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 2017/03/23 00:12:44 UTC
[tika] 01/03: TIKA-1772 More WebVTT magic - for cases with no
header, and with custom headers
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
commit bb82205eece0eb68edee7d7ac24f63cf3934198f
Author: Nick Burch <ni...@gagravarr.org>
AuthorDate: Wed Mar 22 23:25:52 2017 +0000
TIKA-1772 More WebVTT magic - for cases with no header, and with custom headers
---
.../org/apache/tika/mime/tika-mimetypes.xml | 23 ++++++++++++++++++++++
1 file changed, 23 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 e3df6f6..c99ce3f 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
@@ -5991,9 +5991,32 @@
<_comment>Web Video Text Tracks Format</_comment>
<acronym>WebVTT</acronym>
<magic priority="40">
+ <!-- Simple Form -->
+ <match value="WEBVTT\r" type="string" offset="0"/>
+ <match value="WEBVTT\n" type="string" offset="0"/>
+ <!-- With Byte Order Mark -->
+ <match value="0xfeff" offset="0">
+ <match value="WEBVTT\r" type="string" offset="2"/>
+ </match>
+ <match value="0xfeff" offset="0">
+ <match value="WEBVTT\n" type="string" offset="2"/>
+ </match>
+ <!-- Common Header -->
<match value="WEBVTT FILE\r" type="string" offset="0"/>
<match value="WEBVTT FILE\n" type="string" offset="0"/>
</magic>
+ <magic priority="30">
+ <!-- With a custom header - needs a lower priority -->
+ <match value="WEBVTT " type="string" offset="0">
+ <match value="\n\n" type="string" offset="10:50" />
+ </match>
+ <match value="WEBVTT " type="string" offset="0">
+ <match value="\r\r" type="string" offset="10:50" />
+ </match>
+ <match value="WEBVTT " type="string" offset="0">
+ <match value="\r\n\r\n" type="string" offset="10:50" />
+ </match>
+ </magic>
<glob pattern="*.vtt"/>
<sub-class-of type="text/plain"/>
</mime-type>
--
To stop receiving notification emails like this one, please contact
"commits@tika.apache.org" <co...@tika.apache.org>.