Class: PDF::Reader::Encoding

Inherits:
Object
  • Object
show all
Defined in:
lib/pdf/reader/encoding.rb

Overview

Util class for working with string encodings in PDF files. Mostly used to convert strings of various PDF-dialect encodings into UTF-8.

Constant Summary collapse

CONTROL_CHARS =

:nodoc:

[0,1,2,3,4,5,6,7,8,11,12,14,15,16,17,18,19,20,21,22,23,
24,25,26,27,28,29,30,31]
UNKNOWN_CHAR =

0x25AF

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(enc) ⇒ Encoding

Returns a new instance of Encoding.



39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
# File 'lib/pdf/reader/encoding.rb', line 39

def initialize(enc)
  @mapping  = {} # maps from character codes to Unicode codepoints
  # also maps control and invalid chars to UNKNOWN_CHAR
  @string_cache  = {} # maps from character codes to UTF-8 strings.

  if enc.kind_of?(Hash)
    self.differences = enc[:Differences] if enc[:Differences]
    enc = enc[:Encoding] || enc[:BaseEncoding]
  elsif enc != nil
    enc = enc.to_sym
  else
    enc = nil
  end

  @enc_name = enc
  @unpack   = get_unpack(enc)
  @map_file = get_mapping_file(enc)

  load_mapping(@map_file) if @map_file
  add_control_chars_to_mapping
end

Instance Attribute Details

#unpackObject (readonly)

Returns the value of attribute unpack.



37
38
39
# File 'lib/pdf/reader/encoding.rb', line 37

def unpack
  @unpack
end

Instance Method Details

#differencesObject



87
88
89
90
# File 'lib/pdf/reader/encoding.rb', line 87

def differences
  # this method is only used by the spec tests
  @differences ||= {}
end

#differences=(diff) ⇒ Object

set the differences table for this encoding. should be an array in the following format:

[25, :A, 26, :B]

The array alternates between a decimal byte number and a glyph name to map to that byte

To save space the following array is also valid and equivalent to the previous one

[25, :A, :B]

Raises:

  • (ArgumentError)


70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
# File 'lib/pdf/reader/encoding.rb', line 70

def differences=(diff)
  raise ArgumentError, "diff must be an array" unless diff.kind_of?(Array)

  @differences = {}
  byte = 0
  diff.each do |val|
    if val.kind_of?(Numeric)
      byte = val.to_i
    else
      @differences[byte] = val
      @mapping[byte] = names_to_unicode[val]
      byte += 1
    end
  end
  @differences
end

#int_to_name(glyph_code) ⇒ Object

convert an integer glyph code into an Adobe glyph name.

int_to_name(65)
=> :A

Standard character encodings are defined at the bottom of this file



122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
# File 'lib/pdf/reader/encoding.rb', line 122

def int_to_name(glyph_code)
  if @enc_name == :"Identity-H" || @enc_name == :"Identity-V"
    nil
  elsif @enc_name == :MacRomanEncoding
    MAC_ROMAN_ENCODING_TO_NAME[glyph_code]
  elsif @enc_name == :WinAnsiEncoding
    WIN_ANSI_ENCODING_TO_NAME[glyph_code]
  elsif @differences
    @differences[glyph_code]
  elsif @enc_name == :StandardEncoding
    STANDARD_ENCODING_TO_NAME[glyph_code]
  else
    raise "#{@enc_name} does not have an int_to_name mapping"
  end
end

#int_to_utf8_string(glyph_code) ⇒ Object



111
112
113
# File 'lib/pdf/reader/encoding.rb', line 111

def int_to_utf8_string(glyph_code)
  @string_cache[glyph_code] ||= internal_int_to_utf8_string(glyph_code)
end

#to_utf8(str) ⇒ Object

convert the specified string to utf8

  • unpack raw bytes into codepoints

  • replace any that have entries in the differences table with a glyph name

  • convert codepoints from source encoding to Unicode codepoints

  • convert any glyph names to Unicode codepoints

  • replace characters that didn’t convert to Unicode nicely with something valid

  • pack the final array of Unicode codepoints into a utf-8 string

  • mark the string as utf-8 if we’re running on a M17N aware VM



103
104
105
106
107
108
109
# File 'lib/pdf/reader/encoding.rb', line 103

def to_utf8(str)
  if utf8_conversion_impossible?
    little_boxes(str.unpack(unpack).size)
  else
    convert_to_utf8(str)
  end
end