namesplit 0.0.6

data/lib/namesplit/simple_split.rb

@@ -0,0 +1,50 @@
+# Pour les cas de Split les plus simples.
+#
+module Namesplit
+  private
+
+  # Private : Dans le cas où seuls deux éléments composent le string et qu'aucun
+  # nom ou prénom n'est détecté parmi l'un ou l'autre.
+  #
+  def self.with_space
+    words = @full_name.split(" ")
+    @result.first_names = words[0]
+    words.delete(words[0])
+
+    @result.last_name = words.join(" ")
+    @result.quality = 0.3
+  end
+
+  # Private : En fonction des majuscules ou non, on détecte le nom de la
+  # personne. Afin d'éviter les problèmes avec les "-" ou les accents majuscules
+  # "À" on effectue quelques pourcentage.
+  #
+  def self.with_uppercasing
+    words = @full_name.split(" ")
+    return if uppercase_percentage > 0.95
+
+    last_name = ""
+    last_index = 0
+    words.each.with_index do |word, index|
+      result = word.gsub(/[^A-Z]/, "").size / word.size.to_f
+
+      next if result < 0.7
+      next if last_name != "" && last_index != index - 1
+      last_name << " " + word
+      last_index = index
+    end
+
+    return if last_name == ""
+    last_name.strip! && last_name.split(" ").each { |w| words.delete(w) }
+    @result.last_name = last_name
+    @result.first_names = words.join(" ")
+    @result.quality = 0.8
+  end
+
+  # Private : Renvoie le pourcentage de lettre dans la phrase en majuscules.
+  #
+  def self.uppercase_percentage
+    name = @full_name.gsub(/[^A-Za-z]/, "")
+    name.gsub(/[^A-Z]/, "").size / name.size.to_f
+  end
+end

data/lib/namesplit/titleize.rb

@@ -0,0 +1,49 @@
+# Ajoute la méthode titleize pour revoir certains formats de noms.
+#
+module Namesplit
+  # Public : Transforme en titre un string.
+  #
+  def self.titleize(target)
+    # Tous les mots sont traités un à un en découpant la phrase à partir des
+    # espaces.
+    words = target.to_s.split(" ").map do |word|
+      # Les apostrophes internes et les tirets sont gérés correctement
+      word.split("-").map! do |sub_word|
+        sub_word.split("'").map! do |subsub_word|
+          titleize_word(subsub_word)
+        end.join("'")
+      end.join("-")
+    end
+
+    words.join(" ")
+  end
+
+  private
+
+  # Private : Transforme un mot en minuscule et ajoute une majuscule à la
+  # première lettre.
+  #
+  # Exemple :
+  #   "BOÎTE".titleize => "Boîte"
+  #
+  def self.titleize_word(word)
+    accents = { "É" => "é", "È" => "è", "Ê" => "ê", "Ë" => "ë", "À" => "à", "Â" => "â", "Ï" => "ï", "Î" => "î", "Ô" => "ô", "Ù" => "ù", "Û" => "û", "Ü" => "ü", "Ç" => "ç", "Ö" => "ö", "Ÿ" => "ÿ" }
+
+    final = []
+    word.chars.each.with_index do |char, index|
+      if index == 0
+        final << char.upcase
+      else
+        new_char = accents.values_at(char).first
+
+        if new_char.nil?
+          final << char.downcase
+        else
+          final << new_char
+        end
+      end
+    end
+
+    final.join("")
+  end
+end

data/lib/namesplit/version.rb

@@ -0,0 +1,3 @@
+module Namesplit
+  VERSION = "0.0.6"
+end

data/lib/namesplit.rb

@@ -0,0 +1,26 @@
+require "ostruct"
+
+require "namesplit/version"
+require "namesplit/simple_split"
+require "namesplit/clean"
+require "namesplit/titleize"
+require "namesplit/first_names"
+require "namesplit/first_names_list"
+
+module Namesplit
+  # Public : Cette méthode organise progressivement le split du nom et du
+  # prénom. Les différentes solutions sont testées une à une jusqu'à ce que
+  # l'une d'entre elle fonctionne.
+  #
+  def self.split(full_name)
+    @result = OpenStruct.new(quality: 0)
+    return @result if full_name.nil?
+    clean(full_name)
+
+    with_first_names
+    with_uppercasing if @result.first_names.nil?
+    with_space if @result.first_names.nil?
+
+    clean_output
+  end
+end

data/namesplit.gemspec

@@ -0,0 +1,27 @@
+# coding: utf-8
+lib = File.expand_path("../lib", __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require "namesplit/version"
+
+Gem::Specification.new do |spec|
+  spec.name          = "namesplit"
+  spec.version       = Namesplit::VERSION
+  spec.authors       = ["Antoine Finkelstein"]
+  spec.email         = ["antoine.fink@gmail.com"]
+  spec.summary       = %q{Sépare nom et prénom}
+  spec.description   = %q{À partir d'un nom complet, Nameplit renvoie le nom et le prénom.}
+  spec.homepage      = "https://github.com/AntoineFinkelstein/Namesplit"
+  spec.license       = "MIT"
+
+  spec.files         = `git ls-files -z`.split("\x0")
+  spec.executables   = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
+  spec.test_files    = spec.files.grep(%r{^(test|spec|features)/})
+  spec.require_paths = ["lib"]
+
+  spec.add_development_dependency "bundler", "~> 1.6"
+  spec.add_development_dependency "rake", "~> 10.0"
+  spec.add_development_dependency "rspec", "~> 3"
+  spec.add_development_dependency "guard", "~> 2"
+  spec.add_development_dependency "guard-rspec", "~> 4"
+  spec.add_development_dependency "pry", "~> 0.1"
+end

data/spec/namesplit_spec.rb

@@ -0,0 +1,129 @@
+require "spec_helper"
+
+describe Namesplit do
+  it "returns an empty Hash if no string or empty string is given" do
+    expect(Namesplit.split(nil).first_names).to eq(nil)
+    expect(Namesplit.split(nil).first_name).to eq(nil)
+    expect(Namesplit.split(nil).last_name).to eq(nil)
+  end
+
+  it "detects uppercasing 1/3" do
+    input = "Jfbkzebfz OVUIFVEEI"
+    expect(Namesplit.split(input).first_names).to eq("Jfbkzebfz")
+    expect(Namesplit.split(input).first_name).to eq("Jfbkzebfz")
+    expect(Namesplit.split(input).last_name).to eq("Ovuifveei")
+  end
+
+  it "detects uppercasing 2/3" do
+    input = "OVUIFVEEI jfbkzebfz"
+    expect(Namesplit.split(input).first_names).to eq("Jfbkzebfz")
+    expect(Namesplit.split(input).first_name).to eq("Jfbkzebfz")
+    expect(Namesplit.split(input).last_name).to eq("Ovuifveei")
+  end
+
+  it "detects uppercasing 3/3" do
+    input = "DE OVUIFVEEI jfbkzebfz"
+    expect(Namesplit.split(input).first_names).to eq("Jfbkzebfz")
+    expect(Namesplit.split(input).first_name).to eq("Jfbkzebfz")
+    expect(Namesplit.split(input).last_name).to eq("De Ovuifveei")
+  end
+
+  it "works with the simplest of cases" do
+    input = "Albert Einstein"
+    expect(Namesplit.split(input).first_names).to eq("Albert")
+    expect(Namesplit.split(input).first_name).to eq("Albert")
+    expect(Namesplit.split(input).last_name).to eq("Einstein")
+  end
+
+  it "works with the simplest of cases" do
+    input = "Albert D'Einstein-Goon"
+    expect(Namesplit.split(input).first_names).to eq("Albert")
+    expect(Namesplit.split(input).first_name).to eq("Albert")
+    expect(Namesplit.split(input).last_name).to eq("D'Einstein-Goon")
+  end
+
+  it "works with the simple case with two words last name" do
+    input = "Albert De Einstein"
+    expect(Namesplit.split(input).first_names).to eq("Albert")
+    expect(Namesplit.split(input).first_name).to eq("Albert")
+    expect(Namesplit.split(input).last_name).to eq("De Einstein")
+  end
+
+  it "with mutliple first names 1/2" do
+    input = "Albert Thomas Jacques Einstein"
+    expect(Namesplit.split(input).first_names).to eq("Albert Thomas Jacques")
+    expect(Namesplit.split(input).first_name).to eq("Albert")
+    expect(Namesplit.split(input).last_name).to eq("Einstein")
+  end
+
+  it "with mutliple first names 2/2" do
+    input = "Einstein Albert Thomas Jacques"
+    expect(Namesplit.split(input).first_names).to eq("Albert Thomas Jacques")
+    expect(Namesplit.split(input).first_name).to eq("Albert")
+    expect(Namesplit.split(input).last_name).to eq("Einstein")
+  end
+
+  it "cleans the punctuation" do
+    input = "Albert, Einstein!"
+    expect(Namesplit.split(input).first_names).to eq("Albert")
+    expect(Namesplit.split(input).first_name).to eq("Albert")
+    expect(Namesplit.split(input).last_name).to eq("Einstein")
+  end
+
+  it "cleans the spaces" do
+    input = "Albert   Einstein  "
+    expect(Namesplit.split(input).first_names).to eq("Albert")
+    expect(Namesplit.split(input).first_name).to eq("Albert")
+    expect(Namesplit.split(input).last_name).to eq("Einstein")
+  end
+
+  it "works with real data" do
+    input = "BEAUMANOIRE (Pierre-Yves)"
+    expect(Namesplit.split(input).first_names).to eq("Pierre-Yves")
+    expect(Namesplit.split(input).first_name).to eq("Pierre-Yves")
+    expect(Namesplit.split(input).last_name).to eq("Beaumanoire")
+  end
+
+  it "works with real data" do
+    input = "Delorme - Thomas, Cécile Jeanne Marie"
+    expect(Namesplit.split(input).first_names).to eq("Thomas Cécile Jeanne Marie")
+    expect(Namesplit.split(input).first_name).to eq("Thomas")
+    expect(Namesplit.split(input).last_name).to eq("Delorme")
+  end
+
+  it "works with real data" do
+    input = "BERGES MANON, ANASTASIA, ANTOINETTE"
+    expect(Namesplit.split(input).last_name).to eq("Berges")
+    expect(Namesplit.split(input).first_names).to eq("Manon Anastasia Antoinette")
+    expect(Namesplit.split(input).first_name).to eq("Manon")
+  end
+
+  it "works with real data" do
+    input = "LE ROUX Sylvain, Marc, Denis"
+    expect(Namesplit.split(input).first_names).to eq("Sylvain Marc Denis")
+    expect(Namesplit.split(input).first_name).to eq("Sylvain")
+    expect(Namesplit.split(input).last_name).to eq("Le Roux")
+  end
+
+  it "works with real data" do
+    input = "FINCK Jean-Eric"
+    expect(Namesplit.split(input).first_names).to eq("Jean-Eric")
+    expect(Namesplit.split(input).first_name).to eq("Jean-Eric")
+    expect(Namesplit.split(input).last_name).to eq("Finck")
+  end
+
+  it "works with real data" do
+    input = "DUARTE PEREIRA DA COSTA Nelson Edgar"
+    expect(Namesplit.split(input).first_names).to eq("Nelson Edgar")
+    expect(Namesplit.split(input).first_name).to eq("Nelson")
+    expect(Namesplit.split(input).last_name).to eq("Duarte Pereira Da Costa")
+  end
+
+  it "works with real data" do
+    input = "ORTIZ-GOBO Didier Florent"
+    expect(Namesplit.split(input).first_names).to eq("Didier Florent")
+    expect(Namesplit.split(input).first_name).to eq("Didier")
+    expect(Namesplit.split(input).last_name).to eq("Ortiz-Gobo")
+    expect(Namesplit.split(input).full_name).to eq("Ortiz-Gobo Didier Florent")
+  end
+end

data/spec/spec_helper.rb

@@ -0,0 +1,2 @@
+require "pry"
+require "Namesplit"

metadata

@@ -0,0 +1,147 @@
+--- !ruby/object:Gem::Specification
+name: namesplit
+version: !ruby/object:Gem::Version
+  version: 0.0.6
+platform: ruby
+authors:
+- Antoine Finkelstein
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2014-09-18 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.6'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.6'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3'
+- !ruby/object:Gem::Dependency
+  name: guard
+  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: guard-rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '4'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '4'
+- !ruby/object:Gem::Dependency
+  name: pry
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.1'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.1'
+description: "À partir d'un nom complet, Nameplit renvoie le nom et le prénom."
+email:
+- antoine.fink@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- Gemfile
+- Guardfile
+- LICENSE.txt
+- README.md
+- Rakefile
+- lib/namesplit.rb
+- lib/namesplit/clean.rb
+- lib/namesplit/first_names.rb
+- lib/namesplit/first_names_list.rb
+- lib/namesplit/simple_split.rb
+- lib/namesplit/titleize.rb
+- lib/namesplit/version.rb
+- namesplit.gemspec
+- spec/namesplit_spec.rb
+- spec/spec_helper.rb
+homepage: https://github.com/AntoineFinkelstein/Namesplit
+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: 2.4.1
+signing_key: 
+specification_version: 4
+summary: Sépare nom et prénom
+test_files:
+- spec/namesplit_spec.rb
+- spec/spec_helper.rb
+has_rdoc: