parse.cpp.patch

This is a patch I haven't mentioned yet. It's actually for two
separate problems (sorry, Kir).

The first one is related to "Location:" entries in the header
the server sends. According to RFC2616 it should followed by
an absoluteURI, but one some machines there's just an absolute
path to a different page on the server instead. The first part
of the patch is to deal with this more gracefully.

The second patch is for cases where there are links in a document
that start with a slash, i.e. something like

<a href="/foo/bar/xxx.html">

As far as I can see these are not treated correctly (aspseek does
not seem to follow these links), and that's what the second part
of the patch is for.
                                    Regards, Jens
-- 
 Freie Universitaet Berlin     Jens Thoms Toerring
 Universitaetsbibliothek
 Webteam                       Tel: 0049 30 838 56055
 Garystrasse 39                Fax: 0049 30 838 53738
 14195 Berlin                  e-mail: [email protected]


--- aspseek-orig/src/parse.cpp	2003-08-19 13:50:25.000000000 +0200
+++ aspseek-my/src/parse.cpp	2003-08-26 18:38:21.000000000 +0200
@@ -876,6 +876,14 @@
 				string location_unescaped;
 				char *location_trim = str_trim(location);
 				URIUnescapeSGML(location_trim, location_unescaped, ucontent.m_charset);
+
+				// If the URI isn't RFC2616 conform, i.e. isn't a absoluteURI
+				// but just a path prepend it by the server name in the hope
+				// to make it an absoluteURI...
+
+				if ( *location_unescaped.c_str() == '/' )
+					location_unescaped = m_url + location_unescaped;
+
 				if (!newURL.ParseURL(location_unescaped.c_str()))
 				{
 					int newMethod;
@@ -2187,6 +2195,13 @@
 				string href_unescaped;
 				char *href_trim = str_trim(href);
 				URIUnescapeSGML(href_trim, href_unescaped, ucontent->m_charset);
+
+				// Prepend the reference with the server name etc. if it's an
+				// absolute path, otherwise we get in trouble later
+
+				if ( *href_unescaped.c_str() == '/' )
+					href_unescaped = CurSrv->m_url + href_unescaped;
+
 				if (doc->m_hops >= CurSrv->m_maxhops)
 				{
 				}