TIKA-4326: update pdfbox

apache · Jan 24, 2025 · 74f75cf · 74f75cf
1 parent 147d9b1
commit 74f75cf
Show file tree

Hide file tree

Showing 3 changed files with 3 additions and 6 deletions.
diff --git a/tika-parent/pom.xml b/tika-parent/pom.xml
@@ -420,8 +420,7 @@
     <osgi.util.version>1.2.0</osgi.util.version>
     <parso.version>2.0.14</parso.version>
     <pax.exam.version>4.14.0</pax.exam.version>
-    <!-- TODO when updating to 3.0.4, search for TIKA-2342 and achtivate the changes -->
-    <pdfbox.version>3.0.3</pdfbox.version>
+    <pdfbox.version>3.0.4</pdfbox.version>
     <poi.version>5.4.0</poi.version>
     <protobuf.version>3.25.5</protobuf.version>
     <quartz.version>2.5.0</quartz.version>

diff --git a/...ules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/PDFParserConfig.java b/...ules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/PDFParserConfig.java
@@ -226,8 +226,7 @@ public void configure(PDF2XHTML pdf2XHTML) {
             pdf2XHTML.setDropThreshold(dropThreshold);
         }
         pdf2XHTML.setSuppressDuplicateOverlappingText(isSuppressDuplicateOverlappingText());
-        // TODO TIKA-2342 activate after PDFBox release
-        //pdf2XHTML.setIgnoreContentStreamSpaceGlyphs(isIgnoreContentStreamSpaceGlyphs());
+        pdf2XHTML.setIgnoreContentStreamSpaceGlyphs(isIgnoreContentStreamSpaceGlyphs());
     }
 
     /**

diff --git a/...odules/tika-parser-pdf-module/src/test/java/org/apache/tika/parser/pdf/PDFParserTest.java b/...odules/tika-parser-pdf-module/src/test/java/org/apache/tika/parser/pdf/PDFParserTest.java
@@ -465,8 +465,7 @@ public void testDuplicateOverlappingText() throws Exception {
 
     }
 
-    // TODO TIKA-2342 activate after PDFBox release
-    // @Test
+    @Test
     public void testIgnoreContentStreamSpaceGlyphs() throws Exception {
         PDFParser parser = new PDFParser();
         // Default is false (keep spaces, don't sort):