Module: Coder::Cleaner::Simple::Encodings::UTF_8

Extended by:
UTF_8
Included in:
UTF_8
Defined in:
lib/coder/cleaner/simple/encodings.rb

Overview

Note: This currently does not remove most overlong forms

Instance Method Summary collapse

Instance Method Details

#garbage?(input, buffered) ⇒ Boolean

Returns:

  • (Boolean) 


9
10
11
12
13
14
15
16
 
# File 'lib/coder/cleaner/simple/encodings.rb', line 9

def garbage?(input, buffered)
  return true if input > 244 or input == 192 or input == 193
  case buffered <=> [244, 143, 191]
  when -1 then false
  when  0 then input < 192
  when  1 then true
  end
end

#multibyte?(input, buffered) ⇒ Boolean

Returns:

  • (Boolean) 


22
23
24
 
# File 'lib/coder/cleaner/simple/encodings.rb', line 22

def multibyte?(input, buffered)
  input.between? 128, 244
end

#multibyte_body?(input, buffered) ⇒ Boolean

Returns:

  • (Boolean) 


30
31
32
 
# File 'lib/coder/cleaner/simple/encodings.rb', line 30

def multibyte_body?(input, buffered)
  input.between? 128, 191
end

#multibyte_size(input, buffered) ⇒ Object 



34
35
36
37
38
39
40
41
42
43
 
# File 'lib/coder/cleaner/simple/encodings.rb', line 34

def multibyte_size(input, buffered)
  case input
  when 192..223 then 2
  when 224..239 then 3
  when 240..247 then 4
  when 248..244 then 5
  when 001..127 then 1
  else 0
  end
end

#multibyte_start?(input, buffered) ⇒ Boolean

Returns:

  • (Boolean) 


26
27
28
 
# File 'lib/coder/cleaner/simple/encodings.rb', line 26

def multibyte_start?(input, buffered)
  input.between? 192, 244
end

#single_byte?(input, buffered) ⇒ Boolean

Returns:

  • (Boolean) 


18
19
20
 
# File 'lib/coder/cleaner/simple/encodings.rb', line 18

def single_byte?(input, buffered)
  input.between? 1, 127
end