mirror of
https://github.com/yacy/yacy_search_server.git
synced 2024-09-19 00:01:41 +02:00
b6fb239e74
some file types are containers for several files. These containers had been parsed in such a way that the set of resulting parsed content was merged into one single document before parsing. Using this parser infrastructure it is not possible to parse document containers that contain individual files. An example is a rss file where the rss messages can be treated as individual documents with their own url reference. Another example is a surrogate file which was treated with a special operation outside of the parser infrastructure. This commit introduces a redesigned parser interface and a new abstract parser implementation. The new parser interface has now only one entry point and returns always a set of parsed documents. In case of single documents the parser method returns a set of one documents. To be compliant with the new interface, the zip and tar parser had been also completely redesigned. All parsers are now much more simple and cleaner in its structure. The switchboard operations had been extended to operate with sets of parsed files, not single parsed files. additionally, parsing of jar manifest files had been added. git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@6955 6c8d7289-2bf4-0310-a012-ef5d649a1542
129 lines
3.9 KiB
Plaintext
129 lines
3.9 KiB
Plaintext
###
|
|
### This is the MIME file type matching configuration for the YaCy server
|
|
###
|
|
|
|
# Extension = MIME type
|
|
7z = application/x-7z-compressed
|
|
ai = application/postscript
|
|
aiff = audio/x-aiff
|
|
asp = text/html
|
|
aspx = text/html
|
|
au = audio/basic
|
|
avi = video/x-msvideo
|
|
bat = text/plain
|
|
bin = application/octet-stream
|
|
bmp = image/bmp
|
|
bz2 = application/x-bzip2
|
|
class = application/octet-stream
|
|
c = text/plain
|
|
com = application/octet-stream
|
|
css = text/css
|
|
csv = text/csv
|
|
db = application/octet-stream
|
|
dll = application/octet-stream
|
|
doc = application/msword
|
|
docx = application/msword
|
|
dot = application/msword
|
|
dvi = application/x-dvi
|
|
eps = application/postscript
|
|
exe = application/octet-stream
|
|
gif = image/gif
|
|
gz = application/gzip
|
|
gpx = text/xml
|
|
hqx = application/mac-binhex40
|
|
htm = text/html
|
|
html = text/html
|
|
ico = image/bmp
|
|
jar = application/java-archive
|
|
java = text/plain
|
|
jpe = image/jpeg
|
|
jpeg = image/jpeg
|
|
jpg = image/jpeg
|
|
js = text/javascript
|
|
jsp = text/html
|
|
kml = application/vnd.google-earth.kml+xml
|
|
lha = application/x-lzh
|
|
lzh = application/x-lzh
|
|
m4v = video/x-m4v
|
|
mf = application/octet-stream
|
|
mov = video/quicktime
|
|
mp2 = audio/mpeg
|
|
mp3 = audio/mpeg
|
|
mp4 = video/mp4
|
|
mpe = video/mpeg
|
|
mpeg = video/mpeg
|
|
mpg = video/mpeg
|
|
odt = application/vnd.oasis.opendocument.text
|
|
ods = application/vnd.oasis.opendocument.spreadsheet
|
|
odp = application/vnd.oasis.opendocument.presentation
|
|
odg = application/vnd.oasis.opendocument.graphics
|
|
odc = application/vnd.oasis.opendocument.chart
|
|
odf = application/vnd.oasis.opendocument.formula
|
|
odb = application/vnd.oasis.opendocument.database
|
|
odi = application/vnd.oasis.opendocument.image
|
|
odm = application/vnd.oasis.opendocument.text-master
|
|
opml = text/x-opml
|
|
ott = application/vnd.oasis.opendocument.text-template
|
|
ots = application/vnd.oasis.opendocument.spreadsheet-template
|
|
otp = application/vnd.oasis.opendocument.presentation-template
|
|
otg = application/vnd.oasis.opendocument.graphics-template
|
|
ogg = audio/ogg-vorbis
|
|
pac = application/x-ns-proxy-autoconfig
|
|
pdf = application/pdf
|
|
php = application/x-httpd-php
|
|
phtml = application/x-httpd-php
|
|
pl = text/plain
|
|
png = image/png
|
|
pot = application/mspowerpoint
|
|
pps = application/mspowerpoint
|
|
ppt = application/mspowerpoint
|
|
pptx = application/mspowerpoint
|
|
ppz = application/mspowerpoint
|
|
ps = application/postscript
|
|
py = text/html
|
|
qt = video/quicktime
|
|
ra = audio/x-pn-realaudio
|
|
ram = audio/x-pn-realaudio
|
|
rar = application/x-rar
|
|
rdf = application/rdf+xml
|
|
rm = audio/x-pn-realaudio-plugin
|
|
rpm = application/x-rpm
|
|
rss = application/rss+xml
|
|
rtf = application/rtf
|
|
sh = text/plain
|
|
shtml = text/html
|
|
stream = audio/x-qt-stream
|
|
svg = image/svg+xml
|
|
swf = application/x-shockwave-flash
|
|
sxw = application/OOo-writer
|
|
sxc = application/OOo-calc
|
|
sxd = application/OOo-draw
|
|
sxi = application/OOo-impress
|
|
tar = application/tar
|
|
tbz = application/x-bzip2
|
|
tbz2 = application/x-bzip2
|
|
tex = application/x-tex
|
|
tgz = application/tar
|
|
tif = image/tiff
|
|
tiff = image/tiff
|
|
torrent = application/x-bittorrent
|
|
txt = text/plain
|
|
vdx = application/x-visio
|
|
vtx = application/x-visio
|
|
vcf = text/x-vcard
|
|
vsd = application/x-visio
|
|
vst = application/x-visio
|
|
vss = application/vnd.visio
|
|
wav = audio/x-wav
|
|
wmv = video/x-ms-wmv
|
|
xhtml = text/xhtml+xml
|
|
xla = application/msexcel
|
|
xls = application/msexcel
|
|
xlsx = application/msexcel
|
|
xpi = application/x-xpinstall
|
|
xsl = text/xml
|
|
xml = text/xml
|
|
Z = application/x-compress
|
|
zip = application/zip
|
|
default = application/octet-stream
|