Parent: [ec3dbb] (diff)

Child: [d46b76] (diff)

Download this file

mimeconf    353 lines (336 with data), 12.8 kB

# (C) 2004 J.F.Dockes

# Associations of mime types to processing filters ([index] section).
# Other sections describe auxiliary properties associated to the mime types.

## #######################################
# Decompression: these types need a first pass to create a temp file to
# work with. We use a script because uncompress utilities usually work in
# place, which is not suitable. 
#
# Obviously this should be in a [decompress] section or such, but it was once
# forgotten and remained global for compatibility...
#
# The %t parameter will be substituted to the name of a temporary directory
# by recoll. This directory is guaranteed empty when calling the filter
#
# The %f parameter will be substituted with the input file. 
#
# The script (ie: rcluncomp) must output the uncompressed file name on
# stdout. 
application/x-gzip  =  uncompress rcluncomp gunzip %f %t
application/x-compress = uncompress rcluncomp gunzip %f %t
application/x-bzip2 =  uncompress rcluncomp bunzip2 %f %t
application/x-xz = uncompress rcluncomp unxz %f %t
application/x-lzma = uncompress rcluncomp unxz %f %t

## ###################################
# Filters for indexing and internal preview. 
# The "internal" filters are hardwired in the c++ code.
# The external "exec" filters are typically scripts. By default, they output the
# document in simple html format, have a look at the scripts.
# A different format (ie text/plain), and a character set can be defined for
# each filter, see the exemples below (ie: msword)
[index]

# MSWORD: the rcldoc script handles a number of marginal case that raw
# antiword won't:
#  - with wvWare: "text stream of this file is too small to handle" 
#  - with unrtf: rtf files disguising as doc files.
# The default is now again to use rcldoc. Use raw antiword if speed is more
# important for you than catching all data, 
application/msword = exec rcldoc
#application/msword = exec antiword -t -i 1 -m UTF-8;mimetype=text/plain
# You can also use wvware directly but it's much slower.
# application/msword = exec wvWare --charset=utf-8 --nographics

# Also Handle the mime type returned by "file -i" for a suffix-less word
# file. This could probably just as well be an excel file, but we have to
# chose one.
application/vnd.ms-office = exec rcldoc

application/ogg = execm rclaudio
application/pdf = exec rclpdf
application/postscript = exec pstotext;charset=iso-8859-1;mimetype=text/plain
application/vnd.ms-excel = exec xls2csv -c "	" -d utf-8;mimetype=text/plain
application/vnd.ms-powerpoint = exec catppt -d utf-8;mimetype=text/plain
application/vn.oasis.opendocument.txt = exec rclsoff
application/vnd.openxmlformats-officedocument.wordprocessingml.document = \
 exec rclopxml
application/vnd.openxmlformats-officedocument.wordprocessingml.template = \
 exec rclopxml
application/vnd.openxmlformats-officedocument.presentationml.template = \
 exec rclopxml
application/vnd.openxmlformats-officedocument.presentationml.presentation = \
 exec rclopxml
application/vnd.openxmlformats-officedocument.spreadsheetml.sheet = \
 exec rclopxml
application/vnd.openxmlformats-officedocument.spreadsheetml.template =\
 exec rclopxml
application/vnd.sun.xml.calc = exec rclsoff
application/vnd.sun.xml.calc.template = exec rclsoff
application/vnd.sun.xml.draw = exec rclsoff
application/vnd.sun.xml.draw.template = exec rclsoff
application/vnd.sun.xml.impress = exec rclsoff
application/vnd.sun.xml.impress.template = exec rclsoff
application/vnd.sun.xml.math = exec rclsoff
application/vnd.sun.xml.writer = exec rclsoff
application/vnd.sun.xml.writer.global = exec rclsoff
application/vnd.sun.xml.writer.template = exec rclsoff
application/vnd.wordperfect = exec wpd2html;mimetype=text/html
application/x-abiword = exec rclabw
application/x-awk = internal text/plain
application/x-chm = execm rclchm
application/x-dia-diagram = execm rcldia;mimetype=text/plain
application/x-dvi = exec rcldvi
application/x-flac = execm rclaudio
application/x-gnuinfo = execm rclinfo
application/x-gnumeric = exec rclgnm
application/x-kword = exec rclkwd
application/x-lyx = exec rcllyx
application/x-mimehtml = internal message/rfc822
application/x-okular-notes = exec rclokulnote
application/x-perl = internal text/plain
application/x-rar = execm rclrar;charset=default
application/x-scribus = exec rclscribus
application/x-shellscript = internal text/plain
#application/x-tar = execm rcltar
application/x-tex = exec rcltex
application/x-webarchive = execm rclwar
application/zip = execm rclzip;charset=default
audio/mpeg = execm rclaudio
audio/x-karaoke = execm rclkar
image/gif = execm rclimg
image/jp2 = execm rclimg
image/jpeg = execm rclimg
image/png = execm rclimg
image/tiff = execm rclimg
image/vnd.djvu = exec rcldjvu
image/svg+xml = exec rclsvg
image/x-xcf = execm rclimg
message/rfc822 = internal
text/calendar = execm rclics;mimetype=text/plain
text/html  = internal 
text/plain = internal 
text/rtf = exec unrtf --nopict --html;mimetype=text/html
text/x-c = internal
text/x-c++ = internal
text/x-c+ = internal
text/x-csv = internal text/plain
text/x-fictionbook = exec rclfb2
text/x-gaim-log = exec rclgaim
text/x-html-sidux-man = exec rclsiduxman
text/x-html-aptosid-man = exec rclaptosidman
text/x-chm-html = internal text/html
text/x-ini = internal text/plain
text/x-mail = internal
text/x-man = exec rclman
text/x-perl = internal text/plain
text/x-purple-log = exec rclpurple
text/x-purple-html-log = internal text/html
text/x-python = exec rclpython
text/x-shellscript = internal text/plain
text/x-tex = exec rcltex

application/xml = exec rclxml
text/xml = exec rclxml
# Using these instead of the two above would index all parameter and tag
# names, attribute values etc, instead of just the text content.
#application/xml = internal text/plain
#text/xml = internal text/plain

## #############################################
# Icons to be used in the result list if required by gui config
[icons]
application/msword = wordprocessing
application/ogg = sownd
application/pdf = pdf
application/postscript = postscript
application/vnd.ms-excel = spreadsheet
application/vnd.ms-powerpoint = presentation
application/vn.oasis.opendocument.txt = wordprocessing
application/vnd.openxmlformats-officedocument.presentationml.presentation = presentation
application/vnd.openxmlformats-officedocument.presentationml.template = presentation
application/vnd.openxmlformats-officedocument.spreadsheetml.sheet = spreadsheet
application/vnd.openxmlformats-officedocument.spreadsheetml.template = spreadsheet
application/vnd.openxmlformats-officedocument.wordprocessingml.document = wordprocessing
application/vnd.openxmlformats-officedocument.wordprocessingml.template = wordprocessing
application/vnd.sun.xml.calc = spreadsheet
application/vnd.sun.xml.calc.template = spreadsheet
application/vnd.sun.xml.draw = drawing
application/vnd.sun.xml.draw.template = drawing
application/vnd.sun.xml.impress = presentation
application/vnd.sun.xml.impress.template = presentation
application/vnd.sun.xml.math  = wordprocessing
application/vnd.sun.xml.writer = wordprocessing
application/vnd.sun.xml.writer.global = wordprocessing
application/vnd.sun.xml.writer.template = wordprocessing
application/vnd.wordperfect = wordprocessing
application/x-abiword = wordprocessing
application/x-awk = source
application/x-chm = document
application/x-dia-diagram = drawing
application/x-dvi = document
application/x-flac = sownd
application/x-fsdirectory = folder
application/x-gnuinfo = document
application/x-gnumeric = spreadsheet
application/x-kword = wordprocessing
application/x-lyx = wordprocessing
application/x-mimehtml = message
application/x-okular-notes = document
application/x-perl = source
application/x-rar = archive
application/x-scribus = document
application/x-scribus = wordprocessing
application/x-shellscript = source
application/x-tar = archive
application/x-tex = wordprocessing
application/x-webarchive = archive
application/xml = document
application/zip = archive
audio/mpeg = sownd
audio/x-karaoke = sownd
image/bmp = image
image/gif = image
image/jp2 = image
image/jpeg = image
image/png = image
image/svg+xml = drawing
image/tiff = image
image/vnd.djvu = document
image/x-xcf = image
image/x-xpmi = image
message/rfc822 = message
text/html = html
text/plain = txt
text/rtf = wordprocessing
text/x-c = source
text/x-c+ = source
text/x-c++ = source
text/x-csv = txt
text/x-fictionbook = document
text/x-html-aptosid-man = aptosid-book
text/x-html-sidux-man = sidux-book
text/x-ini = txt
text/x-mail = message
text/x-man = document
text/x-perl = source
text/x-purple-html-log = pidgin
text/x-purple-log = pidgin
text/x-python = text-x-python
text/x-shellscript = source
text/x-tex = wordprocessing
text/xml = document

[categories]
# Categories group mime types by "kind". They can be used from the query
# language as an "rclcat" clause. This is fully dynamic, you can change the
# names and groups as you wish, only the mime types are stored in the index.
#
# If you add/remove categories, you may also want to change the
# "guifilters" section below.
text = \
      application/msword \
      application/pdf \
      application/postscript \
      application/vn.oasis.opendocument.txt \
      application/vnd.openxmlformats-officedocument.wordprocessingml.document \
      application/vnd.openxmlformats-officedocument.wordprocessingml.template \
      application/vnd.sun.xml.writer \
      application/vnd.sun.xml.writer.global \
      application/vnd.sun.xml.writer.template \
      application/vnd.wordperfect \
      application/x-abiword \
      application/x-awk \
      application/x-chm \
      application/x-dvi \
      application/x-kword \
      application/x-lyx \
      application/x-okular-notes \
      application/x-perl \
      application/x-scribus \
      application/x-gnuinfo \
      application/x-shellscript \
      application/x-tex \
      application/xml \
      text/xml \
      text/x-csv \
      text/x-tex \
      image/vnd.djvu \
      text/calendar \
      text/html \
      text/plain \
      text/rtf \
      text/x-c \
      text/x-c++ \
      text/x-c+ \
      text/x-fictionbook \
      text/x-html-aptosid-man \
      text/x-html-sidux-man \
      text/x-ini \
      text/x-man \
      text/x-perl \
      text/x-python \
      text/x-shellscript

spreadsheet = \
   application/vnd.ms-excel \
   application/vnd.openxmlformats-officedocument.spreadsheetml.sheet \
   application/vnd.openxmlformats-officedocument.spreadsheetml.template \
   application/vnd.sun.xml.calc \
   application/vnd.sun.xml.calc.template \
   application/x-gnumeric

presentation = application/vnd.ms-powerpoint \
  application/vnd.openxmlformats-officedocument.presentationml.template \
  application/vnd.openxmlformats-officedocument.presentationml.presentation \
  application/vnd.sun.xml.impress \
  application/vnd.sun.xml.impress.template

media = \
      application/ogg \
      application/x-flac \
      audio/mpeg \
      audio/x-karaoke \
      image/gif \
      image/jp2 \
      image/jpeg \
      image/png \
      image/svg+xml \
      image/tiff \
      image/x-xcf \
      image/bmp \
      image/x-xpmi \
      video/mp2p \
      video/mp2t \
      video/mp4 \
      video/x-msvideo \

message = message/rfc822 \
	  text/x-gaim-log \
	  text/x-mail \
	  text/x-purple-log \
	  text/x-purple-html-log \

other = application/vnd.sun.xml.draw \
        application/vnd.sun.xml.draw.template \
        application/vnd.sun.xml.math \
        application/x-dia-diagram \
        application/x-fsdirectory \
        application/x-mimehtml \
        application/x-rar \
	application/x-tar \
        application/x-webarchive \
	application/zip \

[guifilters]
# This defines the top level filters in the GUI (accessed by the the
# radiobuttons above the results area, or a toolbar combobox).
# Each entry defines a label and a query language fragment that will be
# applied to filter the current query if the option is activated.
#
# This does not really belong in mimeconf, but it does belong in the index
# config (not the GUI one), because it's not necessarily the same in all
# configs, it has to go somewhere, and it's not worth a separate config
# file...
#
# By default this filters by document category (see above), but any
# language fragment should be ok. Be aware though that the "document
# history" queries only know about simple "rclcat" filtering.
#
# If you don't want the filter names to be displayed in alphabetic order,
# you can define them with a colon. The part before the colon is not
# displayed but used for ordering, ie: a:zzbutshouldbefirst b:aacomeslast
#
text = rclcat:text
spreadsheet = rclcat:spreadsheet
presentation = rclcat:presentation
media = rclcat:media
message = rclcat:message
other = rclcat:other