Author: jmssiera
Date: Wed Apr 13 14:59:18 2022
New Revision: 1899815

URL: http://svn.apache.org/viewvc?rev=1899815&view=rev
Log:
Fix CONNECTORS-1703

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

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=1899815&r1=1899814&r2=1899815&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
 Wed Apr 13 14:59:18 2022
@@ -788,6 +788,7 @@ public class TikaExtractor extends org.a
                   int totalMetadataLength = 0;
                   boolean maxMetadataReached = false;
                   boolean metadataSkipped = false;
+                  boolean metadataTruncated = false;
 
                   if (token != null) {
                     while ((token = jParser.nextToken()) != null && token != 
JsonToken.END_OBJECT) {
@@ -863,6 +864,9 @@ public class TikaExtractor extends org.a
                             if (!unknownException) {
                               skipMetadata(jParser);
                             }
+                          } else if 
(fieldName.startsWith("X-TIKA:WARN:truncated_metadata")) {
+                            metadataTruncated = true;
+                            skipMetadata(jParser);
                           } else {
                             skipMetadata(jParser);
                           }
@@ -883,6 +887,10 @@ public class TikaExtractor extends org.a
                   } else if (metadataSkipped) {
                     description += "Some metadata have been skipped because 
their names or values exceeded the limits" + System.lineSeparator();
                   }
+
+                  if (metadataTruncated) {
+                    description += "Some metadata have been truncated by Tika 
because they exceeded the limits specified in the Tika conf" + 
System.lineSeparator();
+                  }
                 }
               } else if (responseCode == 503) {
                 // Service interruption; Tika trying to come up.

Modified: manifoldcf/trunk/connectors/tikaservice-rmeta/pom.xml
URL: 
http://svn.apache.org/viewvc/manifoldcf/trunk/connectors/tikaservice-rmeta/pom.xml?rev=1899815&r1=1899814&r2=1899815&view=diff
==============================================================================
--- manifoldcf/trunk/connectors/tikaservice-rmeta/pom.xml (original)
+++ manifoldcf/trunk/connectors/tikaservice-rmeta/pom.xml Wed Apr 13 14:59:18 
2022
@@ -86,11 +86,6 @@
       <version>${project.version}</version>
     </dependency>
     <dependency>
-      <groupId>org.apache.tika</groupId>
-      <artifactId>tika-core</artifactId>
-      <version>${tika.version}</version>
-    </dependency>
-    <dependency>
       <groupId>org.apache.httpcomponents</groupId>
       <artifactId>httpclient</artifactId>
       <version>${httpcomponent.httpclient.version}</version>


Reply via email to