Module: RIMS::RFC822::Parse

Included in:
RIMS::RFC822
Defined in:
lib/rims/rfc822.rb

Defined Under Namespace

Classes: Address

Class Method Summary collapse

Class Method Details

.parse_content_disposition(disposition_txt) ⇒ Object 



172
173
174
 
# File 'lib/rims/rfc822.rb', line 172

def parse_content_disposition(disposition_txt)
  split_parameters(disposition_txt)
end

.parse_content_language(language_tags_txt) ⇒ Object 



177
178
179
180
181
182
183
184
185
186
 
# File 'lib/rims/rfc822.rb', line 177

def parse_content_language(language_tags_txt)
  tag_list = language_tags_txt.split(',')
  for tag in tag_list
    tag.strip!
    tag.freeze
  end
  tag_list.reject!(&:empty?)

  tag_list.freeze
end

.parse_content_type(type_txt) ⇒ Object 



139
140
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
167
168
169
 
# File 'lib/rims/rfc822.rb', line 139

def parse_content_type(type_txt)
  media_type_txt, params = split_parameters(type_txt)
  if (media_type_txt) then
    main_type, sub_type = media_type_txt.split('/', 2)
    if (main_type) then
      main_type.strip!
      main_type.freeze
      if (sub_type) then
        sub_type.strip!
        sub_type.freeze
        if (! main_type.empty? && ! sub_type.empty?) then
          return [ main_type, sub_type, params ].freeze
        end
      end
    end
  end

  # See RFC2045 / 5.2. Content-Type Defaults
  # <https://tools.ietf.org/html/rfc2045#section-5.2>
  #
  #     Default RFC 822 messages without a MIME Content-Type header are taken
  #     by this protocol to be plain text in the US-ASCII character set,
  #     which can be explicitly specified as:
  #
  #       Content-type: text/plain; charset=us-ascii
  #
  [ 'text'.dup.force_encoding(type_txt.encoding).freeze,
    'plain'.dup.force_encoding(type_txt.encoding).freeze,
    params                # default is no charset, it will be `ASCII-8BIT'.
  ].freeze
end

.parse_header(header_txt) ⇒ Object 



23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
 
# File 'lib/rims/rfc822.rb', line 23

def parse_header(header_txt)
  field_pair_list = header_txt.scan(%r{
    ((?#name) \S+? )
    \s* : \s*
    (
       (?#value)
       .*? (?: \R|\z)
       (?: \s .*? (?: \R|\z) )*
    )
  }x)

  for name, value in field_pair_list
    value.strip!
    name.freeze
    value.freeze
  end

  field_pair_list.freeze
end

.parse_mail_address_list(address_list_txt) ⇒ Object 



219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
 
# File 'lib/rims/rfc822.rb', line 219

def parse_mail_address_list(address_list_txt)
  addr_list = []
  src_txt = address_list_txt.dup

  while (true)
    if (src_txt.sub!(%r{
          \A
          \s*
          (?<display_name> \S.*? ) \s* : (?<group_list> .*? ) ;
          \s*
          ,?
        }x, ''))
    then
      display_name = $~[:display_name]
      group_list = $~[:group_list]
      addr_list << Address.new(nil, nil, unquote_phrase(display_name), nil).freeze
      addr_list.concat(parse_mail_address_list(group_list))
      addr_list << Address.new(nil, nil, nil, nil).freeze
    elsif (src_txt.sub!(%r{
             \A
             \s*
             (?<local_part> [^<>@",\s]+ )
             \s* @ \s*
             (?<domain> [^<>@",\s]+ )
             \s*
             ,?
           }x, ''))
    then
      addr_list << Address.new(nil, nil, $~[:local_part].freeze, $~[:domain].freeze).freeze
    elsif (src_txt.sub!(%r{
             \A
             \s*
             (?<display_name> \S.*? )
             \s*
             <
               \s*
               (?:
                 (?<route>
                   @[^<>@",]*
                   (?:
                     , \s*
                     @[^<>@",]*
                   )*
                 )
                 \s*
                 :
               )?
               \s*
               (?<local_part> [^<>@",\s]+ )
               \s* @ \s*
               (?<domain> [^<>@",\s]+ )
               \s*
             >
             \s*
             ,?
           }x, ''))
    then
      display_name = $~[:display_name]
      route = $~[:route]
      local_part = $~[:local_part]
      domain = $~[:domain]
      addr_list << Address.new(unquote_phrase(display_name), route.freeze, local_part.freeze, domain.freeze).freeze
    else
      break
    end
  end

  addr_list.freeze
end

.parse_multipart_body(boundary, body_txt) ⇒ Object 



189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
 
# File 'lib/rims/rfc822.rb', line 189

def parse_multipart_body(boundary, body_txt)
  delim = '--' + boundary
  term = delim + '--'
  body_txt2, _body_epilogue_txt = body_txt.split(term, 2)
  if (body_txt2) then
    _body_preamble_txt, body_parts_txt = body_txt2.split(delim, 2)
    if (body_parts_txt) then
      part_list = body_parts_txt.split(delim, -1)
      for part_txt in part_list
        part_txt.lstrip!
        part_txt.chomp!("\n")
        part_txt.chomp!("\r")
        part_txt.freeze
      end
      return part_list.freeze
    end
  end

  [].freeze
end

.parse_parameters(parameters_txt) ⇒ Object 



96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
 
# File 'lib/rims/rfc822.rb', line 96

def parse_parameters(parameters_txt)
  params = {}
  parameters_txt.scan(%r{
    (?<name> \S+? )
    \s* = \s*
    (?:
      (?<quoted_string> ".*?" ) |
      (?<token> \S+? )
    )
    \s*
    (?: ; | \Z )
  }x) do
    name = $~[:name]
    if ($~[:quoted_string]) then
      quoted_value = $~[:quoted_string]
      value = unquote_phrase(quoted_value)
    else
      value = $~[:token]
    end
    params[name.downcase.freeze] = [ name.freeze, value.freeze ].freeze
  end

  params.freeze
end

.split_message(msg_txt) ⇒ Object 



10
11
12
13
14
15
16
17
18
19
20
 
# File 'lib/rims/rfc822.rb', line 10

def split_message(msg_txt)
  header_txt, body_txt = msg_txt.lstrip.split(/\R\R/, 2)
  if ($&) then
    header_txt << $&
  else
    body_txt = header_txt
    header_txt = nil
  end

  [ header_txt.freeze, body_txt.freeze ].freeze
end

.split_parameters(type_params_txt) ⇒ Object 



122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
 
# File 'lib/rims/rfc822.rb', line 122

def split_parameters(type_params_txt)
  type, params_txt = type_params_txt.split(';', 2)
  if (type) then
    type.strip!
    type.freeze
    if (params_txt) then
      params = parse_parameters(params_txt)
    else
      params = {}.freeze
    end
    [ type, params ].freeze
  else
    [ nil, {}.freeze ].freeze
  end
end

.unquote_phrase(phrase_txt) ⇒ Object 



44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
 
# File 'lib/rims/rfc822.rb', line 44

def unquote_phrase(phrase_txt)
  state = :raw
  src_txt = phrase_txt.dup
  dst_txt = ''.encode(phrase_txt.encoding)

  while (src_txt.sub!(/\A (?: " | \( | \) | \\ | [^"\(\)\\]+ )/x, ''))
    match_txt = $&
    case (state)
    when :raw
      case (match_txt)
      when '"'
        state = :quote
      when '('
        state = :comment
      when "\\"
        unless (src_txt.empty?) then
          dst_txt << src_txt[0]
          src_txt[0] = ''
        end
      else
        dst_txt << match_txt
      end
    when :quote
      case (match_txt)
      when '"'
        state = :raw
      when "\\"
        unless (src_txt.empty?) then
          dst_txt << src_txt[0]
          src_txt[0] = ''
        end
      else
        dst_txt << match_txt
      end
    when :comment
      case (match_txt)
      when ')'
        state = :raw
      when "\\"
        src_txt[0] = ''
      else
        # ignore comment text.
      end
    else
      raise "internal error - unknown state: #{state}"
    end
  end

  dst_txt.freeze
end