Re: Subset display in dir index (was: Auto download...)

Nick Arnett/Multimedia Computing Corp. ([email protected])
Sun, 29 May 1994 10:21:20 -0800


>> Here's an alternative idea -- instead of returning a directory in response
>> to a URL like that, return a list of document <title>s as HREFs! Hmm, I
>> like that one... It would save the server from having to respond to a
>> series of HEAD instructions from a robot, among other things. Adding file
>> sizes might be nice, too.
>
>The Windows NCSA server already supports the ability to have HREFs in the
>titles. It also displays the size and last mod date. BUT... the intent of
>permitting HREFs in the title is to permit annotations, to allow the title
>to link to an expanded description for the file, not to hide the file name.
>I don't see the benefit in hiding the file name in a directory listing.

I explained wrong or you misunderstood. Let me give an example. Let's say
there's a directory with filenames like this:

83499A.htm
18132H.htm
BG602A.htm

Meaningless to most users, right? That's what my generated filenames look
like. I'm suggesting that if the client requests a directory list *.htm,
the default would be to a document back that looks something back like
this:

<title>Directory of myhost.mydomain.com/mydirectory/*.htm</title>

<ul>
<li><a href="http://myhost.mydomain.com/mydirectory/83499A.htm">This is the
title of the first file</a>

<li><a href="http://myhost.mydomain.com/mydirectory/18132H.htm">This is the
title of the second file</a>

<li><a href="http://myhost.mydomain.com/mydirectory/BG602A.htm">This is the
title of the last file</a>

</ul>

I'm suggesting that perhaps something like this should be the *default*
behavior, so that the default deals with information that's intended in all
cases to be meaningful to the user. I have no objections to allowing other
behaviors, including returning the file names.

I don't mean to rule out including other directory-related information in
the HTML that's returned, such as creation and mod dates, etc. Perhaps the
default might include those. Maybe have switches to retrieve any and all
portions of the headers.

One of the great benefits, as I mentioned, could be to speed up robots and
spiders, who typically make a series of "GET HEAD" requests. This would
effectively batch all of those together, at the server, instead of
requiring a long series of transactions.

Nick

Multimedia Computing Corp. (strategic consulting)
Campbell, California
----------------------------------------------------------
"We are surrounded by insurmountable opportunity." -- Pogo