[tika] branch main updated: TIKA-3248: avoid ClassCastException

[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 0810700  TIKA-3248: avoid ClassCastException
     new dd85c73  Merge origin/main into main
0810700 is described below

commit 081070065ec2a989ecfccb9d1186610bbce52f5e
Author: THausherr <til...@snafu.de>
AuthorDate: Mon Dec 14 05:46:44 2020 +0100

    TIKA-3248: avoid ClassCastException
---
 .../apache/tika/parser/pdf/AbstractPDF2XHTML.java  | 24 ++++++++++++----------
 1 file changed, 13 insertions(+), 11 deletions(-)

diff --git 
a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/AbstractPDF2XHTML.java
 
b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/AbstractPDF2XHTML.java
index 28093ce..2ba928a 100644
--- 
a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/AbstractPDF2XHTML.java
+++ 
b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/AbstractPDF2XHTML.java
@@ -473,17 +473,19 @@ class AbstractPDF2XHTML extends PDFTextStripper {
 
                 if (annotation instanceof PDAnnotationFileAttachment) {
                     PDAnnotationFileAttachment fann = 
(PDAnnotationFileAttachment) annotation;
-                    PDComplexFileSpecification fileSpec = 
(PDComplexFileSpecification) fann.getFile();
-                    try {
-                        AttributesImpl attributes = new AttributesImpl();
-                        attributes.addAttribute("", "source", "source", 
"CDATA", "annotation");
-                        
extractMultiOSPDEmbeddedFiles(fann.getAttachmentName(), fileSpec, attributes);
-                    } catch (SAXException e) {
-                        throw new IOExceptionWithCause("file embedded in 
annotation sax exception", e);
-                    } catch (TikaException e) {
-                        throw new IOExceptionWithCause("file embedded in 
annotation tika exception", e);
-                    } catch (IOException e) {
-                        handleCatchableIOE(e);
+                    if (fann.getFile() instanceof PDComplexFileSpecification) {
+                        PDComplexFileSpecification fileSpec = 
(PDComplexFileSpecification) fann.getFile();
+                        try {
+                            AttributesImpl attributes = new AttributesImpl();
+                            attributes.addAttribute("", "source", "source", 
"CDATA", "annotation");
+                            
extractMultiOSPDEmbeddedFiles(fann.getAttachmentName(), fileSpec, attributes);
+                        } catch (SAXException e) {
+                            throw new IOExceptionWithCause("file embedded in 
annotation sax exception", e);
+                        } catch (TikaException e) {
+                            throw new IOExceptionWithCause("file embedded in 
annotation tika exception", e);
+                        } catch (IOException e) {
+                            handleCatchableIOE(e);
+                        }
                     }
                 } else if (annotation instanceof PDAnnotationWidget) {
                     handleWidget((PDAnnotationWidget)annotation);