Parent:
[87216c]
(diff)
Child:
[4f0c17]
(diff)
Download this file
rcldjvu
130 lines (116 with data), 3.1 kB
#!/bin/sh
# @(#$Id: rcldjvu,v 1.2 2006-04-04 16:03:28 dockes Exp $ (C) 2005 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.,
# 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
#================================================================
# rcldjvu
# Extract text from a djvu file by executing djvused and djvutxt
#
# We use djvused to extract a possible title, djvutxt for the text
#
# Of course this only means anything if the djvu document actually has
# a text layer !
#
#================================================================
LANG=C ; export LANG
LC_ALL=C ; export LC_ALL
progname="rcldjvu"
# show help message
if test $# -ne 1 -o "$1" = "--help"
then
printf 'Convert a djvu file to HTML text for recoll indexation.\n'
printf 'Usage: %s [infile]\n' "$progname"
exit 1
fi
infile="$1"
iscmd()
{
cmd=$1
case $cmd in
*/*)
if test -x $cmd ; then return 0; else return 1; fi ;;
*)
oldifs=$IFS; IFS=":"; set -- $PATH; IFS=$oldifs
for d in $*;do test -x $d/$cmd && return 0;done
return 1 ;;
esac
}
checkcmds()
{
for cmd in $*;do
if iscmd $cmd
then
a=1
else
echo $cmd not found 1>&2
exit 1
fi
done
}
checkcmds djvutxt djvused awk
# check the input file existence
if test ! -f "$infile"
then
printf '%s: %s: no such file\n' "$progname" "$infile"
exit 1
fi
# Title: we try to extract it from the annotations. djvused outputs string
# in C/awk \-escaped notation. Awk can only process this in string
# constants, so we have a first awk pass to create an awk program to parse
# the string as a constant (...). This is not exactly robust or nice
title=`djvused "$infile" -e 'select 1;output-ant' | \
grep ' (title ' | sed -e 's/^.* (title //' -e 's/)$//' |\
awk '
{
printf("BEGIN {s = %s; print s}\n", $0)
}' | awk -f -`
cat <<EOF
<html>
<head>
<title>$title</title>
<meta http-equiv="Content-Type" content="text/html;charset=UTF-8">
</head>
<body>
<pre>
EOF
djvutxt "$infile" | sed -e 's/[ ][ ]*$//' | \
awk '
BEGIN {
cont = ""
}
{
$0 = cont $0
cont = ""
if ($0 == "\f") {
print "</p>\n<hr>\n<p>"
next
} else if ($0 ~ /[-]$/) {
# Break at last whitespace
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
}'
cat <<EOF
</pre>
</body>
</html>
EOF