From 09ac1c52ff497daaf6b0d44ee46e1782a95671ae Mon Sep 17 00:00:00 2001
From: Alan Davis <alan.davis@alfresco.com>
Date: Fri, 16 May 2014 16:38:52 +0000
Subject: [PATCH] Merged HEAD-BUG-FIX (4.3/Cloud) to HEAD (4.3/Cloud)    68539:
 Merged V4.2-BUG-FIX (4.2.3) to HEAD-BUG-FIX (4.3/Cloud)       68468:
 MNT-11350: Upgrade of Tika to 1.6-SNAPSHOT          - Disabled parsing of
 embedded images in metadata extraction as well

git-svn-id: https://svn.alfresco.com/repos/alfresco-enterprise/alfresco/HEAD/root@70421 c4b6b30b-aa2e-2d43-bbcb-ca4b014f7261
---
 config/alfresco/content-services-context.xml | 27 +++++++++++---------
 1 file changed, 15 insertions(+), 12 deletions(-)

diff --git a/config/alfresco/content-services-context.xml b/config/alfresco/content-services-context.xml
index 92e04b9560..bd69136cf2 100644
--- a/config/alfresco/content-services-context.xml
+++ b/config/alfresco/content-services-context.xml
@@ -260,13 +260,26 @@
       </property>
    </bean>
 
+   <bean id="pdfBoxEmbededDocumentSelector"
+         class="org.alfresco.repo.content.metadata.MediaTypeDisablingDocumentSelector">
+      <property name="disabledMediaTypes">
+         <list>
+            <value>image/jpeg</value>
+            <value>image/tiff</value>
+            <value>image/png</value>
+         </list>
+       </property>
+   </bean>
+
    <!-- Content Metadata Extractors -->
    <!-- The last one listed for any mimetype will be used if available -->
    <!-- As such, the Tika auto-detect fallback should be listed first -->
    <bean id="extracter.TikaAuto"       class="org.alfresco.repo.content.metadata.TikaAutoMetadataExtracter"     parent="baseMetadataExtracter">
       <constructor-arg><ref bean="tikaConfig"/></constructor-arg>
    </bean>
-   <bean id="extracter.PDFBox"        class="org.alfresco.repo.content.metadata.PdfBoxMetadataExtracter"        parent="baseMetadataExtracter" />
+   <bean id="extracter.PDFBox"        class="org.alfresco.repo.content.metadata.PdfBoxMetadataExtracter"        parent="baseMetadataExtracter">
+      <property name="documentSelector" ref="pdfBoxEmbededDocumentSelector" />
+   </bean>
    <bean id="extracter.Poi"           class="org.alfresco.repo.content.metadata.PoiMetadataExtracter"           parent="baseMetadataExtracter" />
    <bean id="extracter.Office"        class="org.alfresco.repo.content.metadata.OfficeMetadataExtracter"        parent="baseMetadataExtracter" />
    <bean id="extracter.Mail"          class="org.alfresco.repo.content.metadata.MailMetadataExtracter"          parent="baseMetadataExtracter" />
@@ -462,17 +475,7 @@
    <bean id="transformer.PdfBox"
          class="org.alfresco.repo.content.transform.PdfBoxContentTransformer"
          parent="baseContentTransformer" >
-         <property name="documentSelector">
-            <bean class="org.alfresco.repo.content.metadata.MediaTypeDisablingDocumentSelector">
-                <property name="disabledMediaTypes">
-                    <list>
-                        <value>image/jpeg</value>
-                        <value>image/tiff</value>
-                        <value>image/png</value>
-                    </list>
-                </property>
-            </bean>
-         </property>
+         <property name="documentSelector" ref="pdfBoxEmbededDocumentSelector" />
    </bean>
    
    <bean id="transformer.PdfBox.TextToPdf"