This is an automated email from the ASF dual-hosted git repository. nick pushed a commit to branch master in repository https://gitbox.apache.org/repos/asf/tika.git
The following commit(s) were added to refs/heads/master by this push: new bada130 As per RFC2361, the official mimetype for WAV is audio/vnd.wav bada130 is described below commit bada130efe32560a5b3c26472029f3bd536040b8 Author: Nick Burch <n...@gagravarr.org> AuthorDate: Thu Jun 29 22:36:09 2017 +0100 As per RFC2361, the official mimetype for WAV is audio/vnd.wav --- CHANGES.txt | 3 +++ tika-core/src/main/resources/org/apache/tika/mime/tika-mimetypes.xml | 5 ++++- tika-core/src/test/java/org/apache/tika/TikaDetectionTest.java | 3 ++- .../src/main/java/org/apache/tika/parser/audio/AudioParser.java | 5 +++-- tika-parsers/src/test/java/org/apache/tika/mime/TestMimeTypes.java | 2 +- .../src/test/java/org/apache/tika/parser/audio/AudioParserTest.java | 2 +- 6 files changed, 14 insertions(+), 6 deletions(-) diff --git a/CHANGES.txt b/CHANGES.txt index e8a4a74..0d6b55f 100644 --- a/CHANGES.txt +++ b/CHANGES.txt @@ -22,6 +22,9 @@ Release 1.15.1 - ??/??/???? * Enable base32 encoding of digests and enable BouncyCastle implementations of digest algorithms (TIKA-2386). + * Canonical Mimetype of WAVE audio changed to match RFC 2361 defined + version, audio/vnd.wave, older audio/x-wav remains as an alias + Release 1.15 - 05/23/2017 * Tika now has a module for Deep Learning powered by the 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 f278dd6..10905da 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 @@ -4811,7 +4811,10 @@ <!-- <glob pattern="*.rpm"/> - conflicts with application/x-rpm --> </mime-type> - <mime-type type="audio/x-wav"> + <mime-type type="audio/vnd.wave"> + <alias type="audio/x-wav"/> + <alias type="audio/wave"/> + <alias type="audio/wav"/> <acronym>WAV</acronym> <magic priority="20"> <match value="RIFF....WAVE" type="string" offset="0" diff --git a/tika-core/src/test/java/org/apache/tika/TikaDetectionTest.java b/tika-core/src/test/java/org/apache/tika/TikaDetectionTest.java index 6e0a3bb..cdf8b2d 100644 --- a/tika-core/src/test/java/org/apache/tika/TikaDetectionTest.java +++ b/tika-core/src/test/java/org/apache/tika/TikaDetectionTest.java @@ -677,7 +677,8 @@ public class TikaDetectionTest { assertEquals("audio/x-pn-realaudio", tika.detect("x.ram")); assertEquals("audio/x-pn-realaudio", tika.detect("x.ra")); assertEquals("audio/x-pn-realaudio-plugin", tika.detect("x.rmp")); - assertEquals("audio/x-wav", tika.detect("x.wav")); + // Differ from httpd - wav was properly registered in RFC 2361 + //assertEquals("audio/x-wav", tika.detect("x.wav")); assertEquals("chemical/x-cdx", tika.detect("x.cdx")); assertEquals("chemical/x-cif", tika.detect("x.cif")); assertEquals("chemical/x-cmdf", tika.detect("x.cmdf")); diff --git a/tika-parsers/src/main/java/org/apache/tika/parser/audio/AudioParser.java b/tika-parsers/src/main/java/org/apache/tika/parser/audio/AudioParser.java index a6c2e9d..50cd8b7 100644 --- a/tika-parsers/src/main/java/org/apache/tika/parser/audio/AudioParser.java +++ b/tika-parsers/src/main/java/org/apache/tika/parser/audio/AudioParser.java @@ -50,7 +50,8 @@ public class AudioParser extends AbstractParser { private static final Set<MediaType> SUPPORTED_TYPES = Collections.unmodifiableSet(new HashSet<MediaType>(Arrays.asList( MediaType.audio("basic"), - MediaType.audio("x-wav"), + MediaType.audio("vnd.wave"), // Official, fixed in Tika 1.16 + MediaType.audio("x-wav"), // Older, used until Tika 1.16 MediaType.audio("x-aiff")))); public Set<MediaType> getSupportedTypes(ParseContext context) { @@ -73,7 +74,7 @@ public class AudioParser extends AbstractParser { } else if (type == Type.AU || type == Type.SND) { metadata.set(Metadata.CONTENT_TYPE, "audio/basic"); } else if (type == Type.WAVE) { - metadata.set(Metadata.CONTENT_TYPE, "audio/x-wav"); + metadata.set(Metadata.CONTENT_TYPE, "audio/vnd.wave"); } AudioFormat audioFormat = fileFormat.getFormat(); 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 828dd6e..97bb908 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 @@ -804,7 +804,7 @@ public class TestMimeTypes { assertType("application/xml", "testXML.xml"); assertType("audio/basic", "testAU.au"); assertType("audio/x-aiff", "testAIFF.aif"); - assertType("audio/x-wav", "testWAV.wav"); + assertType("audio/vnd.wave", "testWAV.wav"); assertType("audio/midi", "testMID.mid"); assertType("application/x-msaccess", "testACCESS.mdb"); assertType("application/x-font-ttf", "testTrueType3.ttf"); diff --git a/tika-parsers/src/test/java/org/apache/tika/parser/audio/AudioParserTest.java b/tika-parsers/src/test/java/org/apache/tika/parser/audio/AudioParserTest.java index d35de32..9cfbab1 100644 --- a/tika-parsers/src/test/java/org/apache/tika/parser/audio/AudioParserTest.java +++ b/tika-parsers/src/test/java/org/apache/tika/parser/audio/AudioParserTest.java @@ -31,7 +31,7 @@ public class AudioParserTest { String content = new Tika().parseToString( AudioParserTest.class.getResourceAsStream(path), metadata); - assertEquals("audio/x-wav", metadata.get(Metadata.CONTENT_TYPE)); + assertEquals("audio/vnd.wave", metadata.get(Metadata.CONTENT_TYPE)); assertEquals("44100.0", metadata.get("samplerate")); assertEquals("2", metadata.get("channels")); assertEquals("16", metadata.get("bits")); -- To stop receiving notification emails like this one, please contact ['"commits@tika.apache.org" <commits@tika.apache.org>'].