(tika) branch main updated: TIKA-4445: support dc:rights

[tilman]

This is an automated email from the ASF dual-hosted git repository.

tilman pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/tika.git


The following commit(s) were added to refs/heads/main by this push:
     new 2c20c30ea TIKA-4445: support dc:rights
2c20c30ea is described below

commit 2c20c30ea7c2f80da963afbc8ec79b9203ba73df
Author: Tilman Hausherr <til...@apache.org>
AuthorDate: Thu Jun 26 20:51:58 2025 +0200

    TIKA-4445: support dc:rights
---
 .../main/java/org/apache/tika/parser/pdf/PDMetadataExtractor.java    | 5 +++--
 .../src/test/java/org/apache/tika/parser/pdf/CustomTikaXMPTest.java  | 1 +
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git 
a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/PDMetadataExtractor.java
 
b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/PDMetadataExtractor.java
index a8d35e1ba..9489fd007 100644
--- 
a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/PDMetadataExtractor.java
+++ 
b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/PDMetadataExtractor.java
@@ -78,7 +78,7 @@ public class PDMetadataExtractor {
     public static void extract(XMPMetadata xmp, Metadata metadata, 
ParseContext context) {
         extractBasic(xmp, metadata);
         extractPDF(xmp, metadata);
-        extractDublin(xmp, metadata);
+        extractDublinCore(xmp, metadata);
         JempboxExtractor.extractXMPMM(xmp, metadata);
         extractPDFA(xmp, metadata);
         extractPDFX(xmp, metadata);
@@ -106,7 +106,7 @@ public class PDMetadataExtractor {
         }
     }
 
-    private static void extractDublin(XMPMetadata xmp, Metadata metadata) {
+    private static void extractDublinCore(XMPMetadata xmp, Metadata metadata) {
         XMPSchemaDublinCore dcSchema = null;
         try {
             dcSchema = xmp.getDublinCoreSchema();
@@ -125,6 +125,7 @@ public class PDMetadataExtractor {
             extractDublinCoreListItems(metadata, TikaCoreProperties.RELATION, 
dcSchema);
             extractDublinCoreSimpleItem(metadata, TikaCoreProperties.SOURCE, 
dcSchema);
             extractDublinCoreListItems(metadata, TikaCoreProperties.SUBJECT, 
dcSchema);
+            extractMultilingualItems(metadata, TikaCoreProperties.RIGHTS, 
null, dcSchema);
         }
     }
 
diff --git 
a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pdf-module/src/test/java/org/apache/tika/parser/pdf/CustomTikaXMPTest.java
 
b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pdf-module/src/test/java/org/apache/tika/parser/pdf/CustomTikaXMPTest.java
index 56611c707..5e61740cf 100644
--- 
a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pdf-module/src/test/java/org/apache/tika/parser/pdf/CustomTikaXMPTest.java
+++ 
b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pdf-module/src/test/java/org/apache/tika/parser/pdf/CustomTikaXMPTest.java
@@ -89,6 +89,7 @@ public class CustomTikaXMPTest extends TikaTest {
         assertEquals("International Union of Thinkology", 
metadata.get(TikaCoreProperties.PUBLISHER));
         assertEquals("Relation", metadata.get(TikaCoreProperties.RELATION));
         assertEquals("Journal of Thinkology", 
metadata.get(TikaCoreProperties.SOURCE));
+        assertEquals("Copyright (c) 1939 International Union of Thinkology", 
metadata.get(TikaCoreProperties.RIGHTS));
         assertEquals("Thinking: is it needed?", 
metadata.get(TikaCoreProperties.DESCRIPTION));
         String[] subjects = metadata.getValues(TikaCoreProperties.SUBJECT);
         assertEquals(5, subjects.length);