You are viewing a plain text version of this content. The canonical link for it is here.
Posted to oak-commits@jackrabbit.apache.org by ro...@apache.org on 2025/12/22 13:13:10 UTC
(jackrabbit-oak) branch issue/OAK-12046 created (now 2826884b50)
This is an automated email from the ASF dual-hosted git repository.
rombert pushed a change to branch issue/OAK-12046
in repository https://gitbox.apache.org/repos/asf/jackrabbit-oak.git
at 2826884b50 OAK-12046 - Update default Tika config
This branch includes the following new commits:
new 2826884b50 OAK-12046 - Update default Tika config
The 1 revisions listed above as "new" are entirely new to this
repository and will be described in separate emails. The revisions
listed as "add" were already present in the repository and have only
been added to this reference.
(jackrabbit-oak) 01/01: OAK-12046 - Update default Tika config
Posted by ro...@apache.org.
This is an automated email from the ASF dual-hosted git repository.
rombert pushed a commit to branch issue/OAK-12046
in repository https://gitbox.apache.org/repos/asf/jackrabbit-oak.git
commit 2826884b50e3065a6d94d4b1e8b274c2e7e46849
Author: Robert Munteanu <ro...@apache.org>
AuthorDate: Mon Dec 22 14:12:21 2025 +0100
OAK-12046 - Update default Tika config
---
.../jackrabbit/oak/plugins/index/lucene/tika-config.xml | 11 ++++++++++-
.../oak/plugins/index/search/spi/editor/tika-config.xml | 11 ++++++++++-
2 files changed, 20 insertions(+), 2 deletions(-)
diff --git a/oak-lucene/src/main/resources/org/apache/jackrabbit/oak/plugins/index/lucene/tika-config.xml b/oak-lucene/src/main/resources/org/apache/jackrabbit/oak/plugins/index/lucene/tika-config.xml
index 54f229d699..07e002c479 100644
--- a/oak-lucene/src/main/resources/org/apache/jackrabbit/oak/plugins/index/lucene/tika-config.xml
+++ b/oak-lucene/src/main/resources/org/apache/jackrabbit/oak/plugins/index/lucene/tika-config.xml
@@ -24,7 +24,16 @@
<detector class="org.apache.tika.detect.TypeDetector"/>
</detectors>
<parsers>
- <parser class="org.apache.tika.parser.DefaultParser"/>
+ <parser class="org.apache.tika.parser.DefaultParser">
+ <!-- the PDF parser is configured below -->
+ <parser-exclude class="org.apache.tika.parser.pdf.PDFParser"/>
+ </parser>
+ <parser class="org.apache.tika.parser.pdf.PDFParser">
+ <params>
+ <!-- Disable XFA/AcroForm extraction -->
+ <param name="extractAcroFormContent" type="bool">false</param>
+ </params>
+ </parser>
<parser class="org.apache.tika.parser.EmptyParser">
<!-- Disable package extraction as it's too resource-intensive -->
<mime>application/x-archive</mime>
diff --git a/oak-search/src/main/resources/org/apache/jackrabbit/oak/plugins/index/search/spi/editor/tika-config.xml b/oak-search/src/main/resources/org/apache/jackrabbit/oak/plugins/index/search/spi/editor/tika-config.xml
index 54f229d699..07e002c479 100644
--- a/oak-search/src/main/resources/org/apache/jackrabbit/oak/plugins/index/search/spi/editor/tika-config.xml
+++ b/oak-search/src/main/resources/org/apache/jackrabbit/oak/plugins/index/search/spi/editor/tika-config.xml
@@ -24,7 +24,16 @@
<detector class="org.apache.tika.detect.TypeDetector"/>
</detectors>
<parsers>
- <parser class="org.apache.tika.parser.DefaultParser"/>
+ <parser class="org.apache.tika.parser.DefaultParser">
+ <!-- the PDF parser is configured below -->
+ <parser-exclude class="org.apache.tika.parser.pdf.PDFParser"/>
+ </parser>
+ <parser class="org.apache.tika.parser.pdf.PDFParser">
+ <params>
+ <!-- Disable XFA/AcroForm extraction -->
+ <param name="extractAcroFormContent" type="bool">false</param>
+ </params>
+ </parser>
<parser class="org.apache.tika.parser.EmptyParser">
<!-- Disable package extraction as it's too resource-intensive -->
<mime>application/x-archive</mime>