You are viewing a plain text version of this content. The canonical link for it is here.
Posted to docs-cvs@perl.apache.org by st...@apache.org on 2002/01/31 02:51:50 UTC
cvs commit: modperl-docs/src/search spider.pl swish.conf
stas 02/01/30 17:51:50
Modified: tmpl/custom/html page_body
src/search spider.pl swish.conf
Log:
- allow spidering based on sections!!!
Submitted by: Bill Moseley <mo...@hank.org>
Reviewed by: stas
Revision Changes Path
1.12 +2 -0 modperl-docs/tmpl/custom/html/page_body
Index: page_body
===================================================================
RCS file: /home/cvs/modperl-docs/tmpl/custom/html/page_body,v
retrieving revision 1.11
retrieving revision 1.12
diff -u -r1.11 -r1.12
--- page_body 30 Jan 2002 05:14:46 -0000 1.11
+++ page_body 31 Jan 2002 01:51:50 -0000 1.12
@@ -18,6 +18,7 @@
# render the content
"<!-- SwishCommand index -->";
FOREACH sec = doc.body;
+ '<div class="index_section">';
sec;
"<br><br>";
IF loop.count == loop.size;
@@ -28,6 +29,7 @@
INCLUDE top_link;
END;
"<br><br>";
+ "</div>";
END;
"<!-- SwishCommand noindex -->";
%]
1.2 +3 -3 modperl-docs/src/search/spider.pl
Index: spider.pl
===================================================================
RCS file: /home/cvs/modperl-docs/src/search/spider.pl,v
retrieving revision 1.1
retrieving revision 1.2
diff -u -r1.1 -r1.2
--- spider.pl 30 Jan 2002 06:35:00 -0000 1.1
+++ spider.pl 31 Jan 2002 01:51:50 -0000 1.2
@@ -2,7 +2,7 @@
use strict;
-# $Id: spider.pl,v 1.1 2002/01/30 06:35:00 stas Exp $
+# $Id: spider.pl,v 1.2 2002/01/31 01:51:50 stas Exp $
#
# "prog" document source for spidering web servers
#
@@ -23,7 +23,7 @@
use HTML::Tagset;
use vars '$VERSION';
-$VERSION = sprintf '%d.%02d', q$Revision: 1.1 $ =~ /: (\d+)\.(\d+)/;
+$VERSION = sprintf '%d.%02d', q$Revision: 1.2 $ =~ /: (\d+)\.(\d+)/;
use vars '$bit';
use constant DEBUG_ERRORS => $bit = 1; # program errors
@@ -410,7 +410,7 @@
print STDERR "-Skipped indexing $uri some callback set 'no_index' flag\n" if $server->{debug}&DEBUG_SKIPPED;
} else {
- return unless check_user_function( 'filter_content', $uri, $server, $response, \$content );
+ return $links_extracted unless check_user_function( 'filter_content', $uri, $server, $response, \$content );
output_content( $server, \$content, $uri, $response )
unless $server->{no_index};
1.2 +0 -2 modperl-docs/src/search/swish.conf
Index: swish.conf
===================================================================
RCS file: /home/cvs/modperl-docs/src/search/swish.conf,v
retrieving revision 1.1
retrieving revision 1.2
diff -u -r1.1 -r1.2
--- swish.conf 30 Jan 2002 06:35:00 -0000 1.1
+++ swish.conf 31 Jan 2002 01:51:50 -0000 1.2
@@ -1,5 +1,3 @@
-SwishProgParameters default http://perl.apache.org/~stas/modperl-site/
-#SwishProgParameters default http://localhost/modperl-site/
IndexDir ./spider.pl
DefaultContents HTML2
StoreDescription HTML2 <body> 100000
---------------------------------------------------------------------
To unsubscribe, e-mail: docs-cvs-unsubscribe@perl.apache.org
For additional commands, e-mail: docs-cvs-help@perl.apache.org