Class: Namor::Namor

Inherits:
Object
  • Object
show all
Defined in:
lib/namor/namor.rb

Instance Method Summary collapse

Constructor Details

#initialize(opts = {}) ⇒ Namor

Returns a new instance of Namor.



2
3
4
# File 'lib/namor/namor.rb', line 2

def initialize(opts = {})
  config(opts)
end

Instance Method Details

#components(*args) ⇒ Object



70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
# File 'lib/namor/namor.rb', line 70

def components(*args)
  suppression_list = @config[:suppress] ? @config[:suppress].map(&:upcase) : []

  names = args
  bits = []
  names.compact.each do |name|
    name = name.dup
    name.gsub!(/\([^\(]*\)/, '')
    name.gsub!(/\[[^\[]*\]/, '')
    name.gsub!(/[\(\)\[\]\']/, '')
    name.gsub!(/[,._-]/, ' ')
    bits += name.split(/\s+/).map(&:upcase)
  end

  suppress_re = %w{MD JR SR I+ IV}.join('|')
  bits.delete_if {|bit| suppression_list.include?(bit) || bit =~ /^(#{suppress_re})$/}
  bits.delete_if(&:empty?)
  bits.uniq.sort
end

#config(opts) ⇒ Object



6
7
8
# File 'lib/namor/namor.rb', line 6

def config(opts)
  @config = opts
end

#extract(name, opts = {}) ⇒ Object



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
# File 'lib/namor/namor.rb', line 25

def extract(name, opts = {})
  return [] if name.nil?

  detitled_name = scrub(name, opts)

  if detitled_name =~ /,/
    # "last, first[ middle]"
    lastname, firstname = detitled_name.split(/\s*,\s*/)
    lastname.gsub!(/ /, '')
    middlename = nil
    if firstname && firstname =~ / /
      pieces = firstname.split(/ +/)
      firstname = pieces.shift
      middlename = pieces.join if pieces.any?
    end
  else
    # "first [middle ]last"
    pieces = detitled_name.split(' ')
    firstname = pieces.shift
    middlename = nil
    if pieces.count > 1 && pieces.first.length == 1
      # assume this is a middle initial
      middlename = pieces.shift
    end

    lastname = pieces.join
  end

  firstname = nil if firstname.empty?
  middlename = nil if middlename && middlename.empty?
  lastname = nil if lastname.empty?

  fm = [firstname, middlename].compact.join(' ')
  fullname = [lastname, fm].compact.join(',')

  [firstname, middlename, lastname, fullname]
end

#extract_with_cluster(name, opts = {}) ⇒ Object



63
64
65
66
67
# File 'lib/namor/namor.rb', line 63

def extract_with_cluster(name, opts = {})
  ary = extract(name, opts)
  return [] if ary.empty?
  ary << ary.last.gsub(/\W/, '_')
end

#scrub(name, opts = {}) ⇒ Object

clean up a single name component

  • output all converted to uppercase

  • strip leading ZZ+ or XX+ (frequently used as invalid-account prefixes)

  • remove any words that are in the user-provided suppression list

  • remove words from list of common suffixes (Jr, Sr etc)

  • remove anything inside parenthesis

  • remove punctuation

  • squeeze whitespace & trim spaces from ends



18
19
20
21
22
23
# File 'lib/namor/namor.rb', line 18

def scrub(name, opts = {})
  suppression_list = @config[:suppress] || []
  suppression_re = (suppression_list + (opts[:suppress]||[])).compact.map(&:upcase).join('|')

  name && name.upcase.gsub(/^[ZX]{2,}/, '').gsub(/\b(#{suppression_re})\b/i, '').gsub(/\b(JR|SR|II|III|IV)\b/i, '').gsub(/\([^\(]*\)/, '').gsub(/\./, ' ').gsub(/[_'-]/, '').gsub(/,\s*$/, '').gsub(/ +/, ' ').strip
end