mirror of
https://git.code.sf.net/p/seeddms/code
synced 2024-11-26 15:32:13 +00:00
92 lines
2.6 KiB
Plaintext
92 lines
2.6 KiB
Plaintext
Conversion to text for fulltext search
|
|
=======================================
|
|
|
|
text/plain
|
|
text/csv
|
|
application/csv
|
|
cat '%s'
|
|
|
|
application/pdf
|
|
pdftotext -nopgbrk %s - | sed -e 's/ [a-zA-Z0-9.]\{1\} / /g' -e 's/[0-9.]//g'
|
|
|
|
application/vnd.openxmlformats-officedocument.wordprocessingml.document
|
|
docx2txt '%s' -
|
|
|
|
application/msword
|
|
catdoc %s
|
|
|
|
application/vnd.openxmlformats-officedocument.spreadsheetml.sheet
|
|
xlsx2csv %s
|
|
|
|
application/vnd.ms-excel
|
|
xls2csv %s
|
|
|
|
text/html
|
|
html2text %s
|
|
|
|
Many office formats
|
|
unoconv -d document -f txt --stdout '%s'
|
|
|
|
Conversion to pdf for pdf preview
|
|
==================================
|
|
|
|
text/plain
|
|
text/csv
|
|
application/csv
|
|
application/vnd.oasis.opendocument.text
|
|
application/msword
|
|
application/vnd.wordperfect
|
|
text/rtf
|
|
unoconv -d document -f pdf --stdout -v '%f' > '%o'
|
|
|
|
image/png
|
|
image/jpg
|
|
image/jpeg
|
|
convert -f pdf -density 300 '%f' '%o'
|
|
|
|
application/vnd.ms-powerpoint
|
|
application/vnd.openxmlformats-officedocument.presentationml.presentation
|
|
application/vnd.oasis.opendocument.presentation
|
|
unoconv -d presentation -f pdf --stdout -v '%f' > '%o'
|
|
|
|
application/vnd.ms-excel
|
|
application/vnd.openxmlformats-officedocument.spreadsheetml.sheet
|
|
application/vnd.oasis.opendocument.spreadsheet
|
|
unoconv -d spreadsheet -f pdf --stdout -v '%f' > '%o'
|
|
|
|
Conversion to png for preview images
|
|
=====================================
|
|
|
|
If you have problems running convert on PDF documents then read this page
|
|
https://askubuntu.com/questions/1081895/trouble-with-batch-conversion-of-png-to-pdf-using-convert
|
|
It basically instructs you to comment out the line
|
|
|
|
<policy domain="coder" rights="none" pattern="PDF" />
|
|
|
|
in /etc/ImageMagick-6/policy.xml
|
|
|
|
image/jpg
|
|
image/jpeg
|
|
image/png
|
|
convert -resize %wx '%f' '%o'
|
|
|
|
application/pdf
|
|
gs -dBATCH -dNOPAUSE -sDEVICE=png16m -dPDFFitPage -r72x72 -sOutputFile=- -dFirstPage=1 -dLastPage=1 -q '%f' | convert -resize %wx png:- '%o'
|
|
|
|
text/plain
|
|
a2ps -1 -a1 -R -B -o - '%f' | gs -dBATCH -dNOPAUSE -sDEVICE=png16m -dFirstPage=1 -dLastPage=1 -dPDFFitPage -r72x72 -sOutputFile=- -q - | convert -resize %wx png:- '%o'
|
|
|
|
application/msword
|
|
application/vnd.oasis.opendocument.spreadsheet
|
|
application/vnd.oasis.opendocument.text
|
|
application/vnd.openxmlformats-officedocument.spreadsheetml.sheet
|
|
application/vnd.ms-excel
|
|
application/vnd.openxmlformats-officedocument.wordprocessingml.document
|
|
text/rtf
|
|
application/vnd.ms-powerpoint
|
|
text/csv
|
|
application/csv
|
|
application/vnd.wordperfect
|
|
unoconv -d document -e PageRange=1 -f pdf --stdout -v '%f' | gs -dBATCH -dNOPAUSE -sDEVICE=pngalpha -dPDFFitPage -r72x72 -sOutputFile=- -dFirstPage=1 -dLastPage=1 -q - | convert -resize %wx png:- '%o'
|
|
|