Skip to content

OAK-12046 - Update default Tika config #2671

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
rombert wants to merge 2 commits into
base: trunk
Choose a base branch
from
+26 −3
Draft

OAK-12046 - Update default Tika config #2671

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
2826884
OAK-12046 - Update default Tika config
rombert Dec 22, 2025
3ad34c5
OAK-12046 - Update default Tika config
rombert Dec 22, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions oak-lucene/pom.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -116,6 +116,7 @@
</Export-Package>
<Import-Package>
org.apache.lucene.sandbox.*;resolution:=optional,
org.apache.tika.parser.pdf;resolution:=optional, <!-- Allow configuring the PDFParser -->
!org.apache.lucene.*,
!org.apache.jackrabbit.oak.cache,
!com.sun.management.*,
Expand Down
11 changes: 10 additions & 1 deletion oak-lucene/src/main/resources/org/apache/jackrabbit/oak/plugins/index/lucene/tika-config.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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>
Expand Down
6 changes: 5 additions & 1 deletion ...rg/apache/jackrabbit/oak/plugins/index/search/spi/binary/FulltextBinaryTextExtractor.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -33,6 +33,7 @@
import org.apache.jackrabbit.oak.stats.StatisticsProvider;
import org.apache.jackrabbit.oak.stats.StatsOptions;
import org.apache.jackrabbit.oak.stats.TimerStats;
import org.apache.tika.config.ServiceLoader;
import org.apache.tika.config.TikaConfig;
import org.apache.tika.exception.TikaException;
import org.apache.tika.exception.WriteLimitReachedException;
Expand Down Expand Up @@ -287,7 +288,9 @@ private static TikaConfigHolder initializeTikaConfig(@Nullable IndexDefinition d
String configSource = null;

try {
Thread.currentThread().setContextClassLoader(FulltextIndexEditorContext.class.getClassLoader());
ClassLoader newContextClassLoader = FulltextIndexEditorContext.class.getClassLoader();
Thread.currentThread().setContextClassLoader(newContextClassLoader);
ServiceLoader.setContextClassLoader(newContextClassLoader);
if (definition != null && definition.hasCustomTikaConfig()) {
log.debug("[{}] Using custom tika config", definition.getIndexName());
configSource = "Custom config at " + definition.getIndexPath();
Expand All @@ -308,6 +311,7 @@ private static TikaConfigHolder initializeTikaConfig(@Nullable IndexDefinition d
} finally {
IOUtils.closeQuietly(configStream);
Thread.currentThread().setContextClassLoader(current);
ServiceLoader.setContextClassLoader(null); // Tika default is null
}
return new TikaConfigHolder(TikaConfig.getDefaultConfig(), "Default Config");
}
Expand Down
11 changes: 10 additions & 1 deletion .../main/resources/org/apache/jackrabbit/oak/plugins/index/search/spi/editor/tika-config.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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>
Expand Down
Loading