Author: schuch
Date: Mon Nov 28 20:10:45 2022
New Revision: 1905582

URL: http://svn.apache.org/viewvc?rev=1905582&view=rev
Log:
Fix forbiddenapis violation in rmeta TikaExtractor

Modified:
    
manifoldcf/trunk/connectors/tikaservice-rmeta/connector/src/main/java/org/apache/manifoldcf/agents/transformation/tikaservice/rmeta/TikaExtractor.java

Modified: 
manifoldcf/trunk/connectors/tikaservice-rmeta/connector/src/main/java/org/apache/manifoldcf/agents/transformation/tikaservice/rmeta/TikaExtractor.java
URL: 
http://svn.apache.org/viewvc/manifoldcf/trunk/connectors/tikaservice-rmeta/connector/src/main/java/org/apache/manifoldcf/agents/transformation/tikaservice/rmeta/TikaExtractor.java?rev=1905582&r1=1905581&r2=1905582&view=diff
==============================================================================
--- 
manifoldcf/trunk/connectors/tikaservice-rmeta/connector/src/main/java/org/apache/manifoldcf/agents/transformation/tikaservice/rmeta/TikaExtractor.java
 (original)
+++ 
manifoldcf/trunk/connectors/tikaservice-rmeta/connector/src/main/java/org/apache/manifoldcf/agents/transformation/tikaservice/rmeta/TikaExtractor.java
 Mon Nov 28 20:10:45 2022
@@ -904,12 +904,12 @@ public class TikaExtractor extends org.a
 
                   // If the are embedded resources, add their names, if 
possible, to the metadata
                   for (final String embeddedResourceName : 
embeddedResourcesNames) {
-                    final int resourceNameBytesLength = 
embeddedResourceName.getBytes().length;
+                    final int resourceNameBytesLength = 
embeddedResourceName.getBytes(StandardCharsets.UTF_8).length;
 
                     final int totalMetadataLengthPreview = totalMetadataLength 
+ resourceNameBytesLength;
                     if (totalMetadataLengthPreview <= sp.totalMetadataLimit) {
                       if (!metadata.containsKey("embeddedResourcesNames")) {
-                        totalMetadataLength += 
"embeddedResourcesNames".getBytes().length;
+                        totalMetadataLength += 
"embeddedResourcesNames".getBytes(StandardCharsets.UTF_8).length;
                         metadata.put("embeddedResourcesNames", new 
ArrayList<>());
                       }
                       
metadata.get("embeddedResourcesNames").add(embeddedResourceName);


Reply via email to