human_name_parser 0.0.1

data/.gitignore

@@ -0,0 +1,4 @@
+*.gem
+.bundle
+Gemfile.lock
+pkg/*

data/Gemfile

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

data/LICENSE

@@ -0,0 +1,22 @@
+(The MIT License)
+
+Copyright (c) 2011 Adam Bachman
+
+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 +1,39 @@
+Attempt to parse and categorize the parts of names.
+
+With code borrowed from:
+
+* https://github.com/bricooke/name_parser
+* https://github.com/jasonpriem/HumanNameParser.php
+* https://github.com/jconley88/NameParser
+
+## Install
+
+`gem install human_name_parser`
+
+## Usage
+
+    require 'rubygems'
+    require 'human_name_parser'
+
+    name = HumanNameParser.parse 'George W. Bush Jr.'
+    name.first    # => 'George'
+    name.last     # => 'Bush'
+    name.initials # => 'GWB'
+    name.suffix   # => 'Jr.'
+    name.to_s     # => 'George W. Bush Jr.'
+
+## Development
+
+    ~/ $ git clone ... && cd human_name_parser
+    ~/ $ bundle install
+    ~/ $ rake
+
+## TODO
+
+Handle nicknames
+
+Handle strangely placed commas
+
+Handle multiple last names. e.g., "Björn Charles O'Malley y Muñoz"
+
+Handle multiple first names. e.g., "Mary Joe Francis Smith"

data/Rakefile

@@ -0,0 +1,10 @@
+require "bundler/gem_tasks"
+require 'rspec/core/rake_task'
+
+task :default => [:spec]
+
+desc "Run all specs"
+RSpec::Core::RakeTask.new do |t|
+  t.rspec_opts = %w(-fs --color)
+  t.ruby_opts = %w(-w)
+end

data/fixtures/test_names.txt

@@ -0,0 +1,31 @@
+Björn O'Malley||Björn|||O'Malley|
+Bin Lin||Bin|||Lin|
+Linda Jones||Linda|||Jones|
+Jason H. Priem||Jason||H.|Priem|
+Björn O'Malley-Muñoz||Björn|||O'Malley-Muñoz|
+Björn C. O'Malley||Björn||C.|O'Malley|
+Björn "Bill" O'Malley||Björn|Bill||O'Malley|
+Björn ("Bill") O'Malley||Björn|Bill||O'Malley|
+Björn ("Wild Bill") O'Malley||Björn|Wild Bill||O'Malley|
+Björn (Bill) O'Malley||Björn|Bill||O'Malley|
+Björn 'Bill' O'Malley||Björn|Bill||O'Malley|
+Björn C O'Malley||Björn||C|O'Malley|
+Björn C. R. O'Malley||Björn||C. R.|O'Malley|
+Björn Charles O'Malley||Björn||Charles|O'Malley|
+Björn Charles R. O'Malley||Björn||Charles R.|O'Malley|
+Björn van O'Malley||Björn|||van O'Malley|
+Björn Charles van der O'Malley||Björn||Charles|van der O'Malley|
+Björn Charles O'Malley y Muñoz||Björn||Charles|O'Malley y Muñoz|
+Björn O'Malley, Jr.||Björn|||O'Malley|Jr.
+Björn O'Malley Jr||Björn|||O'Malley|Jr
+B O'Malley||B|||O'Malley|
+William Carlos Williams||William||Carlos|Williams|
+C. Björn Roger O'Malley|C.|Björn||Roger|O'Malley|
+B. C. O'Malley||B.||C.|O'Malley|
+B C O'Malley||B||C|O'Malley|
+B.J. Thomas||B.J.|||Thomas|
+O'Malley, Björn||Björn|||O'Malley|
+O'Malley, Björn Jr||Björn|||O'Malley|Jr
+O'Malley, C. Björn|C.|Björn|||O'Malley|
+O'Malley, C. Björn III|C.|Björn|||O'Malley|III
+O'Malley y Muñoz, C. Björn Roger III|C.|Björn||Roger|O'Malley y Muñoz|III

data/human_name_parser.gemspec

@@ -0,0 +1,20 @@
+# -*- encoding: utf-8 -*-
+$:.push File.expand_path("../lib", __FILE__)
+require "human_name_parser/version"
+
+Gem::Specification.new do |s|
+  s.name        = "human_name_parser"
+  s.version     = HumanNameParser::VERSION
+  s.authors     = ["Adam Bachman"]
+  s.email       = ["adam.bachman@gmail.com"]
+  s.homepage    = "https://github.com/abachman/human_name_parser"
+  s.summary     = %q{Split most American names into their component parts.}
+  s.description = %q{human_name_parser is intended to split names into their component parts.}
+
+  s.files         = `git ls-files`.split("\n")
+  s.test_files    = `git ls-files -- {test,spec,features}/*`.split("\n")
+  s.executables   = `git ls-files -- bin/*`.split("\n").map{ |f| File.basename(f) }
+  s.require_paths = ["lib"]
+
+  s.add_development_dependency "rspec"
+end

data/lib/human_name_parser/name.rb

@@ -0,0 +1,149 @@
+module HumanNameParser
+  class Name
+    PREFIXES = ['mr', 'ms', 'miss', 'mrs', 'sir', 'prof', 'professor', 'md', 'dr']
+    SUFFIXES = ['esq','esquire','jr','sr','2','ii','iii','iv']
+    LAST_PREFIXES = ['al', 'bar','ben','bin','da','dal','de la', 'de', 'del', 'der', 'di', 'el', 'ibn', 'la', 'le', 'mc', 'san', 'st', 'ste', 'van', 'van der', 'van den', 'vel','von']
+
+    attr_accessor :first, :middle, :last, :prefix, :suffix
+
+    def initialize name
+      self.first  = ''
+      self.middle = ''
+      self.last   = ''
+      self.prefix = ''
+      self.suffix = ''
+
+      @input_string = name
+
+      parse
+    end
+
+    def parse
+      normalize_and_split
+
+      if @split_name.length == 1
+        _first, _ = @split_name
+        self.first = _first
+        self.last  = ''
+      elsif @split_name.length == 2
+        _first, _last = @split_name
+        self.first = _first
+        self.last  = _last
+      else
+        parse_prefix.
+          parse_suffix.
+          parse_last_name.
+          parse_first_name.
+          parse_middle_name
+      end
+    end
+
+    def parse_prefix
+      if is_prefix? @split_name.first
+        self.prefix = @split_name.shift
+      end
+
+      return self
+    end
+
+    def parse_suffix
+      self.suffix = []
+      while is_suffix? @split_name.last
+        self.suffix.unshift @split_name.pop
+      end
+      self.suffix = self.suffix.join(' ')
+
+      return self
+    end
+
+    def parse_last_name
+      self.last = []
+      self.last.unshift @split_name.pop
+
+      while is_last_name_prefix?(@split_name.last)
+        self.last.unshift @split_name.pop
+      end
+
+      self.last = self.last.join(' ')
+
+      return self
+    end
+
+    def parse_first_name
+      self.first = @split_name.shift || ''
+
+      return self
+    end
+
+    def parse_middle_name
+      # whatever's left
+      self.middle = @split_name.join ' '
+
+      return self
+    end
+
+    def initials
+      _i = ''
+      _i += self.first.slice(0,1)  if self.first && self.first.length > 0
+      _i += self.middle.slice(0,1) if self.middle && self.middle.length > 0
+      _i += self.last.slice(0,1)   if self.last && self.last.length > 0
+      _i.upcase
+    end
+
+    def to_s
+      [
+        self.prefix,
+        self.first,
+        self.middle,
+        self.last,
+        self.suffix
+      ].reject {|n| n.length == 0}.join(' ')
+    end
+
+  private
+    def normalize_and_split
+      if @input_string.count(",") > 1
+        # this is a thing that I cannot recognize
+        @split_name = []
+      elsif @input_string.count(",") == 1
+        @split_name = split_last_comma_first_middle
+      else
+        @split_name = split_first_middle_last
+      end
+
+      return self
+    end
+
+    def split_last_comma_first_middle
+      match = @input_string.match(",")
+      normalized = ""
+      if match
+        normalized = [match.post_match.strip, match.pre_match.strip].join(" ")
+      end
+      normalized.split(" ")
+    end
+
+    def split_first_middle_last
+      @input_string.split(" ")
+    end
+
+    def is_prefix?(string)
+      is_ix?(PREFIXES, string)
+    end
+
+    def is_suffix?(string)
+      is_ix?(SUFFIXES, string)
+    end
+
+    def is_last_name_prefix?(string)
+      return false if string.nil? || string == ""
+      LAST_PREFIXES.any? { |p| string.downcase.match(/^#{p}$/) }
+    end
+
+    def is_ix?(kind, string)
+      return false if string.nil? || string == ""
+      kind.any? {|k| string.downcase.match(/^#{k}\.?$/)}
+    end
+
+  end
+end

data/lib/human_name_parser/version.rb

@@ -0,0 +1,3 @@
+module HumanNameParser
+  VERSION = "0.0.1"
+end

data/lib/human_name_parser.rb

@@ -0,0 +1,9 @@
+require "human_name_parser/version"
+
+module HumanNameParser
+  autoload :Name, 'human_name_parser/name'
+
+  def self.parse input_string
+    return Name.new(input_string)
+  end
+end

data/spec/human_name_parser_spec.rb

@@ -0,0 +1,15 @@
+require 'human_name_parser'
+
+describe HumanNameParser do
+  it "returns a Name object" do
+    name = HumanNameParser.parse ''
+    name.class.should == HumanNameParser::Name
+  end
+
+  it "parses names" do
+    name = HumanNameParser.parse "John H. Smith"
+    name.first.should == 'John'
+    name.last.should == 'Smith'
+    name.initials.should == 'JHS'
+  end
+end

data/spec/name_spec.rb

@@ -0,0 +1,154 @@
+require 'human_name_parser/name'
+
+describe HumanNameParser::Name do
+  # any unicode issues?
+  context "when full name is Björn Charles van der O'Malley" do
+    let(:full_name) { "Björn Charles van der O'Malley" }
+    it "should parse the name" do
+      @name = HumanNameParser::Name.new full_name
+      @name.first.should == 'Björn'
+      @name.last.should == "van der O'Malley"
+      @name.middle.should == 'Charles'
+    end
+  end
+
+  context 'when full name is Mary Lou Smith' do
+    let(:full_name) { "Mary Lou Smith" }
+    before do
+      @name = HumanNameParser::Name.new full_name
+    end
+
+    it "gets first name" do
+      @name.first.should == 'Mary'
+    end
+
+    it "gets last name" do
+      @name.last.should == 'Smith'
+    end
+
+    it "gets prefix" do
+      @name.prefix.should == ''
+    end
+
+    it "gets suffix" do
+      @name.suffix.should == ''
+    end
+
+    it "gets initials" do
+      @name.initials.should == 'MLS'
+    end
+  end
+
+  context 'when full name is Mr. Alphonse di Morel Jr. Esq.' do
+    let(:full_name) { "Mr. Alphonse di Morel Jr. Esq." }
+    before { @name = HumanNameParser::Name.new full_name }
+
+    it "gets first" do
+      @name.first.should == 'Alphonse'
+    end
+
+    it "gets last" do
+      @name.last.should == 'di Morel'
+    end
+
+    it "gets prefix" do
+      @name.prefix.should == 'Mr.'
+    end
+
+    it "gets suffix" do
+      @name.suffix.should == 'Jr. Esq.'
+    end
+
+    it "gets initials" do
+      @name.initials.should == 'AD'
+    end
+  end
+
+  context 'when full name is ROBOTO' do
+    let(:full_name) { "ROBOTO" }
+    before { @name = HumanNameParser::Name.new full_name }
+
+    it "gets first" do
+      @name.first.should == 'ROBOTO'
+    end
+
+    it 'gets initials' do
+      @name.initials.should == 'R'
+    end
+
+    it "doesn't get last" do
+      @name.last.should == ''
+    end
+  end
+
+  context 'when full name is John Paul Ringo' do
+    let(:full_name) { "John Paul Ringo" }
+    before { @name = HumanNameParser::Name.new full_name }
+
+    it "gets first" do
+      @name.first.should == 'John'
+    end
+
+    it 'gets initials' do
+      @name.initials.should == 'JPR'
+    end
+
+    it "gets last" do
+      @name.last.should == 'Ringo'
+    end
+
+    it "gets middle" do
+      @name.middle.should == 'Paul'
+    end
+  end
+
+  context 'when full name is Downey Jr., Robert' do
+    let(:full_name) { 'Downey Jr., Robert' }
+    before { @name = HumanNameParser::Name.new full_name }
+
+    it "gets first" do
+      @name.first.should == 'Robert'
+    end
+
+    it 'gets initials' do
+      @name.initials.should == 'RD'
+    end
+
+    it "gets last" do
+      @name.last.should == 'Downey'
+    end
+
+    it "gets middle" do
+      @name.middle.should == ''
+    end
+
+    it "gets suffix" do
+      @name.suffix.should == 'Jr.'
+    end
+  end
+
+  context 'when full name is garbage' do
+    let(:full_name) { '1234 Anywhere St., North Pole, SD 22323' }
+    before { @name = HumanNameParser::Name.new full_name }
+
+    it "gets first" do
+      @name.first.should == ''
+    end
+
+    it 'gets initials' do
+      @name.initials.should == ''
+    end
+
+    it "gets last" do
+      @name.last.should == ''
+    end
+
+    it "gets middle" do
+      @name.middle.should == ''
+    end
+
+    it "gets suffix" do
+      @name.suffix.should == ''
+    end
+  end
+end

data/spec/spec_helper.rb

@@ -0,0 +1,8 @@
+$:.unshift File.expand_path('..', __FILE__)
+$:.unshift File.expand_path('../../lib', __FILE__)
+require 'human_name_parser'
+require 'rspec'
+
+RSpec.configure do |c|
+  c.mock_with :rspec
+end

metadata

@@ -0,0 +1,95 @@
+--- !ruby/object:Gem::Specification 
+name: human_name_parser
+version: !ruby/object:Gem::Version 
+  hash: 29
+  prerelease: 
+  segments: 
+  - 0
+  - 0
+  - 1
+  version: 0.0.1
+platform: ruby
+authors: 
+- Adam Bachman
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2011-11-10 00:00:00 -05:00
+default_executable: 
+dependencies: 
+- !ruby/object:Gem::Dependency 
+  name: rspec
+  prerelease: false
+  requirement: &id001 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        hash: 3
+        segments: 
+        - 0
+        version: "0"
+  type: :development
+  version_requirements: *id001
+description: human_name_parser is intended to split names into their component parts.
+email: 
+- adam.bachman@gmail.com
+executables: []
+
+extensions: []
+
+extra_rdoc_files: []
+
+files: 
+- .gitignore
+- Gemfile
+- LICENSE
+- README.md
+- Rakefile
+- fixtures/test_names.txt
+- human_name_parser.gemspec
+- lib/human_name_parser.rb
+- lib/human_name_parser/name.rb
+- lib/human_name_parser/version.rb
+- spec/human_name_parser_spec.rb
+- spec/name_spec.rb
+- spec/spec_helper.rb
+has_rdoc: true
+homepage: https://github.com/abachman/human_name_parser
+licenses: []
+
+post_install_message: 
+rdoc_options: []
+
+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: 1.6.2
+signing_key: 
+specification_version: 3
+summary: Split most American names into their component parts.
+test_files: 
+- spec/human_name_parser_spec.rb
+- spec/name_spec.rb
+- spec/spec_helper.rb