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 = 
'0.1.2'

Class Method Summary collapse

Class Method Details

.hash(path, seed = File.size(path), hash = XXhash::XXhashInternal::StreamingHash64.new(seed)) ⇒ Object

We default to 64 bit xxhash.

Raises:

  • (ArgumentError) 


9
10
11
12
13
14
15
16
17
18
19
20
21
22
 
# File 'lib/sampling-hash.rb', line 9

def self.hash(path, seed = File.size(path), hash = XXhash::XXhashInternal::StreamingHash64.new(seed))
  raise ArgumentError, 'file not found' unless File.file?(path)

  File.open(path, 'r') do |fd|

    sio = SamplingIO.new(fd)
    sio.samples do |chunk|
      hash.update(chunk)
    end

    hash.digest

  end
end

.hash32(path, seed = File.size(path)) ⇒ Object 



24
25
26
 
# File 'lib/sampling-hash.rb', line 24

def self.hash32(path, seed = File.size(path))
  hash path, seed, XXHash::XXhashInternal::StreamingHash32.new(seed)
end

.hash64(path, seed = File.size(path)) ⇒ Object 



28
29
30
 
# File 'lib/sampling-hash.rb', line 28

def self.hash64(path, seed = File.size(path))
  hash path, seed, XXHash::XXhashInternal::StreamingHash64.new(seed)
end