gistfile1.txt

require 'rubygems'
require 'avro'

count = ARGV[0] ? ARGV[0].to_i : 10000
puts "writing #{count} records"

SCHEMA = <<-JSON
{ "type": "record",
  "name": "User",
  "fields" : [
    {"name": "username", "type": "string"},
    {"name": "age", "type": "int"},
    {"name": "verified", "type": "boolean", "default": "false"}
  ]}
JSON
 
file = File.open('data.avr', 'wb')
schema = Avro::Schema.parse(SCHEMA)
writer = Avro::IO::DatumWriter.new(schema)
dw = Avro::DataFile::Writer.new(file, writer, schema)

count.times do
  dw << {"username" => "john", "age" => 25, "verified" => true}
end
dw.close

puts "data.avr: #{File.new("data.avr").stat.size}"

file = File.open('data.json', 'w')

count.times do
  file << Yajl::Encoder.encode({"username" => "john", "age" => 25, "verified" => true})
end
file.close

puts "data.json: #{File.new("data.json").stat.size}"