In my intermittent online presence, I've been happily watching Dave Winer's ramp-up with OPML toward OSCON with things like "How to implement an OPML directory browser". I love outliners, and though it's been a little while since I played with Radio, I loved Instant Outlining and the transclusion of outside outlines into the one at hand via URL. And when Dave first introduced the idea of an OPML-based distributed web directory, I figured it was the start of another nifty twist in the web fabric. (You know, the kind that makes wrinkles? The kind of wrinkles that make brains smarter?)

Anyway, even given all this, OPML has always bugged me, and I'm not alone. In fact, today I found a link to OML, the Outline Markup Language project on ?SourceForge, which seems to seek to address many of the same things that have bugged me. That is, things like UserLand application-specific tags, and extension via arbitrary attributes. Though I'm no master of deep XML magic, these things struck me as grungy.

But you know, we're designing for recombinant growth with the lazyweb here (or at least, Dave Winer was and is), and OPML looks like one of those dirty things that got thrown together quickly in order to enable a laundry list of further projects. It works, isn't all that hard to grasp, and has gotten adopted quickly. There's momentum there. As Dave says, there is no wait for tools.

So, now there's also OML starting. Hopefully this won't become another rehash of the RSS fight.
Because, I sense many similar issues between the two. Maybe it would have been better still if OML had been named something completely avoiding the letters O, P, M, or L. I already see mailing list charters being called out in order to quiet unwanted discussion of fundamentals, but, hopefully we can avoid anyone claiming that they have the One True Format, all fighting for the same name and slapping each other around with version numbers. Gah.

Anyway. I like OML but see some grunge in it as well. At the moment, I'm using an OPML-supporting tool. I can't imagine that conversion would be more than an XSLT file away. Well, maybe more than that. Beyond that, let's agree to disagree and viva le fork. Let the best, most demonstratably capable format win. Meanwhile, I'm still considering that Tinderbox license to see if I might like multi-dimensional outlining...

shortname=opml_vs_oml