[tika] branch main updated: TIKA-3832 -- move item count check into inner loop as added protection

[tallison]

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

tallison 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 a3072aeb7 TIKA-3832 -- move item count check into inner loop as added 
protection
a3072aeb7 is described below

commit a3072aeb7cf01f91cdb5d4e94408937cdade1086
Author: tallison <talli...@apache.org>
AuthorDate: Fri Aug 5 10:10:04 2022 -0400

    TIKA-3832 -- move item count check into inner loop as added protection
---
 .../src/main/java/org/apache/tika/parser/pdf/AbstractPDF2XHTML.java    | 3 +++
 1 file changed, 3 insertions(+)

diff --git 
a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/AbstractPDF2XHTML.java
 
b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/AbstractPDF2XHTML.java
index 9de6e0daf..7e7ef16ea 100644
--- 
a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/AbstractPDF2XHTML.java
+++ 
b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/AbstractPDF2XHTML.java
@@ -975,6 +975,9 @@ class AbstractPDF2XHTML extends PDFTextStripper {
                 if (seen.contains(current)) {
                     break;
                 }
+                if (itemCount > MAX_BOOKMARK_ITEMS) {
+                    break;
+                }
                 seen.add(current);
                 xhtml.startElement("li");
                 xhtml.characters(current.getTitle());