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 2015/11/10 17:18:45 UTC

svn commit: r1713677 - in /tika/trunk: tika-core/src/main/resources/org/apache/tika/mime/ tika-parsers/src/main/java/org/apache/tika/parser/pkg/ tika-parsers/src/test/java/org/apache/tika/detect/ tika-parsers/src/test/resources/test-documents/

Author: nick
Date: Tue Nov 10 16:18:45 2015
New Revision: 1713677

URL: http://svn.apache.org/viewvc?rev=1713677&view=rev
Log:
TIKA-1792 ASiC E and S mimetypes, detection and tests. Files and mimetype from Roberto Benedetti

Added:
    tika/trunk/tika-parsers/src/test/resources/test-documents/testASiCE.asice   (with props)
    tika/trunk/tika-parsers/src/test/resources/test-documents/testASiCS.asics   (with props)
Modified:
    tika/trunk/tika-core/src/main/resources/org/apache/tika/mime/tika-mimetypes.xml
    tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/pkg/ZipContainerDetector.java
    tika/trunk/tika-parsers/src/test/java/org/apache/tika/detect/TestContainerAwareDetector.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=1713677&r1=1713676&r2=1713677&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 Tue Nov 10 16:18:45 2015
@@ -992,6 +992,33 @@
     <glob pattern="*.es3"/>
     <glob pattern="*.et3"/>
   </mime-type>
+
+  <mime-type type="application/vnd.etsi.asic-e+zip">
+    <acronym>ASiC-E</acronym>
+    <_comment>Extended Associated Signature Container</_comment>
+    <sub-class-of type="application/zip"/>
+    <!-- Only works if the mimetype file is the first zip entry -->
+    <magic priority="50">
+      <match value="PK\003\004" type="string" offset="0">
+        <match value="mimetypeapplication/vnd.etsi.asic-e+zip" type="string" offset="30" />
+      </match>
+    </magic>
+    <glob pattern="*.asice" />
+  </mime-type>
+
+  <mime-type type="application/vnd.etsi.asic-s+zip">
+    <acronym>ASiC-S</acronym>
+    <_comment>Simple Associated Signature Container</_comment>
+    <sub-class-of type="application/zip"/>
+    <!-- Only works if the mimetype file is the first zip entry -->
+    <magic priority="50">
+      <match value="PK\003\004" type="string" offset="0">
+        <match value="mimetypeapplication/vnd.etsi.asic-s+zip" type="string" offset="30" />
+      </match>
+    </magic>
+    <glob pattern="*.asics" />
+  </mime-type>
+
   <mime-type type="application/vnd.etsi.aoc+xml"/>
   <mime-type type="application/vnd.etsi.cug+xml"/>
   <mime-type type="application/vnd.etsi.iptvcommand+xml"/>
@@ -3834,6 +3861,7 @@
   <!-- =================================================================== -->
   <mime-type type="application/x-tika-ooxml">
     <sub-class-of type="application/zip"/>
+    <!-- Only works if the Content Types file is the first zip entry -->
     <magic priority="50">
       <match value="PK\003\004" type="string" offset="0">
         <match value="[Content_Types].xml" type="string" offset="30"/>

Modified: tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/pkg/ZipContainerDetector.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/pkg/ZipContainerDetector.java?rev=1713677&r1=1713676&r2=1713677&view=diff
==============================================================================
--- tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/pkg/ZipContainerDetector.java (original)
+++ tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/pkg/ZipContainerDetector.java Tue Nov 10 16:18:45 2015
@@ -180,9 +180,9 @@ public class ZipContainerDetector implem
     }
 
     /**
-     * OpenDocument files, along with EPub files, have a mimetype
-     *  entry in the root of their Zip file. This entry contains the
-     *  mimetype of the overall file, stored as a single string.  
+     * OpenDocument files, along with EPub files and ASiC ones, have a 
+     *  mimetype entry in the root of their Zip file. This entry contains
+     *  the mimetype of the overall file, stored as a single string.  
      */
     private static MediaType detectOpenDocument(ZipFile zip) {
         try {

Modified: tika/trunk/tika-parsers/src/test/java/org/apache/tika/detect/TestContainerAwareDetector.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/test/java/org/apache/tika/detect/TestContainerAwareDetector.java?rev=1713677&r1=1713676&r2=1713677&view=diff
==============================================================================
--- tika/trunk/tika-parsers/src/test/java/org/apache/tika/detect/TestContainerAwareDetector.java (original)
+++ tika/trunk/tika-parsers/src/test/java/org/apache/tika/detect/TestContainerAwareDetector.java Tue Nov 10 16:18:45 2015
@@ -324,7 +324,15 @@ public class TestContainerAwareDetector
     public void testDetectIPA() throws Exception {
         assertTypeByNameAndData("testIPA.ipa", "application/x-itunes-ipa");
         assertTypeByData("testIPA.ipa", "application/x-itunes-ipa");
-     }
+    }
+    
+    @Test
+    public void testASiC() throws Exception {
+        assertTypeByData("testASiCE.asice", "application/vnd.etsi.asic-e+zip");
+        assertTypeByData("testASiCS.asics", "application/vnd.etsi.asic-s+zip");
+        assertTypeByNameAndData("testASiCE.asice", "application/vnd.etsi.asic-e+zip");
+        assertTypeByNameAndData("testASiCS.asics", "application/vnd.etsi.asic-s+zip");
+    }
      
     @Test
     public void testDetectZip() throws Exception {

Added: tika/trunk/tika-parsers/src/test/resources/test-documents/testASiCE.asice
URL: http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/test/resources/test-documents/testASiCE.asice?rev=1713677&view=auto
==============================================================================
Binary file - no diff available.

Propchange: tika/trunk/tika-parsers/src/test/resources/test-documents/testASiCE.asice
------------------------------------------------------------------------------
    svn:mime-type = application/octet-stream

Added: tika/trunk/tika-parsers/src/test/resources/test-documents/testASiCS.asics
URL: http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/test/resources/test-documents/testASiCS.asics?rev=1713677&view=auto
==============================================================================
Binary file - no diff available.

Propchange: tika/trunk/tika-parsers/src/test/resources/test-documents/testASiCS.asics
------------------------------------------------------------------------------
    svn:mime-type = application/octet-stream