dschmidt commented on code in PR #3090:
URL: https://github.com/apache/tika/pull/3090#discussion_r3901619821
##########
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-audiovideo-module/src/test/java/org/apache/tika/parser/mp4/MP4ParserTest.java:
##########
@@ -179,16 +181,54 @@ public void testMP4MultipleCovers() throws Exception {
assertEquals(3, metadataList.size());
//a png data atom (well-known type 14) followed by a jpeg one (13)
+ //covr carries no picture type, so the first image is the thumbnail
Metadata front = metadataList.get(1);
assertEquals("image/png", front.get(HttpHeaders.CONTENT_TYPE));
- assertEquals(TikaCoreProperties.EmbeddedResourceType.INLINE.toString(),
+
assertEquals(TikaCoreProperties.EmbeddedResourceType.THUMBNAIL.toString(),
front.get(TikaCoreProperties.EMBEDDED_RESOURCE_TYPE));
Metadata back = metadataList.get(2);
assertEquals("image/jpeg", back.get(HttpHeaders.CONTENT_TYPE));
assertEquals(TikaCoreProperties.EmbeddedResourceType.INLINE.toString(),
back.get(TikaCoreProperties.EMBEDDED_RESOURCE_TYPE));
}
+ /**
+ * A cover in a second udta box is still an inline picture: the first
+ * cover of the file is its thumbnail, not the first of every box
+ */
+ @Test
+ public void testCoversAcrossUserDataBoxes() throws Exception {
+ byte[] file;
+ try (InputStream is =
getResourceAsStream("/test-documents/testMP4_coverArt.m4a")) {
+ file = is.readAllBytes();
+ }
+ //append a copy of the file's udta box (with its covr) at the top level
+ int udta = indexOf(file, "udta".getBytes(StandardCharsets.ISO_8859_1))
- 4;
+ int size = ByteBuffer.wrap(file, udta, 4).getInt();
+ ByteArrayOutputStream bos = new ByteArrayOutputStream();
Review Comment:
Guarded: the test fails with a clear message if the fixture loses its udta
box.
##########
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-audiovideo-module/src/main/java/org/apache/tika/parser/ogg/OggAudioParser.java:
##########
@@ -117,8 +114,14 @@ protected static void extractChannelInfo(Metadata
metadata, int channelCount) {
}
}
- protected static void extractComments(Metadata metadata,
XHTMLContentHandler xhtml,
- VorbisStyleComments comments, ParseContext context)
+ /**
+ * @return the pictures carried in the comments; the caller emits them
+ * through {@link #extractPictures(List, XHTMLContentHandler,
ParseContext)},
+ * {@link FlacParser} first merges them with the native PICTURE blocks so
+ * one file yields one thumbnail
+ */
+ protected static List<PictureBlock> extractComments(Metadata metadata,
+ XHTMLContentHandler xhtml, VorbisStyleComments comments,
ParseContext context)
throws IOException, TikaException, SAXException {
Review Comment:
Removed.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
