This is an automated email from the ASF dual-hosted git repository.
tallison pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/tika.git
The following commit(s) were added to refs/heads/main by this push:
new 6ebf9cdb7 improve detection of audio/mpeg TIKA-3994 (#1052)
6ebf9cdb7 is described below
commit 6ebf9cdb7445d5731f4471a1ce903376e904ec13
Author: Tim Allison <talli...@apache.org>
AuthorDate: Fri Mar 31 13:38:54 2023 -0400
improve detection of audio/mpeg TIKA-3994 (#1052)
---
tika-core/src/main/resources/org/apache/tika/mime/tika-mimetypes.xml | 4 ++++
1 file changed, 4 insertions(+)
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 a877a2e11..fdb855f1c 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
@@ -5243,10 +5243,14 @@
<match value="0xfffb" type="string" offset="0"/> <!-- V1, L3 -->
<match value="0xfffc" type="string" offset="0"/> <!-- V1, L2, CRC -->
<match value="0xfffd" type="string" offset="0"/> <!-- V1, L2 -->
+ <match value="0xffe3" type="string" offset="0"/> <!-- MP3 2.5 from
pronom -->
<!-- TIKA-417: This is the UTF-16 LE byte order mark! -->
<!-- match value="0xfffe" type="string" offset="0"/ --> <!-- V1, L1, CRC
-->
<match value="0xffff" type="string" offset="0"/> <!-- V1, L1 -->
<match value="ID3" type="string" offset="0"/>
+ <!-- in the wild, 0D0A or quite a few \x00 may precede the magic -->
+ <match
value="(?:\\x0D\\x0A|\\x00{1,1024})(?:\\xff[\\xe3\\xf2\\xf3\\xf4\\xf5\\xf6\\xf7\\xf8\\xf9\\xfa\\xfb\\xfc\\xfd\\xfe\\xff]|ID3)"
+ type="regex" offset="0"/>
</magic>
<glob pattern="*.mpga"/>
<glob pattern="*.mp2"/>
