Class: Unisec::Decdump

Inherits:
Object
  • Object
show all
Defined in:
lib/unisec/decdump.rb

Overview

Decimal dump (decdump) of all Unicode encodings.

Instance Attribute Summary collapse

Class Method Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(str) ⇒ Decdump

Init the decdump.

Examples:

ded = Unisec::Decdump.new('I 💕 Ruby 💎')
ded.utf8 # => "073 032 240 159 146 149 032 082 117 098 121 032 240 159 146 142"
ded.utf16be # => "|000 073| |000 032| |216 061| |220 149| |000 032| |000 082| |000 117| |000 098| |000 121| |000 032| |216 061| |220 142|"
ded.utf32be # => "|000 000 000 073| |000 000 000 032| |000 001 244 149| |000 000 000 032| |000 000 000 082| |000 000 000 117| |000 000 000 098| |000 000 000 121| |000 000 000 032| |000 001 244 142|"

Parameters:

  • str (String) —

    Input string to encode



36
37
38
39
40
41
42
 
# File 'lib/unisec/decdump.rb', line 36

def initialize(str)
  @utf8 = Decdump.utf8(str)
  @utf16be = Decdump.utf16be(str)
  @utf16le = Decdump.utf16le(str)
  @utf32be = Decdump.utf32be(str)
  @utf32le = Decdump.utf32le(str)
end

Instance Attribute Details

#utf16be ⇒ String (readonly)

UTF-16BE decdump

Returns:

  • (String) —

    UTF-16BE decdump



15
16
17
 
# File 'lib/unisec/decdump.rb', line 15

def utf16be
  @utf16be
end

#utf16le ⇒ String (readonly)

UTF-16LE decdump

Returns:

  • (String) —

    UTF-16LE decdump



19
20
21
 
# File 'lib/unisec/decdump.rb', line 19

def utf16le
  @utf16le
end

#utf32be ⇒ String (readonly)

UTF-32BE decdump

Returns:

  • (String) —

    UTF-32BE decdump



23
24
25
 
# File 'lib/unisec/decdump.rb', line 23

def utf32be
  @utf32be
end

#utf32le ⇒ String (readonly)

UTF-32LE decdump

Returns:

  • (String) —

    UTF-32LE decdump



27
28
29
 
# File 'lib/unisec/decdump.rb', line 27

def utf32le
  @utf32le
end

#utf8 ⇒ String (readonly)

UTF-8 decdump

Returns:



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

def utf8
  @utf8
end

Class Method Details

.utf16be(str) ⇒ String

Encode to UTF-16BE in decdump format (packed by code unit = every 2 bytes)

Examples:

Unisec::Decdump.utf16be('🐋') # => "|216 061| |220 011|"

Parameters:

  • str (String) —

    Input string to encode

Returns:

  • (String) —

    decdump (UTF-16BE encoded)



58
59
60
61
62
63
 
# File 'lib/unisec/decdump.rb', line 58

def self.utf16be(str)
  dec_chuncks = str.encode('UTF-16BE').to_hex.scan(/.{2}/).map do |x|
    x.hex2dec(padding: 3)
  end
  dec_chuncks.join(' ').scan(/\d+ \d+/).map { |x| "|#{x}|" }.join(' ')
end

.utf16le(str) ⇒ String

Encode to UTF-16LE in decdump format (packed by code unit = every 2 bytes)

Examples:

Unisec::Decdump.utf16le('🐋') # => "|061 216| |011 220|"

Parameters:

  • str (String) —

    Input string to encode

Returns:

  • (String) —

    decdump (UTF-16LE encoded)



70
71
72
73
74
75
 
# File 'lib/unisec/decdump.rb', line 70

def self.utf16le(str)
  dec_chuncks = str.encode('UTF-16LE').to_hex.scan(/.{2}/).map do |x|
    x.hex2dec(padding: 3)
  end
  dec_chuncks.join(' ').scan(/\d+ \d+/).map { |x| "|#{x}|" }.join(' ')
end

.utf32be(str) ⇒ String

Encode to UTF-32BE in decdump format (packed by code unit = every 4 bytes)

Examples:

Unisec::Decdump.utf32be('🐋') # => "|000 001 244 011|"

Parameters:

  • str (String) —

    Input string to encode

Returns:

  • (String) —

    decdump (UTF-32BE encoded)



82
83
84
85
86
87
 
# File 'lib/unisec/decdump.rb', line 82

def self.utf32be(str)
  dec_chuncks = str.encode('UTF-32BE').to_hex.scan(/.{2}/).map do |x|
    x.hex2dec(padding: 3)
  end
  dec_chuncks.join(' ').scan(/\d+ \d+ \d+ \d+/).map { |x| "|#{x}|" }.join(' ')
end

.utf32le(str) ⇒ String

Encode to UTF-32LE in decdump format (packed by code unit = every 4 bytes)

Examples:

Unisec::Decdump.utf32le('🐋') # => "|011 244 001 000|"

Parameters:

  • str (String) —

    Input string to encode

Returns:

  • (String) —

    decdump (UTF-32LE encoded)



94
95
96
97
98
99
 
# File 'lib/unisec/decdump.rb', line 94

def self.utf32le(str)
  dec_chuncks = str.encode('UTF-32LE').to_hex.scan(/.{2}/).map do |x|
    x.hex2dec(padding: 3)
  end
  dec_chuncks.join(' ').scan(/\d+ \d+ \d+ \d+/).map { |x| "|#{x}|" }.join(' ')
end

.utf8(str) ⇒ String

Encode to UTF-8 in decdump format (spaced at every code unit = every byte)

Examples:

Unisec::Decdump.utf8('🐋') # => "240 159 144 139"

Parameters:

  • str (String) —

    Input string to encode

Returns:

  • (String) —

    decdump (UTF-8 encoded)



49
50
51
 
# File 'lib/unisec/decdump.rb', line 49

def self.utf8(str)
  str.encode('UTF-8').to_hex.scan(/.{2}/).map { |x| x.hex2dec(padding: 3) }.join(' ')
end

Instance Method Details

#display ⇒ String

Display a CLI-friendly output summurizing the decdump in all Unicode encodings

Examples:

puts Unisec::Decdump.new('K').display # =>
# UTF-8: 226 132 170
# UTF-16BE: |033 042|
# UTF-16LE: |042 033|
# UTF-32BE: |000 000 033 042|
# UTF-32LE: |042 033 000 000|

Returns:

  • (String) —

    CLI-ready output



110
111
112
113
114
115
116
 
# File 'lib/unisec/decdump.rb', line 110

def display
  "UTF-8: #{@utf8}\n" \
  "UTF-16BE: #{@utf16be}\n" \
  "UTF-16LE: #{@utf16le}\n" \
  "UTF-32BE: #{@utf32be}\n" \
  "UTF-32LE: #{@utf32le}".gsub('|', Paint['|', :red])
end