Class: Namor::Namor
- Inherits:
-
Object
- Object
- Namor::Namor
- Defined in:
- lib/namor/namor.rb
Instance Method Summary collapse
- #components(*args) ⇒ Object
- #config(opts) ⇒ Object
- #demaiden(lastname) ⇒ Object
- #extract(name, opts = {}) ⇒ Object
- #extract_with_cluster(name, opts = {}) ⇒ Object
- #final_cleaning(name) ⇒ Object
- #fullscrub(name, opts = {}) ⇒ Object
-
#initialize(opts = {}) ⇒ Namor
constructor
A new instance of Namor.
-
#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.
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
94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 |
# File 'lib/namor/namor.rb', line 94 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 |
#demaiden(lastname) ⇒ Object
29 30 31 32 33 34 35 36 |
# File 'lib/namor/namor.rb', line 29 def demaiden(lastname) return [nil,nil] unless lastname && !lastname.empty? if lastname =~ /\-/ [lastname.gsub(/ /, ''), lastname.split(/\-/).last.gsub(/ /, '')] else [lastname.gsub(/ /, ''), lastname.split(/ /).last] end end |
#extract(name, opts = {}) ⇒ Object
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 |
# File 'lib/namor/namor.rb', line 46 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, de_maidened_last = demaiden(lastname) middlename = nil if firstname && firstname =~ / / pieces = firstname.split(/ +/) firstname = pieces.shift middlename = pieces.join if pieces.any? end else # "first [middle-initial ]last" or "first everything-else-is-the-lastname" pieces = detitled_name.split(' ') firstname = pieces.shift if pieces.count > 1 && pieces.first.length == 1 # assume this is a middle initial middlename = pieces.shift else middlename = nil end lastname, de_maidened_last = demaiden(pieces.join(' ')) end firstname = final_cleaning(firstname) middlename = final_cleaning(middlename) lastname = final_cleaning(lastname) de_maidened_last = final_cleaning(de_maidened_last) fm = [firstname, middlename].compact.join(' ') fullname = [lastname, fm].compact.join(',') nee_fullname = [de_maidened_last, fm].compact.join(',') [firstname, middlename, lastname, fullname, nee_fullname] end |
#extract_with_cluster(name, opts = {}) ⇒ Object
87 88 89 90 91 |
# File 'lib/namor/namor.rb', line 87 def extract_with_cluster(name, opts = {}) ary = extract(name, opts) return [] if ary.empty? ary << ary.last.gsub(/\W/, '_') end |
#final_cleaning(name) ⇒ Object
38 39 40 41 42 43 44 |
# File 'lib/namor/namor.rb', line 38 def final_cleaning(name) if name && !name.empty? name.gsub(/\-/, '') else nil end end |
#fullscrub(name, opts = {}) ⇒ Object
25 26 27 |
# File 'lib/namor/namor.rb', line 25 def fullscrub(name, opts = {}) final_cleaning(scrub(name, opts)) 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 = Regexp.new('(\s|^)' + (suppression_list + (opts[:suppress]||[])).compact.map(&:upcase).join('|') + '(\s|\.|$)') name && name.upcase.gsub(/^[ZX]{2,}/, '').gsub(suppression_re, '').gsub(/\b(JR|SR|II|III|IV)\b/i, '').gsub(/\([^\(]*\)/, '').gsub(/\./, ' ').gsub(/[_'\&]/, '').gsub(/,\s*$/, '').gsub(/ +/, ' ').strip end |