165 lines
4.0 KiB
Bash
Executable File
165 lines
4.0 KiB
Bash
Executable File
#!/bin/sh
|
|
# @(#$Id: rcldvi,v 1.7 2008-10-08 16:15:22 dockes Exp $ (C) 2006 J.F.Dockes
|
|
|
|
# This program is free software; you can redistribute it and/or modify
|
|
# it under the terms of the GNU General Public License as published by
|
|
# the Free Software Foundation; either version 2 of the License, or
|
|
# (at your option) any later version.
|
|
#
|
|
# This program is distributed in the hope that it will be useful,
|
|
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
# GNU General Public License for more details.
|
|
#
|
|
# You should have received a copy of the GNU General Public License
|
|
# along with this program; if not, write to the
|
|
# Free Software Foundation, Inc.,
|
|
# 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
|
|
|
|
#
|
|
# Extract text from a dvi file by either executing dvitops and
|
|
# pstotext or using catdvi.
|
|
#
|
|
# pstotext does not work any more with gs 9.22-25, so catdvi is always
|
|
# needed now.
|
|
# Initially dvitops had given better results during tests, and was
|
|
# chosen first if available, but the dvitops/pstotext combination
|
|
# is much slower than catdvi set variables. In any case, the
|
|
# program is not too good with special characters (e.g. ligatures)
|
|
|
|
LANG=C ; export LANG
|
|
LC_ALL=C ; export LC_ALL
|
|
progname="rcldvi"
|
|
filetype=dvi
|
|
|
|
|
|
#RECFILTCOMMONCODE
|
|
##############################################################################
|
|
# !! Leave the previous line unmodified!! Code imported from the
|
|
# recfiltcommon file
|
|
|
|
# Utility code common to all shell filters. This could be sourced at run
|
|
# time, but it's slightly more efficient to include the code in the
|
|
# filters at build time (with a sed script).
|
|
|
|
# Describe error in a way that can be interpreted by our caller
|
|
senderror()
|
|
{
|
|
echo RECFILTERROR $*
|
|
# Also alert on stderr just in case
|
|
echo ":2:$progname::: $*" 1>&2
|
|
exit 1
|
|
}
|
|
|
|
iscmd()
|
|
{
|
|
cmd=$1
|
|
case $cmd in
|
|
*/*)
|
|
if test -x $cmd -a ! -d $cmd ; then return 0; else return 1; fi ;;
|
|
*)
|
|
oldifs=$IFS; IFS=":"; set -- $PATH; IFS=$oldifs
|
|
for d in $*;do test -x $d/$cmd -a ! -d $d/$cmd && return 0;done
|
|
return 1 ;;
|
|
esac
|
|
}
|
|
|
|
checkcmds()
|
|
{
|
|
for cmd in $*;do
|
|
if iscmd $cmd
|
|
then
|
|
a=1
|
|
else
|
|
senderror HELPERNOTFOUND $cmd
|
|
fi
|
|
done
|
|
}
|
|
|
|
# show help message
|
|
if test $# -ne 1 -o "$1" = "--help"
|
|
then
|
|
echo "Convert a $filetype file to HTML text for Recoll indexing."
|
|
echo "Usage: $progname [infile]"
|
|
exit 1
|
|
fi
|
|
|
|
infile="$1"
|
|
|
|
# check the input file existence (may be '-' for stdin)
|
|
if test "X$infile" != X- -a ! -f "$infile"
|
|
then
|
|
senderror INPUTNOSUCHFILE "$infile"
|
|
fi
|
|
|
|
# protect access to our temp files and directories
|
|
umask 77
|
|
|
|
##############################################################################
|
|
# !! Leave the following line unmodified !
|
|
#ENDRECFILTCOMMONCODE
|
|
|
|
decoderdvips()
|
|
{
|
|
dvips -f $1 2> /dev/null | pstotext | iconv -f cp1252 -t utf-8 -c -s
|
|
}
|
|
decodercatdvi()
|
|
{
|
|
catdvi --output-encoding=UTF-8 $1
|
|
}
|
|
decoder=""
|
|
|
|
# pstotext does not work any more
|
|
# iscmd dvips
|
|
# isdvips=$?
|
|
# iscmd pstotext
|
|
# ispstotext=$?
|
|
# if test $isdvips -eq 0 -a $ispstotext -eq 0; then
|
|
# decoder=decoderdvips
|
|
# elif iscmd catdvi ; then
|
|
# decoder=decodercatdvi
|
|
# fi
|
|
|
|
if iscmd catdvi ; then
|
|
decoder=decodercatdvi
|
|
fi
|
|
|
|
if test X$decoder = X ; then
|
|
senderror HELPERNOTFOUND catdvi
|
|
fi
|
|
|
|
# The strange 'BEGIN' setup is to prevent 'file' from thinking this file
|
|
# is an awk program
|
|
$decoder "$infile" |
|
|
awk 'BEGIN'\
|
|
' {
|
|
printf("<html><head><title></title>\n")
|
|
printf("<meta http-equiv=\"Content-Type\" content=\"text/html;charset=UTF-8\">\n")
|
|
printf("</head>\n<body><p>");
|
|
cont = ""
|
|
}
|
|
{
|
|
$0 = cont $0
|
|
cont = ""
|
|
|
|
if ($0 == "\f") {
|
|
print "</p>\n<hr>\n\f<p>"
|
|
next
|
|
} else if ($0 ~ /-$/) {
|
|
match($0, "[ \t][^ \t]+$")
|
|
line = substr($0, 0, RSTART)
|
|
cont = substr($0, RSTART, RLENGTH)
|
|
$0 = line
|
|
gsub("-", "", cont)
|
|
}
|
|
|
|
gsub(/&/, "\\&", $0)
|
|
gsub(/</, "\\<", $0)
|
|
gsub(/>/, "\\>", $0)
|
|
|
|
print $0 "<br>"
|
|
}
|
|
END {
|
|
print "</p></body></html>"
|
|
}'
|