Author: nick
Date: Thu Jul 29 13:20:57 2010
New Revision: 980442
URL: http://svn.apache.org/viewvc?rev=980442&view=rev
Log:
Container aware detection for Jars, and add stub TODOs for iWork files
(TIKA-447)
Added:
tika/trunk/tika-parsers/src/test/resources/test-documents/testJAR.jar
(with props)
Modified:
tika/trunk/tika-parsers/src/main/java/org/apache/tika/detect/ZipContainerDetector.java
tika/trunk/tika-parsers/src/test/java/org/apache/tika/detect/TestContainerAwareDetector.java
Modified:
tika/trunk/tika-parsers/src/main/java/org/apache/tika/detect/ZipContainerDetector.java
URL:
http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/main/java/org/apache/tika/detect/ZipContainerDetector.java?rev=980442&r1=980441&r2=980442&view=diff
==============================================================================
---
tika/trunk/tika-parsers/src/main/java/org/apache/tika/detect/ZipContainerDetector.java
(original)
+++
tika/trunk/tika-parsers/src/main/java/org/apache/tika/detect/ZipContainerDetector.java
Thu Jul 29 13:20:57 2010
@@ -79,7 +79,13 @@ public class ZipContainerDetector implem
} catch(InvalidFormatException e) {
throw new IOException("Office Open XML File detected, but
corrupted", e);
}
+ } else if(entry.getName().equals("buildVersionHistory.plist")) {
+ // TODO - iWork
+ } else if(entry.getName().equals("META-INF/")) {
+ // Java Jar
+ return MediaType.application("java-archive");
}
+
entry = zip.getNextEntry();
}
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=980442&r1=980441&r2=980442&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
Thu Jul 29 13:20:57 2010
@@ -42,7 +42,7 @@ public class TestContainerAwareDetector
private InputStream getTestDoc(String filename) {
InputStream input =
TestContainerAwareDetector.class.getResourceAsStream(
"/test-documents/" + filename);
- assertNotNull(input);
+ assertNotNull("Test file not found - " + filename, input);
return input;
}
@@ -135,7 +135,23 @@ public class TestContainerAwareDetector
);
}
+ public void testDetectIWork() throws Exception {
+ // TODO
+ }
+
public void testDetectZip() throws Exception {
+ TikaInputStream tis;
+ tis = TikaInputStream.get(getTestDoc("test-documents.zip"));
+ assertEquals(
+ MediaType.application("zip"),
+ d.detect(tis, new Metadata())
+ );
+
+ tis = TikaInputStream.get(getTestDoc("testJAR.jar"));
+ assertEquals(
+ MediaType.application("java-archive"),
+ d.detect(tis, new Metadata())
+ );
}
}
Added: tika/trunk/tika-parsers/src/test/resources/test-documents/testJAR.jar
URL:
http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/test/resources/test-documents/testJAR.jar?rev=980442&view=auto
==============================================================================
Binary file - no diff available.
Propchange:
tika/trunk/tika-parsers/src/test/resources/test-documents/testJAR.jar
------------------------------------------------------------------------------
svn:mime-type = application/octet-stream