Class: PDF::Reader::Encoding::WinAnsiEncoding

Inherits:
PDF::Reader::Encoding show all
Defined in:
lib/pdf/reader/encoding.rb

Constant Summary

Constants inherited from PDF::Reader::Encoding

UNKNOWN_CHAR

Instance Attribute Summary

Attributes inherited from PDF::Reader::Encoding

#differences

Instance Method Summary collapse

Methods inherited from PDF::Reader::Encoding

factory

Instance Method Details

#to_utf8(str, tounicode = nil) ⇒ Object

convert a WinAnsiEncoding string into UTF-8



776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
 
# File 'lib/pdf/reader/encoding.rb', line 776

def to_utf8(str, tounicode = nil)
  # content of this method borrowed from REXML::Encoding.decode_cp1252
  # for further reading:
  # http://www.intertwingly.net/stories/2004/04/14/i18n.html
  array_latin9 = str.unpack('C*')
  array_latin9 = self.process_differences(array_latin9)
  array_enc = []
  array_latin9.each do |num|
    if tounicode && (code = tounicode.decode(num))
      array_enc << code
    elsif tounicode
      array_enc << PDF::Reader::Encoding::UNKNOWN_CHAR
    else
      case num
        # characters that added compared to iso-8859-1
      when 0x80; array_enc << 0x20AC # 0xe2 0x82 0xac
      when 0x82; array_enc << 0x201A # 0xe2 0x82 0x9a
      when 0x83; array_enc << 0x0192 # 0xc6 0x92
      when 0x84; array_enc << 0x201E # 0xe2 0x82 0x9e
      when 0x85; array_enc << 0x2026 # 0xe2 0x80 0xa6
      when 0x86; array_enc << 0x2020 # 0xe2 0x80 0xa0
      when 0x87; array_enc << 0x2021 # 0xe2 0x80 0xa1
      when 0x88; array_enc << 0x02C6 # 0xcb 0x86
      when 0x89; array_enc << 0x2030 # 0xe2 0x80 0xb0
      when 0x8A; array_enc << 0x0160 # 0xc5 0xa0
      when 0x8B; array_enc << 0x2039 # 0xe2 0x80 0xb9
      when 0x8C; array_enc << 0x0152 # 0xc5 0x92
      when 0x8E; array_enc << 0x017D # 0xc5 0xbd
      when 0x91; array_enc << 0x2018 # 0xe2 0x80 0x98
      when 0x92; array_enc << 0x2019 # 0xe2 0x80 0x99
      when 0x93; array_enc << 0x201C
      when 0x94; array_enc << 0x201D
      when 0x95; array_enc << 0x2022
      when 0x96; array_enc << 0x2013
      when 0x97; array_enc << 0x2014
      when 0x98; array_enc << 0x02DC
      when 0x99; array_enc << 0x2122
      when 0x9A; array_enc << 0x0161
      when 0x9B; array_enc << 0x203A
      when 0x9C; array_enc << 0x0152 # 0xc5 0x93
      when 0x9E; array_enc << 0x017E # 0xc5 0xbe
      when 0x9F; array_enc << 0x0178
      else
        array_enc << num
      end
    end
  end

  # convert any glyph names to unicode codepoints
  array_enc = self.process_glyphnames(array_enc)

  # replace charcters that didn't convert to unicode nicely with something valid
  array_enc.collect! { |c| c ? c : PDF::Reader::Encoding::UNKNOWN_CHAR }

  # pack all our Unicode codepoints into a UTF-8 string
  ret = array_enc.pack("U*")

  # set the strings encoding correctly under ruby 1.9+
  ret.force_encoding("UTF-8") if ret.respond_to?(:force_encoding)

  return ret
end