Module: MailAddress

Defined in:
lib/mail_address.rb,
lib/mail_address/address.rb,
lib/mail_address/version.rb,
lib/mail_address/mail_address.rb,
lib/mail_address/simple_parser.rb

Defined Under Namespace

Classes: Address

Constant Summary collapse

VERSION = 
"1.2.20"
OPENERS_ =

This module is ported from Google Closure JavaScript Library

-> https://github.com/google/closure-library/blob/master/closure/goog/format/emailaddress.js

'"<(['
CLOSERS_ = 
'">)]'
ADDRESS_SEPARATORS_ =

SPECIAL_CHARS = ‘()<>@:\".[]’

',;'
ESCAPED_DOUBLE_QUOTES_ =

CHARS_REQUIRE_QUOTES_ = SPECIAL_CHARS + ADDRESS_SEPARATORS_

/\\\"/
ESCAPED_BACKSLASHES_ = 
/\\\\/
QUOTED_REGEX_STR_ = 
'[+a-zA-Z0-9_.!#$%&\'*\\/=?^`{|}~\-]+'
UNQUOTED_REGEX_STR_ = 
'"' + QUOTED_REGEX_STR_ + '"'
LOCAL_PART_REGEXP_STR_ = 
'(?:' + QUOTED_REGEX_STR_ + '|' + UNQUOTED_REGEX_STR_ + ')'
DOMAIN_PART_REGEXP_STR_ = 
'([a-zA-Z0-9\-_]+\\.)+[a-zA-Z0-9]{2,63}'
EMAIL_ADDRESS_ = 
Regexp.new('\\A' + LOCAL_PART_REGEXP_STR_ + '@' + DOMAIN_PART_REGEXP_STR_ + '\\z')

Class Method Summary collapse

Class Method Details

.collapse_whitespace(str) ⇒ Object 



121
122
123
 
# File 'lib/mail_address/simple_parser.rb', line 121

def self.collapse_whitespace(str)
  str.gsub(/[\s\xc2\xa0]+/, ' ').strip
end

.get_token(str, pos) ⇒ Object 



87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
 
# File 'lib/mail_address/simple_parser.rb', line 87

def self.get_token(str, pos)
  ch = str[pos]
  p = OPENERS_.index(ch)
  return ch unless p

  if (self.is_escaped_dbl_quote(str, pos))
    # If an opener is an escaped quote we do not treat it as a real opener
    # and keep accumulating the token.
    return ch
  end
  closer_char = CLOSERS_[p]
  end_pos = str.index(closer_char, pos + 1)

  # If the closer is a quote we go forward skipping escaped quotes until we
  # hit the real closing one.
  while (end_pos && end_pos >= 0 && self.is_escaped_dbl_quote(str, end_pos))
    end_pos = str.index(closer_char, end_pos + 1)
  end

  token = (end_pos && end_pos >= 0) ? str[pos .. end_pos] : ch
  return token
end

.is_address_separator(ch) ⇒ Object 



129
130
131
 
# File 'lib/mail_address/simple_parser.rb', line 129

def self.is_address_separator(ch)
  ADDRESS_SEPARATORS_.include? ch
end

.is_empty_or_whitespace(str) ⇒ Object 



125
126
127
 
# File 'lib/mail_address/simple_parser.rb', line 125

def self.is_empty_or_whitespace(str)
  /\A[\s\xc2\xa0]*\z/ =~ str
end

.is_escaped_dbl_quote(str, pos) ⇒ Object 



110
111
112
113
114
115
116
117
118
119
 
# File 'lib/mail_address/simple_parser.rb', line 110

def self.is_escaped_dbl_quote(str, pos)
  return false if str[pos] != '"'
  slash_count = 0

  for idx in (pos - 1).downto(0)
    break unless str[idx] == '\\'
    slash_count += 1
  end
  (slash_count % 2) != 0
end

.is_valid(address) ⇒ Object 



133
134
135
 
# File 'lib/mail_address/simple_parser.rb', line 133

def self.is_valid(address)
  EMAIL_ADDRESS_ =~ address.address
end

.parse(*addresses) ⇒ Object 



8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
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
 
# File 'lib/mail_address/mail_address.rb', line 8

def self.parse(*addresses)
  lines = addresses.grep(String)
  line = lines.join('').strip

  # empty or <> or < or >
  if line.empty? || line.match(/\A[<>;, \\]+\z/)
    return [ MailAddress::Address.new(line, nil, line) ]
  end

  # undisclosed-recipient
  if line.match(/undisclosed[ \-]recipients?: ?;?/i)
    return [ MailAddress::Address.new(line, nil, line) ]
  end

  phrase, address, objs = [], [], []
  original = ''
  depth, idx, end_paren_idx = 0, 0, 0

  tokens = _tokenize lines
  len    = tokens.length
  _next  = _find_next idx, tokens, len

  for idx in 0 ... len do

    token = tokens[idx]
    substr = token[0, 1]
    original << token

    if (end_paren_idx > 0 && end_paren_idx >= idx)
      next
    end

    if (substr == '(' && !address.empty?)
      end_paren_idx = _find_next_paren(idx, tokens, len)
      if end_paren_idx == -1
        # end paren doesn't exist
        # but nothing to do
      end
      rem = tokens[idx .. end_paren_idx]
      phrase.push(rem.join(''))
    elsif (substr == '<')
      depth += 1
    elsif (substr == '>')
      depth -= 1 if depth > 0
    elsif (substr == ',' || substr == ';')
      original.sub!(/[,;]\s*\z/, '')

      if depth > 0
        # raise "Unmatched '<>' in line"
        o = MailAddress::Address.new(original, nil, original)
        phrase.clear; address.clear
      else
        o = _complete(phrase, address, original)
      end

      objs.push(o) if o
      depth = 0
      end_paren_idx = 0
      original = ''
      _next = _find_next idx+1, tokens, len
    elsif (depth > 0)
      token.strip!
      address.push(token)
    elsif (_next == '<')
      phrase.push(token)
    elsif ( token.match(/^[.\@:;]/) || address.empty? || address[-1].match(/^[.\@:;]/) )
      token.strip!
      address.push(token)
    else
      phrase.push(token)
    end
  end
  objs
end

.parse_first(*addresses) ⇒ Object 



4
5
6
 
# File 'lib/mail_address/mail_address.rb', line 4

def self.parse_first(*addresses)
  self.parse(*addresses).first
end

.parse_internal(addr) ⇒ Object 



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
 
# File 'lib/mail_address/simple_parser.rb', line 51

def self.parse_internal(addr)
  name = ''
  address = ''
  i = 0
  while (i < addr.length)
    token = get_token(addr, i)
    if (token[0] == '<' && token.index('>'))
      end_i = token.index('>')
      address = token[1, end_i - 1]
    elsif (address == '')
      name << token
    end
    i += token.length
  end

  # Check if it's a simple email address of the form "[email protected]".
  if (address == '' && name.index('@'))
    address = name
    name = ''
  end

  name = self.collapse_whitespace(name)
  name = name[1 .. -2] if name.start_with?('\'') && name.end_with?('\'')
  name = name[1 .. -2] if name.start_with?('"') && name.end_with?('"')

  # Replace escaped quotes and slashes.
  name = name.gsub(ESCAPED_DOUBLE_QUOTES_, '"')
  name = name.gsub(ESCAPED_BACKSLASHES_, '\\')

  #address = goog.string.collapseWhitespace(address);
  address.strip!

  addr = addr.strip
  MailAddress::Address.new(name, address, addr)
end

.parse_simple(str) ⇒ Object Also known as: g_parse 



21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
 
# File 'lib/mail_address/simple_parser.rb', line 21

def self.parse_simple(str)
  result = []
  email = token = ''

  # Remove non-UNIX-style newlines that would otherwise cause getToken_ to
  # choke. Remove multiple consecutive whitespace characters for the same
  # reason.
  str = self.collapse_whitespace(str)
  i = 0
  while (i < str.length)
    token = get_token(str, i)
    if self.is_address_separator(token) || (token == ' ' && self.is_valid(self.parse_internal(email)))
      if !self.is_empty_or_whitespace(email)
        result.push(self.parse_internal(email))
      end
      email = ''
      i += 1
      next
    end
    email << token
    i += token.length
  end

  # Add the final token.
  if (!self.is_empty_or_whitespace(email))
    result.push(self.parse_internal(email))
  end
  return result
end