This is an automated email from the ASF dual-hosted git repository.
tilman pushed a commit to branch branch_2x
in repository https://gitbox.apache.org/repos/asf/tika.git
The following commit(s) were added to refs/heads/branch_2x by this push:
new 0cba318f0 further improvements
0cba318f0 is described below
commit 0cba318f0ad871f1e565d7f1df2646a7b955b874
Author: tallison <[email protected]>
AuthorDate: Wed Aug 6 12:21:05 2025 -0400
further improvements
---
.../src/main/java/org/apache/tika/utils/XMLReaderUtils.java | 12 ++++++------
1 file changed, 6 insertions(+), 6 deletions(-)
diff --git a/tika-core/src/main/java/org/apache/tika/utils/XMLReaderUtils.java
b/tika-core/src/main/java/org/apache/tika/utils/XMLReaderUtils.java
index f00d513f1..ca5226a88 100644
--- a/tika-core/src/main/java/org/apache/tika/utils/XMLReaderUtils.java
+++ b/tika-core/src/main/java/org/apache/tika/utils/XMLReaderUtils.java
@@ -37,7 +37,6 @@ import javax.xml.parsers.ParserConfigurationException;
import javax.xml.parsers.SAXParser;
import javax.xml.parsers.SAXParserFactory;
import javax.xml.stream.XMLInputFactory;
-import javax.xml.stream.XMLResolver;
import javax.xml.transform.Transformer;
import javax.xml.transform.TransformerConfigurationException;
import javax.xml.transform.TransformerFactory;
@@ -122,8 +121,6 @@ public class XMLReaderUtils implements Serializable {
private static final AtomicInteger POOL_GENERATION = new AtomicInteger();
private static final EntityResolver IGNORING_SAX_ENTITY_RESOLVER =
(publicId, systemId) -> new InputSource(new StringReader(""));
- private static final XMLResolver IGNORING_STAX_ENTITY_RESOLVER =
- (publicID, systemID, baseURI, namespace) -> "";
/**
* Parser pool size
*/
@@ -285,7 +282,7 @@ public class XMLReaderUtils implements Serializable {
* If a factory is not explicitly specified, then a default factory
* instance is created and returned. The default factory instance is
* configured to be namespace-aware and to apply reasonable security
- * using the {@link #IGNORING_STAX_ENTITY_RESOLVER}.
+ * precautions.
*
* @return StAX input factory
* @since Apache Tika 1.13
@@ -293,12 +290,15 @@ public class XMLReaderUtils implements Serializable {
public static XMLInputFactory getXMLInputFactory() {
XMLInputFactory factory = XMLInputFactory.newFactory();
+ if (LOG.isDebugEnabled()) {
+ LOG.debug("XMLInputFactory class {}", factory.getClass());
+ }
+ factory.setProperty(XMLConstants.ACCESS_EXTERNAL_DTD, "");
tryToSetStaxProperty(factory, XMLInputFactory.IS_NAMESPACE_AWARE,
true);
tryToSetStaxProperty(factory, XMLInputFactory.IS_VALIDATING, false);
tryToSetStaxProperty(factory, XMLInputFactory.SUPPORT_DTD, false);
tryToSetStaxProperty(factory,
XMLInputFactory.IS_SUPPORTING_EXTERNAL_ENTITIES, false);
- factory.setXMLResolver(IGNORING_STAX_ENTITY_RESOLVER);
trySetStaxSecurityManager(factory);
return factory;
}
@@ -1083,4 +1083,4 @@ public class XMLReaderUtils implements Serializable {
trySetXercesSecurityManager(saxParser);
}
}
-}
+}
\ No newline at end of file
