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 2014/04/25 11:21:16 UTC

svn commit: r1589958 - 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/mime/ tika-parsers/src/test/java/org/apache/tika/parser/pkg/

Author: nick
Date: Fri Apr 25 09:21:15 2014
New Revision: 1589958

URL: http://svn.apache.org/r1589958
Log:
TIKA-1280 GZip now has an official mimetype

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/CompressorParser.java
    tika/trunk/tika-parsers/src/test/java/org/apache/tika/mime/TestMimeTypes.java
    tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/pkg/GzipParserTest.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=1589958&r1=1589957&r2=1589958&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 Fri Apr 25 09:21:15 2014
@@ -2819,8 +2819,9 @@
     <sub-class-of type="application/x-tar"/>
   </mime-type>
 
-  <mime-type type="application/x-gzip">
+  <mime-type type="application/gzip">
     <_comment>Gzip Compressed Archive</_comment>
+    <alias type="application/x-gzip"/>
     <magic priority="40">
       <match value="\037\213" type="string" offset="0" />
       <match value="\x1f\x8b" type="string" offset="0" />

Modified: tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/pkg/CompressorParser.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/pkg/CompressorParser.java?rev=1589958&r1=1589957&r2=1589958&view=diff
==============================================================================
--- tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/pkg/CompressorParser.java (original)
+++ tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/pkg/CompressorParser.java Fri Apr 25 09:21:15 2014
@@ -53,12 +53,13 @@ public class CompressorParser extends Ab
 
     private static final MediaType BZIP = MediaType.application("x-bzip");
     private static final MediaType BZIP2 = MediaType.application("x-bzip2");
-    private static final MediaType GZIP = MediaType.application("x-gzip");
+    private static final MediaType GZIP = MediaType.application("gzip");
+    private static final MediaType GZIP_ALT = MediaType.application("x-gzip");
     private static final MediaType XZ = MediaType.application("x-xz");
     private static final MediaType PACK = MediaType.application("application/x-java-pack200");
 
     private static final Set<MediaType> SUPPORTED_TYPES =
-            MediaType.set(BZIP, BZIP2, GZIP, XZ, PACK);
+            MediaType.set(BZIP, BZIP2, GZIP, GZIP_ALT, XZ, PACK);
 
     static MediaType getMediaType(CompressorInputStream stream) {
         // TODO Add support for the remaining CompressorInputStream formats:

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=1589958&r1=1589957&r2=1589958&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 Fri Apr 25 09:21:15 2014
@@ -287,7 +287,7 @@ public class TestMimeTypes {
        assertTypeByName("application/x-archive", "test.ar");
        assertTypeByName("application/zip",    "test.zip");
        assertTypeByName("application/x-tar",  "test.tar");
-       assertTypeByName("application/x-gzip", "test.tgz"); // See GZIP, not tar contents of it
+       assertTypeByName("application/gzip", "test.tgz"); // See GZIP, not tar contents of it
        assertTypeByName("application/x-cpio", "test.cpio");
        
        // TODO Add an example .deb and .udeb, then check these
@@ -297,7 +297,7 @@ public class TestMimeTypes {
        assertTypeByData("application/x-archive", "testARofSND.ar"); 
        assertTypeByData("application/zip",    "test-documents.zip");
        assertTypeByData("application/x-gtar",  "test-documents.tar"); // GNU TAR
-       assertTypeByData("application/x-gzip", "test-documents.tgz"); // See GZIP, not tar contents of it
+       assertTypeByData("application/gzip", "test-documents.tgz"); // See GZIP, not tar contents of it
        assertTypeByData("application/x-cpio", "test-documents.cpio");
        
        // For spanned zip files, the .zip file doesn't have the header, it's the other parts
@@ -421,8 +421,8 @@ public class TestMimeTypes {
         assertTypeByName("image/svg+xml", "x.SVG");
 
         // Should *.svgz be svg or gzip
-        assertType("application/x-gzip", "testSVG.svgz");
-        assertTypeByData("application/x-gzip", "testSVG.svgz");
+        assertType("application/gzip", "testSVG.svgz");
+        assertTypeByData("application/gzip", "testSVG.svgz");
         assertTypeByName("image/svg+xml", "x.svgz");
         assertTypeByName("image/svg+xml", "x.SVGZ");
     }
@@ -498,8 +498,8 @@ public class TestMimeTypes {
         assertTypeByName("application/x-ms-wmz", "x.wmz");
         assertTypeByName("application/x-ms-wmz", "x.WMZ");
         // TODO: Need a test emz file
-        assertTypeByName("application/x-gzip", "x.emz");
-        assertTypeByName("application/x-gzip", "x.EMZ");
+        assertTypeByName("application/gzip", "x.emz");
+        assertTypeByName("application/gzip", "x.EMZ");
     }
 
     @Test

Modified: tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/pkg/GzipParserTest.java
URL: http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/pkg/GzipParserTest.java?rev=1589958&r1=1589957&r2=1589958&view=diff
==============================================================================
--- tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/pkg/GzipParserTest.java (original)
+++ tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/pkg/GzipParserTest.java Fri Apr 25 09:21:15 2014
@@ -47,7 +47,7 @@ public class GzipParserTest extends Abst
             stream.close();
         }
 
-        assertEquals("application/x-gzip", metadata.get(Metadata.CONTENT_TYPE));
+        assertEquals("application/gzip", metadata.get(Metadata.CONTENT_TYPE));
         String content = handler.toString();
         assertTrue(content.contains("test-documents/testEXCEL.xls"));
         assertTrue(content.contains("Sample Excel Worksheet"));
@@ -112,7 +112,7 @@ public class GzipParserTest extends Abst
             stream.close();
         }
 
-        assertEquals("application/x-gzip", metadata.get(Metadata.CONTENT_TYPE));
+        assertEquals("application/gzip", metadata.get(Metadata.CONTENT_TYPE));
         String content = handler.toString();
         assertTrue(content.contains("Test SVG image"));
     }