Class: NameTamer

Inherits:
Object
  • Object
show all
Defined in:
lib/name-tamer.rb,
lib/name-tamer/version.rb

Overview

References: www.w3.org/International/questions/qa-personal-names github.com/berkmancenter/namae github.com/mericson/people en.wikipedia.org/wiki/Types_of_business_entity en.wikipedia.org/wiki/List_of_post-nominal_letters_(USA) en.wikipedia.org/wiki/List_of_post-nominal_letters_(United_Kingdom) en.wikipedia.org/wiki/Nobiliary_particle en.wikipedia.org/wiki/Spanish_naming_customs linguistlist.org/pubs/tocs/JournalUnifiedStyleSheet2007.pdf [PDF]

Constant Summary collapse

VERSION = 
'0.2.12'

Instance Attribute Summary collapse

Class Method Summary collapse

Instance Method Summary collapse

Instance Attribute Details

#name ⇒ Object (readonly)

Returns the value of attribute name.



16
17
18
 
# File 'lib/name-tamer.rb', line 16

def name
  @name
end

Class Method Details

.[](name, args = {}) ⇒ Object 



19
20
21
 
# File 'lib/name-tamer.rb', line 19

def [](name, args = {})
  new name, args
end

.parameterize(string, args = {}) ⇒ Object

Make a slug from a string



24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
 
# File 'lib/name-tamer.rb', line 24

def parameterize(string, args = {})
  sep     = args[:sep]      || SLUG_DELIMITER
  rfc3987 = args[:rfc3987]  || false
  filter  = args[:filter]   || (rfc3987 ? FILTER_RFC3987 : FILTER_COMPAT)

  new_string = string.dup

  new_string
    .whitespace_to!(sep)
    .invalid_chars_to!(sep)
    .strip_unwanted!(filter)
    .fix_separators!(sep)
    .approximate_latin_chars!

  # Have we got anything left?
  new_string = '_' if new_string.empty?

  # downcase any latin characters
  new_string.downcase
end

Instance Method Details

#contact_type ⇒ Object 



94
95
96
97
 
# File 'lib/name-tamer.rb', line 94

def contact_type
  nice_name # make sure we've done the bit which infers contact_type
  contact_type_best_effort
end

#contact_type=(new_contact_type) ⇒ Object 



99
100
101
102
103
104
105
106
107
 
# File 'lib/name-tamer.rb', line 99

def contact_type=(new_contact_type)
  ct_as_sym = new_contact_type.to_sym

  unless @contact_type.nil? || @contact_type == ct_as_sym
    puts "Changing contact type of #{@name} from #{@contact_type} to #{new_contact_type}"
  end

  @contact_type = ct_as_sym
end

#nice_name ⇒ Object 



60
61
62
63
64
65
66
67
68
69
70
71
72
73
 
# File 'lib/name-tamer.rb', line 60

def nice_name
  unless @nice_name
    @nice_name = tidy_name.dup      # Start with the tidied name

    remove_adfixes                  # prefixes and suffixes: "Smith, John, Jr." -> "Smith, John"
    fixup_last_name_first           # "Smith, John" -> "John Smith"
    fixup_mismatched_braces         # "Ceres (AZ" -> "Ceres (AZ)"
    remove_adfixes                  # prefixes and suffixes: "Mr John Smith Jr." -> "John Smith"
    name_wrangle                    # proper name case and non-breaking spaces
    use_nonbreaking_spaces_in_compound_names
  end

  @nice_name
end

#simple_name ⇒ Object 



75
76
77
78
79
80
81
82
83
84
85
86
87
88
 
# File 'lib/name-tamer.rb', line 75

def simple_name
  unless @simple_name
    @simple_name = nice_name.dup    # Start with nice name

    remove_initials               # "John Q. Doe" -> "John Doe"
    remove_middle_names           # "Philip Seymour Hoffman" -> "Philip Hoffman"
    remove_periods_from_initials  # "J.P.R. Williams" -> "JPR Williams"
    standardize_words             # "B&Q Intl" -> "B and Q International"

    @simple_name.whitespace_to!(ASCII_SPACE)
  end

  @simple_name
end

#slug ⇒ Object 



90
91
92
 
# File 'lib/name-tamer.rb', line 90

def slug
  @slug ||= NameTamer.parameterize simple_name.dup # "John Doe" -> "john-doe"
end

#tidy_name ⇒ Object 



46
47
48
49
50
51
52
53
54
55
56
57
58
 
# File 'lib/name-tamer.rb', line 46

def tidy_name
  unless @tidy_name
    @tidy_name = name.dup # Start with the name we've received

    unescape              # Unescape percent-encoded characters and fix UTF-8 encoding
    remove_zero_width     # remove zero-width characters
    tidy_spacing          # " John   Smith " -> "John Smith"
    fix_encoding_errors   # "Ren\u00c3\u00a9 Descartes" -> "Ren\u00e9 Descartes"
    consolidate_initials  # "I. B. M." -> "I.B.M."
  end

  @tidy_name
end