You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tika.apache.org by ni...@apache.org on 2014/06/06 15:49:17 UTC

svn commit: r1600887 - in /tika/trunk/tika-core/src: main/resources/org/apache/tika/mime/tika-mimetypes.xml test/java/org/apache/tika/TikaDetectionTest.java

Author: nick
Date: Fri Jun  6 13:49:17 2014
New Revision: 1600887

URL: http://svn.apache.org/r1600887
Log:
TIKA-1326 MSI files are, rather improbably, based on OLE2 documents not Windows PE files. Patch from Luis Filipe Nassif plus test updates

Modified:
    tika/trunk/tika-core/src/main/resources/org/apache/tika/mime/tika-mimetypes.xml
    tika/trunk/tika-core/src/test/java/org/apache/tika/TikaDetectionTest.java

Modified: tika/trunk/tika-core/src/main/resources/org/apache/tika/mime/tika-mimetypes.xml
URL: http://svn.apache.org/viewvc/tika/trunk/tika-core/src/main/resources/org/apache/tika/mime/tika-mimetypes.xml?rev=1600887&r1=1600886&r2=1600887&view=diff
==============================================================================
--- tika/trunk/tika-core/src/main/resources/org/apache/tika/mime/tika-mimetypes.xml (original)
+++ tika/trunk/tika-core/src/main/resources/org/apache/tika/mime/tika-mimetypes.xml Fri Jun  6 13:49:17 2014
@@ -3010,12 +3010,21 @@
     <glob pattern="*.dll"/>
     <glob pattern="*.com"/>
     <glob pattern="*.bat"/>
-    <glob pattern="*.msi"/>
     <magic priority="50">
       <match value="MZ" type="string" offset="0"/>
     </magic>
   </mime-type>
 
+  <mime-type type="application/x-ms-installer">
+    <_comment>Microsoft Windows Installer</_comment> 
+    <sub-class-of type="application/x-tika-msoffice"/>
+    <alias type="application/x-windows-installer"/>
+    <alias type="application/x-msi"/>
+    <glob pattern="*.msi"/>
+    <glob pattern="*.msp"/>
+    <glob pattern="*.mst"/>
+  </mime-type>
+
   <mime-type type="application/x-msdownload;format=pe">
     <sub-class-of type="application/x-msdownload"/>
     <magic priority="55">

Modified: tika/trunk/tika-core/src/test/java/org/apache/tika/TikaDetectionTest.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-core/src/test/java/org/apache/tika/TikaDetectionTest.java?rev=1600887&r1=1600886&r2=1600887&view=diff
==============================================================================
--- tika/trunk/tika-core/src/test/java/org/apache/tika/TikaDetectionTest.java (original)
+++ tika/trunk/tika-core/src/test/java/org/apache/tika/TikaDetectionTest.java Fri Jun  6 13:49:17 2014
@@ -584,7 +584,8 @@ public class TikaDetectionTest {
         assertEquals("application/x-msdownload", tika.detect("x.dll"));
         assertEquals("application/x-msdownload", tika.detect("x.com"));
         assertEquals("application/x-msdownload", tika.detect("x.bat"));
-        assertEquals("application/x-msdownload", tika.detect("x.msi"));
+        // Differ from httpd - MSI is different from normal windows executables
+        //assertEquals("application/x-msdownload", tika.detect("x.msi"));
         assertEquals("application/x-msmediaview", tika.detect("x.mvb"));
         assertEquals("application/x-msmediaview", tika.detect("x.m13"));
         assertEquals("application/x-msmediaview", tika.detect("x.m14"));