You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tika.apache.org by ma...@apache.org on 2016/04/19 04:14:55 UTC
[1/2] tika git commit: updated mime magic for cab, quicktime,
fits and netcdf based on fht analysis on polar-data dump
Repository: tika
Updated Branches:
refs/heads/master e4dc21ce2 -> d40f8d40b
updated mime magic for cab, quicktime, fits and netcdf based on fht analysis on polar-data dump
Project: http://git-wip-us.apache.org/repos/asf/tika/repo
Commit: http://git-wip-us.apache.org/repos/asf/tika/commit/86579ec5
Tree: http://git-wip-us.apache.org/repos/asf/tika/tree/86579ec5
Diff: http://git-wip-us.apache.org/repos/asf/tika/diff/86579ec5
Branch: refs/heads/master
Commit: 86579ec5644ca5fac47d945423b824d8ca7b0c57
Parents: 9a1ba94
Author: Nithin Krishna <ot...@usc.edu>
Authored: Thu Mar 3 02:28:17 2016 -0800
Committer: Nithin Krishna <ot...@usc.edu>
Committed: Thu Mar 3 02:28:17 2016 -0800
----------------------------------------------------------------------
.../resources/org/apache/tika/mime/tika-mimetypes.xml | 11 +++++++++++
1 file changed, 11 insertions(+)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/tika/blob/86579ec5/tika-core/src/main/resources/org/apache/tika/mime/tika-mimetypes.xml
----------------------------------------------------------------------
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 95f41e6..196d9df 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
@@ -1506,6 +1506,9 @@
<mime-type type="application/vnd.ms-asf"/>
<mime-type type="application/vnd.ms-cab-compressed">
<glob pattern="*.cab"/>
+ <magic priority="50">
+ <match value="MSCF" type="string" offset="0" />
+ </magic>
</mime-type>
<!-- http://www.iana.org/assignments/media-types/application/vnd.ms-excel -->
@@ -3590,7 +3593,11 @@
<mime-type type="application/x-netcdf">
<glob pattern="*.nc"/>
<glob pattern="*.cdf"/>
+ <magic priority="50">
+ <match value="0x43444601" type="string" offset="0"/>
+ </magic>
</mime-type>
+
<mime-type type="application/x-pkcs12">
<glob pattern="*.p12"/>
<glob pattern="*.pfx"/>
@@ -4629,6 +4636,9 @@
<mime-type type="image/fits">
<sub-class-of type="application/fits"/>
+ <magic priority="50">
+ <match value="0x53494D504C4520203D2020" type="string" offset="0"/>
+ </magic>
</mime-type>
<mime-type type="image/g3fax">
@@ -6370,6 +6380,7 @@
<match value="mdat" type="string" offset="4"/>
<!-- General match, specific ftypXXX ones present for subtypes -->
<match value="ftyp" type="string" offset="4"/>
+ <match value="wide" type="string" offset="4"/>
</magic>
<glob pattern="*.qt"/>
<glob pattern="*.mov"/>
[2/2] tika git commit: Update changes.txt and record #85 and fix
conflicts.
Posted by ma...@apache.org.
Update changes.txt and record #85 and fix conflicts.
Project: http://git-wip-us.apache.org/repos/asf/tika/repo
Commit: http://git-wip-us.apache.org/repos/asf/tika/commit/d40f8d40
Tree: http://git-wip-us.apache.org/repos/asf/tika/tree/d40f8d40
Diff: http://git-wip-us.apache.org/repos/asf/tika/diff/d40f8d40
Branch: refs/heads/master
Commit: d40f8d40bf9458e664dbad2ab797718eba828fcb
Parents: e4dc21c 86579ec
Author: Chris Mattmann <ma...@apache.org>
Authored: Mon Apr 18 19:14:38 2016 -0700
Committer: Chris Mattmann <ma...@apache.org>
Committed: Mon Apr 18 19:14:38 2016 -0700
----------------------------------------------------------------------
CHANGES.txt | 3 ++-
.../main/resources/org/apache/tika/mime/tika-mimetypes.xml | 9 +++++++++
2 files changed, 11 insertions(+), 1 deletion(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/tika/blob/d40f8d40/CHANGES.txt
----------------------------------------------------------------------
diff --cc CHANGES.txt
index ea7eb49,08ac1dc..9f37ab1
--- a/CHANGES.txt
+++ b/CHANGES.txt
@@@ -1,43 -1,5 +1,44 @@@
Release 1.13 - ???
+ * Improvements to MIME database for detection of Scientific
- and other formats present in the TREC-DD-Polar dataset (TIKA-1881).
++ and other formats present in the TREC-DD-Polar dataset
++ (TIKA-1881, GitHub-85).
+
+ * LinkContentHandler now extracts links from script tags
+ via Joseph Naegele (TIKA-1937).
+
+ * Handle per page IOExceptions more robustly in PDFParser (TIKA-1948).
+
+ * Upgrade commons-compress to 1.11 (TIKA-1949).
+
+ * Add detection for embedded MSChart.Graph files (TIKA-1033).
+
+ * Fix NPE in Sqlite parser from Nick C (TIKA-1927).
+
+ * Fix NPE in Open Document parser from Nick C (TIKA-1916).
+
+ * Upgrade mp4parser's isoparser to 1.1.7 (TIKA-1924 and TIKA-1931).
+
+ * Upgrade BouncyCastle to 1.54 (TIKA-1923).
+
+ * Upgrade Jackcess to 2.1.3 (TIKA-1922).
+
+ * Upgrade Drew Noakes' metadata-extractor to 2.8.1 (TIKA-1921).
+
+ * Upgrade Gson in tika-serialization to 2.6.2 (TIka-1920).
+
+ * Upgrade commons-cli in tika-batch to 1.3.1 (TIKA-1919).
+
+ * Upgrade to PDFBox 2.0.0 (TIKA-1285). MAJOR CHANGES in PDFParser:
+ * The classic sequential parser is no longer available.
+ * Tiff files are no longer extracted by default. See
+ https://pdfbox.apache.org/2.0/dependencies.html#optional-components
+ for optional components to process Tiff files.
+ * Some truncated/corrupted files that had some content extracted
+ with 1.8.11 may have no content extracted in 2.0.0 (see TIKA-1912).
+
+ * Add XMPMM support to PDFParser and JpegParser via Jempbox (TIKA-1894).
+
* Move serialization of TikaConfig to tika-core and enable dumping
of the config file via tika-app (TIKA-1657).
http://git-wip-us.apache.org/repos/asf/tika/blob/d40f8d40/tika-core/src/main/resources/org/apache/tika/mime/tika-mimetypes.xml
----------------------------------------------------------------------
diff --cc tika-core/src/main/resources/org/apache/tika/mime/tika-mimetypes.xml
index 716e2a1,196d9df..7e22526
--- 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
@@@ -1526,10 -1505,10 +1526,13 @@@
</mime-type>
<mime-type type="application/vnd.ms-asf"/>
<mime-type type="application/vnd.ms-cab-compressed">
+ <magic priority="50">
+ <match value="MSCF\000\000\000\000" type="string" offset="0"/>
+ </magic>
<glob pattern="*.cab"/>
+ <magic priority="50">
+ <match value="MSCF" type="string" offset="0" />
+ </magic>
</mime-type>
<!-- http://www.iana.org/assignments/media-types/application/vnd.ms-excel -->
@@@ -3623,10 -3594,10 +3626,12 @@@
<glob pattern="*.nc"/>
<glob pattern="*.cdf"/>
<magic priority="50">
+ <match value="CDF\001" type="string" offset="0" />
+ <match value="CDF\002" type="string" offset="0" />
+ <match value="0x43444601" type="string" offset="0"/>
</magic>
</mime-type>
+
<mime-type type="application/x-pkcs12">
<glob pattern="*.p12"/>
<glob pattern="*.pfx"/>