name-tamer 0.0.0

checksums.yaml

@@ -0,0 +1,15 @@
+---
+!binary "U0hBMQ==":
+  metadata.gz: !binary |-
+    YzRiZjg0NGY3ODliMzVjZWM0ZDBhMjExYjNjODMyMmJmZTExNDRiMA==
+  data.tar.gz: !binary |-
+    ZmZmODdkOGIwYzBlN2I3MjM3OTVjNzBhZGM0ZjQ2MTk0MmQ3MmIyMg==
+SHA512:
+  metadata.gz: !binary |-
+    YzhhNzUxMTY5OWQ4YjkxYzUxNTMxNTBhYjNkZGMyMDE1MDFmNDNkMmY2Y2Uy
+    ZWVmODhiMGM3OTBjNWE3ZmI0NGI0Yjk4MTRiZWYyMWRkZTY0NjBhNzI5NWNm
+    Nzk4ODliZjU3OTc3YzY4MzdkYWYyYzU4ODE4ZGJhNjkwNmE1MDU=
+  data.tar.gz: !binary |-
+    YWNiMjZhODI5NDk2MmI1Y2E4MWUyYTg4NTk0M2ExMGFkNzhhZjdlZDRiYzJm
+    ZDI0ZjNiYmJlMWNiYjRmOTYxMGU5MTdlMTZjYzA0YTZjNjdkYTliOTc1YWRj
+    ZmM1ZWYwZTA5ZjQ5NDc2OGQ4NzA1NTgwYzM0MTNlYTFjMzgzMDc=

data/.env

@@ -0,0 +1 @@
+PATH=/home/build/.rvm/gems/ruby-2.1.1/bin:/home/build/.rvm/gems/ruby-2.1.1@global/bin:/home/build/.rvm/rubies/ruby-2.1.1/bin:/home/build/.rvm/bin:/usr/local/heroku/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/usr/local/games:/home/build/.rvm/gems/ruby-2.1.1@global/bin/bundle

data/.gitignore

@@ -0,0 +1,24 @@
+*.rbc
+capybara-*.html
+.rspec
+/log
+/tmp
+/db/*.sqlite3
+/public/system
+/coverage/
+/spec/tmp
+**.orig
+rerun.txt
+pickle-email-*.html
+config/initializers/secret_token.rb
+config/secrets.yml
+
+## Environment normalisation:
+/.bundle
+/vendor/bundle
+
+# these should all be checked in to normalise the environment:
+# Gemfile.lock, .ruby-version, .ruby-gemset
+
+# unless supporting rvm < 1.11.0 or doing something fancy, ignore this:
+.rvmrc

data/.ruby-version

@@ -0,0 +1 @@
+2.1.2

data/Gemfile

@@ -0,0 +1,4 @@
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in foreplay.gemspec
+gemspec

data/Gemfile.lock

@@ -0,0 +1,42 @@
+PATH
+  remote: .
+  specs:
+    name-tamer (0.0.0)
+      activesupport (~> 3)
+
+GEM
+  remote: https://rubygems.org/
+  specs:
+    activesupport (3.2.13)
+      i18n (= 0.6.1)
+      multi_json (~> 1.0)
+    diff-lcs (1.2.5)
+    docile (1.1.3)
+    gem-release (0.7.3)
+    i18n (0.6.1)
+    multi_json (1.10.1)
+    rake (10.3.2)
+    rspec (2.14.1)
+      rspec-core (~> 2.14.0)
+      rspec-expectations (~> 2.14.0)
+      rspec-mocks (~> 2.14.0)
+    rspec-core (2.14.8)
+    rspec-expectations (2.14.5)
+      diff-lcs (>= 1.1.3, < 2.0)
+    rspec-mocks (2.14.6)
+    simplecov (0.8.2)
+      docile (~> 1.1.0)
+      multi_json
+      simplecov-html (~> 0.8.0)
+    simplecov-html (0.8.0)
+
+PLATFORMS
+  ruby
+
+DEPENDENCIES
+  bundler (~> 1)
+  gem-release (~> 0)
+  name-tamer!
+  rake (~> 10)
+  rspec (~> 2)
+  simplecov (~> 0)

data/LICENSE

@@ -0,0 +1,21 @@
+The MIT License (MIT)
+
+Copyright (c) 2014 Xenapto
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

data/README.md

@@ -0,0 +1,48 @@
+# NameTamer
+
+[![Gem Version](https://badge.fury.io/rb/name-tamer.png)](http://badge.fury.io/rb/name-tamer)
+[![Code Climate](https://codeclimate.com/github/Xenapto/name-tamer.png)](https://codeclimate.com/github/Xenapto/name-tamer)
+[![Dependency Status](https://gemnasium.com/Xenapto/name-tamer.png)](https://gemnasium.com/Xenapto/name-tamer)
+![build status](https://circleci.com/gh/Xenapto/name-tamer.png?circle-token=dd3a51864d33f6506b18a355bc901b90c0df3b3b)
+
+NameTamer: deploying Rails projects to Ubuntu using Foreman
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+    gem 'name-tamer'
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install name-tamer
+
+## Usage
+
+Examples:
+
+```ruby
+NameTamer['Mr. John Q. Smith III, MD'].simple_name # => John Smith
+```
+
+```ruby
+name_tamer = NameTamer['Mr. John Q. Smith III, MD']
+name_tamer.slug # => john-smith
+name_tamer.nice_name # => John Q. Smith
+```
+
+## Contributing
+
+1.  Fork it
+1.  Create your feature branch (`git checkout -b my-new-feature`)
+1.  Commit your changes (`git commit -am 'Add some feature'`)
+1.  Push to the branch (`git push origin my-new-feature`)
+1.  Create new Pull Request
+
+## Acknowledgements
+
+1.  Thanks to Ryan Bigg for the guide to making your first gem https://github.com/radar/guides/blob/master/gem-development.md

data/Rakefile

@@ -0,0 +1 @@
+require "bundler/gem_tasks"

data/bin/name-tamer

@@ -0,0 +1,3 @@
+#!/usr/bin/env ruby
+require 'name_tamer/cli'
+NameTamer::CLI.start

data/lib/name_tamer.rb

@@ -0,0 +1,509 @@
+# encoding: utf-8
+
+# References:
+# http://www.w3.org/International/questions/qa-personal-names
+# https://github.com/berkmancenter/namae
+# https://github.com/mericson
+# http://en.wikipedia.org/wiki/Types_of_business_entity
+# http://en.wikipedia.org/wiki/List_of_post-nominal_letters_(USA)
+# http://en.wikipedia.org/wiki/List_of_post-nominal_letters_(United_Kingdom)
+# http://en.wikipedia.org/wiki/Nobiliary_particle
+# http://en.wikipedia.org/wiki/Spanish_naming_customs
+# http://linguistlist.org/pubs/tocs/JournalUnifiedStyleSheet2007.pdf [PDF]
+require 'active_support/core_ext/object'
+
+class NameTamer
+  attr_reader :name, :contact_type
+
+  class << self
+    def [](name, args = {})
+      new name, args
+    end
+  end
+
+  def nice_name
+    if @nice_name.nil?
+      @nice_name = @name.dup          # Start with the name we've received
+
+      tidy_spacing                    # " John   Smith " -> "John Smith"
+      consolidate_initials            # "I. B. M." -> "I.B.M."
+      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
+
+  def search_name
+    if @search_name.nil?
+      @search_name = nice_name.dup    # Start with nice name
+
+      remove_initials                 # "John Q. Doe" -> "John Doe"
+      remove_middle_names             # "Philip Seymour Hoffman" -> "Philip Hoffman"
+      remove_dots_from_abbreviations  # "J.P.R. Williams" -> "JPR Williams"
+      standardize_words               # "B&Q Intl" -> "B and Q International"
+
+      @search_name = ensure_whitespace_is_ascii_space @search_name
+    end
+
+    @search_name
+  end
+
+  def slug
+    if @slug.nil?
+      @slug = search_name.dup         # Start with search name
+      slugify                         # "John Doe" -> "john-doe"
+    end
+
+    @slug
+  end
+
+  def contact_type
+    nice_name # make sure we've done the bit which infers contact_type
+    contact_type_best_effort
+  end
+
+=begin These lines aren't used and aren't covered by specs
+  def name=(new_name)
+    initialize new_name, :contact_type => @contact_type
+  end
+
+  def contact_type=(new_contact_type)
+    initialize @name, :contact_type => new_contact_type
+  end
+
+  def to_hash
+    {
+      name:         @name,
+      nice_name:    @nice_name,
+      search_name:  @search_name,
+      slug:         @slug,
+      contact_type: @contact_type,
+      last_name:    @last_name,
+      remainder:    @remainder,
+      adfix_found:  @adfix_found
+    }
+  end
+=end
+
+  private
+
+  #--------------------------------------------------------
+  # Tidy up the name we've received
+  #--------------------------------------------------------
+
+  def tidy_spacing
+    @nice_name.gsub!(/,\s*/, ', ') # Ensure commas have exactly one space after them
+    @nice_name.strip!              # remove leading & trailing whitespace
+
+    @nice_name = ensure_whitespace_is_ascii_space @nice_name
+  end
+
+  # Remove spaces from groups of initials
+  def consolidate_initials
+    @nice_name.gsub!(/\b([a-z])\.* (?=[a-z][\. ])/i) { |match| "#{$1}." }   # Remove spaces from initial groups
+    @nice_name.gsub!(/\b([a-z](?:\.[a-z])+)\.?(?= )/i) { |match| "#{$1}." } # Ensure each group ends with a dot
+  end
+
+  # An adfix is either a prefix or a suffix
+  def remove_adfixes
+    if @last_name.nil?
+      # Our name is still in one part, not two
+      begin
+        @nice_name = remove_outermost_adfix(:suffix, @nice_name)
+      end while @adfix_found
+
+      begin
+        @nice_name = remove_outermost_adfix(:prefix, @nice_name)
+      end while @adfix_found
+    else
+      # Our name is currently in two halves
+      begin
+        @last_name = remove_outermost_adfix(:suffix, @last_name)
+      end while @adfix_found
+
+      begin
+        @remainder = remove_outermost_adfix(:prefix, @remainder)
+      end while @adfix_found
+    end
+  end
+
+  # Names in the form "Smith, John" need to be turned around to "John Smith"
+  def fixup_last_name_first
+    unless @contact_type == :organization
+      parts = @nice_name.split ', '
+
+      if parts.count == 2
+        @last_name    = parts[0] # Sometimes the last name alone is all caps and we can name-case it
+        @remainder    = parts[1]
+      end
+    end
+  end
+
+  # Sometimes we end up with mismatched braces after adfix stripping
+  # e.g. "Ceres (Ceres Holdings LLC)" -> "Ceres (Ceres Holdings"
+  def fixup_mismatched_braces
+    left_brace_count  = @nice_name.count '('
+    right_brace_count = @nice_name.count ')'
+
+    if left_brace_count > right_brace_count
+      @nice_name += ')'
+    elsif left_brace_count < right_brace_count
+      @nice_name = '(' + @nice_name
+    end
+  end
+
+  def name_wrangle
+    # Fix case if all caps or all lowercase
+    if @last_name.nil?
+      lowercase = @nice_name.downcase
+      uppercase = @nice_name.upcase
+
+      # Some companies like to be all lowercase so don't mess with them
+      @nice_name  = name_case(lowercase) if @nice_name == uppercase || ( @nice_name == lowercase && @contact_type != :organization )
+    else
+      lowercase = @last_name.downcase
+      uppercase = @last_name.upcase
+      @last_name  = name_case(lowercase) if @last_name == uppercase || @last_name == lowercase
+
+      @nice_name  = "#{@remainder} #{@last_name}"
+    end
+  end
+
+  # Conjoin compound names with non-breaking spaces
+  def use_nonbreaking_spaces_in_compound_names
+    # Fix known last names that have spaces (not hyphens!)
+    [
+      'Lane Fox', 'Bonham Carter', 'Pitt Rivers', 'Lloyd Webber', 'Sebag Montefiore',
+      'Holmes à Court', 'Holmes a Court', 'Baron Cohen',
+      'Service Company', 'Corporation Company', 'Corporation System', 'Incorporations Limited'
+    ].each do |compound_name|
+      @nice_name.gsub!(compound_name, compound_name.tr(ASCII_SPACE, NONBREAKING_SPACE))
+    end
+
+    NAME_MODIFIERS.each do |modifier|
+      @nice_name.gsub!(/([[:space:]]#{modifier})([[:space:]])/i) { |match| "#{$1}#{NONBREAKING_SPACE}" }
+    end
+  end
+
+  #--------------------------------------------------------
+  # Make search name from nice name
+  #--------------------------------------------------------
+
+  # Remove initials from personal names unless they are the only identifier.
+  # i.e. only remove initials if there's also a proper name there
+  def remove_initials
+    if @contact_type == :person
+      name = @search_name.gsub(/\b([a-z](?:\.*\s+|\.))/i, '')
+
+      # If the name still has at least one space we're OK
+      @search_name = name if name.include?(ASCII_SPACE)
+    end
+  end
+
+  def remove_middle_names
+    if @contact_type == :person
+      parts = @search_name.split
+      @search_name = "#{parts[0]} #{parts[-1]}" if parts.count > 2
+    end
+  end
+
+  def remove_dots_from_abbreviations
+    @search_name.gsub!(/\b([a-z])\./i) { |match| $1 }
+  end
+
+  def standardize_words
+    @search_name.gsub!(/ *& */, ' and ')              # replace ampersand characters with ' and '
+    @search_name.gsub!(/ *\+ */, ' plus ')            # replace plus signs with ' plus '
+    @search_name.gsub!(/\bintl\b/i, 'International')  # replace 'intl' with 'International'
+  end
+
+  #--------------------------------------------------------
+  # Make slug from search name
+  #--------------------------------------------------------
+
+  def slugify
+    # Inflector::parameterize just gives up with non-latin characters so...
+    #@slug = @slug.parameterize # Can't use this
+
+    # Instead we'll do it ourselves
+    @slug = parameterize @slug
+  end
+
+  #--------------------------------------------------------
+  # Initialization and utilities
+  #--------------------------------------------------------
+
+  def initialize(name, args = {})
+    @name         = name || ''
+    @contact_type = args[:contact_type].to_sym unless args[:contact_type].nil?
+
+    @nice_name    = nil
+    @search_name  = nil
+    @slug         = nil
+
+    @last_name    = nil
+    @remainder    = nil
+
+    @adfix_found  = false
+  end
+
+  def set_contact_type contact_type
+    contact_type_sym = contact_type.to_sym
+    puts "Changing contact type of #{@name} from #{@contact_type} to #{contact_type}".red unless @contact_type.nil? || @contact_type == contact_type_sym
+    @contact_type = contact_type_sym
+  end
+
+  # If we don't know the contact type, what's our best guess?
+  def contact_type_best_effort
+    if @contact_type
+      @contact_type
+    else
+      # If it's just one word we'll assume organization.
+      # If more then we'll assume a person
+      @name.include?(ASCII_SPACE) ? :person : :organization
+    end
+  end
+
+  def ensure_whitespace_is_ascii_space string
+    string.gsub(/[[:space:]]+/, ASCII_SPACE) # /\s/ doesn't match Unicode whitespace in Ruby 1.9.3
+  end
+
+  # We pass to this routine either prefixes or suffixes
+  def remove_outermost_adfix adfix_type, name_part
+    adfixes       = ADFIX_PATTERNS[adfix_type]
+    contact_type  = contact_type_best_effort
+    parts         = name_part.partition adfixes[contact_type]
+    @adfix_found  = parts[1].present?
+
+    # If the contact type is indeterminate and we didn't find a diagnostic adfix
+    # for a person then try again for an organization
+    if @contact_type.nil?
+      unless @adfix_found
+        contact_type  = :organization
+        parts         = name_part.partition adfixes[contact_type]
+        @adfix_found  = parts[1].present?
+      end
+    end
+
+    if @adfix_found
+      # If we've found a diagnostic adfix then set the contact type
+      set_contact_type contact_type
+
+      # The remainder of the name will be in parts[0] or parts[2] depending
+      # on whether this is a prefix or a suffix.
+      # We'll also remove any trailing commas we've exposed.
+      result = (parts[0] + parts[2]).gsub(/\s*,\s*$/, '')
+    else
+      result = name_part
+    end
+
+    result
+  end
+
+  # Original Version of NameCase:
+  # Copyright (c) Mark Summerfield 1998-2008. All Rights Reserved
+  # This module may be used/distributed/modified under the same terms as Perl itself
+  # http://dev.perl.org/licenses/ (GPL)
+  #
+  # Ruby Version:
+  # Copyright (c) Aaron Patterson 2006
+  # NameCase is distributed under the GPL license.
+  #
+  # Substantially modified for Xendata
+  # Improved in several areas, also now adds non-breaking spaces for
+  # compound names like "van der Pump"
+  def name_case lowercase
+    name = lowercase # We assume the name is passed already downcased
+    name.gsub!(/\b\w/) { |first| first.upcase }
+    name.gsub!(/\'\w\b/) { |c| c.downcase } # Lowercase 's
+
+    # Our list of terminal characters that indicate a non-celtic name used
+    # to include o but we removed it because of MacMurdo.
+    if name =~ /\bMac[A-Za-z]{2,}[^acizj]\b/ or name =~ /\bMc/
+      name.gsub!(/\b(Ma?c)([A-Za-z]+)/) { |match| $1 + $2.capitalize }
+
+      # Fix Mac exceptions
+      [
+        'MacEdo', 'MacEvicius', 'MacHado', 'MacHar', 'MacHin', 'MacHlin', 'MacIas', 'MacIulis', 'MacKie', 'MacKle',
+        'MacKlin', 'MacKmin', 'MacKmurdo', 'MacQuarie', 'MacLise', 'MacKenzie'
+      ].each { |mac_name| name.gsub!(/\b#{mac_name}/, mac_name.capitalize) }
+    end
+
+    # Fix ff wierdybonks
+    [
+      'Fforbes', 'Fforde', 'Ffinch', 'Ffrench', 'Ffoulkes'
+    ].each { |ff_name| name.gsub!(ff_name,ff_name.downcase) }
+
+    # Fixes for name modifiers followed by space
+    # Also replaces spaces with non-breaking spaces
+    NAME_MODIFIERS.each do |modifier|
+      name.gsub!(/((?:[[:space:]]|^)#{modifier})(\s+|-)/) { |match| "#{$1.rstrip.downcase}#{$2.tr(ASCII_SPACE, NONBREAKING_SPACE)}" }
+    end
+
+    # Fixes for name modifiers followed by an apostrophe, e.g. d'Artagnan, Commedia dell'Arte
+    ['Dell', 'D'].each do |modifier|
+      name.gsub!(/(.#{modifier}')(\w)/) { |match| "#{$1.rstrip.downcase}#{$2}" }
+    end
+
+    # Upcase words with no vowels, e.g JPR Williams
+    name.gsub!(/\b([bcdfghjklmnpqrstvwxz]+)\b/i) { |match| $1.upcase }
+    # Except Ng
+    name.gsub!(/\b(NG)\b/i) { |match| $1.capitalize } # http://en.wikipedia.org/wiki/Ng
+
+    name
+  end
+
+  def parameterize string, args = {}
+    sep     = args[:sep]      || SLUG_DELIMITER
+    rfc3987 = args[:rfc3987]  || false
+    filter  = args[:filter]   || (rfc3987 ? FILTER_RFC3987 : FILTER_COMPAT)
+
+    # First we unescape any pct-encoded characters. These might turn into
+    # things we want to alter for the slug, like whitespace (e.g. %20)
+    parameterized_string = URI.unescape(string)
+
+    # Then we change any whitespace into our separator character
+    parameterized_string.gsub!(/\s+/, sep)
+
+    # Then we strip any illegal characters out completely
+    parameterized_string.gsub!(filter, '')
+
+    # Make sure separators are not where they shouldn't be
+    unless sep.nil? || sep.empty?
+      re_sep = Regexp.escape(sep)
+      # No more than one of the separator in a row.
+      parameterized_string.gsub!(/#{re_sep}{2,}/, sep)
+      # Remove leading/trailing separator.
+      parameterized_string.gsub!(/^#{re_sep}|#{re_sep}$/i, '')
+    end
+
+    # downcase if it's all latin
+    parameterized_string.downcase
+  end
+
+  #--------------------------------------------------------
+  # Constants
+  #--------------------------------------------------------
+
+  NONBREAKING_SPACE = "\u00a0"
+  ASCII_SPACE       = "\u0020"
+  ADFIX_JOINERS     = "[#{ASCII_SPACE}-]"
+  SLUG_DELIMITER    =  '-'
+
+  # Constants for parameterizing Unicode strings for IRIs
+  #
+  # Allowed characters in an IRI segment are defined by RFC 3987
+  # (https://tools.ietf.org/html/rfc3987#section-2.2) as follows:
+  #
+  #    isegment-nz-nc = 1*( iunreserved / pct-encoded / sub-delims
+  #                         / "@" )
+  #                   ; non-zero-length segment without any colon ":"
+  #
+  #    iunreserved    = ALPHA / DIGIT / "-" / "." / "_" / "~" / ucschar
+  #
+  #    pct-encoded    = "%" HEXDIG HEXDIG
+  #
+  #    sub-delims     = "!" / "$" / "&" / "'" / "(" / ")"
+  #                   / "*" / "+" / "," / ";" / "="
+  #
+  #    ucschar        = %xA0-D7FF / %xF900-FDCF / %xFDF0-FFEF
+  #                   / %x10000-1FFFD / %x20000-2FFFD / %x30000-3FFFD
+  #                   / %x40000-4FFFD / %x50000-5FFFD / %x60000-6FFFD
+  #                   / %x70000-7FFFD / %x80000-8FFFD / %x90000-9FFFD
+  #                   / %xA0000-AFFFD / %xB0000-BFFFD / %xC0000-CFFFD
+  #                   / %xD0000-DFFFD / %xE1000-EFFFD
+  #
+  # Note that we can't use Unicode code points above \uFFFF because of
+  # regex limitations, so we'll ignore ucschar above that point.
+  #
+  # We're using the most restrictive segment definition (isegment-nz-nc)
+  # to avoid any possible problems with the IRI that it one day might
+  # get placed in.
+  ALPHA           = 'A-Za-z'
+  DIGIT           = '0-9'
+  UCSCHAR         = '\u00A0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF'
+  IUNRESERVED     = "#{ALPHA}#{DIGIT}\\-\\._~#{UCSCHAR}"
+  SUBDELIMS       = '!$&\'\(\)\*+,;='
+  ISEGMENT_NZ_NC  = "#{IUNRESERVED}#{SUBDELIMS}@" # pct-encoded not needed
+  FILTER_RFC3987  = /[^#{ISEGMENT_NZ_NC}]/
+  FILTER_COMPAT   = /[^#{ALPHA}#{DIGIT}\-_#{UCSCHAR}]/
+
+  NAME_MODIFIERS    = [
+    'Al', 'Ap', 'Ben', 'Dell[ae]', 'D[aeiou]', 'De[lr]', 'D[ao]s', 'El', 'La', 'L[eo]',
+    'V[ao]n', 'Of', 'St[\.]?'
+  ]
+
+  # These are the prefixes and suffixes we want to remove
+  # If you add to the list, you can use spaces and dots where appropriate
+  # Ensure any single letters are followed by a dot because we'll add one to the string
+  # during processing, e.g. "y Cía." should be "y. Cía."
+  ADFIXES = {
+    prefix: {
+      person: [
+        'Baron', 'Baroness', 'Capt.', 'Captain', 'Col.', 'Colonel', 'Dame',
+        'Doctor', 'Dr.', 'Judge', 'Justice', 'Lady', 'Lieut.', 'Lieutenant',
+        'Lord', 'Madame', 'Major', 'Master', 'Matron', 'Messrs.', 'Mgr.',
+        'Miss', 'Mister', 'Mlle.', 'Mme.', 'Mons.', 'Mr.', 'Mr. & Mrs.',
+        'Mr. and Mrs.', 'Mrs.', 'Msgr.', 'Prof.', 'Professor', 'Rev.',
+        'Reverend', 'Sir', 'Sister', 'The Hon.', 'The Lady.', 'The Lord',
+        'The Rt. Hon.'
+      ],
+      organization: [
+        'Fa.', 'P.T.', 'P.T. Tbk.', 'U.D.'
+      ],
+      before:'\\A', after:ADFIX_JOINERS
+    },
+    suffix: {
+      person: [
+        'C.I.S.S.P.', 'B.Tech.', 'D.Phil.', 'B.Eng.', 'C.F.A.', 'D.B.E.', 'D.D.S.', 'Eng.D.', 'M.B.A.', 'M.B.E.',
+        'M.E.P.', 'M.Eng.', 'M.S.P.', 'O.B.E.', 'P.M.C.', 'P.M.P.', 'P.S.P.', 'B.Ed.', 'B.Sc.', 'Ed.D.', 'LL.B.',
+        'LL.D.', 'LL.M.', 'M.Ed.', 'M.Sc.', 'Ph.D.', 'B.A.', 'Esq.', 'J.D.', 'K.C.', 'M.A.', 'M.D.', 'M.P.', 'O.K.',
+        'P.A.', 'Q.C.', 'III', 'Jr.', 'Sr.', 'II', 'IV', 'V'
+      ],
+      organization: [
+        'S. de R.L. de C.V.', 'S.A.P.I. de C.V.', 'y. Cía. S. en C.', 'Private Limited', 'S.M. Pte. Ltd.',
+        'Cía. S. C. A.', 'y. Cía. S. C.', 'S.A. de C.V.', 'spol. s.r.o.', '(Pty.) Ltd.', '(Pvt.) Ltd.', 'A.D.S.I.Tz.',
+        'S.p. z.o.o.', '(Pvt.)Ltd.', 'akc. spol.', 'Cía. Ltda.', 'E.B.V.B.A.', 'P. Limited', 'S. de R.L.', 'S.I.C.A.V.',
+        'S.P.R.L.U.', 'А.Д.С.И.Ц.', '(P.) Ltd.', 'C. por A.', 'Comm.V.A.', 'Ltd. Şti.', 'Plc. Ltd.', 'Pte. Ltd.',
+        'Pty. Ltd.', 'Pvt. Ltd.', 'Soc. Col.', 'A.M.B.A.', 'A.S.B.L.', 'A.V.E.E.', 'B.V.B.A.', 'B.V.I.O.', 'C.V.B.A.',
+        'C.V.O.A.', 'E.E.I.G.', 'E.I.R.L.', 'E.O.O.D.', 'E.U.R.L.', 'F.M.B.A.', 'G.m.b.H.', 'Ges.b.R.', 'I.L.L.C.',
+        'K.G.a.A.', 'L.L.L.P.', 'Ltd. Co.', 'Ltd. Co.', 'M.E.P.E.', 'n.y.r.t.', 'O.V.E.E.', 'P.E.E.C.', 'P.L.L.C.',
+        'P.L.L.C.', 'S. en C.', 'S.a.p.a.', 'S.A.R.L.', 'S.à.R.L.', 'S.A.S.U.', 'S.C.e.I.', 'S.C.O.P.', 'S.C.p.A.',
+        'S.C.R.I.', 'S.C.R.L.', 'S.M.B.A.', 'S.P.R.L.', 'Е.О.О.Д.', 'and Co.', 'Comm.V.', 'Limited', 'P. Ltd.',
+        'Part.G.', 'Sh.p.k.', '&. Co.', 'C.X.A.', 'd.n.o.', 'd.o.o.', 'E.A.D.', 'e.h.f.', 'E.P.E.', 'E.S.V.', 'F.C.P.',
+        'F.I.E.', 'G.b.R.', 'G.I.E.', 'G.M.K.', 'G.S.K.', 'H.U.F.', 'K.D.A.', 'k.f.t.', 'k.h.t.', 'k.k.t.', 'L.L.C.',
+        'L.L.P.', 'o.h.f.', 'O.H.G.', 'O.O.D.', 'O.y.j.', 'p.l.c.', 'P.S.U.', 'S.A.E.', 'S.A.S.', 'S.C.A.', 'S.C.E.',
+        'S.C.S.', 'S.E.M.', 'S.E.P.', 's.e.s.', 'S.G.R.', 'S.N.C.', 'S.p.A.', 'S.P.E.', 'S.R.L.', 's.r.o.', 'Unltd.',
+        'V.O.F.', 'V.o.G.', 'v.o.s.', 'V.Z.W.', 'z.r.t.', 'А.А.Т.', 'Е.А.Д.', 'З.А.Т.', 'К.Д.А.', 'О.О.Д.', 'Т.А.А.',
+        '股份有限公司', 'Ap.S.', 'Corp.', 'ltda.', 'Sh.A.', 'st.G.', 'Ultd.', 'a.b.', 'A.D.', 'A.E.', 'A.G.', 'A.S.',
+        'A.Ş.', 'A.y.', 'B.M.', 'b.t.', 'B.V.', 'C.A.', 'C.V.', 'd.d.', 'e.c.', 'E.E.', 'e.G.', 'E.I.', 'E.P.', 'E.T.',
+        'E.U.', 'e.v.', 'G.K.', 'G.P.', 'h.f.', 'Inc.', 'K.D.', 'K.G.', 'K.K.', 'k.s.', 'k.v.', 'K.y.', 'L.C.', 'L.P.',
+        'Ltd.', 'N.K.', 'N.L.', 'N.V.', 'O.E.', 'O.G.', 'O.Ü.', 'O.y.', 'P.C.', 'p.l.', 'Pty.', 'PUP.', 'Pvt.', 'r.t.',
+        'S.A.', 'S.D.', 'S.E.', 's.f.', 'S.L.', 'S.P.', 'S.s.', 'T.K.', 'T.Ü.', 'U.Ü.', 'Y.K.', 'А.Д.', 'І.П.', 'К.Д.',
+        'ПУП.', 'С.Д.', 'בע"מ', '任意組合', '匿名組合', '合同会社', '合名会社', '合資会社', '有限会社', '有限公司', '株式会社',
+        'A/S', 'G/S', 'I/S', 'K/S', 'P/S'
+      ],
+      before:ADFIX_JOINERS, after:'\\z'
+    }
+  }
+
+  ADFIX_PATTERNS = {}
+
+  [:prefix, :suffix].each do |adfix_type|
+    patterns  = {}
+    adfix     = ADFIXES[adfix_type]
+
+    [:person, :organization].each do |contact_type|
+      with_optional_spaces    = adfix[contact_type].map { |p| p.gsub(ASCII_SPACE,' *') }
+      pattern_string          = with_optional_spaces.join('|').gsub('.', '\.*')
+      patterns[contact_type]  = /#{adfix[:before]}\(*(?:#{pattern_string})\)*#{adfix[:after]}/i
+    end
+
+    ADFIX_PATTERNS[adfix_type] = patterns
+  end
+end

data/lib/name_tamer/version.rb

@@ -0,0 +1,3 @@
+class NameTamer
+  VERSION = "0.0.0"
+end

data/name-tamer.gemspec

@@ -0,0 +1,27 @@
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'name_tamer/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = 'name-tamer'
+  spec.version       = NameTamer::VERSION
+  spec.authors       = ['Xenapto']
+  spec.email         = ['developers@xenapto.com']
+  spec.description   = %q{Useful methods for taming names}
+  spec.summary       = %q{Example: NameTamer['Mr. John Q. Smith III, MD'].simple_name # => John Smith}
+  spec.homepage      = 'https://github.com/Xenapto/name-tamer'
+  spec.license       = 'MIT'
+
+  spec.files         = `git ls-files`.split($/)
+  spec.executables   = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
+  spec.test_files    = spec.files.grep(%r{^(test|spec|features|coverage)/})
+  spec.require_paths = ['lib']
+
+  spec.add_runtime_dependency 'activesupport', '~> 3'
+
+  spec.add_development_dependency 'bundler', '~> 1'
+  spec.add_development_dependency 'rake', '~> 10'
+  spec.add_development_dependency 'rspec', '~> 2'
+  spec.add_development_dependency 'gem-release', '~> 0'
+  spec.add_development_dependency 'simplecov', '~> 0'
+end

data/spec/name_tamer_spec.rb

@@ -0,0 +1,166 @@
+# encoding: utf-8
+require 'spec_helper'
+require 'name_tamer'
+
+describe NameTamer do
+  let(:names) do
+    [
+      { n:'John Smith', t: :person, nn:'John Smith', sn:'John Smith', s:'john-smith' },
+      { n:'JOHN SMITH', t: :person, nn:'John Smith', sn:'John Smith', s:'john-smith' },
+      { n:'john smith', t: :person, nn:'John Smith', sn:'John Smith', s:'john-smith' },
+      { n:'Smith, John', t: :person, nn:'John Smith', sn:'John Smith', s:'john-smith' },
+      { n:'John    Smith', t: :person, nn:'John Smith', sn:'John Smith', s:'john-smith' },
+      { n:'Smith, John', nn:'John Smith', sn:'John Smith', s:'john-smith' },
+      { n:'John J Smith', t: :person, nn:'John J Smith', sn:'John Smith', s:'john-smith' },
+      { n:'John J. Smith', t: :person, nn:'John J. Smith', sn:'John Smith', s:'john-smith' },
+      { n:'SMITH, Mr John J.R.', t: :person, nn:'John J.R. Smith', sn:'John Smith', s:'john-smith' },
+      { n:' SMITH,  Mr John J. R.  ', t: :person, nn:'John J.R. Smith', sn:'John Smith', s:'john-smith' },
+      { n:'SMITH, Mr John J.R.', nn:'John J.R. Smith', sn:'John Smith', s:'john-smith' },
+      { n:'Mr John J.R. SMITH JD', t: :person, nn:'John J.R. SMITH', sn:'John SMITH', s:'john-smith' },
+      { n:'Mr John J.R. SMITH III,JD', t: :person, nn:'John J.R. SMITH', sn:'John SMITH', s:'john-smith' },
+      { n:'Mr John J.R. SMITH JD', nn:'John J.R. SMITH', sn:'John SMITH', s:'john-smith' },
+      { n:'Mr Jean-Michel SMITH JD', t: :person, nn:'Jean-Michel SMITH', sn:'Jean-Michel SMITH', s:'jean-michel-smith' },
+      { n:'Mr Jean Michel-SMITH JD', nn:'Jean Michel-SMITH', sn:'Jean Michel-SMITH', s:'jean-michel-smith' },
+      { n:'Dr Martha Lane Fox Ph.D', nn:'Martha Lane Fox', sn:'Martha Lane Fox', s:'martha-lane-fox' },
+      { n:'Lane Fox Ph.D, Dr Martha', t: :person, nn:'Martha Lane Fox', sn:'Martha Lane Fox', s:'martha-lane-fox' },
+      { n:'Baroness Lane-Fox of Lewisham', t: :person, nn:'Lane-Fox of Lewisham', sn:'Lane-Fox of Lewisham', s:'lane-fox-of-lewisham' },
+      { n:'MACDONALDS LLC', nn:'MacDonalds', sn:'MacDonalds', s:'macdonalds' },
+      { n:'MACDONALDS LLC', t: :organization, nn:'MacDonalds', sn:'MacDonalds', s:'macdonalds' },
+      { n:'macdonalds', t: :organization, nn:'macdonalds', sn:'macdonalds', s:'macdonalds' },
+      { n:'Pugh, Pugh, Barney McGrew, Cuthbert, Dibble & Grub LLP', t: :organization, nn:'Pugh, Pugh, Barney McGrew, Cuthbert, Dibble & Grub', sn:'Pugh, Pugh, Barney McGrew, Cuthbert, Dibble and Grub', s:'pugh-pugh-barney-mcgrew-cuthbert-dibble-and-grub' },
+      { n:'Pugh, Pugh, Barney McGrew, Cuthbert, Dibble & Grub LLP', nn:'Pugh, Pugh, Barney McGrew, Cuthbert, Dibble & Grub', sn:'Pugh, Pugh, Barney McGrew, Cuthbert, Dibble and Grub', s:'pugh-pugh-barney-mcgrew-cuthbert-dibble-and-grub' },
+      { n:'Pugh, Pugh, Barney McGrew, Cuthbert, Dibble & Grub LLP', nn:'Pugh, Pugh, Barney McGrew, Cuthbert, Dibble & Grub', sn:'Pugh, Pugh, Barney McGrew, Cuthbert, Dibble and Grub', s:'pugh-pugh-barney-mcgrew-cuthbert-dibble-and-grub' },
+      { n:'K.V.A. Instruments y Cía S. en C.', nn:'K.V.A. Instruments', sn:'KVA Instruments', s:'kva-instruments' },
+      { n:'K. V. A. Instruments y Cía S. en C.', nn:'K.V.A. Instruments', sn:'KVA Instruments', s:'kva-instruments' },
+      { n:'J.P. Rangaswami', nn:'J.P. Rangaswami', sn:'JP Rangaswami', s:'jp-rangaswami' },
+      { n:'J. P. Rangaswami', nn:'J.P. Rangaswami', sn:'JP Rangaswami', s:'jp-rangaswami' },
+      { n:'J P Rangaswami', nn:'J.P. Rangaswami', sn:'JP Rangaswami', s:'jp-rangaswami' },
+      { n:'JP Rangaswami', nn:'JP Rangaswami', sn:'JP Rangaswami', s:'jp-rangaswami' },
+      { n:'Audrey fforbes', nn:'Audrey fforbes', sn:'Audrey fforbes', s:'audrey-fforbes' },
+      { n:'J. Arthur Rank', t: :person, nn:'J. Arthur Rank', sn:'Arthur Rank', s:'arthur-rank' },
+      { n:'PHILIP NG', t: :person, nn:'Philip Ng', sn:'Philip Ng', s:'philip-ng' },
+      { n:'Super R&D', nn:'Super R&D', sn:'Super R and D', s:'super-r-and-d' },
+      { n:'Harry Dean Stanton', t: :person, nn:'Harry Dean Stanton', sn:'Harry Stanton', s:'harry-stanton' },
+      { n:'Union Square Ventures', t: :organization, nn:'Union Square Ventures', sn:'Union Square Ventures', s:'union-square-ventures' },
+      { n:'J Arthur Rank Inc.', t: :organization, nn:'J Arthur Rank', sn:'J Arthur Rank', s:'j-arthur-rank' },
+      { n:'Jean VAN DER VELDE', t: :person, nn:'Jean VAN DER VELDE', sn:'Jean VAN DER VELDE', s:'jean-van-der-velde' },
+      { n:'Al Capone', t: :person, nn:'Al Capone', sn:'Al Capone', s:'al-capone' },
+      { n:'Fahd al-Saud', t: :person, nn:'Fahd al-Saud', sn:'Fahd al-Saud', s:'fahd-al-saud' },
+      { n:'Mehmet al Auouiby', t: :person, nn:'Mehmet al Auouiby', sn:'Mehmet al Auouiby', s:'mehmet-al-auouiby' },
+      { n:'Macquarie Bank', t: :organization, nn:'Macquarie Bank', sn:'Macquarie Bank', s:'macquarie-bank' },
+      { n:"COMMEDIA DELL'ARTE", t: :organization, nn:"Commedia dell'Arte", sn:"Commedia dell'Arte", s:'commedia-dellarte' },
+      { n:'Della Smith', t: :person, nn:'Della Smith', sn:'Della Smith', s:'della-smith' },
+      { n:'Antonio DELLA MONTEVERDE', nn:'Antonio DELLA MONTEVERDE', sn:'Antonio DELLA MONTEVERDE', s:'antonio-della-monteverde' },
+      { n:'Tony St Clair', t: :person, nn:'Tony St Clair', sn:'Tony St Clair', s:'tony-st-clair' },
+      { n:'Seamus O\'Malley', t: :person, nn:'Seamus O\'Malley', sn:'Seamus O\'Malley', s:'seamus-omalley' },
+      { n:'SeedCamp', t: :organization, nn:'SeedCamp', sn:'SeedCamp', s:'seedcamp' },
+      { n:'Peter Van Der Auwera', t: :person, nn:'Peter Van Der Auwera', sn:'Peter Van Der Auwera', s:'peter-van-der-auwera' },
+      { n:'VAN DER AUWERA, Peter', t: :person, nn:'Peter van der Auwera', sn:'Peter van der Auwera', s:'peter-van-der-auwera' },
+      { n:'Li Fan', t: :person, nn:'Li Fan', sn:'Li Fan', s:'li-fan' },
+      { n:'Fan Li', t: :person, nn:'Fan Li', sn:'Fan Li', s:'fan-li' },
+      { n:'Levi Strauss & Co.', nn:'Levi Strauss', sn:'Levi Strauss', s:'levi-strauss' },
+      { n:'Standard & Poor\'s', t: :organization, nn:'Standard & Poor\'s', sn:'Standard and Poor\'s', s:'standard-and-poors' },
+      { n:'I B M Services', t: :organization, nn:'I.B.M. Services', sn:'IBM Services', s:'ibm-services' },
+      { n:'Sean Park DDS', t: :person, nn:'Sean Park', sn:'Sean Park', s:'sean-park' },
+      { n:'SEAN MACLISE PARK', t: :person, nn:'Sean Maclise Park', sn:'Sean Park', s:'sean-park' },
+      { n:'AJ Hanna', t: :person, nn:'AJ Hanna', sn:'AJ Hanna', s:'aj-hanna' },
+      { n:'Free & Clear', t: :organization, nn:'Free & Clear', sn:'Free and Clear', s:'free-and-clear' },
+      { n:'Adam D\'ANGELO', t: :person, nn:'Adam D\'ANGELO', sn:'Adam D\'ANGELO', s:'adam-dangelo' },
+      { n:'MACKENZIE, Doug', t: :person, nn:'Doug Mackenzie', sn:'Doug Mackenzie', s:'doug-mackenzie' },
+      { n:'Up + Down', t: :organization, nn:'Up + Down', sn:'Up plus Down', s:'up-plus-down' },
+      { n:'San Francisco Ltd', t: :organization, nn:'San Francisco', sn:'San Francisco', s:'san-francisco' },
+      { n:'AT&T', t: :organization, nn:'At&T', sn:'At and T', s:'at-and-t' },
+      { n:'SMITH, John, Jr.', t: :person, nn:'John Smith', sn:'John Smith', s:'john-smith' },
+      { n:'I Heart Movies', t: :organization, nn:'I Heart Movies', sn:'I Heart Movies', s:'i-heart-movies' },
+      { n:'Y Combinator', t: :organization, nn:'Y Combinator', sn:'Y Combinator', s:'y-combinator' },
+      { n:'Ben\'s 10 Hens', t: :organization, nn:'Ben\'s 10 Hens', sn:'Ben\'s 10 Hens', s:'bens-10-hens' },
+      { n:'Elazer Edelman, MD , PhD', t: :person, nn:'Elazer Edelman', sn:'Elazer Edelman', s:'elazer-edelman' },
+      { n:'Judith M. O\'Brien', t: :person, nn:'Judith M. O\'Brien', sn:'Judith O\'Brien', s:'judith-obrien' },
+      { n:'MORRISON, Van', t: :person, nn:'Van Morrison', sn:'Van Morrison', s:'van-morrison' },
+      { n:'i/o Ventures', t: :organization, nn:'i/o Ventures', sn:'i/o Ventures', s:'io-ventures' },
+      { n:'C T Corporation System', t: :person, nn:'C.T. Corporation System', sn:'CT Corporation System', s:'ct-corporation-system'},
+      { n:'C.T. Corporation System', t: :person, nn:'C.T. Corporation System', sn:'CT Corporation System', s:'ct-corporation-system'},
+      { n:'CT Corporation System', t: :person, nn:'CT Corporation System', sn:'CT Corporation System', s:'ct-corporation-system'},
+      { n:'Corporation Service Company', t: :person, nn:'Corporation Service Company', sn:'Corporation Service Company', s:'corporation-service-company'},
+      { n:'Kurshuni,Inc.', t: :organization, nn:'Kurshuni', sn:'Kurshuni', s:'kurshuni' },
+      { n:'Cellular Inc-LLC', t: :organization, nn:'Cellular', sn:'Cellular', s:'cellular' },
+      { n:'Emtec (AZ) Limited', t: :organization, nn:'Emtec (AZ)', sn:'Emtec (AZ)', s:'emtec-az' },
+      { n:'Emtec (LLC) Limited', t: :organization, nn:'Emtec', sn:'Emtec', s:'emtec' },
+      { n:'Emtec (XYZ LLC) Limited', t: :organization, nn:'Emtec (XYZ)', sn:'Emtec (XYZ)', s:'emtec-xyz' },
+      { n:'Tao Ma', t: :person, nn:'Tao', sn:'Tao', s:'tao' }, # Unfortunate but we can't distinguish between Ma and M.A.
+      { n:'(Mr.) Courtney J. Miller, J.D., LL.M.', t: :person, nn:'Courtney J. Miller', sn:'Courtney Miller', s:'courtney-miller' },
+      { n:'(Mr Woo) The Window Cleaner', t: :person, nn:'(Woo) The Window Cleaner', sn:'(Woo) Cleaner', s:'woo-cleaner'},
+      { n:'DOMINIC MACMURDO', t: :person, nn:'Dominic MacMurdo', sn:'Dominic MacMurdo', s:'dominic-macmurdo' },
+      { n:'DOMINIC MACEDO', t: :person, nn:'Dominic Macedo', sn:'Dominic Macedo', s:'dominic-macedo' },
+      { n:'DOMINIC MACDONALD', t: :person, nn:'Dominic MacDonald', sn:'Dominic MacDonald', s:'dominic-macdonald' },
+      { n:'AGUSTA DO ROMEIRO', t: :person, nn:'Agusta do Romeiro', sn:'Agusta do Romeiro', s:'agusta-do-romeiro' },
+      { n:'CARLOS DOS SANTOS', t: :person, nn:'Carlos dos Santos', sn:'Carlos dos Santos', s:'carlos-dos-santos' },
+      { n:'유정 신', t: :organization, nn:'유정 신', sn:'유정 신', s:'유정-신' },
+      { n:'xxx%52zzz', t: :organization, nn:'xxx%52zzz', sn:'xxx%52zzz', s:'xxxrzzz' },
+      { n:'Евгений Болотнов', t: :organization, nn:'Евгений Болотнов', sn:'Евгений Болотнов', s:'Евгений-Болотнов' },
+      { n:'김태성', t: :organization, nn:'김태성', sn:'김태성', s:'김태성' },
+      { n:'ゴルフスタジアム', t: :organization, nn:'ゴルフスタジアム', sn:'ゴルフスタジアム', s:'ゴルフスタジアム' },
+      { n:'我摘', t: :organization, nn:'我摘', sn:'我摘', s:'我摘' },
+      { n:'Καρατζάς Στέφανος', t: :organization, nn:'Καρατζάς Στέφανος', sn:'Καρατζάς Στέφανος', s:'Καρατζάς-Στέφανος' },
+      { n:'โชติวัน วัฒนลาภ', t: :organization, nn:'โชติวัน วัฒนลาภ', sn:'โชติวัน วัฒนลาภ', s:'โชติวัน-วัฒนลาภ' },
+      { n:'張 續寶', t: :organization, nn:'張 續寶', sn:'張 續寶', s:'張-續寶' },
+      { n:'Юрий Гайдук', t: :organization, nn:'Юрий Гайдук', sn:'Юрий Гайдук', s:'Юрий-Гайдук' },
+      { n:'☣ ©Ʀѱ∏†ʘ Σɏ§†℈Ϻ ☣', t: :organization, nn:'☣ ©Ʀѱ∏†ʘ Σɏ§†℈Ϻ ☣', sn:'☣ ©Ʀѱ∏†ʘ Σɏ§†℈Ϻ ☣', s:'☣-©Ʀѱ∏†ʘ-Σɏ§†℈Ϻ-☣' },
+      { n:'♠ KlasikB0i ♠', t: :organization, nn:'♠ KlasikB0i ♠', sn:'♠ KlasikB0i ♠', s:'♠-klasikb0i-♠' },
+      { n:'* Shorusan *', t: :organization, nn:'* Shorusan *', sn:'* Shorusan *', s:'shorusan' },
+      { n:'项目谷', t: :organization, nn:'项目谷', sn:'项目谷', s:'项目谷' },
+      { n:'ООО "Инновационные полимерные адгезивы"', t: :organization, nn:'ООО "Инновационные полимерные адгезивы"', sn:'ООО "Инновационные полимерные адгезивы"', s:'ООО-Инновационные-полимерные-адгезивы' },
+      { n:'عبدالله ...', t: :organization, nn:'عبدالله ...', sn:'عبدالله ...', s:'عبدالله' },
+      { n:'กมลชนก ทิศไธสง', t: :organization, nn:'กมลชนก ทิศไธสง', sn:'กมลชนก ทิศไธสง', s:'กมลชนก-ทิศไธสง' },
+      { n:'יוֹ אָב', t: :organization, nn:'יוֹ אָב', sn:'יוֹ אָב', s:'יוֹ-אָב' },
+      { n:'יגאל נימני', t: :organization, nn:'יגאל נימני', sn:'יגאל נימני', s:'יגאל-נימני' },
+      { n:'ניסים דניאלי', t: :organization, nn:'ניסים דניאלי', sn:'ניסים דניאלי', s:'ניסים-דניאלי' },
+      { n:'مساء الخير', t: :organization, nn:'مساء الخير', sn:'مساء الخير', s:'مساء-الخير' },
+      { n:'محمود ياسر', t: :organization, nn:'محمود ياسر', sn:'محمود ياسر', s:'محمود-ياسر' },
+      { n:'קובי ביטר', t: :organization, nn:'קובי ביטר', sn:'קובי ביטר', s:'קובי-ביטר' },
+      { n:'الملاك الحارس', t: :organization, nn:'الملاك الحارس', sn:'الملاك الحارس', s:'الملاك-الحارس' },
+      { n:'কবির হাসান', t: :organization, nn:'কবির হাসান', sn:'কবির হাসান', s:'কবির-হাসান' }
+    ]
+  end
+
+  it "makes a slug from #{name}" do
+    names.each do |name_data|
+      name = name_data[:n]
+      NameTamer[name, contact_type:name_data[:t]].slug.should == name_data[:s]
+    end
+  end
+
+  it "makes a nice name from #{name}" do
+    names.each do |name_data|
+      name      = name_data[:n]
+      nice_name = NameTamer[name, contact_type:name_data[:t]].nice_name
+
+      nice_name.should == name_data[:nn]
+    end
+  end
+
+  it "makes a searchable name from #{name}" do
+    names.each do |name_data|
+      name = name_data[:n]
+      NameTamer[name, contact_type:name_data[:t]].search_name.should == name_data[:sn]
+    end
+  end
+end
+
+describe 'contact type inference' do
+  it 'infers that "Mr. John Smith" is a person' do
+    NameTamer['Mr. John Smith'].contact_type.should eq(:person)
+  end
+
+  it 'infers that "Di Doo Doo d.o.o." is an organization' do
+    NameTamer['Di Doo Doo d.o.o.'].contact_type.should eq(:organization)
+  end
+
+  it 'infers that "DiDooDoo" is an organization' do
+    NameTamer['DiDooDoo'].contact_type.should eq(:organization)
+  end
+
+  it 'infers that "John Smith" is a person' do
+    NameTamer['John Smith'].contact_type.should eq(:person)
+  end
+end

data/spec/spec_helper.rb

@@ -0,0 +1,16 @@
+# Initialize simplecov for coverage report.
+require 'simplecov'
+SimpleCov.start
+
+RSpec.configure do |config|
+ # Run specs in random order to surface order dependencies. If you find an
+  # order dependency and want to debug it, you can fix the order by providing
+  # the seed, which is printed after each run.
+  #     --seed 1234
+  config.order = "random"
+
+  # Manually-added
+  config.color_enabled = true
+  config.tty = true
+  config.formatter = :documentation
+end

metadata

@@ -0,0 +1,146 @@
+--- !ruby/object:Gem::Specification
+name: name-tamer
+version: !ruby/object:Gem::Version
+  version: 0.0.0
+platform: ruby
+authors:
+- Xenapto
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2014-05-30 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: activesupport
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '3'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '3'
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '10'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '10'
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '2'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '2'
+- !ruby/object:Gem::Dependency
+  name: gem-release
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: simplecov
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '0'
+description: Useful methods for taming names
+email:
+- developers@xenapto.com
+executables:
+- name-tamer
+extensions: []
+extra_rdoc_files: []
+files:
+- .env
+- .gitignore
+- .ruby-version
+- Gemfile
+- Gemfile.lock
+- LICENSE
+- README.md
+- Rakefile
+- bin/name-tamer
+- lib/name_tamer.rb
+- lib/name_tamer/version.rb
+- name-tamer.gemspec
+- spec/name_tamer_spec.rb
+- spec/spec_helper.rb
+homepage: https://github.com/Xenapto/name-tamer
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.2.2
+signing_key: 
+specification_version: 4
+summary: ! 'Example: NameTamer[''Mr. John Q. Smith III, MD''].simple_name # => John
+  Smith'
+test_files:
+- spec/name_tamer_spec.rb
+- spec/spec_helper.rb