full-name-splitter 0.1.0

data/README.mdown

@@ -0,0 +1,58 @@
+*FullNameSplitter* splits full name into first and last name considering name prefixes and initials
+
+If you include the module it requires attribute accessors first\_name and last\_name and adds #full\_name, #full\_name= to the class
+
+For example
+
+    require 'full_name_splitter'
+    
+    class Incognito
+      include FullNameSplitter
+      attr_accessor :first_name, :last_name
+    end
+    
+    incognito = Incognito.new :full_name => "George H. W. Bush"
+    incognito.first_name # => "George H. W."
+    incognito.last_name  # => "Bush"
+
+    incognito = Incognito.new :full_name => "Kevin J. O'Connor"
+    incognito.first_name # => "Kevin J."
+    incognito.last_name  # => "O'Connor"
+
+    incognito = Incognito.new :full_name => "Thomas G. Della Fave"
+    incognito.first_name # => "Thomas G."
+    incognito.last_name  # => "Della Fave"
+
+    incognito = Incognito.new :full_name => "Gabriel Van Helsing"
+    incognito.first_name # => "Gabriel"
+    incognito.last_name  # => "Van Helsing"
+
+If full name isn't complete *FullNameSplitter* tries to split partially
+
+    incognito = Incognito.new :full_name => "George W."
+    incognito.first_name # => "George W."
+    incognito.last_name  # => nil
+
+    incognito = Incognito.new :full_name => "George"
+    incognito.first_name # => "George"
+    incognito.last_name  # => nil
+
+    incognito = Incognito.new :full_name => "Van Helsing"
+    incognito.first_name # => nil
+    incognito.last_name  # => "Van Helsing"
+
+    incognito = Incognito.new :full_name => "d'Artagnan"
+    incognito.first_name # => nil
+    incognito.last_name  # => "d'Artagnan"
+
+For other examples see _spec/lib/full\_name\_splitter\_spec.rb_
+
+Also you can use splitter directly by calling module function FullNameSplitter::split
+
+    FullNameSplitter.split("Juan Martín de la Cruz Gómez")  # => ["Juan Martín", "de la Cruz Gómez"]
+    FullNameSplitter.split("Ludwig Mies van der Rohe")      # => ["Ludwig", "Mies van der Rohe"]
+    
+If the lib can't split a name correctly, it is possible to split by comma
+
+    FullNameSplitter.split("John Quincy Adams")   # => ["John Quincy", "Adams"]
+    FullNameSplitter.split("John, Quincy Adams")  # => ["John", "Quincy Adams"]

data/Rakefile

@@ -0,0 +1,26 @@
+require "rubygems"
+require "spec/rake/spectask"
+
+task :default => :spec
+
+desc "Run all specification examples"
+Spec::Rake::SpecTask.new do |t|
+  t.spec_opts = ['--options', "spec/spec.opts"]
+  t.spec_files = FileList['spec/**/*_spec.rb']
+end
+
+
+begin
+  require 'jeweler'
+  Jeweler::Tasks.new do |gemspec|
+    gemspec.name = "full-name-splitter"
+    gemspec.summary = "*FullNameSplitter* splits full name into first and last name considering name prefixes and initials"
+    gemspec.description = ""
+    gemspec.email = "trevor@trevorcreech.com"
+    gemspec.homepage = "http://github.com/zedlander/full-name-splitter"
+    gemspec.authors = ["Pavel Gorbokon", "Trevor Creech"]
+  end
+  Jeweler::GemcutterTasks.new
+rescue LoadError
+  puts "Jeweler not available. Install it with: gem install jeweler"
+end

data/VERSION

@@ -0,0 +1 @@
+0.1.0

data/features/partial_split.feature

@@ -0,0 +1,18 @@
+Feature: Split partial name
+  In order to split full name into first name and last name
+  As a full name holder
+  I want to get first name and last name
+  
+  Scenario Outline: Partial Names
+    Given Incognito instance object
+    When I assign <full_name> to incognito
+    Then he should have partial <first_name> or partial <last_name>
+
+    Examples:
+      | full_name     | first_name      | last_name       |
+      | Van Helsing   | nil             | "Van Helsing"   |
+      | d'Artagnan    | nil             | "d'Artagnan"    |
+      | O'Connor      | nil             | "O'Connor"      |
+      | George        | "George"        | nil             |
+      | Kevin J.      | "Kevin J."      | nil             |
+      | George H. W.  | "George H. W."  | nil             |

data/features/split.feature

@@ -0,0 +1,93 @@
+Feature: Split given full name
+  In order to split full name into first name and last name
+  As a full name holder
+  I want to get first name and last name
+  
+  Scenario Outline: American/European
+    Given Incognito instance object
+    When I assign <full_name> to incognito
+    Then he should have a <first_name> and a <last_name>
+
+    Examples:
+      | full_name                                 | first_name        |last_name                        |
+      | John Smith                                | John              | Smith                           |
+      | Kevin J. O'Connor                         | Kevin J.          | O'Connor                        |
+      | George W Bush                             | George W          | Bush                            |
+      | George H. W. Bush                         | George H. W.      | Bush                            |
+      | James K. Polk                             | James K.          | Polk                            |
+      | William Henry Harrison                    | William Henry     | Harrison                        |
+      | John Quincy Adams                         | John Quincy       | Adams                           |
+      | John Quincy                               | John              | Quincy                          |
+
+    Scenario Outline: French
+      Given Incognito instance object
+      When I assign <full_name> to incognito
+      Then he should have a <first_name> and a <last_name>
+
+      Examples:
+        | full_name                                 | first_name        | last_name                       |
+        | Pierre de Montesquiou                     | Pierre            | de Montesquiou                  |
+        | Charles d'Artagnan                        | Charles           | d'Artagnan                      |
+        | Anne du Bourg                             | Anne              | du Bourg                        |
+
+    Scenario Outline: Italian
+      Given Incognito instance object
+      When I assign <full_name> to incognito
+      Then he should have a <first_name> and a <last_name>
+
+      Examples:
+        | full_name                                 | first_name        | last_name                       |
+        | Maria del Carmen Menendez                 | Maria             | del Carmen Menendez             |
+        | Alessandro Del Piero                      | Alessandro        | Del Piero                       |
+        | Thomas G. Della Fave                      | Thomas G.         | Della Fave                      |
+        | Federica Pellegrini                       | Federica          | Pellegrini                      |
+        | Leonardo da Vinci                         | Leonardo          | da Vinci                        |
+        | Alberto Del Sole                          | Alberto           | Del Sole                        |
+        | Adriano Dello Spavento                    | Adriano           | Dello Spavento                  |
+        | Luca Delle Fave                           | Luca              | Delle Fave                      |
+        | Francesca Della Valle                     | Francesca         | Della Valle                     |
+        | Guido Delle Colonne                       | Guido             | Delle Colonne                   |
+        | Tomasso D'Arco                            | Tomasso           | D'Arco                          |
+
+    Scenario Outline: German
+      Given Incognito instance object
+      When I assign <full_name> to incognito
+      Then he should have a <first_name> and a <last_name>
+
+      Examples:
+        | full_name                                 | first_name        | last_name                       |
+        | Ludwig Mies van der Rohe                  | Ludwig            | Mies van der Rohe               |
+        | Johann Wolfgang von Goethe                | Johann Wolfgang   | von Goethe                      |
+
+    Scenario Outline: Dutch
+      Given Incognito instance object
+      When I assign <full_name> to incognito
+      Then he should have a <first_name> and a <last_name>
+
+      Examples:
+        | full_name                                 | first_name        | last_name                       |
+        | Gabriel Van Helsing                       | Gabriel           | Van Helsing                     |
+        | Johan de heer Van Kampen                  | Johan             | de heer Van Kampen              |
+        | Han Van De Casteele                       | Han               | Van De Casteele                 |
+        | Han Vande Casteele                        | Han               | Vande Casteele                  |
+
+    Scenario Outline: Spanish
+      Given Incognito instance object
+      When I assign <full_name> to incognito
+      Then he should have a <first_name> and a <last_name>
+
+      Examples:
+        | full_name                                 | first_name        | last_name                       |
+        | Juan Martín de la Cruz Gómez              | Juan Martín       | de la Cruz Gómez                |
+        | Javier Reyes de la Barrera                | Javier            | Reyes de la Barrera             |
+        | Rosa María Pérez Martínez Vda. de la Cruz | Rosa María        | Pérez Martínez Vda. de la Cruz  |
+
+    Scenario Outline: Asian
+      Given Incognito instance object
+      When I assign <full_name> to incognito
+      Then he should have a <first_name> and a <last_name>
+
+      Examples:
+        | full_name                                 | first_name        | last_name                       |
+        | Jaazaniah ben Shaphan                     | Jaazaniah         | ben Shaphan                     |
+        | Noda' bi-Yehudah                          | Noda'             | bi-Yehudah                      |

data/features/step_definitions/split_steps.rb

@@ -0,0 +1,17 @@
+Given /^Incognito instance object$/ do
+  @incognito = Incognito.new
+end
+
+When /^I assign (.+) to incognito$/ do |full_name|
+ @incognito.full_name = full_name
+end
+
+Then /^he should have a (.+) and a (.+)$/ do |first_name, last_name|
+  @incognito.first_name.should == first_name
+  @incognito.last_name.should  == last_name
+end
+
+Then /^he should have partial (.+) or partial (.+)$/ do |first_name, last_name|
+  @incognito.first_name.inspect.should == first_name
+  @incognito.last_name.inspect.should  == last_name
+end

data/features/support/env.rb

@@ -0,0 +1,6 @@
+require File.expand_path(File.dirname(__FILE__) + '/../../spec/spec_helper.rb')
+
+class Incognito
+  include FullNameSplitter
+  attr_accessor :first_name, :last_name
+end

data/full-name-splitter.gemspec

@@ -0,0 +1,52 @@
+# Generated by jeweler
+# DO NOT EDIT THIS FILE DIRECTLY
+# Instead, edit Jeweler::Tasks in Rakefile, and run the gemspec command
+# -*- encoding: utf-8 -*-
+
+Gem::Specification.new do |s|
+  s.name = %q{full-name-splitter}
+  s.version = "0.1.0"
+
+  s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
+  s.authors = ["Pavel Gorbokon", "Trevor Creech"]
+  s.date = %q{2010-09-10}
+  s.description = %q{}
+  s.email = %q{trevor@trevorcreech.com}
+  s.extra_rdoc_files = [
+    "README.mdown"
+  ]
+  s.files = [
+    "README.mdown",
+     "Rakefile",
+     "VERSION",
+     "features/partial_split.feature",
+     "features/split.feature",
+     "features/step_definitions/split_steps.rb",
+     "features/support/env.rb",
+     "full-name-splitter.gemspec",
+     "lib/full-name-splitter.rb",
+     "spec/lib/full_name_splitter_spec.rb",
+     "spec/spec.opts",
+     "spec/spec_helper.rb"
+  ]
+  s.homepage = %q{http://github.com/zedlander/full-name-splitter}
+  s.rdoc_options = ["--charset=UTF-8"]
+  s.require_paths = ["lib"]
+  s.rubygems_version = %q{1.3.7}
+  s.summary = %q{*FullNameSplitter* splits full name into first and last name considering name prefixes and initials}
+  s.test_files = [
+    "spec/lib/full_name_splitter_spec.rb",
+     "spec/spec_helper.rb"
+  ]
+
+  if s.respond_to? :specification_version then
+    current_version = Gem::Specification::CURRENT_SPECIFICATION_VERSION
+    s.specification_version = 3
+
+    if Gem::Version.new(Gem::VERSION) >= Gem::Version.new('1.2.0') then
+    else
+    end
+  else
+  end
+end
+

data/lib/full-name-splitter.rb

@@ -0,0 +1,105 @@
+# -*- coding: utf-8 -*-
+# requires full accessable first_name and last_name attributes
+module FullNameSplitter
+
+  PREFIXES = %w(de da la du del dei vda. dello della degli delle van von der den heer ten ter vande vanden vander voor ver aan mc ben).freeze
+
+  class Splitter
+    
+    def initialize(full_name)
+      @full_name  = full_name
+      @first_name = []
+      @last_name  = []
+      split!
+    end
+
+    def split!
+      @units = @full_name.split(/\s+/)
+      while @unit = @units.shift do
+        if prefix? or with_apostrophe? or (first_name? and last_unit? and not initial?)
+          @last_name << @unit and break
+        else
+          @first_name << @unit
+        end
+      end
+      @last_name += @units
+
+      adjust_exceptions!
+    end
+
+    def first_name
+      @first_name.empty? ? nil : @first_name.join(' ')
+    end
+
+    def last_name
+      @last_name.empty? ? nil : @last_name.join(' ')
+    end
+
+    private
+
+    def prefix?
+      PREFIXES.include?(@unit.downcase)
+    end
+
+    # M or W.
+    def initial?
+      @unit =~ /^\w\.?$/
+    end
+
+    # O'Connor, d'Artagnan match
+    # Noda' doesn't match
+    def with_apostrophe?
+      @unit =~ /\w{1}'\w+/
+    end
+    
+    def last_unit?
+      @units.empty?
+    end
+    
+    def first_name?
+      not @first_name.empty?
+    end
+    
+    def adjust_exceptions!
+      return if @first_name.size <= 1
+      
+      # Adjusting exceptions like 
+      # "Ludwig Mies van der Rohe"      => ["Ludwig",         "Mies van der Rohe"   ]
+      # "Juan Martín de la Cruz Gómez"  => ["Juan Martín",    "de la Cruz Gómez"    ]
+      # "Javier Reyes de la Barrera"    => ["Javier",         "Reyes de la Barrera" ]
+      # Rosa María Pérez Martínez Vda. de la Cruz 
+      #                                 => ["Rosa María",     "Pérez Martínez Vda. de la Cruz"]
+      if last_name =~ /^(van der|(vda\. )?de la \w+$)/i
+        loop do
+          @last_name.unshift @first_name.pop
+          break if @first_name.size <= 2
+        end
+      end
+    end
+  end
+  
+  def full_name
+    [first_name, last_name].compact.join(' ')
+  end
+  
+  def full_name=(name)
+    self.first_name, self.last_name = split(name)
+  end
+  
+  private 
+  
+  def split(name)
+    name = name.to_s.strip.gsub(/\s+/, ' ')
+    
+    if name.include?(',')
+      name.
+        split(/\s*,\s*/, 2).            # ",van  helsing" produces  ["", "van helsing"]
+        map{ |u| u.empty? ? nil : u }   # but it should be [nil, "van helsing"] by lib convection
+    else
+      splitter = Splitter.new(name)
+      [splitter.first_name, splitter.last_name]
+    end
+  end
+  
+  module_function :split
+end

data/spec/lib/full_name_splitter_spec.rb

@@ -0,0 +1,114 @@
+# -*- coding: utf-8 -*-
+require File.expand_path(File.dirname(__FILE__) + '/../spec_helper')
+
+class Incognito
+  include FullNameSplitter
+  attr_accessor :first_name, :last_name
+end
+
+describe Incognito do
+  describe "#full_name=" do
+
+    #
+    # Environment
+    #
+
+    subject { Incognito.new }
+
+    def gum(first, last)
+      "[#{first}] + [#{last}]"
+    end
+
+
+    #
+    # Examples
+    #
+
+    {
+      "John Smith"                    => ["John",           "Smith"               ],
+
+      "Kevin J. O'Connor"             => ["Kevin J.",       "O'Connor"            ],
+      "Gabriel Van Helsing"           => ["Gabriel",        "Van Helsing"         ],
+      "Pierre de Montesquiou"         => ["Pierre",         "de Montesquiou"      ],
+      "Charles d'Artagnan"            => ["Charles",        "d'Artagnan"          ],
+      "Jaazaniah ben Shaphan"         => ["Jaazaniah",      "ben Shaphan"         ],
+      "Noda' bi-Yehudah"              => ["Noda'",          "bi-Yehudah"          ],
+      "Maria del Carmen Menendez"     => ["Maria",          "del Carmen Menendez" ],
+      "Alessandro Del Piero"          => ["Alessandro",     "Del Piero"           ],
+
+      "George W Bush"                 => ["George W",       "Bush"                ],
+      "George H. W. Bush"             => ["George H. W.",   "Bush"                ],
+      "James K. Polk"                 => ["James K.",       "Polk"                ],
+      "William Henry Harrison"        => ["William Henry",  "Harrison"            ],
+      "John Quincy Adams"             => ["John Quincy",    "Adams"               ],
+
+      "John Quincy"                   => ["John",           "Quincy"              ],
+      "George H. W."                  => ["George H. W.",   nil                   ],
+      "Van Helsing"                   => [nil,              "Van Helsing"         ],
+      "d'Artagnan"                    => [nil,              "d'Artagnan"          ],
+      "O'Connor"                      => [nil,              "O'Connor"            ],
+
+      "George"                        => ["George",         nil                   ],
+      "Kevin J. "                     => ["Kevin J.",       nil                   ],
+
+      "Thomas G. Della Fave"          => ["Thomas G.",      "Della Fave"          ],
+      "Anne du Bourg"                 => ["Anne",           "du Bourg"            ],
+
+      # German
+      "Johann Wolfgang von Goethe"    => ["Johann Wolfgang", "von Goethe"         ],
+
+      # Spanish-speaking countries
+      "Juan Martín de la Cruz Gómez"  => ["Juan Martín",    "de la Cruz Gómez"    ],
+      "Javier Reyes de la Barrera"    => ["Javier",         "Reyes de la Barrera" ],
+      "Rosa María Pérez Martínez Vda. de la Cruz" =>
+                                         ["Rosa María",    "Pérez Martínez Vda. de la Cruz"],
+
+      # Italian
+      "Federica Pellegrini"           => ["Federica",       "Pellegrini"          ],
+      "Leonardo da Vinci"             => ["Leonardo",       "da Vinci"            ],
+      # sounds like a fancy medival action movie star pseudonim
+      "Alberto Del Sole"              => ["Alberto",        "Del Sole"            ],
+      # horror movie star pseudonim?
+      "Adriano Dello Spavento"        => ["Adriano",        "Dello Spavento"      ],
+      "Luca Delle Fave"               => ["Luca",           "Delle Fave"          ],
+      "Francesca Della Valle"         => ["Francesca",      "Della Valle"         ],
+      "Guido Delle Colonne"           => ["Guido",          "Delle Colonne"       ],
+      "Tomasso D'Arco"                => ["Tomasso",        "D'Arco"              ],
+
+      # Dutch
+      "Johan de heer Van Kampen"      => ["Johan",          "de heer Van Kampen"  ],
+      "Han Van De Casteele"           => ["Han",            "Van De Casteele"     ],
+      "Han Vande Casteele"            => ["Han",            "Vande Casteele"      ],
+
+      # Exceptions?
+      # the architect Ludwig Mies van der Rohe, from the West German city of Aachen, was originally Ludwig Mies;
+      "Ludwig Mies van der Rohe"      => ["Ludwig",         "Mies van der Rohe"   ],
+
+      # If comma is provided then split by comma
+
+      "John, Quincy Adams"             => ["John",    "Quincy Adams"              ],
+      "Ludwig Mies, van der Rohe"      => ["Ludwig Mies", "van der Rohe"          ],
+
+      # Test ignoring unnecessary whitespaces
+      "\t Ludwig  Mies\t van der Rohe "   => ["Ludwig", "Mies van der Rohe"       ],
+      "\t Ludwig  Mies,\t van  der Rohe " => ["Ludwig Mies", "van der Rohe"       ],
+      "\t Ludwig      "                   => ["Ludwig", nil                       ],
+      "  van  helsing "                   => [nil, "van helsing"                  ],
+      " , van  helsing "                  => [nil, "van helsing"                  ],
+      "\t Ludwig  Mies,\t van  der Rohe " => ["Ludwig Mies", "van der Rohe"       ],
+
+    }.
+
+    each do |full_name, split_name|
+      it "should split #{full_name} to '#{split_name.first}' and '#{split_name.last}'" do
+        subject.full_name = full_name
+        gum(subject.first_name, subject.last_name).should == gum(*split_name)
+      end
+
+      it "should split #{full_name} to '#{split_name.first}' and '#{split_name.last}' when called as module function" do
+        FullNameSplitter.split(full_name).should == split_name
+      end
+
+    end
+  end
+end

data/spec/spec.opts

@@ -0,0 +1,2 @@
+--colour
+--format specdoc

data/spec/spec_helper.rb

@@ -0,0 +1 @@
+require File.expand_path(File.dirname(__FILE__) + '/../lib/full_name_splitter.rb')

metadata

@@ -0,0 +1,80 @@
+--- !ruby/object:Gem::Specification 
+name: full-name-splitter
+version: !ruby/object:Gem::Version 
+  hash: 27
+  prerelease: false
+  segments: 
+  - 0
+  - 1
+  - 0
+  version: 0.1.0
+platform: ruby
+authors: 
+- Pavel Gorbokon
+- Trevor Creech
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2010-09-10 00:00:00 -07:00
+default_executable: 
+dependencies: []
+
+description: ""
+email: trevor@trevorcreech.com
+executables: []
+
+extensions: []
+
+extra_rdoc_files: 
+- README.mdown
+files: 
+- README.mdown
+- Rakefile
+- VERSION
+- features/partial_split.feature
+- features/split.feature
+- features/step_definitions/split_steps.rb
+- features/support/env.rb
+- full-name-splitter.gemspec
+- lib/full-name-splitter.rb
+- spec/lib/full_name_splitter_spec.rb
+- spec/spec.opts
+- spec/spec_helper.rb
+has_rdoc: true
+homepage: http://github.com/zedlander/full-name-splitter
+licenses: []
+
+post_install_message: 
+rdoc_options: 
+- --charset=UTF-8
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
+      version: "0"
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
+      version: "0"
+requirements: []
+
+rubyforge_project: 
+rubygems_version: 1.3.7
+signing_key: 
+specification_version: 3
+summary: "*FullNameSplitter* splits full name into first and last name considering name prefixes and initials"
+test_files: 
+- spec/lib/full_name_splitter_spec.rb
+- spec/spec_helper.rb