Module: Mail::Encodings

Extended by:
Utilities
Includes:
Constants
Defined in:
lib/mail/encodings.rb,
lib/mail/encodings/7bit.rb,
lib/mail/encodings/8bit.rb,
lib/mail/encodings/base64.rb,
lib/mail/encodings/binary.rb,
lib/mail/encodings/identity.rb,
lib/mail/encodings/unix_to_unix.rb,
lib/mail/encodings/quoted_printable.rb,
lib/mail/encodings/transfer_encoding.rb

Defined Under Namespace

Classes: Base64, Binary, EightBit, Identity, QuotedPrintable, SevenBit, TransferEncoding, UnixToUnix

Constant Summary

Constants included from Utilities

Utilities::TO_CRLF_REGEX

Constants included from Constants

Constants::ASTERISK, Constants::ATOM_UNSAFE, Constants::B_VALUES, Constants::CAPITAL_M, Constants::COLON, Constants::CONTROL_CHAR, Constants::CR, Constants::CRLF, Constants::CR_ENCODED, Constants::EMPTY, Constants::ENCODED_VALUE, Constants::EQUAL_LF, Constants::FIELD_BODY, Constants::FIELD_LINE, Constants::FIELD_NAME, Constants::FIELD_PREFIX, Constants::FIELD_SPLIT, Constants::FULL_ENCODED_VALUE, Constants::FWS, Constants::HEADER_LINE, Constants::HEADER_SPLIT, Constants::HYPHEN, Constants::LAX_CRLF, Constants::LF, Constants::LF_ENCODED, Constants::NULL_SENDER, Constants::PHRASE_UNSAFE, Constants::QP_SAFE, Constants::QP_UNSAFE, Constants::Q_VALUES, Constants::SPACE, Constants::TEXT, Constants::TOKEN_UNSAFE, Constants::UNDERSCORE, Constants::UNFOLD_WS, Constants::WSP

Class Method Summary collapse

Methods included from Utilities

atom_safe?, binary_unsafe_to_crlf, binary_unsafe_to_lf, blank?, bracket, capitalize_field, constantize, dasherize, dquote, escape_paren, generate_message_id, map_lines, map_with_index, match_to_s, paren, quote_atom, quote_phrase, quote_token, safe_for_line_ending_conversion?, to_crlf, to_lf, token_safe?, unbracket, underscoreize, unescape, unparen, unquote, uri_escape, uri_parser, uri_unescape

Class Method Details

.address_encode(address, charset = 'utf-8') ⇒ Object 


168
169
170
171
172
173
174
 
# File 'lib/mail/encodings.rb', line 168

def Encodings.address_encode(address, charset = 'utf-8')
  if address.is_a?(Array)
    address.compact.map { |a| Encodings.address_encode(a, charset) }.join(", ")
  elsif address
    encode_non_usascii(address, charset)
  end
end

.b_value_encode(string, encoding = nil) ⇒ Object

Encode a string with Base64 Encoding and returns it ready to be inserted as a value for a field, that is, in the =?<charset>?B?<string>?= format

Example:

Encodings.b_value_encode('This is あ string', 'UTF-8')
#=> "=?UTF-8?B?VGhpcyBpcyDjgYIgc3RyaW5n?="


224
225
226
227
228
229
230
231
232
233
 
# File 'lib/mail/encodings.rb', line 224

def Encodings.b_value_encode(string, encoding = nil)
  if string.to_s.ascii_only?
    string
  else
    Encodings.each_base64_chunk_byterange(string, 60).map do |chunk|
      str, encoding = RubyVer.b_value_encode(chunk, encoding)
      "=?#{encoding}?B?#{str.chomp}?="
    end.join(" ")
  end
end

.decode_encode(str, output_type) ⇒ Object

Decodes or encodes a string as needed for either Base64 or QP encoding types in the =?<encoding>??<string>?=“ format.

The output type needs to be :decode to decode the input string or :encode to encode the input string. The character set used for encoding will either be the value of $KCODE for Ruby < 1.9 or the encoding on the string passed in.

On encoding, will only send out Base64 encoded strings.


106
107
108
109
110
111
112
113
114
115
116
117
 
# File 'lib/mail/encodings.rb', line 106

def Encodings.decode_encode(str, output_type)
  case
  when output_type == :decode
    Encodings.value_decode(str)
  else
    if str.ascii_only?
      str
    else
      Encodings.b_value_encode(str, find_encoding(str))
    end
  end
end

.defined?(name) ⇒ Boolean

Is the encoding we want defined?

Example:

Encodings.defined?(:base64) #=> true

Returns:

  • (Boolean) 

29
30
31
 
# File 'lib/mail/encodings.rb', line 29

def Encodings.defined?(name)
  @transfer_encodings.include? get_name(name)
end

.encode_non_usascii(address, charset) ⇒ Object 


176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
 
# File 'lib/mail/encodings.rb', line 176

def Encodings.encode_non_usascii(address, charset)
  return address if address.ascii_only? or charset.nil?

  # With KCODE=u we can't use regexps on other encodings. Go ASCII.
  with_ascii_kcode do
    # Encode all strings embedded inside of quotes
    address = address.gsub(/("[^"]*[^\/]")/) { |s| Encodings.b_value_encode(unquote(s), charset) }

    # Then loop through all remaining items and encode as needed
    tokens = address.split(/\s/)

    map_with_index(tokens) do |word, i|
      if word.ascii_only?
        word
      else
        previous_non_ascii = i>0 && tokens[i-1] && !tokens[i-1].ascii_only?
        if previous_non_ascii #why are we adding an extra space here?
          word = " #{word}"
        end
        Encodings.b_value_encode(word, charset)
      end
    end.join(' ')
  end
end

.get_all ⇒ Object 


45
46
47
 
# File 'lib/mail/encodings.rb', line 45

def Encodings.get_all
  @transfer_encodings.values
end

.get_encoding(name) ⇒ Object

Gets a defined encoding type, QuotedPrintable or Base64 for now.

Each encoding needs to be defined as a Mail::Encodings::ClassName for this to work, allows us to add other encodings in the future.

Example:

Encodings.get_encoding(:base64) #=> Mail::Encodings::Base64


41
42
43
 
# File 'lib/mail/encodings.rb', line 41

def Encodings.get_encoding(name)
  @transfer_encodings[get_name(name)]
end

.get_name(name) ⇒ Object 


49
50
51
 
# File 'lib/mail/encodings.rb', line 49

def Encodings.get_name(name)
  underscoreize(name).downcase
end

.param_decode(str, encoding) ⇒ Object

Decodes a parameter value using URI Escaping.

Example:

Mail::Encodings.param_decode("This%20is%20fun", 'us-ascii') #=> "This is fun"

str = Mail::Encodings.param_decode("This%20is%20fun", 'iso-8559-1')
str.encoding #=> 'ISO-8859-1'      ## Only on Ruby 1.9
str #=> "This is fun"


94
95
96
 
# File 'lib/mail/encodings.rb', line 94

def Encodings.param_decode(str, encoding)
  RubyVer.param_decode(str, encoding)
end

.param_encode(str) ⇒ Object

Encodes a parameter value using URI Escaping, note the language field 'en' can be set using Mail::Configuration, like so:

Mail.defaults do
  param_encode_language 'jp'
end

The character set used for encoding will either be the value of $KCODE for Ruby < 1.9 or the encoding on the string passed in.

Example:

Mail::Encodings.param_encode("This is fun") #=> "us-ascii'en'This%20is%20fun"


74
75
76
77
78
79
80
81
82
83
 
# File 'lib/mail/encodings.rb', line 74

def Encodings.param_encode(str)
  case
  when str.ascii_only? && str =~ TOKEN_UNSAFE
    %Q{"#{str}"}
  when str.ascii_only?
    str
  else
    RubyVer.param_encode(str)
  end
end

.q_value_encode(encoded_str, encoding = nil) ⇒ Object

Encode a string with Quoted-Printable Encoding and returns it ready to be inserted as a value for a field, that is, in the =?<charset>?Q?<string>?= format

Example:

Encodings.q_value_encode('This is あ string', 'UTF-8')
#=> "=?UTF-8?Q?This_is_=E3=81=82_string?="


242
243
244
245
246
247
248
249
 
# File 'lib/mail/encodings.rb', line 242

def Encodings.q_value_encode(encoded_str, encoding = nil)
  return encoded_str if encoded_str.to_s.ascii_only?
  string, encoding = RubyVer.q_value_encode(encoded_str, encoding)
  string.gsub!("=\r\n", '') # We already have limited the string to the length we want
  map_lines(string) do |str|
    "=?#{encoding}?Q?#{str.chomp.gsub(/ /, '_')}?="
  end.join(" ")
end

.register(name, cls) ⇒ Object

Register transfer encoding

Example

Encodings.register “base64”, Mail::Encodings::Base64


20
21
22
 
# File 'lib/mail/encodings.rb', line 20

def Encodings.register(name, cls)
  @transfer_encodings[get_name(name)] = cls
end

.transcode_charset(str, from_charset, to_charset = 'UTF-8') ⇒ Object 


53
54
55
56
57
58
59
 
# File 'lib/mail/encodings.rb', line 53

def Encodings.transcode_charset(str, from_charset, to_charset = 'UTF-8')
  if from_charset
    RubyVer.transcode_charset str, from_charset, to_charset
  else
    str
  end
end

.unquote_and_convert_to(str, to_encoding) ⇒ Object

Takes an encoded string of the format =?<encoding>??<string>?=


141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
 
# File 'lib/mail/encodings.rb', line 141

def Encodings.unquote_and_convert_to(str, to_encoding)
  output = value_decode( str ).to_s # output is already converted to UTF-8

  if 'utf8' == to_encoding.to_s.downcase.gsub("-", "")
    output
  elsif to_encoding
    begin
      if RUBY_VERSION >= '1.9'
        output.encode(to_encoding)
      else
        require 'iconv'
        Iconv.iconv(to_encoding, 'UTF-8', output).first
      end
    rescue Iconv::IllegalSequence, Iconv::InvalidEncoding, Errno::EINVAL
      # the 'from' parameter specifies a charset other than what the text
      # actually is...not much we can do in this case but just return the
      # unconverted text.
      #
      # Ditto if either parameter represents an unknown charset, like
      # X-UNKNOWN.
      output
    end
  else
    output
  end
end

.value_decode(str) ⇒ Object

Decodes a given string as Base64 or Quoted Printable, depending on what type it is.

String has to be of the format =?<encoding>??<string>?=


123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
 
# File 'lib/mail/encodings.rb', line 123

def Encodings.value_decode(str)
  # Optimization: If there's no encoded-words in the string, just return it
  return str unless str =~ ENCODED_VALUE

  lines = collapse_adjacent_encodings(str)

  # Split on white-space boundaries with capture, so we capture the white-space as well
  lines.each do |line|
    line.gsub!(ENCODED_VALUE) do |string|
      case $2
      when *B_VALUES then b_value_decode(string)
      when *Q_VALUES then q_value_decode(string)
      end
    end
  end.join("")
end

.with_ascii_kcode ⇒ Object

:nodoc:


203
204
205
206
207
208
209
210
 
# File 'lib/mail/encodings.rb', line 203

def Encodings.with_ascii_kcode #:nodoc:
  if $KCODE
    $KCODE, original_kcode = '', $KCODE
  end
  yield
ensure
  $KCODE = original_kcode if original_kcode
end