#!/bin/sh
#
# digidir
#
# Creates a standalone HTDIG searchable index of a directory of web or
# text documents that can be put onto CD-ROM or traded with other
# machines. If put on a CD-ROM, the CD-ROM can be mounted directly
# under /home/httpd/html with no further configuration required.
#
# Usage:
#
# $ cd /home/httpd/html
# $ mkdir documents
# $ [fill "documents" dorectory with text or HTML files ]
# $ digdir documents
#
# At this point, the directory "documents" contains the
# original documents themselves, as well as a search.html
# search form, and all "htdig" config and database files
# (hidden under documents/.htdig). This directory can
# be moved to any other machine.
#
# NOTE: as of htdig 3.1.x, the HTDIG database is architecture
# dependant, so the database can only be moved to machines
# of like architecture. This is a design flaw in htdig.
#
# Requirments:
# On the machine which is used to initially generate the index,
# HTDIG 3.1.x must be installed. Get it from http://www.htdig.org/
#
# On the machine which is use to search the database, only
# /home/httpd/html/cgi-bin/htsearch (from HTDIG 3.1.x) must exist.
#
# Author:
# Rick Richardson, rick@digi.com, November 1999.
#
# This software is donated to the PUBLIC DOMAIN and may be used for
# any purpose without restriction. No warrantees expressed or
# implied. Your mileage may vary.
#
error() {
echo "digdir error: $*"
exit 1
}
DIR="$1"
PATH=$PATH:/usr/sbin
[ -d "$DIR" ] || error "directory name missing or non-existant"
case "$DIR" in
/*) error "directory name must be relative to current directory";;
esac
cd $DIR || error "can't chdir to $DIR"
HERE=`pwd`
#
# Remove the old database and copy in a fresh set of HTDIG
# distribution files.
#
rm -f search.html
rm -rf .htdig
mkdir .htdig || error "can't make directory $HERE/.htdig"
(
cd /var/lib/htdig; find common ! -name 'db.*' ! -name '*.db' |
cpio -pudm $HERE/.htdig
)
mkdir .htdig/db || error "can't make directory $HERE/.htdig"
#
# Make a copy of the matching htsearch binary, so that
# somebody who gets a copy of this index and doesn't
# have a matching htsearch binary handy can just grab
# it from here and stash it in cgi-bin. Also copy this
# shell script in case somebody wants to regen the index.
#
cp -a /home/httpd/cgi-bin/htsearch $0 .htdig/ ||
error "can't find htsearch binary"
#
# Create two config files, one for htdig and one for htsearch
#
# Using two config files allows us to eliminate any appearance
# of an absolute URL (one with a domain name, even localhost)
# in the results, thus making the database portable.
#
# We convert the output URL to ../$DIR because the browsers
# idea of the current directory will be cgi-bin.
#
DCONF=$HERE/.htdig/htdig.conf
SCONF=$HERE/.htdig/htsearch.conf
cp /etc/htdig/htdig.conf $DCONF
cp /etc/htdig/htdig.conf $SCONF
cat <<-EOF >> $DCONF
database_dir: $HERE/.htdig/db
common_dir: $HERE/.htdig/common
start_url: http://localhost/$DIR/
local_urls: http://localhost/$DIR/=/home/httpd/html/$DIR/
local_user_urls: http:/=/home/,/public_html/
url_part_aliases: http://localhost/$DIR *$DIR
EOF
cat <<-EOF >> $SCONF
database_dir: $HERE/.htdig/db
common_dir: $HERE/.htdig/common
start_url: http://localhost/$DIR/
local_urls: http://localhost/$DIR/=/home/httpd/html/$DIR/
local_user_urls: http:/=/home/,/public_html/
url_part_aliases: http:../$DIR *$DIR
EOF
#
# Generate the database using HTDIG
#
htdig -v -c $DCONF -i
htmerge -c $DCONF
htnotify -c $DCONF
htfuzzy -c $DCONF endings
htfuzzy -c $DCONF synonyms
#
# Create the initial search page
#
CGI="http:/cgi-bin/htsearch?-c$SCONF"
cat <<-EOF > search.html
ht://Dig WWW Search of $DIR
WWW Site Search
This search will allow you to search the contents of
all documents under this directory.
EOF
#
# Fixup the templates that create the refine page, etc.
#
# Change these from method GET to POST so that the
# -c$SCONF option will work.
#
for i in header nomatch syntax wrapper
do
ex .htdig/common/$i.html <<-EOF
g#.(CGI)#s##$CGI#
g#method=.get.#s##method="post"#
w
q
EOF
done