You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tika.apache.org by ju...@apache.org on 2009/09/27 16:54:03 UTC
svn commit: r819322 -
/lucene/tika/trunk/tika-core/src/main/resources/org/apache/tika/mime/tika-mimetypes.xml
Author: jukka
Date: Sun Sep 27 14:54:02 2009
New Revision: 819322
URL: http://svn.apache.org/viewvc?rev=819322&view=rev
Log:
TIKA-285: Update media type registry to the latest httpd mime type database
More merging of the mime.types information. Work in progress...
Modified:
lucene/tika/trunk/tika-core/src/main/resources/org/apache/tika/mime/tika-mimetypes.xml
Modified: lucene/tika/trunk/tika-core/src/main/resources/org/apache/tika/mime/tika-mimetypes.xml
URL: http://svn.apache.org/viewvc/lucene/tika/trunk/tika-core/src/main/resources/org/apache/tika/mime/tika-mimetypes.xml?rev=819322&r1=819321&r2=819322&view=diff
==============================================================================
--- lucene/tika/trunk/tika-core/src/main/resources/org/apache/tika/mime/tika-mimetypes.xml (original)
+++ lucene/tika/trunk/tika-core/src/main/resources/org/apache/tika/mime/tika-mimetypes.xml Sun Sep 27 14:54:02 2009
@@ -641,13 +641,6 @@
<root-XML localName="feed" namespaceURI="http://purl.org/atom/ns#" />
</mime-type>
- <mime-type type="application/mac-binhex40">
- <magic priority="50">
- <match value="must\ be\ converted\ with\ BinHex" type="string" offset="11" />
- </magic>
- <glob pattern="*.hqx" />
- </mime-type>
-
<mime-type type="application/mac-compactpro">
<glob pattern="*.cpt" />
</mime-type>
@@ -1379,120 +1372,6 @@
<mime-type type="model/vrml">
<glob pattern="*.vrml" />
</mime-type>
- <mime-type type="text/troff">
- <magic priority="50">
- <match value=".\\"" type="string" offset="0" />
- <match value="'\\"" type="string" offset="0" />
- <match value="'.\\"" type="string" offset="0" />
- <match value="\\"" type="string" offset="0" />
- <match value="'''" type="string" offset="0" />
- </magic>
- </mime-type>
- <mime-type type="text/x-diff">
- <magic priority="50">
- <match value="diff\ " type="string" offset="0" />
- <match value="***\ " type="string" offset="0" />
- <match value="Only\ in\ " type="string" offset="0" />
- <match value="Common\ subdirectories:\ " type="string" offset="0" />
- <match value="Index:" type="string" offset="0" />
- </magic>
- </mime-type>
- <mime-type type="video/mpeg">
- <glob pattern="*.mpg" />
- <glob pattern="*.mpeg" />
- </mime-type>
- <mime-type type="video/quicktime">
- <magic priority="50">
- <match value="moov" type="string" offset="4" />
- <match value="mdat" type="string" offset="4" />
- <match value="ftyp" type="string" offset="4" />
- </magic>
- <glob pattern="*.mov" />
- </mime-type>
- <mime-type type="video/x-flc">
- <glob pattern="*.flc" />
- </mime-type>
- <mime-type type="video/x-fli">
- <glob pattern="*.fli" />
- </mime-type>
- <mime-type type="video/x-flv">
- <magic priority="50">
- <match value="FLV" type="string" offset="0" />
- </magic>
- <glob pattern="*.flv" />
- </mime-type>
- <mime-type type="video/x-jng">
- <magic priority="50">
- <match value="\x8bJNG" type="string" offset="0" />
- </magic>
- <glob pattern="*.jng" />
- </mime-type>
- <mime-type type="video/x-mng">
- <magic priority="50">
- <match value="\x8aMNG" type="string" offset="0" />
- </magic>
- <glob pattern="*.mng" />
- </mime-type>
- <mime-type type="video/x-msvideo">
- <magic priority="50">
- <match value="RIFF....AVI " type="string" offset="0"
- mask="0xFFFFFFFF00000000FFFFFFFF" />
- </magic>
- <glob pattern="*.avi" />
- <alias type="video/avi" />
- <alias type="video/msvideo" />
- </mime-type>
- <mime-type type="video/x-sgi-movie">
- <magic priority="50">
- <match value="MOVI" type="string" offset="0" />
- </magic>
- </mime-type>
- <mime-type type="application/x-Berkeley-DB">
- <magic priority="50">
- <match value="0x00061561" type="big32" offset="0" />
- <match value="0x00061561" type="host32" offset="12" />
- <match value="0x00061561" type="big32" offset="12" />
- <match value="0x00061561" type="little32" offset="12" />
- <match value="0x00053162" type="host32" offset="12" />
- <match value="0x00053162" type="big32" offset="12" />
- <match value="0x00053162" type="little32" offset="12" />
- <match value="0x00042253" type="host32" offset="12" />
- <match value="0x00042253" type="big32" offset="12" />
- <match value="0x00042253" type="little32" offset="12" />
- <match value="0x00040988" type="host32" offset="12" />
- <match value="0x00040988" type="little32" offset="12" />
- <match value="0x00040988" type="big32" offset="12" />
- <match value="0x00053162" type="host32" offset="0" />
- <match value="0x00053162" type="big32" offset="0" />
- <match value="0x00053162" type="little32" offset="0" />
- </magic>
- </mime-type>
- <mime-type type="application/x-BibTeX-text-file">
- <magic priority="50">
- <match value="%\ BibTeX\ `" type="string" offset="0" />
- <match value="%%%\ \ " type="string" offset="73" />
- <match value="%\ BibTeX\ standard\ bibliography\ " type="string" offset="0" />
- <match value="%%%\ \ @BibTeX-style-file{" type="string" offset="73" />
- <match value="@article{" type="string" offset="0" />
- <match value="@book{" type="string" offset="0" />
- <match value="@inbook{" type="string" offset="0" />
- <match value="@incollection{" type="string" offset="0" />
- <match value="@inproceedings{" type="string" offset="0" />
- <match value="@manual{" type="string" offset="0" />
- <match value="@misc{" type="string" offset="0" />
- <match value="@preamble{" type="string" offset="0" />
- <match value="@phdthesis{" type="string" offset="0" />
- <match value="@techreport{" type="string" offset="0" />
- <match value="@unpublished{" type="string" offset="0" />
- </magic>
- <glob pattern="*.bib" />
- <glob pattern="*.bibtex" />
- </mime-type>
- <mime-type type="application/x-BinHex-binary-text">
- <magic priority="50">
- <match value="must\ be\ converted\ with\ BinHex" type="string" offset="11" />
- </magic>
- </mime-type>
<mime-type type="application/activemessage"/>
<mime-type type="application/andrew-inset">
@@ -1599,9 +1478,16 @@
<mime-type type="application/lost+xml">
<glob pattern="*.lostxml"/>
</mime-type>
+
<mime-type type="application/mac-binhex40">
+ <alias type="application/mac-binhex"/>
+ <alias type="application/binhex"/>
+ <magic priority="50">
+ <match value="must\ be\ converted\ with\ BinHex" type="string" offset="11"/>
+ </magic>
<glob pattern="*.hqx"/>
</mime-type>
+
<mime-type type="application/mac-compactpro">
<glob pattern="*.cpt"/>
</mime-type>
@@ -3142,6 +3028,50 @@
<mime-type type="application/x-bcpio">
<glob pattern="*.bcpio"/>
</mime-type>
+
+ <mime-type type="application/x-berkeley-db">
+ <magic priority="50">
+ <match value="0x00061561" type="big32" offset="0"/>
+ <match value="0x00061561" type="host32" offset="12"/>
+ <match value="0x00061561" type="big32" offset="12"/>
+ <match value="0x00061561" type="little32" offset="12"/>
+ <match value="0x00053162" type="host32" offset="12"/>
+ <match value="0x00053162" type="big32" offset="12"/>
+ <match value="0x00053162" type="little32" offset="12"/>
+ <match value="0x00042253" type="host32" offset="12"/>
+ <match value="0x00042253" type="big32" offset="12"/>
+ <match value="0x00042253" type="little32" offset="12"/>
+ <match value="0x00040988" type="host32" offset="12"/>
+ <match value="0x00040988" type="little32" offset="12"/>
+ <match value="0x00040988" type="big32" offset="12"/>
+ <match value="0x00053162" type="host32" offset="0"/>
+ <match value="0x00053162" type="big32" offset="0"/>
+ <match value="0x00053162" type="little32" offset="0"/>
+ </magic>
+ </mime-type>
+
+ <mime-type type="application/x-bibtex-text-file">
+ <magic priority="50">
+ <match value="%\ BibTeX\ `" type="string" offset="0"/>
+ <match value="%%%\ \ " type="string" offset="73"/>
+ <match value="%\ BibTeX\ standard\ bibliography\ " type="string" offset="0"/>
+ <match value="%%%\ \ @BibTeX-style-file{" type="string" offset="73"/>
+ <match value="@article{" type="string" offset="0"/>
+ <match value="@book{" type="string" offset="0"/>
+ <match value="@inbook{" type="string" offset="0"/>
+ <match value="@incollection{" type="string" offset="0"/>
+ <match value="@inproceedings{" type="string" offset="0"/>
+ <match value="@manual{" type="string" offset="0"/>
+ <match value="@misc{" type="string" offset="0"/>
+ <match value="@preamble{" type="string" offset="0"/>
+ <match value="@phdthesis{" type="string" offset="0"/>
+ <match value="@techreport{" type="string" offset="0"/>
+ <match value="@unpublished{" type="string" offset="0"/>
+ </magic>
+ <glob pattern="*.bib"/>
+ <glob pattern="*.bibtex"/>
+ </mime-type>
+
<mime-type type="application/x-bittorrent">
<glob pattern="*.torrent"/>
</mime-type>
@@ -3335,6 +3265,7 @@
<mime-type type="application/x-rar-compressed">
<glob pattern="*.rar"/>
</mime-type>
+
<mime-type type="application/x-sh">
<sub-class-of type="text/plain"/>
<glob pattern="*.sh"/>
@@ -3909,7 +3840,15 @@
<mime-type type="text/tab-separated-values">
<glob pattern="*.tsv"/>
</mime-type>
+
<mime-type type="text/troff">
+ <magic priority="50">
+ <match value=".\\"" type="string" offset="0"/>
+ <match value="'\\"" type="string" offset="0"/>
+ <match value="'.\\"" type="string" offset="0"/>
+ <match value="\\"" type="string" offset="0"/>
+ <match value="'''" type="string" offset="0"/>
+ </magic>
<glob pattern="*.t"/>
<glob pattern="*.tr"/>
<glob pattern="*.roff"/>
@@ -3917,6 +3856,7 @@
<glob pattern="*.me"/>
<glob pattern="*.ms"/>
</mime-type>
+
<mime-type type="text/ulpfec"/>
<mime-type type="text/uri-list">
<glob pattern="*.uri"/>
@@ -3985,6 +3925,19 @@
<glob pattern="*.hh"/>
<glob pattern="*.dic"/>
</mime-type>
+
+ <mime-type type="text/x-diff">
+ <magic priority="50">
+ <match value="diff\ " type="string" offset="0"/>
+ <match value="***\ " type="string" offset="0"/>
+ <match value="Only\ in\ " type="string" offset="0"/>
+ <match value="Common\ subdirectories:\ " type="string" offset="0"/>
+ <match value="Index:" type="string" offset="0"/>
+ </magic>
+ <glob pattern="*.diff"/>
+ <glob pattern="*.patch"/>
+ </mime-type>
+
<mime-type type="text/x-fortran">
<glob pattern="*.f"/>
<glob pattern="*.for"/>
@@ -4056,6 +4009,7 @@
<glob pattern="*.mpg4"/>
</mime-type>
<mime-type type="video/mp4v-es"/>
+
<mime-type type="video/mpeg">
<glob pattern="*.mpeg"/>
<glob pattern="*.mpg"/>
@@ -4063,6 +4017,7 @@
<glob pattern="*.m1v"/>
<glob pattern="*.m2v"/>
</mime-type>
+
<mime-type type="video/mpeg4-generic"/>
<mime-type type="video/mpv"/>
<mime-type type="video/nv"/>
@@ -4071,10 +4026,17 @@
</mime-type>
<mime-type type="video/parityfec"/>
<mime-type type="video/pointer"/>
+
<mime-type type="video/quicktime">
+ <magic priority="50">
+ <match value="moov" type="string" offset="4"/>
+ <match value="mdat" type="string" offset="4"/>
+ <match value="ftyp" type="string" offset="4"/>
+ </magic>
<glob pattern="*.qt"/>
<glob pattern="*.mov"/>
</mime-type>
+
<mime-type type="video/raw"/>
<mime-type type="video/rtp-enc-aescm128"/>
<mime-type type="video/rtx"/>
@@ -4115,15 +4077,40 @@
<mime-type type="video/x-f4v">
<glob pattern="*.f4v"/>
</mime-type>
+
+ <mime-type type="video/x-flc">
+ <glob pattern="*.flc"/>
+ </mime-type>
+
<mime-type type="video/x-fli">
<glob pattern="*.fli"/>
</mime-type>
+
<mime-type type="video/x-flv">
+ <magic priority="50">
+ <match value="FLV" type="string" offset="0"/>
+ </magic>
<glob pattern="*.flv"/>
</mime-type>
+
+ <mime-type type="video/x-jng">
+ <magic priority="50">
+ <match value="\x8bJNG" type="string" offset="0"/>
+ </magic>
+ <glob pattern="*.jng"/>
+ </mime-type>
+
<mime-type type="video/x-m4v">
<glob pattern="*.m4v"/>
</mime-type>
+
+ <mime-type type="video/x-mng">
+ <magic priority="50">
+ <match value="\x8aMNG" type="string" offset="0"/>
+ </magic>
+ <glob pattern="*.mng"/>
+ </mime-type>
+
<mime-type type="video/x-ms-asf">
<glob pattern="*.asf"/>
<glob pattern="*.asx"/>
@@ -4140,12 +4127,24 @@
<mime-type type="video/x-ms-wvx">
<glob pattern="*.wvx"/>
</mime-type>
+
<mime-type type="video/x-msvideo">
+ <alias type="video/avi"/>
+ <alias type="video/msvideo"/>
+ <magic priority="50">
+ <match value="RIFF....AVI " type="string" offset="0"
+ mask="0xFFFFFFFF00000000FFFFFFFF"/>
+ </magic>
<glob pattern="*.avi"/>
</mime-type>
+
<mime-type type="video/x-sgi-movie">
+ <magic priority="50">
+ <match value="MOVI" type="string" offset="0"/>
+ </magic>
<glob pattern="*.movie"/>
</mime-type>
+
<mime-type type="x-conference/x-cooltalk">
<glob pattern="*.ice"/>
</mime-type>