;
         } catch (OutOfMemoryError oe) {
             System.err.format("OutOfMemoryError occurred when extracting text from bitstream in Item %s. " +
                 "You may wish to enable 'textextractor.use-temp-file'.%n", currentItem.getID().toString());