No solution for that problem yet, sorry. As mentioned in the discussion above it would be necessary to store a text version in parallel to the binary somewhere, and the project I would have needed it for went another route before that was sorted out.
Below is my version of the search_content_filter, which does pdf and word conversion, but it is just in a testing state. Among other things the executables for the conversion need to be parametrized. Also you need to switch off the abstracts display upon search results obviously, otherwise the conversion is triggered on every results page for each pdf and word document found.
ad_proc search_content_filter {
_txt
_data
mime
} {
@author Neophytos Demetriou
} {
upvar $_txt txt
upvar $_data data
ns_log notice "!> search_content_filter +++ $mime"
set file_ending(application/msword) doc
set conversion_code(application/msword) {exec catdoc -d utf-8 $tmp_orig > $tmp_txt}
set file_ending(application/pdf) pdf
set conversion_code(application/pdf) {exec pdftotext -enc UTF-8 $tmp_orig}
switch $mime {
{text/plain} {
set txt $data
}
{text/html} {
set txt $data
}
{application/pdf} -
{application/msword} {
# convert to text
# get tempfile name
set tmpnam [ns_tmpnam]
set tmp_orig "$tmpnam.$file_ending($mime)"
set tmp_txt "$tmpnam.txt"
# write original data to tmpfile
set tmp_orig_fp [open $tmp_orig w]
fconfigure $tmp_orig_fp -encoding binary
puts $tmp_orig_fp $data
close $tmp_orig_fp
# call conversion program
eval $conversion_code($mime)
# read temporary text file
set tmp_txt_fp [open $tmp_txt]
fconfigure $tmp_txt_fp -encoding utf-8
set txt [read $tmp_txt_fp]
close $tmp_txt_fp
# delete tmp files
file delete $tmp_orig
file delete $tmp_txt
}
}
}
