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 2016/01/26 17:33:16 UTC

[2/2] tika git commit: TIKA-1823 AutoCAD DWF mime magic and subtypes

TIKA-1823 AutoCAD DWF mime magic and subtypes

Parent AutoCAD DWF mimetype and general magic, based on patch from
Luca Moretti, along with version-specific subtypes with more specific
magic


Project: http://git-wip-us.apache.org/repos/asf/tika/repo
Commit: http://git-wip-us.apache.org/repos/asf/tika/commit/6a092332
Tree: http://git-wip-us.apache.org/repos/asf/tika/tree/6a092332
Diff: http://git-wip-us.apache.org/repos/asf/tika/diff/6a092332

Branch: refs/heads/master
Commit: 6a092332686e02ba26456e52fb0ce8bc5b42be56
Parents: 38fbc50
Author: Nick Burch <ni...@gagravarr.org>
Authored: Tue Jan 26 16:31:17 2016 +0000
Committer: Nick Burch <ni...@gagravarr.org>
Committed: Tue Jan 26 16:31:17 2016 +0000

----------------------------------------------------------------------
 .../org/apache/tika/mime/tika-mimetypes.xml     | 30 ++++++++++++++++++++
 .../org/apache/tika/mime/TestMimeTypes.java     |  5 ++++
 2 files changed, 35 insertions(+)
----------------------------------------------------------------------


http://git-wip-us.apache.org/repos/asf/tika/blob/6a092332/tika-core/src/main/resources/org/apache/tika/mime/tika-mimetypes.xml
----------------------------------------------------------------------
diff --git a/tika-core/src/main/resources/org/apache/tika/mime/tika-mimetypes.xml b/tika-core/src/main/resources/org/apache/tika/mime/tika-mimetypes.xml
index 5d152a5..1d7b42b 100644
--- a/tika-core/src/main/resources/org/apache/tika/mime/tika-mimetypes.xml
+++ b/tika-core/src/main/resources/org/apache/tika/mime/tika-mimetypes.xml
@@ -5250,8 +5250,38 @@
   </mime-type>
 
   <mime-type type="model/vnd.dwf">
+    <acronym>DWF</acronym>
+    <_comment>AutoCAD Design Web Format</_comment>
+    <alias type="drawing/x-dwf"/>
+    <magic priority="50">
+      <match type="string" offset="0" value="(DWF V">
+         <match type="string" offset="8" value=".">
+            <match type="string" offset="11" value=")" />
+         </match>
+      </match>
+    </magic>
     <glob pattern="*.dwf"/>
   </mime-type>
+  <mime-type type="model/vnd.dwf;version=6">
+    <!-- Zip file with DWF header on the front -->
+    <magic priority="60">
+      <match type="string" offset="0" value="(DWF V06.">
+         <match type="string" offset="11" value=")PK" />
+      </match>
+    </magic>
+    <sub-class-of type="model/vnd.dwf"/>
+  </mime-type>
+  <mime-type type="model/vnd.dwf;version=5">
+    <magic priority="60">
+      <match type="string" offset="0" value="(DWF V00.55)"/>
+    </magic>
+  </mime-type>
+  <mime-type type="model/vnd.dwf;version=2">
+    <magic priority="60">
+      <match type="string" offset="0" value="(DWF V00.22)"/>
+    </magic>
+  </mime-type>
+
   <mime-type type="model/vnd.dwfx+xps">
     <_comment>AutoCAD Design Web Format</_comment>
     <glob pattern="*.dwfx"/>

http://git-wip-us.apache.org/repos/asf/tika/blob/6a092332/tika-parsers/src/test/java/org/apache/tika/mime/TestMimeTypes.java
----------------------------------------------------------------------
diff --git a/tika-parsers/src/test/java/org/apache/tika/mime/TestMimeTypes.java b/tika-parsers/src/test/java/org/apache/tika/mime/TestMimeTypes.java
index 28aae81..2f9193d 100644
--- a/tika-parsers/src/test/java/org/apache/tika/mime/TestMimeTypes.java
+++ b/tika-parsers/src/test/java/org/apache/tika/mime/TestMimeTypes.java
@@ -538,6 +538,11 @@ public class TestMimeTypes {
         assertTypeByData("image/vnd.dwg", "testDWG2010.dwg");
         
         // From name, gets the common parent type
+        assertTypeByName("model/vnd.dwf", "x.dwf");
+        // With the data, can work out it's the v6 zip-based flavour
+        assertTypeByData("model/vnd.dwf; version=6", "testDWF2010.dwf");
+        
+        // From name, gets the common parent type
         assertTypeByName("image/vnd.dxf", "x.dxf");
         // With the data, can work out it's the ASCII flavour
         assertTypeByData("image/vnd.dxf; format=ascii", "testDXF_ascii.dxf");