Class: String

Inherits:
Object
  • Object
show all
Includes:
RMMSeg
Defined in:
lib/string.rb

Instance Method Summary collapse

Instance Method Details

#hash_vl ⇒ Object 



9
 
# File 'ext/string_hashing/string_hashing.c', line 9

VALUE method_hash_vl(VALUE self, VALUE bitlength);

#hash_vl_rb(length) ⇒ Object 



15
16
17
18
19
20
21
22
23
24
25
26
 
# File 'lib/string.rb', line 15

def hash_vl_rb(length)
  return 0 if self == ""

  x = self.bytes.first << 7
  m = 1000003
  mask = (1<<length) - 1
  self.each_byte{ |char| x = ((x * m) ^ char.to_i) & mask }

  x ^= self.bytes.count
  x = -2 if x == -1
  x
end

#segment ⇒ Object 



28
29
30
31
32
33
34
35
36
37
38
39
 
# File 'lib/string.rb', line 28

def segment
 algor = RMMSeg::Algorithm.new(self)
 result = []
 loop do
   tok = algor.next_token
   word = (Tyccl.get_similar(tok.text.force_encoding('utf-8')).first.first rescue nil)
   word = tok.text if word.nil? && !tok.nil?
   break if word.nil?
   result << word
 end
 result
end

#simhash(options = {}) ⇒ Object 



11
12
13
 
# File 'lib/string.rb', line 11

def simhash(options={})
  Simhash.hash(self.segment, options)
end