Author: jukka
Date: Mon Oct 15 15:43:06 2007
New Revision: 584951

URL: http://svn.apache.org/viewvc?rev=584951&view=rev
Log:
TIKA-70 - Better MIME information for the Open Document formats

Modified:
    incubator/tika/trunk/CHANGES.txt
    incubator/tika/trunk/src/main/resources/mime/tika-mimetypes.xml
    
incubator/tika/trunk/src/test/java/org/apache/tika/parser/AutoDetectParserTest.java

Modified: incubator/tika/trunk/CHANGES.txt
URL: 
http://svn.apache.org/viewvc/incubator/tika/trunk/CHANGES.txt?rev=584951&r1=584950&r2=584951&view=diff
==============================================================================
--- incubator/tika/trunk/CHANGES.txt (original)
+++ incubator/tika/trunk/CHANGES.txt Mon Oct 15 15:43:06 2007
@@ -115,3 +115,5 @@
 51. TIKA-68 - Add dummy parser classes to be used as sentinels (jukka)
 
 52. TIKA-67 - Add an auto-detecting Parser implementation (jukka)
+
+53. TIKA-70 - Better MIME information for the Open Document formats (jukka)

Modified: incubator/tika/trunk/src/main/resources/mime/tika-mimetypes.xml
URL: 
http://svn.apache.org/viewvc/incubator/tika/trunk/src/main/resources/mime/tika-mimetypes.xml?rev=584951&r1=584950&r2=584951&view=diff
==============================================================================
--- incubator/tika/trunk/src/main/resources/mime/tika-mimetypes.xml (original)
+++ incubator/tika/trunk/src/main/resources/mime/tika-mimetypes.xml Mon Oct 15 
15:43:06 2007
@@ -89,22 +89,210 @@
                <glob pattern="*.xld" />
                <alias type="application/msexcel" />
        </mime-type>
-
+
+<!-- ===================================================================== -->
+<!-- Open Document Format for Office Applications (OpenDocument) v1.0      -->
+<!-- http://www.oasis-open.org/specs/index.php#opendocumentv1.0            -->
+<!-- ===================================================================== -->
+
        <mime-type type="application/vnd.oasis.opendocument.text">
+               <comment>OpenDocument v1.0: Text document</comment>
+               <alias type="application/x-vnd.oasis.opendocument.text" />
                <glob pattern="*.odt" />
-       </mime-type>
-
-
+               <magic>
+                       <match type="string" offset="0" value="PK">
+                               <match type="string" offset="30"
+                                       
value="mimetypeapplication/vnd.oasis.opendocument.text" />
+                       </match>
+               </magic>
+       </mime-type>
+
+       <mime-type type="application/vnd.oasis.opendocument.text-template">
+               <comment>OpenDocument v1.0: Text document used as 
template</comment>
+               <alias 
type="application/x-vnd.oasis.opendocument.text-template" />
+               <glob pattern="*.ott" />
+               <magic>
+                       <match type="string" offset="0" value="PK">
+                               <match type="string" offset="30"
+                                       
value="mimetypeapplication/vnd.oasis.opendocument.text-template" />
+                       </match>
+               </magic>
+       </mime-type>
+
+       <mime-type type="application/vnd.oasis.opendocument.graphics">
+               <comment>OpenDocument v1.0: Graphics document 
(Drawing)</comment>
+               <alias type="application/x-vnd.oasis.opendocument.graphics" />
+               <glob pattern="*.odg" />
+               <magic>
+                       <match type="string" offset="0" value="PK">
+                               <match type="string" offset="30"
+                                       
value="mimetypeapplication/vnd.oasis.opendocument.graphics" />
+                       </match>
+               </magic>
+       </mime-type>
+
+       <mime-type type="application/vnd.oasis.opendocument.graphics-template">
+               <comment>OpenDocument v1.0: Graphics document used as 
template</comment>
+               <alias 
type="application/x-vnd.oasis.opendocument.graphics-template" />
+               <glob pattern="*.otg" />
+               <magic>
+                       <match type="string" offset="0" value="PK">
+                               <match type="string" offset="30"
+                                       
value="mimetypeapplication/vnd.oasis.opendocument.graphics-template" />
+                       </match>
+               </magic>
+       </mime-type>
+
+       <mime-type type="application/vnd.oasis.opendocument.presentation">
+               <comment>OpenDocument v1.0: Presentation document</comment>
+               <alias type="application/x-vnd.oasis.opendocument.presentation" 
/>
+               <glob pattern="*.odp" />
+               <magic>
+                       <match type="string" offset="0" value="PK">
+                               <match type="string" offset="30"
+                                       
value="mimetypeapplication/vnd.oasis.opendocument.presentation" />
+                       </match>
+               </magic>
+       </mime-type>
+
+       <mime-type 
type="application/vnd.oasis.opendocument.presentation-template">
+               <comment>OpenDocument v1.0: Presentation document used as 
template</comment>
+               <alias 
type="application/x-vnd.oasis.opendocument.presentation-template" />
+               <glob pattern="*.otp" />
+               <magic>
+                       <match type="string" offset="0" value="PK">
+                               <match type="string" offset="30"
+                                       
value="mimetypeapplication/vnd.oasis.opendocument.presentation-template" />
+                       </match>
+               </magic>
+       </mime-type>
+
+       <mime-type type="application/vnd.oasis.opendocument.spreadsheet">
+               <comment>OpenDocument v1.0: Spreadsheet document</comment>
+               <alias type="application/x-vnd.oasis.opendocument.spreadsheet" 
/>
+               <glob pattern="*.ods" />
+               <magic>
+                       <match type="string" offset="0" value="PK">
+                               <match type="string" offset="30"
+                                       
value="mimetypeapplication/vnd.oasis.opendocument.spreadsheet" />
+                       </match>
+               </magic>
+       </mime-type>
+
+       <mime-type 
type="application/vnd.oasis.opendocument.spreadsheet-template">
+               <comment>OpenDocument v1.0: Spreadsheet document used as 
template</comment>
+               <alias 
type="application/x-vnd.oasis.opendocument.spreadsheet-template" />
+               <glob pattern="*.ots" />
+               <magic>
+                       <match type="string" offset="0" value="PK">
+                               <match type="string" offset="30"
+                                       
value="mimetypeapplication/vnd.oasis.opendocument.spreadsheet-template" />
+                       </match>
+               </magic>
+       </mime-type>
+
+       <mime-type type="application/vnd.oasis.opendocument.chart">
+               <comment>OpenDocument v1.0: Chart document</comment>
+               <alias type="application/x-vnd.oasis.opendocument.chart" />
+               <glob pattern="*.odc" />
+               <magic>
+                       <match type="string" offset="0" value="PK">
+                               <match type="string" offset="30"
+                                       
value="mimetypeapplication/vnd.oasis.opendocument.chart" />
+                       </match>
+               </magic>
+       </mime-type>
+
+       <mime-type type="application/vnd.oasis.opendocument.chart-template">
+               <comment>OpenDocument v1.0: Chart document used as 
template</comment>
+               <alias 
type="application/x-vnd.oasis.opendocument.chart-template" />
+               <glob pattern="*.otc" />
+               <magic>
+                       <match type="string" offset="0" value="PK">
+                               <match type="string" offset="30"
+                                       
value="mimetypeapplication/vnd.oasis.opendocument.chart-template" />
+                       </match>
+               </magic>
+       </mime-type>
+
+       <mime-type type="application/vnd.oasis.opendocument.image">
+               <comment>OpenDocument v1.0: Image document</comment>
+               <alias type="application/x-vnd.oasis.opendocument.image" />
+               <glob pattern="*.odi" />
+               <magic>
+                       <match type="string" offset="0" value="PK">
+                               <match type="string" offset="30"
+                                       
value="mimetypeapplication/vnd.oasis.opendocument.image" />
+                       </match>
+               </magic>
+       </mime-type>
+
+       <mime-type type="application/vnd.oasis.opendocument.image-template">
+               <comment>OpenDocument v1.0: Image document used as 
template</comment>
+               <alias 
type="application/x-vnd.oasis.opendocument.image-template" />
+               <glob pattern="*.oti" />
+               <magic>
+                       <match type="string" offset="0" value="PK">
+                               <match type="string" offset="30"
+                                       
value="mimetypeapplication/vnd.oasis.opendocument.image-template" />
+                       </match>
+               </magic>
+       </mime-type>
+
+       <mime-type type="application/vnd.oasis.opendocument.formula">
+               <comment>OpenDocument v1.0: Formula document</comment>
+               <alias type="application/x-vnd.oasis.opendocument.formula" />
+               <glob pattern="*.odf" />
+               <magic>
+                       <match type="string" offset="0" value="PK">
+                               <match type="string" offset="30"
+                                       
value="mimetypeapplication/vnd.oasis.opendocument.formula" />
+                       </match>
+               </magic>
+       </mime-type>
+
+       <mime-type type="application/vnd.oasis.opendocument.formula-template">
+               <comment>OpenDocument v1.0: Formula document used as 
template</comment>
+               <alias 
type="application/x-vnd.oasis.opendocument.formula-template" />
+               <glob pattern="*.otf" />
+               <magic>
+                       <match type="string" offset="0" value="PK">
+                               <match type="string" offset="30"
+                                       
value="mimetypeapplication/vnd.oasis.opendocument.formula-template" />
+                       </match>
+               </magic>
+       </mime-type>
+
+       <mime-type type="application/vnd.oasis.opendocument.textmaster">
+               <comment>OpenDocument v1.0: Global Text document</comment>
+               <alias type="application/x-vnd.oasis.opendocument.textmaster" />
+               <glob pattern="*.odm" />
+               <magic>
+                       <match type="string" offset="0" value="PK">
+                               <match type="string" offset="30"
+                                       
value="mimetypeapplication/vnd.oasis.opendocument.textmaster" />
+                       </match>
+               </magic>
+       </mime-type>
+
+       <mime-type type="application/vnd.oasis.opendocument.text-web">
+               <comment>OpenDocument v1.0: Text document used as template for 
HTML documents</comment>
+               <alias type="application/x-vnd.oasis.opendocument.text-web" />
+               <glob pattern="*.oth" />
+               <magic>
+                       <match type="string" offset="0" value="PK">
+                               <match type="string" offset="30"
+                                       
value="mimetypeapplication/vnd.oasis.opendocument.text-web" />
+                       </match>
+               </magic>
+       </mime-type>
+
        <mime-type type="application/zip">
                <alias type="application/x-zip-compressed" />
                <magic priority="40">
                        <match value="PK\003\004" type="string" offset="0" />
                </magic>
                <glob pattern="*.zip" />
-       </mime-type>
-
-       <mime-type type="application/vnd.oasis.opendocument.text">
-               <glob pattern="*.oth" />
        </mime-type>
 
        <mime-type type="application/msword">

Modified: 
incubator/tika/trunk/src/test/java/org/apache/tika/parser/AutoDetectParserTest.java
URL: 
http://svn.apache.org/viewvc/incubator/tika/trunk/src/test/java/org/apache/tika/parser/AutoDetectParserTest.java?rev=584951&r1=584950&r2=584951&view=diff
==============================================================================
--- 
incubator/tika/trunk/src/test/java/org/apache/tika/parser/AutoDetectParserTest.java
 (original)
+++ 
incubator/tika/trunk/src/test/java/org/apache/tika/parser/AutoDetectParserTest.java
 Mon Oct 15 15:43:06 2007
@@ -55,12 +55,10 @@
                 "/test-documents/testHTML.html",
                 "text/html",
                 "Test Indexation Html");
-        /* FIXME: OpenDocument autodetection doesn't work
         assertAutoDetect(
                 "/test-documents/testOpenOffice2.odt",
                 "application/vnd.oasis.opendocument.text",
                 "This is a sample Open Office document");
-         */
         assertAutoDetect(
                 "/test-documents/testPDF.pdf",
                 "application/pdf",
@@ -84,7 +82,7 @@
         assertAutoDetect(
                 "/test-documents/testXML.xml",
                 "application/xml",
-                "Archimède et Lius");
+                "Lius");
     }
 
 }


Reply via email to