Author: nick
Date: Wed Dec 24 03:13:18 2014
New Revision: 1647721
URL: http://svn.apache.org/r1647721
Log:
TIKA-879 Add a new parent mime type, for the text based message formats, of
text/x-tika-text-based-message, which allows Thunderbird messages to be
correctly detected as they now show up as being text based not binary based in
the hierarchy
Modified:
tika/trunk/tika-core/src/main/resources/org/apache/tika/mime/tika-mimetypes.xml
tika/trunk/tika-parsers/src/test/java/org/apache/tika/mime/TestMimeTypes.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=1647721&r1=1647720&r2=1647721&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
Wed Dec 24 03:13:18 2014
@@ -2877,6 +2877,7 @@
<match value="\nDate:" type="string" offset="2:9"/>
</magic>
<glob pattern="*.emlx"/>
+ <sub-class-of type="text/x-tika-text-based-message"/>
</mime-type>
<mime-type type="application/x-killustrator">
@@ -4900,6 +4901,7 @@
<match value="Xref:" type="string" offset="0" />
<match value="Article" type="string" offset="0" />
</magic>
+ <sub-class-of type="text/x-tika-text-based-message"/>
</mime-type>
<mime-type type="message/partial"/>
@@ -4925,6 +4927,7 @@
<glob pattern="*.mime"/>
<glob pattern="*.mht"/>
<glob pattern="*.mhtml"/>
+ <sub-class-of type="text/x-tika-text-based-message"/>
</mime-type>
<mime-type type="message/s-http"/>
@@ -5722,6 +5725,10 @@
<sub-class-of type="text/plain"/>
</mime-type>
+ <mime-type type="text/x-tika-text-based-message">
+ <_comment>Text-based (non-binary) Message</_comment>
+ </mime-type>
+
<mime-type type="text/x-uuencode">
<glob pattern="*.uu"/>
</mime-type>
Modified:
tika/trunk/tika-parsers/src/test/java/org/apache/tika/mime/TestMimeTypes.java
URL:
http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/test/java/org/apache/tika/mime/TestMimeTypes.java?rev=1647721&r1=1647720&r2=1647721&view=diff
==============================================================================
---
tika/trunk/tika-parsers/src/test/java/org/apache/tika/mime/TestMimeTypes.java
(original)
+++
tika/trunk/tika-parsers/src/test/java/org/apache/tika/mime/TestMimeTypes.java
Wed Dec 24 03:13:18 2014
@@ -757,13 +757,18 @@ public class TestMimeTypes {
}
@Test
- public void testEmlx() throws IOException {
+ public void testEmail() throws IOException {
+ // EMLX
assertTypeDetection("testEMLX.emlx", "message/x-emlx");
- }
-
- @Test
- public void testGroupWiseEml() throws Exception {
+
+ // Groupwise
assertTypeDetection("testGroupWiseEml.eml", "message/rfc822");
+
+ // Lotus
+ assertTypeDetection("testLotusEml.eml", "message/rfc822");
+
+ // Thunderbird - doesn't currently work by name
+ assertTypeByNameAndData("message/rfc822", "testThunderbirdEml.eml");
}
@Test