home
***
CD-ROM
|
disk
|
FTP
|
other
***
search
/
SunSoft Catalyst CDWARE 1996 May to August
/
Catalyst CDWARE 1996 May to August.iso
/
.products
/
.bin
/
httpd
/
Solaris_2
/
newwais.pl
< prev
next >
Wrap
Perl Script
|
1996-03-19
|
5KB
|
191 lines
#!./perl
#
# newwais.pl -- WAIS search interface
#
# from wais.pl
#
# Tony Sanders <sanders@bsdi.com>, Nov 1993
#
# Example configuration (in local.conf):
# map topdir wais.pl &do_wais($top, $path, $query, "database", "title")
#
# this script uses a sneaky feature of Mosaic that interpretes a
# single text input form with the name 'isindex' (case sensitive) to
# the same as a <ISINDEX>. On non-mosaic clients, you wind up with an
# additional query
#
# Note that I know even less about perl than the other two people
# who hacked this, so feel free to send hate mail to pjh@netcom.com
# if I did something really bad (or if there is a better way of
# grabbing the filename off the end of a path.
#
# parse disc name from ServerName Environt Variable with this script
do './variables.pl';
$oldLIB = $ENV{"LD_LIBRARY_PATH"};
$ENV{"LD_LIBRARY_PATH"} = "$oldLIB:/usr/ucblib";
#require 'ctime.pl';
&get_request;
$waisq = "./waisq";
$waisd = "/tmp/.wais/wais";
$src = "catalyst_catalog";
$title = "Example Data";
#
# file type map based on file extension, since all file types
# come back type URL
#
%filetype = (
'html', 'HTML File',
);
#
# code
#
sub send_index {
print "Content-type: text/html\n\n";
print "<HEAD>\n<TITLE>Index of ", $title, "</TITLE>\n</HEAD>\n";
print "<BODY bgcolor=\"#DDDDDD\">\n<H1>", $title, "</H1>\n";
print "This is an index of the information on this server. Please\n";
print "type a query in the search dialog.\n<P>";
print "You may use compound searches, such as: <CODE>environment AND cgi</CODE>\n";
print "<ISINDEX>";
}
sub get_request {
if ($ENV{'REQUEST_METHOD'} eq "POST") {
read(STDIN, $request, $ENV{'CONTENT_LENGTH'});
} elsif ($ENV{'REQUEST_METHOD'} eq "GET" ) {
$request = $ENV{'QUERY_STRING'};
}
@names = &url_decode(split(/[&=]/, $request));
%rqpairs = @names;
}
sub url_decode {
# Decode a URL encoded string or array of strings
# + -> space
# %xx -> character xx
foreach (@_) {
tr/+/ /;
s/%(..)/pack("c",hex($1))/ge;
}
@_;
}
sub do_wais {
# local($top, $path, $query, $src, $title) = @_;
# strip the escape off of *'s
for (@ARGV){s/\\//g};
local(@query) = $rqpairs{"isindex"};;
local($pquery) = join(" ", @query);
local($nquery) = $pquery;
$nquery =~ tr/[A-Z]/[a-z]/;
if (!(($nquery =~ / and /) || ($nquery =~ / or /)))
{
$nquery =~ s/ //g;
}
#
# grab a wais source if there is one
#
local($test) = $ENV{'PATH_INFO'};
if ($test)
{
$test =~ s/\///;
$src = "catalyst_catalog";
$title = $test;
}
close STDERR;
open(STDERR, ">/dev/null");
print "Content-type: text/html\n\n";
$ENV{'HOME'} = "/";
open(WAISQ, "-|") || exec ($waisq, "-c", $waisd, "-m", 100,
"-f", "-", "-S", "$src.src", "-g", $nquery);
print "<HEAD>\n<TITLE>Search of ", "Catalyst Catalog $disc_rest", "</TITLE>\n</HEAD>\n";
print "<img src=\"/.wais/images/goto_home.gif\">\n";
print "<BODY bgcolor=\"#DDDDDD\">\n<H1>Catalyst Catalog on $disc_name $disc_rest</H1>\n";
print "<HR><FORM method=\"POST\" action=\"/cgi-bin/newwais.pl/$src\">\n";
print "Enter keyword(s):\n";
# print "<input name=\"isindex\" value=\"@query\" size=30></FORM><HR>\n";
print "<input name=\"isindex\" value=\"$pquery\" size=30></FORM><HR>\n";
print "$title contains the following\n";
print "items relevant to <B>\`$pquery\':</B><P>\n";
print "<center>";
print "<table border=5>";
print "<DL>\n";
print "<th> Document Matched</th>";
print "<tr>\n";
local($hits, $score, $headline, $lines, $bytes, $type, $date);
print "<OL>";
while (<WAISQ>) {
/:score\s+(\d+)/ && ($score = $1);
/:number-of-lines\s+(\d+)/ && ($lines = $1);
/:number-of-bytes\s+(\d+)/ && ($bytes = $1);
/:type "(.*)"/ && ($type = $1);
/:headline "(.*)"/ && ($headline = $1); # XXX
/:date "(\d+)"/ && ($date = $1, $hits++, &docdone);
}
print "</table>";
print "</center>";
print "</OL>";
close(WAISQ);
print "</DL>\n";
if ($hits == 0) {
print "Nothing found.\n";
}
print "</BODY>\n";
}
sub docdone {
if ($headline =~ /Search produced no result/) {
print "<HR>";
print "<h1>Search produced no result.</h1>";
} else {
$docname = $headline;
$docname =~ s/\.([^.]*)$//;
$extension= $1;
$docname =~ s/\/([^\/]*)$//;
$docname = $1;
print "<td><LI><A HREF=\"$headline\"><B>$docname</B></A></td>\n";
print "<tr>";
}
$score = $headline = $lines = $bytes = $type = $date = '';
}
eval '&do_wais';