Module: SamplingHash

Defined in:
lib/sampling-hash.rb,
lib/sampling-hash/hash.rb,
lib/sampling-hash/sampler.rb,
lib/sampling-hash/version.rb,
lib/sampling-hash/sampling-io.rb

Defined Under Namespace

Classes: Hash, Sampler, SamplingIO

Constant Summary collapse

VERSION = 
'0.0.2'

Class Method Summary collapse

Class Method Details

.hash(path, seed = File.size(path)) ⇒ Object

Raises:

  • (ArgumentError) 


8
9
10
11
12
13
14
15
16
17
18
19
 
# File 'lib/sampling-hash.rb', line 8

def self.hash(path, seed = File.size(path))
  raise ArgumentError, 'file not found' unless File.file?(path)

  hash = XXhash::Internal::StreamingHash.new(seed)

  sio = SamplingIO.new(File.open(path, 'r'))
  sio.samples do |chunk|
    hash.update(chunk)
  end

  hash.digest
end