Month: June 2007

Latex should die (or evolve a lot)

Lately I happened to not tolerate anymore the ugly dirac spec, the pdf produced is w/out a index, the font are horrible and the reason is that they made use of latex instead of something saner (docbook anyone?)

This rant isn’t about the dirac spec anyway, the content isn’t bad at all, is just the presentation.

This rant isn’t even about their usage of latex, it is pretty much correct and produces documentation even if you have an ancient tex distribution (tetex).

Now my angry words are at latex in itself since it is the root of the problem.

Latex pros:
– large library of modules, styles stuff
– large userbase
– very nice programs that makes use it less annoying (kile)

Latex cons:
– Doesn’t support truetype fonts out of box, nor lots of image formats.
– It’s default fonts are anything but beauty on screen
– the syntax is between bad and ugly
– you end up with overcomplicated systems to keep your documents in shape
– you spend more time figuring out what to use instead of using it (and the time isn’t short)
– the document build system isn’t exactly an example of clarity.

Seems that many of those issue got addressed on texlive, that sadly we don’t have in portage since few people would touch tex since it is an ugly monster.

All in all you may think that latex is good enough since there aren’t saner alternatives if you want produce a book that doesn’t look a wordprocessor printout… Well, there are nicer alternatives IMHO, one being xml markups since you can convert them with ease (almost), you may produce them using maybe quicker markups (e.g. texy), you can mix and match them (including mathml and svg in docbook isn’t difficult. Sadly there aren’t good authoring tools like kile. Would be simpler make a good authoring tool (yea, I know emacs is wonderful for xml editing) or make latex less ugly from an user and developer POV?

Alive, hopefully

You may wonder what I’m doing since has been a long time since the latest blog item, well I was busy trying to do too many thing, searching, traveling and so on.

Here a summary:

– I eventually released feng as you can see on http://live.polito.it
That involved getting the website up, writing lots of documentation (that hopefully someone will read), hacking the code to be in the right shape and making the whole bundle bearable for people with less understanding of autotools and dependencies… I hope the first release isn’t that ugly and I thank dario and alessandro for their help =)

– The ffmpeg bug tracker is taking shape eventually, hacking roundup isn’t the simplest thing in the world
mostly because examples and alternate templates aren’t available; the documentation saves the day most of the times anyway. you may see it on https://roundup.mplayerhq.hu/roundup/ffmpeg/

– On the cell side I started hacking a bit the build system in order to have it working for me (using gentoo, standard paths and stock gcc toolchain) and for the ones that are using the IBM sdk/fedora (bogus paths, shortened prefixes) I hope the people in charge of deciding what would be the standard for writing and running spu code would provide a sane default. Hopefully one I’ll have more time I’ll start writing something on my own, so far I’m just testing pathes and contributions by others ^^;

– the vorbis and theora rfc are proceedings and currently feng and gst are interoperable, I hope to complete the standardization and move to something else, it’s taking too much!

– my altivec work on cairo is still on hold, I hope to get enough time to push an update (since the ibm/sony mathlib has an implementation of vector integer division I could rip it and add some more vector ops in pixman).

– the SoC with ffmpeg has already started, so far I’m receiving some good feedbacks from my student and I’m trying to find the time to reread the dirac spec in order to follow him better.

That’s more or less all, the keyword of the whole document is TIME, lately the lscube involvement took a bit too much mostly because you cannot manage the time well if you have your plans spoiled every by unexpected priorities appearing out of the blue.