(tika) branch main updated: TIKA-4727 -- catch ioobe (#2885)

[tallison]

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

tballison 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 55655ed296 TIKA-4727 -- catch ioobe (#2885)
55655ed296 is described below

commit 55655ed296657a583679bf586e650c4100cd838f
Author: Tim Allison <talli...@apache.org>
AuthorDate: Tue Jun 9 21:49:52 2026 +0200

    TIKA-4727 -- catch ioobe (#2885)
---
 .../java/org/apache/tika/parser/microsoft/HSLFExtractor.java     | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git 
a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/HSLFExtractor.java
 
b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/HSLFExtractor.java
index e516979da0..dca24644dd 100644
--- 
a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/HSLFExtractor.java
+++ 
b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/HSLFExtractor.java
@@ -614,7 +614,14 @@ public class HSLFExtractor extends AbstractPOIFSExtractor {
         }
         for (HSLFShape shape : shapes) {
             if (shape instanceof HSLFPictureShape) {
-                HSLFPictureData pd = ((HSLFPictureShape) 
shape).getPictureData();
+                HSLFPictureData pd;
+                try {
+                    pd = ((HSLFPictureShape) shape).getPictureData();
+                } catch (IndexOutOfBoundsException e) {
+                    // corrupt Escher BSE record -- skip page anchoring for 
this shape
+                    EmbeddedDocumentUtil.recordEmbeddedStreamException(e, 
parentMetadata);
+                    continue;
+                }
                 if (pd != null) {
                     picToSlides.computeIfAbsent(pd.getIndex(), k -> new 
HashSet<>()).add(slideNum);
                 }