From: Phil G. <jus...@co...> - 2003-12-08 23:36:06
|
On Fri, 5 Dec 2003 11:21:53 -0600, Alex Roitman <sh...@al...> wrote: > On Fri, Dec 05, 2003 at 04:16:03PM +0800, Bret Busby wrote: >> >> A couple of things (questions, not arguments); firstly, could you tell >> me, out of curiosity, the original aim of GRAMPS? I am not sure of that, >> and as you mention the possibility of digressing from the original aim >> of GRAMPS, I am interested. > > Sure. As I said in my previous message, GRAMPS aims to be a personal > genealogy program. This assumes (1) data is personal and is stored at > the person's computer; (2) a person should be able to install the > precompiled program, fire it up, and start his/her research. > > (1) means that distributed system is an unnecessary overhead. (2) means > that a person depends on whoever setting up the central data storage > (I can't see my aunt doing it on her own). > I'm just starting to use GRAMPS so I wasn't going to make any comments. But, in setting it up, I came across something that relates to (1) & (2) above. My wife and I share the same PC with separate accounts. I went through some configuration of the file & directory authorities, creating a group profile, etc so that we can both update the same file. Still having trouble when she wants to add an image to the directory but no trouble updating the file. Eventually I'll figure out the correct folder authority to allow this to happen. Anyway, I think it would be nice to support a multi-user install or single-user install so that multiple users on the same pc could use the product. Or, an FAQ so it would be easy to set up. I think your Dad is right-on, btw. Phil > As to what's between us and our goal, please see TODO file from the CVS > http://cvs.sourceforge.net/viewcvs.py/gramps/gramps2/TODO > and the RFE list at > http://sourceforge.net/tracker/?group_id=25770&atid=385140 > With the fact that most of us also have a little side job during most of > the > daytime, we're not exactly zooming towards the goal, not always anyway > :-) > >> The second thing is this. I tried looking for a diagram of the GEDCOM >> schema or structure, and I can't find one. I think it may ("officially") >> be named the "GEDCOM Data Model Chart". I am looking for something like >> an ER-diagram, that I can use as a starting point, for the file data >> structure. > > The GEDCOM 5.5 standard is documented at > http://www.gendex.com/gedcom55/55gctoc.htm > As for the GEDCOM 6 XML standard, last time I checkd it was still in its > proposal stage. I'm not sure whether it's finished now. > >> Whatever happens, I want to try to create a database system, with a >> scripting front-end; either Perl or PHP, and I need an idea of the >> current (as in version 5.5) GEDCOM data structure, as a starting point. >> >> This I would need for system analysis and design. > > It is our experience that GEDCOM 5.5 has a lot of drawbacks in > describing some real-world situations (like multiple parents of a person > -- real and adoptive parents, and stuff like that). The GRAMPS data > structure tried to address these shortcomings, so you may be better off > looking at out data structure. > > You are welcome to look at the src/RelLib.py file which has the core > classes for most of GRAMPS' data. If you want to, you can > automatically produce the whole set of documents based on all the python > code of GRAMPS with any standard doc generation tools for python > (happydoc worked for me). Let me know if you'd like me to do it for you. > > Alternatively, take a look at the XML file for > example/gramps/data.gramps (after gunzip-ing it), it should be very > self-explanatory. > >> If you have access to, or, a pointer to, a diagrams such as I seek, >> could you please advise? > > Not sure about diagrams, but the above reference completely describes > GEDCOM. You can draw diagrams based on that. They're going to be very > tangled I suspect, just like our lives are a mess :-) > > Good luck, > Alex > Phil -- Using Mandrake Linux 9.2 http://www.mandrakesoft.com |