You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tika.apache.org by ta...@apache.org on 2019/11/22 18:49:07 UTC

[tika] branch branch_1x updated: add embedding depth to rpw handler

This is an automated email from the ASF dual-hosted git repository.

tallison pushed a commit to branch branch_1x
in repository https://gitbox.apache.org/repos/asf/tika.git


The following commit(s) were added to refs/heads/branch_1x by this push:
     new 5c1c29c  add embedding depth to rpw handler
5c1c29c is described below

commit 5c1c29cae749fdf240b6d3a95441302c4f5450b8
Author: tballison <ta...@apache.org>
AuthorDate: Fri Nov 22 13:48:50 2019 -0500

    add embedding depth to rpw handler
---
 .../org/apache/tika/sax/AbstractRecursiveParserWrapperHandler.java  | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/tika-core/src/main/java/org/apache/tika/sax/AbstractRecursiveParserWrapperHandler.java b/tika-core/src/main/java/org/apache/tika/sax/AbstractRecursiveParserWrapperHandler.java
index c76080a..8515f09 100644
--- a/tika-core/src/main/java/org/apache/tika/sax/AbstractRecursiveParserWrapperHandler.java
+++ b/tika-core/src/main/java/org/apache/tika/sax/AbstractRecursiveParserWrapperHandler.java
@@ -54,6 +54,10 @@ public abstract class AbstractRecursiveParserWrapperHandler extends DefaultHandl
     public final static Property EMBEDDED_RESOURCE_PATH =
             Property.internalText(TikaCoreProperties.TIKA_META_PREFIX+"embedded_resource_path");
 
+    public final static Property EMBEDDED_DEPTH =
+            Property.internalInteger(TikaCoreProperties.TIKA_META_PREFIX+"embedded_depth");
+
+
     private final ContentHandlerFactory contentHandlerFactory;
 
     private static final int MAX_DEPTH = 100;
@@ -93,6 +97,7 @@ public abstract class AbstractRecursiveParserWrapperHandler extends DefaultHandl
         if (embeddedDepth >= MAX_DEPTH) {
             throw new SAXException("Max embedded depth reached: "+embeddedDepth);
         }
+        metadata.set(EMBEDDED_DEPTH, embeddedDepth);
     }
     /**
      * This is called after parsing each embedded document.  Override this
@@ -120,6 +125,7 @@ public abstract class AbstractRecursiveParserWrapperHandler extends DefaultHandl
         if (hasHitMaximumEmbeddedResources()) {
             metadata.set(EMBEDDED_RESOURCE_LIMIT_REACHED, "true");
         }
+        metadata.set(EMBEDDED_DEPTH, 0);
     }
 
     /**