cassandra-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Ted Zlatanov <...@lifelogs.com>
Subject Re: Row with many columns
Date Fri, 19 Feb 2010 17:59:48 GMT
On Fri, 19 Feb 2010 11:46:25 +0100 Wojciech Kaczmarek <kaczmarek.w@gmail.com> wrote:


WK> You can use get_range_slice with the start_key and finish_key crafted like
WK> this:
WK> assume id is "<10-digits-worldId:whatever_objectId>"
WK> to get objects from world with id=42 you do:
WK> start_key='0000000042:', end_key='0000000042~'
WK> (for the ending mark of end_key choose any character which is greater than
WK> your delimiter ':' in a sort order)
WK> Just remember the keys ordering is defined by the specific Partitioner class
WK> used)

It's still not clear what's in each object supercolumn in your current
schema.  How do you encode a relationship between two objects?  How do
you encode an object's properties?  That's the heart of your design.

For the row keys I agree with Wojciech, you need to let Cassandra handle
objects as rows to get good results.

Ted


Mime
View raw message