The world now has ghetto Hive!  Just what CouchDB needed..

Enter an idea: what if I could marry the ease of SQL to the flexibility of CouchDB? Actually, it was more like: what's the most amusing thing I could build after a day like today?

I'm a big fan of perl: there's nothing perl can't do, and with a wonderful repository like CPAN throwing together a script that would make the devil himself shiver becomes an easy task. Sure, perl can be so messy and complex that it can't even be parsed, but like any language, under the right circumstances it can really shine.

An hour later, I had the beginnings of a masterpiece, a bridge between the worlds of SQL and NoSQL. It was the worst abuse of technology that I could think of: a SQL front-end to CouchDB.

via NoSQL meet SQL.

But seriously, its a neat script.

Tags: CouchDB,Database,Hive,NoSQL,Perl,SQL
Categories: Technology
No Comments »

Ok, so there are a ton of write-ups about CouchDB.  This is my take on it, and this will probably follow my rambling blog post style..

What I Like (in no particular order):

• Made of the web
• Fast
• Scalable
• Fun
• Widely supported
• Versioning
• No Schema

What I Don’t Like:

• Lack of enterprise usage (at least reported usage)

So CouchDB is made of the web.  Not made for the web, but made of it.  The only interface (thats actually used at least, there is support for erlang messaging not using REST) is a REST interface returning JSON formatted data.  CouchDB stores all data in a JSON format, and is completely schemaless.  Everything is stored as a unique document.  Documents can have many versions, which is great for replication, even with multiple master updates, the newest revision wins (and there is support for using logic to merge in a case of multiple “new” versions).

Show me more… »

Tags: CouchDB,Scalability,Web
Categories: Technology
No Comments »

So Dunxu came through, he had a project idea.  Its a pretty awesome idea too!  Not that I’ll share it with you yet, but you will see it eventually.  Now instead of going out at night, I’ll just be hacking away at my desk.  It will definitely save me money, I guess I’ll still show up at the analyst happy hours.  (And pretty much whenever my friends go out…)

Technologies I’m planning on using in one place or another:

ruby on rails – web frontend, so far its pretty easy to hack in…

erlang – powering some more compute intensive operations using mapreduce potentially spawned over a compute grid, but only if the site takes off.

python – because why not, its fast enough and plays well with others, its my project and I’ll hack it together however I want!

Amazon AWS – eventually…

memcached – used pretty much everywhere, databases are too slow for popular lookups…

Some database system, but I’m not sure which yet, but it will be behind the cache.  I’m thinking maybe ErlyDB or CouchDB.  As I said earlier, its my project and I’ll hack it together however I want.

Show me more… »

Tags: Amazon AWS,CouchDB,erlang,ErlyDB,Facebook Auth,JSON,MapReduce,Memcached,OpenID,python,Ruby,Ruby on Rails,SOA,SOAP
Categories: Technology
No Comments »