Module: ContactSport::Encoding

Defined in:
lib/contact_sport/encoding.rb

Constant Summary collapse

BYTE_ORDER_MARKS =

github.com/Manfred/Ensure-encoding/blob/master/lib/ensure/encoding.rb github.com/oleander/rchardet/blob/master/lib/rchardet/universaldetector.rb

{
  ::Encoding::UTF_32BE => [0x00, 0x00, 0xfe, 0xff],
  ::Encoding::UTF_32LE => [0xff, 0xfe, 0x00, 0x00],
  ::Encoding::UTF_8    => [0xef, 0xbb, 0xbf],
  ::Encoding::UTF_16BE => [0xfe, 0xff],
  ::Encoding::UTF_16LE => [0xff, 0xfe],
}
FALLBACK_ENCODING = 
::Encoding::ISO_8859_1

Class Method Summary collapse

Class Method Details

.guess_encoding(file) ⇒ Object

Guesses the encoding of the given file.



17
18
19
20
21
22
 
# File 'lib/contact_sport/encoding.rb', line 17

def self.guess_encoding(file)
  # First look for a byte order mark (BOM).
  first_bytes = IO.read(file, 4).bytes.to_a
  bom = BYTE_ORDER_MARKS.detect { |encoding, bytes| first_bytes[0...bytes.length] == bytes }
  bom ? bom.first : FALLBACK_ENCODING
end